Commit 74872263cc83bb7cbd8d548e83b441f4bf2f2249 | zig

author	Andrew Kelley <andrew@ziglang.org> 2020-01-22 17:42:02-05:00
committer	Andrew Kelley <andrew@ziglang.org> 2020-01-22 17:42:44-05:00
log	74872263cc83bb7cbd8d548e83b441f4bf2f2249
tree	6c4e7bb2cbcb97d3b16259ecebcb05915921ecfe
parent	97b2ac598b91194c09a96c9ed86e4f9b266d019c
signature	Commit is signed but in an unrecognized format.

lib/headers: update to clang 10.x C headers

upstream revision: 3cce3790072249cbe51b96cea26bc78019c11fd0

29 files changed, 17040 insertions(+), 14853 deletions(-)

lib/include/__clang_cuda_intrinsics.h+9-1

...	@@ -211,7 +211,15 @@ inline __device__ unsigned int __ballot_sync(unsigned int mask, int pred) {	...	@@ -211,7 +211,15 @@ inline __device__ unsigned int __ballot_sync(unsigned int mask, int pred) {
211	return __nvvm_vote_ballot_sync(mask, pred);	211	return __nvvm_vote_ballot_sync(mask, pred);
212	}	212	}
213		213
214	inline __device__ unsigned int __activemask() { return __nvvm_vote_ballot(1); }	214	inline __device__ unsigned int __activemask() {
		215	#if CUDA_VERSION < 9020
		216	return __nvvm_vote_ballot(1);
		217	#else
		218	unsigned int mask;
		219	asm volatile("activemask.b32 %0;" : "=r"(mask));
		220	return mask;
		221	#endif
		222	}
215		223
216	inline __device__ unsigned int __fns(unsigned mask, unsigned base, int offset) {	224	inline __device__ unsigned int __fns(unsigned mask, unsigned base, int offset) {
217	return __nvvm_fns(mask, base, offset);	225	return __nvvm_fns(mask, base, offset);

lib/include/altivec.h+86-59

 @@ -2761,8 +2761,8 @@ static __inline__ vector double __ATTRS_o_ai vec_xl_len(double *__a,
   return (vector double)__builtin_vsx_lxvl(__a, (__b << 56));
 }
-static __inline__ vector double __ATTRS_o_ai vec_xl_len_r(unsigned char *__a,
+static __inline__ vector unsigned char __ATTRS_o_ai
-                                                          size_t __b) {
+vec_xl_len_r(unsigned char *__a, size_t __b) {
   vector unsigned char __res =
       (vector unsigned char)__builtin_vsx_lxvll(__a, (__b << 56));
 #ifdef __LITTLE_ENDIAN__
 @@ -2876,9 +2876,10 @@ static __inline__ vector double __ATTRS_o_ai vec_cpsgn(vector double __a,
 #ifdef __VSX__
 #define vec_ctf(__a, __b)                                                      \
   _Generic((__a), vector int                                                   \
-           : (vector float)__builtin_altivec_vcfsx((__a), (__b)),              \
+           : (vector float)__builtin_altivec_vcfsx((vector int)(__a), (__b)),  \
              vector unsigned int                                               \
-           : (vector float)__builtin_altivec_vcfux((vector int)(__a), (__b)),  \
+           : (vector float)__builtin_altivec_vcfux((vector unsigned int)(__a), \
+                                                   (__b)),                     \
              vector unsigned long long                                         \
            : (__builtin_convertvector((vector unsigned long long)(__a),        \
                                       vector double) *                         \
 @@ -2892,9 +2893,10 @@ static __inline__ vector double __ATTRS_o_ai vec_cpsgn(vector double __a,
 #else
 #define vec_ctf(__a, __b)                                                      \
   _Generic((__a), vector int                                                   \
-           : (vector float)__builtin_altivec_vcfsx((__a), (__b)),              \
+           : (vector float)__builtin_altivec_vcfsx((vector int)(__a), (__b)),  \
              vector unsigned int                                               \
-           : (vector float)__builtin_altivec_vcfux((vector int)(__a), (__b)))
+           : (vector float)__builtin_altivec_vcfux((vector unsigned int)(__a), \
+                                                   (__b)))
 #endif
 /* vec_vcfsx */
 @@ -2910,10 +2912,11 @@ static __inline__ vector double __ATTRS_o_ai vec_cpsgn(vector double __a,
 #ifdef __VSX__
 #define vec_cts(__a, __b)                                                      \
   _Generic((__a), vector float                                                 \
-           : __builtin_altivec_vctsxs((__a), (__b)), vector double             \
+           : __builtin_altivec_vctsxs((vector float)(__a), (__b)),             \
+             vector double                                                     \
            : __extension__({                                                   \
              vector double __ret =                                             \
-                 (__a) *                                                       \
+                 (vector double)(__a) *                                        \
                  (vector double)(vector unsigned long long)((0x3ffULL + (__b)) \
                                                             << 52);            \
              __builtin_convertvector(__ret, vector signed long long);          \
 @@ -2931,10 +2934,11 @@ static __inline__ vector double __ATTRS_o_ai vec_cpsgn(vector double __a,
 #ifdef __VSX__
 #define vec_ctu(__a, __b)                                                      \
   _Generic((__a), vector float                                                 \
-           : __builtin_altivec_vctuxs((__a), (__b)), vector double             \
+           : __builtin_altivec_vctuxs((vector float)(__a), (__b)),             \
+             vector double                                                     \
            : __extension__({                                                   \
              vector double __ret =                                             \
-                 (__a) *                                                       \
+                 (vector double)(__a) *                                        \
                  (vector double)(vector unsigned long long)((0x3ffULL + __b)   \
                                                             << 52);            \
              __builtin_convertvector(__ret, vector unsigned long long);        \
 @@ -3286,9 +3290,7 @@ static __inline__ vector double __ATTRS_o_ai vec_div(vector double __a,
 /* vec_dss */
-static __inline__ void __attribute__((__always_inline__)) vec_dss(int __a) {
+#define vec_dss __builtin_altivec_dss
-  __builtin_altivec_dss(__a);
-}
 /* vec_dssall */
 @@ -6301,19 +6303,20 @@ static __inline__ vector float __ATTRS_o_ai vec_or(vector float __a,
 #ifdef __VSX__
 static __inline__ vector double __ATTRS_o_ai vec_or(vector bool long long __a,
                                                     vector double __b) {
-  return (vector unsigned long long)__a | (vector unsigned long long)__b;
+  return (vector double)((vector unsigned long long)__a |
+                         (vector unsigned long long)__b);
 }
 static __inline__ vector double __ATTRS_o_ai vec_or(vector double __a,
                                                     vector bool long long __b) {
-  return (vector unsigned long long)__a | (vector unsigned long long)__b;
+  return (vector double)((vector unsigned long long)__a |
+                         (vector unsigned long long)__b);
 }
 static __inline__ vector double __ATTRS_o_ai vec_or(vector double __a,
                                                     vector double __b) {
-  vector unsigned long long __res =
+  return (vector double)((vector unsigned long long)__a |
-      (vector unsigned long long)__a | (vector unsigned long long)__b;
+                         (vector unsigned long long)__b);
-  return (vector double)__res;
 }
 static __inline__ vector signed long long __ATTRS_o_ai
 @@ -14781,7 +14784,7 @@ static __inline__ int __ATTRS_o_ai vec_all_ne(vector bool long long __a,
 static __inline__ int __ATTRS_o_ai vec_all_ne(vector float __a,
                                               vector float __b) {
 #ifdef __VSX__
-  return __builtin_vsx_xvcmpeqdp_p(__CR6_EQ, __a, __b);
+  return __builtin_vsx_xvcmpeqsp_p(__CR6_EQ, __a, __b);
 #else
   return __builtin_altivec_vcmpeqfp_p(__CR6_EQ, __a, __b);
 #endif
 @@ -16361,27 +16364,32 @@ vec_xl(signed long long __offset, unsigned char *__ptr) {
 static inline __ATTRS_o_ai vector signed short vec_xl(signed long long __offset,
                                                       signed short *__ptr) {
-  return *(unaligned_vec_sshort *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_sshort *)__addr;
 }
 static inline __ATTRS_o_ai vector unsigned short
 vec_xl(signed long long __offset, unsigned short *__ptr) {
-  return *(unaligned_vec_ushort *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_ushort *)__addr;
 }
 static inline __ATTRS_o_ai vector signed int vec_xl(signed long long __offset,
                                                     signed int *__ptr) {
-  return *(unaligned_vec_sint *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_sint *)__addr;
 }
 static inline __ATTRS_o_ai vector unsigned int vec_xl(signed long long __offset,
                                                       unsigned int *__ptr) {
-  return *(unaligned_vec_uint *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_uint *)__addr;
 }
 static inline __ATTRS_o_ai vector float vec_xl(signed long long __offset,
                                                float *__ptr) {
-  return *(unaligned_vec_float *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_float *)__addr;
 }
 #ifdef __VSX__
 @@ -16391,17 +16399,20 @@ typedef vector double unaligned_vec_double __attribute__((aligned(1)));
 static inline __ATTRS_o_ai vector signed long long
 vec_xl(signed long long __offset, signed long long *__ptr) {
-  return *(unaligned_vec_sll *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_sll *)__addr;
 }
 static inline __ATTRS_o_ai vector unsigned long long
 vec_xl(signed long long __offset, unsigned long long *__ptr) {
-  return *(unaligned_vec_ull *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_ull *)__addr;
 }
 static inline __ATTRS_o_ai vector double vec_xl(signed long long __offset,
                                                 double *__ptr) {
-  return *(unaligned_vec_double *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_double *)__addr;
 }
 #endif
 @@ -16411,12 +16422,14 @@ typedef vector unsigned __int128 unaligned_vec_ui128
     __attribute__((aligned(1)));
 static inline __ATTRS_o_ai vector signed __int128
 vec_xl(signed long long __offset, signed __int128 *__ptr) {
-  return *(unaligned_vec_si128 *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_si128 *)__addr;
 }
 static inline __ATTRS_o_ai vector unsigned __int128
 vec_xl(signed long long __offset, unsigned __int128 *__ptr) {
-  return *(unaligned_vec_ui128 *)(__ptr + __offset);
+  signed char *__addr = (signed char *)__ptr + __offset;
+  return *(unaligned_vec_ui128 *)__addr;
 }
 #endif
 @@ -16425,27 +16438,27 @@ vec_xl(signed long long __offset, unsigned __int128 *__ptr) {
 #ifdef __LITTLE_ENDIAN__
 static __inline__ vector signed char __ATTRS_o_ai
 vec_xl_be(signed long long __offset, signed char *__ptr) {
-  vector signed char __vec = __builtin_vsx_lxvd2x_be(__offset, __ptr);
+  vector signed char __vec = (vector signed char)__builtin_vsx_lxvd2x_be(__offset, __ptr);
   return __builtin_shufflevector(__vec, __vec, 7, 6, 5, 4, 3, 2, 1, 0, 15, 14,
                                  13, 12, 11, 10, 9, 8);
 }
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_xl_be(signed long long __offset, unsigned char *__ptr) {
-  vector unsigned char __vec = __builtin_vsx_lxvd2x_be(__offset, __ptr);
+  vector unsigned char __vec = (vector unsigned char)__builtin_vsx_lxvd2x_be(__offset, __ptr);
   return __builtin_shufflevector(__vec, __vec, 7, 6, 5, 4, 3, 2, 1, 0, 15, 14,
                                  13, 12, 11, 10, 9, 8);
 }
 static __inline__ vector signed short  __ATTRS_o_ai
 vec_xl_be(signed long long __offset, signed short *__ptr) {
-  vector signed short __vec = __builtin_vsx_lxvd2x_be(__offset, __ptr);
+  vector signed short __vec = (vector signed short)__builtin_vsx_lxvd2x_be(__offset, __ptr);
   return __builtin_shufflevector(__vec, __vec, 3, 2, 1, 0, 7, 6, 5, 4);
 }
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_xl_be(signed long long __offset, unsigned short *__ptr) {
-  vector unsigned short __vec = __builtin_vsx_lxvd2x_be(__offset, __ptr);
+  vector unsigned short __vec = (vector unsigned short)__builtin_vsx_lxvd2x_be(__offset, __ptr);
   return __builtin_shufflevector(__vec, __vec, 3, 2, 1, 0, 7, 6, 5, 4);
 }
 @@ -16513,50 +16526,58 @@ static inline __ATTRS_o_ai void vec_xst(vector unsigned char __vec,
 static inline __ATTRS_o_ai void vec_xst(vector signed short __vec,
                                         signed long long __offset,
                                         signed short *__ptr) {
-  *(unaligned_vec_sshort *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_sshort *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector unsigned short __vec,
                                         signed long long __offset,
                                         unsigned short *__ptr) {
-  *(unaligned_vec_ushort *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_ushort *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector signed int __vec,
                                         signed long long __offset,
                                         signed int *__ptr) {
-  *(unaligned_vec_sint *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_sint *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector unsigned int __vec,
                                         signed long long __offset,
                                         unsigned int *__ptr) {
-  *(unaligned_vec_uint *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_uint *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector float __vec,
                                         signed long long __offset,
                                         float *__ptr) {
-  *(unaligned_vec_float *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_float *)__addr = __vec;
 }
 #ifdef __VSX__
 static inline __ATTRS_o_ai void vec_xst(vector signed long long __vec,
                                         signed long long __offset,
                                         signed long long *__ptr) {
-  *(unaligned_vec_sll *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_sll *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector unsigned long long __vec,
                                         signed long long __offset,
                                         unsigned long long *__ptr) {
-  *(unaligned_vec_ull *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_ull *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector double __vec,
                                         signed long long __offset,
                                         double *__ptr) {
-  *(unaligned_vec_double *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_double *)__addr = __vec;
 }
 #endif
 @@ -16564,13 +16585,15 @@ static inline __ATTRS_o_ai void vec_xst(vector double __vec,
 static inline __ATTRS_o_ai void vec_xst(vector signed __int128 __vec,
                                         signed long long __offset,
                                         signed __int128 *__ptr) {
-  *(unaligned_vec_si128 *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_si128 *)__addr = __vec;
 }
 static inline __ATTRS_o_ai void vec_xst(vector unsigned __int128 __vec,
                                         signed long long __offset,
                                         unsigned __int128 *__ptr) {
-  *(unaligned_vec_ui128 *)(__ptr + __offset) = __vec;
+  signed char *__addr = (signed char *)__ptr + __offset;
+  *(unaligned_vec_ui128 *)__addr = __vec;
 }
 #endif
 @@ -16583,7 +16606,8 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed char __vec,
   vector signed char __tmp =
      __builtin_shufflevector(__vec, __vec, 7, 6, 5, 4, 3, 2, 1, 0, 15, 14,
                              13, 12, 11, 10, 9, 8);
-  __builtin_vsx_stxvd2x_be(__tmp, __offset, __ptr);
+  typedef __attribute__((vector_size(sizeof(__tmp)))) double __vector_double;
+  __builtin_vsx_stxvd2x_be((__vector_double)__tmp, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned char __vec,
 @@ -16592,7 +16616,8 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned char __vec,
   vector unsigned char __tmp =
      __builtin_shufflevector(__vec, __vec, 7, 6, 5, 4, 3, 2, 1, 0, 15, 14,
                              13, 12, 11, 10, 9, 8);
-  __builtin_vsx_stxvd2x_be(__tmp, __offset, __ptr);
+  typedef __attribute__((vector_size(sizeof(__tmp)))) double __vector_double;
+  __builtin_vsx_stxvd2x_be((__vector_double)__tmp, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed short __vec,
 @@ -16600,7 +16625,8 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed short __vec,
                                                signed short *__ptr) {
   vector signed short __tmp =
      __builtin_shufflevector(__vec, __vec, 3, 2, 1, 0, 7, 6, 5, 4);
-  __builtin_vsx_stxvd2x_be(__tmp, __offset, __ptr);
+  typedef __attribute__((vector_size(sizeof(__tmp)))) double __vector_double;
+  __builtin_vsx_stxvd2x_be((__vector_double)__tmp, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned short __vec,
 @@ -16608,7 +16634,8 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned short __vec,
                                                unsigned short *__ptr) {
   vector unsigned short __tmp =
      __builtin_shufflevector(__vec, __vec, 3, 2, 1, 0, 7, 6, 5, 4);
-  __builtin_vsx_stxvd2x_be(__tmp, __offset, __ptr);
+  typedef __attribute__((vector_size(sizeof(__tmp)))) double __vector_double;
+  __builtin_vsx_stxvd2x_be((__vector_double)__tmp, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed int __vec,
 @@ -16620,32 +16647,32 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed int __vec,
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned int __vec,
                                                signed long long  __offset,
                                                unsigned int *__ptr) {
-  __builtin_vsx_stxvw4x_be(__vec, __offset, __ptr);
+  __builtin_vsx_stxvw4x_be((vector int)__vec, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector float __vec,
                                                signed long long  __offset,
                                                float *__ptr) {
-  __builtin_vsx_stxvw4x_be(__vec, __offset, __ptr);
+  __builtin_vsx_stxvw4x_be((vector int)__vec, __offset, __ptr);
 }
 #ifdef __VSX__
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector signed long long __vec,
                                                signed long long  __offset,
                                                signed long long *__ptr) {
-  __builtin_vsx_stxvd2x_be(__vec, __offset, __ptr);
+  __builtin_vsx_stxvd2x_be((vector double)__vec, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned long long __vec,
                                                signed long long  __offset,
                                                unsigned long long *__ptr) {
-  __builtin_vsx_stxvd2x_be(__vec, __offset, __ptr);
+  __builtin_vsx_stxvd2x_be((vector double)__vec, __offset, __ptr);
 }
 static __inline__ void __ATTRS_o_ai vec_xst_be(vector double __vec,
                                                signed long long  __offset,
                                                double *__ptr) {
-  __builtin_vsx_stxvd2x_be(__vec, __offset, __ptr);
+  __builtin_vsx_stxvd2x_be((vector double)__vec, __offset, __ptr);
 }
 #endif
 @@ -16667,13 +16694,13 @@ static __inline__ void __ATTRS_o_ai vec_xst_be(vector unsigned __int128 __vec,
 #endif
 #ifdef __POWER9_VECTOR__
-#define vec_test_data_class(__a, __b)                                      \
+#define vec_test_data_class(__a, __b)                                          \
-        _Generic((__a),                                                    \
+  _Generic(                                                                    \
-           vector float:                                                   \
+      (__a), vector float                                                      \
-             (vector bool int)__builtin_vsx_xvtstdcsp((__a), (__b)),       \
+      : (vector bool int)__builtin_vsx_xvtstdcsp((vector float)(__a), (__b)),  \
-           vector double:                                                  \
+        vector double                                                          \
-             (vector bool long long)__builtin_vsx_xvtstdcdp((__a), (__b))  \
+      : (vector bool long long)__builtin_vsx_xvtstdcdp((vector double)(__a),   \
-        )
+                                                       (__b)))
 #endif /* #ifdef __POWER9_VECTOR__ */

lib/include/arm_acle.h+49-1

...	@@ -90,9 +90,11 @@ __swp(uint32_t __x, volatile uint32_t *__p) {	...	@@ -90,9 +90,11 @@ __swp(uint32_t __x, volatile uint32_t *__p) {
90	#endif	90	#endif
91		91
92	/* 8.7 NOP */	92	/* 8.7 NOP */
		93	#if !defined(_MSC_VER) \|\| !defined(__aarch64__)
93	static __inline__ void __attribute__((__always_inline__, __nodebug__)) __nop(void) {	94	static __inline__ void __attribute__((__always_inline__, __nodebug__)) __nop(void) {
94	__builtin_arm_nop();	95	__builtin_arm_nop();
95	}	96	}
		97	#endif
96		98
97	/* 9 DATA-PROCESSING INTRINSICS */	99	/* 9 DATA-PROCESSING INTRINSICS */
98	/* 9.2 Miscellaneous data-processing intrinsics */	100	/* 9.2 Miscellaneous data-processing intrinsics */
...	@@ -139,6 +141,26 @@ __clzll(uint64_t __t) {	...	@@ -139,6 +141,26 @@ __clzll(uint64_t __t) {
139	return __builtin_clzll(__t);	141	return __builtin_clzll(__t);
140	}	142	}
141		143
		144	/* CLS */
		145	static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
		146	__cls(uint32_t __t) {
		147	return __builtin_arm_cls(__t);
		148	}
		149
		150	static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
		151	__clsl(unsigned long __t) {
		152	#if __SIZEOF_LONG__ == 4
		153	return __builtin_arm_cls(__t);
		154	#else
		155	return __builtin_arm_cls64(__t);
		156	#endif
		157	}
		158
		159	static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
		160	__clsll(uint64_t __t) {
		161	return __builtin_arm_cls64(__t);
		162	}
		163
142	/* REV */	164	/* REV */
143	static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))	165	static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
144	__rev(uint32_t __t) {	166	__rev(uint32_t __t) {
...	@@ -609,11 +631,15 @@ __jcvt(double __a) {	...	@@ -609,11 +631,15 @@ __jcvt(double __a) {
609	#define __arm_rsr(sysreg) __builtin_arm_rsr(sysreg)	631	#define __arm_rsr(sysreg) __builtin_arm_rsr(sysreg)
610	#define __arm_rsr64(sysreg) __builtin_arm_rsr64(sysreg)	632	#define __arm_rsr64(sysreg) __builtin_arm_rsr64(sysreg)
611	#define __arm_rsrp(sysreg) __builtin_arm_rsrp(sysreg)	633	#define __arm_rsrp(sysreg) __builtin_arm_rsrp(sysreg)
		634	#define __arm_rsrf(sysreg) __builtin_bit_cast(float, __arm_rsr(sysreg))
		635	#define __arm_rsrf64(sysreg) __builtin_bit_cast(double, __arm_rsr64(sysreg))
612	#define __arm_wsr(sysreg, v) __builtin_arm_wsr(sysreg, v)	636	#define __arm_wsr(sysreg, v) __builtin_arm_wsr(sysreg, v)
613	#define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)	637	#define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)
614	#define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)	638	#define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)
		639	#define __arm_wsrf(sysreg, v) __arm_wsr(sysreg, __builtin_bit_cast(uint32_t, v))
		640	#define __arm_wsrf64(sysreg, v) __arm_wsr64(sysreg, __builtin_bit_cast(uint64_t, v))
615		641
616	// Memory Tagging Extensions (MTE) Intrinsics	642	/* Memory Tagging Extensions (MTE) Intrinsics */
617	#if __ARM_FEATURE_MEMORY_TAGGING	643	#if __ARM_FEATURE_MEMORY_TAGGING
618	#define __arm_mte_create_random_tag(__ptr, __mask) __builtin_arm_irg(__ptr, __mask)	644	#define __arm_mte_create_random_tag(__ptr, __mask) __builtin_arm_irg(__ptr, __mask)
619	#define __arm_mte_increment_tag(__ptr, __tag_offset) __builtin_arm_addg(__ptr, __tag_offset)	645	#define __arm_mte_increment_tag(__ptr, __tag_offset) __builtin_arm_addg(__ptr, __tag_offset)
...	@@ -623,6 +649,28 @@ __jcvt(double __a) {	...	@@ -623,6 +649,28 @@ __jcvt(double __a) {
623	#define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)	649	#define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)
624	#endif	650	#endif
625		651
		652	/* Transactional Memory Extension (TME) Intrinsics */
		653	#if __ARM_FEATURE_TME
		654
		655	#define _TMFAILURE_REASON 0x00007fffu
		656	#define _TMFAILURE_RTRY 0x00008000u
		657	#define _TMFAILURE_CNCL 0x00010000u
		658	#define _TMFAILURE_MEM 0x00020000u
		659	#define _TMFAILURE_IMP 0x00040000u
		660	#define _TMFAILURE_ERR 0x00080000u
		661	#define _TMFAILURE_SIZE 0x00100000u
		662	#define _TMFAILURE_NEST 0x00200000u
		663	#define _TMFAILURE_DBG 0x00400000u
		664	#define _TMFAILURE_INT 0x00800000u
		665	#define _TMFAILURE_TRIVIAL 0x01000000u
		666
		667	#define __tstart() __builtin_arm_tstart()
		668	#define __tcommit() __builtin_arm_tcommit()
		669	#define __tcancel(__arg) __builtin_arm_tcancel(__arg)
		670	#define __ttest() __builtin_arm_ttest()
		671
		672	#endif /* __ARM_FEATURE_TME */
		673
626	#if defined(__cplusplus)	674	#if defined(__cplusplus)
627	}	675	}
628	#endif	676	#endif

lib/include/arm_cmse.h created+217

...	@@ -0,0 +1,217 @@
1	//===---- arm_cmse.h - Arm CMSE support -----------------------------------===//
2	//
3	// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4	// See https://llvm.org/LICENSE.txt for license information.
5	// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6	//
7	//===----------------------------------------------------------------------===//
8
9	#ifndef __ARM_CMSE_H
10	#define __ARM_CMSE_H
11
12	#if (__ARM_FEATURE_CMSE & 0x1)
13	#include <stddef.h>
14	#include <stdint.h>
15
16	#define __ARM_CMSE_SECURE_MODE (__ARM_FEATURE_CMSE & 0x2)
17	#define CMSE_MPU_READWRITE 1 /* checks if readwrite_ok field is set */
18	#define CMSE_AU_NONSECURE 2 /* checks if permissions have secure field unset */
19	#define CMSE_MPU_UNPRIV 4 /* sets T flag on TT insrtuction */
20	#define CMSE_MPU_READ 8 /* checks if read_ok field is set */
21	#define CMSE_MPU_NONSECURE 16 /* sets A flag, checks if secure field unset */
22	#define CMSE_NONSECURE (CMSE_AU_NONSECURE \| CMSE_MPU_NONSECURE)
23
24	#define cmse_check_pointed_object(p, f) \
25	cmse_check_address_range((p), sizeof(*(p)), (f))
26
27	#if defined(__cplusplus)
28	extern "C" {
29	#endif
30
31	typedef union {
32	struct cmse_address_info {
33	#ifdef __ARM_BIG_ENDIAN
34	/* __ARM_BIG_ENDIAN */
35	#if (__ARM_CMSE_SECURE_MODE)
36	unsigned idau_region : 8;
37	unsigned idau_region_valid : 1;
38	unsigned secure : 1;
39	unsigned nonsecure_readwrite_ok : 1;
40	unsigned nonsecure_read_ok : 1;
41	#else
42	unsigned : 12;
43	#endif
44	unsigned readwrite_ok : 1;
45	unsigned read_ok : 1;
46	#if (__ARM_CMSE_SECURE_MODE)
47	unsigned sau_region_valid : 1;
48	#else
49	unsigned : 1;
50	#endif
51	unsigned mpu_region_valid : 1;
52	#if (__ARM_CMSE_SECURE_MODE)
53	unsigned sau_region : 8;
54	#else
55	unsigned : 8;
56	#endif
57	unsigned mpu_region : 8;
58
59	#else /* __ARM_LITTLE_ENDIAN */
60	unsigned mpu_region : 8;
61	#if (__ARM_CMSE_SECURE_MODE)
62	unsigned sau_region : 8;
63	#else
64	unsigned : 8;
65	#endif
66	unsigned mpu_region_valid : 1;
67	#if (__ARM_CMSE_SECURE_MODE)
68	unsigned sau_region_valid : 1;
69	#else
70	unsigned : 1;
71	#endif
72	unsigned read_ok : 1;
73	unsigned readwrite_ok : 1;
74	#if (__ARM_CMSE_SECURE_MODE)
75	unsigned nonsecure_read_ok : 1;
76	unsigned nonsecure_readwrite_ok : 1;
77	unsigned secure : 1;
78	unsigned idau_region_valid : 1;
79	unsigned idau_region : 8;
80	#else
81	unsigned : 12;
82	#endif
83	#endif /__ARM_LITTLE_ENDIAN /
84	} flags;
85	unsigned value;
86	} cmse_address_info_t;
87
88	static cmse_address_info_t __attribute__((__always_inline__, __nodebug__))
89	cmse_TT(void *__p) {
90	cmse_address_info_t __u;
91	__u.value = __builtin_arm_cmse_TT(__p);
92	return __u;
93	}
94	static cmse_address_info_t __attribute__((__always_inline__, __nodebug__))
95	cmse_TTT(void *__p) {
96	cmse_address_info_t __u;
97	__u.value = __builtin_arm_cmse_TTT(__p);
98	return __u;
99	}
100
101	#if __ARM_CMSE_SECURE_MODE
102	static cmse_address_info_t __attribute__((__always_inline__, __nodebug__))
103	cmse_TTA(void *__p) {
104	cmse_address_info_t __u;
105	__u.value = __builtin_arm_cmse_TTA(__p);
106	return __u;
107	}
108	static cmse_address_info_t __attribute__((__always_inline__, __nodebug__))
109	cmse_TTAT(void *__p) {
110	cmse_address_info_t __u;
111	__u.value = __builtin_arm_cmse_TTAT(__p);
112	return __u;
113	}
114	#endif
115
116	#define cmse_TT_fptr(p) cmse_TT(__builtin_bit_cast(void *, (p)))
117	#define cmse_TTT_fptr(p) cmse_TTT(__builtin_bit_cast(void *, (p)))
118
119	#if __ARM_CMSE_SECURE_MODE
120	#define cmse_TTA_fptr(p) cmse_TTA(__builtin_bit_cast(void *, (p)))
121	#define cmse_TTAT_fptr(p) cmse_TTAT(__builtin_bit_cast(void *, (p)))
122	#endif
123
124	static void *__attribute__((__always_inline__))
125	cmse_check_address_range(void *__pb, size_t __s, int __flags) {
126	uintptr_t __begin = (uintptr_t)__pb;
127	uintptr_t __end = __begin + __s - 1;
128
129	if (__end < __begin)
130	return NULL; /* wrap around check */
131
132	/* Check whether the range crosses a 32-bytes aligned address */
133	const int __single_check = (__begin ^ __end) < 0x20u;
134
135	/* execute the right variant of the TT instructions */
136	void __pe = (void )__end;
137	cmse_address_info_t __permb, __perme;
138	switch (__flags & (CMSE_MPU_UNPRIV \| CMSE_MPU_NONSECURE)) {
139	case 0:
140	__permb = cmse_TT(__pb);
141	__perme = __single_check ? __permb : cmse_TT(__pe);
142	break;
143	case CMSE_MPU_UNPRIV:
144	__permb = cmse_TTT(__pb);
145	__perme = __single_check ? __permb : cmse_TTT(__pe);
146	break;
147	#if __ARM_CMSE_SECURE_MODE
148	case CMSE_MPU_NONSECURE:
149	__permb = cmse_TTA(__pb);
150	__perme = __single_check ? __permb : cmse_TTA(__pe);
151	break;
152	case CMSE_MPU_UNPRIV \| CMSE_MPU_NONSECURE:
153	__permb = cmse_TTAT(__pb);
154	__perme = __single_check ? __permb : cmse_TTAT(__pe);
155	break;
156	#endif
157	/* if CMSE_NONSECURE is specified w/o __ARM_CMSE_SECURE_MODE */
158	default:
159	return NULL;
160	}
161
162	/* check that the range does not cross MPU, SAU, or IDAU region boundaries */
163	if (__permb.value != __perme.value)
164	return NULL;
165	#if !(__ARM_CMSE_SECURE_MODE)
166	/* CMSE_AU_NONSECURE is only supported when __ARM_FEATURE_CMSE & 0x2 */
167	if (__flags & CMSE_AU_NONSECURE)
168	return NULL;
169	#endif
170
171	/* check the permission on the range */
172	switch (__flags & ~(CMSE_MPU_UNPRIV \| CMSE_MPU_NONSECURE)) {
173	#if (__ARM_CMSE_SECURE_MODE)
174	case CMSE_MPU_READ \| CMSE_MPU_READWRITE \| CMSE_AU_NONSECURE:
175	case CMSE_MPU_READWRITE \| CMSE_AU_NONSECURE:
176	return __permb.flags.nonsecure_readwrite_ok ? __pb : NULL;
177
178	case CMSE_MPU_READ \| CMSE_AU_NONSECURE:
179	return __permb.flags.nonsecure_read_ok ? __pb : NULL;
180
181	case CMSE_AU_NONSECURE:
182	return __permb.flags.secure ? NULL : __pb;
183	#endif
184	case CMSE_MPU_READ \| CMSE_MPU_READWRITE:
185	case CMSE_MPU_READWRITE:
186	return __permb.flags.readwrite_ok ? __pb : NULL;
187
188	case CMSE_MPU_READ:
189	return __permb.flags.read_ok ? __pb : NULL;
190
191	default:
192	return NULL;
193	}
194	}
195
196	#if __ARM_CMSE_SECURE_MODE
197	static int __attribute__((__always_inline__, __nodebug__))
198	cmse_nonsecure_caller(void) {
199	return !((uintptr_t)__builtin_return_address(0) & 1);
200	}
201
202	#define cmse_nsfptr_create(p) \
203	__builtin_bit_cast(__typeof__(p), \
204	(__builtin_bit_cast(uintptr_t, p) & ~(uintptr_t)1))
205
206	#define cmse_is_nsfptr(p) ((__builtin_bit_cast(uintptr_t, p) & 1) == 0)
207
208	#endif /* __ARM_CMSE_SECURE_MODE */
209
210	void __attribute__((__noreturn__)) cmse_abort(void);
211	#if defined(__cplusplus)
212	}
213	#endif
214
215	#endif /* (__ARM_FEATURE_CMSE & 0x1) */
216
217	#endif /* __ARM_CMSE_H */

lib/include/arm_fp16.h+26-929

...	@@ -30,7 +30,6 @@ typedef __fp16 float16_t;	...	@@ -30,7 +30,6 @@ typedef __fp16 float16_t;
30	#define __ai static __inline__ __attribute__((__always_inline__, __nodebug__))	30	#define __ai static __inline__ __attribute__((__always_inline__, __nodebug__))
31		31
32	#if defined(__ARM_FEATURE_FP16_SCALAR_ARITHMETIC) && defined(__aarch64__)	32	#if defined(__ARM_FEATURE_FP16_SCALAR_ARITHMETIC) && defined(__aarch64__)
33	#ifdef __LITTLE_ENDIAN__
34	#define vabdh_f16(__p0, __p1) __extension__ ({ \	33	#define vabdh_f16(__p0, __p1) __extension__ ({ \
35	float16_t __s0 = __p0; \	34	float16_t __s0 = __p0; \
36	float16_t __s1 = __p1; \	35	float16_t __s1 = __p1; \
...	@@ -38,41 +37,12 @@ typedef __fp16 float16_t;	...	@@ -38,41 +37,12 @@ typedef __fp16 float16_t;
38	__ret = (float16_t) __builtin_neon_vabdh_f16(__s0, __s1); \	37	__ret = (float16_t) __builtin_neon_vabdh_f16(__s0, __s1); \
39	__ret; \	38	__ret; \
40	})	39	})
41	#else
42	#define vabdh_f16(__p0, __p1) __extension__ ({ \
43	float16_t __s0 = __p0; \
44	float16_t __s1 = __p1; \
45	float16_t __ret; \
46	__ret = (float16_t) __builtin_neon_vabdh_f16(__s0, __s1); \
47	__ret; \
48	})
49	#endif
50
51	#ifdef __LITTLE_ENDIAN__
52	#define vabsh_f16(__p0) __extension__ ({ \
53	float16_t __s0 = __p0; \
54	float16_t __ret; \
55	__ret = (float16_t) __builtin_neon_vabsh_f16(__s0); \
56	__ret; \
57	})
58	#else
59	#define vabsh_f16(__p0) __extension__ ({ \	40	#define vabsh_f16(__p0) __extension__ ({ \
60	float16_t __s0 = __p0; \	41	float16_t __s0 = __p0; \
61	float16_t __ret; \	42	float16_t __ret; \
62	__ret = (float16_t) __builtin_neon_vabsh_f16(__s0); \	43	__ret = (float16_t) __builtin_neon_vabsh_f16(__s0); \
63	__ret; \	44	__ret; \
64	})	45	})
65	#endif
66
67	#ifdef __LITTLE_ENDIAN__
68	#define vaddh_f16(__p0, __p1) __extension__ ({ \
69	float16_t __s0 = __p0; \
70	float16_t __s1 = __p1; \
71	float16_t __ret; \
72	__ret = (float16_t) __builtin_neon_vaddh_f16(__s0, __s1); \
73	__ret; \
74	})
75	#else
76	#define vaddh_f16(__p0, __p1) __extension__ ({ \	46	#define vaddh_f16(__p0, __p1) __extension__ ({ \
77	float16_t __s0 = __p0; \	47	float16_t __s0 = __p0; \
78	float16_t __s1 = __p1; \	48	float16_t __s1 = __p1; \
...	@@ -80,9 +50,6 @@ typedef __fp16 float16_t;	...	@@ -80,9 +50,6 @@ typedef __fp16 float16_t;
80	__ret = (float16_t) __builtin_neon_vaddh_f16(__s0, __s1); \	50	__ret = (float16_t) __builtin_neon_vaddh_f16(__s0, __s1); \
81	__ret; \	51	__ret; \
82	})	52	})
83	#endif
84
85	#ifdef __LITTLE_ENDIAN__
86	#define vcageh_f16(__p0, __p1) __extension__ ({ \	53	#define vcageh_f16(__p0, __p1) __extension__ ({ \
87	float16_t __s0 = __p0; \	54	float16_t __s0 = __p0; \
88	float16_t __s1 = __p1; \	55	float16_t __s1 = __p1; \
...	@@ -90,25 +57,6 @@ typedef __fp16 float16_t;	...	@@ -90,25 +57,6 @@ typedef __fp16 float16_t;
90	__ret = (uint16_t) __builtin_neon_vcageh_f16(__s0, __s1); \	57	__ret = (uint16_t) __builtin_neon_vcageh_f16(__s0, __s1); \
91	__ret; \	58	__ret; \
92	})	59	})
93	#else
94	#define vcageh_f16(__p0, __p1) __extension__ ({ \
95	float16_t __s0 = __p0; \
96	float16_t __s1 = __p1; \
97	uint16_t __ret; \
98	__ret = (uint16_t) __builtin_neon_vcageh_f16(__s0, __s1); \
99	__ret; \
100	})
101	#endif
102
103	#ifdef __LITTLE_ENDIAN__
104	#define vcagth_f16(__p0, __p1) __extension__ ({ \
105	float16_t __s0 = __p0; \
106	float16_t __s1 = __p1; \
107	uint16_t __ret; \
108	__ret = (uint16_t) __builtin_neon_vcagth_f16(__s0, __s1); \
109	__ret; \
110	})
111	#else
112	#define vcagth_f16(__p0, __p1) __extension__ ({ \	60	#define vcagth_f16(__p0, __p1) __extension__ ({ \
113	float16_t __s0 = __p0; \	61	float16_t __s0 = __p0; \
114	float16_t __s1 = __p1; \	62	float16_t __s1 = __p1; \
...	@@ -116,17 +64,6 @@ typedef __fp16 float16_t;	...	@@ -116,17 +64,6 @@ typedef __fp16 float16_t;
116	__ret = (uint16_t) __builtin_neon_vcagth_f16(__s0, __s1); \	64	__ret = (uint16_t) __builtin_neon_vcagth_f16(__s0, __s1); \
117	__ret; \	65	__ret; \
118	})	66	})
119	#endif
120
121	#ifdef __LITTLE_ENDIAN__
122	#define vcaleh_f16(__p0, __p1) __extension__ ({ \
123	float16_t __s0 = __p0; \
124	float16_t __s1 = __p1; \
125	uint16_t __ret; \
126	__ret = (uint16_t) __builtin_neon_vcaleh_f16(__s0, __s1); \
127	__ret; \
128	})
129	#else
130	#define vcaleh_f16(__p0, __p1) __extension__ ({ \	67	#define vcaleh_f16(__p0, __p1) __extension__ ({ \
131	float16_t __s0 = __p0; \	68	float16_t __s0 = __p0; \
132	float16_t __s1 = __p1; \	69	float16_t __s1 = __p1; \
...	@@ -134,9 +71,6 @@ typedef __fp16 float16_t;	...	@@ -134,9 +71,6 @@ typedef __fp16 float16_t;
134	__ret = (uint16_t) __builtin_neon_vcaleh_f16(__s0, __s1); \	71	__ret = (uint16_t) __builtin_neon_vcaleh_f16(__s0, __s1); \
135	__ret; \	72	__ret; \
136	})	73	})
137	#endif
138
139	#ifdef __LITTLE_ENDIAN__
140	#define vcalth_f16(__p0, __p1) __extension__ ({ \	74	#define vcalth_f16(__p0, __p1) __extension__ ({ \
141	float16_t __s0 = __p0; \	75	float16_t __s0 = __p0; \
142	float16_t __s1 = __p1; \	76	float16_t __s1 = __p1; \
...	@@ -144,25 +78,6 @@ typedef __fp16 float16_t;	...	@@ -144,25 +78,6 @@ typedef __fp16 float16_t;
144	__ret = (uint16_t) __builtin_neon_vcalth_f16(__s0, __s1); \	78	__ret = (uint16_t) __builtin_neon_vcalth_f16(__s0, __s1); \
145	__ret; \	79	__ret; \
146	})	80	})
147	#else
148	#define vcalth_f16(__p0, __p1) __extension__ ({ \
149	float16_t __s0 = __p0; \
150	float16_t __s1 = __p1; \
151	uint16_t __ret; \
152	__ret = (uint16_t) __builtin_neon_vcalth_f16(__s0, __s1); \
153	__ret; \
154	})
155	#endif
156
157	#ifdef __LITTLE_ENDIAN__
158	#define vceqh_f16(__p0, __p1) __extension__ ({ \
159	float16_t __s0 = __p0; \
160	float16_t __s1 = __p1; \
161	uint16_t __ret; \
162	__ret = (uint16_t) __builtin_neon_vceqh_f16(__s0, __s1); \
163	__ret; \
164	})
165	#else
166	#define vceqh_f16(__p0, __p1) __extension__ ({ \	81	#define vceqh_f16(__p0, __p1) __extension__ ({ \
167	float16_t __s0 = __p0; \	82	float16_t __s0 = __p0; \
168	float16_t __s1 = __p1; \	83	float16_t __s1 = __p1; \
...	@@ -170,33 +85,12 @@ typedef __fp16 float16_t;	...	@@ -170,33 +85,12 @@ typedef __fp16 float16_t;
170	__ret = (uint16_t) __builtin_neon_vceqh_f16(__s0, __s1); \	85	__ret = (uint16_t) __builtin_neon_vceqh_f16(__s0, __s1); \
171	__ret; \	86	__ret; \
172	})	87	})
173	#endif
174
175	#ifdef __LITTLE_ENDIAN__
176	#define vceqzh_f16(__p0) __extension__ ({ \
177	float16_t __s0 = __p0; \
178	uint16_t __ret; \
179	__ret = (uint16_t) __builtin_neon_vceqzh_f16(__s0); \
180	__ret; \
181	})
182	#else
183	#define vceqzh_f16(__p0) __extension__ ({ \	88	#define vceqzh_f16(__p0) __extension__ ({ \
184	float16_t __s0 = __p0; \	89	float16_t __s0 = __p0; \
185	uint16_t __ret; \	90	uint16_t __ret; \
186	__ret = (uint16_t) __builtin_neon_vceqzh_f16(__s0); \	91	__ret = (uint16_t) __builtin_neon_vceqzh_f16(__s0); \
187	__ret; \	92	__ret; \
188	})	93	})
189	#endif
190
191	#ifdef __LITTLE_ENDIAN__
192	#define vcgeh_f16(__p0, __p1) __extension__ ({ \
193	float16_t __s0 = __p0; \
194	float16_t __s1 = __p1; \
195	uint16_t __ret; \
196	__ret = (uint16_t) __builtin_neon_vcgeh_f16(__s0, __s1); \
197	__ret; \
198	})
199	#else
200	#define vcgeh_f16(__p0, __p1) __extension__ ({ \	94	#define vcgeh_f16(__p0, __p1) __extension__ ({ \
201	float16_t __s0 = __p0; \	95	float16_t __s0 = __p0; \
202	float16_t __s1 = __p1; \	96	float16_t __s1 = __p1; \
...	@@ -204,33 +98,12 @@ typedef __fp16 float16_t;	...	@@ -204,33 +98,12 @@ typedef __fp16 float16_t;
204	__ret = (uint16_t) __builtin_neon_vcgeh_f16(__s0, __s1); \	98	__ret = (uint16_t) __builtin_neon_vcgeh_f16(__s0, __s1); \
205	__ret; \	99	__ret; \
206	})	100	})
207	#endif
208
209	#ifdef __LITTLE_ENDIAN__
210	#define vcgezh_f16(__p0) __extension__ ({ \
211	float16_t __s0 = __p0; \
212	uint16_t __ret; \
213	__ret = (uint16_t) __builtin_neon_vcgezh_f16(__s0); \
214	__ret; \
215	})
216	#else
217	#define vcgezh_f16(__p0) __extension__ ({ \	101	#define vcgezh_f16(__p0) __extension__ ({ \
218	float16_t __s0 = __p0; \	102	float16_t __s0 = __p0; \
219	uint16_t __ret; \	103	uint16_t __ret; \
220	__ret = (uint16_t) __builtin_neon_vcgezh_f16(__s0); \	104	__ret = (uint16_t) __builtin_neon_vcgezh_f16(__s0); \
221	__ret; \	105	__ret; \
222	})	106	})
223	#endif
224
225	#ifdef __LITTLE_ENDIAN__
226	#define vcgth_f16(__p0, __p1) __extension__ ({ \
227	float16_t __s0 = __p0; \
228	float16_t __s1 = __p1; \
229	uint16_t __ret; \
230	__ret = (uint16_t) __builtin_neon_vcgth_f16(__s0, __s1); \
231	__ret; \
232	})
233	#else
234	#define vcgth_f16(__p0, __p1) __extension__ ({ \	107	#define vcgth_f16(__p0, __p1) __extension__ ({ \
235	float16_t __s0 = __p0; \	108	float16_t __s0 = __p0; \
236	float16_t __s1 = __p1; \	109	float16_t __s1 = __p1; \
...	@@ -238,25 +111,12 @@ typedef __fp16 float16_t;	...	@@ -238,25 +111,12 @@ typedef __fp16 float16_t;
238	__ret = (uint16_t) __builtin_neon_vcgth_f16(__s0, __s1); \	111	__ret = (uint16_t) __builtin_neon_vcgth_f16(__s0, __s1); \
239	__ret; \	112	__ret; \
240	})	113	})
241	#endif
242
243	#ifdef __LITTLE_ENDIAN__
244	#define vcgtzh_f16(__p0) __extension__ ({ \
245	float16_t __s0 = __p0; \
246	uint16_t __ret; \
247	__ret = (uint16_t) __builtin_neon_vcgtzh_f16(__s0); \
248	__ret; \
249	})
250	#else
251	#define vcgtzh_f16(__p0) __extension__ ({ \	114	#define vcgtzh_f16(__p0) __extension__ ({ \
252	float16_t __s0 = __p0; \	115	float16_t __s0 = __p0; \
253	uint16_t __ret; \	116	uint16_t __ret; \
254	__ret = (uint16_t) __builtin_neon_vcgtzh_f16(__s0); \	117	__ret = (uint16_t) __builtin_neon_vcgtzh_f16(__s0); \
255	__ret; \	118	__ret; \
256	})	119	})
257	#endif
258
259	#ifdef __LITTLE_ENDIAN__
260	#define vcleh_f16(__p0, __p1) __extension__ ({ \	120	#define vcleh_f16(__p0, __p1) __extension__ ({ \
261	float16_t __s0 = __p0; \	121	float16_t __s0 = __p0; \
262	float16_t __s1 = __p1; \	122	float16_t __s1 = __p1; \
...	@@ -264,41 +124,12 @@ typedef __fp16 float16_t;	...	@@ -264,41 +124,12 @@ typedef __fp16 float16_t;
264	__ret = (uint16_t) __builtin_neon_vcleh_f16(__s0, __s1); \	124	__ret = (uint16_t) __builtin_neon_vcleh_f16(__s0, __s1); \
265	__ret; \	125	__ret; \
266	})	126	})
267	#else
268	#define vcleh_f16(__p0, __p1) __extension__ ({ \
269	float16_t __s0 = __p0; \
270	float16_t __s1 = __p1; \
271	uint16_t __ret; \
272	__ret = (uint16_t) __builtin_neon_vcleh_f16(__s0, __s1); \
273	__ret; \
274	})
275	#endif
276
277	#ifdef __LITTLE_ENDIAN__
278	#define vclezh_f16(__p0) __extension__ ({ \
279	float16_t __s0 = __p0; \
280	uint16_t __ret; \
281	__ret = (uint16_t) __builtin_neon_vclezh_f16(__s0); \
282	__ret; \
283	})
284	#else
285	#define vclezh_f16(__p0) __extension__ ({ \	127	#define vclezh_f16(__p0) __extension__ ({ \
286	float16_t __s0 = __p0; \	128	float16_t __s0 = __p0; \
287	uint16_t __ret; \	129	uint16_t __ret; \
288	__ret = (uint16_t) __builtin_neon_vclezh_f16(__s0); \	130	__ret = (uint16_t) __builtin_neon_vclezh_f16(__s0); \
289	__ret; \	131	__ret; \
290	})	132	})
291	#endif
292
293	#ifdef __LITTLE_ENDIAN__
294	#define vclth_f16(__p0, __p1) __extension__ ({ \
295	float16_t __s0 = __p0; \
296	float16_t __s1 = __p1; \
297	uint16_t __ret; \
298	__ret = (uint16_t) __builtin_neon_vclth_f16(__s0, __s1); \
299	__ret; \
300	})
301	#else
302	#define vclth_f16(__p0, __p1) __extension__ ({ \	133	#define vclth_f16(__p0, __p1) __extension__ ({ \
303	float16_t __s0 = __p0; \	134	float16_t __s0 = __p0; \
304	float16_t __s1 = __p1; \	135	float16_t __s1 = __p1; \
...	@@ -306,789 +137,300 @@ typedef __fp16 float16_t;	...	@@ -306,789 +137,300 @@ typedef __fp16 float16_t;
306	__ret = (uint16_t) __builtin_neon_vclth_f16(__s0, __s1); \	137	__ret = (uint16_t) __builtin_neon_vclth_f16(__s0, __s1); \
307	__ret; \	138	__ret; \
308	})	139	})
309	#endif
310
311	#ifdef __LITTLE_ENDIAN__
312	#define vcltzh_f16(__p0) __extension__ ({ \
313	float16_t __s0 = __p0; \
314	uint16_t __ret; \
315	__ret = (uint16_t) __builtin_neon_vcltzh_f16(__s0); \
316	__ret; \
317	})
318	#else
319	#define vcltzh_f16(__p0) __extension__ ({ \	140	#define vcltzh_f16(__p0) __extension__ ({ \
320	float16_t __s0 = __p0; \	141	float16_t __s0 = __p0; \
321	uint16_t __ret; \	142	uint16_t __ret; \
322	__ret = (uint16_t) __builtin_neon_vcltzh_f16(__s0); \	143	__ret = (uint16_t) __builtin_neon_vcltzh_f16(__s0); \
323	__ret; \	144	__ret; \
324	})	145	})
325	#endif
326
327	#ifdef __LITTLE_ENDIAN__
328	#define vcvth_n_s16_f16(__p0, __p1) __extension__ ({ \
329	float16_t __s0 = __p0; \
330	int16_t __ret; \
331	__ret = (int16_t) __builtin_neon_vcvth_n_s16_f16(__s0, __p1); \
332	__ret; \
333	})
334	#else
335	#define vcvth_n_s16_f16(__p0, __p1) __extension__ ({ \	146	#define vcvth_n_s16_f16(__p0, __p1) __extension__ ({ \
336	float16_t __s0 = __p0; \	147	float16_t __s0 = __p0; \
337	int16_t __ret; \	148	int16_t __ret; \
338	__ret = (int16_t) __builtin_neon_vcvth_n_s16_f16(__s0, __p1); \	149	__ret = (int16_t) __builtin_neon_vcvth_n_s16_f16(__s0, __p1); \
339	__ret; \	150	__ret; \
340	})	151	})
341	#endif
342
343	#ifdef __LITTLE_ENDIAN__
344	#define vcvth_n_s32_f16(__p0, __p1) __extension__ ({ \
345	float16_t __s0 = __p0; \
346	int32_t __ret; \
347	__ret = (int32_t) __builtin_neon_vcvth_n_s32_f16(__s0, __p1); \
348	__ret; \
349	})
350	#else
351	#define vcvth_n_s32_f16(__p0, __p1) __extension__ ({ \	152	#define vcvth_n_s32_f16(__p0, __p1) __extension__ ({ \
352	float16_t __s0 = __p0; \	153	float16_t __s0 = __p0; \
353	int32_t __ret; \	154	int32_t __ret; \
354	__ret = (int32_t) __builtin_neon_vcvth_n_s32_f16(__s0, __p1); \	155	__ret = (int32_t) __builtin_neon_vcvth_n_s32_f16(__s0, __p1); \
355	__ret; \	156	__ret; \
356	})	157	})
357	#endif
358
359	#ifdef __LITTLE_ENDIAN__
360	#define vcvth_n_s64_f16(__p0, __p1) __extension__ ({ \
361	float16_t __s0 = __p0; \
362	int64_t __ret; \
363	__ret = (int64_t) __builtin_neon_vcvth_n_s64_f16(__s0, __p1); \
364	__ret; \
365	})
366	#else
367	#define vcvth_n_s64_f16(__p0, __p1) __extension__ ({ \	158	#define vcvth_n_s64_f16(__p0, __p1) __extension__ ({ \
368	float16_t __s0 = __p0; \	159	float16_t __s0 = __p0; \
369	int64_t __ret; \	160	int64_t __ret; \
370	__ret = (int64_t) __builtin_neon_vcvth_n_s64_f16(__s0, __p1); \	161	__ret = (int64_t) __builtin_neon_vcvth_n_s64_f16(__s0, __p1); \
371	__ret; \	162	__ret; \
372	})	163	})
373	#endif
374
375	#ifdef __LITTLE_ENDIAN__
376	#define vcvth_n_u16_f16(__p0, __p1) __extension__ ({ \
377	float16_t __s0 = __p0; \
378	uint16_t __ret; \
379	__ret = (uint16_t) __builtin_neon_vcvth_n_u16_f16(__s0, __p1); \
380	__ret; \
381	})
382	#else
383	#define vcvth_n_u16_f16(__p0, __p1) __extension__ ({ \	164	#define vcvth_n_u16_f16(__p0, __p1) __extension__ ({ \
384	float16_t __s0 = __p0; \	165	float16_t __s0 = __p0; \
385	uint16_t __ret; \	166	uint16_t __ret; \
386	__ret = (uint16_t) __builtin_neon_vcvth_n_u16_f16(__s0, __p1); \	167	__ret = (uint16_t) __builtin_neon_vcvth_n_u16_f16(__s0, __p1); \
387	__ret; \	168	__ret; \
388	})	169	})
389	#endif
390
391	#ifdef __LITTLE_ENDIAN__
392	#define vcvth_n_u32_f16(__p0, __p1) __extension__ ({ \
393	float16_t __s0 = __p0; \
394	uint32_t __ret; \
395	__ret = (uint32_t) __builtin_neon_vcvth_n_u32_f16(__s0, __p1); \
396	__ret; \
397	})
398	#else
399	#define vcvth_n_u32_f16(__p0, __p1) __extension__ ({ \	170	#define vcvth_n_u32_f16(__p0, __p1) __extension__ ({ \
400	float16_t __s0 = __p0; \	171	float16_t __s0 = __p0; \
401	uint32_t __ret; \	172	uint32_t __ret; \
402	__ret = (uint32_t) __builtin_neon_vcvth_n_u32_f16(__s0, __p1); \	173	__ret = (uint32_t) __builtin_neon_vcvth_n_u32_f16(__s0, __p1); \
403	__ret; \	174	__ret; \
404	})	175	})
405	#endif
406
407	#ifdef __LITTLE_ENDIAN__
408	#define vcvth_n_u64_f16(__p0, __p1) __extension__ ({ \
409	float16_t __s0 = __p0; \
410	uint64_t __ret; \
411	__ret = (uint64_t) __builtin_neon_vcvth_n_u64_f16(__s0, __p1); \
412	__ret; \
413	})
414	#else
415	#define vcvth_n_u64_f16(__p0, __p1) __extension__ ({ \	176	#define vcvth_n_u64_f16(__p0, __p1) __extension__ ({ \
416	float16_t __s0 = __p0; \	177	float16_t __s0 = __p0; \
417	uint64_t __ret; \	178	uint64_t __ret; \
418	__ret = (uint64_t) __builtin_neon_vcvth_n_u64_f16(__s0, __p1); \	179	__ret = (uint64_t) __builtin_neon_vcvth_n_u64_f16(__s0, __p1); \
419	__ret; \	180	__ret; \
420	})	181	})
421	#endif
422
423	#ifdef __LITTLE_ENDIAN__
424	#define vcvth_s16_f16(__p0) __extension__ ({ \
425	float16_t __s0 = __p0; \
426	int16_t __ret; \
427	__ret = (int16_t) __builtin_neon_vcvth_s16_f16(__s0); \
428	__ret; \
429	})
430	#else
431	#define vcvth_s16_f16(__p0) __extension__ ({ \	182	#define vcvth_s16_f16(__p0) __extension__ ({ \
432	float16_t __s0 = __p0; \	183	float16_t __s0 = __p0; \
433	int16_t __ret; \	184	int16_t __ret; \
434	__ret = (int16_t) __builtin_neon_vcvth_s16_f16(__s0); \	185	__ret = (int16_t) __builtin_neon_vcvth_s16_f16(__s0); \
435	__ret; \	186	__ret; \
436	})	187	})
437	#endif
438
439	#ifdef __LITTLE_ENDIAN__
440	#define vcvth_s32_f16(__p0) __extension__ ({ \
441	float16_t __s0 = __p0; \
442	int32_t __ret; \
443	__ret = (int32_t) __builtin_neon_vcvth_s32_f16(__s0); \
444	__ret; \
445	})
446	#else
447	#define vcvth_s32_f16(__p0) __extension__ ({ \	188	#define vcvth_s32_f16(__p0) __extension__ ({ \
448	float16_t __s0 = __p0; \	189	float16_t __s0 = __p0; \
449	int32_t __ret; \	190	int32_t __ret; \
450	__ret = (int32_t) __builtin_neon_vcvth_s32_f16(__s0); \	191	__ret = (int32_t) __builtin_neon_vcvth_s32_f16(__s0); \
451	__ret; \	192	__ret; \
452	})	193	})
453	#endif
454
455	#ifdef __LITTLE_ENDIAN__
456	#define vcvth_s64_f16(__p0) __extension__ ({ \
457	float16_t __s0 = __p0; \
458	int64_t __ret; \
459	__ret = (int64_t) __builtin_neon_vcvth_s64_f16(__s0); \
460	__ret; \
461	})
462	#else
463	#define vcvth_s64_f16(__p0) __extension__ ({ \	194	#define vcvth_s64_f16(__p0) __extension__ ({ \
464	float16_t __s0 = __p0; \	195	float16_t __s0 = __p0; \
465	int64_t __ret; \	196	int64_t __ret; \
466	__ret = (int64_t) __builtin_neon_vcvth_s64_f16(__s0); \	197	__ret = (int64_t) __builtin_neon_vcvth_s64_f16(__s0); \
467	__ret; \	198	__ret; \
468	})	199	})
469	#endif
470
471	#ifdef __LITTLE_ENDIAN__
472	#define vcvth_u16_f16(__p0) __extension__ ({ \
473	float16_t __s0 = __p0; \
474	uint16_t __ret; \
475	__ret = (uint16_t) __builtin_neon_vcvth_u16_f16(__s0); \
476	__ret; \
477	})
478	#else
479	#define vcvth_u16_f16(__p0) __extension__ ({ \	200	#define vcvth_u16_f16(__p0) __extension__ ({ \
480	float16_t __s0 = __p0; \	201	float16_t __s0 = __p0; \
481	uint16_t __ret; \	202	uint16_t __ret; \
482	__ret = (uint16_t) __builtin_neon_vcvth_u16_f16(__s0); \	203	__ret = (uint16_t) __builtin_neon_vcvth_u16_f16(__s0); \
483	__ret; \	204	__ret; \
484	})	205	})
485	#endif
486
487	#ifdef __LITTLE_ENDIAN__
488	#define vcvth_u32_f16(__p0) __extension__ ({ \
489	float16_t __s0 = __p0; \
490	uint32_t __ret; \
491	__ret = (uint32_t) __builtin_neon_vcvth_u32_f16(__s0); \
492	__ret; \
493	})
494	#else
495	#define vcvth_u32_f16(__p0) __extension__ ({ \	206	#define vcvth_u32_f16(__p0) __extension__ ({ \
496	float16_t __s0 = __p0; \	207	float16_t __s0 = __p0; \
497	uint32_t __ret; \	208	uint32_t __ret; \
498	__ret = (uint32_t) __builtin_neon_vcvth_u32_f16(__s0); \	209	__ret = (uint32_t) __builtin_neon_vcvth_u32_f16(__s0); \
499	__ret; \	210	__ret; \
500	})	211	})
501	#endif
502
503	#ifdef __LITTLE_ENDIAN__
504	#define vcvth_u64_f16(__p0) __extension__ ({ \
505	float16_t __s0 = __p0; \
506	uint64_t __ret; \
507	__ret = (uint64_t) __builtin_neon_vcvth_u64_f16(__s0); \
508	__ret; \
509	})
510	#else
511	#define vcvth_u64_f16(__p0) __extension__ ({ \	212	#define vcvth_u64_f16(__p0) __extension__ ({ \
512	float16_t __s0 = __p0; \	213	float16_t __s0 = __p0; \
513	uint64_t __ret; \	214	uint64_t __ret; \
514	__ret = (uint64_t) __builtin_neon_vcvth_u64_f16(__s0); \	215	__ret = (uint64_t) __builtin_neon_vcvth_u64_f16(__s0); \
515	__ret; \	216	__ret; \
516	})	217	})
517	#endif
518
519	#ifdef __LITTLE_ENDIAN__
520	#define vcvtah_s16_f16(__p0) __extension__ ({ \
521	float16_t __s0 = __p0; \
522	int16_t __ret; \
523	__ret = (int16_t) __builtin_neon_vcvtah_s16_f16(__s0); \
524	__ret; \
525	})
526	#else
527	#define vcvtah_s16_f16(__p0) __extension__ ({ \	218	#define vcvtah_s16_f16(__p0) __extension__ ({ \
528	float16_t __s0 = __p0; \	219	float16_t __s0 = __p0; \
529	int16_t __ret; \	220	int16_t __ret; \
530	__ret = (int16_t) __builtin_neon_vcvtah_s16_f16(__s0); \	221	__ret = (int16_t) __builtin_neon_vcvtah_s16_f16(__s0); \
531	__ret; \	222	__ret; \
532	})	223	})
533	#endif
534
535	#ifdef __LITTLE_ENDIAN__
536	#define vcvtah_s32_f16(__p0) __extension__ ({ \
537	float16_t __s0 = __p0; \
538	int32_t __ret; \
539	__ret = (int32_t) __builtin_neon_vcvtah_s32_f16(__s0); \
540	__ret; \
541	})
542	#else
543	#define vcvtah_s32_f16(__p0) __extension__ ({ \	224	#define vcvtah_s32_f16(__p0) __extension__ ({ \
544	float16_t __s0 = __p0; \	225	float16_t __s0 = __p0; \
545	int32_t __ret; \	226	int32_t __ret; \
546	__ret = (int32_t) __builtin_neon_vcvtah_s32_f16(__s0); \	227	__ret = (int32_t) __builtin_neon_vcvtah_s32_f16(__s0); \
547	__ret; \	228	__ret; \
548	})	229	})
549	#endif
550
551	#ifdef __LITTLE_ENDIAN__
552	#define vcvtah_s64_f16(__p0) __extension__ ({ \
553	float16_t __s0 = __p0; \
554	int64_t __ret; \
555	__ret = (int64_t) __builtin_neon_vcvtah_s64_f16(__s0); \
556	__ret; \
557	})
558	#else
559	#define vcvtah_s64_f16(__p0) __extension__ ({ \	230	#define vcvtah_s64_f16(__p0) __extension__ ({ \
560	float16_t __s0 = __p0; \	231	float16_t __s0 = __p0; \
561	int64_t __ret; \	232	int64_t __ret; \
562	__ret = (int64_t) __builtin_neon_vcvtah_s64_f16(__s0); \	233	__ret = (int64_t) __builtin_neon_vcvtah_s64_f16(__s0); \
563	__ret; \	234	__ret; \
564	})	235	})
565	#endif
566
567	#ifdef __LITTLE_ENDIAN__
568	#define vcvtah_u16_f16(__p0) __extension__ ({ \
569	float16_t __s0 = __p0; \
570	uint16_t __ret; \
571	__ret = (uint16_t) __builtin_neon_vcvtah_u16_f16(__s0); \
572	__ret; \
573	})
574	#else
575	#define vcvtah_u16_f16(__p0) __extension__ ({ \	236	#define vcvtah_u16_f16(__p0) __extension__ ({ \
576	float16_t __s0 = __p0; \	237	float16_t __s0 = __p0; \
577	uint16_t __ret; \	238	uint16_t __ret; \
578	__ret = (uint16_t) __builtin_neon_vcvtah_u16_f16(__s0); \	239	__ret = (uint16_t) __builtin_neon_vcvtah_u16_f16(__s0); \
579	__ret; \	240	__ret; \
580	})	241	})
581	#endif
582
583	#ifdef __LITTLE_ENDIAN__
584	#define vcvtah_u32_f16(__p0) __extension__ ({ \
585	float16_t __s0 = __p0; \
586	uint32_t __ret; \
587	__ret = (uint32_t) __builtin_neon_vcvtah_u32_f16(__s0); \
588	__ret; \
589	})
590	#else
591	#define vcvtah_u32_f16(__p0) __extension__ ({ \	242	#define vcvtah_u32_f16(__p0) __extension__ ({ \
592	float16_t __s0 = __p0; \	243	float16_t __s0 = __p0; \
593	uint32_t __ret; \	244	uint32_t __ret; \
594	__ret = (uint32_t) __builtin_neon_vcvtah_u32_f16(__s0); \	245	__ret = (uint32_t) __builtin_neon_vcvtah_u32_f16(__s0); \
595	__ret; \	246	__ret; \
596	})	247	})
597	#endif
598
599	#ifdef __LITTLE_ENDIAN__
600	#define vcvtah_u64_f16(__p0) __extension__ ({ \	248	#define vcvtah_u64_f16(__p0) __extension__ ({ \
601	float16_t __s0 = __p0; \	249	float16_t __s0 = __p0; \
602	uint64_t __ret; \	250	uint64_t __ret; \
603	__ret = (uint64_t) __builtin_neon_vcvtah_u64_f16(__s0); \	251	__ret = (uint64_t) __builtin_neon_vcvtah_u64_f16(__s0); \
604	__ret; \	252	__ret; \
605	})	253	})
606	#else	254	#define vcvth_f16_u16(__p0) __extension__ ({ \
607	#define vcvtah_u64_f16(__p0) __extension__ ({ \	255	uint16_t __s0 = __p0; \
608	float16_t __s0 = __p0; \	256	float16_t __ret; \
609	uint64_t __ret; \	257	__ret = (float16_t) __builtin_neon_vcvth_f16_u16(__s0); \
610	__ret = (uint64_t) __builtin_neon_vcvtah_u64_f16(__s0); \
611	__ret; \	258	__ret; \
612	})	259	})
613	#endif	260	#define vcvth_f16_s16(__p0) __extension__ ({ \
614		261	int16_t __s0 = __p0; \
615	#ifdef __LITTLE_ENDIAN__
616	__ai float16_t vcvth_f16_u32(uint32_t __p0) {
617	float16_t __ret;
618	__ret = (float16_t) __builtin_neon_vcvth_f16_u32(__p0);
619	return __ret;
620	}
621	#else
622	__ai float16_t vcvth_f16_u32(uint32_t __p0) {
623	float16_t __ret;
624	__ret = (float16_t) __builtin_neon_vcvth_f16_u32(__p0);
625	return __ret;
626	}
627	#endif
628
629	#ifdef __LITTLE_ENDIAN__
630	__ai float16_t vcvth_f16_u64(uint64_t __p0) {
631	float16_t __ret;
632	__ret = (float16_t) __builtin_neon_vcvth_f16_u64(__p0);
633	return __ret;
634	}
635	#else
636	__ai float16_t vcvth_f16_u64(uint64_t __p0) {
637	float16_t __ret;
638	__ret = (float16_t) __builtin_neon_vcvth_f16_u64(__p0);
639	return __ret;
640	}
641	#endif
642
643	#ifdef __LITTLE_ENDIAN__
644	__ai float16_t vcvth_f16_u16(uint16_t __p0) {
645	float16_t __ret;
646	__ret = (float16_t) __builtin_neon_vcvth_f16_u16(__p0);
647	return __ret;
648	}
649	#else
650	__ai float16_t vcvth_f16_u16(uint16_t __p0) {
651	float16_t __ret;
652	__ret = (float16_t) __builtin_neon_vcvth_f16_u16(__p0);
653	return __ret;
654	}
655	#endif
656
657	#ifdef __LITTLE_ENDIAN__
658	__ai float16_t vcvth_f16_s32(int32_t __p0) {
659	float16_t __ret;
660	__ret = (float16_t) __builtin_neon_vcvth_f16_s32(__p0);
661	return __ret;
662	}
663	#else
664	__ai float16_t vcvth_f16_s32(int32_t __p0) {
665	float16_t __ret;
666	__ret = (float16_t) __builtin_neon_vcvth_f16_s32(__p0);
667	return __ret;
668	}
669	#endif
670
671	#ifdef __LITTLE_ENDIAN__
672	__ai float16_t vcvth_f16_s64(int64_t __p0) {
673	float16_t __ret;
674	__ret = (float16_t) __builtin_neon_vcvth_f16_s64(__p0);
675	return __ret;
676	}
677	#else
678	__ai float16_t vcvth_f16_s64(int64_t __p0) {
679	float16_t __ret;
680	__ret = (float16_t) __builtin_neon_vcvth_f16_s64(__p0);
681	return __ret;
682	}
683	#endif
684
685	#ifdef __LITTLE_ENDIAN__
686	__ai float16_t vcvth_f16_s16(int16_t __p0) {
687	float16_t __ret;
688	__ret = (float16_t) __builtin_neon_vcvth_f16_s16(__p0);
689	return __ret;
690	}
691	#else
692	__ai float16_t vcvth_f16_s16(int16_t __p0) {
693	float16_t __ret;
694	__ret = (float16_t) __builtin_neon_vcvth_f16_s16(__p0);
695	return __ret;
696	}
697	#endif
698
699	#ifdef __LITTLE_ENDIAN__
700	#define vcvth_n_f16_u32(__p0, __p1) __extension__ ({ \
701	uint32_t __s0 = __p0; \
702	float16_t __ret; \	262	float16_t __ret; \
703	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u32(__s0, __p1); \	263	__ret = (float16_t) __builtin_neon_vcvth_f16_s16(__s0); \
704	__ret; \	264	__ret; \
705	})	265	})
706	#else	266	#define vcvth_f16_u32(__p0) __extension__ ({ \
707	#define vcvth_n_f16_u32(__p0, __p1) __extension__ ({ \
708	uint32_t __s0 = __p0; \	267	uint32_t __s0 = __p0; \
709	float16_t __ret; \	268	float16_t __ret; \
710	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u32(__s0, __p1); \	269	__ret = (float16_t) __builtin_neon_vcvth_f16_u32(__s0); \
711	__ret; \	270	__ret; \
712	})	271	})
713	#endif	272	#define vcvth_f16_s32(__p0) __extension__ ({ \
714		273	int32_t __s0 = __p0; \
715	#ifdef __LITTLE_ENDIAN__
716	#define vcvth_n_f16_u64(__p0, __p1) __extension__ ({ \
717	uint64_t __s0 = __p0; \
718	float16_t __ret; \	274	float16_t __ret; \
719	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u64(__s0, __p1); \	275	__ret = (float16_t) __builtin_neon_vcvth_f16_s32(__s0); \
720	__ret; \	276	__ret; \
721	})	277	})
722	#else	278	#define vcvth_f16_u64(__p0) __extension__ ({ \
723	#define vcvth_n_f16_u64(__p0, __p1) __extension__ ({ \
724	uint64_t __s0 = __p0; \	279	uint64_t __s0 = __p0; \
725	float16_t __ret; \	280	float16_t __ret; \
726	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u64(__s0, __p1); \	281	__ret = (float16_t) __builtin_neon_vcvth_f16_u64(__s0); \
727	__ret; \
728	})
729	#endif
730
731	#ifdef __LITTLE_ENDIAN__
732	#define vcvth_n_f16_u16(__p0, __p1) __extension__ ({ \
733	uint16_t __s0 = __p0; \
734	float16_t __ret; \
735	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u16(__s0, __p1); \
736	__ret; \	282	__ret; \
737	})	283	})
738	#else	284	#define vcvth_f16_s64(__p0) __extension__ ({ \
739	#define vcvth_n_f16_u16(__p0, __p1) __extension__ ({ \	285	int64_t __s0 = __p0; \
740	uint16_t __s0 = __p0; \
741	float16_t __ret; \	286	float16_t __ret; \
742	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u16(__s0, __p1); \	287	__ret = (float16_t) __builtin_neon_vcvth_f16_s64(__s0); \
743	__ret; \	288	__ret; \
744	})	289	})
745	#endif	290	#define vcvth_n_f16_u32(__p0, __p1) __extension__ ({ \
746		291	uint32_t __s0 = __p0; \
747	#ifdef __LITTLE_ENDIAN__
748	#define vcvth_n_f16_s32(__p0, __p1) __extension__ ({ \
749	int32_t __s0 = __p0; \
750	float16_t __ret; \	292	float16_t __ret; \
751	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s32(__s0, __p1); \	293	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u32(__s0, __p1); \
752	__ret; \	294	__ret; \
753	})	295	})
754	#else
755	#define vcvth_n_f16_s32(__p0, __p1) __extension__ ({ \	296	#define vcvth_n_f16_s32(__p0, __p1) __extension__ ({ \
756	int32_t __s0 = __p0; \	297	int32_t __s0 = __p0; \
757	float16_t __ret; \	298	float16_t __ret; \
758	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s32(__s0, __p1); \	299	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s32(__s0, __p1); \
759	__ret; \	300	__ret; \
760	})	301	})
761	#endif	302	#define vcvth_n_f16_u64(__p0, __p1) __extension__ ({ \
762		303	uint64_t __s0 = __p0; \
763	#ifdef __LITTLE_ENDIAN__
764	#define vcvth_n_f16_s64(__p0, __p1) __extension__ ({ \
765	int64_t __s0 = __p0; \
766	float16_t __ret; \	304	float16_t __ret; \
767	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s64(__s0, __p1); \	305	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u64(__s0, __p1); \
768	__ret; \	306	__ret; \
769	})	307	})
770	#else
771	#define vcvth_n_f16_s64(__p0, __p1) __extension__ ({ \	308	#define vcvth_n_f16_s64(__p0, __p1) __extension__ ({ \
772	int64_t __s0 = __p0; \	309	int64_t __s0 = __p0; \
773	float16_t __ret; \	310	float16_t __ret; \
774	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s64(__s0, __p1); \	311	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s64(__s0, __p1); \
775	__ret; \	312	__ret; \
776	})	313	})
777	#endif	314	#define vcvth_n_f16_u16(__p0, __p1) __extension__ ({ \
778		315	uint16_t __s0 = __p0; \
779	#ifdef __LITTLE_ENDIAN__
780	#define vcvth_n_f16_s16(__p0, __p1) __extension__ ({ \
781	int16_t __s0 = __p0; \
782	float16_t __ret; \	316	float16_t __ret; \
783	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s16(__s0, __p1); \	317	__ret = (float16_t) __builtin_neon_vcvth_n_f16_u16(__s0, __p1); \
784	__ret; \	318	__ret; \
785	})	319	})
786	#else
787	#define vcvth_n_f16_s16(__p0, __p1) __extension__ ({ \	320	#define vcvth_n_f16_s16(__p0, __p1) __extension__ ({ \
788	int16_t __s0 = __p0; \	321	int16_t __s0 = __p0; \
789	float16_t __ret; \	322	float16_t __ret; \
790	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s16(__s0, __p1); \	323	__ret = (float16_t) __builtin_neon_vcvth_n_f16_s16(__s0, __p1); \
791	__ret; \	324	__ret; \
792	})	325	})
793	#endif
794
795	#ifdef __LITTLE_ENDIAN__
796	#define vcvtmh_s16_f16(__p0) __extension__ ({ \
797	float16_t __s0 = __p0; \
798	int16_t __ret; \
799	__ret = (int16_t) __builtin_neon_vcvtmh_s16_f16(__s0); \
800	__ret; \
801	})
802	#else
803	#define vcvtmh_s16_f16(__p0) __extension__ ({ \	326	#define vcvtmh_s16_f16(__p0) __extension__ ({ \
804	float16_t __s0 = __p0; \	327	float16_t __s0 = __p0; \
805	int16_t __ret; \	328	int16_t __ret; \
806	__ret = (int16_t) __builtin_neon_vcvtmh_s16_f16(__s0); \	329	__ret = (int16_t) __builtin_neon_vcvtmh_s16_f16(__s0); \
807	__ret; \	330	__ret; \
808	})	331	})
809	#endif
810
811	#ifdef __LITTLE_ENDIAN__
812	#define vcvtmh_s32_f16(__p0) __extension__ ({ \
813	float16_t __s0 = __p0; \
814	int32_t __ret; \
815	__ret = (int32_t) __builtin_neon_vcvtmh_s32_f16(__s0); \
816	__ret; \
817	})
818	#else
819	#define vcvtmh_s32_f16(__p0) __extension__ ({ \	332	#define vcvtmh_s32_f16(__p0) __extension__ ({ \
820	float16_t __s0 = __p0; \	333	float16_t __s0 = __p0; \
821	int32_t __ret; \	334	int32_t __ret; \
822	__ret = (int32_t) __builtin_neon_vcvtmh_s32_f16(__s0); \	335	__ret = (int32_t) __builtin_neon_vcvtmh_s32_f16(__s0); \
823	__ret; \	336	__ret; \
824	})	337	})
825	#endif
826
827	#ifdef __LITTLE_ENDIAN__
828	#define vcvtmh_s64_f16(__p0) __extension__ ({ \
829	float16_t __s0 = __p0; \
830	int64_t __ret; \
831	__ret = (int64_t) __builtin_neon_vcvtmh_s64_f16(__s0); \
832	__ret; \
833	})
834	#else
835	#define vcvtmh_s64_f16(__p0) __extension__ ({ \	338	#define vcvtmh_s64_f16(__p0) __extension__ ({ \
836	float16_t __s0 = __p0; \	339	float16_t __s0 = __p0; \
837	int64_t __ret; \	340	int64_t __ret; \
838	__ret = (int64_t) __builtin_neon_vcvtmh_s64_f16(__s0); \	341	__ret = (int64_t) __builtin_neon_vcvtmh_s64_f16(__s0); \
839	__ret; \	342	__ret; \
840	})	343	})
841	#endif
842
843	#ifdef __LITTLE_ENDIAN__
844	#define vcvtmh_u16_f16(__p0) __extension__ ({ \
845	float16_t __s0 = __p0; \
846	uint16_t __ret; \
847	__ret = (uint16_t) __builtin_neon_vcvtmh_u16_f16(__s0); \
848	__ret; \
849	})
850	#else
851	#define vcvtmh_u16_f16(__p0) __extension__ ({ \	344	#define vcvtmh_u16_f16(__p0) __extension__ ({ \
852	float16_t __s0 = __p0; \	345	float16_t __s0 = __p0; \
853	uint16_t __ret; \	346	uint16_t __ret; \
854	__ret = (uint16_t) __builtin_neon_vcvtmh_u16_f16(__s0); \	347	__ret = (uint16_t) __builtin_neon_vcvtmh_u16_f16(__s0); \
855	__ret; \	348	__ret; \
856	})	349	})
857	#endif
858
859	#ifdef __LITTLE_ENDIAN__
860	#define vcvtmh_u32_f16(__p0) __extension__ ({ \
861	float16_t __s0 = __p0; \
862	uint32_t __ret; \
863	__ret = (uint32_t) __builtin_neon_vcvtmh_u32_f16(__s0); \
864	__ret; \
865	})
866	#else
867	#define vcvtmh_u32_f16(__p0) __extension__ ({ \	350	#define vcvtmh_u32_f16(__p0) __extension__ ({ \
868	float16_t __s0 = __p0; \	351	float16_t __s0 = __p0; \
869	uint32_t __ret; \	352	uint32_t __ret; \
870	__ret = (uint32_t) __builtin_neon_vcvtmh_u32_f16(__s0); \	353	__ret = (uint32_t) __builtin_neon_vcvtmh_u32_f16(__s0); \
871	__ret; \	354	__ret; \
872	})	355	})
873	#endif
874
875	#ifdef __LITTLE_ENDIAN__
876	#define vcvtmh_u64_f16(__p0) __extension__ ({ \
877	float16_t __s0 = __p0; \
878	uint64_t __ret; \
879	__ret = (uint64_t) __builtin_neon_vcvtmh_u64_f16(__s0); \
880	__ret; \
881	})
882	#else
883	#define vcvtmh_u64_f16(__p0) __extension__ ({ \	356	#define vcvtmh_u64_f16(__p0) __extension__ ({ \
884	float16_t __s0 = __p0; \	357	float16_t __s0 = __p0; \
885	uint64_t __ret; \	358	uint64_t __ret; \
886	__ret = (uint64_t) __builtin_neon_vcvtmh_u64_f16(__s0); \	359	__ret = (uint64_t) __builtin_neon_vcvtmh_u64_f16(__s0); \
887	__ret; \	360	__ret; \
888	})	361	})
889	#endif
890
891	#ifdef __LITTLE_ENDIAN__
892	#define vcvtnh_s16_f16(__p0) __extension__ ({ \
893	float16_t __s0 = __p0; \
894	int16_t __ret; \
895	__ret = (int16_t) __builtin_neon_vcvtnh_s16_f16(__s0); \
896	__ret; \
897	})
898	#else
899	#define vcvtnh_s16_f16(__p0) __extension__ ({ \	362	#define vcvtnh_s16_f16(__p0) __extension__ ({ \
900	float16_t __s0 = __p0; \	363	float16_t __s0 = __p0; \
901	int16_t __ret; \	364	int16_t __ret; \
902	__ret = (int16_t) __builtin_neon_vcvtnh_s16_f16(__s0); \	365	__ret = (int16_t) __builtin_neon_vcvtnh_s16_f16(__s0); \
903	__ret; \	366	__ret; \
904	})	367	})
905	#endif
906
907	#ifdef __LITTLE_ENDIAN__
908	#define vcvtnh_s32_f16(__p0) __extension__ ({ \
909	float16_t __s0 = __p0; \
910	int32_t __ret; \
911	__ret = (int32_t) __builtin_neon_vcvtnh_s32_f16(__s0); \
912	__ret; \
913	})
914	#else
915	#define vcvtnh_s32_f16(__p0) __extension__ ({ \	368	#define vcvtnh_s32_f16(__p0) __extension__ ({ \
916	float16_t __s0 = __p0; \	369	float16_t __s0 = __p0; \
917	int32_t __ret; \	370	int32_t __ret; \
918	__ret = (int32_t) __builtin_neon_vcvtnh_s32_f16(__s0); \	371	__ret = (int32_t) __builtin_neon_vcvtnh_s32_f16(__s0); \
919	__ret; \	372	__ret; \
920	})	373	})
921	#endif
922
923	#ifdef __LITTLE_ENDIAN__
924	#define vcvtnh_s64_f16(__p0) __extension__ ({ \
925	float16_t __s0 = __p0; \
926	int64_t __ret; \
927	__ret = (int64_t) __builtin_neon_vcvtnh_s64_f16(__s0); \
928	__ret; \
929	})
930	#else
931	#define vcvtnh_s64_f16(__p0) __extension__ ({ \	374	#define vcvtnh_s64_f16(__p0) __extension__ ({ \
932	float16_t __s0 = __p0; \	375	float16_t __s0 = __p0; \
933	int64_t __ret; \	376	int64_t __ret; \
934	__ret = (int64_t) __builtin_neon_vcvtnh_s64_f16(__s0); \	377	__ret = (int64_t) __builtin_neon_vcvtnh_s64_f16(__s0); \
935	__ret; \	378	__ret; \
936	})	379	})
937	#endif
938
939	#ifdef __LITTLE_ENDIAN__
940	#define vcvtnh_u16_f16(__p0) __extension__ ({ \
941	float16_t __s0 = __p0; \
942	uint16_t __ret; \
943	__ret = (uint16_t) __builtin_neon_vcvtnh_u16_f16(__s0); \
944	__ret; \
945	})
946	#else
947	#define vcvtnh_u16_f16(__p0) __extension__ ({ \	380	#define vcvtnh_u16_f16(__p0) __extension__ ({ \
948	float16_t __s0 = __p0; \	381	float16_t __s0 = __p0; \
949	uint16_t __ret; \	382	uint16_t __ret; \
950	__ret = (uint16_t) __builtin_neon_vcvtnh_u16_f16(__s0); \	383	__ret = (uint16_t) __builtin_neon_vcvtnh_u16_f16(__s0); \
951	__ret; \	384	__ret; \
952	})	385	})
953	#endif
954
955	#ifdef __LITTLE_ENDIAN__
956	#define vcvtnh_u32_f16(__p0) __extension__ ({ \
957	float16_t __s0 = __p0; \
958	uint32_t __ret; \
959	__ret = (uint32_t) __builtin_neon_vcvtnh_u32_f16(__s0); \
960	__ret; \
961	})
962	#else
963	#define vcvtnh_u32_f16(__p0) __extension__ ({ \	386	#define vcvtnh_u32_f16(__p0) __extension__ ({ \
964	float16_t __s0 = __p0; \	387	float16_t __s0 = __p0; \
965	uint32_t __ret; \	388	uint32_t __ret; \
966	__ret = (uint32_t) __builtin_neon_vcvtnh_u32_f16(__s0); \	389	__ret = (uint32_t) __builtin_neon_vcvtnh_u32_f16(__s0); \
967	__ret; \	390	__ret; \
968	})	391	})
969	#endif
970
971	#ifdef __LITTLE_ENDIAN__
972	#define vcvtnh_u64_f16(__p0) __extension__ ({ \
973	float16_t __s0 = __p0; \
974	uint64_t __ret; \
975	__ret = (uint64_t) __builtin_neon_vcvtnh_u64_f16(__s0); \
976	__ret; \
977	})
978	#else
979	#define vcvtnh_u64_f16(__p0) __extension__ ({ \	392	#define vcvtnh_u64_f16(__p0) __extension__ ({ \
980	float16_t __s0 = __p0; \	393	float16_t __s0 = __p0; \
981	uint64_t __ret; \	394	uint64_t __ret; \
982	__ret = (uint64_t) __builtin_neon_vcvtnh_u64_f16(__s0); \	395	__ret = (uint64_t) __builtin_neon_vcvtnh_u64_f16(__s0); \
983	__ret; \	396	__ret; \
984	})	397	})
985	#endif
986
987	#ifdef __LITTLE_ENDIAN__
988	#define vcvtph_s16_f16(__p0) __extension__ ({ \
989	float16_t __s0 = __p0; \
990	int16_t __ret; \
991	__ret = (int16_t) __builtin_neon_vcvtph_s16_f16(__s0); \
992	__ret; \
993	})
994	#else
995	#define vcvtph_s16_f16(__p0) __extension__ ({ \	398	#define vcvtph_s16_f16(__p0) __extension__ ({ \
996	float16_t __s0 = __p0; \	399	float16_t __s0 = __p0; \
997	int16_t __ret; \	400	int16_t __ret; \
998	__ret = (int16_t) __builtin_neon_vcvtph_s16_f16(__s0); \	401	__ret = (int16_t) __builtin_neon_vcvtph_s16_f16(__s0); \
999	__ret; \	402	__ret; \
1000	})	403	})
1001	#endif
1002
1003	#ifdef __LITTLE_ENDIAN__
1004	#define vcvtph_s32_f16(__p0) __extension__ ({ \
1005	float16_t __s0 = __p0; \
1006	int32_t __ret; \
1007	__ret = (int32_t) __builtin_neon_vcvtph_s32_f16(__s0); \
1008	__ret; \
1009	})
1010	#else
1011	#define vcvtph_s32_f16(__p0) __extension__ ({ \	404	#define vcvtph_s32_f16(__p0) __extension__ ({ \
1012	float16_t __s0 = __p0; \	405	float16_t __s0 = __p0; \
1013	int32_t __ret; \	406	int32_t __ret; \
1014	__ret = (int32_t) __builtin_neon_vcvtph_s32_f16(__s0); \	407	__ret = (int32_t) __builtin_neon_vcvtph_s32_f16(__s0); \
1015	__ret; \	408	__ret; \
1016	})	409	})
1017	#endif
1018
1019	#ifdef __LITTLE_ENDIAN__
1020	#define vcvtph_s64_f16(__p0) __extension__ ({ \
1021	float16_t __s0 = __p0; \
1022	int64_t __ret; \
1023	__ret = (int64_t) __builtin_neon_vcvtph_s64_f16(__s0); \
1024	__ret; \
1025	})
1026	#else
1027	#define vcvtph_s64_f16(__p0) __extension__ ({ \	410	#define vcvtph_s64_f16(__p0) __extension__ ({ \
1028	float16_t __s0 = __p0; \	411	float16_t __s0 = __p0; \
1029	int64_t __ret; \	412	int64_t __ret; \
1030	__ret = (int64_t) __builtin_neon_vcvtph_s64_f16(__s0); \	413	__ret = (int64_t) __builtin_neon_vcvtph_s64_f16(__s0); \
1031	__ret; \	414	__ret; \
1032	})	415	})
1033	#endif
1034
1035	#ifdef __LITTLE_ENDIAN__
1036	#define vcvtph_u16_f16(__p0) __extension__ ({ \
1037	float16_t __s0 = __p0; \
1038	uint16_t __ret; \
1039	__ret = (uint16_t) __builtin_neon_vcvtph_u16_f16(__s0); \
1040	__ret; \
1041	})
1042	#else
1043	#define vcvtph_u16_f16(__p0) __extension__ ({ \	416	#define vcvtph_u16_f16(__p0) __extension__ ({ \
1044	float16_t __s0 = __p0; \	417	float16_t __s0 = __p0; \
1045	uint16_t __ret; \	418	uint16_t __ret; \
1046	__ret = (uint16_t) __builtin_neon_vcvtph_u16_f16(__s0); \	419	__ret = (uint16_t) __builtin_neon_vcvtph_u16_f16(__s0); \
1047	__ret; \	420	__ret; \
1048	})	421	})
1049	#endif
1050
1051	#ifdef __LITTLE_ENDIAN__
1052	#define vcvtph_u32_f16(__p0) __extension__ ({ \
1053	float16_t __s0 = __p0; \
1054	uint32_t __ret; \
1055	__ret = (uint32_t) __builtin_neon_vcvtph_u32_f16(__s0); \
1056	__ret; \
1057	})
1058	#else
1059	#define vcvtph_u32_f16(__p0) __extension__ ({ \	422	#define vcvtph_u32_f16(__p0) __extension__ ({ \
1060	float16_t __s0 = __p0; \	423	float16_t __s0 = __p0; \
1061	uint32_t __ret; \	424	uint32_t __ret; \
1062	__ret = (uint32_t) __builtin_neon_vcvtph_u32_f16(__s0); \	425	__ret = (uint32_t) __builtin_neon_vcvtph_u32_f16(__s0); \
1063	__ret; \	426	__ret; \
1064	})	427	})
1065	#endif
1066
1067	#ifdef __LITTLE_ENDIAN__
1068	#define vcvtph_u64_f16(__p0) __extension__ ({ \
1069	float16_t __s0 = __p0; \
1070	uint64_t __ret; \
1071	__ret = (uint64_t) __builtin_neon_vcvtph_u64_f16(__s0); \
1072	__ret; \
1073	})
1074	#else
1075	#define vcvtph_u64_f16(__p0) __extension__ ({ \	428	#define vcvtph_u64_f16(__p0) __extension__ ({ \
1076	float16_t __s0 = __p0; \	429	float16_t __s0 = __p0; \
1077	uint64_t __ret; \	430	uint64_t __ret; \
1078	__ret = (uint64_t) __builtin_neon_vcvtph_u64_f16(__s0); \	431	__ret = (uint64_t) __builtin_neon_vcvtph_u64_f16(__s0); \
1079	__ret; \	432	__ret; \
1080	})	433	})
1081	#endif
1082
1083	#ifdef __LITTLE_ENDIAN__
1084	#define vdivh_f16(__p0, __p1) __extension__ ({ \
1085	float16_t __s0 = __p0; \
1086	float16_t __s1 = __p1; \
1087	float16_t __ret; \
1088	__ret = (float16_t) __builtin_neon_vdivh_f16(__s0, __s1); \
1089	__ret; \
1090	})
1091	#else
1092	#define vdivh_f16(__p0, __p1) __extension__ ({ \	434	#define vdivh_f16(__p0, __p1) __extension__ ({ \
1093	float16_t __s0 = __p0; \	435	float16_t __s0 = __p0; \
1094	float16_t __s1 = __p1; \	436	float16_t __s1 = __p1; \
...	@@ -1096,18 +438,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1096,18 +438,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1096	__ret = (float16_t) __builtin_neon_vdivh_f16(__s0, __s1); \	438	__ret = (float16_t) __builtin_neon_vdivh_f16(__s0, __s1); \
1097	__ret; \	439	__ret; \
1098	})	440	})
1099	#endif
1100
1101	#ifdef __LITTLE_ENDIAN__
1102	#define vfmah_f16(__p0, __p1, __p2) __extension__ ({ \
1103	float16_t __s0 = __p0; \
1104	float16_t __s1 = __p1; \
1105	float16_t __s2 = __p2; \
1106	float16_t __ret; \
1107	__ret = (float16_t) __builtin_neon_vfmah_f16(__s0, __s1, __s2); \
1108	__ret; \
1109	})
1110	#else
1111	#define vfmah_f16(__p0, __p1, __p2) __extension__ ({ \	441	#define vfmah_f16(__p0, __p1, __p2) __extension__ ({ \
1112	float16_t __s0 = __p0; \	442	float16_t __s0 = __p0; \
1113	float16_t __s1 = __p1; \	443	float16_t __s1 = __p1; \
...	@@ -1116,18 +446,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1116,18 +446,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1116	__ret = (float16_t) __builtin_neon_vfmah_f16(__s0, __s1, __s2); \	446	__ret = (float16_t) __builtin_neon_vfmah_f16(__s0, __s1, __s2); \
1117	__ret; \	447	__ret; \
1118	})	448	})
1119	#endif
1120
1121	#ifdef __LITTLE_ENDIAN__
1122	#define vfmsh_f16(__p0, __p1, __p2) __extension__ ({ \
1123	float16_t __s0 = __p0; \
1124	float16_t __s1 = __p1; \
1125	float16_t __s2 = __p2; \
1126	float16_t __ret; \
1127	__ret = (float16_t) __builtin_neon_vfmsh_f16(__s0, __s1, __s2); \
1128	__ret; \
1129	})
1130	#else
1131	#define vfmsh_f16(__p0, __p1, __p2) __extension__ ({ \	449	#define vfmsh_f16(__p0, __p1, __p2) __extension__ ({ \
1132	float16_t __s0 = __p0; \	450	float16_t __s0 = __p0; \
1133	float16_t __s1 = __p1; \	451	float16_t __s1 = __p1; \
...	@@ -1136,17 +454,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1136,17 +454,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1136	__ret = (float16_t) __builtin_neon_vfmsh_f16(__s0, __s1, __s2); \	454	__ret = (float16_t) __builtin_neon_vfmsh_f16(__s0, __s1, __s2); \
1137	__ret; \	455	__ret; \
1138	})	456	})
1139	#endif
1140
1141	#ifdef __LITTLE_ENDIAN__
1142	#define vmaxh_f16(__p0, __p1) __extension__ ({ \
1143	float16_t __s0 = __p0; \
1144	float16_t __s1 = __p1; \
1145	float16_t __ret; \
1146	__ret = (float16_t) __builtin_neon_vmaxh_f16(__s0, __s1); \
1147	__ret; \
1148	})
1149	#else
1150	#define vmaxh_f16(__p0, __p1) __extension__ ({ \	457	#define vmaxh_f16(__p0, __p1) __extension__ ({ \
1151	float16_t __s0 = __p0; \	458	float16_t __s0 = __p0; \
1152	float16_t __s1 = __p1; \	459	float16_t __s1 = __p1; \
...	@@ -1154,17 +461,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1154,17 +461,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1154	__ret = (float16_t) __builtin_neon_vmaxh_f16(__s0, __s1); \	461	__ret = (float16_t) __builtin_neon_vmaxh_f16(__s0, __s1); \
1155	__ret; \	462	__ret; \
1156	})	463	})
1157	#endif
1158
1159	#ifdef __LITTLE_ENDIAN__
1160	#define vmaxnmh_f16(__p0, __p1) __extension__ ({ \
1161	float16_t __s0 = __p0; \
1162	float16_t __s1 = __p1; \
1163	float16_t __ret; \
1164	__ret = (float16_t) __builtin_neon_vmaxnmh_f16(__s0, __s1); \
1165	__ret; \
1166	})
1167	#else
1168	#define vmaxnmh_f16(__p0, __p1) __extension__ ({ \	464	#define vmaxnmh_f16(__p0, __p1) __extension__ ({ \
1169	float16_t __s0 = __p0; \	465	float16_t __s0 = __p0; \
1170	float16_t __s1 = __p1; \	466	float16_t __s1 = __p1; \
...	@@ -1172,17 +468,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1172,17 +468,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1172	__ret = (float16_t) __builtin_neon_vmaxnmh_f16(__s0, __s1); \	468	__ret = (float16_t) __builtin_neon_vmaxnmh_f16(__s0, __s1); \
1173	__ret; \	469	__ret; \
1174	})	470	})
1175	#endif
1176
1177	#ifdef __LITTLE_ENDIAN__
1178	#define vminh_f16(__p0, __p1) __extension__ ({ \
1179	float16_t __s0 = __p0; \
1180	float16_t __s1 = __p1; \
1181	float16_t __ret; \
1182	__ret = (float16_t) __builtin_neon_vminh_f16(__s0, __s1); \
1183	__ret; \
1184	})
1185	#else
1186	#define vminh_f16(__p0, __p1) __extension__ ({ \	471	#define vminh_f16(__p0, __p1) __extension__ ({ \
1187	float16_t __s0 = __p0; \	472	float16_t __s0 = __p0; \
1188	float16_t __s1 = __p1; \	473	float16_t __s1 = __p1; \
...	@@ -1190,17 +475,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1190,17 +475,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1190	__ret = (float16_t) __builtin_neon_vminh_f16(__s0, __s1); \	475	__ret = (float16_t) __builtin_neon_vminh_f16(__s0, __s1); \
1191	__ret; \	476	__ret; \
1192	})	477	})
1193	#endif
1194
1195	#ifdef __LITTLE_ENDIAN__
1196	#define vminnmh_f16(__p0, __p1) __extension__ ({ \
1197	float16_t __s0 = __p0; \
1198	float16_t __s1 = __p1; \
1199	float16_t __ret; \
1200	__ret = (float16_t) __builtin_neon_vminnmh_f16(__s0, __s1); \
1201	__ret; \
1202	})
1203	#else
1204	#define vminnmh_f16(__p0, __p1) __extension__ ({ \	478	#define vminnmh_f16(__p0, __p1) __extension__ ({ \
1205	float16_t __s0 = __p0; \	479	float16_t __s0 = __p0; \
1206	float16_t __s1 = __p1; \	480	float16_t __s1 = __p1; \
...	@@ -1208,17 +482,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1208,17 +482,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1208	__ret = (float16_t) __builtin_neon_vminnmh_f16(__s0, __s1); \	482	__ret = (float16_t) __builtin_neon_vminnmh_f16(__s0, __s1); \
1209	__ret; \	483	__ret; \
1210	})	484	})
1211	#endif
1212
1213	#ifdef __LITTLE_ENDIAN__
1214	#define vmulh_f16(__p0, __p1) __extension__ ({ \
1215	float16_t __s0 = __p0; \
1216	float16_t __s1 = __p1; \
1217	float16_t __ret; \
1218	__ret = (float16_t) __builtin_neon_vmulh_f16(__s0, __s1); \
1219	__ret; \
1220	})
1221	#else
1222	#define vmulh_f16(__p0, __p1) __extension__ ({ \	485	#define vmulh_f16(__p0, __p1) __extension__ ({ \
1223	float16_t __s0 = __p0; \	486	float16_t __s0 = __p0; \
1224	float16_t __s1 = __p1; \	487	float16_t __s1 = __p1; \
...	@@ -1226,17 +489,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1226,17 +489,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1226	__ret = (float16_t) __builtin_neon_vmulh_f16(__s0, __s1); \	489	__ret = (float16_t) __builtin_neon_vmulh_f16(__s0, __s1); \
1227	__ret; \	490	__ret; \
1228	})	491	})
1229	#endif
1230
1231	#ifdef __LITTLE_ENDIAN__
1232	#define vmulxh_f16(__p0, __p1) __extension__ ({ \
1233	float16_t __s0 = __p0; \
1234	float16_t __s1 = __p1; \
1235	float16_t __ret; \
1236	__ret = (float16_t) __builtin_neon_vmulxh_f16(__s0, __s1); \
1237	__ret; \
1238	})
1239	#else
1240	#define vmulxh_f16(__p0, __p1) __extension__ ({ \	492	#define vmulxh_f16(__p0, __p1) __extension__ ({ \
1241	float16_t __s0 = __p0; \	493	float16_t __s0 = __p0; \
1242	float16_t __s1 = __p1; \	494	float16_t __s1 = __p1; \
...	@@ -1244,49 +496,18 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1244,49 +496,18 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1244	__ret = (float16_t) __builtin_neon_vmulxh_f16(__s0, __s1); \	496	__ret = (float16_t) __builtin_neon_vmulxh_f16(__s0, __s1); \
1245	__ret; \	497	__ret; \
1246	})	498	})
1247	#endif
1248
1249	#ifdef __LITTLE_ENDIAN__
1250	#define vnegh_f16(__p0) __extension__ ({ \
1251	float16_t __s0 = __p0; \
1252	float16_t __ret; \
1253	__ret = (float16_t) __builtin_neon_vnegh_f16(__s0); \
1254	__ret; \
1255	})
1256	#else
1257	#define vnegh_f16(__p0) __extension__ ({ \	499	#define vnegh_f16(__p0) __extension__ ({ \
1258	float16_t __s0 = __p0; \	500	float16_t __s0 = __p0; \
1259	float16_t __ret; \	501	float16_t __ret; \
1260	__ret = (float16_t) __builtin_neon_vnegh_f16(__s0); \	502	__ret = (float16_t) __builtin_neon_vnegh_f16(__s0); \
1261	__ret; \	503	__ret; \
1262	})	504	})
1263	#endif
1264
1265	#ifdef __LITTLE_ENDIAN__
1266	#define vrecpeh_f16(__p0) __extension__ ({ \
1267	float16_t __s0 = __p0; \
1268	float16_t __ret; \
1269	__ret = (float16_t) __builtin_neon_vrecpeh_f16(__s0); \
1270	__ret; \
1271	})
1272	#else
1273	#define vrecpeh_f16(__p0) __extension__ ({ \	505	#define vrecpeh_f16(__p0) __extension__ ({ \
1274	float16_t __s0 = __p0; \	506	float16_t __s0 = __p0; \
1275	float16_t __ret; \	507	float16_t __ret; \
1276	__ret = (float16_t) __builtin_neon_vrecpeh_f16(__s0); \	508	__ret = (float16_t) __builtin_neon_vrecpeh_f16(__s0); \
1277	__ret; \	509	__ret; \
1278	})	510	})
1279	#endif
1280
1281	#ifdef __LITTLE_ENDIAN__
1282	#define vrecpsh_f16(__p0, __p1) __extension__ ({ \
1283	float16_t __s0 = __p0; \
1284	float16_t __s1 = __p1; \
1285	float16_t __ret; \
1286	__ret = (float16_t) __builtin_neon_vrecpsh_f16(__s0, __s1); \
1287	__ret; \
1288	})
1289	#else
1290	#define vrecpsh_f16(__p0, __p1) __extension__ ({ \	511	#define vrecpsh_f16(__p0, __p1) __extension__ ({ \
1291	float16_t __s0 = __p0; \	512	float16_t __s0 = __p0; \
1292	float16_t __s1 = __p1; \	513	float16_t __s1 = __p1; \
...	@@ -1294,161 +515,60 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1294,161 +515,60 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1294	__ret = (float16_t) __builtin_neon_vrecpsh_f16(__s0, __s1); \	515	__ret = (float16_t) __builtin_neon_vrecpsh_f16(__s0, __s1); \
1295	__ret; \	516	__ret; \
1296	})	517	})
1297	#endif
1298
1299	#ifdef __LITTLE_ENDIAN__
1300	#define vrecpxh_f16(__p0) __extension__ ({ \
1301	float16_t __s0 = __p0; \
1302	float16_t __ret; \
1303	__ret = (float16_t) __builtin_neon_vrecpxh_f16(__s0); \
1304	__ret; \
1305	})
1306	#else
1307	#define vrecpxh_f16(__p0) __extension__ ({ \	518	#define vrecpxh_f16(__p0) __extension__ ({ \
1308	float16_t __s0 = __p0; \	519	float16_t __s0 = __p0; \
1309	float16_t __ret; \	520	float16_t __ret; \
1310	__ret = (float16_t) __builtin_neon_vrecpxh_f16(__s0); \	521	__ret = (float16_t) __builtin_neon_vrecpxh_f16(__s0); \
1311	__ret; \	522	__ret; \
1312	})	523	})
1313	#endif
1314
1315	#ifdef __LITTLE_ENDIAN__
1316	#define vrndh_f16(__p0) __extension__ ({ \
1317	float16_t __s0 = __p0; \
1318	float16_t __ret; \
1319	__ret = (float16_t) __builtin_neon_vrndh_f16(__s0); \
1320	__ret; \
1321	})
1322	#else
1323	#define vrndh_f16(__p0) __extension__ ({ \	524	#define vrndh_f16(__p0) __extension__ ({ \
1324	float16_t __s0 = __p0; \	525	float16_t __s0 = __p0; \
1325	float16_t __ret; \	526	float16_t __ret; \
1326	__ret = (float16_t) __builtin_neon_vrndh_f16(__s0); \	527	__ret = (float16_t) __builtin_neon_vrndh_f16(__s0); \
1327	__ret; \	528	__ret; \
1328	})	529	})
1329	#endif
1330
1331	#ifdef __LITTLE_ENDIAN__
1332	#define vrndah_f16(__p0) __extension__ ({ \
1333	float16_t __s0 = __p0; \
1334	float16_t __ret; \
1335	__ret = (float16_t) __builtin_neon_vrndah_f16(__s0); \
1336	__ret; \
1337	})
1338	#else
1339	#define vrndah_f16(__p0) __extension__ ({ \	530	#define vrndah_f16(__p0) __extension__ ({ \
1340	float16_t __s0 = __p0; \	531	float16_t __s0 = __p0; \
1341	float16_t __ret; \	532	float16_t __ret; \
1342	__ret = (float16_t) __builtin_neon_vrndah_f16(__s0); \	533	__ret = (float16_t) __builtin_neon_vrndah_f16(__s0); \
1343	__ret; \	534	__ret; \
1344	})	535	})
1345	#endif
1346
1347	#ifdef __LITTLE_ENDIAN__
1348	#define vrndih_f16(__p0) __extension__ ({ \
1349	float16_t __s0 = __p0; \
1350	float16_t __ret; \
1351	__ret = (float16_t) __builtin_neon_vrndih_f16(__s0); \
1352	__ret; \
1353	})
1354	#else
1355	#define vrndih_f16(__p0) __extension__ ({ \	536	#define vrndih_f16(__p0) __extension__ ({ \
1356	float16_t __s0 = __p0; \	537	float16_t __s0 = __p0; \
1357	float16_t __ret; \	538	float16_t __ret; \
1358	__ret = (float16_t) __builtin_neon_vrndih_f16(__s0); \	539	__ret = (float16_t) __builtin_neon_vrndih_f16(__s0); \
1359	__ret; \	540	__ret; \
1360	})	541	})
1361	#endif
1362
1363	#ifdef __LITTLE_ENDIAN__
1364	#define vrndmh_f16(__p0) __extension__ ({ \
1365	float16_t __s0 = __p0; \
1366	float16_t __ret; \
1367	__ret = (float16_t) __builtin_neon_vrndmh_f16(__s0); \
1368	__ret; \
1369	})
1370	#else
1371	#define vrndmh_f16(__p0) __extension__ ({ \	542	#define vrndmh_f16(__p0) __extension__ ({ \
1372	float16_t __s0 = __p0; \	543	float16_t __s0 = __p0; \
1373	float16_t __ret; \	544	float16_t __ret; \
1374	__ret = (float16_t) __builtin_neon_vrndmh_f16(__s0); \	545	__ret = (float16_t) __builtin_neon_vrndmh_f16(__s0); \
1375	__ret; \	546	__ret; \
1376	})	547	})
1377	#endif
1378
1379	#ifdef __LITTLE_ENDIAN__
1380	#define vrndnh_f16(__p0) __extension__ ({ \
1381	float16_t __s0 = __p0; \
1382	float16_t __ret; \
1383	__ret = (float16_t) __builtin_neon_vrndnh_f16(__s0); \
1384	__ret; \
1385	})
1386	#else
1387	#define vrndnh_f16(__p0) __extension__ ({ \	548	#define vrndnh_f16(__p0) __extension__ ({ \
1388	float16_t __s0 = __p0; \	549	float16_t __s0 = __p0; \
1389	float16_t __ret; \	550	float16_t __ret; \
1390	__ret = (float16_t) __builtin_neon_vrndnh_f16(__s0); \	551	__ret = (float16_t) __builtin_neon_vrndnh_f16(__s0); \
1391	__ret; \	552	__ret; \
1392	})	553	})
1393	#endif
1394
1395	#ifdef __LITTLE_ENDIAN__
1396	#define vrndph_f16(__p0) __extension__ ({ \
1397	float16_t __s0 = __p0; \
1398	float16_t __ret; \
1399	__ret = (float16_t) __builtin_neon_vrndph_f16(__s0); \
1400	__ret; \
1401	})
1402	#else
1403	#define vrndph_f16(__p0) __extension__ ({ \	554	#define vrndph_f16(__p0) __extension__ ({ \
1404	float16_t __s0 = __p0; \	555	float16_t __s0 = __p0; \
1405	float16_t __ret; \	556	float16_t __ret; \
1406	__ret = (float16_t) __builtin_neon_vrndph_f16(__s0); \	557	__ret = (float16_t) __builtin_neon_vrndph_f16(__s0); \
1407	__ret; \	558	__ret; \
1408	})	559	})
1409	#endif
1410
1411	#ifdef __LITTLE_ENDIAN__
1412	#define vrndxh_f16(__p0) __extension__ ({ \
1413	float16_t __s0 = __p0; \
1414	float16_t __ret; \
1415	__ret = (float16_t) __builtin_neon_vrndxh_f16(__s0); \
1416	__ret; \
1417	})
1418	#else
1419	#define vrndxh_f16(__p0) __extension__ ({ \	560	#define vrndxh_f16(__p0) __extension__ ({ \
1420	float16_t __s0 = __p0; \	561	float16_t __s0 = __p0; \
1421	float16_t __ret; \	562	float16_t __ret; \
1422	__ret = (float16_t) __builtin_neon_vrndxh_f16(__s0); \	563	__ret = (float16_t) __builtin_neon_vrndxh_f16(__s0); \
1423	__ret; \	564	__ret; \
1424	})	565	})
1425	#endif
1426
1427	#ifdef __LITTLE_ENDIAN__
1428	#define vrsqrteh_f16(__p0) __extension__ ({ \
1429	float16_t __s0 = __p0; \
1430	float16_t __ret; \
1431	__ret = (float16_t) __builtin_neon_vrsqrteh_f16(__s0); \
1432	__ret; \
1433	})
1434	#else
1435	#define vrsqrteh_f16(__p0) __extension__ ({ \	566	#define vrsqrteh_f16(__p0) __extension__ ({ \
1436	float16_t __s0 = __p0; \	567	float16_t __s0 = __p0; \
1437	float16_t __ret; \	568	float16_t __ret; \
1438	__ret = (float16_t) __builtin_neon_vrsqrteh_f16(__s0); \	569	__ret = (float16_t) __builtin_neon_vrsqrteh_f16(__s0); \
1439	__ret; \	570	__ret; \
1440	})	571	})
1441	#endif
1442
1443	#ifdef __LITTLE_ENDIAN__
1444	#define vrsqrtsh_f16(__p0, __p1) __extension__ ({ \
1445	float16_t __s0 = __p0; \
1446	float16_t __s1 = __p1; \
1447	float16_t __ret; \
1448	__ret = (float16_t) __builtin_neon_vrsqrtsh_f16(__s0, __s1); \
1449	__ret; \
1450	})
1451	#else
1452	#define vrsqrtsh_f16(__p0, __p1) __extension__ ({ \	572	#define vrsqrtsh_f16(__p0, __p1) __extension__ ({ \
1453	float16_t __s0 = __p0; \	573	float16_t __s0 = __p0; \
1454	float16_t __s1 = __p1; \	574	float16_t __s1 = __p1; \
...	@@ -1456,33 +576,12 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1456,33 +576,12 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1456	__ret = (float16_t) __builtin_neon_vrsqrtsh_f16(__s0, __s1); \	576	__ret = (float16_t) __builtin_neon_vrsqrtsh_f16(__s0, __s1); \
1457	__ret; \	577	__ret; \
1458	})	578	})
1459	#endif
1460
1461	#ifdef __LITTLE_ENDIAN__
1462	#define vsqrth_f16(__p0) __extension__ ({ \
1463	float16_t __s0 = __p0; \
1464	float16_t __ret; \
1465	__ret = (float16_t) __builtin_neon_vsqrth_f16(__s0); \
1466	__ret; \
1467	})
1468	#else
1469	#define vsqrth_f16(__p0) __extension__ ({ \	579	#define vsqrth_f16(__p0) __extension__ ({ \
1470	float16_t __s0 = __p0; \	580	float16_t __s0 = __p0; \
1471	float16_t __ret; \	581	float16_t __ret; \
1472	__ret = (float16_t) __builtin_neon_vsqrth_f16(__s0); \	582	__ret = (float16_t) __builtin_neon_vsqrth_f16(__s0); \
1473	__ret; \	583	__ret; \
1474	})	584	})
1475	#endif
1476
1477	#ifdef __LITTLE_ENDIAN__
1478	#define vsubh_f16(__p0, __p1) __extension__ ({ \
1479	float16_t __s0 = __p0; \
1480	float16_t __s1 = __p1; \
1481	float16_t __ret; \
1482	__ret = (float16_t) __builtin_neon_vsubh_f16(__s0, __s1); \
1483	__ret; \
1484	})
1485	#else
1486	#define vsubh_f16(__p0, __p1) __extension__ ({ \	585	#define vsubh_f16(__p0, __p1) __extension__ ({ \
1487	float16_t __s0 = __p0; \	586	float16_t __s0 = __p0; \
1488	float16_t __s1 = __p1; \	587	float16_t __s1 = __p1; \
...	@@ -1492,8 +591,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {	...	@@ -1492,8 +591,6 @@ __ai float16_t vcvth_f16_s16(int16_t __p0) {
1492	})	591	})
1493	#endif	592	#endif
1494		593
1495	#endif
1496
1497	#undef __ai	594	#undef __ai
1498		595
1499	#endif /* __ARM_FP16_H */	596	#endif /* __ARM_FP16_H */

lib/include/arm_mve.h created+12563

...	@@ -0,0 +1,12563 @@
1	/*===---- arm_mve.h - ARM MVE intrinsics -----------------------------------===
2	*
3	*
4	* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
5	* See https://llvm.org/LICENSE.txt for license information.
6	* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7	*
8	*===-----------------------------------------------------------------------===
9	*/
10
11	#ifndef __ARM_MVE_H
12	#define __ARM_MVE_H
13
14	#if !__ARM_FEATURE_MVE
15	#error "MVE support not enabled"
16	#endif
17
18	#include <stdint.h>
19
20	typedef uint16_t mve_pred16_t;
21	typedef __attribute__((neon_vector_type(8))) int16_t int16x8_t;
22	typedef struct { int16x8_t val[2]; } int16x8x2_t;
23	typedef struct { int16x8_t val[4]; } int16x8x4_t;
24	typedef __attribute__((neon_vector_type(4))) int32_t int32x4_t;
25	typedef struct { int32x4_t val[2]; } int32x4x2_t;
26	typedef struct { int32x4_t val[4]; } int32x4x4_t;
27	typedef __attribute__((neon_vector_type(2))) int64_t int64x2_t;
28	typedef struct { int64x2_t val[2]; } int64x2x2_t;
29	typedef struct { int64x2_t val[4]; } int64x2x4_t;
30	typedef __attribute__((neon_vector_type(16))) int8_t int8x16_t;
31	typedef struct { int8x16_t val[2]; } int8x16x2_t;
32	typedef struct { int8x16_t val[4]; } int8x16x4_t;
33	typedef __attribute__((neon_vector_type(8))) uint16_t uint16x8_t;
34	typedef struct { uint16x8_t val[2]; } uint16x8x2_t;
35	typedef struct { uint16x8_t val[4]; } uint16x8x4_t;
36	typedef __attribute__((neon_vector_type(4))) uint32_t uint32x4_t;
37	typedef struct { uint32x4_t val[2]; } uint32x4x2_t;
38	typedef struct { uint32x4_t val[4]; } uint32x4x4_t;
39	typedef __attribute__((neon_vector_type(2))) uint64_t uint64x2_t;
40	typedef struct { uint64x2_t val[2]; } uint64x2x2_t;
41	typedef struct { uint64x2_t val[4]; } uint64x2x4_t;
42	typedef __attribute__((neon_vector_type(16))) uint8_t uint8x16_t;
43	typedef struct { uint8x16_t val[2]; } uint8x16x2_t;
44	typedef struct { uint8x16_t val[4]; } uint8x16x4_t;
45
46	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_asrl)))
47	int64_t __arm_asrl(int64_t, int32_t);
48	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_lsll)))
49	uint64_t __arm_lsll(uint64_t, int32_t);
50	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshr)))
51	int32_t __arm_sqrshr(int32_t, int32_t);
52	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshrl)))
53	int64_t __arm_sqrshrl(int64_t, int32_t);
54	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshrl_sat48)))
55	int64_t __arm_sqrshrl_sat48(int64_t, int32_t);
56	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqshl)))
57	int32_t __arm_sqshl(int32_t, int);
58	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqshll)))
59	int64_t __arm_sqshll(int64_t, int);
60	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_srshr)))
61	int32_t __arm_srshr(int32_t, int);
62	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_srshrl)))
63	int64_t __arm_srshrl(int64_t, int);
64	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshl)))
65	uint32_t __arm_uqrshl(uint32_t, int32_t);
66	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshll)))
67	uint64_t __arm_uqrshll(uint64_t, int32_t);
68	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshll_sat48)))
69	uint64_t __arm_uqrshll_sat48(uint64_t, int32_t);
70	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqshl)))
71	uint32_t __arm_uqshl(uint32_t, int);
72	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqshll)))
73	uint64_t __arm_uqshll(uint64_t, int);
74	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_urshr)))
75	uint32_t __arm_urshr(uint32_t, int);
76	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_urshrl)))
77	uint64_t __arm_urshrl(uint64_t, int);
78	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s16)))
79	uint32_t __arm_vabavq_p_s16(uint32_t, int16x8_t, int16x8_t, mve_pred16_t);
80	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s16)))
81	uint32_t __arm_vabavq_p(uint32_t, int16x8_t, int16x8_t, mve_pred16_t);
82	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s32)))
83	uint32_t __arm_vabavq_p_s32(uint32_t, int32x4_t, int32x4_t, mve_pred16_t);
84	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s32)))
85	uint32_t __arm_vabavq_p(uint32_t, int32x4_t, int32x4_t, mve_pred16_t);
86	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s8)))
87	uint32_t __arm_vabavq_p_s8(uint32_t, int8x16_t, int8x16_t, mve_pred16_t);
88	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s8)))
89	uint32_t __arm_vabavq_p(uint32_t, int8x16_t, int8x16_t, mve_pred16_t);
90	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u16)))
91	uint32_t __arm_vabavq_p_u16(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
92	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u16)))
93	uint32_t __arm_vabavq_p(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
94	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u32)))
95	uint32_t __arm_vabavq_p_u32(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
96	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u32)))
97	uint32_t __arm_vabavq_p(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
98	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u8)))
99	uint32_t __arm_vabavq_p_u8(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
100	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u8)))
101	uint32_t __arm_vabavq_p(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
102	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s16)))
103	uint32_t __arm_vabavq_s16(uint32_t, int16x8_t, int16x8_t);
104	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s16)))
105	uint32_t __arm_vabavq(uint32_t, int16x8_t, int16x8_t);
106	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s32)))
107	uint32_t __arm_vabavq_s32(uint32_t, int32x4_t, int32x4_t);
108	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s32)))
109	uint32_t __arm_vabavq(uint32_t, int32x4_t, int32x4_t);
110	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s8)))
111	uint32_t __arm_vabavq_s8(uint32_t, int8x16_t, int8x16_t);
112	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s8)))
113	uint32_t __arm_vabavq(uint32_t, int8x16_t, int8x16_t);
114	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u16)))
115	uint32_t __arm_vabavq_u16(uint32_t, uint16x8_t, uint16x8_t);
116	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u16)))
117	uint32_t __arm_vabavq(uint32_t, uint16x8_t, uint16x8_t);
118	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u32)))
119	uint32_t __arm_vabavq_u32(uint32_t, uint32x4_t, uint32x4_t);
120	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u32)))
121	uint32_t __arm_vabavq(uint32_t, uint32x4_t, uint32x4_t);
122	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u8)))
123	uint32_t __arm_vabavq_u8(uint32_t, uint8x16_t, uint8x16_t);
124	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u8)))
125	uint32_t __arm_vabavq(uint32_t, uint8x16_t, uint8x16_t);
126	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s16)))
127	int16x8_t __arm_vabdq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
128	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s16)))
129	int16x8_t __arm_vabdq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
130	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s32)))
131	int32x4_t __arm_vabdq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
132	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s32)))
133	int32x4_t __arm_vabdq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
134	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s8)))
135	int8x16_t __arm_vabdq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
136	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s8)))
137	int8x16_t __arm_vabdq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
138	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u16)))
139	uint16x8_t __arm_vabdq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
140	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u16)))
141	uint16x8_t __arm_vabdq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
142	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u32)))
143	uint32x4_t __arm_vabdq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
144	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u32)))
145	uint32x4_t __arm_vabdq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
146	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u8)))
147	uint8x16_t __arm_vabdq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
148	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u8)))
149	uint8x16_t __arm_vabdq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
150	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s16)))
151	int16x8_t __arm_vabdq_s16(int16x8_t, int16x8_t);
152	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s16)))
153	int16x8_t __arm_vabdq(int16x8_t, int16x8_t);
154	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s32)))
155	int32x4_t __arm_vabdq_s32(int32x4_t, int32x4_t);
156	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s32)))
157	int32x4_t __arm_vabdq(int32x4_t, int32x4_t);
158	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s8)))
159	int8x16_t __arm_vabdq_s8(int8x16_t, int8x16_t);
160	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s8)))
161	int8x16_t __arm_vabdq(int8x16_t, int8x16_t);
162	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u16)))
163	uint16x8_t __arm_vabdq_u16(uint16x8_t, uint16x8_t);
164	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u16)))
165	uint16x8_t __arm_vabdq(uint16x8_t, uint16x8_t);
166	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u32)))
167	uint32x4_t __arm_vabdq_u32(uint32x4_t, uint32x4_t);
168	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u32)))
169	uint32x4_t __arm_vabdq(uint32x4_t, uint32x4_t);
170	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u8)))
171	uint8x16_t __arm_vabdq_u8(uint8x16_t, uint8x16_t);
172	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u8)))
173	uint8x16_t __arm_vabdq(uint8x16_t, uint8x16_t);
174	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s16)))
175	int16x8_t __arm_vabdq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
176	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s16)))
177	int16x8_t __arm_vabdq_x(int16x8_t, int16x8_t, mve_pred16_t);
178	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s32)))
179	int32x4_t __arm_vabdq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
180	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s32)))
181	int32x4_t __arm_vabdq_x(int32x4_t, int32x4_t, mve_pred16_t);
182	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s8)))
183	int8x16_t __arm_vabdq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
184	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s8)))
185	int8x16_t __arm_vabdq_x(int8x16_t, int8x16_t, mve_pred16_t);
186	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u16)))
187	uint16x8_t __arm_vabdq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
188	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u16)))
189	uint16x8_t __arm_vabdq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
190	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u32)))
191	uint32x4_t __arm_vabdq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
192	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u32)))
193	uint32x4_t __arm_vabdq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
194	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u8)))
195	uint8x16_t __arm_vabdq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
196	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u8)))
197	uint8x16_t __arm_vabdq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
198	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_s32)))
199	int32x4_t __arm_vadciq_m_s32(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
200	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_s32)))
201	int32x4_t __arm_vadciq_m(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
202	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_u32)))
203	uint32x4_t __arm_vadciq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
204	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_u32)))
205	uint32x4_t __arm_vadciq_m(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
206	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_s32)))
207	int32x4_t __arm_vadciq_s32(int32x4_t, int32x4_t, unsigned *);
208	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_s32)))
209	int32x4_t __arm_vadciq(int32x4_t, int32x4_t, unsigned *);
210	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_u32)))
211	uint32x4_t __arm_vadciq_u32(uint32x4_t, uint32x4_t, unsigned *);
212	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_u32)))
213	uint32x4_t __arm_vadciq(uint32x4_t, uint32x4_t, unsigned *);
214	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_s32)))
215	int32x4_t __arm_vadcq_m_s32(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
216	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_s32)))
217	int32x4_t __arm_vadcq_m(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
218	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_u32)))
219	uint32x4_t __arm_vadcq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
220	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_u32)))
221	uint32x4_t __arm_vadcq_m(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
222	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_s32)))
223	int32x4_t __arm_vadcq_s32(int32x4_t, int32x4_t, unsigned *);
224	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_s32)))
225	int32x4_t __arm_vadcq(int32x4_t, int32x4_t, unsigned *);
226	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_u32)))
227	uint32x4_t __arm_vadcq_u32(uint32x4_t, uint32x4_t, unsigned *);
228	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_u32)))
229	uint32x4_t __arm_vadcq(uint32x4_t, uint32x4_t, unsigned *);
230	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s16)))
231	int16x8_t __arm_vaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
232	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s16)))
233	int16x8_t __arm_vaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
234	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s32)))
235	int32x4_t __arm_vaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
236	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s32)))
237	int32x4_t __arm_vaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
238	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s8)))
239	int8x16_t __arm_vaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
240	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s8)))
241	int8x16_t __arm_vaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
242	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u16)))
243	uint16x8_t __arm_vaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
244	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u16)))
245	uint16x8_t __arm_vaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
246	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u32)))
247	uint32x4_t __arm_vaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
248	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u32)))
249	uint32x4_t __arm_vaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
250	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u8)))
251	uint8x16_t __arm_vaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
252	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u8)))
253	uint8x16_t __arm_vaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
254	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s16)))
255	int16x8_t __arm_vaddq_s16(int16x8_t, int16x8_t);
256	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s16)))
257	int16x8_t __arm_vaddq(int16x8_t, int16x8_t);
258	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s32)))
259	int32x4_t __arm_vaddq_s32(int32x4_t, int32x4_t);
260	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s32)))
261	int32x4_t __arm_vaddq(int32x4_t, int32x4_t);
262	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s8)))
263	int8x16_t __arm_vaddq_s8(int8x16_t, int8x16_t);
264	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s8)))
265	int8x16_t __arm_vaddq(int8x16_t, int8x16_t);
266	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u16)))
267	uint16x8_t __arm_vaddq_u16(uint16x8_t, uint16x8_t);
268	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u16)))
269	uint16x8_t __arm_vaddq(uint16x8_t, uint16x8_t);
270	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u32)))
271	uint32x4_t __arm_vaddq_u32(uint32x4_t, uint32x4_t);
272	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u32)))
273	uint32x4_t __arm_vaddq(uint32x4_t, uint32x4_t);
274	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u8)))
275	uint8x16_t __arm_vaddq_u8(uint8x16_t, uint8x16_t);
276	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u8)))
277	uint8x16_t __arm_vaddq(uint8x16_t, uint8x16_t);
278	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s16)))
279	int16x8_t __arm_vaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
280	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s16)))
281	int16x8_t __arm_vaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
282	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s32)))
283	int32x4_t __arm_vaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
284	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s32)))
285	int32x4_t __arm_vaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
286	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s8)))
287	int8x16_t __arm_vaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
288	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s8)))
289	int8x16_t __arm_vaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
290	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u16)))
291	uint16x8_t __arm_vaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
292	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u16)))
293	uint16x8_t __arm_vaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
294	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u32)))
295	uint32x4_t __arm_vaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
296	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u32)))
297	uint32x4_t __arm_vaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
298	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u8)))
299	uint8x16_t __arm_vaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
300	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u8)))
301	uint8x16_t __arm_vaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
302	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s16)))
303	int16x8_t __arm_vandq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
304	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s16)))
305	int16x8_t __arm_vandq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
306	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s32)))
307	int32x4_t __arm_vandq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
308	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s32)))
309	int32x4_t __arm_vandq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
310	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s8)))
311	int8x16_t __arm_vandq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
312	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s8)))
313	int8x16_t __arm_vandq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
314	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u16)))
315	uint16x8_t __arm_vandq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
316	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u16)))
317	uint16x8_t __arm_vandq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
318	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u32)))
319	uint32x4_t __arm_vandq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
320	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u32)))
321	uint32x4_t __arm_vandq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
322	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u8)))
323	uint8x16_t __arm_vandq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
324	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u8)))
325	uint8x16_t __arm_vandq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
326	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s16)))
327	int16x8_t __arm_vandq_s16(int16x8_t, int16x8_t);
328	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s16)))
329	int16x8_t __arm_vandq(int16x8_t, int16x8_t);
330	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s32)))
331	int32x4_t __arm_vandq_s32(int32x4_t, int32x4_t);
332	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s32)))
333	int32x4_t __arm_vandq(int32x4_t, int32x4_t);
334	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s8)))
335	int8x16_t __arm_vandq_s8(int8x16_t, int8x16_t);
336	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s8)))
337	int8x16_t __arm_vandq(int8x16_t, int8x16_t);
338	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u16)))
339	uint16x8_t __arm_vandq_u16(uint16x8_t, uint16x8_t);
340	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u16)))
341	uint16x8_t __arm_vandq(uint16x8_t, uint16x8_t);
342	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u32)))
343	uint32x4_t __arm_vandq_u32(uint32x4_t, uint32x4_t);
344	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u32)))
345	uint32x4_t __arm_vandq(uint32x4_t, uint32x4_t);
346	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u8)))
347	uint8x16_t __arm_vandq_u8(uint8x16_t, uint8x16_t);
348	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u8)))
349	uint8x16_t __arm_vandq(uint8x16_t, uint8x16_t);
350	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s16)))
351	int16x8_t __arm_vandq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
352	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s16)))
353	int16x8_t __arm_vandq_x(int16x8_t, int16x8_t, mve_pred16_t);
354	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s32)))
355	int32x4_t __arm_vandq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
356	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s32)))
357	int32x4_t __arm_vandq_x(int32x4_t, int32x4_t, mve_pred16_t);
358	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s8)))
359	int8x16_t __arm_vandq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
360	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s8)))
361	int8x16_t __arm_vandq_x(int8x16_t, int8x16_t, mve_pred16_t);
362	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u16)))
363	uint16x8_t __arm_vandq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
364	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u16)))
365	uint16x8_t __arm_vandq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
366	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u32)))
367	uint32x4_t __arm_vandq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
368	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u32)))
369	uint32x4_t __arm_vandq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
370	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u8)))
371	uint8x16_t __arm_vandq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
372	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u8)))
373	uint8x16_t __arm_vandq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
374	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s16)))
375	int16x8_t __arm_vbicq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
376	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s16)))
377	int16x8_t __arm_vbicq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
378	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s32)))
379	int32x4_t __arm_vbicq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
380	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s32)))
381	int32x4_t __arm_vbicq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
382	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s8)))
383	int8x16_t __arm_vbicq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
384	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s8)))
385	int8x16_t __arm_vbicq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
386	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u16)))
387	uint16x8_t __arm_vbicq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
388	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u16)))
389	uint16x8_t __arm_vbicq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
390	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u32)))
391	uint32x4_t __arm_vbicq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
392	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u32)))
393	uint32x4_t __arm_vbicq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
394	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u8)))
395	uint8x16_t __arm_vbicq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
396	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u8)))
397	uint8x16_t __arm_vbicq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
398	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s16)))
399	int16x8_t __arm_vbicq_s16(int16x8_t, int16x8_t);
400	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s16)))
401	int16x8_t __arm_vbicq(int16x8_t, int16x8_t);
402	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s32)))
403	int32x4_t __arm_vbicq_s32(int32x4_t, int32x4_t);
404	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s32)))
405	int32x4_t __arm_vbicq(int32x4_t, int32x4_t);
406	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s8)))
407	int8x16_t __arm_vbicq_s8(int8x16_t, int8x16_t);
408	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s8)))
409	int8x16_t __arm_vbicq(int8x16_t, int8x16_t);
410	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u16)))
411	uint16x8_t __arm_vbicq_u16(uint16x8_t, uint16x8_t);
412	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u16)))
413	uint16x8_t __arm_vbicq(uint16x8_t, uint16x8_t);
414	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u32)))
415	uint32x4_t __arm_vbicq_u32(uint32x4_t, uint32x4_t);
416	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u32)))
417	uint32x4_t __arm_vbicq(uint32x4_t, uint32x4_t);
418	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u8)))
419	uint8x16_t __arm_vbicq_u8(uint8x16_t, uint8x16_t);
420	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u8)))
421	uint8x16_t __arm_vbicq(uint8x16_t, uint8x16_t);
422	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s16)))
423	int16x8_t __arm_vbicq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
424	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s16)))
425	int16x8_t __arm_vbicq_x(int16x8_t, int16x8_t, mve_pred16_t);
426	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s32)))
427	int32x4_t __arm_vbicq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
428	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s32)))
429	int32x4_t __arm_vbicq_x(int32x4_t, int32x4_t, mve_pred16_t);
430	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s8)))
431	int8x16_t __arm_vbicq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
432	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s8)))
433	int8x16_t __arm_vbicq_x(int8x16_t, int8x16_t, mve_pred16_t);
434	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u16)))
435	uint16x8_t __arm_vbicq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
436	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u16)))
437	uint16x8_t __arm_vbicq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
438	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u32)))
439	uint32x4_t __arm_vbicq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
440	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u32)))
441	uint32x4_t __arm_vbicq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
442	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u8)))
443	uint8x16_t __arm_vbicq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
444	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u8)))
445	uint8x16_t __arm_vbicq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
446	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s16)))
447	int16x8_t __arm_vcaddq_rot270_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
448	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s16)))
449	int16x8_t __arm_vcaddq_rot270_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
450	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s32)))
451	int32x4_t __arm_vcaddq_rot270_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
452	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s32)))
453	int32x4_t __arm_vcaddq_rot270_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
454	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s8)))
455	int8x16_t __arm_vcaddq_rot270_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
456	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s8)))
457	int8x16_t __arm_vcaddq_rot270_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
458	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u16)))
459	uint16x8_t __arm_vcaddq_rot270_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
460	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u16)))
461	uint16x8_t __arm_vcaddq_rot270_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
462	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u32)))
463	uint32x4_t __arm_vcaddq_rot270_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
464	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u32)))
465	uint32x4_t __arm_vcaddq_rot270_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
466	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u8)))
467	uint8x16_t __arm_vcaddq_rot270_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
468	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u8)))
469	uint8x16_t __arm_vcaddq_rot270_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
470	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s16)))
471	int16x8_t __arm_vcaddq_rot270_s16(int16x8_t, int16x8_t);
472	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s16)))
473	int16x8_t __arm_vcaddq_rot270(int16x8_t, int16x8_t);
474	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s32)))
475	int32x4_t __arm_vcaddq_rot270_s32(int32x4_t, int32x4_t);
476	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s32)))
477	int32x4_t __arm_vcaddq_rot270(int32x4_t, int32x4_t);
478	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s8)))
479	int8x16_t __arm_vcaddq_rot270_s8(int8x16_t, int8x16_t);
480	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s8)))
481	int8x16_t __arm_vcaddq_rot270(int8x16_t, int8x16_t);
482	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u16)))
483	uint16x8_t __arm_vcaddq_rot270_u16(uint16x8_t, uint16x8_t);
484	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u16)))
485	uint16x8_t __arm_vcaddq_rot270(uint16x8_t, uint16x8_t);
486	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u32)))
487	uint32x4_t __arm_vcaddq_rot270_u32(uint32x4_t, uint32x4_t);
488	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u32)))
489	uint32x4_t __arm_vcaddq_rot270(uint32x4_t, uint32x4_t);
490	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u8)))
491	uint8x16_t __arm_vcaddq_rot270_u8(uint8x16_t, uint8x16_t);
492	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u8)))
493	uint8x16_t __arm_vcaddq_rot270(uint8x16_t, uint8x16_t);
494	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s16)))
495	int16x8_t __arm_vcaddq_rot270_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
496	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s16)))
497	int16x8_t __arm_vcaddq_rot270_x(int16x8_t, int16x8_t, mve_pred16_t);
498	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s32)))
499	int32x4_t __arm_vcaddq_rot270_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
500	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s32)))
501	int32x4_t __arm_vcaddq_rot270_x(int32x4_t, int32x4_t, mve_pred16_t);
502	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s8)))
503	int8x16_t __arm_vcaddq_rot270_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
504	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s8)))
505	int8x16_t __arm_vcaddq_rot270_x(int8x16_t, int8x16_t, mve_pred16_t);
506	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u16)))
507	uint16x8_t __arm_vcaddq_rot270_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
508	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u16)))
509	uint16x8_t __arm_vcaddq_rot270_x(uint16x8_t, uint16x8_t, mve_pred16_t);
510	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u32)))
511	uint32x4_t __arm_vcaddq_rot270_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
512	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u32)))
513	uint32x4_t __arm_vcaddq_rot270_x(uint32x4_t, uint32x4_t, mve_pred16_t);
514	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u8)))
515	uint8x16_t __arm_vcaddq_rot270_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
516	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u8)))
517	uint8x16_t __arm_vcaddq_rot270_x(uint8x16_t, uint8x16_t, mve_pred16_t);
518	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s16)))
519	int16x8_t __arm_vcaddq_rot90_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
520	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s16)))
521	int16x8_t __arm_vcaddq_rot90_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
522	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s32)))
523	int32x4_t __arm_vcaddq_rot90_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
524	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s32)))
525	int32x4_t __arm_vcaddq_rot90_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
526	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s8)))
527	int8x16_t __arm_vcaddq_rot90_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
528	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s8)))
529	int8x16_t __arm_vcaddq_rot90_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
530	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u16)))
531	uint16x8_t __arm_vcaddq_rot90_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
532	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u16)))
533	uint16x8_t __arm_vcaddq_rot90_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
534	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u32)))
535	uint32x4_t __arm_vcaddq_rot90_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
536	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u32)))
537	uint32x4_t __arm_vcaddq_rot90_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
538	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u8)))
539	uint8x16_t __arm_vcaddq_rot90_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
540	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u8)))
541	uint8x16_t __arm_vcaddq_rot90_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
542	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s16)))
543	int16x8_t __arm_vcaddq_rot90_s16(int16x8_t, int16x8_t);
544	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s16)))
545	int16x8_t __arm_vcaddq_rot90(int16x8_t, int16x8_t);
546	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s32)))
547	int32x4_t __arm_vcaddq_rot90_s32(int32x4_t, int32x4_t);
548	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s32)))
549	int32x4_t __arm_vcaddq_rot90(int32x4_t, int32x4_t);
550	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s8)))
551	int8x16_t __arm_vcaddq_rot90_s8(int8x16_t, int8x16_t);
552	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s8)))
553	int8x16_t __arm_vcaddq_rot90(int8x16_t, int8x16_t);
554	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u16)))
555	uint16x8_t __arm_vcaddq_rot90_u16(uint16x8_t, uint16x8_t);
556	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u16)))
557	uint16x8_t __arm_vcaddq_rot90(uint16x8_t, uint16x8_t);
558	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u32)))
559	uint32x4_t __arm_vcaddq_rot90_u32(uint32x4_t, uint32x4_t);
560	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u32)))
561	uint32x4_t __arm_vcaddq_rot90(uint32x4_t, uint32x4_t);
562	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u8)))
563	uint8x16_t __arm_vcaddq_rot90_u8(uint8x16_t, uint8x16_t);
564	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u8)))
565	uint8x16_t __arm_vcaddq_rot90(uint8x16_t, uint8x16_t);
566	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s16)))
567	int16x8_t __arm_vcaddq_rot90_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
568	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s16)))
569	int16x8_t __arm_vcaddq_rot90_x(int16x8_t, int16x8_t, mve_pred16_t);
570	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s32)))
571	int32x4_t __arm_vcaddq_rot90_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
572	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s32)))
573	int32x4_t __arm_vcaddq_rot90_x(int32x4_t, int32x4_t, mve_pred16_t);
574	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s8)))
575	int8x16_t __arm_vcaddq_rot90_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
576	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s8)))
577	int8x16_t __arm_vcaddq_rot90_x(int8x16_t, int8x16_t, mve_pred16_t);
578	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u16)))
579	uint16x8_t __arm_vcaddq_rot90_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
580	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u16)))
581	uint16x8_t __arm_vcaddq_rot90_x(uint16x8_t, uint16x8_t, mve_pred16_t);
582	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u32)))
583	uint32x4_t __arm_vcaddq_rot90_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
584	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u32)))
585	uint32x4_t __arm_vcaddq_rot90_x(uint32x4_t, uint32x4_t, mve_pred16_t);
586	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u8)))
587	uint8x16_t __arm_vcaddq_rot90_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
588	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u8)))
589	uint8x16_t __arm_vcaddq_rot90_x(uint8x16_t, uint8x16_t, mve_pred16_t);
590	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u16)))
591	mve_pred16_t __arm_vcmpcsq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
592	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u16)))
593	mve_pred16_t __arm_vcmpcsq_m(uint16x8_t, uint16_t, mve_pred16_t);
594	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u32)))
595	mve_pred16_t __arm_vcmpcsq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
596	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u32)))
597	mve_pred16_t __arm_vcmpcsq_m(uint32x4_t, uint32_t, mve_pred16_t);
598	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u8)))
599	mve_pred16_t __arm_vcmpcsq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
600	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u8)))
601	mve_pred16_t __arm_vcmpcsq_m(uint8x16_t, uint8_t, mve_pred16_t);
602	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u16)))
603	mve_pred16_t __arm_vcmpcsq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
604	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u16)))
605	mve_pred16_t __arm_vcmpcsq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
606	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u32)))
607	mve_pred16_t __arm_vcmpcsq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
608	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u32)))
609	mve_pred16_t __arm_vcmpcsq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
610	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u8)))
611	mve_pred16_t __arm_vcmpcsq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
612	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u8)))
613	mve_pred16_t __arm_vcmpcsq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
614	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u16)))
615	mve_pred16_t __arm_vcmpcsq_n_u16(uint16x8_t, uint16_t);
616	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u16)))
617	mve_pred16_t __arm_vcmpcsq(uint16x8_t, uint16_t);
618	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u32)))
619	mve_pred16_t __arm_vcmpcsq_n_u32(uint32x4_t, uint32_t);
620	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u32)))
621	mve_pred16_t __arm_vcmpcsq(uint32x4_t, uint32_t);
622	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u8)))
623	mve_pred16_t __arm_vcmpcsq_n_u8(uint8x16_t, uint8_t);
624	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u8)))
625	mve_pred16_t __arm_vcmpcsq(uint8x16_t, uint8_t);
626	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u16)))
627	mve_pred16_t __arm_vcmpcsq_u16(uint16x8_t, uint16x8_t);
628	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u16)))
629	mve_pred16_t __arm_vcmpcsq(uint16x8_t, uint16x8_t);
630	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u32)))
631	mve_pred16_t __arm_vcmpcsq_u32(uint32x4_t, uint32x4_t);
632	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u32)))
633	mve_pred16_t __arm_vcmpcsq(uint32x4_t, uint32x4_t);
634	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u8)))
635	mve_pred16_t __arm_vcmpcsq_u8(uint8x16_t, uint8x16_t);
636	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u8)))
637	mve_pred16_t __arm_vcmpcsq(uint8x16_t, uint8x16_t);
638	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s16)))
639	mve_pred16_t __arm_vcmpeqq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
640	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s16)))
641	mve_pred16_t __arm_vcmpeqq_m(int16x8_t, int16_t, mve_pred16_t);
642	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s32)))
643	mve_pred16_t __arm_vcmpeqq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
644	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s32)))
645	mve_pred16_t __arm_vcmpeqq_m(int32x4_t, int32_t, mve_pred16_t);
646	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s8)))
647	mve_pred16_t __arm_vcmpeqq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
648	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s8)))
649	mve_pred16_t __arm_vcmpeqq_m(int8x16_t, int8_t, mve_pred16_t);
650	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u16)))
651	mve_pred16_t __arm_vcmpeqq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
652	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u16)))
653	mve_pred16_t __arm_vcmpeqq_m(uint16x8_t, uint16_t, mve_pred16_t);
654	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u32)))
655	mve_pred16_t __arm_vcmpeqq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
656	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u32)))
657	mve_pred16_t __arm_vcmpeqq_m(uint32x4_t, uint32_t, mve_pred16_t);
658	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u8)))
659	mve_pred16_t __arm_vcmpeqq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
660	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u8)))
661	mve_pred16_t __arm_vcmpeqq_m(uint8x16_t, uint8_t, mve_pred16_t);
662	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s16)))
663	mve_pred16_t __arm_vcmpeqq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
664	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s16)))
665	mve_pred16_t __arm_vcmpeqq_m(int16x8_t, int16x8_t, mve_pred16_t);
666	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s32)))
667	mve_pred16_t __arm_vcmpeqq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
668	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s32)))
669	mve_pred16_t __arm_vcmpeqq_m(int32x4_t, int32x4_t, mve_pred16_t);
670	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s8)))
671	mve_pred16_t __arm_vcmpeqq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
672	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s8)))
673	mve_pred16_t __arm_vcmpeqq_m(int8x16_t, int8x16_t, mve_pred16_t);
674	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u16)))
675	mve_pred16_t __arm_vcmpeqq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
676	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u16)))
677	mve_pred16_t __arm_vcmpeqq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
678	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u32)))
679	mve_pred16_t __arm_vcmpeqq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
680	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u32)))
681	mve_pred16_t __arm_vcmpeqq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
682	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u8)))
683	mve_pred16_t __arm_vcmpeqq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
684	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u8)))
685	mve_pred16_t __arm_vcmpeqq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
686	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s16)))
687	mve_pred16_t __arm_vcmpeqq_n_s16(int16x8_t, int16_t);
688	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s16)))
689	mve_pred16_t __arm_vcmpeqq(int16x8_t, int16_t);
690	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s32)))
691	mve_pred16_t __arm_vcmpeqq_n_s32(int32x4_t, int32_t);
692	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s32)))
693	mve_pred16_t __arm_vcmpeqq(int32x4_t, int32_t);
694	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s8)))
695	mve_pred16_t __arm_vcmpeqq_n_s8(int8x16_t, int8_t);
696	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s8)))
697	mve_pred16_t __arm_vcmpeqq(int8x16_t, int8_t);
698	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u16)))
699	mve_pred16_t __arm_vcmpeqq_n_u16(uint16x8_t, uint16_t);
700	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u16)))
701	mve_pred16_t __arm_vcmpeqq(uint16x8_t, uint16_t);
702	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u32)))
703	mve_pred16_t __arm_vcmpeqq_n_u32(uint32x4_t, uint32_t);
704	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u32)))
705	mve_pred16_t __arm_vcmpeqq(uint32x4_t, uint32_t);
706	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u8)))
707	mve_pred16_t __arm_vcmpeqq_n_u8(uint8x16_t, uint8_t);
708	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u8)))
709	mve_pred16_t __arm_vcmpeqq(uint8x16_t, uint8_t);
710	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s16)))
711	mve_pred16_t __arm_vcmpeqq_s16(int16x8_t, int16x8_t);
712	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s16)))
713	mve_pred16_t __arm_vcmpeqq(int16x8_t, int16x8_t);
714	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s32)))
715	mve_pred16_t __arm_vcmpeqq_s32(int32x4_t, int32x4_t);
716	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s32)))
717	mve_pred16_t __arm_vcmpeqq(int32x4_t, int32x4_t);
718	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s8)))
719	mve_pred16_t __arm_vcmpeqq_s8(int8x16_t, int8x16_t);
720	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s8)))
721	mve_pred16_t __arm_vcmpeqq(int8x16_t, int8x16_t);
722	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u16)))
723	mve_pred16_t __arm_vcmpeqq_u16(uint16x8_t, uint16x8_t);
724	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u16)))
725	mve_pred16_t __arm_vcmpeqq(uint16x8_t, uint16x8_t);
726	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u32)))
727	mve_pred16_t __arm_vcmpeqq_u32(uint32x4_t, uint32x4_t);
728	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u32)))
729	mve_pred16_t __arm_vcmpeqq(uint32x4_t, uint32x4_t);
730	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u8)))
731	mve_pred16_t __arm_vcmpeqq_u8(uint8x16_t, uint8x16_t);
732	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u8)))
733	mve_pred16_t __arm_vcmpeqq(uint8x16_t, uint8x16_t);
734	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s16)))
735	mve_pred16_t __arm_vcmpgeq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
736	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s16)))
737	mve_pred16_t __arm_vcmpgeq_m(int16x8_t, int16_t, mve_pred16_t);
738	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s32)))
739	mve_pred16_t __arm_vcmpgeq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
740	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s32)))
741	mve_pred16_t __arm_vcmpgeq_m(int32x4_t, int32_t, mve_pred16_t);
742	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s8)))
743	mve_pred16_t __arm_vcmpgeq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
744	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s8)))
745	mve_pred16_t __arm_vcmpgeq_m(int8x16_t, int8_t, mve_pred16_t);
746	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s16)))
747	mve_pred16_t __arm_vcmpgeq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
748	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s16)))
749	mve_pred16_t __arm_vcmpgeq_m(int16x8_t, int16x8_t, mve_pred16_t);
750	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s32)))
751	mve_pred16_t __arm_vcmpgeq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
752	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s32)))
753	mve_pred16_t __arm_vcmpgeq_m(int32x4_t, int32x4_t, mve_pred16_t);
754	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s8)))
755	mve_pred16_t __arm_vcmpgeq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
756	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s8)))
757	mve_pred16_t __arm_vcmpgeq_m(int8x16_t, int8x16_t, mve_pred16_t);
758	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s16)))
759	mve_pred16_t __arm_vcmpgeq_n_s16(int16x8_t, int16_t);
760	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s16)))
761	mve_pred16_t __arm_vcmpgeq(int16x8_t, int16_t);
762	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s32)))
763	mve_pred16_t __arm_vcmpgeq_n_s32(int32x4_t, int32_t);
764	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s32)))
765	mve_pred16_t __arm_vcmpgeq(int32x4_t, int32_t);
766	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s8)))
767	mve_pred16_t __arm_vcmpgeq_n_s8(int8x16_t, int8_t);
768	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s8)))
769	mve_pred16_t __arm_vcmpgeq(int8x16_t, int8_t);
770	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s16)))
771	mve_pred16_t __arm_vcmpgeq_s16(int16x8_t, int16x8_t);
772	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s16)))
773	mve_pred16_t __arm_vcmpgeq(int16x8_t, int16x8_t);
774	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s32)))
775	mve_pred16_t __arm_vcmpgeq_s32(int32x4_t, int32x4_t);
776	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s32)))
777	mve_pred16_t __arm_vcmpgeq(int32x4_t, int32x4_t);
778	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s8)))
779	mve_pred16_t __arm_vcmpgeq_s8(int8x16_t, int8x16_t);
780	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s8)))
781	mve_pred16_t __arm_vcmpgeq(int8x16_t, int8x16_t);
782	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s16)))
783	mve_pred16_t __arm_vcmpgtq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
784	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s16)))
785	mve_pred16_t __arm_vcmpgtq_m(int16x8_t, int16_t, mve_pred16_t);
786	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s32)))
787	mve_pred16_t __arm_vcmpgtq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
788	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s32)))
789	mve_pred16_t __arm_vcmpgtq_m(int32x4_t, int32_t, mve_pred16_t);
790	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s8)))
791	mve_pred16_t __arm_vcmpgtq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
792	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s8)))
793	mve_pred16_t __arm_vcmpgtq_m(int8x16_t, int8_t, mve_pred16_t);
794	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s16)))
795	mve_pred16_t __arm_vcmpgtq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
796	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s16)))
797	mve_pred16_t __arm_vcmpgtq_m(int16x8_t, int16x8_t, mve_pred16_t);
798	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s32)))
799	mve_pred16_t __arm_vcmpgtq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
800	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s32)))
801	mve_pred16_t __arm_vcmpgtq_m(int32x4_t, int32x4_t, mve_pred16_t);
802	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s8)))
803	mve_pred16_t __arm_vcmpgtq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
804	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s8)))
805	mve_pred16_t __arm_vcmpgtq_m(int8x16_t, int8x16_t, mve_pred16_t);
806	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s16)))
807	mve_pred16_t __arm_vcmpgtq_n_s16(int16x8_t, int16_t);
808	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s16)))
809	mve_pred16_t __arm_vcmpgtq(int16x8_t, int16_t);
810	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s32)))
811	mve_pred16_t __arm_vcmpgtq_n_s32(int32x4_t, int32_t);
812	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s32)))
813	mve_pred16_t __arm_vcmpgtq(int32x4_t, int32_t);
814	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s8)))
815	mve_pred16_t __arm_vcmpgtq_n_s8(int8x16_t, int8_t);
816	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s8)))
817	mve_pred16_t __arm_vcmpgtq(int8x16_t, int8_t);
818	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s16)))
819	mve_pred16_t __arm_vcmpgtq_s16(int16x8_t, int16x8_t);
820	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s16)))
821	mve_pred16_t __arm_vcmpgtq(int16x8_t, int16x8_t);
822	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s32)))
823	mve_pred16_t __arm_vcmpgtq_s32(int32x4_t, int32x4_t);
824	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s32)))
825	mve_pred16_t __arm_vcmpgtq(int32x4_t, int32x4_t);
826	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s8)))
827	mve_pred16_t __arm_vcmpgtq_s8(int8x16_t, int8x16_t);
828	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s8)))
829	mve_pred16_t __arm_vcmpgtq(int8x16_t, int8x16_t);
830	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u16)))
831	mve_pred16_t __arm_vcmphiq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
832	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u16)))
833	mve_pred16_t __arm_vcmphiq_m(uint16x8_t, uint16_t, mve_pred16_t);
834	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u32)))
835	mve_pred16_t __arm_vcmphiq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
836	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u32)))
837	mve_pred16_t __arm_vcmphiq_m(uint32x4_t, uint32_t, mve_pred16_t);
838	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u8)))
839	mve_pred16_t __arm_vcmphiq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
840	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u8)))
841	mve_pred16_t __arm_vcmphiq_m(uint8x16_t, uint8_t, mve_pred16_t);
842	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u16)))
843	mve_pred16_t __arm_vcmphiq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
844	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u16)))
845	mve_pred16_t __arm_vcmphiq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
846	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u32)))
847	mve_pred16_t __arm_vcmphiq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
848	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u32)))
849	mve_pred16_t __arm_vcmphiq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
850	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u8)))
851	mve_pred16_t __arm_vcmphiq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
852	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u8)))
853	mve_pred16_t __arm_vcmphiq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
854	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u16)))
855	mve_pred16_t __arm_vcmphiq_n_u16(uint16x8_t, uint16_t);
856	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u16)))
857	mve_pred16_t __arm_vcmphiq(uint16x8_t, uint16_t);
858	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u32)))
859	mve_pred16_t __arm_vcmphiq_n_u32(uint32x4_t, uint32_t);
860	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u32)))
861	mve_pred16_t __arm_vcmphiq(uint32x4_t, uint32_t);
862	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u8)))
863	mve_pred16_t __arm_vcmphiq_n_u8(uint8x16_t, uint8_t);
864	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u8)))
865	mve_pred16_t __arm_vcmphiq(uint8x16_t, uint8_t);
866	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u16)))
867	mve_pred16_t __arm_vcmphiq_u16(uint16x8_t, uint16x8_t);
868	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u16)))
869	mve_pred16_t __arm_vcmphiq(uint16x8_t, uint16x8_t);
870	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u32)))
871	mve_pred16_t __arm_vcmphiq_u32(uint32x4_t, uint32x4_t);
872	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u32)))
873	mve_pred16_t __arm_vcmphiq(uint32x4_t, uint32x4_t);
874	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u8)))
875	mve_pred16_t __arm_vcmphiq_u8(uint8x16_t, uint8x16_t);
876	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u8)))
877	mve_pred16_t __arm_vcmphiq(uint8x16_t, uint8x16_t);
878	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s16)))
879	mve_pred16_t __arm_vcmpleq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
880	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s16)))
881	mve_pred16_t __arm_vcmpleq_m(int16x8_t, int16_t, mve_pred16_t);
882	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s32)))
883	mve_pred16_t __arm_vcmpleq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
884	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s32)))
885	mve_pred16_t __arm_vcmpleq_m(int32x4_t, int32_t, mve_pred16_t);
886	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s8)))
887	mve_pred16_t __arm_vcmpleq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
888	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s8)))
889	mve_pred16_t __arm_vcmpleq_m(int8x16_t, int8_t, mve_pred16_t);
890	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s16)))
891	mve_pred16_t __arm_vcmpleq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
892	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s16)))
893	mve_pred16_t __arm_vcmpleq_m(int16x8_t, int16x8_t, mve_pred16_t);
894	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s32)))
895	mve_pred16_t __arm_vcmpleq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
896	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s32)))
897	mve_pred16_t __arm_vcmpleq_m(int32x4_t, int32x4_t, mve_pred16_t);
898	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s8)))
899	mve_pred16_t __arm_vcmpleq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
900	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s8)))
901	mve_pred16_t __arm_vcmpleq_m(int8x16_t, int8x16_t, mve_pred16_t);
902	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s16)))
903	mve_pred16_t __arm_vcmpleq_n_s16(int16x8_t, int16_t);
904	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s16)))
905	mve_pred16_t __arm_vcmpleq(int16x8_t, int16_t);
906	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s32)))
907	mve_pred16_t __arm_vcmpleq_n_s32(int32x4_t, int32_t);
908	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s32)))
909	mve_pred16_t __arm_vcmpleq(int32x4_t, int32_t);
910	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s8)))
911	mve_pred16_t __arm_vcmpleq_n_s8(int8x16_t, int8_t);
912	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s8)))
913	mve_pred16_t __arm_vcmpleq(int8x16_t, int8_t);
914	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s16)))
915	mve_pred16_t __arm_vcmpleq_s16(int16x8_t, int16x8_t);
916	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s16)))
917	mve_pred16_t __arm_vcmpleq(int16x8_t, int16x8_t);
918	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s32)))
919	mve_pred16_t __arm_vcmpleq_s32(int32x4_t, int32x4_t);
920	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s32)))
921	mve_pred16_t __arm_vcmpleq(int32x4_t, int32x4_t);
922	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s8)))
923	mve_pred16_t __arm_vcmpleq_s8(int8x16_t, int8x16_t);
924	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s8)))
925	mve_pred16_t __arm_vcmpleq(int8x16_t, int8x16_t);
926	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s16)))
927	mve_pred16_t __arm_vcmpltq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
928	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s16)))
929	mve_pred16_t __arm_vcmpltq_m(int16x8_t, int16_t, mve_pred16_t);
930	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s32)))
931	mve_pred16_t __arm_vcmpltq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
932	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s32)))
933	mve_pred16_t __arm_vcmpltq_m(int32x4_t, int32_t, mve_pred16_t);
934	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s8)))
935	mve_pred16_t __arm_vcmpltq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
936	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s8)))
937	mve_pred16_t __arm_vcmpltq_m(int8x16_t, int8_t, mve_pred16_t);
938	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s16)))
939	mve_pred16_t __arm_vcmpltq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
940	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s16)))
941	mve_pred16_t __arm_vcmpltq_m(int16x8_t, int16x8_t, mve_pred16_t);
942	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s32)))
943	mve_pred16_t __arm_vcmpltq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
944	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s32)))
945	mve_pred16_t __arm_vcmpltq_m(int32x4_t, int32x4_t, mve_pred16_t);
946	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s8)))
947	mve_pred16_t __arm_vcmpltq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
948	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s8)))
949	mve_pred16_t __arm_vcmpltq_m(int8x16_t, int8x16_t, mve_pred16_t);
950	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s16)))
951	mve_pred16_t __arm_vcmpltq_n_s16(int16x8_t, int16_t);
952	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s16)))
953	mve_pred16_t __arm_vcmpltq(int16x8_t, int16_t);
954	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s32)))
955	mve_pred16_t __arm_vcmpltq_n_s32(int32x4_t, int32_t);
956	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s32)))
957	mve_pred16_t __arm_vcmpltq(int32x4_t, int32_t);
958	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s8)))
959	mve_pred16_t __arm_vcmpltq_n_s8(int8x16_t, int8_t);
960	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s8)))
961	mve_pred16_t __arm_vcmpltq(int8x16_t, int8_t);
962	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s16)))
963	mve_pred16_t __arm_vcmpltq_s16(int16x8_t, int16x8_t);
964	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s16)))
965	mve_pred16_t __arm_vcmpltq(int16x8_t, int16x8_t);
966	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s32)))
967	mve_pred16_t __arm_vcmpltq_s32(int32x4_t, int32x4_t);
968	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s32)))
969	mve_pred16_t __arm_vcmpltq(int32x4_t, int32x4_t);
970	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s8)))
971	mve_pred16_t __arm_vcmpltq_s8(int8x16_t, int8x16_t);
972	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s8)))
973	mve_pred16_t __arm_vcmpltq(int8x16_t, int8x16_t);
974	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s16)))
975	mve_pred16_t __arm_vcmpneq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
976	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s16)))
977	mve_pred16_t __arm_vcmpneq_m(int16x8_t, int16_t, mve_pred16_t);
978	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s32)))
979	mve_pred16_t __arm_vcmpneq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
980	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s32)))
981	mve_pred16_t __arm_vcmpneq_m(int32x4_t, int32_t, mve_pred16_t);
982	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s8)))
983	mve_pred16_t __arm_vcmpneq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
984	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s8)))
985	mve_pred16_t __arm_vcmpneq_m(int8x16_t, int8_t, mve_pred16_t);
986	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u16)))
987	mve_pred16_t __arm_vcmpneq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
988	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u16)))
989	mve_pred16_t __arm_vcmpneq_m(uint16x8_t, uint16_t, mve_pred16_t);
990	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u32)))
991	mve_pred16_t __arm_vcmpneq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
992	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u32)))
993	mve_pred16_t __arm_vcmpneq_m(uint32x4_t, uint32_t, mve_pred16_t);
994	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u8)))
995	mve_pred16_t __arm_vcmpneq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
996	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u8)))
997	mve_pred16_t __arm_vcmpneq_m(uint8x16_t, uint8_t, mve_pred16_t);
998	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s16)))
999	mve_pred16_t __arm_vcmpneq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
1000	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s16)))
1001	mve_pred16_t __arm_vcmpneq_m(int16x8_t, int16x8_t, mve_pred16_t);
1002	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s32)))
1003	mve_pred16_t __arm_vcmpneq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
1004	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s32)))
1005	mve_pred16_t __arm_vcmpneq_m(int32x4_t, int32x4_t, mve_pred16_t);
1006	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s8)))
1007	mve_pred16_t __arm_vcmpneq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
1008	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s8)))
1009	mve_pred16_t __arm_vcmpneq_m(int8x16_t, int8x16_t, mve_pred16_t);
1010	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u16)))
1011	mve_pred16_t __arm_vcmpneq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1012	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u16)))
1013	mve_pred16_t __arm_vcmpneq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
1014	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u32)))
1015	mve_pred16_t __arm_vcmpneq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1016	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u32)))
1017	mve_pred16_t __arm_vcmpneq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
1018	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u8)))
1019	mve_pred16_t __arm_vcmpneq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1020	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u8)))
1021	mve_pred16_t __arm_vcmpneq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
1022	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s16)))
1023	mve_pred16_t __arm_vcmpneq_n_s16(int16x8_t, int16_t);
1024	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s16)))
1025	mve_pred16_t __arm_vcmpneq(int16x8_t, int16_t);
1026	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s32)))
1027	mve_pred16_t __arm_vcmpneq_n_s32(int32x4_t, int32_t);
1028	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s32)))
1029	mve_pred16_t __arm_vcmpneq(int32x4_t, int32_t);
1030	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s8)))
1031	mve_pred16_t __arm_vcmpneq_n_s8(int8x16_t, int8_t);
1032	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s8)))
1033	mve_pred16_t __arm_vcmpneq(int8x16_t, int8_t);
1034	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u16)))
1035	mve_pred16_t __arm_vcmpneq_n_u16(uint16x8_t, uint16_t);
1036	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u16)))
1037	mve_pred16_t __arm_vcmpneq(uint16x8_t, uint16_t);
1038	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u32)))
1039	mve_pred16_t __arm_vcmpneq_n_u32(uint32x4_t, uint32_t);
1040	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u32)))
1041	mve_pred16_t __arm_vcmpneq(uint32x4_t, uint32_t);
1042	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u8)))
1043	mve_pred16_t __arm_vcmpneq_n_u8(uint8x16_t, uint8_t);
1044	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u8)))
1045	mve_pred16_t __arm_vcmpneq(uint8x16_t, uint8_t);
1046	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s16)))
1047	mve_pred16_t __arm_vcmpneq_s16(int16x8_t, int16x8_t);
1048	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s16)))
1049	mve_pred16_t __arm_vcmpneq(int16x8_t, int16x8_t);
1050	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s32)))
1051	mve_pred16_t __arm_vcmpneq_s32(int32x4_t, int32x4_t);
1052	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s32)))
1053	mve_pred16_t __arm_vcmpneq(int32x4_t, int32x4_t);
1054	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s8)))
1055	mve_pred16_t __arm_vcmpneq_s8(int8x16_t, int8x16_t);
1056	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s8)))
1057	mve_pred16_t __arm_vcmpneq(int8x16_t, int8x16_t);
1058	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u16)))
1059	mve_pred16_t __arm_vcmpneq_u16(uint16x8_t, uint16x8_t);
1060	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u16)))
1061	mve_pred16_t __arm_vcmpneq(uint16x8_t, uint16x8_t);
1062	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u32)))
1063	mve_pred16_t __arm_vcmpneq_u32(uint32x4_t, uint32x4_t);
1064	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u32)))
1065	mve_pred16_t __arm_vcmpneq(uint32x4_t, uint32x4_t);
1066	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u8)))
1067	mve_pred16_t __arm_vcmpneq_u8(uint8x16_t, uint8x16_t);
1068	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u8)))
1069	mve_pred16_t __arm_vcmpneq(uint8x16_t, uint8x16_t);
1070	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s16)))
1071	int16x8_t __arm_vcreateq_s16(uint64_t, uint64_t);
1072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s32)))
1073	int32x4_t __arm_vcreateq_s32(uint64_t, uint64_t);
1074	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s64)))
1075	int64x2_t __arm_vcreateq_s64(uint64_t, uint64_t);
1076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s8)))
1077	int8x16_t __arm_vcreateq_s8(uint64_t, uint64_t);
1078	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u16)))
1079	uint16x8_t __arm_vcreateq_u16(uint64_t, uint64_t);
1080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u32)))
1081	uint32x4_t __arm_vcreateq_u32(uint64_t, uint64_t);
1082	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u64)))
1083	uint64x2_t __arm_vcreateq_u64(uint64_t, uint64_t);
1084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u8)))
1085	uint8x16_t __arm_vcreateq_u8(uint64_t, uint64_t);
1086	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp16q)))
1087	mve_pred16_t __arm_vctp16q(uint32_t);
1088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp16q_m)))
1089	mve_pred16_t __arm_vctp16q_m(uint32_t, mve_pred16_t);
1090	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp32q)))
1091	mve_pred16_t __arm_vctp32q(uint32_t);
1092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp32q_m)))
1093	mve_pred16_t __arm_vctp32q_m(uint32_t, mve_pred16_t);
1094	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp64q)))
1095	mve_pred16_t __arm_vctp64q(uint32_t);
1096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp64q_m)))
1097	mve_pred16_t __arm_vctp64q_m(uint32_t, mve_pred16_t);
1098	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp8q)))
1099	mve_pred16_t __arm_vctp8q(uint32_t);
1100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp8q_m)))
1101	mve_pred16_t __arm_vctp8q_m(uint32_t, mve_pred16_t);
1102	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s16)))
1103	int16x8_t __arm_veorq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1104	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s16)))
1105	int16x8_t __arm_veorq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1106	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s32)))
1107	int32x4_t __arm_veorq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1108	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s32)))
1109	int32x4_t __arm_veorq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1110	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s8)))
1111	int8x16_t __arm_veorq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1112	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s8)))
1113	int8x16_t __arm_veorq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1114	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u16)))
1115	uint16x8_t __arm_veorq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1116	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u16)))
1117	uint16x8_t __arm_veorq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1118	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u32)))
1119	uint32x4_t __arm_veorq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1120	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u32)))
1121	uint32x4_t __arm_veorq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1122	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u8)))
1123	uint8x16_t __arm_veorq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1124	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u8)))
1125	uint8x16_t __arm_veorq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1126	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s16)))
1127	int16x8_t __arm_veorq_s16(int16x8_t, int16x8_t);
1128	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s16)))
1129	int16x8_t __arm_veorq(int16x8_t, int16x8_t);
1130	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s32)))
1131	int32x4_t __arm_veorq_s32(int32x4_t, int32x4_t);
1132	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s32)))
1133	int32x4_t __arm_veorq(int32x4_t, int32x4_t);
1134	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s8)))
1135	int8x16_t __arm_veorq_s8(int8x16_t, int8x16_t);
1136	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s8)))
1137	int8x16_t __arm_veorq(int8x16_t, int8x16_t);
1138	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u16)))
1139	uint16x8_t __arm_veorq_u16(uint16x8_t, uint16x8_t);
1140	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u16)))
1141	uint16x8_t __arm_veorq(uint16x8_t, uint16x8_t);
1142	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u32)))
1143	uint32x4_t __arm_veorq_u32(uint32x4_t, uint32x4_t);
1144	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u32)))
1145	uint32x4_t __arm_veorq(uint32x4_t, uint32x4_t);
1146	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u8)))
1147	uint8x16_t __arm_veorq_u8(uint8x16_t, uint8x16_t);
1148	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u8)))
1149	uint8x16_t __arm_veorq(uint8x16_t, uint8x16_t);
1150	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s16)))
1151	int16x8_t __arm_veorq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1152	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s16)))
1153	int16x8_t __arm_veorq_x(int16x8_t, int16x8_t, mve_pred16_t);
1154	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s32)))
1155	int32x4_t __arm_veorq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1156	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s32)))
1157	int32x4_t __arm_veorq_x(int32x4_t, int32x4_t, mve_pred16_t);
1158	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s8)))
1159	int8x16_t __arm_veorq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1160	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s8)))
1161	int8x16_t __arm_veorq_x(int8x16_t, int8x16_t, mve_pred16_t);
1162	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u16)))
1163	uint16x8_t __arm_veorq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1164	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u16)))
1165	uint16x8_t __arm_veorq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
1166	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u32)))
1167	uint32x4_t __arm_veorq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1168	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u32)))
1169	uint32x4_t __arm_veorq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
1170	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u8)))
1171	uint8x16_t __arm_veorq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1172	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u8)))
1173	uint8x16_t __arm_veorq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
1174	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s16)))
1175	int16_t __arm_vgetq_lane_s16(int16x8_t, int);
1176	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s16)))
1177	int16_t __arm_vgetq_lane(int16x8_t, int);
1178	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s32)))
1179	int32_t __arm_vgetq_lane_s32(int32x4_t, int);
1180	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s32)))
1181	int32_t __arm_vgetq_lane(int32x4_t, int);
1182	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s64)))
1183	int64_t __arm_vgetq_lane_s64(int64x2_t, int);
1184	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s64)))
1185	int64_t __arm_vgetq_lane(int64x2_t, int);
1186	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s8)))
1187	int8_t __arm_vgetq_lane_s8(int8x16_t, int);
1188	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s8)))
1189	int8_t __arm_vgetq_lane(int8x16_t, int);
1190	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u16)))
1191	uint16_t __arm_vgetq_lane_u16(uint16x8_t, int);
1192	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u16)))
1193	uint16_t __arm_vgetq_lane(uint16x8_t, int);
1194	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u32)))
1195	uint32_t __arm_vgetq_lane_u32(uint32x4_t, int);
1196	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u32)))
1197	uint32_t __arm_vgetq_lane(uint32x4_t, int);
1198	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u64)))
1199	uint64_t __arm_vgetq_lane_u64(uint64x2_t, int);
1200	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u64)))
1201	uint64_t __arm_vgetq_lane(uint64x2_t, int);
1202	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u8)))
1203	uint8_t __arm_vgetq_lane_u8(uint8x16_t, int);
1204	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u8)))
1205	uint8_t __arm_vgetq_lane(uint8x16_t, int);
1206	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s16)))
1207	int16x8_t __arm_vhaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1208	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s16)))
1209	int16x8_t __arm_vhaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1210	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s32)))
1211	int32x4_t __arm_vhaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1212	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s32)))
1213	int32x4_t __arm_vhaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1214	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s8)))
1215	int8x16_t __arm_vhaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1216	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s8)))
1217	int8x16_t __arm_vhaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1218	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u16)))
1219	uint16x8_t __arm_vhaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1220	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u16)))
1221	uint16x8_t __arm_vhaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1222	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u32)))
1223	uint32x4_t __arm_vhaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1224	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u32)))
1225	uint32x4_t __arm_vhaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1226	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u8)))
1227	uint8x16_t __arm_vhaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1228	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u8)))
1229	uint8x16_t __arm_vhaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1230	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s16)))
1231	int16x8_t __arm_vhaddq_s16(int16x8_t, int16x8_t);
1232	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s16)))
1233	int16x8_t __arm_vhaddq(int16x8_t, int16x8_t);
1234	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s32)))
1235	int32x4_t __arm_vhaddq_s32(int32x4_t, int32x4_t);
1236	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s32)))
1237	int32x4_t __arm_vhaddq(int32x4_t, int32x4_t);
1238	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s8)))
1239	int8x16_t __arm_vhaddq_s8(int8x16_t, int8x16_t);
1240	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s8)))
1241	int8x16_t __arm_vhaddq(int8x16_t, int8x16_t);
1242	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u16)))
1243	uint16x8_t __arm_vhaddq_u16(uint16x8_t, uint16x8_t);
1244	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u16)))
1245	uint16x8_t __arm_vhaddq(uint16x8_t, uint16x8_t);
1246	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u32)))
1247	uint32x4_t __arm_vhaddq_u32(uint32x4_t, uint32x4_t);
1248	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u32)))
1249	uint32x4_t __arm_vhaddq(uint32x4_t, uint32x4_t);
1250	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u8)))
1251	uint8x16_t __arm_vhaddq_u8(uint8x16_t, uint8x16_t);
1252	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u8)))
1253	uint8x16_t __arm_vhaddq(uint8x16_t, uint8x16_t);
1254	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s16)))
1255	int16x8_t __arm_vhaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1256	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s16)))
1257	int16x8_t __arm_vhaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
1258	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s32)))
1259	int32x4_t __arm_vhaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1260	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s32)))
1261	int32x4_t __arm_vhaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
1262	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s8)))
1263	int8x16_t __arm_vhaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1264	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s8)))
1265	int8x16_t __arm_vhaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
1266	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u16)))
1267	uint16x8_t __arm_vhaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1268	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u16)))
1269	uint16x8_t __arm_vhaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
1270	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u32)))
1271	uint32x4_t __arm_vhaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1272	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u32)))
1273	uint32x4_t __arm_vhaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
1274	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u8)))
1275	uint8x16_t __arm_vhaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1276	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u8)))
1277	uint8x16_t __arm_vhaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
1278	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s16)))
1279	int16x8_t __arm_vhcaddq_rot270_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1280	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s16)))
1281	int16x8_t __arm_vhcaddq_rot270_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1282	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s32)))
1283	int32x4_t __arm_vhcaddq_rot270_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1284	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s32)))
1285	int32x4_t __arm_vhcaddq_rot270_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1286	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s8)))
1287	int8x16_t __arm_vhcaddq_rot270_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1288	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s8)))
1289	int8x16_t __arm_vhcaddq_rot270_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1290	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s16)))
1291	int16x8_t __arm_vhcaddq_rot270_s16(int16x8_t, int16x8_t);
1292	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s16)))
1293	int16x8_t __arm_vhcaddq_rot270(int16x8_t, int16x8_t);
1294	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s32)))
1295	int32x4_t __arm_vhcaddq_rot270_s32(int32x4_t, int32x4_t);
1296	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s32)))
1297	int32x4_t __arm_vhcaddq_rot270(int32x4_t, int32x4_t);
1298	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s8)))
1299	int8x16_t __arm_vhcaddq_rot270_s8(int8x16_t, int8x16_t);
1300	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s8)))
1301	int8x16_t __arm_vhcaddq_rot270(int8x16_t, int8x16_t);
1302	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s16)))
1303	int16x8_t __arm_vhcaddq_rot270_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1304	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s16)))
1305	int16x8_t __arm_vhcaddq_rot270_x(int16x8_t, int16x8_t, mve_pred16_t);
1306	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s32)))
1307	int32x4_t __arm_vhcaddq_rot270_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1308	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s32)))
1309	int32x4_t __arm_vhcaddq_rot270_x(int32x4_t, int32x4_t, mve_pred16_t);
1310	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s8)))
1311	int8x16_t __arm_vhcaddq_rot270_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1312	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s8)))
1313	int8x16_t __arm_vhcaddq_rot270_x(int8x16_t, int8x16_t, mve_pred16_t);
1314	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s16)))
1315	int16x8_t __arm_vhcaddq_rot90_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1316	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s16)))
1317	int16x8_t __arm_vhcaddq_rot90_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1318	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s32)))
1319	int32x4_t __arm_vhcaddq_rot90_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1320	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s32)))
1321	int32x4_t __arm_vhcaddq_rot90_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1322	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s8)))
1323	int8x16_t __arm_vhcaddq_rot90_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1324	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s8)))
1325	int8x16_t __arm_vhcaddq_rot90_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1326	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s16)))
1327	int16x8_t __arm_vhcaddq_rot90_s16(int16x8_t, int16x8_t);
1328	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s16)))
1329	int16x8_t __arm_vhcaddq_rot90(int16x8_t, int16x8_t);
1330	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s32)))
1331	int32x4_t __arm_vhcaddq_rot90_s32(int32x4_t, int32x4_t);
1332	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s32)))
1333	int32x4_t __arm_vhcaddq_rot90(int32x4_t, int32x4_t);
1334	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s8)))
1335	int8x16_t __arm_vhcaddq_rot90_s8(int8x16_t, int8x16_t);
1336	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s8)))
1337	int8x16_t __arm_vhcaddq_rot90(int8x16_t, int8x16_t);
1338	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s16)))
1339	int16x8_t __arm_vhcaddq_rot90_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1340	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s16)))
1341	int16x8_t __arm_vhcaddq_rot90_x(int16x8_t, int16x8_t, mve_pred16_t);
1342	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s32)))
1343	int32x4_t __arm_vhcaddq_rot90_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1344	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s32)))
1345	int32x4_t __arm_vhcaddq_rot90_x(int32x4_t, int32x4_t, mve_pred16_t);
1346	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s8)))
1347	int8x16_t __arm_vhcaddq_rot90_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1348	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s8)))
1349	int8x16_t __arm_vhcaddq_rot90_x(int8x16_t, int8x16_t, mve_pred16_t);
1350	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s16)))
1351	int16x8_t __arm_vhsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1352	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s16)))
1353	int16x8_t __arm_vhsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1354	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s32)))
1355	int32x4_t __arm_vhsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1356	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s32)))
1357	int32x4_t __arm_vhsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1358	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s8)))
1359	int8x16_t __arm_vhsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1360	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s8)))
1361	int8x16_t __arm_vhsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1362	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u16)))
1363	uint16x8_t __arm_vhsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1364	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u16)))
1365	uint16x8_t __arm_vhsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1366	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u32)))
1367	uint32x4_t __arm_vhsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1368	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u32)))
1369	uint32x4_t __arm_vhsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1370	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u8)))
1371	uint8x16_t __arm_vhsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1372	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u8)))
1373	uint8x16_t __arm_vhsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1374	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s16)))
1375	int16x8_t __arm_vhsubq_s16(int16x8_t, int16x8_t);
1376	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s16)))
1377	int16x8_t __arm_vhsubq(int16x8_t, int16x8_t);
1378	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s32)))
1379	int32x4_t __arm_vhsubq_s32(int32x4_t, int32x4_t);
1380	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s32)))
1381	int32x4_t __arm_vhsubq(int32x4_t, int32x4_t);
1382	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s8)))
1383	int8x16_t __arm_vhsubq_s8(int8x16_t, int8x16_t);
1384	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s8)))
1385	int8x16_t __arm_vhsubq(int8x16_t, int8x16_t);
1386	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u16)))
1387	uint16x8_t __arm_vhsubq_u16(uint16x8_t, uint16x8_t);
1388	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u16)))
1389	uint16x8_t __arm_vhsubq(uint16x8_t, uint16x8_t);
1390	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u32)))
1391	uint32x4_t __arm_vhsubq_u32(uint32x4_t, uint32x4_t);
1392	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u32)))
1393	uint32x4_t __arm_vhsubq(uint32x4_t, uint32x4_t);
1394	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u8)))
1395	uint8x16_t __arm_vhsubq_u8(uint8x16_t, uint8x16_t);
1396	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u8)))
1397	uint8x16_t __arm_vhsubq(uint8x16_t, uint8x16_t);
1398	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s16)))
1399	int16x8_t __arm_vhsubq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1400	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s16)))
1401	int16x8_t __arm_vhsubq_x(int16x8_t, int16x8_t, mve_pred16_t);
1402	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s32)))
1403	int32x4_t __arm_vhsubq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1404	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s32)))
1405	int32x4_t __arm_vhsubq_x(int32x4_t, int32x4_t, mve_pred16_t);
1406	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s8)))
1407	int8x16_t __arm_vhsubq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1408	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s8)))
1409	int8x16_t __arm_vhsubq_x(int8x16_t, int8x16_t, mve_pred16_t);
1410	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u16)))
1411	uint16x8_t __arm_vhsubq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1412	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u16)))
1413	uint16x8_t __arm_vhsubq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
1414	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u32)))
1415	uint32x4_t __arm_vhsubq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1416	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u32)))
1417	uint32x4_t __arm_vhsubq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
1418	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u8)))
1419	uint8x16_t __arm_vhsubq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1420	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u8)))
1421	uint8x16_t __arm_vhsubq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
1422	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s16)))
1423	int16x8_t __arm_vld1q_s16(const int16_t *);
1424	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s16)))
1425	int16x8_t __arm_vld1q(const int16_t *);
1426	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s32)))
1427	int32x4_t __arm_vld1q_s32(const int32_t *);
1428	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s32)))
1429	int32x4_t __arm_vld1q(const int32_t *);
1430	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s8)))
1431	int8x16_t __arm_vld1q_s8(const int8_t *);
1432	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s8)))
1433	int8x16_t __arm_vld1q(const int8_t *);
1434	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u16)))
1435	uint16x8_t __arm_vld1q_u16(const uint16_t *);
1436	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u16)))
1437	uint16x8_t __arm_vld1q(const uint16_t *);
1438	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u32)))
1439	uint32x4_t __arm_vld1q_u32(const uint32_t *);
1440	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u32)))
1441	uint32x4_t __arm_vld1q(const uint32_t *);
1442	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u8)))
1443	uint8x16_t __arm_vld1q_u8(const uint8_t *);
1444	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u8)))
1445	uint8x16_t __arm_vld1q(const uint8_t *);
1446	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s16)))
1447	int16x8_t __arm_vld1q_z_s16(const int16_t *, mve_pred16_t);
1448	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s16)))
1449	int16x8_t __arm_vld1q_z(const int16_t *, mve_pred16_t);
1450	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s32)))
1451	int32x4_t __arm_vld1q_z_s32(const int32_t *, mve_pred16_t);
1452	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s32)))
1453	int32x4_t __arm_vld1q_z(const int32_t *, mve_pred16_t);
1454	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s8)))
1455	int8x16_t __arm_vld1q_z_s8(const int8_t *, mve_pred16_t);
1456	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s8)))
1457	int8x16_t __arm_vld1q_z(const int8_t *, mve_pred16_t);
1458	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u16)))
1459	uint16x8_t __arm_vld1q_z_u16(const uint16_t *, mve_pred16_t);
1460	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u16)))
1461	uint16x8_t __arm_vld1q_z(const uint16_t *, mve_pred16_t);
1462	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u32)))
1463	uint32x4_t __arm_vld1q_z_u32(const uint32_t *, mve_pred16_t);
1464	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u32)))
1465	uint32x4_t __arm_vld1q_z(const uint32_t *, mve_pred16_t);
1466	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u8)))
1467	uint8x16_t __arm_vld1q_z_u8(const uint8_t *, mve_pred16_t);
1468	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u8)))
1469	uint8x16_t __arm_vld1q_z(const uint8_t *, mve_pred16_t);
1470	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s16)))
1471	int16x8x2_t __arm_vld2q_s16(const int16_t *);
1472	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s16)))
1473	int16x8x2_t __arm_vld2q(const int16_t *);
1474	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s32)))
1475	int32x4x2_t __arm_vld2q_s32(const int32_t *);
1476	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s32)))
1477	int32x4x2_t __arm_vld2q(const int32_t *);
1478	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s8)))
1479	int8x16x2_t __arm_vld2q_s8(const int8_t *);
1480	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s8)))
1481	int8x16x2_t __arm_vld2q(const int8_t *);
1482	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u16)))
1483	uint16x8x2_t __arm_vld2q_u16(const uint16_t *);
1484	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u16)))
1485	uint16x8x2_t __arm_vld2q(const uint16_t *);
1486	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u32)))
1487	uint32x4x2_t __arm_vld2q_u32(const uint32_t *);
1488	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u32)))
1489	uint32x4x2_t __arm_vld2q(const uint32_t *);
1490	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u8)))
1491	uint8x16x2_t __arm_vld2q_u8(const uint8_t *);
1492	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u8)))
1493	uint8x16x2_t __arm_vld2q(const uint8_t *);
1494	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s16)))
1495	int16x8x4_t __arm_vld4q_s16(const int16_t *);
1496	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s16)))
1497	int16x8x4_t __arm_vld4q(const int16_t *);
1498	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s32)))
1499	int32x4x4_t __arm_vld4q_s32(const int32_t *);
1500	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s32)))
1501	int32x4x4_t __arm_vld4q(const int32_t *);
1502	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s8)))
1503	int8x16x4_t __arm_vld4q_s8(const int8_t *);
1504	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s8)))
1505	int8x16x4_t __arm_vld4q(const int8_t *);
1506	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u16)))
1507	uint16x8x4_t __arm_vld4q_u16(const uint16_t *);
1508	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u16)))
1509	uint16x8x4_t __arm_vld4q(const uint16_t *);
1510	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u32)))
1511	uint32x4x4_t __arm_vld4q_u32(const uint32_t *);
1512	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u32)))
1513	uint32x4x4_t __arm_vld4q(const uint32_t *);
1514	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u8)))
1515	uint8x16x4_t __arm_vld4q_u8(const uint8_t *);
1516	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u8)))
1517	uint8x16x4_t __arm_vld4q(const uint8_t *);
1518	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s16)))
1519	int16x8_t __arm_vldrbq_gather_offset_s16(const int8_t *, uint16x8_t);
1520	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s16)))
1521	int16x8_t __arm_vldrbq_gather_offset(const int8_t *, uint16x8_t);
1522	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s32)))
1523	int32x4_t __arm_vldrbq_gather_offset_s32(const int8_t *, uint32x4_t);
1524	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s32)))
1525	int32x4_t __arm_vldrbq_gather_offset(const int8_t *, uint32x4_t);
1526	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s8)))
1527	int8x16_t __arm_vldrbq_gather_offset_s8(const int8_t *, uint8x16_t);
1528	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s8)))
1529	int8x16_t __arm_vldrbq_gather_offset(const int8_t *, uint8x16_t);
1530	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u16)))
1531	uint16x8_t __arm_vldrbq_gather_offset_u16(const uint8_t *, uint16x8_t);
1532	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u16)))
1533	uint16x8_t __arm_vldrbq_gather_offset(const uint8_t *, uint16x8_t);
1534	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u32)))
1535	uint32x4_t __arm_vldrbq_gather_offset_u32(const uint8_t *, uint32x4_t);
1536	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u32)))
1537	uint32x4_t __arm_vldrbq_gather_offset(const uint8_t *, uint32x4_t);
1538	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u8)))
1539	uint8x16_t __arm_vldrbq_gather_offset_u8(const uint8_t *, uint8x16_t);
1540	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u8)))
1541	uint8x16_t __arm_vldrbq_gather_offset(const uint8_t *, uint8x16_t);
1542	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s16)))
1543	int16x8_t __arm_vldrbq_gather_offset_z_s16(const int8_t *, uint16x8_t, mve_pred16_t);
1544	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s16)))
1545	int16x8_t __arm_vldrbq_gather_offset_z(const int8_t *, uint16x8_t, mve_pred16_t);
1546	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s32)))
1547	int32x4_t __arm_vldrbq_gather_offset_z_s32(const int8_t *, uint32x4_t, mve_pred16_t);
1548	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s32)))
1549	int32x4_t __arm_vldrbq_gather_offset_z(const int8_t *, uint32x4_t, mve_pred16_t);
1550	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s8)))
1551	int8x16_t __arm_vldrbq_gather_offset_z_s8(const int8_t *, uint8x16_t, mve_pred16_t);
1552	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s8)))
1553	int8x16_t __arm_vldrbq_gather_offset_z(const int8_t *, uint8x16_t, mve_pred16_t);
1554	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u16)))
1555	uint16x8_t __arm_vldrbq_gather_offset_z_u16(const uint8_t *, uint16x8_t, mve_pred16_t);
1556	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u16)))
1557	uint16x8_t __arm_vldrbq_gather_offset_z(const uint8_t *, uint16x8_t, mve_pred16_t);
1558	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u32)))
1559	uint32x4_t __arm_vldrbq_gather_offset_z_u32(const uint8_t *, uint32x4_t, mve_pred16_t);
1560	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u32)))
1561	uint32x4_t __arm_vldrbq_gather_offset_z(const uint8_t *, uint32x4_t, mve_pred16_t);
1562	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u8)))
1563	uint8x16_t __arm_vldrbq_gather_offset_z_u8(const uint8_t *, uint8x16_t, mve_pred16_t);
1564	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u8)))
1565	uint8x16_t __arm_vldrbq_gather_offset_z(const uint8_t *, uint8x16_t, mve_pred16_t);
1566	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s16)))
1567	int16x8_t __arm_vldrbq_s16(const int8_t *);
1568	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s32)))
1569	int32x4_t __arm_vldrbq_s32(const int8_t *);
1570	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s8)))
1571	int8x16_t __arm_vldrbq_s8(const int8_t *);
1572	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u16)))
1573	uint16x8_t __arm_vldrbq_u16(const uint8_t *);
1574	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u32)))
1575	uint32x4_t __arm_vldrbq_u32(const uint8_t *);
1576	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u8)))
1577	uint8x16_t __arm_vldrbq_u8(const uint8_t *);
1578	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s16)))
1579	int16x8_t __arm_vldrbq_z_s16(const int8_t *, mve_pred16_t);
1580	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s32)))
1581	int32x4_t __arm_vldrbq_z_s32(const int8_t *, mve_pred16_t);
1582	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s8)))
1583	int8x16_t __arm_vldrbq_z_s8(const int8_t *, mve_pred16_t);
1584	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u16)))
1585	uint16x8_t __arm_vldrbq_z_u16(const uint8_t *, mve_pred16_t);
1586	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u32)))
1587	uint32x4_t __arm_vldrbq_z_u32(const uint8_t *, mve_pred16_t);
1588	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u8)))
1589	uint8x16_t __arm_vldrbq_z_u8(const uint8_t *, mve_pred16_t);
1590	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_s64)))
1591	int64x2_t __arm_vldrdq_gather_base_s64(uint64x2_t, int);
1592	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_u64)))
1593	uint64x2_t __arm_vldrdq_gather_base_u64(uint64x2_t, int);
1594	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_s64)))
1595	int64x2_t __arm_vldrdq_gather_base_wb_s64(uint64x2_t *, int);
1596	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_u64)))
1597	uint64x2_t __arm_vldrdq_gather_base_wb_u64(uint64x2_t *, int);
1598	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_z_s64)))
1599	int64x2_t __arm_vldrdq_gather_base_wb_z_s64(uint64x2_t *, int, mve_pred16_t);
1600	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_z_u64)))
1601	uint64x2_t __arm_vldrdq_gather_base_wb_z_u64(uint64x2_t *, int, mve_pred16_t);
1602	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_z_s64)))
1603	int64x2_t __arm_vldrdq_gather_base_z_s64(uint64x2_t, int, mve_pred16_t);
1604	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_z_u64)))
1605	uint64x2_t __arm_vldrdq_gather_base_z_u64(uint64x2_t, int, mve_pred16_t);
1606	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_s64)))
1607	int64x2_t __arm_vldrdq_gather_offset_s64(const int64_t *, uint64x2_t);
1608	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_s64)))
1609	int64x2_t __arm_vldrdq_gather_offset(const int64_t *, uint64x2_t);
1610	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_u64)))
1611	uint64x2_t __arm_vldrdq_gather_offset_u64(const uint64_t *, uint64x2_t);
1612	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_u64)))
1613	uint64x2_t __arm_vldrdq_gather_offset(const uint64_t *, uint64x2_t);
1614	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_s64)))
1615	int64x2_t __arm_vldrdq_gather_offset_z_s64(const int64_t *, uint64x2_t, mve_pred16_t);
1616	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_s64)))
1617	int64x2_t __arm_vldrdq_gather_offset_z(const int64_t *, uint64x2_t, mve_pred16_t);
1618	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_u64)))
1619	uint64x2_t __arm_vldrdq_gather_offset_z_u64(const uint64_t *, uint64x2_t, mve_pred16_t);
1620	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_u64)))
1621	uint64x2_t __arm_vldrdq_gather_offset_z(const uint64_t *, uint64x2_t, mve_pred16_t);
1622	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_s64)))
1623	int64x2_t __arm_vldrdq_gather_shifted_offset_s64(const int64_t *, uint64x2_t);
1624	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_s64)))
1625	int64x2_t __arm_vldrdq_gather_shifted_offset(const int64_t *, uint64x2_t);
1626	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_u64)))
1627	uint64x2_t __arm_vldrdq_gather_shifted_offset_u64(const uint64_t *, uint64x2_t);
1628	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_u64)))
1629	uint64x2_t __arm_vldrdq_gather_shifted_offset(const uint64_t *, uint64x2_t);
1630	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_s64)))
1631	int64x2_t __arm_vldrdq_gather_shifted_offset_z_s64(const int64_t *, uint64x2_t, mve_pred16_t);
1632	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_s64)))
1633	int64x2_t __arm_vldrdq_gather_shifted_offset_z(const int64_t *, uint64x2_t, mve_pred16_t);
1634	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_u64)))
1635	uint64x2_t __arm_vldrdq_gather_shifted_offset_z_u64(const uint64_t *, uint64x2_t, mve_pred16_t);
1636	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_u64)))
1637	uint64x2_t __arm_vldrdq_gather_shifted_offset_z(const uint64_t *, uint64x2_t, mve_pred16_t);
1638	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s16)))
1639	int16x8_t __arm_vldrhq_gather_offset_s16(const int16_t *, uint16x8_t);
1640	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s16)))
1641	int16x8_t __arm_vldrhq_gather_offset(const int16_t *, uint16x8_t);
1642	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s32)))
1643	int32x4_t __arm_vldrhq_gather_offset_s32(const int16_t *, uint32x4_t);
1644	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s32)))
1645	int32x4_t __arm_vldrhq_gather_offset(const int16_t *, uint32x4_t);
1646	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u16)))
1647	uint16x8_t __arm_vldrhq_gather_offset_u16(const uint16_t *, uint16x8_t);
1648	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u16)))
1649	uint16x8_t __arm_vldrhq_gather_offset(const uint16_t *, uint16x8_t);
1650	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u32)))
1651	uint32x4_t __arm_vldrhq_gather_offset_u32(const uint16_t *, uint32x4_t);
1652	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u32)))
1653	uint32x4_t __arm_vldrhq_gather_offset(const uint16_t *, uint32x4_t);
1654	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s16)))
1655	int16x8_t __arm_vldrhq_gather_offset_z_s16(const int16_t *, uint16x8_t, mve_pred16_t);
1656	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s16)))
1657	int16x8_t __arm_vldrhq_gather_offset_z(const int16_t *, uint16x8_t, mve_pred16_t);
1658	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s32)))
1659	int32x4_t __arm_vldrhq_gather_offset_z_s32(const int16_t *, uint32x4_t, mve_pred16_t);
1660	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s32)))
1661	int32x4_t __arm_vldrhq_gather_offset_z(const int16_t *, uint32x4_t, mve_pred16_t);
1662	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u16)))
1663	uint16x8_t __arm_vldrhq_gather_offset_z_u16(const uint16_t *, uint16x8_t, mve_pred16_t);
1664	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u16)))
1665	uint16x8_t __arm_vldrhq_gather_offset_z(const uint16_t *, uint16x8_t, mve_pred16_t);
1666	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u32)))
1667	uint32x4_t __arm_vldrhq_gather_offset_z_u32(const uint16_t *, uint32x4_t, mve_pred16_t);
1668	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u32)))
1669	uint32x4_t __arm_vldrhq_gather_offset_z(const uint16_t *, uint32x4_t, mve_pred16_t);
1670	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s16)))
1671	int16x8_t __arm_vldrhq_gather_shifted_offset_s16(const int16_t *, uint16x8_t);
1672	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s16)))
1673	int16x8_t __arm_vldrhq_gather_shifted_offset(const int16_t *, uint16x8_t);
1674	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s32)))
1675	int32x4_t __arm_vldrhq_gather_shifted_offset_s32(const int16_t *, uint32x4_t);
1676	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s32)))
1677	int32x4_t __arm_vldrhq_gather_shifted_offset(const int16_t *, uint32x4_t);
1678	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u16)))
1679	uint16x8_t __arm_vldrhq_gather_shifted_offset_u16(const uint16_t *, uint16x8_t);
1680	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u16)))
1681	uint16x8_t __arm_vldrhq_gather_shifted_offset(const uint16_t *, uint16x8_t);
1682	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u32)))
1683	uint32x4_t __arm_vldrhq_gather_shifted_offset_u32(const uint16_t *, uint32x4_t);
1684	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u32)))
1685	uint32x4_t __arm_vldrhq_gather_shifted_offset(const uint16_t *, uint32x4_t);
1686	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s16)))
1687	int16x8_t __arm_vldrhq_gather_shifted_offset_z_s16(const int16_t *, uint16x8_t, mve_pred16_t);
1688	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s16)))
1689	int16x8_t __arm_vldrhq_gather_shifted_offset_z(const int16_t *, uint16x8_t, mve_pred16_t);
1690	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s32)))
1691	int32x4_t __arm_vldrhq_gather_shifted_offset_z_s32(const int16_t *, uint32x4_t, mve_pred16_t);
1692	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s32)))
1693	int32x4_t __arm_vldrhq_gather_shifted_offset_z(const int16_t *, uint32x4_t, mve_pred16_t);
1694	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u16)))
1695	uint16x8_t __arm_vldrhq_gather_shifted_offset_z_u16(const uint16_t *, uint16x8_t, mve_pred16_t);
1696	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u16)))
1697	uint16x8_t __arm_vldrhq_gather_shifted_offset_z(const uint16_t *, uint16x8_t, mve_pred16_t);
1698	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u32)))
1699	uint32x4_t __arm_vldrhq_gather_shifted_offset_z_u32(const uint16_t *, uint32x4_t, mve_pred16_t);
1700	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u32)))
1701	uint32x4_t __arm_vldrhq_gather_shifted_offset_z(const uint16_t *, uint32x4_t, mve_pred16_t);
1702	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_s16)))
1703	int16x8_t __arm_vldrhq_s16(const int16_t *);
1704	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_s32)))
1705	int32x4_t __arm_vldrhq_s32(const int16_t *);
1706	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_u16)))
1707	uint16x8_t __arm_vldrhq_u16(const uint16_t *);
1708	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_u32)))
1709	uint32x4_t __arm_vldrhq_u32(const uint16_t *);
1710	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_s16)))
1711	int16x8_t __arm_vldrhq_z_s16(const int16_t *, mve_pred16_t);
1712	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_s32)))
1713	int32x4_t __arm_vldrhq_z_s32(const int16_t *, mve_pred16_t);
1714	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_u16)))
1715	uint16x8_t __arm_vldrhq_z_u16(const uint16_t *, mve_pred16_t);
1716	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_u32)))
1717	uint32x4_t __arm_vldrhq_z_u32(const uint16_t *, mve_pred16_t);
1718	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_s32)))
1719	int32x4_t __arm_vldrwq_gather_base_s32(uint32x4_t, int);
1720	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_u32)))
1721	uint32x4_t __arm_vldrwq_gather_base_u32(uint32x4_t, int);
1722	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_s32)))
1723	int32x4_t __arm_vldrwq_gather_base_wb_s32(uint32x4_t *, int);
1724	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_u32)))
1725	uint32x4_t __arm_vldrwq_gather_base_wb_u32(uint32x4_t *, int);
1726	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_s32)))
1727	int32x4_t __arm_vldrwq_gather_base_wb_z_s32(uint32x4_t *, int, mve_pred16_t);
1728	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_u32)))
1729	uint32x4_t __arm_vldrwq_gather_base_wb_z_u32(uint32x4_t *, int, mve_pred16_t);
1730	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_s32)))
1731	int32x4_t __arm_vldrwq_gather_base_z_s32(uint32x4_t, int, mve_pred16_t);
1732	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_u32)))
1733	uint32x4_t __arm_vldrwq_gather_base_z_u32(uint32x4_t, int, mve_pred16_t);
1734	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_s32)))
1735	int32x4_t __arm_vldrwq_gather_offset_s32(const int32_t *, uint32x4_t);
1736	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_s32)))
1737	int32x4_t __arm_vldrwq_gather_offset(const int32_t *, uint32x4_t);
1738	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_u32)))
1739	uint32x4_t __arm_vldrwq_gather_offset_u32(const uint32_t *, uint32x4_t);
1740	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_u32)))
1741	uint32x4_t __arm_vldrwq_gather_offset(const uint32_t *, uint32x4_t);
1742	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_s32)))
1743	int32x4_t __arm_vldrwq_gather_offset_z_s32(const int32_t *, uint32x4_t, mve_pred16_t);
1744	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_s32)))
1745	int32x4_t __arm_vldrwq_gather_offset_z(const int32_t *, uint32x4_t, mve_pred16_t);
1746	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_u32)))
1747	uint32x4_t __arm_vldrwq_gather_offset_z_u32(const uint32_t *, uint32x4_t, mve_pred16_t);
1748	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_u32)))
1749	uint32x4_t __arm_vldrwq_gather_offset_z(const uint32_t *, uint32x4_t, mve_pred16_t);
1750	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_s32)))
1751	int32x4_t __arm_vldrwq_gather_shifted_offset_s32(const int32_t *, uint32x4_t);
1752	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_s32)))
1753	int32x4_t __arm_vldrwq_gather_shifted_offset(const int32_t *, uint32x4_t);
1754	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_u32)))
1755	uint32x4_t __arm_vldrwq_gather_shifted_offset_u32(const uint32_t *, uint32x4_t);
1756	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_u32)))
1757	uint32x4_t __arm_vldrwq_gather_shifted_offset(const uint32_t *, uint32x4_t);
1758	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_s32)))
1759	int32x4_t __arm_vldrwq_gather_shifted_offset_z_s32(const int32_t *, uint32x4_t, mve_pred16_t);
1760	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_s32)))
1761	int32x4_t __arm_vldrwq_gather_shifted_offset_z(const int32_t *, uint32x4_t, mve_pred16_t);
1762	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_u32)))
1763	uint32x4_t __arm_vldrwq_gather_shifted_offset_z_u32(const uint32_t *, uint32x4_t, mve_pred16_t);
1764	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_u32)))
1765	uint32x4_t __arm_vldrwq_gather_shifted_offset_z(const uint32_t *, uint32x4_t, mve_pred16_t);
1766	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_s32)))
1767	int32x4_t __arm_vldrwq_s32(const int32_t *);
1768	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_u32)))
1769	uint32x4_t __arm_vldrwq_u32(const uint32_t *);
1770	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_s32)))
1771	int32x4_t __arm_vldrwq_z_s32(const int32_t *, mve_pred16_t);
1772	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_u32)))
1773	uint32x4_t __arm_vldrwq_z_u32(const uint32_t *, mve_pred16_t);
1774	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s16)))
1775	int16x8_t __arm_vmaxq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1776	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s16)))
1777	int16x8_t __arm_vmaxq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1778	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s32)))
1779	int32x4_t __arm_vmaxq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1780	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s32)))
1781	int32x4_t __arm_vmaxq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1782	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s8)))
1783	int8x16_t __arm_vmaxq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1784	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s8)))
1785	int8x16_t __arm_vmaxq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1786	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u16)))
1787	uint16x8_t __arm_vmaxq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1788	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u16)))
1789	uint16x8_t __arm_vmaxq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1790	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u32)))
1791	uint32x4_t __arm_vmaxq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1792	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u32)))
1793	uint32x4_t __arm_vmaxq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1794	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u8)))
1795	uint8x16_t __arm_vmaxq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1796	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u8)))
1797	uint8x16_t __arm_vmaxq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1798	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s16)))
1799	int16x8_t __arm_vmaxq_s16(int16x8_t, int16x8_t);
1800	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s16)))
1801	int16x8_t __arm_vmaxq(int16x8_t, int16x8_t);
1802	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s32)))
1803	int32x4_t __arm_vmaxq_s32(int32x4_t, int32x4_t);
1804	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s32)))
1805	int32x4_t __arm_vmaxq(int32x4_t, int32x4_t);
1806	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s8)))
1807	int8x16_t __arm_vmaxq_s8(int8x16_t, int8x16_t);
1808	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s8)))
1809	int8x16_t __arm_vmaxq(int8x16_t, int8x16_t);
1810	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u16)))
1811	uint16x8_t __arm_vmaxq_u16(uint16x8_t, uint16x8_t);
1812	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u16)))
1813	uint16x8_t __arm_vmaxq(uint16x8_t, uint16x8_t);
1814	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u32)))
1815	uint32x4_t __arm_vmaxq_u32(uint32x4_t, uint32x4_t);
1816	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u32)))
1817	uint32x4_t __arm_vmaxq(uint32x4_t, uint32x4_t);
1818	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u8)))
1819	uint8x16_t __arm_vmaxq_u8(uint8x16_t, uint8x16_t);
1820	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u8)))
1821	uint8x16_t __arm_vmaxq(uint8x16_t, uint8x16_t);
1822	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s16)))
1823	int16x8_t __arm_vmaxq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1824	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s16)))
1825	int16x8_t __arm_vmaxq_x(int16x8_t, int16x8_t, mve_pred16_t);
1826	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s32)))
1827	int32x4_t __arm_vmaxq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1828	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s32)))
1829	int32x4_t __arm_vmaxq_x(int32x4_t, int32x4_t, mve_pred16_t);
1830	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s8)))
1831	int8x16_t __arm_vmaxq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1832	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s8)))
1833	int8x16_t __arm_vmaxq_x(int8x16_t, int8x16_t, mve_pred16_t);
1834	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u16)))
1835	uint16x8_t __arm_vmaxq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1836	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u16)))
1837	uint16x8_t __arm_vmaxq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
1838	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u32)))
1839	uint32x4_t __arm_vmaxq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1840	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u32)))
1841	uint32x4_t __arm_vmaxq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
1842	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u8)))
1843	uint8x16_t __arm_vmaxq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1844	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u8)))
1845	uint8x16_t __arm_vmaxq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
1846	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s16)))
1847	int16_t __arm_vmaxvq_s16(int16_t, int16x8_t);
1848	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s16)))
1849	int16_t __arm_vmaxvq(int16_t, int16x8_t);
1850	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s32)))
1851	int32_t __arm_vmaxvq_s32(int32_t, int32x4_t);
1852	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s32)))
1853	int32_t __arm_vmaxvq(int32_t, int32x4_t);
1854	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s8)))
1855	int8_t __arm_vmaxvq_s8(int8_t, int8x16_t);
1856	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s8)))
1857	int8_t __arm_vmaxvq(int8_t, int8x16_t);
1858	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u16)))
1859	uint16_t __arm_vmaxvq_u16(uint16_t, uint16x8_t);
1860	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u16)))
1861	uint16_t __arm_vmaxvq(uint16_t, uint16x8_t);
1862	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u32)))
1863	uint32_t __arm_vmaxvq_u32(uint32_t, uint32x4_t);
1864	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u32)))
1865	uint32_t __arm_vmaxvq(uint32_t, uint32x4_t);
1866	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u8)))
1867	uint8_t __arm_vmaxvq_u8(uint8_t, uint8x16_t);
1868	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u8)))
1869	uint8_t __arm_vmaxvq(uint8_t, uint8x16_t);
1870	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s16)))
1871	int16x8_t __arm_vminq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1872	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s16)))
1873	int16x8_t __arm_vminq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
1874	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s32)))
1875	int32x4_t __arm_vminq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1876	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s32)))
1877	int32x4_t __arm_vminq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
1878	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s8)))
1879	int8x16_t __arm_vminq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1880	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s8)))
1881	int8x16_t __arm_vminq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
1882	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u16)))
1883	uint16x8_t __arm_vminq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1884	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u16)))
1885	uint16x8_t __arm_vminq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1886	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u32)))
1887	uint32x4_t __arm_vminq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1888	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u32)))
1889	uint32x4_t __arm_vminq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1890	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u8)))
1891	uint8x16_t __arm_vminq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1892	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u8)))
1893	uint8x16_t __arm_vminq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1894	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s16)))
1895	int16x8_t __arm_vminq_s16(int16x8_t, int16x8_t);
1896	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s16)))
1897	int16x8_t __arm_vminq(int16x8_t, int16x8_t);
1898	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s32)))
1899	int32x4_t __arm_vminq_s32(int32x4_t, int32x4_t);
1900	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s32)))
1901	int32x4_t __arm_vminq(int32x4_t, int32x4_t);
1902	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s8)))
1903	int8x16_t __arm_vminq_s8(int8x16_t, int8x16_t);
1904	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s8)))
1905	int8x16_t __arm_vminq(int8x16_t, int8x16_t);
1906	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u16)))
1907	uint16x8_t __arm_vminq_u16(uint16x8_t, uint16x8_t);
1908	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u16)))
1909	uint16x8_t __arm_vminq(uint16x8_t, uint16x8_t);
1910	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u32)))
1911	uint32x4_t __arm_vminq_u32(uint32x4_t, uint32x4_t);
1912	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u32)))
1913	uint32x4_t __arm_vminq(uint32x4_t, uint32x4_t);
1914	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u8)))
1915	uint8x16_t __arm_vminq_u8(uint8x16_t, uint8x16_t);
1916	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u8)))
1917	uint8x16_t __arm_vminq(uint8x16_t, uint8x16_t);
1918	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s16)))
1919	int16x8_t __arm_vminq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
1920	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s16)))
1921	int16x8_t __arm_vminq_x(int16x8_t, int16x8_t, mve_pred16_t);
1922	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s32)))
1923	int32x4_t __arm_vminq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
1924	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s32)))
1925	int32x4_t __arm_vminq_x(int32x4_t, int32x4_t, mve_pred16_t);
1926	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s8)))
1927	int8x16_t __arm_vminq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
1928	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s8)))
1929	int8x16_t __arm_vminq_x(int8x16_t, int8x16_t, mve_pred16_t);
1930	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u16)))
1931	uint16x8_t __arm_vminq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
1932	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u16)))
1933	uint16x8_t __arm_vminq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
1934	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u32)))
1935	uint32x4_t __arm_vminq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
1936	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u32)))
1937	uint32x4_t __arm_vminq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
1938	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u8)))
1939	uint8x16_t __arm_vminq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
1940	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u8)))
1941	uint8x16_t __arm_vminq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
1942	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s16)))
1943	int16_t __arm_vminvq_s16(int16_t, int16x8_t);
1944	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s16)))
1945	int16_t __arm_vminvq(int16_t, int16x8_t);
1946	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s32)))
1947	int32_t __arm_vminvq_s32(int32_t, int32x4_t);
1948	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s32)))
1949	int32_t __arm_vminvq(int32_t, int32x4_t);
1950	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s8)))
1951	int8_t __arm_vminvq_s8(int8_t, int8x16_t);
1952	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s8)))
1953	int8_t __arm_vminvq(int8_t, int8x16_t);
1954	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u16)))
1955	uint16_t __arm_vminvq_u16(uint16_t, uint16x8_t);
1956	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u16)))
1957	uint16_t __arm_vminvq(uint16_t, uint16x8_t);
1958	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u32)))
1959	uint32_t __arm_vminvq_u32(uint32_t, uint32x4_t);
1960	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u32)))
1961	uint32_t __arm_vminvq(uint32_t, uint32x4_t);
1962	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u8)))
1963	uint8_t __arm_vminvq_u8(uint8_t, uint8x16_t);
1964	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u8)))
1965	uint8_t __arm_vminvq(uint8_t, uint8x16_t);
1966	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s16)))
1967	int32_t __arm_vmladavaq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
1968	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s16)))
1969	int32_t __arm_vmladavaq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
1970	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s32)))
1971	int32_t __arm_vmladavaq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
1972	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s32)))
1973	int32_t __arm_vmladavaq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
1974	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s8)))
1975	int32_t __arm_vmladavaq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
1976	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s8)))
1977	int32_t __arm_vmladavaq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
1978	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u16)))
1979	uint32_t __arm_vmladavaq_p_u16(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1980	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u16)))
1981	uint32_t __arm_vmladavaq_p(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
1982	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u32)))
1983	uint32_t __arm_vmladavaq_p_u32(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1984	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u32)))
1985	uint32_t __arm_vmladavaq_p(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
1986	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u8)))
1987	uint32_t __arm_vmladavaq_p_u8(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1988	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u8)))
1989	uint32_t __arm_vmladavaq_p(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
1990	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s16)))
1991	int32_t __arm_vmladavaq_s16(int32_t, int16x8_t, int16x8_t);
1992	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s16)))
1993	int32_t __arm_vmladavaq(int32_t, int16x8_t, int16x8_t);
1994	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s32)))
1995	int32_t __arm_vmladavaq_s32(int32_t, int32x4_t, int32x4_t);
1996	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s32)))
1997	int32_t __arm_vmladavaq(int32_t, int32x4_t, int32x4_t);
1998	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s8)))
1999	int32_t __arm_vmladavaq_s8(int32_t, int8x16_t, int8x16_t);
2000	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s8)))
2001	int32_t __arm_vmladavaq(int32_t, int8x16_t, int8x16_t);
2002	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u16)))
2003	uint32_t __arm_vmladavaq_u16(uint32_t, uint16x8_t, uint16x8_t);
2004	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u16)))
2005	uint32_t __arm_vmladavaq(uint32_t, uint16x8_t, uint16x8_t);
2006	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u32)))
2007	uint32_t __arm_vmladavaq_u32(uint32_t, uint32x4_t, uint32x4_t);
2008	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u32)))
2009	uint32_t __arm_vmladavaq(uint32_t, uint32x4_t, uint32x4_t);
2010	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u8)))
2011	uint32_t __arm_vmladavaq_u8(uint32_t, uint8x16_t, uint8x16_t);
2012	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u8)))
2013	uint32_t __arm_vmladavaq(uint32_t, uint8x16_t, uint8x16_t);
2014	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s16)))
2015	int32_t __arm_vmladavaxq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2016	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s16)))
2017	int32_t __arm_vmladavaxq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2018	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s32)))
2019	int32_t __arm_vmladavaxq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2020	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s32)))
2021	int32_t __arm_vmladavaxq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2022	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s8)))
2023	int32_t __arm_vmladavaxq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2024	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s8)))
2025	int32_t __arm_vmladavaxq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2026	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s16)))
2027	int32_t __arm_vmladavaxq_s16(int32_t, int16x8_t, int16x8_t);
2028	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s16)))
2029	int32_t __arm_vmladavaxq(int32_t, int16x8_t, int16x8_t);
2030	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s32)))
2031	int32_t __arm_vmladavaxq_s32(int32_t, int32x4_t, int32x4_t);
2032	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s32)))
2033	int32_t __arm_vmladavaxq(int32_t, int32x4_t, int32x4_t);
2034	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s8)))
2035	int32_t __arm_vmladavaxq_s8(int32_t, int8x16_t, int8x16_t);
2036	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s8)))
2037	int32_t __arm_vmladavaxq(int32_t, int8x16_t, int8x16_t);
2038	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s16)))
2039	int32_t __arm_vmladavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2040	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s16)))
2041	int32_t __arm_vmladavq_p(int16x8_t, int16x8_t, mve_pred16_t);
2042	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s32)))
2043	int32_t __arm_vmladavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2044	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s32)))
2045	int32_t __arm_vmladavq_p(int32x4_t, int32x4_t, mve_pred16_t);
2046	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s8)))
2047	int32_t __arm_vmladavq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
2048	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s8)))
2049	int32_t __arm_vmladavq_p(int8x16_t, int8x16_t, mve_pred16_t);
2050	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u16)))
2051	uint32_t __arm_vmladavq_p_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2052	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u16)))
2053	uint32_t __arm_vmladavq_p(uint16x8_t, uint16x8_t, mve_pred16_t);
2054	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u32)))
2055	uint32_t __arm_vmladavq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2056	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u32)))
2057	uint32_t __arm_vmladavq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
2058	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u8)))
2059	uint32_t __arm_vmladavq_p_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2060	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u8)))
2061	uint32_t __arm_vmladavq_p(uint8x16_t, uint8x16_t, mve_pred16_t);
2062	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s16)))
2063	int32_t __arm_vmladavq_s16(int16x8_t, int16x8_t);
2064	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s16)))
2065	int32_t __arm_vmladavq(int16x8_t, int16x8_t);
2066	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s32)))
2067	int32_t __arm_vmladavq_s32(int32x4_t, int32x4_t);
2068	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s32)))
2069	int32_t __arm_vmladavq(int32x4_t, int32x4_t);
2070	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s8)))
2071	int32_t __arm_vmladavq_s8(int8x16_t, int8x16_t);
2072	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s8)))
2073	int32_t __arm_vmladavq(int8x16_t, int8x16_t);
2074	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u16)))
2075	uint32_t __arm_vmladavq_u16(uint16x8_t, uint16x8_t);
2076	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u16)))
2077	uint32_t __arm_vmladavq(uint16x8_t, uint16x8_t);
2078	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u32)))
2079	uint32_t __arm_vmladavq_u32(uint32x4_t, uint32x4_t);
2080	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u32)))
2081	uint32_t __arm_vmladavq(uint32x4_t, uint32x4_t);
2082	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u8)))
2083	uint32_t __arm_vmladavq_u8(uint8x16_t, uint8x16_t);
2084	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u8)))
2085	uint32_t __arm_vmladavq(uint8x16_t, uint8x16_t);
2086	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s16)))
2087	int32_t __arm_vmladavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2088	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s16)))
2089	int32_t __arm_vmladavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
2090	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s32)))
2091	int32_t __arm_vmladavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2092	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s32)))
2093	int32_t __arm_vmladavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
2094	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s8)))
2095	int32_t __arm_vmladavxq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
2096	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s8)))
2097	int32_t __arm_vmladavxq_p(int8x16_t, int8x16_t, mve_pred16_t);
2098	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s16)))
2099	int32_t __arm_vmladavxq_s16(int16x8_t, int16x8_t);
2100	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s16)))
2101	int32_t __arm_vmladavxq(int16x8_t, int16x8_t);
2102	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s32)))
2103	int32_t __arm_vmladavxq_s32(int32x4_t, int32x4_t);
2104	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s32)))
2105	int32_t __arm_vmladavxq(int32x4_t, int32x4_t);
2106	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s8)))
2107	int32_t __arm_vmladavxq_s8(int8x16_t, int8x16_t);
2108	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s8)))
2109	int32_t __arm_vmladavxq(int8x16_t, int8x16_t);
2110	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s16)))
2111	int64_t __arm_vmlaldavaq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2112	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s16)))
2113	int64_t __arm_vmlaldavaq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2114	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s32)))
2115	int64_t __arm_vmlaldavaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2116	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s32)))
2117	int64_t __arm_vmlaldavaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2118	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u16)))
2119	uint64_t __arm_vmlaldavaq_p_u16(uint64_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2120	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u16)))
2121	uint64_t __arm_vmlaldavaq_p(uint64_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2122	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u32)))
2123	uint64_t __arm_vmlaldavaq_p_u32(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2124	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u32)))
2125	uint64_t __arm_vmlaldavaq_p(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2126	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s16)))
2127	int64_t __arm_vmlaldavaq_s16(int64_t, int16x8_t, int16x8_t);
2128	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s16)))
2129	int64_t __arm_vmlaldavaq(int64_t, int16x8_t, int16x8_t);
2130	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s32)))
2131	int64_t __arm_vmlaldavaq_s32(int64_t, int32x4_t, int32x4_t);
2132	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s32)))
2133	int64_t __arm_vmlaldavaq(int64_t, int32x4_t, int32x4_t);
2134	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u16)))
2135	uint64_t __arm_vmlaldavaq_u16(uint64_t, uint16x8_t, uint16x8_t);
2136	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u16)))
2137	uint64_t __arm_vmlaldavaq(uint64_t, uint16x8_t, uint16x8_t);
2138	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u32)))
2139	uint64_t __arm_vmlaldavaq_u32(uint64_t, uint32x4_t, uint32x4_t);
2140	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u32)))
2141	uint64_t __arm_vmlaldavaq(uint64_t, uint32x4_t, uint32x4_t);
2142	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s16)))
2143	int64_t __arm_vmlaldavaxq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2144	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s16)))
2145	int64_t __arm_vmlaldavaxq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2146	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s32)))
2147	int64_t __arm_vmlaldavaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2148	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s32)))
2149	int64_t __arm_vmlaldavaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2150	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s16)))
2151	int64_t __arm_vmlaldavaxq_s16(int64_t, int16x8_t, int16x8_t);
2152	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s16)))
2153	int64_t __arm_vmlaldavaxq(int64_t, int16x8_t, int16x8_t);
2154	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s32)))
2155	int64_t __arm_vmlaldavaxq_s32(int64_t, int32x4_t, int32x4_t);
2156	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s32)))
2157	int64_t __arm_vmlaldavaxq(int64_t, int32x4_t, int32x4_t);
2158	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s16)))
2159	int64_t __arm_vmlaldavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2160	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s16)))
2161	int64_t __arm_vmlaldavq_p(int16x8_t, int16x8_t, mve_pred16_t);
2162	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s32)))
2163	int64_t __arm_vmlaldavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2164	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s32)))
2165	int64_t __arm_vmlaldavq_p(int32x4_t, int32x4_t, mve_pred16_t);
2166	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u16)))
2167	uint64_t __arm_vmlaldavq_p_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2168	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u16)))
2169	uint64_t __arm_vmlaldavq_p(uint16x8_t, uint16x8_t, mve_pred16_t);
2170	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u32)))
2171	uint64_t __arm_vmlaldavq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2172	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u32)))
2173	uint64_t __arm_vmlaldavq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
2174	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s16)))
2175	int64_t __arm_vmlaldavq_s16(int16x8_t, int16x8_t);
2176	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s16)))
2177	int64_t __arm_vmlaldavq(int16x8_t, int16x8_t);
2178	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s32)))
2179	int64_t __arm_vmlaldavq_s32(int32x4_t, int32x4_t);
2180	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s32)))
2181	int64_t __arm_vmlaldavq(int32x4_t, int32x4_t);
2182	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u16)))
2183	uint64_t __arm_vmlaldavq_u16(uint16x8_t, uint16x8_t);
2184	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u16)))
2185	uint64_t __arm_vmlaldavq(uint16x8_t, uint16x8_t);
2186	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u32)))
2187	uint64_t __arm_vmlaldavq_u32(uint32x4_t, uint32x4_t);
2188	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u32)))
2189	uint64_t __arm_vmlaldavq(uint32x4_t, uint32x4_t);
2190	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s16)))
2191	int64_t __arm_vmlaldavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2192	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s16)))
2193	int64_t __arm_vmlaldavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
2194	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s32)))
2195	int64_t __arm_vmlaldavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2196	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s32)))
2197	int64_t __arm_vmlaldavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
2198	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s16)))
2199	int64_t __arm_vmlaldavxq_s16(int16x8_t, int16x8_t);
2200	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s16)))
2201	int64_t __arm_vmlaldavxq(int16x8_t, int16x8_t);
2202	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s32)))
2203	int64_t __arm_vmlaldavxq_s32(int32x4_t, int32x4_t);
2204	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s32)))
2205	int64_t __arm_vmlaldavxq(int32x4_t, int32x4_t);
2206	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s16)))
2207	int32_t __arm_vmlsdavaq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2208	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s16)))
2209	int32_t __arm_vmlsdavaq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2210	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s32)))
2211	int32_t __arm_vmlsdavaq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2212	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s32)))
2213	int32_t __arm_vmlsdavaq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2214	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s8)))
2215	int32_t __arm_vmlsdavaq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2216	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s8)))
2217	int32_t __arm_vmlsdavaq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2218	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s16)))
2219	int32_t __arm_vmlsdavaq_s16(int32_t, int16x8_t, int16x8_t);
2220	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s16)))
2221	int32_t __arm_vmlsdavaq(int32_t, int16x8_t, int16x8_t);
2222	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s32)))
2223	int32_t __arm_vmlsdavaq_s32(int32_t, int32x4_t, int32x4_t);
2224	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s32)))
2225	int32_t __arm_vmlsdavaq(int32_t, int32x4_t, int32x4_t);
2226	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s8)))
2227	int32_t __arm_vmlsdavaq_s8(int32_t, int8x16_t, int8x16_t);
2228	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s8)))
2229	int32_t __arm_vmlsdavaq(int32_t, int8x16_t, int8x16_t);
2230	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s16)))
2231	int32_t __arm_vmlsdavaxq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2232	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s16)))
2233	int32_t __arm_vmlsdavaxq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
2234	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s32)))
2235	int32_t __arm_vmlsdavaxq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2236	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s32)))
2237	int32_t __arm_vmlsdavaxq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
2238	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s8)))
2239	int32_t __arm_vmlsdavaxq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2240	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s8)))
2241	int32_t __arm_vmlsdavaxq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
2242	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s16)))
2243	int32_t __arm_vmlsdavaxq_s16(int32_t, int16x8_t, int16x8_t);
2244	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s16)))
2245	int32_t __arm_vmlsdavaxq(int32_t, int16x8_t, int16x8_t);
2246	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s32)))
2247	int32_t __arm_vmlsdavaxq_s32(int32_t, int32x4_t, int32x4_t);
2248	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s32)))
2249	int32_t __arm_vmlsdavaxq(int32_t, int32x4_t, int32x4_t);
2250	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s8)))
2251	int32_t __arm_vmlsdavaxq_s8(int32_t, int8x16_t, int8x16_t);
2252	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s8)))
2253	int32_t __arm_vmlsdavaxq(int32_t, int8x16_t, int8x16_t);
2254	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s16)))
2255	int32_t __arm_vmlsdavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2256	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s16)))
2257	int32_t __arm_vmlsdavq_p(int16x8_t, int16x8_t, mve_pred16_t);
2258	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s32)))
2259	int32_t __arm_vmlsdavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2260	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s32)))
2261	int32_t __arm_vmlsdavq_p(int32x4_t, int32x4_t, mve_pred16_t);
2262	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s8)))
2263	int32_t __arm_vmlsdavq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
2264	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s8)))
2265	int32_t __arm_vmlsdavq_p(int8x16_t, int8x16_t, mve_pred16_t);
2266	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s16)))
2267	int32_t __arm_vmlsdavq_s16(int16x8_t, int16x8_t);
2268	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s16)))
2269	int32_t __arm_vmlsdavq(int16x8_t, int16x8_t);
2270	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s32)))
2271	int32_t __arm_vmlsdavq_s32(int32x4_t, int32x4_t);
2272	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s32)))
2273	int32_t __arm_vmlsdavq(int32x4_t, int32x4_t);
2274	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s8)))
2275	int32_t __arm_vmlsdavq_s8(int8x16_t, int8x16_t);
2276	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s8)))
2277	int32_t __arm_vmlsdavq(int8x16_t, int8x16_t);
2278	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s16)))
2279	int32_t __arm_vmlsdavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2280	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s16)))
2281	int32_t __arm_vmlsdavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
2282	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s32)))
2283	int32_t __arm_vmlsdavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2284	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s32)))
2285	int32_t __arm_vmlsdavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
2286	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s8)))
2287	int32_t __arm_vmlsdavxq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
2288	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s8)))
2289	int32_t __arm_vmlsdavxq_p(int8x16_t, int8x16_t, mve_pred16_t);
2290	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s16)))
2291	int32_t __arm_vmlsdavxq_s16(int16x8_t, int16x8_t);
2292	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s16)))
2293	int32_t __arm_vmlsdavxq(int16x8_t, int16x8_t);
2294	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s32)))
2295	int32_t __arm_vmlsdavxq_s32(int32x4_t, int32x4_t);
2296	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s32)))
2297	int32_t __arm_vmlsdavxq(int32x4_t, int32x4_t);
2298	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s8)))
2299	int32_t __arm_vmlsdavxq_s8(int8x16_t, int8x16_t);
2300	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s8)))
2301	int32_t __arm_vmlsdavxq(int8x16_t, int8x16_t);
2302	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s16)))
2303	int64_t __arm_vmlsldavaq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2304	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s16)))
2305	int64_t __arm_vmlsldavaq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2306	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s32)))
2307	int64_t __arm_vmlsldavaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2308	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s32)))
2309	int64_t __arm_vmlsldavaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2310	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s16)))
2311	int64_t __arm_vmlsldavaq_s16(int64_t, int16x8_t, int16x8_t);
2312	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s16)))
2313	int64_t __arm_vmlsldavaq(int64_t, int16x8_t, int16x8_t);
2314	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s32)))
2315	int64_t __arm_vmlsldavaq_s32(int64_t, int32x4_t, int32x4_t);
2316	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s32)))
2317	int64_t __arm_vmlsldavaq(int64_t, int32x4_t, int32x4_t);
2318	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s16)))
2319	int64_t __arm_vmlsldavaxq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2320	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s16)))
2321	int64_t __arm_vmlsldavaxq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
2322	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s32)))
2323	int64_t __arm_vmlsldavaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2324	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s32)))
2325	int64_t __arm_vmlsldavaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
2326	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s16)))
2327	int64_t __arm_vmlsldavaxq_s16(int64_t, int16x8_t, int16x8_t);
2328	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s16)))
2329	int64_t __arm_vmlsldavaxq(int64_t, int16x8_t, int16x8_t);
2330	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s32)))
2331	int64_t __arm_vmlsldavaxq_s32(int64_t, int32x4_t, int32x4_t);
2332	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s32)))
2333	int64_t __arm_vmlsldavaxq(int64_t, int32x4_t, int32x4_t);
2334	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s16)))
2335	int64_t __arm_vmlsldavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2336	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s16)))
2337	int64_t __arm_vmlsldavq_p(int16x8_t, int16x8_t, mve_pred16_t);
2338	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s32)))
2339	int64_t __arm_vmlsldavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2340	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s32)))
2341	int64_t __arm_vmlsldavq_p(int32x4_t, int32x4_t, mve_pred16_t);
2342	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s16)))
2343	int64_t __arm_vmlsldavq_s16(int16x8_t, int16x8_t);
2344	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s16)))
2345	int64_t __arm_vmlsldavq(int16x8_t, int16x8_t);
2346	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s32)))
2347	int64_t __arm_vmlsldavq_s32(int32x4_t, int32x4_t);
2348	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s32)))
2349	int64_t __arm_vmlsldavq(int32x4_t, int32x4_t);
2350	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s16)))
2351	int64_t __arm_vmlsldavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
2352	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s16)))
2353	int64_t __arm_vmlsldavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
2354	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s32)))
2355	int64_t __arm_vmlsldavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
2356	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s32)))
2357	int64_t __arm_vmlsldavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
2358	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s16)))
2359	int64_t __arm_vmlsldavxq_s16(int16x8_t, int16x8_t);
2360	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s16)))
2361	int64_t __arm_vmlsldavxq(int16x8_t, int16x8_t);
2362	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s32)))
2363	int64_t __arm_vmlsldavxq_s32(int32x4_t, int32x4_t);
2364	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s32)))
2365	int64_t __arm_vmlsldavxq(int32x4_t, int32x4_t);
2366	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s16)))
2367	int16x8_t __arm_vmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2368	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s16)))
2369	int16x8_t __arm_vmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2370	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s32)))
2371	int32x4_t __arm_vmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2372	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s32)))
2373	int32x4_t __arm_vmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2374	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s8)))
2375	int8x16_t __arm_vmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2376	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s8)))
2377	int8x16_t __arm_vmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2378	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u16)))
2379	uint16x8_t __arm_vmulhq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2380	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u16)))
2381	uint16x8_t __arm_vmulhq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2382	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u32)))
2383	uint32x4_t __arm_vmulhq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2384	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u32)))
2385	uint32x4_t __arm_vmulhq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2386	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u8)))
2387	uint8x16_t __arm_vmulhq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2388	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u8)))
2389	uint8x16_t __arm_vmulhq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2390	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s16)))
2391	int16x8_t __arm_vmulhq_s16(int16x8_t, int16x8_t);
2392	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s16)))
2393	int16x8_t __arm_vmulhq(int16x8_t, int16x8_t);
2394	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s32)))
2395	int32x4_t __arm_vmulhq_s32(int32x4_t, int32x4_t);
2396	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s32)))
2397	int32x4_t __arm_vmulhq(int32x4_t, int32x4_t);
2398	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s8)))
2399	int8x16_t __arm_vmulhq_s8(int8x16_t, int8x16_t);
2400	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s8)))
2401	int8x16_t __arm_vmulhq(int8x16_t, int8x16_t);
2402	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u16)))
2403	uint16x8_t __arm_vmulhq_u16(uint16x8_t, uint16x8_t);
2404	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u16)))
2405	uint16x8_t __arm_vmulhq(uint16x8_t, uint16x8_t);
2406	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u32)))
2407	uint32x4_t __arm_vmulhq_u32(uint32x4_t, uint32x4_t);
2408	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u32)))
2409	uint32x4_t __arm_vmulhq(uint32x4_t, uint32x4_t);
2410	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u8)))
2411	uint8x16_t __arm_vmulhq_u8(uint8x16_t, uint8x16_t);
2412	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u8)))
2413	uint8x16_t __arm_vmulhq(uint8x16_t, uint8x16_t);
2414	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s16)))
2415	int16x8_t __arm_vmulhq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2416	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s16)))
2417	int16x8_t __arm_vmulhq_x(int16x8_t, int16x8_t, mve_pred16_t);
2418	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s32)))
2419	int32x4_t __arm_vmulhq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2420	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s32)))
2421	int32x4_t __arm_vmulhq_x(int32x4_t, int32x4_t, mve_pred16_t);
2422	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s8)))
2423	int8x16_t __arm_vmulhq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2424	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s8)))
2425	int8x16_t __arm_vmulhq_x(int8x16_t, int8x16_t, mve_pred16_t);
2426	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u16)))
2427	uint16x8_t __arm_vmulhq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2428	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u16)))
2429	uint16x8_t __arm_vmulhq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2430	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u32)))
2431	uint32x4_t __arm_vmulhq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2432	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u32)))
2433	uint32x4_t __arm_vmulhq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2434	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u8)))
2435	uint8x16_t __arm_vmulhq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2436	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u8)))
2437	uint8x16_t __arm_vmulhq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2438	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s16)))
2439	int32x4_t __arm_vmullbq_int_m_s16(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
2440	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s16)))
2441	int32x4_t __arm_vmullbq_int_m(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
2442	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s32)))
2443	int64x2_t __arm_vmullbq_int_m_s32(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
2444	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s32)))
2445	int64x2_t __arm_vmullbq_int_m(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
2446	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s8)))
2447	int16x8_t __arm_vmullbq_int_m_s8(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
2448	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s8)))
2449	int16x8_t __arm_vmullbq_int_m(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
2450	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u16)))
2451	uint32x4_t __arm_vmullbq_int_m_u16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2452	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u16)))
2453	uint32x4_t __arm_vmullbq_int_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2454	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u32)))
2455	uint64x2_t __arm_vmullbq_int_m_u32(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2456	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u32)))
2457	uint64x2_t __arm_vmullbq_int_m(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2458	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u8)))
2459	uint16x8_t __arm_vmullbq_int_m_u8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2460	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u8)))
2461	uint16x8_t __arm_vmullbq_int_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2462	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s16)))
2463	int32x4_t __arm_vmullbq_int_s16(int16x8_t, int16x8_t);
2464	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s16)))
2465	int32x4_t __arm_vmullbq_int(int16x8_t, int16x8_t);
2466	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s32)))
2467	int64x2_t __arm_vmullbq_int_s32(int32x4_t, int32x4_t);
2468	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s32)))
2469	int64x2_t __arm_vmullbq_int(int32x4_t, int32x4_t);
2470	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s8)))
2471	int16x8_t __arm_vmullbq_int_s8(int8x16_t, int8x16_t);
2472	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s8)))
2473	int16x8_t __arm_vmullbq_int(int8x16_t, int8x16_t);
2474	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u16)))
2475	uint32x4_t __arm_vmullbq_int_u16(uint16x8_t, uint16x8_t);
2476	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u16)))
2477	uint32x4_t __arm_vmullbq_int(uint16x8_t, uint16x8_t);
2478	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u32)))
2479	uint64x2_t __arm_vmullbq_int_u32(uint32x4_t, uint32x4_t);
2480	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u32)))
2481	uint64x2_t __arm_vmullbq_int(uint32x4_t, uint32x4_t);
2482	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u8)))
2483	uint16x8_t __arm_vmullbq_int_u8(uint8x16_t, uint8x16_t);
2484	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u8)))
2485	uint16x8_t __arm_vmullbq_int(uint8x16_t, uint8x16_t);
2486	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s16)))
2487	int32x4_t __arm_vmullbq_int_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2488	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s16)))
2489	int32x4_t __arm_vmullbq_int_x(int16x8_t, int16x8_t, mve_pred16_t);
2490	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s32)))
2491	int64x2_t __arm_vmullbq_int_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2492	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s32)))
2493	int64x2_t __arm_vmullbq_int_x(int32x4_t, int32x4_t, mve_pred16_t);
2494	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s8)))
2495	int16x8_t __arm_vmullbq_int_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2496	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s8)))
2497	int16x8_t __arm_vmullbq_int_x(int8x16_t, int8x16_t, mve_pred16_t);
2498	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u16)))
2499	uint32x4_t __arm_vmullbq_int_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2500	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u16)))
2501	uint32x4_t __arm_vmullbq_int_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2502	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u32)))
2503	uint64x2_t __arm_vmullbq_int_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2504	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u32)))
2505	uint64x2_t __arm_vmullbq_int_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2506	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u8)))
2507	uint16x8_t __arm_vmullbq_int_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2508	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u8)))
2509	uint16x8_t __arm_vmullbq_int_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2510	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p16)))
2511	uint32x4_t __arm_vmullbq_poly_m_p16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2512	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p16)))
2513	uint32x4_t __arm_vmullbq_poly_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2514	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p8)))
2515	uint16x8_t __arm_vmullbq_poly_m_p8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2516	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p8)))
2517	uint16x8_t __arm_vmullbq_poly_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2518	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p16)))
2519	uint32x4_t __arm_vmullbq_poly_p16(uint16x8_t, uint16x8_t);
2520	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p16)))
2521	uint32x4_t __arm_vmullbq_poly(uint16x8_t, uint16x8_t);
2522	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p8)))
2523	uint16x8_t __arm_vmullbq_poly_p8(uint8x16_t, uint8x16_t);
2524	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p8)))
2525	uint16x8_t __arm_vmullbq_poly(uint8x16_t, uint8x16_t);
2526	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p16)))
2527	uint32x4_t __arm_vmullbq_poly_x_p16(uint16x8_t, uint16x8_t, mve_pred16_t);
2528	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p16)))
2529	uint32x4_t __arm_vmullbq_poly_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2530	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p8)))
2531	uint16x8_t __arm_vmullbq_poly_x_p8(uint8x16_t, uint8x16_t, mve_pred16_t);
2532	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p8)))
2533	uint16x8_t __arm_vmullbq_poly_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2534	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s16)))
2535	int32x4_t __arm_vmulltq_int_m_s16(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
2536	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s16)))
2537	int32x4_t __arm_vmulltq_int_m(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
2538	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s32)))
2539	int64x2_t __arm_vmulltq_int_m_s32(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
2540	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s32)))
2541	int64x2_t __arm_vmulltq_int_m(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
2542	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s8)))
2543	int16x8_t __arm_vmulltq_int_m_s8(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
2544	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s8)))
2545	int16x8_t __arm_vmulltq_int_m(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
2546	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u16)))
2547	uint32x4_t __arm_vmulltq_int_m_u16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2548	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u16)))
2549	uint32x4_t __arm_vmulltq_int_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2550	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u32)))
2551	uint64x2_t __arm_vmulltq_int_m_u32(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2552	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u32)))
2553	uint64x2_t __arm_vmulltq_int_m(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2554	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u8)))
2555	uint16x8_t __arm_vmulltq_int_m_u8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2556	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u8)))
2557	uint16x8_t __arm_vmulltq_int_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2558	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s16)))
2559	int32x4_t __arm_vmulltq_int_s16(int16x8_t, int16x8_t);
2560	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s16)))
2561	int32x4_t __arm_vmulltq_int(int16x8_t, int16x8_t);
2562	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s32)))
2563	int64x2_t __arm_vmulltq_int_s32(int32x4_t, int32x4_t);
2564	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s32)))
2565	int64x2_t __arm_vmulltq_int(int32x4_t, int32x4_t);
2566	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s8)))
2567	int16x8_t __arm_vmulltq_int_s8(int8x16_t, int8x16_t);
2568	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s8)))
2569	int16x8_t __arm_vmulltq_int(int8x16_t, int8x16_t);
2570	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u16)))
2571	uint32x4_t __arm_vmulltq_int_u16(uint16x8_t, uint16x8_t);
2572	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u16)))
2573	uint32x4_t __arm_vmulltq_int(uint16x8_t, uint16x8_t);
2574	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u32)))
2575	uint64x2_t __arm_vmulltq_int_u32(uint32x4_t, uint32x4_t);
2576	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u32)))
2577	uint64x2_t __arm_vmulltq_int(uint32x4_t, uint32x4_t);
2578	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u8)))
2579	uint16x8_t __arm_vmulltq_int_u8(uint8x16_t, uint8x16_t);
2580	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u8)))
2581	uint16x8_t __arm_vmulltq_int(uint8x16_t, uint8x16_t);
2582	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s16)))
2583	int32x4_t __arm_vmulltq_int_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2584	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s16)))
2585	int32x4_t __arm_vmulltq_int_x(int16x8_t, int16x8_t, mve_pred16_t);
2586	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s32)))
2587	int64x2_t __arm_vmulltq_int_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2588	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s32)))
2589	int64x2_t __arm_vmulltq_int_x(int32x4_t, int32x4_t, mve_pred16_t);
2590	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s8)))
2591	int16x8_t __arm_vmulltq_int_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2592	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s8)))
2593	int16x8_t __arm_vmulltq_int_x(int8x16_t, int8x16_t, mve_pred16_t);
2594	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u16)))
2595	uint32x4_t __arm_vmulltq_int_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2596	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u16)))
2597	uint32x4_t __arm_vmulltq_int_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2598	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u32)))
2599	uint64x2_t __arm_vmulltq_int_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2600	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u32)))
2601	uint64x2_t __arm_vmulltq_int_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2602	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u8)))
2603	uint16x8_t __arm_vmulltq_int_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2604	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u8)))
2605	uint16x8_t __arm_vmulltq_int_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2606	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p16)))
2607	uint32x4_t __arm_vmulltq_poly_m_p16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2608	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p16)))
2609	uint32x4_t __arm_vmulltq_poly_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2610	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p8)))
2611	uint16x8_t __arm_vmulltq_poly_m_p8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2612	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p8)))
2613	uint16x8_t __arm_vmulltq_poly_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2614	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p16)))
2615	uint32x4_t __arm_vmulltq_poly_p16(uint16x8_t, uint16x8_t);
2616	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p16)))
2617	uint32x4_t __arm_vmulltq_poly(uint16x8_t, uint16x8_t);
2618	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p8)))
2619	uint16x8_t __arm_vmulltq_poly_p8(uint8x16_t, uint8x16_t);
2620	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p8)))
2621	uint16x8_t __arm_vmulltq_poly(uint8x16_t, uint8x16_t);
2622	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p16)))
2623	uint32x4_t __arm_vmulltq_poly_x_p16(uint16x8_t, uint16x8_t, mve_pred16_t);
2624	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p16)))
2625	uint32x4_t __arm_vmulltq_poly_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2626	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p8)))
2627	uint16x8_t __arm_vmulltq_poly_x_p8(uint8x16_t, uint8x16_t, mve_pred16_t);
2628	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p8)))
2629	uint16x8_t __arm_vmulltq_poly_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2630	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s16)))
2631	int16x8_t __arm_vmulq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2632	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s16)))
2633	int16x8_t __arm_vmulq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2634	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s32)))
2635	int32x4_t __arm_vmulq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2636	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s32)))
2637	int32x4_t __arm_vmulq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2638	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s8)))
2639	int8x16_t __arm_vmulq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2640	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s8)))
2641	int8x16_t __arm_vmulq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2642	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u16)))
2643	uint16x8_t __arm_vmulq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2644	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u16)))
2645	uint16x8_t __arm_vmulq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2646	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u32)))
2647	uint32x4_t __arm_vmulq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2648	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u32)))
2649	uint32x4_t __arm_vmulq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2650	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u8)))
2651	uint8x16_t __arm_vmulq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2652	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u8)))
2653	uint8x16_t __arm_vmulq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2654	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s16)))
2655	int16x8_t __arm_vmulq_s16(int16x8_t, int16x8_t);
2656	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s16)))
2657	int16x8_t __arm_vmulq(int16x8_t, int16x8_t);
2658	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s32)))
2659	int32x4_t __arm_vmulq_s32(int32x4_t, int32x4_t);
2660	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s32)))
2661	int32x4_t __arm_vmulq(int32x4_t, int32x4_t);
2662	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s8)))
2663	int8x16_t __arm_vmulq_s8(int8x16_t, int8x16_t);
2664	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s8)))
2665	int8x16_t __arm_vmulq(int8x16_t, int8x16_t);
2666	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u16)))
2667	uint16x8_t __arm_vmulq_u16(uint16x8_t, uint16x8_t);
2668	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u16)))
2669	uint16x8_t __arm_vmulq(uint16x8_t, uint16x8_t);
2670	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u32)))
2671	uint32x4_t __arm_vmulq_u32(uint32x4_t, uint32x4_t);
2672	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u32)))
2673	uint32x4_t __arm_vmulq(uint32x4_t, uint32x4_t);
2674	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u8)))
2675	uint8x16_t __arm_vmulq_u8(uint8x16_t, uint8x16_t);
2676	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u8)))
2677	uint8x16_t __arm_vmulq(uint8x16_t, uint8x16_t);
2678	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s16)))
2679	int16x8_t __arm_vmulq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2680	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s16)))
2681	int16x8_t __arm_vmulq_x(int16x8_t, int16x8_t, mve_pred16_t);
2682	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s32)))
2683	int32x4_t __arm_vmulq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2684	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s32)))
2685	int32x4_t __arm_vmulq_x(int32x4_t, int32x4_t, mve_pred16_t);
2686	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s8)))
2687	int8x16_t __arm_vmulq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2688	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s8)))
2689	int8x16_t __arm_vmulq_x(int8x16_t, int8x16_t, mve_pred16_t);
2690	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u16)))
2691	uint16x8_t __arm_vmulq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2692	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u16)))
2693	uint16x8_t __arm_vmulq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2694	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u32)))
2695	uint32x4_t __arm_vmulq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2696	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u32)))
2697	uint32x4_t __arm_vmulq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2698	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u8)))
2699	uint8x16_t __arm_vmulq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2700	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u8)))
2701	uint8x16_t __arm_vmulq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2702	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s16)))
2703	int16x8_t __arm_vornq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2704	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s16)))
2705	int16x8_t __arm_vornq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2706	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s32)))
2707	int32x4_t __arm_vornq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2708	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s32)))
2709	int32x4_t __arm_vornq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2710	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s8)))
2711	int8x16_t __arm_vornq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2712	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s8)))
2713	int8x16_t __arm_vornq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2714	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u16)))
2715	uint16x8_t __arm_vornq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2716	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u16)))
2717	uint16x8_t __arm_vornq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2718	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u32)))
2719	uint32x4_t __arm_vornq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2720	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u32)))
2721	uint32x4_t __arm_vornq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2722	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u8)))
2723	uint8x16_t __arm_vornq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2724	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u8)))
2725	uint8x16_t __arm_vornq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2726	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s16)))
2727	int16x8_t __arm_vornq_s16(int16x8_t, int16x8_t);
2728	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s16)))
2729	int16x8_t __arm_vornq(int16x8_t, int16x8_t);
2730	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s32)))
2731	int32x4_t __arm_vornq_s32(int32x4_t, int32x4_t);
2732	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s32)))
2733	int32x4_t __arm_vornq(int32x4_t, int32x4_t);
2734	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s8)))
2735	int8x16_t __arm_vornq_s8(int8x16_t, int8x16_t);
2736	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s8)))
2737	int8x16_t __arm_vornq(int8x16_t, int8x16_t);
2738	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u16)))
2739	uint16x8_t __arm_vornq_u16(uint16x8_t, uint16x8_t);
2740	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u16)))
2741	uint16x8_t __arm_vornq(uint16x8_t, uint16x8_t);
2742	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u32)))
2743	uint32x4_t __arm_vornq_u32(uint32x4_t, uint32x4_t);
2744	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u32)))
2745	uint32x4_t __arm_vornq(uint32x4_t, uint32x4_t);
2746	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u8)))
2747	uint8x16_t __arm_vornq_u8(uint8x16_t, uint8x16_t);
2748	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u8)))
2749	uint8x16_t __arm_vornq(uint8x16_t, uint8x16_t);
2750	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s16)))
2751	int16x8_t __arm_vornq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2752	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s16)))
2753	int16x8_t __arm_vornq_x(int16x8_t, int16x8_t, mve_pred16_t);
2754	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s32)))
2755	int32x4_t __arm_vornq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2756	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s32)))
2757	int32x4_t __arm_vornq_x(int32x4_t, int32x4_t, mve_pred16_t);
2758	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s8)))
2759	int8x16_t __arm_vornq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2760	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s8)))
2761	int8x16_t __arm_vornq_x(int8x16_t, int8x16_t, mve_pred16_t);
2762	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u16)))
2763	uint16x8_t __arm_vornq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2764	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u16)))
2765	uint16x8_t __arm_vornq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2766	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u32)))
2767	uint32x4_t __arm_vornq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2768	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u32)))
2769	uint32x4_t __arm_vornq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2770	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u8)))
2771	uint8x16_t __arm_vornq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2772	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u8)))
2773	uint8x16_t __arm_vornq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2774	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s16)))
2775	int16x8_t __arm_vorrq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2776	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s16)))
2777	int16x8_t __arm_vorrq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2778	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s32)))
2779	int32x4_t __arm_vorrq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2780	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s32)))
2781	int32x4_t __arm_vorrq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2782	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s8)))
2783	int8x16_t __arm_vorrq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2784	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s8)))
2785	int8x16_t __arm_vorrq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2786	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u16)))
2787	uint16x8_t __arm_vorrq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2788	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u16)))
2789	uint16x8_t __arm_vorrq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2790	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u32)))
2791	uint32x4_t __arm_vorrq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2792	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u32)))
2793	uint32x4_t __arm_vorrq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2794	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u8)))
2795	uint8x16_t __arm_vorrq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2796	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u8)))
2797	uint8x16_t __arm_vorrq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2798	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s16)))
2799	int16x8_t __arm_vorrq_s16(int16x8_t, int16x8_t);
2800	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s16)))
2801	int16x8_t __arm_vorrq(int16x8_t, int16x8_t);
2802	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s32)))
2803	int32x4_t __arm_vorrq_s32(int32x4_t, int32x4_t);
2804	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s32)))
2805	int32x4_t __arm_vorrq(int32x4_t, int32x4_t);
2806	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s8)))
2807	int8x16_t __arm_vorrq_s8(int8x16_t, int8x16_t);
2808	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s8)))
2809	int8x16_t __arm_vorrq(int8x16_t, int8x16_t);
2810	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u16)))
2811	uint16x8_t __arm_vorrq_u16(uint16x8_t, uint16x8_t);
2812	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u16)))
2813	uint16x8_t __arm_vorrq(uint16x8_t, uint16x8_t);
2814	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u32)))
2815	uint32x4_t __arm_vorrq_u32(uint32x4_t, uint32x4_t);
2816	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u32)))
2817	uint32x4_t __arm_vorrq(uint32x4_t, uint32x4_t);
2818	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u8)))
2819	uint8x16_t __arm_vorrq_u8(uint8x16_t, uint8x16_t);
2820	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u8)))
2821	uint8x16_t __arm_vorrq(uint8x16_t, uint8x16_t);
2822	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s16)))
2823	int16x8_t __arm_vorrq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
2824	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s16)))
2825	int16x8_t __arm_vorrq_x(int16x8_t, int16x8_t, mve_pred16_t);
2826	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s32)))
2827	int32x4_t __arm_vorrq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
2828	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s32)))
2829	int32x4_t __arm_vorrq_x(int32x4_t, int32x4_t, mve_pred16_t);
2830	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s8)))
2831	int8x16_t __arm_vorrq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
2832	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s8)))
2833	int8x16_t __arm_vorrq_x(int8x16_t, int8x16_t, mve_pred16_t);
2834	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u16)))
2835	uint16x8_t __arm_vorrq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2836	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u16)))
2837	uint16x8_t __arm_vorrq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
2838	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u32)))
2839	uint32x4_t __arm_vorrq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2840	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u32)))
2841	uint32x4_t __arm_vorrq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
2842	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u8)))
2843	uint8x16_t __arm_vorrq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2844	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u8)))
2845	uint8x16_t __arm_vorrq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
2846	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpnot)))
2847	mve_pred16_t __arm_vpnot(mve_pred16_t);
2848	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s16)))
2849	int16x8_t __arm_vpselq_s16(int16x8_t, int16x8_t, mve_pred16_t);
2850	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s16)))
2851	int16x8_t __arm_vpselq(int16x8_t, int16x8_t, mve_pred16_t);
2852	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s32)))
2853	int32x4_t __arm_vpselq_s32(int32x4_t, int32x4_t, mve_pred16_t);
2854	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s32)))
2855	int32x4_t __arm_vpselq(int32x4_t, int32x4_t, mve_pred16_t);
2856	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s64)))
2857	int64x2_t __arm_vpselq_s64(int64x2_t, int64x2_t, mve_pred16_t);
2858	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s64)))
2859	int64x2_t __arm_vpselq(int64x2_t, int64x2_t, mve_pred16_t);
2860	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s8)))
2861	int8x16_t __arm_vpselq_s8(int8x16_t, int8x16_t, mve_pred16_t);
2862	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s8)))
2863	int8x16_t __arm_vpselq(int8x16_t, int8x16_t, mve_pred16_t);
2864	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u16)))
2865	uint16x8_t __arm_vpselq_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
2866	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u16)))
2867	uint16x8_t __arm_vpselq(uint16x8_t, uint16x8_t, mve_pred16_t);
2868	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u32)))
2869	uint32x4_t __arm_vpselq_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
2870	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u32)))
2871	uint32x4_t __arm_vpselq(uint32x4_t, uint32x4_t, mve_pred16_t);
2872	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u64)))
2873	uint64x2_t __arm_vpselq_u64(uint64x2_t, uint64x2_t, mve_pred16_t);
2874	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u64)))
2875	uint64x2_t __arm_vpselq(uint64x2_t, uint64x2_t, mve_pred16_t);
2876	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u8)))
2877	uint8x16_t __arm_vpselq_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
2878	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u8)))
2879	uint8x16_t __arm_vpselq(uint8x16_t, uint8x16_t, mve_pred16_t);
2880	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s16)))
2881	int16x8_t __arm_vqaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2882	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s16)))
2883	int16x8_t __arm_vqaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2884	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s32)))
2885	int32x4_t __arm_vqaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2886	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s32)))
2887	int32x4_t __arm_vqaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2888	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s8)))
2889	int8x16_t __arm_vqaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2890	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s8)))
2891	int8x16_t __arm_vqaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2892	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u16)))
2893	uint16x8_t __arm_vqaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2894	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u16)))
2895	uint16x8_t __arm_vqaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
2896	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u32)))
2897	uint32x4_t __arm_vqaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2898	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u32)))
2899	uint32x4_t __arm_vqaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
2900	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u8)))
2901	uint8x16_t __arm_vqaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2902	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u8)))
2903	uint8x16_t __arm_vqaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
2904	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s16)))
2905	int16x8_t __arm_vqaddq_s16(int16x8_t, int16x8_t);
2906	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s16)))
2907	int16x8_t __arm_vqaddq(int16x8_t, int16x8_t);
2908	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s32)))
2909	int32x4_t __arm_vqaddq_s32(int32x4_t, int32x4_t);
2910	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s32)))
2911	int32x4_t __arm_vqaddq(int32x4_t, int32x4_t);
2912	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s8)))
2913	int8x16_t __arm_vqaddq_s8(int8x16_t, int8x16_t);
2914	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s8)))
2915	int8x16_t __arm_vqaddq(int8x16_t, int8x16_t);
2916	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u16)))
2917	uint16x8_t __arm_vqaddq_u16(uint16x8_t, uint16x8_t);
2918	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u16)))
2919	uint16x8_t __arm_vqaddq(uint16x8_t, uint16x8_t);
2920	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u32)))
2921	uint32x4_t __arm_vqaddq_u32(uint32x4_t, uint32x4_t);
2922	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u32)))
2923	uint32x4_t __arm_vqaddq(uint32x4_t, uint32x4_t);
2924	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u8)))
2925	uint8x16_t __arm_vqaddq_u8(uint8x16_t, uint8x16_t);
2926	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u8)))
2927	uint8x16_t __arm_vqaddq(uint8x16_t, uint8x16_t);
2928	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s16)))
2929	int16x8_t __arm_vqdmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2930	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s16)))
2931	int16x8_t __arm_vqdmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2932	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s32)))
2933	int32x4_t __arm_vqdmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2934	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s32)))
2935	int32x4_t __arm_vqdmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2936	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s8)))
2937	int8x16_t __arm_vqdmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2938	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s8)))
2939	int8x16_t __arm_vqdmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2940	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s16)))
2941	int16x8_t __arm_vqdmulhq_s16(int16x8_t, int16x8_t);
2942	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s16)))
2943	int16x8_t __arm_vqdmulhq(int16x8_t, int16x8_t);
2944	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s32)))
2945	int32x4_t __arm_vqdmulhq_s32(int32x4_t, int32x4_t);
2946	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s32)))
2947	int32x4_t __arm_vqdmulhq(int32x4_t, int32x4_t);
2948	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s8)))
2949	int8x16_t __arm_vqdmulhq_s8(int8x16_t, int8x16_t);
2950	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s8)))
2951	int8x16_t __arm_vqdmulhq(int8x16_t, int8x16_t);
2952	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s16)))
2953	int16x8_t __arm_vqrdmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2954	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s16)))
2955	int16x8_t __arm_vqrdmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
2956	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s32)))
2957	int32x4_t __arm_vqrdmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2958	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s32)))
2959	int32x4_t __arm_vqrdmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
2960	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s8)))
2961	int8x16_t __arm_vqrdmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2962	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s8)))
2963	int8x16_t __arm_vqrdmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
2964	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s16)))
2965	int16x8_t __arm_vqrdmulhq_s16(int16x8_t, int16x8_t);
2966	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s16)))
2967	int16x8_t __arm_vqrdmulhq(int16x8_t, int16x8_t);
2968	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s32)))
2969	int32x4_t __arm_vqrdmulhq_s32(int32x4_t, int32x4_t);
2970	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s32)))
2971	int32x4_t __arm_vqrdmulhq(int32x4_t, int32x4_t);
2972	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s8)))
2973	int8x16_t __arm_vqrdmulhq_s8(int8x16_t, int8x16_t);
2974	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s8)))
2975	int8x16_t __arm_vqrdmulhq(int8x16_t, int8x16_t);
2976	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s16)))
2977	int16x8_t __arm_vqrshlq_m_n_s16(int16x8_t, int32_t, mve_pred16_t);
2978	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s16)))
2979	int16x8_t __arm_vqrshlq_m_n(int16x8_t, int32_t, mve_pred16_t);
2980	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s32)))
2981	int32x4_t __arm_vqrshlq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
2982	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s32)))
2983	int32x4_t __arm_vqrshlq_m_n(int32x4_t, int32_t, mve_pred16_t);
2984	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s8)))
2985	int8x16_t __arm_vqrshlq_m_n_s8(int8x16_t, int32_t, mve_pred16_t);
2986	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s8)))
2987	int8x16_t __arm_vqrshlq_m_n(int8x16_t, int32_t, mve_pred16_t);
2988	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u16)))
2989	uint16x8_t __arm_vqrshlq_m_n_u16(uint16x8_t, int32_t, mve_pred16_t);
2990	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u16)))
2991	uint16x8_t __arm_vqrshlq_m_n(uint16x8_t, int32_t, mve_pred16_t);
2992	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u32)))
2993	uint32x4_t __arm_vqrshlq_m_n_u32(uint32x4_t, int32_t, mve_pred16_t);
2994	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u32)))
2995	uint32x4_t __arm_vqrshlq_m_n(uint32x4_t, int32_t, mve_pred16_t);
2996	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u8)))
2997	uint8x16_t __arm_vqrshlq_m_n_u8(uint8x16_t, int32_t, mve_pred16_t);
2998	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u8)))
2999	uint8x16_t __arm_vqrshlq_m_n(uint8x16_t, int32_t, mve_pred16_t);
3000	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s16)))
3001	int16x8_t __arm_vqrshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3002	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s16)))
3003	int16x8_t __arm_vqrshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3004	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s32)))
3005	int32x4_t __arm_vqrshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3006	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s32)))
3007	int32x4_t __arm_vqrshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3008	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s8)))
3009	int8x16_t __arm_vqrshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3010	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s8)))
3011	int8x16_t __arm_vqrshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3012	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u16)))
3013	uint16x8_t __arm_vqrshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3014	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u16)))
3015	uint16x8_t __arm_vqrshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3016	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u32)))
3017	uint32x4_t __arm_vqrshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3018	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u32)))
3019	uint32x4_t __arm_vqrshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3020	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u8)))
3021	uint8x16_t __arm_vqrshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3022	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u8)))
3023	uint8x16_t __arm_vqrshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3024	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s16)))
3025	int16x8_t __arm_vqrshlq_n_s16(int16x8_t, int32_t);
3026	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s16)))
3027	int16x8_t __arm_vqrshlq(int16x8_t, int32_t);
3028	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s32)))
3029	int32x4_t __arm_vqrshlq_n_s32(int32x4_t, int32_t);
3030	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s32)))
3031	int32x4_t __arm_vqrshlq(int32x4_t, int32_t);
3032	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s8)))
3033	int8x16_t __arm_vqrshlq_n_s8(int8x16_t, int32_t);
3034	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s8)))
3035	int8x16_t __arm_vqrshlq(int8x16_t, int32_t);
3036	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u16)))
3037	uint16x8_t __arm_vqrshlq_n_u16(uint16x8_t, int32_t);
3038	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u16)))
3039	uint16x8_t __arm_vqrshlq(uint16x8_t, int32_t);
3040	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u32)))
3041	uint32x4_t __arm_vqrshlq_n_u32(uint32x4_t, int32_t);
3042	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u32)))
3043	uint32x4_t __arm_vqrshlq(uint32x4_t, int32_t);
3044	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u8)))
3045	uint8x16_t __arm_vqrshlq_n_u8(uint8x16_t, int32_t);
3046	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u8)))
3047	uint8x16_t __arm_vqrshlq(uint8x16_t, int32_t);
3048	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s16)))
3049	int16x8_t __arm_vqrshlq_s16(int16x8_t, int16x8_t);
3050	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s16)))
3051	int16x8_t __arm_vqrshlq(int16x8_t, int16x8_t);
3052	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s32)))
3053	int32x4_t __arm_vqrshlq_s32(int32x4_t, int32x4_t);
3054	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s32)))
3055	int32x4_t __arm_vqrshlq(int32x4_t, int32x4_t);
3056	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s8)))
3057	int8x16_t __arm_vqrshlq_s8(int8x16_t, int8x16_t);
3058	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s8)))
3059	int8x16_t __arm_vqrshlq(int8x16_t, int8x16_t);
3060	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u16)))
3061	uint16x8_t __arm_vqrshlq_u16(uint16x8_t, int16x8_t);
3062	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u16)))
3063	uint16x8_t __arm_vqrshlq(uint16x8_t, int16x8_t);
3064	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u32)))
3065	uint32x4_t __arm_vqrshlq_u32(uint32x4_t, int32x4_t);
3066	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u32)))
3067	uint32x4_t __arm_vqrshlq(uint32x4_t, int32x4_t);
3068	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u8)))
3069	uint8x16_t __arm_vqrshlq_u8(uint8x16_t, int8x16_t);
3070	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u8)))
3071	uint8x16_t __arm_vqrshlq(uint8x16_t, int8x16_t);
3072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s16)))
3073	int8x16_t __arm_vqrshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
3074	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s16)))
3075	int8x16_t __arm_vqrshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
3076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s32)))
3077	int16x8_t __arm_vqrshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
3078	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s32)))
3079	int16x8_t __arm_vqrshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
3080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u16)))
3081	uint8x16_t __arm_vqrshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3082	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u16)))
3083	uint8x16_t __arm_vqrshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u32)))
3085	uint16x8_t __arm_vqrshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3086	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u32)))
3087	uint16x8_t __arm_vqrshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s16)))
3089	int8x16_t __arm_vqrshrnbq_n_s16(int8x16_t, int16x8_t, int);
3090	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s16)))
3091	int8x16_t __arm_vqrshrnbq(int8x16_t, int16x8_t, int);
3092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s32)))
3093	int16x8_t __arm_vqrshrnbq_n_s32(int16x8_t, int32x4_t, int);
3094	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s32)))
3095	int16x8_t __arm_vqrshrnbq(int16x8_t, int32x4_t, int);
3096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u16)))
3097	uint8x16_t __arm_vqrshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
3098	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u16)))
3099	uint8x16_t __arm_vqrshrnbq(uint8x16_t, uint16x8_t, int);
3100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u32)))
3101	uint16x8_t __arm_vqrshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
3102	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u32)))
3103	uint16x8_t __arm_vqrshrnbq(uint16x8_t, uint32x4_t, int);
3104	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s16)))
3105	int8x16_t __arm_vqrshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
3106	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s16)))
3107	int8x16_t __arm_vqrshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
3108	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s32)))
3109	int16x8_t __arm_vqrshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
3110	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s32)))
3111	int16x8_t __arm_vqrshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
3112	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u16)))
3113	uint8x16_t __arm_vqrshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3114	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u16)))
3115	uint8x16_t __arm_vqrshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3116	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u32)))
3117	uint16x8_t __arm_vqrshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3118	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u32)))
3119	uint16x8_t __arm_vqrshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3120	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s16)))
3121	int8x16_t __arm_vqrshrntq_n_s16(int8x16_t, int16x8_t, int);
3122	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s16)))
3123	int8x16_t __arm_vqrshrntq(int8x16_t, int16x8_t, int);
3124	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s32)))
3125	int16x8_t __arm_vqrshrntq_n_s32(int16x8_t, int32x4_t, int);
3126	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s32)))
3127	int16x8_t __arm_vqrshrntq(int16x8_t, int32x4_t, int);
3128	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u16)))
3129	uint8x16_t __arm_vqrshrntq_n_u16(uint8x16_t, uint16x8_t, int);
3130	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u16)))
3131	uint8x16_t __arm_vqrshrntq(uint8x16_t, uint16x8_t, int);
3132	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u32)))
3133	uint16x8_t __arm_vqrshrntq_n_u32(uint16x8_t, uint32x4_t, int);
3134	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u32)))
3135	uint16x8_t __arm_vqrshrntq(uint16x8_t, uint32x4_t, int);
3136	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s16)))
3137	uint8x16_t __arm_vqrshrunbq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
3138	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s16)))
3139	uint8x16_t __arm_vqrshrunbq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
3140	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s32)))
3141	uint16x8_t __arm_vqrshrunbq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
3142	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s32)))
3143	uint16x8_t __arm_vqrshrunbq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
3144	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s16)))
3145	uint8x16_t __arm_vqrshrunbq_n_s16(uint8x16_t, int16x8_t, int);
3146	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s16)))
3147	uint8x16_t __arm_vqrshrunbq(uint8x16_t, int16x8_t, int);
3148	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s32)))
3149	uint16x8_t __arm_vqrshrunbq_n_s32(uint16x8_t, int32x4_t, int);
3150	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s32)))
3151	uint16x8_t __arm_vqrshrunbq(uint16x8_t, int32x4_t, int);
3152	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s16)))
3153	uint8x16_t __arm_vqrshruntq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
3154	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s16)))
3155	uint8x16_t __arm_vqrshruntq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
3156	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s32)))
3157	uint16x8_t __arm_vqrshruntq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
3158	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s32)))
3159	uint16x8_t __arm_vqrshruntq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
3160	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s16)))
3161	uint8x16_t __arm_vqrshruntq_n_s16(uint8x16_t, int16x8_t, int);
3162	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s16)))
3163	uint8x16_t __arm_vqrshruntq(uint8x16_t, int16x8_t, int);
3164	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s32)))
3165	uint16x8_t __arm_vqrshruntq_n_s32(uint16x8_t, int32x4_t, int);
3166	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s32)))
3167	uint16x8_t __arm_vqrshruntq(uint16x8_t, int32x4_t, int);
3168	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s16)))
3169	int16x8_t __arm_vqshlq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
3170	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s16)))
3171	int16x8_t __arm_vqshlq_m_n(int16x8_t, int16x8_t, int, mve_pred16_t);
3172	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s32)))
3173	int32x4_t __arm_vqshlq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
3174	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s32)))
3175	int32x4_t __arm_vqshlq_m_n(int32x4_t, int32x4_t, int, mve_pred16_t);
3176	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s8)))
3177	int8x16_t __arm_vqshlq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
3178	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s8)))
3179	int8x16_t __arm_vqshlq_m_n(int8x16_t, int8x16_t, int, mve_pred16_t);
3180	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u16)))
3181	uint16x8_t __arm_vqshlq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
3182	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u16)))
3183	uint16x8_t __arm_vqshlq_m_n(uint16x8_t, uint16x8_t, int, mve_pred16_t);
3184	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u32)))
3185	uint32x4_t __arm_vqshlq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
3186	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u32)))
3187	uint32x4_t __arm_vqshlq_m_n(uint32x4_t, uint32x4_t, int, mve_pred16_t);
3188	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u8)))
3189	uint8x16_t __arm_vqshlq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
3190	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u8)))
3191	uint8x16_t __arm_vqshlq_m_n(uint8x16_t, uint8x16_t, int, mve_pred16_t);
3192	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s16)))
3193	int16x8_t __arm_vqshlq_m_r_s16(int16x8_t, int32_t, mve_pred16_t);
3194	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s16)))
3195	int16x8_t __arm_vqshlq_m_r(int16x8_t, int32_t, mve_pred16_t);
3196	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s32)))
3197	int32x4_t __arm_vqshlq_m_r_s32(int32x4_t, int32_t, mve_pred16_t);
3198	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s32)))
3199	int32x4_t __arm_vqshlq_m_r(int32x4_t, int32_t, mve_pred16_t);
3200	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s8)))
3201	int8x16_t __arm_vqshlq_m_r_s8(int8x16_t, int32_t, mve_pred16_t);
3202	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s8)))
3203	int8x16_t __arm_vqshlq_m_r(int8x16_t, int32_t, mve_pred16_t);
3204	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u16)))
3205	uint16x8_t __arm_vqshlq_m_r_u16(uint16x8_t, int32_t, mve_pred16_t);
3206	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u16)))
3207	uint16x8_t __arm_vqshlq_m_r(uint16x8_t, int32_t, mve_pred16_t);
3208	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u32)))
3209	uint32x4_t __arm_vqshlq_m_r_u32(uint32x4_t, int32_t, mve_pred16_t);
3210	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u32)))
3211	uint32x4_t __arm_vqshlq_m_r(uint32x4_t, int32_t, mve_pred16_t);
3212	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u8)))
3213	uint8x16_t __arm_vqshlq_m_r_u8(uint8x16_t, int32_t, mve_pred16_t);
3214	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u8)))
3215	uint8x16_t __arm_vqshlq_m_r(uint8x16_t, int32_t, mve_pred16_t);
3216	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s16)))
3217	int16x8_t __arm_vqshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3218	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s16)))
3219	int16x8_t __arm_vqshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3220	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s32)))
3221	int32x4_t __arm_vqshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3222	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s32)))
3223	int32x4_t __arm_vqshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3224	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s8)))
3225	int8x16_t __arm_vqshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3226	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s8)))
3227	int8x16_t __arm_vqshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3228	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u16)))
3229	uint16x8_t __arm_vqshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3230	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u16)))
3231	uint16x8_t __arm_vqshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3232	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u32)))
3233	uint32x4_t __arm_vqshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3234	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u32)))
3235	uint32x4_t __arm_vqshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3236	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u8)))
3237	uint8x16_t __arm_vqshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3238	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u8)))
3239	uint8x16_t __arm_vqshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3240	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s16)))
3241	int16x8_t __arm_vqshlq_n_s16(int16x8_t, int);
3242	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s16)))
3243	int16x8_t __arm_vqshlq_n(int16x8_t, int);
3244	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s32)))
3245	int32x4_t __arm_vqshlq_n_s32(int32x4_t, int);
3246	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s32)))
3247	int32x4_t __arm_vqshlq_n(int32x4_t, int);
3248	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s8)))
3249	int8x16_t __arm_vqshlq_n_s8(int8x16_t, int);
3250	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s8)))
3251	int8x16_t __arm_vqshlq_n(int8x16_t, int);
3252	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u16)))
3253	uint16x8_t __arm_vqshlq_n_u16(uint16x8_t, int);
3254	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u16)))
3255	uint16x8_t __arm_vqshlq_n(uint16x8_t, int);
3256	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u32)))
3257	uint32x4_t __arm_vqshlq_n_u32(uint32x4_t, int);
3258	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u32)))
3259	uint32x4_t __arm_vqshlq_n(uint32x4_t, int);
3260	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u8)))
3261	uint8x16_t __arm_vqshlq_n_u8(uint8x16_t, int);
3262	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u8)))
3263	uint8x16_t __arm_vqshlq_n(uint8x16_t, int);
3264	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s16)))
3265	int16x8_t __arm_vqshlq_r_s16(int16x8_t, int32_t);
3266	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s16)))
3267	int16x8_t __arm_vqshlq_r(int16x8_t, int32_t);
3268	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s32)))
3269	int32x4_t __arm_vqshlq_r_s32(int32x4_t, int32_t);
3270	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s32)))
3271	int32x4_t __arm_vqshlq_r(int32x4_t, int32_t);
3272	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s8)))
3273	int8x16_t __arm_vqshlq_r_s8(int8x16_t, int32_t);
3274	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s8)))
3275	int8x16_t __arm_vqshlq_r(int8x16_t, int32_t);
3276	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u16)))
3277	uint16x8_t __arm_vqshlq_r_u16(uint16x8_t, int32_t);
3278	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u16)))
3279	uint16x8_t __arm_vqshlq_r(uint16x8_t, int32_t);
3280	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u32)))
3281	uint32x4_t __arm_vqshlq_r_u32(uint32x4_t, int32_t);
3282	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u32)))
3283	uint32x4_t __arm_vqshlq_r(uint32x4_t, int32_t);
3284	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u8)))
3285	uint8x16_t __arm_vqshlq_r_u8(uint8x16_t, int32_t);
3286	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u8)))
3287	uint8x16_t __arm_vqshlq_r(uint8x16_t, int32_t);
3288	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s16)))
3289	int16x8_t __arm_vqshlq_s16(int16x8_t, int16x8_t);
3290	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s16)))
3291	int16x8_t __arm_vqshlq(int16x8_t, int16x8_t);
3292	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s32)))
3293	int32x4_t __arm_vqshlq_s32(int32x4_t, int32x4_t);
3294	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s32)))
3295	int32x4_t __arm_vqshlq(int32x4_t, int32x4_t);
3296	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s8)))
3297	int8x16_t __arm_vqshlq_s8(int8x16_t, int8x16_t);
3298	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s8)))
3299	int8x16_t __arm_vqshlq(int8x16_t, int8x16_t);
3300	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u16)))
3301	uint16x8_t __arm_vqshlq_u16(uint16x8_t, int16x8_t);
3302	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u16)))
3303	uint16x8_t __arm_vqshlq(uint16x8_t, int16x8_t);
3304	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u32)))
3305	uint32x4_t __arm_vqshlq_u32(uint32x4_t, int32x4_t);
3306	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u32)))
3307	uint32x4_t __arm_vqshlq(uint32x4_t, int32x4_t);
3308	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u8)))
3309	uint8x16_t __arm_vqshlq_u8(uint8x16_t, int8x16_t);
3310	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u8)))
3311	uint8x16_t __arm_vqshlq(uint8x16_t, int8x16_t);
3312	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s16)))
3313	uint16x8_t __arm_vqshluq_m_n_s16(uint16x8_t, int16x8_t, int, mve_pred16_t);
3314	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s16)))
3315	uint16x8_t __arm_vqshluq_m(uint16x8_t, int16x8_t, int, mve_pred16_t);
3316	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s32)))
3317	uint32x4_t __arm_vqshluq_m_n_s32(uint32x4_t, int32x4_t, int, mve_pred16_t);
3318	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s32)))
3319	uint32x4_t __arm_vqshluq_m(uint32x4_t, int32x4_t, int, mve_pred16_t);
3320	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s8)))
3321	uint8x16_t __arm_vqshluq_m_n_s8(uint8x16_t, int8x16_t, int, mve_pred16_t);
3322	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s8)))
3323	uint8x16_t __arm_vqshluq_m(uint8x16_t, int8x16_t, int, mve_pred16_t);
3324	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s16)))
3325	uint16x8_t __arm_vqshluq_n_s16(int16x8_t, int);
3326	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s16)))
3327	uint16x8_t __arm_vqshluq(int16x8_t, int);
3328	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s32)))
3329	uint32x4_t __arm_vqshluq_n_s32(int32x4_t, int);
3330	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s32)))
3331	uint32x4_t __arm_vqshluq(int32x4_t, int);
3332	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s8)))
3333	uint8x16_t __arm_vqshluq_n_s8(int8x16_t, int);
3334	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s8)))
3335	uint8x16_t __arm_vqshluq(int8x16_t, int);
3336	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s16)))
3337	int8x16_t __arm_vqshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
3338	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s16)))
3339	int8x16_t __arm_vqshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
3340	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s32)))
3341	int16x8_t __arm_vqshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
3342	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s32)))
3343	int16x8_t __arm_vqshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
3344	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u16)))
3345	uint8x16_t __arm_vqshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3346	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u16)))
3347	uint8x16_t __arm_vqshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3348	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u32)))
3349	uint16x8_t __arm_vqshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3350	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u32)))
3351	uint16x8_t __arm_vqshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3352	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s16)))
3353	int8x16_t __arm_vqshrnbq_n_s16(int8x16_t, int16x8_t, int);
3354	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s16)))
3355	int8x16_t __arm_vqshrnbq(int8x16_t, int16x8_t, int);
3356	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s32)))
3357	int16x8_t __arm_vqshrnbq_n_s32(int16x8_t, int32x4_t, int);
3358	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s32)))
3359	int16x8_t __arm_vqshrnbq(int16x8_t, int32x4_t, int);
3360	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u16)))
3361	uint8x16_t __arm_vqshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
3362	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u16)))
3363	uint8x16_t __arm_vqshrnbq(uint8x16_t, uint16x8_t, int);
3364	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u32)))
3365	uint16x8_t __arm_vqshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
3366	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u32)))
3367	uint16x8_t __arm_vqshrnbq(uint16x8_t, uint32x4_t, int);
3368	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s16)))
3369	int8x16_t __arm_vqshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
3370	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s16)))
3371	int8x16_t __arm_vqshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
3372	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s32)))
3373	int16x8_t __arm_vqshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
3374	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s32)))
3375	int16x8_t __arm_vqshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
3376	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u16)))
3377	uint8x16_t __arm_vqshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3378	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u16)))
3379	uint8x16_t __arm_vqshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
3380	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u32)))
3381	uint16x8_t __arm_vqshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3382	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u32)))
3383	uint16x8_t __arm_vqshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
3384	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s16)))
3385	int8x16_t __arm_vqshrntq_n_s16(int8x16_t, int16x8_t, int);
3386	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s16)))
3387	int8x16_t __arm_vqshrntq(int8x16_t, int16x8_t, int);
3388	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s32)))
3389	int16x8_t __arm_vqshrntq_n_s32(int16x8_t, int32x4_t, int);
3390	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s32)))
3391	int16x8_t __arm_vqshrntq(int16x8_t, int32x4_t, int);
3392	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u16)))
3393	uint8x16_t __arm_vqshrntq_n_u16(uint8x16_t, uint16x8_t, int);
3394	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u16)))
3395	uint8x16_t __arm_vqshrntq(uint8x16_t, uint16x8_t, int);
3396	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u32)))
3397	uint16x8_t __arm_vqshrntq_n_u32(uint16x8_t, uint32x4_t, int);
3398	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u32)))
3399	uint16x8_t __arm_vqshrntq(uint16x8_t, uint32x4_t, int);
3400	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s16)))
3401	uint8x16_t __arm_vqshrunbq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
3402	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s16)))
3403	uint8x16_t __arm_vqshrunbq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
3404	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s32)))
3405	uint16x8_t __arm_vqshrunbq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
3406	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s32)))
3407	uint16x8_t __arm_vqshrunbq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
3408	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s16)))
3409	uint8x16_t __arm_vqshrunbq_n_s16(uint8x16_t, int16x8_t, int);
3410	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s16)))
3411	uint8x16_t __arm_vqshrunbq(uint8x16_t, int16x8_t, int);
3412	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s32)))
3413	uint16x8_t __arm_vqshrunbq_n_s32(uint16x8_t, int32x4_t, int);
3414	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s32)))
3415	uint16x8_t __arm_vqshrunbq(uint16x8_t, int32x4_t, int);
3416	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s16)))
3417	uint8x16_t __arm_vqshruntq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
3418	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s16)))
3419	uint8x16_t __arm_vqshruntq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
3420	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s32)))
3421	uint16x8_t __arm_vqshruntq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
3422	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s32)))
3423	uint16x8_t __arm_vqshruntq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
3424	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s16)))
3425	uint8x16_t __arm_vqshruntq_n_s16(uint8x16_t, int16x8_t, int);
3426	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s16)))
3427	uint8x16_t __arm_vqshruntq(uint8x16_t, int16x8_t, int);
3428	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s32)))
3429	uint16x8_t __arm_vqshruntq_n_s32(uint16x8_t, int32x4_t, int);
3430	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s32)))
3431	uint16x8_t __arm_vqshruntq(uint16x8_t, int32x4_t, int);
3432	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s16)))
3433	int16x8_t __arm_vqsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3434	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s16)))
3435	int16x8_t __arm_vqsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3436	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s32)))
3437	int32x4_t __arm_vqsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3438	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s32)))
3439	int32x4_t __arm_vqsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3440	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s8)))
3441	int8x16_t __arm_vqsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3442	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s8)))
3443	int8x16_t __arm_vqsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3444	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u16)))
3445	uint16x8_t __arm_vqsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3446	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u16)))
3447	uint16x8_t __arm_vqsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3448	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u32)))
3449	uint32x4_t __arm_vqsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3450	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u32)))
3451	uint32x4_t __arm_vqsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3452	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u8)))
3453	uint8x16_t __arm_vqsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3454	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u8)))
3455	uint8x16_t __arm_vqsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3456	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s16)))
3457	int16x8_t __arm_vqsubq_s16(int16x8_t, int16x8_t);
3458	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s16)))
3459	int16x8_t __arm_vqsubq(int16x8_t, int16x8_t);
3460	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s32)))
3461	int32x4_t __arm_vqsubq_s32(int32x4_t, int32x4_t);
3462	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s32)))
3463	int32x4_t __arm_vqsubq(int32x4_t, int32x4_t);
3464	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s8)))
3465	int8x16_t __arm_vqsubq_s8(int8x16_t, int8x16_t);
3466	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s8)))
3467	int8x16_t __arm_vqsubq(int8x16_t, int8x16_t);
3468	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u16)))
3469	uint16x8_t __arm_vqsubq_u16(uint16x8_t, uint16x8_t);
3470	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u16)))
3471	uint16x8_t __arm_vqsubq(uint16x8_t, uint16x8_t);
3472	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u32)))
3473	uint32x4_t __arm_vqsubq_u32(uint32x4_t, uint32x4_t);
3474	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u32)))
3475	uint32x4_t __arm_vqsubq(uint32x4_t, uint32x4_t);
3476	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u8)))
3477	uint8x16_t __arm_vqsubq_u8(uint8x16_t, uint8x16_t);
3478	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u8)))
3479	uint8x16_t __arm_vqsubq(uint8x16_t, uint8x16_t);
3480	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s32)))
3481	int16x8_t __arm_vreinterpretq_s16_s32(int32x4_t);
3482	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s32)))
3483	int16x8_t __arm_vreinterpretq_s16(int32x4_t);
3484	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s64)))
3485	int16x8_t __arm_vreinterpretq_s16_s64(int64x2_t);
3486	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s64)))
3487	int16x8_t __arm_vreinterpretq_s16(int64x2_t);
3488	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s8)))
3489	int16x8_t __arm_vreinterpretq_s16_s8(int8x16_t);
3490	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s8)))
3491	int16x8_t __arm_vreinterpretq_s16(int8x16_t);
3492	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u16)))
3493	int16x8_t __arm_vreinterpretq_s16_u16(uint16x8_t);
3494	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u16)))
3495	int16x8_t __arm_vreinterpretq_s16(uint16x8_t);
3496	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u32)))
3497	int16x8_t __arm_vreinterpretq_s16_u32(uint32x4_t);
3498	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u32)))
3499	int16x8_t __arm_vreinterpretq_s16(uint32x4_t);
3500	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u64)))
3501	int16x8_t __arm_vreinterpretq_s16_u64(uint64x2_t);
3502	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u64)))
3503	int16x8_t __arm_vreinterpretq_s16(uint64x2_t);
3504	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u8)))
3505	int16x8_t __arm_vreinterpretq_s16_u8(uint8x16_t);
3506	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u8)))
3507	int16x8_t __arm_vreinterpretq_s16(uint8x16_t);
3508	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s16)))
3509	int32x4_t __arm_vreinterpretq_s32_s16(int16x8_t);
3510	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s16)))
3511	int32x4_t __arm_vreinterpretq_s32(int16x8_t);
3512	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s64)))
3513	int32x4_t __arm_vreinterpretq_s32_s64(int64x2_t);
3514	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s64)))
3515	int32x4_t __arm_vreinterpretq_s32(int64x2_t);
3516	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s8)))
3517	int32x4_t __arm_vreinterpretq_s32_s8(int8x16_t);
3518	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s8)))
3519	int32x4_t __arm_vreinterpretq_s32(int8x16_t);
3520	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u16)))
3521	int32x4_t __arm_vreinterpretq_s32_u16(uint16x8_t);
3522	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u16)))
3523	int32x4_t __arm_vreinterpretq_s32(uint16x8_t);
3524	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u32)))
3525	int32x4_t __arm_vreinterpretq_s32_u32(uint32x4_t);
3526	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u32)))
3527	int32x4_t __arm_vreinterpretq_s32(uint32x4_t);
3528	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u64)))
3529	int32x4_t __arm_vreinterpretq_s32_u64(uint64x2_t);
3530	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u64)))
3531	int32x4_t __arm_vreinterpretq_s32(uint64x2_t);
3532	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u8)))
3533	int32x4_t __arm_vreinterpretq_s32_u8(uint8x16_t);
3534	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u8)))
3535	int32x4_t __arm_vreinterpretq_s32(uint8x16_t);
3536	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s16)))
3537	int64x2_t __arm_vreinterpretq_s64_s16(int16x8_t);
3538	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s16)))
3539	int64x2_t __arm_vreinterpretq_s64(int16x8_t);
3540	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s32)))
3541	int64x2_t __arm_vreinterpretq_s64_s32(int32x4_t);
3542	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s32)))
3543	int64x2_t __arm_vreinterpretq_s64(int32x4_t);
3544	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s8)))
3545	int64x2_t __arm_vreinterpretq_s64_s8(int8x16_t);
3546	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s8)))
3547	int64x2_t __arm_vreinterpretq_s64(int8x16_t);
3548	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u16)))
3549	int64x2_t __arm_vreinterpretq_s64_u16(uint16x8_t);
3550	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u16)))
3551	int64x2_t __arm_vreinterpretq_s64(uint16x8_t);
3552	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u32)))
3553	int64x2_t __arm_vreinterpretq_s64_u32(uint32x4_t);
3554	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u32)))
3555	int64x2_t __arm_vreinterpretq_s64(uint32x4_t);
3556	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u64)))
3557	int64x2_t __arm_vreinterpretq_s64_u64(uint64x2_t);
3558	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u64)))
3559	int64x2_t __arm_vreinterpretq_s64(uint64x2_t);
3560	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u8)))
3561	int64x2_t __arm_vreinterpretq_s64_u8(uint8x16_t);
3562	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u8)))
3563	int64x2_t __arm_vreinterpretq_s64(uint8x16_t);
3564	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s16)))
3565	int8x16_t __arm_vreinterpretq_s8_s16(int16x8_t);
3566	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s16)))
3567	int8x16_t __arm_vreinterpretq_s8(int16x8_t);
3568	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s32)))
3569	int8x16_t __arm_vreinterpretq_s8_s32(int32x4_t);
3570	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s32)))
3571	int8x16_t __arm_vreinterpretq_s8(int32x4_t);
3572	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s64)))
3573	int8x16_t __arm_vreinterpretq_s8_s64(int64x2_t);
3574	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s64)))
3575	int8x16_t __arm_vreinterpretq_s8(int64x2_t);
3576	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u16)))
3577	int8x16_t __arm_vreinterpretq_s8_u16(uint16x8_t);
3578	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u16)))
3579	int8x16_t __arm_vreinterpretq_s8(uint16x8_t);
3580	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u32)))
3581	int8x16_t __arm_vreinterpretq_s8_u32(uint32x4_t);
3582	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u32)))
3583	int8x16_t __arm_vreinterpretq_s8(uint32x4_t);
3584	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u64)))
3585	int8x16_t __arm_vreinterpretq_s8_u64(uint64x2_t);
3586	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u64)))
3587	int8x16_t __arm_vreinterpretq_s8(uint64x2_t);
3588	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u8)))
3589	int8x16_t __arm_vreinterpretq_s8_u8(uint8x16_t);
3590	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u8)))
3591	int8x16_t __arm_vreinterpretq_s8(uint8x16_t);
3592	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s16)))
3593	uint16x8_t __arm_vreinterpretq_u16_s16(int16x8_t);
3594	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s16)))
3595	uint16x8_t __arm_vreinterpretq_u16(int16x8_t);
3596	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s32)))
3597	uint16x8_t __arm_vreinterpretq_u16_s32(int32x4_t);
3598	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s32)))
3599	uint16x8_t __arm_vreinterpretq_u16(int32x4_t);
3600	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s64)))
3601	uint16x8_t __arm_vreinterpretq_u16_s64(int64x2_t);
3602	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s64)))
3603	uint16x8_t __arm_vreinterpretq_u16(int64x2_t);
3604	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s8)))
3605	uint16x8_t __arm_vreinterpretq_u16_s8(int8x16_t);
3606	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s8)))
3607	uint16x8_t __arm_vreinterpretq_u16(int8x16_t);
3608	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u32)))
3609	uint16x8_t __arm_vreinterpretq_u16_u32(uint32x4_t);
3610	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u32)))
3611	uint16x8_t __arm_vreinterpretq_u16(uint32x4_t);
3612	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u64)))
3613	uint16x8_t __arm_vreinterpretq_u16_u64(uint64x2_t);
3614	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u64)))
3615	uint16x8_t __arm_vreinterpretq_u16(uint64x2_t);
3616	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u8)))
3617	uint16x8_t __arm_vreinterpretq_u16_u8(uint8x16_t);
3618	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u8)))
3619	uint16x8_t __arm_vreinterpretq_u16(uint8x16_t);
3620	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s16)))
3621	uint32x4_t __arm_vreinterpretq_u32_s16(int16x8_t);
3622	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s16)))
3623	uint32x4_t __arm_vreinterpretq_u32(int16x8_t);
3624	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s32)))
3625	uint32x4_t __arm_vreinterpretq_u32_s32(int32x4_t);
3626	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s32)))
3627	uint32x4_t __arm_vreinterpretq_u32(int32x4_t);
3628	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s64)))
3629	uint32x4_t __arm_vreinterpretq_u32_s64(int64x2_t);
3630	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s64)))
3631	uint32x4_t __arm_vreinterpretq_u32(int64x2_t);
3632	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s8)))
3633	uint32x4_t __arm_vreinterpretq_u32_s8(int8x16_t);
3634	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s8)))
3635	uint32x4_t __arm_vreinterpretq_u32(int8x16_t);
3636	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u16)))
3637	uint32x4_t __arm_vreinterpretq_u32_u16(uint16x8_t);
3638	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u16)))
3639	uint32x4_t __arm_vreinterpretq_u32(uint16x8_t);
3640	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u64)))
3641	uint32x4_t __arm_vreinterpretq_u32_u64(uint64x2_t);
3642	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u64)))
3643	uint32x4_t __arm_vreinterpretq_u32(uint64x2_t);
3644	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u8)))
3645	uint32x4_t __arm_vreinterpretq_u32_u8(uint8x16_t);
3646	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u8)))
3647	uint32x4_t __arm_vreinterpretq_u32(uint8x16_t);
3648	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s16)))
3649	uint64x2_t __arm_vreinterpretq_u64_s16(int16x8_t);
3650	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s16)))
3651	uint64x2_t __arm_vreinterpretq_u64(int16x8_t);
3652	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s32)))
3653	uint64x2_t __arm_vreinterpretq_u64_s32(int32x4_t);
3654	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s32)))
3655	uint64x2_t __arm_vreinterpretq_u64(int32x4_t);
3656	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s64)))
3657	uint64x2_t __arm_vreinterpretq_u64_s64(int64x2_t);
3658	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s64)))
3659	uint64x2_t __arm_vreinterpretq_u64(int64x2_t);
3660	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s8)))
3661	uint64x2_t __arm_vreinterpretq_u64_s8(int8x16_t);
3662	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s8)))
3663	uint64x2_t __arm_vreinterpretq_u64(int8x16_t);
3664	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u16)))
3665	uint64x2_t __arm_vreinterpretq_u64_u16(uint16x8_t);
3666	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u16)))
3667	uint64x2_t __arm_vreinterpretq_u64(uint16x8_t);
3668	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u32)))
3669	uint64x2_t __arm_vreinterpretq_u64_u32(uint32x4_t);
3670	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u32)))
3671	uint64x2_t __arm_vreinterpretq_u64(uint32x4_t);
3672	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u8)))
3673	uint64x2_t __arm_vreinterpretq_u64_u8(uint8x16_t);
3674	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u8)))
3675	uint64x2_t __arm_vreinterpretq_u64(uint8x16_t);
3676	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s16)))
3677	uint8x16_t __arm_vreinterpretq_u8_s16(int16x8_t);
3678	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s16)))
3679	uint8x16_t __arm_vreinterpretq_u8(int16x8_t);
3680	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s32)))
3681	uint8x16_t __arm_vreinterpretq_u8_s32(int32x4_t);
3682	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s32)))
3683	uint8x16_t __arm_vreinterpretq_u8(int32x4_t);
3684	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s64)))
3685	uint8x16_t __arm_vreinterpretq_u8_s64(int64x2_t);
3686	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s64)))
3687	uint8x16_t __arm_vreinterpretq_u8(int64x2_t);
3688	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s8)))
3689	uint8x16_t __arm_vreinterpretq_u8_s8(int8x16_t);
3690	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s8)))
3691	uint8x16_t __arm_vreinterpretq_u8(int8x16_t);
3692	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u16)))
3693	uint8x16_t __arm_vreinterpretq_u8_u16(uint16x8_t);
3694	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u16)))
3695	uint8x16_t __arm_vreinterpretq_u8(uint16x8_t);
3696	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u32)))
3697	uint8x16_t __arm_vreinterpretq_u8_u32(uint32x4_t);
3698	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u32)))
3699	uint8x16_t __arm_vreinterpretq_u8(uint32x4_t);
3700	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u64)))
3701	uint8x16_t __arm_vreinterpretq_u8_u64(uint64x2_t);
3702	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u64)))
3703	uint8x16_t __arm_vreinterpretq_u8(uint64x2_t);
3704	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s16)))
3705	int16x8_t __arm_vrhaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3706	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s16)))
3707	int16x8_t __arm_vrhaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3708	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s32)))
3709	int32x4_t __arm_vrhaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3710	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s32)))
3711	int32x4_t __arm_vrhaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3712	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s8)))
3713	int8x16_t __arm_vrhaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3714	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s8)))
3715	int8x16_t __arm_vrhaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3716	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u16)))
3717	uint16x8_t __arm_vrhaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3718	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u16)))
3719	uint16x8_t __arm_vrhaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3720	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u32)))
3721	uint32x4_t __arm_vrhaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3722	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u32)))
3723	uint32x4_t __arm_vrhaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3724	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u8)))
3725	uint8x16_t __arm_vrhaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3726	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u8)))
3727	uint8x16_t __arm_vrhaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3728	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s16)))
3729	int16x8_t __arm_vrhaddq_s16(int16x8_t, int16x8_t);
3730	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s16)))
3731	int16x8_t __arm_vrhaddq(int16x8_t, int16x8_t);
3732	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s32)))
3733	int32x4_t __arm_vrhaddq_s32(int32x4_t, int32x4_t);
3734	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s32)))
3735	int32x4_t __arm_vrhaddq(int32x4_t, int32x4_t);
3736	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s8)))
3737	int8x16_t __arm_vrhaddq_s8(int8x16_t, int8x16_t);
3738	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s8)))
3739	int8x16_t __arm_vrhaddq(int8x16_t, int8x16_t);
3740	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u16)))
3741	uint16x8_t __arm_vrhaddq_u16(uint16x8_t, uint16x8_t);
3742	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u16)))
3743	uint16x8_t __arm_vrhaddq(uint16x8_t, uint16x8_t);
3744	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u32)))
3745	uint32x4_t __arm_vrhaddq_u32(uint32x4_t, uint32x4_t);
3746	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u32)))
3747	uint32x4_t __arm_vrhaddq(uint32x4_t, uint32x4_t);
3748	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u8)))
3749	uint8x16_t __arm_vrhaddq_u8(uint8x16_t, uint8x16_t);
3750	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u8)))
3751	uint8x16_t __arm_vrhaddq(uint8x16_t, uint8x16_t);
3752	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s16)))
3753	int16x8_t __arm_vrhaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
3754	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s16)))
3755	int16x8_t __arm_vrhaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
3756	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s32)))
3757	int32x4_t __arm_vrhaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
3758	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s32)))
3759	int32x4_t __arm_vrhaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
3760	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s8)))
3761	int8x16_t __arm_vrhaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
3762	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s8)))
3763	int8x16_t __arm_vrhaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
3764	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u16)))
3765	uint16x8_t __arm_vrhaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
3766	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u16)))
3767	uint16x8_t __arm_vrhaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
3768	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u32)))
3769	uint32x4_t __arm_vrhaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
3770	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u32)))
3771	uint32x4_t __arm_vrhaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
3772	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u8)))
3773	uint8x16_t __arm_vrhaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
3774	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u8)))
3775	uint8x16_t __arm_vrhaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
3776	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_s32)))
3777	int64_t __arm_vrmlaldavhaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3778	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_s32)))
3779	int64_t __arm_vrmlaldavhaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3780	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_u32)))
3781	uint64_t __arm_vrmlaldavhaq_p_u32(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3782	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_u32)))
3783	uint64_t __arm_vrmlaldavhaq_p(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3784	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_s32)))
3785	int64_t __arm_vrmlaldavhaq_s32(int64_t, int32x4_t, int32x4_t);
3786	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_s32)))
3787	int64_t __arm_vrmlaldavhaq(int64_t, int32x4_t, int32x4_t);
3788	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_u32)))
3789	uint64_t __arm_vrmlaldavhaq_u32(uint64_t, uint32x4_t, uint32x4_t);
3790	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_u32)))
3791	uint64_t __arm_vrmlaldavhaq(uint64_t, uint32x4_t, uint32x4_t);
3792	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_p_s32)))
3793	int64_t __arm_vrmlaldavhaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3794	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_p_s32)))
3795	int64_t __arm_vrmlaldavhaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3796	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_s32)))
3797	int64_t __arm_vrmlaldavhaxq_s32(int64_t, int32x4_t, int32x4_t);
3798	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_s32)))
3799	int64_t __arm_vrmlaldavhaxq(int64_t, int32x4_t, int32x4_t);
3800	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_s32)))
3801	int64_t __arm_vrmlaldavhq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
3802	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_s32)))
3803	int64_t __arm_vrmlaldavhq_p(int32x4_t, int32x4_t, mve_pred16_t);
3804	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_u32)))
3805	uint64_t __arm_vrmlaldavhq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
3806	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_u32)))
3807	uint64_t __arm_vrmlaldavhq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
3808	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_s32)))
3809	int64_t __arm_vrmlaldavhq_s32(int32x4_t, int32x4_t);
3810	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_s32)))
3811	int64_t __arm_vrmlaldavhq(int32x4_t, int32x4_t);
3812	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_u32)))
3813	uint64_t __arm_vrmlaldavhq_u32(uint32x4_t, uint32x4_t);
3814	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_u32)))
3815	uint64_t __arm_vrmlaldavhq(uint32x4_t, uint32x4_t);
3816	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_p_s32)))
3817	int64_t __arm_vrmlaldavhxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
3818	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_p_s32)))
3819	int64_t __arm_vrmlaldavhxq_p(int32x4_t, int32x4_t, mve_pred16_t);
3820	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_s32)))
3821	int64_t __arm_vrmlaldavhxq_s32(int32x4_t, int32x4_t);
3822	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_s32)))
3823	int64_t __arm_vrmlaldavhxq(int32x4_t, int32x4_t);
3824	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_p_s32)))
3825	int64_t __arm_vrmlsldavhaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3826	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_p_s32)))
3827	int64_t __arm_vrmlsldavhaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3828	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_s32)))
3829	int64_t __arm_vrmlsldavhaq_s32(int64_t, int32x4_t, int32x4_t);
3830	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_s32)))
3831	int64_t __arm_vrmlsldavhaq(int64_t, int32x4_t, int32x4_t);
3832	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_p_s32)))
3833	int64_t __arm_vrmlsldavhaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3834	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_p_s32)))
3835	int64_t __arm_vrmlsldavhaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
3836	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_s32)))
3837	int64_t __arm_vrmlsldavhaxq_s32(int64_t, int32x4_t, int32x4_t);
3838	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_s32)))
3839	int64_t __arm_vrmlsldavhaxq(int64_t, int32x4_t, int32x4_t);
3840	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_p_s32)))
3841	int64_t __arm_vrmlsldavhq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
3842	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_p_s32)))
3843	int64_t __arm_vrmlsldavhq_p(int32x4_t, int32x4_t, mve_pred16_t);
3844	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_s32)))
3845	int64_t __arm_vrmlsldavhq_s32(int32x4_t, int32x4_t);
3846	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_s32)))
3847	int64_t __arm_vrmlsldavhq(int32x4_t, int32x4_t);
3848	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_p_s32)))
3849	int64_t __arm_vrmlsldavhxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
3850	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_p_s32)))
3851	int64_t __arm_vrmlsldavhxq_p(int32x4_t, int32x4_t, mve_pred16_t);
3852	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_s32)))
3853	int64_t __arm_vrmlsldavhxq_s32(int32x4_t, int32x4_t);
3854	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_s32)))
3855	int64_t __arm_vrmlsldavhxq(int32x4_t, int32x4_t);
3856	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s16)))
3857	int16x8_t __arm_vrmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3858	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s16)))
3859	int16x8_t __arm_vrmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3860	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s32)))
3861	int32x4_t __arm_vrmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3862	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s32)))
3863	int32x4_t __arm_vrmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3864	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s8)))
3865	int8x16_t __arm_vrmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3866	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s8)))
3867	int8x16_t __arm_vrmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3868	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u16)))
3869	uint16x8_t __arm_vrmulhq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3870	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u16)))
3871	uint16x8_t __arm_vrmulhq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
3872	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u32)))
3873	uint32x4_t __arm_vrmulhq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3874	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u32)))
3875	uint32x4_t __arm_vrmulhq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
3876	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u8)))
3877	uint8x16_t __arm_vrmulhq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3878	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u8)))
3879	uint8x16_t __arm_vrmulhq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
3880	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s16)))
3881	int16x8_t __arm_vrmulhq_s16(int16x8_t, int16x8_t);
3882	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s16)))
3883	int16x8_t __arm_vrmulhq(int16x8_t, int16x8_t);
3884	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s32)))
3885	int32x4_t __arm_vrmulhq_s32(int32x4_t, int32x4_t);
3886	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s32)))
3887	int32x4_t __arm_vrmulhq(int32x4_t, int32x4_t);
3888	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s8)))
3889	int8x16_t __arm_vrmulhq_s8(int8x16_t, int8x16_t);
3890	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s8)))
3891	int8x16_t __arm_vrmulhq(int8x16_t, int8x16_t);
3892	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u16)))
3893	uint16x8_t __arm_vrmulhq_u16(uint16x8_t, uint16x8_t);
3894	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u16)))
3895	uint16x8_t __arm_vrmulhq(uint16x8_t, uint16x8_t);
3896	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u32)))
3897	uint32x4_t __arm_vrmulhq_u32(uint32x4_t, uint32x4_t);
3898	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u32)))
3899	uint32x4_t __arm_vrmulhq(uint32x4_t, uint32x4_t);
3900	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u8)))
3901	uint8x16_t __arm_vrmulhq_u8(uint8x16_t, uint8x16_t);
3902	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u8)))
3903	uint8x16_t __arm_vrmulhq(uint8x16_t, uint8x16_t);
3904	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s16)))
3905	int16x8_t __arm_vrmulhq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
3906	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s16)))
3907	int16x8_t __arm_vrmulhq_x(int16x8_t, int16x8_t, mve_pred16_t);
3908	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s32)))
3909	int32x4_t __arm_vrmulhq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
3910	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s32)))
3911	int32x4_t __arm_vrmulhq_x(int32x4_t, int32x4_t, mve_pred16_t);
3912	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s8)))
3913	int8x16_t __arm_vrmulhq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
3914	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s8)))
3915	int8x16_t __arm_vrmulhq_x(int8x16_t, int8x16_t, mve_pred16_t);
3916	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u16)))
3917	uint16x8_t __arm_vrmulhq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
3918	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u16)))
3919	uint16x8_t __arm_vrmulhq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
3920	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u32)))
3921	uint32x4_t __arm_vrmulhq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
3922	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u32)))
3923	uint32x4_t __arm_vrmulhq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
3924	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u8)))
3925	uint8x16_t __arm_vrmulhq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
3926	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u8)))
3927	uint8x16_t __arm_vrmulhq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
3928	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s16)))
3929	int16x8_t __arm_vrshlq_m_n_s16(int16x8_t, int32_t, mve_pred16_t);
3930	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s16)))
3931	int16x8_t __arm_vrshlq_m_n(int16x8_t, int32_t, mve_pred16_t);
3932	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s32)))
3933	int32x4_t __arm_vrshlq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
3934	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s32)))
3935	int32x4_t __arm_vrshlq_m_n(int32x4_t, int32_t, mve_pred16_t);
3936	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s8)))
3937	int8x16_t __arm_vrshlq_m_n_s8(int8x16_t, int32_t, mve_pred16_t);
3938	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s8)))
3939	int8x16_t __arm_vrshlq_m_n(int8x16_t, int32_t, mve_pred16_t);
3940	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u16)))
3941	uint16x8_t __arm_vrshlq_m_n_u16(uint16x8_t, int32_t, mve_pred16_t);
3942	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u16)))
3943	uint16x8_t __arm_vrshlq_m_n(uint16x8_t, int32_t, mve_pred16_t);
3944	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u32)))
3945	uint32x4_t __arm_vrshlq_m_n_u32(uint32x4_t, int32_t, mve_pred16_t);
3946	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u32)))
3947	uint32x4_t __arm_vrshlq_m_n(uint32x4_t, int32_t, mve_pred16_t);
3948	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u8)))
3949	uint8x16_t __arm_vrshlq_m_n_u8(uint8x16_t, int32_t, mve_pred16_t);
3950	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u8)))
3951	uint8x16_t __arm_vrshlq_m_n(uint8x16_t, int32_t, mve_pred16_t);
3952	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s16)))
3953	int16x8_t __arm_vrshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3954	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s16)))
3955	int16x8_t __arm_vrshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
3956	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s32)))
3957	int32x4_t __arm_vrshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3958	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s32)))
3959	int32x4_t __arm_vrshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
3960	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s8)))
3961	int8x16_t __arm_vrshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3962	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s8)))
3963	int8x16_t __arm_vrshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
3964	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u16)))
3965	uint16x8_t __arm_vrshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3966	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u16)))
3967	uint16x8_t __arm_vrshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
3968	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u32)))
3969	uint32x4_t __arm_vrshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3970	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u32)))
3971	uint32x4_t __arm_vrshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
3972	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u8)))
3973	uint8x16_t __arm_vrshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3974	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u8)))
3975	uint8x16_t __arm_vrshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
3976	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s16)))
3977	int16x8_t __arm_vrshlq_n_s16(int16x8_t, int32_t);
3978	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s16)))
3979	int16x8_t __arm_vrshlq(int16x8_t, int32_t);
3980	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s32)))
3981	int32x4_t __arm_vrshlq_n_s32(int32x4_t, int32_t);
3982	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s32)))
3983	int32x4_t __arm_vrshlq(int32x4_t, int32_t);
3984	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s8)))
3985	int8x16_t __arm_vrshlq_n_s8(int8x16_t, int32_t);
3986	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s8)))
3987	int8x16_t __arm_vrshlq(int8x16_t, int32_t);
3988	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u16)))
3989	uint16x8_t __arm_vrshlq_n_u16(uint16x8_t, int32_t);
3990	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u16)))
3991	uint16x8_t __arm_vrshlq(uint16x8_t, int32_t);
3992	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u32)))
3993	uint32x4_t __arm_vrshlq_n_u32(uint32x4_t, int32_t);
3994	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u32)))
3995	uint32x4_t __arm_vrshlq(uint32x4_t, int32_t);
3996	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u8)))
3997	uint8x16_t __arm_vrshlq_n_u8(uint8x16_t, int32_t);
3998	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u8)))
3999	uint8x16_t __arm_vrshlq(uint8x16_t, int32_t);
4000	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s16)))
4001	int16x8_t __arm_vrshlq_s16(int16x8_t, int16x8_t);
4002	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s16)))
4003	int16x8_t __arm_vrshlq(int16x8_t, int16x8_t);
4004	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s32)))
4005	int32x4_t __arm_vrshlq_s32(int32x4_t, int32x4_t);
4006	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s32)))
4007	int32x4_t __arm_vrshlq(int32x4_t, int32x4_t);
4008	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s8)))
4009	int8x16_t __arm_vrshlq_s8(int8x16_t, int8x16_t);
4010	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s8)))
4011	int8x16_t __arm_vrshlq(int8x16_t, int8x16_t);
4012	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u16)))
4013	uint16x8_t __arm_vrshlq_u16(uint16x8_t, int16x8_t);
4014	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u16)))
4015	uint16x8_t __arm_vrshlq(uint16x8_t, int16x8_t);
4016	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u32)))
4017	uint32x4_t __arm_vrshlq_u32(uint32x4_t, int32x4_t);
4018	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u32)))
4019	uint32x4_t __arm_vrshlq(uint32x4_t, int32x4_t);
4020	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u8)))
4021	uint8x16_t __arm_vrshlq_u8(uint8x16_t, int8x16_t);
4022	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u8)))
4023	uint8x16_t __arm_vrshlq(uint8x16_t, int8x16_t);
4024	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s16)))
4025	int16x8_t __arm_vrshlq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
4026	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s16)))
4027	int16x8_t __arm_vrshlq_x(int16x8_t, int16x8_t, mve_pred16_t);
4028	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s32)))
4029	int32x4_t __arm_vrshlq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
4030	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s32)))
4031	int32x4_t __arm_vrshlq_x(int32x4_t, int32x4_t, mve_pred16_t);
4032	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s8)))
4033	int8x16_t __arm_vrshlq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
4034	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s8)))
4035	int8x16_t __arm_vrshlq_x(int8x16_t, int8x16_t, mve_pred16_t);
4036	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u16)))
4037	uint16x8_t __arm_vrshlq_x_u16(uint16x8_t, int16x8_t, mve_pred16_t);
4038	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u16)))
4039	uint16x8_t __arm_vrshlq_x(uint16x8_t, int16x8_t, mve_pred16_t);
4040	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u32)))
4041	uint32x4_t __arm_vrshlq_x_u32(uint32x4_t, int32x4_t, mve_pred16_t);
4042	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u32)))
4043	uint32x4_t __arm_vrshlq_x(uint32x4_t, int32x4_t, mve_pred16_t);
4044	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u8)))
4045	uint8x16_t __arm_vrshlq_x_u8(uint8x16_t, int8x16_t, mve_pred16_t);
4046	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u8)))
4047	uint8x16_t __arm_vrshlq_x(uint8x16_t, int8x16_t, mve_pred16_t);
4048	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s16)))
4049	int8x16_t __arm_vrshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
4050	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s16)))
4051	int8x16_t __arm_vrshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
4052	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s32)))
4053	int16x8_t __arm_vrshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
4054	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s32)))
4055	int16x8_t __arm_vrshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
4056	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u16)))
4057	uint8x16_t __arm_vrshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4058	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u16)))
4059	uint8x16_t __arm_vrshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4060	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u32)))
4061	uint16x8_t __arm_vrshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4062	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u32)))
4063	uint16x8_t __arm_vrshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4064	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s16)))
4065	int8x16_t __arm_vrshrnbq_n_s16(int8x16_t, int16x8_t, int);
4066	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s16)))
4067	int8x16_t __arm_vrshrnbq(int8x16_t, int16x8_t, int);
4068	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s32)))
4069	int16x8_t __arm_vrshrnbq_n_s32(int16x8_t, int32x4_t, int);
4070	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s32)))
4071	int16x8_t __arm_vrshrnbq(int16x8_t, int32x4_t, int);
4072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u16)))
4073	uint8x16_t __arm_vrshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
4074	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u16)))
4075	uint8x16_t __arm_vrshrnbq(uint8x16_t, uint16x8_t, int);
4076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u32)))
4077	uint16x8_t __arm_vrshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
4078	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u32)))
4079	uint16x8_t __arm_vrshrnbq(uint16x8_t, uint32x4_t, int);
4080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s16)))
4081	int8x16_t __arm_vrshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
4082	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s16)))
4083	int8x16_t __arm_vrshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
4084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s32)))
4085	int16x8_t __arm_vrshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
4086	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s32)))
4087	int16x8_t __arm_vrshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
4088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u16)))
4089	uint8x16_t __arm_vrshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4090	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u16)))
4091	uint8x16_t __arm_vrshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u32)))
4093	uint16x8_t __arm_vrshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4094	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u32)))
4095	uint16x8_t __arm_vrshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s16)))
4097	int8x16_t __arm_vrshrntq_n_s16(int8x16_t, int16x8_t, int);
4098	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s16)))
4099	int8x16_t __arm_vrshrntq(int8x16_t, int16x8_t, int);
4100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s32)))
4101	int16x8_t __arm_vrshrntq_n_s32(int16x8_t, int32x4_t, int);
4102	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s32)))
4103	int16x8_t __arm_vrshrntq(int16x8_t, int32x4_t, int);
4104	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u16)))
4105	uint8x16_t __arm_vrshrntq_n_u16(uint8x16_t, uint16x8_t, int);
4106	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u16)))
4107	uint8x16_t __arm_vrshrntq(uint8x16_t, uint16x8_t, int);
4108	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u32)))
4109	uint16x8_t __arm_vrshrntq_n_u32(uint16x8_t, uint32x4_t, int);
4110	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u32)))
4111	uint16x8_t __arm_vrshrntq(uint16x8_t, uint32x4_t, int);
4112	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s16)))
4113	int16x8_t __arm_vrshrq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
4114	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s16)))
4115	int16x8_t __arm_vrshrq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
4116	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s32)))
4117	int32x4_t __arm_vrshrq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
4118	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s32)))
4119	int32x4_t __arm_vrshrq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
4120	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s8)))
4121	int8x16_t __arm_vrshrq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
4122	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s8)))
4123	int8x16_t __arm_vrshrq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
4124	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u16)))
4125	uint16x8_t __arm_vrshrq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4126	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u16)))
4127	uint16x8_t __arm_vrshrq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4128	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u32)))
4129	uint32x4_t __arm_vrshrq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4130	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u32)))
4131	uint32x4_t __arm_vrshrq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4132	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u8)))
4133	uint8x16_t __arm_vrshrq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4134	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u8)))
4135	uint8x16_t __arm_vrshrq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4136	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s16)))
4137	int16x8_t __arm_vrshrq_n_s16(int16x8_t, int);
4138	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s16)))
4139	int16x8_t __arm_vrshrq(int16x8_t, int);
4140	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s32)))
4141	int32x4_t __arm_vrshrq_n_s32(int32x4_t, int);
4142	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s32)))
4143	int32x4_t __arm_vrshrq(int32x4_t, int);
4144	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s8)))
4145	int8x16_t __arm_vrshrq_n_s8(int8x16_t, int);
4146	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s8)))
4147	int8x16_t __arm_vrshrq(int8x16_t, int);
4148	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u16)))
4149	uint16x8_t __arm_vrshrq_n_u16(uint16x8_t, int);
4150	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u16)))
4151	uint16x8_t __arm_vrshrq(uint16x8_t, int);
4152	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u32)))
4153	uint32x4_t __arm_vrshrq_n_u32(uint32x4_t, int);
4154	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u32)))
4155	uint32x4_t __arm_vrshrq(uint32x4_t, int);
4156	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u8)))
4157	uint8x16_t __arm_vrshrq_n_u8(uint8x16_t, int);
4158	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u8)))
4159	uint8x16_t __arm_vrshrq(uint8x16_t, int);
4160	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s16)))
4161	int16x8_t __arm_vrshrq_x_n_s16(int16x8_t, int, mve_pred16_t);
4162	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s16)))
4163	int16x8_t __arm_vrshrq_x(int16x8_t, int, mve_pred16_t);
4164	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s32)))
4165	int32x4_t __arm_vrshrq_x_n_s32(int32x4_t, int, mve_pred16_t);
4166	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s32)))
4167	int32x4_t __arm_vrshrq_x(int32x4_t, int, mve_pred16_t);
4168	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s8)))
4169	int8x16_t __arm_vrshrq_x_n_s8(int8x16_t, int, mve_pred16_t);
4170	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s8)))
4171	int8x16_t __arm_vrshrq_x(int8x16_t, int, mve_pred16_t);
4172	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u16)))
4173	uint16x8_t __arm_vrshrq_x_n_u16(uint16x8_t, int, mve_pred16_t);
4174	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u16)))
4175	uint16x8_t __arm_vrshrq_x(uint16x8_t, int, mve_pred16_t);
4176	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u32)))
4177	uint32x4_t __arm_vrshrq_x_n_u32(uint32x4_t, int, mve_pred16_t);
4178	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u32)))
4179	uint32x4_t __arm_vrshrq_x(uint32x4_t, int, mve_pred16_t);
4180	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u8)))
4181	uint8x16_t __arm_vrshrq_x_n_u8(uint8x16_t, int, mve_pred16_t);
4182	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u8)))
4183	uint8x16_t __arm_vrshrq_x(uint8x16_t, int, mve_pred16_t);
4184	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s16)))
4185	int16x8_t __arm_vsetq_lane_s16(int16_t, int16x8_t, int);
4186	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s16)))
4187	int16x8_t __arm_vsetq_lane(int16_t, int16x8_t, int);
4188	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s32)))
4189	int32x4_t __arm_vsetq_lane_s32(int32_t, int32x4_t, int);
4190	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s32)))
4191	int32x4_t __arm_vsetq_lane(int32_t, int32x4_t, int);
4192	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s64)))
4193	int64x2_t __arm_vsetq_lane_s64(int64_t, int64x2_t, int);
4194	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s64)))
4195	int64x2_t __arm_vsetq_lane(int64_t, int64x2_t, int);
4196	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s8)))
4197	int8x16_t __arm_vsetq_lane_s8(int8_t, int8x16_t, int);
4198	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s8)))
4199	int8x16_t __arm_vsetq_lane(int8_t, int8x16_t, int);
4200	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u16)))
4201	uint16x8_t __arm_vsetq_lane_u16(uint16_t, uint16x8_t, int);
4202	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u16)))
4203	uint16x8_t __arm_vsetq_lane(uint16_t, uint16x8_t, int);
4204	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u32)))
4205	uint32x4_t __arm_vsetq_lane_u32(uint32_t, uint32x4_t, int);
4206	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u32)))
4207	uint32x4_t __arm_vsetq_lane(uint32_t, uint32x4_t, int);
4208	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u64)))
4209	uint64x2_t __arm_vsetq_lane_u64(uint64_t, uint64x2_t, int);
4210	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u64)))
4211	uint64x2_t __arm_vsetq_lane(uint64_t, uint64x2_t, int);
4212	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u8)))
4213	uint8x16_t __arm_vsetq_lane_u8(uint8_t, uint8x16_t, int);
4214	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u8)))
4215	uint8x16_t __arm_vsetq_lane(uint8_t, uint8x16_t, int);
4216	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s16)))
4217	int32x4_t __arm_vshllbq_m_n_s16(int32x4_t, int16x8_t, int, mve_pred16_t);
4218	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s16)))
4219	int32x4_t __arm_vshllbq_m(int32x4_t, int16x8_t, int, mve_pred16_t);
4220	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s8)))
4221	int16x8_t __arm_vshllbq_m_n_s8(int16x8_t, int8x16_t, int, mve_pred16_t);
4222	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s8)))
4223	int16x8_t __arm_vshllbq_m(int16x8_t, int8x16_t, int, mve_pred16_t);
4224	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u16)))
4225	uint32x4_t __arm_vshllbq_m_n_u16(uint32x4_t, uint16x8_t, int, mve_pred16_t);
4226	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u16)))
4227	uint32x4_t __arm_vshllbq_m(uint32x4_t, uint16x8_t, int, mve_pred16_t);
4228	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u8)))
4229	uint16x8_t __arm_vshllbq_m_n_u8(uint16x8_t, uint8x16_t, int, mve_pred16_t);
4230	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u8)))
4231	uint16x8_t __arm_vshllbq_m(uint16x8_t, uint8x16_t, int, mve_pred16_t);
4232	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s16)))
4233	int32x4_t __arm_vshllbq_n_s16(int16x8_t, int);
4234	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s16)))
4235	int32x4_t __arm_vshllbq(int16x8_t, int);
4236	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s8)))
4237	int16x8_t __arm_vshllbq_n_s8(int8x16_t, int);
4238	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s8)))
4239	int16x8_t __arm_vshllbq(int8x16_t, int);
4240	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u16)))
4241	uint32x4_t __arm_vshllbq_n_u16(uint16x8_t, int);
4242	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u16)))
4243	uint32x4_t __arm_vshllbq(uint16x8_t, int);
4244	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u8)))
4245	uint16x8_t __arm_vshllbq_n_u8(uint8x16_t, int);
4246	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u8)))
4247	uint16x8_t __arm_vshllbq(uint8x16_t, int);
4248	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s16)))
4249	int32x4_t __arm_vshllbq_x_n_s16(int16x8_t, int, mve_pred16_t);
4250	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s16)))
4251	int32x4_t __arm_vshllbq_x(int16x8_t, int, mve_pred16_t);
4252	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s8)))
4253	int16x8_t __arm_vshllbq_x_n_s8(int8x16_t, int, mve_pred16_t);
4254	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s8)))
4255	int16x8_t __arm_vshllbq_x(int8x16_t, int, mve_pred16_t);
4256	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u16)))
4257	uint32x4_t __arm_vshllbq_x_n_u16(uint16x8_t, int, mve_pred16_t);
4258	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u16)))
4259	uint32x4_t __arm_vshllbq_x(uint16x8_t, int, mve_pred16_t);
4260	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u8)))
4261	uint16x8_t __arm_vshllbq_x_n_u8(uint8x16_t, int, mve_pred16_t);
4262	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u8)))
4263	uint16x8_t __arm_vshllbq_x(uint8x16_t, int, mve_pred16_t);
4264	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s16)))
4265	int32x4_t __arm_vshlltq_m_n_s16(int32x4_t, int16x8_t, int, mve_pred16_t);
4266	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s16)))
4267	int32x4_t __arm_vshlltq_m(int32x4_t, int16x8_t, int, mve_pred16_t);
4268	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s8)))
4269	int16x8_t __arm_vshlltq_m_n_s8(int16x8_t, int8x16_t, int, mve_pred16_t);
4270	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s8)))
4271	int16x8_t __arm_vshlltq_m(int16x8_t, int8x16_t, int, mve_pred16_t);
4272	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u16)))
4273	uint32x4_t __arm_vshlltq_m_n_u16(uint32x4_t, uint16x8_t, int, mve_pred16_t);
4274	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u16)))
4275	uint32x4_t __arm_vshlltq_m(uint32x4_t, uint16x8_t, int, mve_pred16_t);
4276	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u8)))
4277	uint16x8_t __arm_vshlltq_m_n_u8(uint16x8_t, uint8x16_t, int, mve_pred16_t);
4278	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u8)))
4279	uint16x8_t __arm_vshlltq_m(uint16x8_t, uint8x16_t, int, mve_pred16_t);
4280	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s16)))
4281	int32x4_t __arm_vshlltq_n_s16(int16x8_t, int);
4282	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s16)))
4283	int32x4_t __arm_vshlltq(int16x8_t, int);
4284	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s8)))
4285	int16x8_t __arm_vshlltq_n_s8(int8x16_t, int);
4286	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s8)))
4287	int16x8_t __arm_vshlltq(int8x16_t, int);
4288	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u16)))
4289	uint32x4_t __arm_vshlltq_n_u16(uint16x8_t, int);
4290	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u16)))
4291	uint32x4_t __arm_vshlltq(uint16x8_t, int);
4292	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u8)))
4293	uint16x8_t __arm_vshlltq_n_u8(uint8x16_t, int);
4294	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u8)))
4295	uint16x8_t __arm_vshlltq(uint8x16_t, int);
4296	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s16)))
4297	int32x4_t __arm_vshlltq_x_n_s16(int16x8_t, int, mve_pred16_t);
4298	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s16)))
4299	int32x4_t __arm_vshlltq_x(int16x8_t, int, mve_pred16_t);
4300	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s8)))
4301	int16x8_t __arm_vshlltq_x_n_s8(int8x16_t, int, mve_pred16_t);
4302	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s8)))
4303	int16x8_t __arm_vshlltq_x(int8x16_t, int, mve_pred16_t);
4304	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u16)))
4305	uint32x4_t __arm_vshlltq_x_n_u16(uint16x8_t, int, mve_pred16_t);
4306	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u16)))
4307	uint32x4_t __arm_vshlltq_x(uint16x8_t, int, mve_pred16_t);
4308	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u8)))
4309	uint16x8_t __arm_vshlltq_x_n_u8(uint8x16_t, int, mve_pred16_t);
4310	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u8)))
4311	uint16x8_t __arm_vshlltq_x(uint8x16_t, int, mve_pred16_t);
4312	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s16)))
4313	int16x8_t __arm_vshlq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
4314	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s16)))
4315	int16x8_t __arm_vshlq_m_n(int16x8_t, int16x8_t, int, mve_pred16_t);
4316	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s32)))
4317	int32x4_t __arm_vshlq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
4318	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s32)))
4319	int32x4_t __arm_vshlq_m_n(int32x4_t, int32x4_t, int, mve_pred16_t);
4320	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s8)))
4321	int8x16_t __arm_vshlq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
4322	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s8)))
4323	int8x16_t __arm_vshlq_m_n(int8x16_t, int8x16_t, int, mve_pred16_t);
4324	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u16)))
4325	uint16x8_t __arm_vshlq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4326	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u16)))
4327	uint16x8_t __arm_vshlq_m_n(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4328	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u32)))
4329	uint32x4_t __arm_vshlq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4330	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u32)))
4331	uint32x4_t __arm_vshlq_m_n(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4332	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u8)))
4333	uint8x16_t __arm_vshlq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4334	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u8)))
4335	uint8x16_t __arm_vshlq_m_n(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4336	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s16)))
4337	int16x8_t __arm_vshlq_m_r_s16(int16x8_t, int32_t, mve_pred16_t);
4338	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s16)))
4339	int16x8_t __arm_vshlq_m_r(int16x8_t, int32_t, mve_pred16_t);
4340	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s32)))
4341	int32x4_t __arm_vshlq_m_r_s32(int32x4_t, int32_t, mve_pred16_t);
4342	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s32)))
4343	int32x4_t __arm_vshlq_m_r(int32x4_t, int32_t, mve_pred16_t);
4344	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s8)))
4345	int8x16_t __arm_vshlq_m_r_s8(int8x16_t, int32_t, mve_pred16_t);
4346	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s8)))
4347	int8x16_t __arm_vshlq_m_r(int8x16_t, int32_t, mve_pred16_t);
4348	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u16)))
4349	uint16x8_t __arm_vshlq_m_r_u16(uint16x8_t, int32_t, mve_pred16_t);
4350	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u16)))
4351	uint16x8_t __arm_vshlq_m_r(uint16x8_t, int32_t, mve_pred16_t);
4352	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u32)))
4353	uint32x4_t __arm_vshlq_m_r_u32(uint32x4_t, int32_t, mve_pred16_t);
4354	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u32)))
4355	uint32x4_t __arm_vshlq_m_r(uint32x4_t, int32_t, mve_pred16_t);
4356	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u8)))
4357	uint8x16_t __arm_vshlq_m_r_u8(uint8x16_t, int32_t, mve_pred16_t);
4358	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u8)))
4359	uint8x16_t __arm_vshlq_m_r(uint8x16_t, int32_t, mve_pred16_t);
4360	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s16)))
4361	int16x8_t __arm_vshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
4362	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s16)))
4363	int16x8_t __arm_vshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
4364	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s32)))
4365	int32x4_t __arm_vshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
4366	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s32)))
4367	int32x4_t __arm_vshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
4368	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s8)))
4369	int8x16_t __arm_vshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
4370	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s8)))
4371	int8x16_t __arm_vshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
4372	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u16)))
4373	uint16x8_t __arm_vshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
4374	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u16)))
4375	uint16x8_t __arm_vshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
4376	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u32)))
4377	uint32x4_t __arm_vshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
4378	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u32)))
4379	uint32x4_t __arm_vshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
4380	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u8)))
4381	uint8x16_t __arm_vshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
4382	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u8)))
4383	uint8x16_t __arm_vshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
4384	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s16)))
4385	int16x8_t __arm_vshlq_n_s16(int16x8_t, int);
4386	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s16)))
4387	int16x8_t __arm_vshlq_n(int16x8_t, int);
4388	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s32)))
4389	int32x4_t __arm_vshlq_n_s32(int32x4_t, int);
4390	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s32)))
4391	int32x4_t __arm_vshlq_n(int32x4_t, int);
4392	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s8)))
4393	int8x16_t __arm_vshlq_n_s8(int8x16_t, int);
4394	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s8)))
4395	int8x16_t __arm_vshlq_n(int8x16_t, int);
4396	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u16)))
4397	uint16x8_t __arm_vshlq_n_u16(uint16x8_t, int);
4398	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u16)))
4399	uint16x8_t __arm_vshlq_n(uint16x8_t, int);
4400	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u32)))
4401	uint32x4_t __arm_vshlq_n_u32(uint32x4_t, int);
4402	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u32)))
4403	uint32x4_t __arm_vshlq_n(uint32x4_t, int);
4404	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u8)))
4405	uint8x16_t __arm_vshlq_n_u8(uint8x16_t, int);
4406	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u8)))
4407	uint8x16_t __arm_vshlq_n(uint8x16_t, int);
4408	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s16)))
4409	int16x8_t __arm_vshlq_r_s16(int16x8_t, int32_t);
4410	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s16)))
4411	int16x8_t __arm_vshlq_r(int16x8_t, int32_t);
4412	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s32)))
4413	int32x4_t __arm_vshlq_r_s32(int32x4_t, int32_t);
4414	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s32)))
4415	int32x4_t __arm_vshlq_r(int32x4_t, int32_t);
4416	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s8)))
4417	int8x16_t __arm_vshlq_r_s8(int8x16_t, int32_t);
4418	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s8)))
4419	int8x16_t __arm_vshlq_r(int8x16_t, int32_t);
4420	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u16)))
4421	uint16x8_t __arm_vshlq_r_u16(uint16x8_t, int32_t);
4422	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u16)))
4423	uint16x8_t __arm_vshlq_r(uint16x8_t, int32_t);
4424	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u32)))
4425	uint32x4_t __arm_vshlq_r_u32(uint32x4_t, int32_t);
4426	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u32)))
4427	uint32x4_t __arm_vshlq_r(uint32x4_t, int32_t);
4428	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u8)))
4429	uint8x16_t __arm_vshlq_r_u8(uint8x16_t, int32_t);
4430	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u8)))
4431	uint8x16_t __arm_vshlq_r(uint8x16_t, int32_t);
4432	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s16)))
4433	int16x8_t __arm_vshlq_s16(int16x8_t, int16x8_t);
4434	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s16)))
4435	int16x8_t __arm_vshlq(int16x8_t, int16x8_t);
4436	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s32)))
4437	int32x4_t __arm_vshlq_s32(int32x4_t, int32x4_t);
4438	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s32)))
4439	int32x4_t __arm_vshlq(int32x4_t, int32x4_t);
4440	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s8)))
4441	int8x16_t __arm_vshlq_s8(int8x16_t, int8x16_t);
4442	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s8)))
4443	int8x16_t __arm_vshlq(int8x16_t, int8x16_t);
4444	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u16)))
4445	uint16x8_t __arm_vshlq_u16(uint16x8_t, int16x8_t);
4446	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u16)))
4447	uint16x8_t __arm_vshlq(uint16x8_t, int16x8_t);
4448	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u32)))
4449	uint32x4_t __arm_vshlq_u32(uint32x4_t, int32x4_t);
4450	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u32)))
4451	uint32x4_t __arm_vshlq(uint32x4_t, int32x4_t);
4452	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u8)))
4453	uint8x16_t __arm_vshlq_u8(uint8x16_t, int8x16_t);
4454	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u8)))
4455	uint8x16_t __arm_vshlq(uint8x16_t, int8x16_t);
4456	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s16)))
4457	int16x8_t __arm_vshlq_x_n_s16(int16x8_t, int, mve_pred16_t);
4458	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s16)))
4459	int16x8_t __arm_vshlq_x_n(int16x8_t, int, mve_pred16_t);
4460	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s32)))
4461	int32x4_t __arm_vshlq_x_n_s32(int32x4_t, int, mve_pred16_t);
4462	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s32)))
4463	int32x4_t __arm_vshlq_x_n(int32x4_t, int, mve_pred16_t);
4464	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s8)))
4465	int8x16_t __arm_vshlq_x_n_s8(int8x16_t, int, mve_pred16_t);
4466	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s8)))
4467	int8x16_t __arm_vshlq_x_n(int8x16_t, int, mve_pred16_t);
4468	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u16)))
4469	uint16x8_t __arm_vshlq_x_n_u16(uint16x8_t, int, mve_pred16_t);
4470	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u16)))
4471	uint16x8_t __arm_vshlq_x_n(uint16x8_t, int, mve_pred16_t);
4472	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u32)))
4473	uint32x4_t __arm_vshlq_x_n_u32(uint32x4_t, int, mve_pred16_t);
4474	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u32)))
4475	uint32x4_t __arm_vshlq_x_n(uint32x4_t, int, mve_pred16_t);
4476	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u8)))
4477	uint8x16_t __arm_vshlq_x_n_u8(uint8x16_t, int, mve_pred16_t);
4478	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u8)))
4479	uint8x16_t __arm_vshlq_x_n(uint8x16_t, int, mve_pred16_t);
4480	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s16)))
4481	int16x8_t __arm_vshlq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
4482	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s16)))
4483	int16x8_t __arm_vshlq_x(int16x8_t, int16x8_t, mve_pred16_t);
4484	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s32)))
4485	int32x4_t __arm_vshlq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
4486	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s32)))
4487	int32x4_t __arm_vshlq_x(int32x4_t, int32x4_t, mve_pred16_t);
4488	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s8)))
4489	int8x16_t __arm_vshlq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
4490	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s8)))
4491	int8x16_t __arm_vshlq_x(int8x16_t, int8x16_t, mve_pred16_t);
4492	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u16)))
4493	uint16x8_t __arm_vshlq_x_u16(uint16x8_t, int16x8_t, mve_pred16_t);
4494	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u16)))
4495	uint16x8_t __arm_vshlq_x(uint16x8_t, int16x8_t, mve_pred16_t);
4496	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u32)))
4497	uint32x4_t __arm_vshlq_x_u32(uint32x4_t, int32x4_t, mve_pred16_t);
4498	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u32)))
4499	uint32x4_t __arm_vshlq_x(uint32x4_t, int32x4_t, mve_pred16_t);
4500	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u8)))
4501	uint8x16_t __arm_vshlq_x_u8(uint8x16_t, int8x16_t, mve_pred16_t);
4502	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u8)))
4503	uint8x16_t __arm_vshlq_x(uint8x16_t, int8x16_t, mve_pred16_t);
4504	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s16)))
4505	int8x16_t __arm_vshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
4506	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s16)))
4507	int8x16_t __arm_vshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
4508	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s32)))
4509	int16x8_t __arm_vshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
4510	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s32)))
4511	int16x8_t __arm_vshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
4512	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u16)))
4513	uint8x16_t __arm_vshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4514	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u16)))
4515	uint8x16_t __arm_vshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4516	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u32)))
4517	uint16x8_t __arm_vshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4518	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u32)))
4519	uint16x8_t __arm_vshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4520	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s16)))
4521	int8x16_t __arm_vshrnbq_n_s16(int8x16_t, int16x8_t, int);
4522	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s16)))
4523	int8x16_t __arm_vshrnbq(int8x16_t, int16x8_t, int);
4524	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s32)))
4525	int16x8_t __arm_vshrnbq_n_s32(int16x8_t, int32x4_t, int);
4526	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s32)))
4527	int16x8_t __arm_vshrnbq(int16x8_t, int32x4_t, int);
4528	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u16)))
4529	uint8x16_t __arm_vshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
4530	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u16)))
4531	uint8x16_t __arm_vshrnbq(uint8x16_t, uint16x8_t, int);
4532	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u32)))
4533	uint16x8_t __arm_vshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
4534	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u32)))
4535	uint16x8_t __arm_vshrnbq(uint16x8_t, uint32x4_t, int);
4536	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s16)))
4537	int8x16_t __arm_vshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
4538	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s16)))
4539	int8x16_t __arm_vshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
4540	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s32)))
4541	int16x8_t __arm_vshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
4542	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s32)))
4543	int16x8_t __arm_vshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
4544	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u16)))
4545	uint8x16_t __arm_vshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4546	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u16)))
4547	uint8x16_t __arm_vshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
4548	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u32)))
4549	uint16x8_t __arm_vshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4550	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u32)))
4551	uint16x8_t __arm_vshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
4552	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s16)))
4553	int8x16_t __arm_vshrntq_n_s16(int8x16_t, int16x8_t, int);
4554	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s16)))
4555	int8x16_t __arm_vshrntq(int8x16_t, int16x8_t, int);
4556	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s32)))
4557	int16x8_t __arm_vshrntq_n_s32(int16x8_t, int32x4_t, int);
4558	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s32)))
4559	int16x8_t __arm_vshrntq(int16x8_t, int32x4_t, int);
4560	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u16)))
4561	uint8x16_t __arm_vshrntq_n_u16(uint8x16_t, uint16x8_t, int);
4562	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u16)))
4563	uint8x16_t __arm_vshrntq(uint8x16_t, uint16x8_t, int);
4564	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u32)))
4565	uint16x8_t __arm_vshrntq_n_u32(uint16x8_t, uint32x4_t, int);
4566	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u32)))
4567	uint16x8_t __arm_vshrntq(uint16x8_t, uint32x4_t, int);
4568	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s16)))
4569	int16x8_t __arm_vshrq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
4570	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s16)))
4571	int16x8_t __arm_vshrq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
4572	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s32)))
4573	int32x4_t __arm_vshrq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
4574	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s32)))
4575	int32x4_t __arm_vshrq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
4576	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s8)))
4577	int8x16_t __arm_vshrq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
4578	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s8)))
4579	int8x16_t __arm_vshrq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
4580	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u16)))
4581	uint16x8_t __arm_vshrq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4582	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u16)))
4583	uint16x8_t __arm_vshrq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4584	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u32)))
4585	uint32x4_t __arm_vshrq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4586	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u32)))
4587	uint32x4_t __arm_vshrq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4588	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u8)))
4589	uint8x16_t __arm_vshrq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4590	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u8)))
4591	uint8x16_t __arm_vshrq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4592	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s16)))
4593	int16x8_t __arm_vshrq_n_s16(int16x8_t, int);
4594	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s16)))
4595	int16x8_t __arm_vshrq(int16x8_t, int);
4596	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s32)))
4597	int32x4_t __arm_vshrq_n_s32(int32x4_t, int);
4598	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s32)))
4599	int32x4_t __arm_vshrq(int32x4_t, int);
4600	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s8)))
4601	int8x16_t __arm_vshrq_n_s8(int8x16_t, int);
4602	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s8)))
4603	int8x16_t __arm_vshrq(int8x16_t, int);
4604	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u16)))
4605	uint16x8_t __arm_vshrq_n_u16(uint16x8_t, int);
4606	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u16)))
4607	uint16x8_t __arm_vshrq(uint16x8_t, int);
4608	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u32)))
4609	uint32x4_t __arm_vshrq_n_u32(uint32x4_t, int);
4610	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u32)))
4611	uint32x4_t __arm_vshrq(uint32x4_t, int);
4612	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u8)))
4613	uint8x16_t __arm_vshrq_n_u8(uint8x16_t, int);
4614	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u8)))
4615	uint8x16_t __arm_vshrq(uint8x16_t, int);
4616	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s16)))
4617	int16x8_t __arm_vshrq_x_n_s16(int16x8_t, int, mve_pred16_t);
4618	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s16)))
4619	int16x8_t __arm_vshrq_x(int16x8_t, int, mve_pred16_t);
4620	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s32)))
4621	int32x4_t __arm_vshrq_x_n_s32(int32x4_t, int, mve_pred16_t);
4622	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s32)))
4623	int32x4_t __arm_vshrq_x(int32x4_t, int, mve_pred16_t);
4624	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s8)))
4625	int8x16_t __arm_vshrq_x_n_s8(int8x16_t, int, mve_pred16_t);
4626	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s8)))
4627	int8x16_t __arm_vshrq_x(int8x16_t, int, mve_pred16_t);
4628	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u16)))
4629	uint16x8_t __arm_vshrq_x_n_u16(uint16x8_t, int, mve_pred16_t);
4630	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u16)))
4631	uint16x8_t __arm_vshrq_x(uint16x8_t, int, mve_pred16_t);
4632	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u32)))
4633	uint32x4_t __arm_vshrq_x_n_u32(uint32x4_t, int, mve_pred16_t);
4634	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u32)))
4635	uint32x4_t __arm_vshrq_x(uint32x4_t, int, mve_pred16_t);
4636	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u8)))
4637	uint8x16_t __arm_vshrq_x_n_u8(uint8x16_t, int, mve_pred16_t);
4638	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u8)))
4639	uint8x16_t __arm_vshrq_x(uint8x16_t, int, mve_pred16_t);
4640	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s16)))
4641	int16x8_t __arm_vsliq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
4642	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s16)))
4643	int16x8_t __arm_vsliq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
4644	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s32)))
4645	int32x4_t __arm_vsliq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
4646	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s32)))
4647	int32x4_t __arm_vsliq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
4648	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s8)))
4649	int8x16_t __arm_vsliq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
4650	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s8)))
4651	int8x16_t __arm_vsliq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
4652	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u16)))
4653	uint16x8_t __arm_vsliq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4654	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u16)))
4655	uint16x8_t __arm_vsliq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4656	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u32)))
4657	uint32x4_t __arm_vsliq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4658	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u32)))
4659	uint32x4_t __arm_vsliq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4660	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u8)))
4661	uint8x16_t __arm_vsliq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4662	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u8)))
4663	uint8x16_t __arm_vsliq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4664	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s16)))
4665	int16x8_t __arm_vsliq_n_s16(int16x8_t, int16x8_t, int);
4666	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s16)))
4667	int16x8_t __arm_vsliq(int16x8_t, int16x8_t, int);
4668	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s32)))
4669	int32x4_t __arm_vsliq_n_s32(int32x4_t, int32x4_t, int);
4670	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s32)))
4671	int32x4_t __arm_vsliq(int32x4_t, int32x4_t, int);
4672	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s8)))
4673	int8x16_t __arm_vsliq_n_s8(int8x16_t, int8x16_t, int);
4674	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s8)))
4675	int8x16_t __arm_vsliq(int8x16_t, int8x16_t, int);
4676	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u16)))
4677	uint16x8_t __arm_vsliq_n_u16(uint16x8_t, uint16x8_t, int);
4678	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u16)))
4679	uint16x8_t __arm_vsliq(uint16x8_t, uint16x8_t, int);
4680	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u32)))
4681	uint32x4_t __arm_vsliq_n_u32(uint32x4_t, uint32x4_t, int);
4682	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u32)))
4683	uint32x4_t __arm_vsliq(uint32x4_t, uint32x4_t, int);
4684	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u8)))
4685	uint8x16_t __arm_vsliq_n_u8(uint8x16_t, uint8x16_t, int);
4686	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u8)))
4687	uint8x16_t __arm_vsliq(uint8x16_t, uint8x16_t, int);
4688	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s16)))
4689	int16x8_t __arm_vsriq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
4690	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s16)))
4691	int16x8_t __arm_vsriq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
4692	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s32)))
4693	int32x4_t __arm_vsriq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
4694	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s32)))
4695	int32x4_t __arm_vsriq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
4696	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s8)))
4697	int8x16_t __arm_vsriq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
4698	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s8)))
4699	int8x16_t __arm_vsriq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
4700	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u16)))
4701	uint16x8_t __arm_vsriq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4702	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u16)))
4703	uint16x8_t __arm_vsriq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
4704	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u32)))
4705	uint32x4_t __arm_vsriq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4706	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u32)))
4707	uint32x4_t __arm_vsriq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
4708	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u8)))
4709	uint8x16_t __arm_vsriq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4710	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u8)))
4711	uint8x16_t __arm_vsriq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
4712	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s16)))
4713	int16x8_t __arm_vsriq_n_s16(int16x8_t, int16x8_t, int);
4714	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s16)))
4715	int16x8_t __arm_vsriq(int16x8_t, int16x8_t, int);
4716	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s32)))
4717	int32x4_t __arm_vsriq_n_s32(int32x4_t, int32x4_t, int);
4718	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s32)))
4719	int32x4_t __arm_vsriq(int32x4_t, int32x4_t, int);
4720	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s8)))
4721	int8x16_t __arm_vsriq_n_s8(int8x16_t, int8x16_t, int);
4722	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s8)))
4723	int8x16_t __arm_vsriq(int8x16_t, int8x16_t, int);
4724	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u16)))
4725	uint16x8_t __arm_vsriq_n_u16(uint16x8_t, uint16x8_t, int);
4726	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u16)))
4727	uint16x8_t __arm_vsriq(uint16x8_t, uint16x8_t, int);
4728	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u32)))
4729	uint32x4_t __arm_vsriq_n_u32(uint32x4_t, uint32x4_t, int);
4730	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u32)))
4731	uint32x4_t __arm_vsriq(uint32x4_t, uint32x4_t, int);
4732	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u8)))
4733	uint8x16_t __arm_vsriq_n_u8(uint8x16_t, uint8x16_t, int);
4734	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u8)))
4735	uint8x16_t __arm_vsriq(uint8x16_t, uint8x16_t, int);
4736	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s16)))
4737	void __arm_vst1q_p_s16(int16_t *, int16x8_t, mve_pred16_t);
4738	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s16)))
4739	void __arm_vst1q_p(int16_t *, int16x8_t, mve_pred16_t);
4740	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s32)))
4741	void __arm_vst1q_p_s32(int32_t *, int32x4_t, mve_pred16_t);
4742	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s32)))
4743	void __arm_vst1q_p(int32_t *, int32x4_t, mve_pred16_t);
4744	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s8)))
4745	void __arm_vst1q_p_s8(int8_t *, int8x16_t, mve_pred16_t);
4746	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s8)))
4747	void __arm_vst1q_p(int8_t *, int8x16_t, mve_pred16_t);
4748	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u16)))
4749	void __arm_vst1q_p_u16(uint16_t *, uint16x8_t, mve_pred16_t);
4750	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u16)))
4751	void __arm_vst1q_p(uint16_t *, uint16x8_t, mve_pred16_t);
4752	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u32)))
4753	void __arm_vst1q_p_u32(uint32_t *, uint32x4_t, mve_pred16_t);
4754	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u32)))
4755	void __arm_vst1q_p(uint32_t *, uint32x4_t, mve_pred16_t);
4756	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u8)))
4757	void __arm_vst1q_p_u8(uint8_t *, uint8x16_t, mve_pred16_t);
4758	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u8)))
4759	void __arm_vst1q_p(uint8_t *, uint8x16_t, mve_pred16_t);
4760	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s16)))
4761	void __arm_vst1q_s16(int16_t *, int16x8_t);
4762	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s16)))
4763	void __arm_vst1q(int16_t *, int16x8_t);
4764	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s32)))
4765	void __arm_vst1q_s32(int32_t *, int32x4_t);
4766	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s32)))
4767	void __arm_vst1q(int32_t *, int32x4_t);
4768	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s8)))
4769	void __arm_vst1q_s8(int8_t *, int8x16_t);
4770	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s8)))
4771	void __arm_vst1q(int8_t *, int8x16_t);
4772	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u16)))
4773	void __arm_vst1q_u16(uint16_t *, uint16x8_t);
4774	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u16)))
4775	void __arm_vst1q(uint16_t *, uint16x8_t);
4776	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u32)))
4777	void __arm_vst1q_u32(uint32_t *, uint32x4_t);
4778	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u32)))
4779	void __arm_vst1q(uint32_t *, uint32x4_t);
4780	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u8)))
4781	void __arm_vst1q_u8(uint8_t *, uint8x16_t);
4782	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u8)))
4783	void __arm_vst1q(uint8_t *, uint8x16_t);
4784	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s16)))
4785	void __arm_vst2q_s16(int16_t *, int16x8x2_t);
4786	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s16)))
4787	void __arm_vst2q(int16_t *, int16x8x2_t);
4788	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s32)))
4789	void __arm_vst2q_s32(int32_t *, int32x4x2_t);
4790	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s32)))
4791	void __arm_vst2q(int32_t *, int32x4x2_t);
4792	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s8)))
4793	void __arm_vst2q_s8(int8_t *, int8x16x2_t);
4794	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s8)))
4795	void __arm_vst2q(int8_t *, int8x16x2_t);
4796	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u16)))
4797	void __arm_vst2q_u16(uint16_t *, uint16x8x2_t);
4798	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u16)))
4799	void __arm_vst2q(uint16_t *, uint16x8x2_t);
4800	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u32)))
4801	void __arm_vst2q_u32(uint32_t *, uint32x4x2_t);
4802	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u32)))
4803	void __arm_vst2q(uint32_t *, uint32x4x2_t);
4804	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u8)))
4805	void __arm_vst2q_u8(uint8_t *, uint8x16x2_t);
4806	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u8)))
4807	void __arm_vst2q(uint8_t *, uint8x16x2_t);
4808	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s16)))
4809	void __arm_vst4q_s16(int16_t *, int16x8x4_t);
4810	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s16)))
4811	void __arm_vst4q(int16_t *, int16x8x4_t);
4812	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s32)))
4813	void __arm_vst4q_s32(int32_t *, int32x4x4_t);
4814	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s32)))
4815	void __arm_vst4q(int32_t *, int32x4x4_t);
4816	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s8)))
4817	void __arm_vst4q_s8(int8_t *, int8x16x4_t);
4818	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s8)))
4819	void __arm_vst4q(int8_t *, int8x16x4_t);
4820	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u16)))
4821	void __arm_vst4q_u16(uint16_t *, uint16x8x4_t);
4822	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u16)))
4823	void __arm_vst4q(uint16_t *, uint16x8x4_t);
4824	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u32)))
4825	void __arm_vst4q_u32(uint32_t *, uint32x4x4_t);
4826	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u32)))
4827	void __arm_vst4q(uint32_t *, uint32x4x4_t);
4828	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u8)))
4829	void __arm_vst4q_u8(uint8_t *, uint8x16x4_t);
4830	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u8)))
4831	void __arm_vst4q(uint8_t *, uint8x16x4_t);
4832	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s16)))
4833	void __arm_vstrbq_p_s16(int8_t *, int16x8_t, mve_pred16_t);
4834	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s16)))
4835	void __arm_vstrbq_p(int8_t *, int16x8_t, mve_pred16_t);
4836	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s32)))
4837	void __arm_vstrbq_p_s32(int8_t *, int32x4_t, mve_pred16_t);
4838	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s32)))
4839	void __arm_vstrbq_p(int8_t *, int32x4_t, mve_pred16_t);
4840	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s8)))
4841	void __arm_vstrbq_p_s8(int8_t *, int8x16_t, mve_pred16_t);
4842	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s8)))
4843	void __arm_vstrbq_p(int8_t *, int8x16_t, mve_pred16_t);
4844	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u16)))
4845	void __arm_vstrbq_p_u16(uint8_t *, uint16x8_t, mve_pred16_t);
4846	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u16)))
4847	void __arm_vstrbq_p(uint8_t *, uint16x8_t, mve_pred16_t);
4848	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u32)))
4849	void __arm_vstrbq_p_u32(uint8_t *, uint32x4_t, mve_pred16_t);
4850	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u32)))
4851	void __arm_vstrbq_p(uint8_t *, uint32x4_t, mve_pred16_t);
4852	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u8)))
4853	void __arm_vstrbq_p_u8(uint8_t *, uint8x16_t, mve_pred16_t);
4854	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u8)))
4855	void __arm_vstrbq_p(uint8_t *, uint8x16_t, mve_pred16_t);
4856	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s16)))
4857	void __arm_vstrbq_s16(int8_t *, int16x8_t);
4858	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s16)))
4859	void __arm_vstrbq(int8_t *, int16x8_t);
4860	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s32)))
4861	void __arm_vstrbq_s32(int8_t *, int32x4_t);
4862	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s32)))
4863	void __arm_vstrbq(int8_t *, int32x4_t);
4864	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s8)))
4865	void __arm_vstrbq_s8(int8_t *, int8x16_t);
4866	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s8)))
4867	void __arm_vstrbq(int8_t *, int8x16_t);
4868	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s16)))
4869	void __arm_vstrbq_scatter_offset_p_s16(int8_t *, uint16x8_t, int16x8_t, mve_pred16_t);
4870	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s16)))
4871	void __arm_vstrbq_scatter_offset_p(int8_t *, uint16x8_t, int16x8_t, mve_pred16_t);
4872	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s32)))
4873	void __arm_vstrbq_scatter_offset_p_s32(int8_t *, uint32x4_t, int32x4_t, mve_pred16_t);
4874	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s32)))
4875	void __arm_vstrbq_scatter_offset_p(int8_t *, uint32x4_t, int32x4_t, mve_pred16_t);
4876	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s8)))
4877	void __arm_vstrbq_scatter_offset_p_s8(int8_t *, uint8x16_t, int8x16_t, mve_pred16_t);
4878	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s8)))
4879	void __arm_vstrbq_scatter_offset_p(int8_t *, uint8x16_t, int8x16_t, mve_pred16_t);
4880	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u16)))
4881	void __arm_vstrbq_scatter_offset_p_u16(uint8_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
4882	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u16)))
4883	void __arm_vstrbq_scatter_offset_p(uint8_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
4884	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u32)))
4885	void __arm_vstrbq_scatter_offset_p_u32(uint8_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
4886	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u32)))
4887	void __arm_vstrbq_scatter_offset_p(uint8_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
4888	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u8)))
4889	void __arm_vstrbq_scatter_offset_p_u8(uint8_t *, uint8x16_t, uint8x16_t, mve_pred16_t);
4890	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u8)))
4891	void __arm_vstrbq_scatter_offset_p(uint8_t *, uint8x16_t, uint8x16_t, mve_pred16_t);
4892	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s16)))
4893	void __arm_vstrbq_scatter_offset_s16(int8_t *, uint16x8_t, int16x8_t);
4894	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s16)))
4895	void __arm_vstrbq_scatter_offset(int8_t *, uint16x8_t, int16x8_t);
4896	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s32)))
4897	void __arm_vstrbq_scatter_offset_s32(int8_t *, uint32x4_t, int32x4_t);
4898	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s32)))
4899	void __arm_vstrbq_scatter_offset(int8_t *, uint32x4_t, int32x4_t);
4900	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s8)))
4901	void __arm_vstrbq_scatter_offset_s8(int8_t *, uint8x16_t, int8x16_t);
4902	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s8)))
4903	void __arm_vstrbq_scatter_offset(int8_t *, uint8x16_t, int8x16_t);
4904	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u16)))
4905	void __arm_vstrbq_scatter_offset_u16(uint8_t *, uint16x8_t, uint16x8_t);
4906	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u16)))
4907	void __arm_vstrbq_scatter_offset(uint8_t *, uint16x8_t, uint16x8_t);
4908	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u32)))
4909	void __arm_vstrbq_scatter_offset_u32(uint8_t *, uint32x4_t, uint32x4_t);
4910	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u32)))
4911	void __arm_vstrbq_scatter_offset(uint8_t *, uint32x4_t, uint32x4_t);
4912	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u8)))
4913	void __arm_vstrbq_scatter_offset_u8(uint8_t *, uint8x16_t, uint8x16_t);
4914	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u8)))
4915	void __arm_vstrbq_scatter_offset(uint8_t *, uint8x16_t, uint8x16_t);
4916	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u16)))
4917	void __arm_vstrbq_u16(uint8_t *, uint16x8_t);
4918	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u16)))
4919	void __arm_vstrbq(uint8_t *, uint16x8_t);
4920	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u32)))
4921	void __arm_vstrbq_u32(uint8_t *, uint32x4_t);
4922	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u32)))
4923	void __arm_vstrbq(uint8_t *, uint32x4_t);
4924	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u8)))
4925	void __arm_vstrbq_u8(uint8_t *, uint8x16_t);
4926	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u8)))
4927	void __arm_vstrbq(uint8_t *, uint8x16_t);
4928	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_s64)))
4929	void __arm_vstrdq_scatter_base_p_s64(uint64x2_t, int, int64x2_t, mve_pred16_t);
4930	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_s64)))
4931	void __arm_vstrdq_scatter_base_p(uint64x2_t, int, int64x2_t, mve_pred16_t);
4932	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_u64)))
4933	void __arm_vstrdq_scatter_base_p_u64(uint64x2_t, int, uint64x2_t, mve_pred16_t);
4934	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_u64)))
4935	void __arm_vstrdq_scatter_base_p(uint64x2_t, int, uint64x2_t, mve_pred16_t);
4936	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_s64)))
4937	void __arm_vstrdq_scatter_base_s64(uint64x2_t, int, int64x2_t);
4938	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_s64)))
4939	void __arm_vstrdq_scatter_base(uint64x2_t, int, int64x2_t);
4940	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_u64)))
4941	void __arm_vstrdq_scatter_base_u64(uint64x2_t, int, uint64x2_t);
4942	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_u64)))
4943	void __arm_vstrdq_scatter_base(uint64x2_t, int, uint64x2_t);
4944	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_s64)))
4945	void __arm_vstrdq_scatter_base_wb_p_s64(uint64x2_t *, int, int64x2_t, mve_pred16_t);
4946	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_s64)))
4947	void __arm_vstrdq_scatter_base_wb_p(uint64x2_t *, int, int64x2_t, mve_pred16_t);
4948	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_u64)))
4949	void __arm_vstrdq_scatter_base_wb_p_u64(uint64x2_t *, int, uint64x2_t, mve_pred16_t);
4950	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_u64)))
4951	void __arm_vstrdq_scatter_base_wb_p(uint64x2_t *, int, uint64x2_t, mve_pred16_t);
4952	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_s64)))
4953	void __arm_vstrdq_scatter_base_wb_s64(uint64x2_t *, int, int64x2_t);
4954	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_s64)))
4955	void __arm_vstrdq_scatter_base_wb(uint64x2_t *, int, int64x2_t);
4956	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_u64)))
4957	void __arm_vstrdq_scatter_base_wb_u64(uint64x2_t *, int, uint64x2_t);
4958	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_u64)))
4959	void __arm_vstrdq_scatter_base_wb(uint64x2_t *, int, uint64x2_t);
4960	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_s64)))
4961	void __arm_vstrdq_scatter_offset_p_s64(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
4962	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_s64)))
4963	void __arm_vstrdq_scatter_offset_p(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
4964	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_u64)))
4965	void __arm_vstrdq_scatter_offset_p_u64(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
4966	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_u64)))
4967	void __arm_vstrdq_scatter_offset_p(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
4968	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_s64)))
4969	void __arm_vstrdq_scatter_offset_s64(int64_t *, uint64x2_t, int64x2_t);
4970	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_s64)))
4971	void __arm_vstrdq_scatter_offset(int64_t *, uint64x2_t, int64x2_t);
4972	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_u64)))
4973	void __arm_vstrdq_scatter_offset_u64(uint64_t *, uint64x2_t, uint64x2_t);
4974	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_u64)))
4975	void __arm_vstrdq_scatter_offset(uint64_t *, uint64x2_t, uint64x2_t);
4976	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_s64)))
4977	void __arm_vstrdq_scatter_shifted_offset_p_s64(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
4978	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_s64)))
4979	void __arm_vstrdq_scatter_shifted_offset_p(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
4980	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_u64)))
4981	void __arm_vstrdq_scatter_shifted_offset_p_u64(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
4982	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_u64)))
4983	void __arm_vstrdq_scatter_shifted_offset_p(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
4984	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_s64)))
4985	void __arm_vstrdq_scatter_shifted_offset_s64(int64_t *, uint64x2_t, int64x2_t);
4986	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_s64)))
4987	void __arm_vstrdq_scatter_shifted_offset(int64_t *, uint64x2_t, int64x2_t);
4988	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_u64)))
4989	void __arm_vstrdq_scatter_shifted_offset_u64(uint64_t *, uint64x2_t, uint64x2_t);
4990	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_u64)))
4991	void __arm_vstrdq_scatter_shifted_offset(uint64_t *, uint64x2_t, uint64x2_t);
4992	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s16)))
4993	void __arm_vstrhq_p_s16(int16_t *, int16x8_t, mve_pred16_t);
4994	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s16)))
4995	void __arm_vstrhq_p(int16_t *, int16x8_t, mve_pred16_t);
4996	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s32)))
4997	void __arm_vstrhq_p_s32(int16_t *, int32x4_t, mve_pred16_t);
4998	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s32)))
4999	void __arm_vstrhq_p(int16_t *, int32x4_t, mve_pred16_t);
5000	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u16)))
5001	void __arm_vstrhq_p_u16(uint16_t *, uint16x8_t, mve_pred16_t);
5002	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u16)))
5003	void __arm_vstrhq_p(uint16_t *, uint16x8_t, mve_pred16_t);
5004	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u32)))
5005	void __arm_vstrhq_p_u32(uint16_t *, uint32x4_t, mve_pred16_t);
5006	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u32)))
5007	void __arm_vstrhq_p(uint16_t *, uint32x4_t, mve_pred16_t);
5008	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s16)))
5009	void __arm_vstrhq_s16(int16_t *, int16x8_t);
5010	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s16)))
5011	void __arm_vstrhq(int16_t *, int16x8_t);
5012	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s32)))
5013	void __arm_vstrhq_s32(int16_t *, int32x4_t);
5014	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s32)))
5015	void __arm_vstrhq(int16_t *, int32x4_t);
5016	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s16)))
5017	void __arm_vstrhq_scatter_offset_p_s16(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
5018	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s16)))
5019	void __arm_vstrhq_scatter_offset_p(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
5020	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s32)))
5021	void __arm_vstrhq_scatter_offset_p_s32(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5022	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s32)))
5023	void __arm_vstrhq_scatter_offset_p(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5024	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u16)))
5025	void __arm_vstrhq_scatter_offset_p_u16(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
5026	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u16)))
5027	void __arm_vstrhq_scatter_offset_p(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
5028	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u32)))
5029	void __arm_vstrhq_scatter_offset_p_u32(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5030	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u32)))
5031	void __arm_vstrhq_scatter_offset_p(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5032	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s16)))
5033	void __arm_vstrhq_scatter_offset_s16(int16_t *, uint16x8_t, int16x8_t);
5034	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s16)))
5035	void __arm_vstrhq_scatter_offset(int16_t *, uint16x8_t, int16x8_t);
5036	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s32)))
5037	void __arm_vstrhq_scatter_offset_s32(int16_t *, uint32x4_t, int32x4_t);
5038	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s32)))
5039	void __arm_vstrhq_scatter_offset(int16_t *, uint32x4_t, int32x4_t);
5040	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u16)))
5041	void __arm_vstrhq_scatter_offset_u16(uint16_t *, uint16x8_t, uint16x8_t);
5042	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u16)))
5043	void __arm_vstrhq_scatter_offset(uint16_t *, uint16x8_t, uint16x8_t);
5044	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u32)))
5045	void __arm_vstrhq_scatter_offset_u32(uint16_t *, uint32x4_t, uint32x4_t);
5046	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u32)))
5047	void __arm_vstrhq_scatter_offset(uint16_t *, uint32x4_t, uint32x4_t);
5048	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s16)))
5049	void __arm_vstrhq_scatter_shifted_offset_p_s16(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
5050	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s16)))
5051	void __arm_vstrhq_scatter_shifted_offset_p(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
5052	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s32)))
5053	void __arm_vstrhq_scatter_shifted_offset_p_s32(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5054	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s32)))
5055	void __arm_vstrhq_scatter_shifted_offset_p(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5056	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u16)))
5057	void __arm_vstrhq_scatter_shifted_offset_p_u16(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
5058	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u16)))
5059	void __arm_vstrhq_scatter_shifted_offset_p(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
5060	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u32)))
5061	void __arm_vstrhq_scatter_shifted_offset_p_u32(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5062	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u32)))
5063	void __arm_vstrhq_scatter_shifted_offset_p(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5064	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s16)))
5065	void __arm_vstrhq_scatter_shifted_offset_s16(int16_t *, uint16x8_t, int16x8_t);
5066	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s16)))
5067	void __arm_vstrhq_scatter_shifted_offset(int16_t *, uint16x8_t, int16x8_t);
5068	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s32)))
5069	void __arm_vstrhq_scatter_shifted_offset_s32(int16_t *, uint32x4_t, int32x4_t);
5070	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s32)))
5071	void __arm_vstrhq_scatter_shifted_offset(int16_t *, uint32x4_t, int32x4_t);
5072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u16)))
5073	void __arm_vstrhq_scatter_shifted_offset_u16(uint16_t *, uint16x8_t, uint16x8_t);
5074	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u16)))
5075	void __arm_vstrhq_scatter_shifted_offset(uint16_t *, uint16x8_t, uint16x8_t);
5076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u32)))
5077	void __arm_vstrhq_scatter_shifted_offset_u32(uint16_t *, uint32x4_t, uint32x4_t);
5078	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u32)))
5079	void __arm_vstrhq_scatter_shifted_offset(uint16_t *, uint32x4_t, uint32x4_t);
5080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u16)))
5081	void __arm_vstrhq_u16(uint16_t *, uint16x8_t);
5082	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u16)))
5083	void __arm_vstrhq(uint16_t *, uint16x8_t);
5084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u32)))
5085	void __arm_vstrhq_u32(uint16_t *, uint32x4_t);
5086	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u32)))
5087	void __arm_vstrhq(uint16_t *, uint32x4_t);
5088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_s32)))
5089	void __arm_vstrwq_p_s32(int32_t *, int32x4_t, mve_pred16_t);
5090	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_s32)))
5091	void __arm_vstrwq_p(int32_t *, int32x4_t, mve_pred16_t);
5092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_u32)))
5093	void __arm_vstrwq_p_u32(uint32_t *, uint32x4_t, mve_pred16_t);
5094	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_u32)))
5095	void __arm_vstrwq_p(uint32_t *, uint32x4_t, mve_pred16_t);
5096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_s32)))
5097	void __arm_vstrwq_s32(int32_t *, int32x4_t);
5098	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_s32)))
5099	void __arm_vstrwq(int32_t *, int32x4_t);
5100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_s32)))
5101	void __arm_vstrwq_scatter_base_p_s32(uint32x4_t, int, int32x4_t, mve_pred16_t);
5102	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_s32)))
5103	void __arm_vstrwq_scatter_base_p(uint32x4_t, int, int32x4_t, mve_pred16_t);
5104	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_u32)))
5105	void __arm_vstrwq_scatter_base_p_u32(uint32x4_t, int, uint32x4_t, mve_pred16_t);
5106	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_u32)))
5107	void __arm_vstrwq_scatter_base_p(uint32x4_t, int, uint32x4_t, mve_pred16_t);
5108	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_s32)))
5109	void __arm_vstrwq_scatter_base_s32(uint32x4_t, int, int32x4_t);
5110	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_s32)))
5111	void __arm_vstrwq_scatter_base(uint32x4_t, int, int32x4_t);
5112	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_u32)))
5113	void __arm_vstrwq_scatter_base_u32(uint32x4_t, int, uint32x4_t);
5114	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_u32)))
5115	void __arm_vstrwq_scatter_base(uint32x4_t, int, uint32x4_t);
5116	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_s32)))
5117	void __arm_vstrwq_scatter_base_wb_p_s32(uint32x4_t *, int, int32x4_t, mve_pred16_t);
5118	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_s32)))
5119	void __arm_vstrwq_scatter_base_wb_p(uint32x4_t *, int, int32x4_t, mve_pred16_t);
5120	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_u32)))
5121	void __arm_vstrwq_scatter_base_wb_p_u32(uint32x4_t *, int, uint32x4_t, mve_pred16_t);
5122	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_u32)))
5123	void __arm_vstrwq_scatter_base_wb_p(uint32x4_t *, int, uint32x4_t, mve_pred16_t);
5124	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_s32)))
5125	void __arm_vstrwq_scatter_base_wb_s32(uint32x4_t *, int, int32x4_t);
5126	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_s32)))
5127	void __arm_vstrwq_scatter_base_wb(uint32x4_t *, int, int32x4_t);
5128	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_u32)))
5129	void __arm_vstrwq_scatter_base_wb_u32(uint32x4_t *, int, uint32x4_t);
5130	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_u32)))
5131	void __arm_vstrwq_scatter_base_wb(uint32x4_t *, int, uint32x4_t);
5132	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_s32)))
5133	void __arm_vstrwq_scatter_offset_p_s32(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5134	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_s32)))
5135	void __arm_vstrwq_scatter_offset_p(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5136	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_u32)))
5137	void __arm_vstrwq_scatter_offset_p_u32(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5138	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_u32)))
5139	void __arm_vstrwq_scatter_offset_p(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5140	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_s32)))
5141	void __arm_vstrwq_scatter_offset_s32(int32_t *, uint32x4_t, int32x4_t);
5142	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_s32)))
5143	void __arm_vstrwq_scatter_offset(int32_t *, uint32x4_t, int32x4_t);
5144	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_u32)))
5145	void __arm_vstrwq_scatter_offset_u32(uint32_t *, uint32x4_t, uint32x4_t);
5146	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_u32)))
5147	void __arm_vstrwq_scatter_offset(uint32_t *, uint32x4_t, uint32x4_t);
5148	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_s32)))
5149	void __arm_vstrwq_scatter_shifted_offset_p_s32(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5150	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_s32)))
5151	void __arm_vstrwq_scatter_shifted_offset_p(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
5152	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_u32)))
5153	void __arm_vstrwq_scatter_shifted_offset_p_u32(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5154	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_u32)))
5155	void __arm_vstrwq_scatter_shifted_offset_p(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
5156	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_s32)))
5157	void __arm_vstrwq_scatter_shifted_offset_s32(int32_t *, uint32x4_t, int32x4_t);
5158	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_s32)))
5159	void __arm_vstrwq_scatter_shifted_offset(int32_t *, uint32x4_t, int32x4_t);
5160	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_u32)))
5161	void __arm_vstrwq_scatter_shifted_offset_u32(uint32_t *, uint32x4_t, uint32x4_t);
5162	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_u32)))
5163	void __arm_vstrwq_scatter_shifted_offset(uint32_t *, uint32x4_t, uint32x4_t);
5164	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_u32)))
5165	void __arm_vstrwq_u32(uint32_t *, uint32x4_t);
5166	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_u32)))
5167	void __arm_vstrwq(uint32_t *, uint32x4_t);
5168	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s16)))
5169	int16x8_t __arm_vsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
5170	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s16)))
5171	int16x8_t __arm_vsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
5172	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s32)))
5173	int32x4_t __arm_vsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
5174	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s32)))
5175	int32x4_t __arm_vsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
5176	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s8)))
5177	int8x16_t __arm_vsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
5178	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s8)))
5179	int8x16_t __arm_vsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
5180	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u16)))
5181	uint16x8_t __arm_vsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
5182	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u16)))
5183	uint16x8_t __arm_vsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
5184	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u32)))
5185	uint32x4_t __arm_vsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
5186	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u32)))
5187	uint32x4_t __arm_vsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
5188	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u8)))
5189	uint8x16_t __arm_vsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
5190	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u8)))
5191	uint8x16_t __arm_vsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
5192	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s16)))
5193	int16x8_t __arm_vsubq_s16(int16x8_t, int16x8_t);
5194	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s16)))
5195	int16x8_t __arm_vsubq(int16x8_t, int16x8_t);
5196	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s32)))
5197	int32x4_t __arm_vsubq_s32(int32x4_t, int32x4_t);
5198	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s32)))
5199	int32x4_t __arm_vsubq(int32x4_t, int32x4_t);
5200	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s8)))
5201	int8x16_t __arm_vsubq_s8(int8x16_t, int8x16_t);
5202	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s8)))
5203	int8x16_t __arm_vsubq(int8x16_t, int8x16_t);
5204	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u16)))
5205	uint16x8_t __arm_vsubq_u16(uint16x8_t, uint16x8_t);
5206	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u16)))
5207	uint16x8_t __arm_vsubq(uint16x8_t, uint16x8_t);
5208	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u32)))
5209	uint32x4_t __arm_vsubq_u32(uint32x4_t, uint32x4_t);
5210	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u32)))
5211	uint32x4_t __arm_vsubq(uint32x4_t, uint32x4_t);
5212	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u8)))
5213	uint8x16_t __arm_vsubq_u8(uint8x16_t, uint8x16_t);
5214	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u8)))
5215	uint8x16_t __arm_vsubq(uint8x16_t, uint8x16_t);
5216	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s16)))
5217	int16x8_t __arm_vsubq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
5218	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s16)))
5219	int16x8_t __arm_vsubq_x(int16x8_t, int16x8_t, mve_pred16_t);
5220	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s32)))
5221	int32x4_t __arm_vsubq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
5222	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s32)))
5223	int32x4_t __arm_vsubq_x(int32x4_t, int32x4_t, mve_pred16_t);
5224	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s8)))
5225	int8x16_t __arm_vsubq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
5226	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s8)))
5227	int8x16_t __arm_vsubq_x(int8x16_t, int8x16_t, mve_pred16_t);
5228	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u16)))
5229	uint16x8_t __arm_vsubq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
5230	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u16)))
5231	uint16x8_t __arm_vsubq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
5232	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u32)))
5233	uint32x4_t __arm_vsubq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
5234	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u32)))
5235	uint32x4_t __arm_vsubq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
5236	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u8)))
5237	uint8x16_t __arm_vsubq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
5238	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u8)))
5239	uint8x16_t __arm_vsubq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
5240	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s16)))
5241	int16x8_t __arm_vuninitializedq(int16x8_t);
5242	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s32)))
5243	int32x4_t __arm_vuninitializedq(int32x4_t);
5244	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s64)))
5245	int64x2_t __arm_vuninitializedq(int64x2_t);
5246	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s8)))
5247	int8x16_t __arm_vuninitializedq(int8x16_t);
5248	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u16)))
5249	uint16x8_t __arm_vuninitializedq(uint16x8_t);
5250	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u32)))
5251	uint32x4_t __arm_vuninitializedq(uint32x4_t);
5252	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u64)))
5253	uint64x2_t __arm_vuninitializedq(uint64x2_t);
5254	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u8)))
5255	uint8x16_t __arm_vuninitializedq(uint8x16_t);
5256	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s16)))
5257	int16x8_t __arm_vuninitializedq_s16();
5258	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s32)))
5259	int32x4_t __arm_vuninitializedq_s32();
5260	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s64)))
5261	int64x2_t __arm_vuninitializedq_s64();
5262	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s8)))
5263	int8x16_t __arm_vuninitializedq_s8();
5264	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u16)))
5265	uint16x8_t __arm_vuninitializedq_u16();
5266	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u32)))
5267	uint32x4_t __arm_vuninitializedq_u32();
5268	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u64)))
5269	uint64x2_t __arm_vuninitializedq_u64();
5270	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u8)))
5271	uint8x16_t __arm_vuninitializedq_u8();
5272
5273	#if (__ARM_FEATURE_MVE & 2)
5274
5275	typedef __fp16 float16_t;
5276	typedef float float32_t;
5277	typedef __attribute__((neon_vector_type(8))) float16_t float16x8_t;
5278	typedef struct { float16x8_t val[2]; } float16x8x2_t;
5279	typedef struct { float16x8_t val[4]; } float16x8x4_t;
5280	typedef __attribute__((neon_vector_type(4))) float32_t float32x4_t;
5281	typedef struct { float32x4_t val[2]; } float32x4x2_t;
5282	typedef struct { float32x4_t val[4]; } float32x4x4_t;
5283
5284	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_f16)))
5285	float16x8_t __arm_vabdq_f16(float16x8_t, float16x8_t);
5286	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_f16)))
5287	float16x8_t __arm_vabdq(float16x8_t, float16x8_t);
5288	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_f32)))
5289	float32x4_t __arm_vabdq_f32(float32x4_t, float32x4_t);
5290	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_f32)))
5291	float32x4_t __arm_vabdq(float32x4_t, float32x4_t);
5292	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f16)))
5293	float16x8_t __arm_vabdq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5294	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f16)))
5295	float16x8_t __arm_vabdq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5296	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f32)))
5297	float32x4_t __arm_vabdq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5298	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f32)))
5299	float32x4_t __arm_vabdq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5300	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f16)))
5301	float16x8_t __arm_vabdq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5302	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f16)))
5303	float16x8_t __arm_vabdq_x(float16x8_t, float16x8_t, mve_pred16_t);
5304	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f32)))
5305	float32x4_t __arm_vabdq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5306	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f32)))
5307	float32x4_t __arm_vabdq_x(float32x4_t, float32x4_t, mve_pred16_t);
5308	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_f16)))
5309	float16x8_t __arm_vaddq_f16(float16x8_t, float16x8_t);
5310	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_f16)))
5311	float16x8_t __arm_vaddq(float16x8_t, float16x8_t);
5312	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_f32)))
5313	float32x4_t __arm_vaddq_f32(float32x4_t, float32x4_t);
5314	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_f32)))
5315	float32x4_t __arm_vaddq(float32x4_t, float32x4_t);
5316	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f16)))
5317	float16x8_t __arm_vaddq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5318	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f16)))
5319	float16x8_t __arm_vaddq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5320	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f32)))
5321	float32x4_t __arm_vaddq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5322	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f32)))
5323	float32x4_t __arm_vaddq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5324	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f16)))
5325	float16x8_t __arm_vaddq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5326	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f16)))
5327	float16x8_t __arm_vaddq_x(float16x8_t, float16x8_t, mve_pred16_t);
5328	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f32)))
5329	float32x4_t __arm_vaddq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5330	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f32)))
5331	float32x4_t __arm_vaddq_x(float32x4_t, float32x4_t, mve_pred16_t);
5332	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_f16)))
5333	float16x8_t __arm_vandq_f16(float16x8_t, float16x8_t);
5334	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_f16)))
5335	float16x8_t __arm_vandq(float16x8_t, float16x8_t);
5336	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_f32)))
5337	float32x4_t __arm_vandq_f32(float32x4_t, float32x4_t);
5338	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_f32)))
5339	float32x4_t __arm_vandq(float32x4_t, float32x4_t);
5340	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f16)))
5341	float16x8_t __arm_vandq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5342	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f16)))
5343	float16x8_t __arm_vandq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5344	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f32)))
5345	float32x4_t __arm_vandq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5346	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f32)))
5347	float32x4_t __arm_vandq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5348	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f16)))
5349	float16x8_t __arm_vandq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5350	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f16)))
5351	float16x8_t __arm_vandq_x(float16x8_t, float16x8_t, mve_pred16_t);
5352	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f32)))
5353	float32x4_t __arm_vandq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5354	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f32)))
5355	float32x4_t __arm_vandq_x(float32x4_t, float32x4_t, mve_pred16_t);
5356	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_f16)))
5357	float16x8_t __arm_vbicq_f16(float16x8_t, float16x8_t);
5358	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_f16)))
5359	float16x8_t __arm_vbicq(float16x8_t, float16x8_t);
5360	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_f32)))
5361	float32x4_t __arm_vbicq_f32(float32x4_t, float32x4_t);
5362	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_f32)))
5363	float32x4_t __arm_vbicq(float32x4_t, float32x4_t);
5364	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f16)))
5365	float16x8_t __arm_vbicq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5366	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f16)))
5367	float16x8_t __arm_vbicq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5368	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f32)))
5369	float32x4_t __arm_vbicq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5370	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f32)))
5371	float32x4_t __arm_vbicq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5372	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f16)))
5373	float16x8_t __arm_vbicq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5374	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f16)))
5375	float16x8_t __arm_vbicq_x(float16x8_t, float16x8_t, mve_pred16_t);
5376	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f32)))
5377	float32x4_t __arm_vbicq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5378	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f32)))
5379	float32x4_t __arm_vbicq_x(float32x4_t, float32x4_t, mve_pred16_t);
5380	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f16)))
5381	float16x8_t __arm_vcaddq_rot270_f16(float16x8_t, float16x8_t);
5382	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f16)))
5383	float16x8_t __arm_vcaddq_rot270(float16x8_t, float16x8_t);
5384	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f32)))
5385	float32x4_t __arm_vcaddq_rot270_f32(float32x4_t, float32x4_t);
5386	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f32)))
5387	float32x4_t __arm_vcaddq_rot270(float32x4_t, float32x4_t);
5388	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f16)))
5389	float16x8_t __arm_vcaddq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5390	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f16)))
5391	float16x8_t __arm_vcaddq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5392	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f32)))
5393	float32x4_t __arm_vcaddq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5394	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f32)))
5395	float32x4_t __arm_vcaddq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5396	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f16)))
5397	float16x8_t __arm_vcaddq_rot270_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5398	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f16)))
5399	float16x8_t __arm_vcaddq_rot270_x(float16x8_t, float16x8_t, mve_pred16_t);
5400	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f32)))
5401	float32x4_t __arm_vcaddq_rot270_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5402	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f32)))
5403	float32x4_t __arm_vcaddq_rot270_x(float32x4_t, float32x4_t, mve_pred16_t);
5404	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f16)))
5405	float16x8_t __arm_vcaddq_rot90_f16(float16x8_t, float16x8_t);
5406	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f16)))
5407	float16x8_t __arm_vcaddq_rot90(float16x8_t, float16x8_t);
5408	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f32)))
5409	float32x4_t __arm_vcaddq_rot90_f32(float32x4_t, float32x4_t);
5410	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f32)))
5411	float32x4_t __arm_vcaddq_rot90(float32x4_t, float32x4_t);
5412	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f16)))
5413	float16x8_t __arm_vcaddq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5414	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f16)))
5415	float16x8_t __arm_vcaddq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5416	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f32)))
5417	float32x4_t __arm_vcaddq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5418	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f32)))
5419	float32x4_t __arm_vcaddq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5420	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f16)))
5421	float16x8_t __arm_vcaddq_rot90_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5422	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f16)))
5423	float16x8_t __arm_vcaddq_rot90_x(float16x8_t, float16x8_t, mve_pred16_t);
5424	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f32)))
5425	float32x4_t __arm_vcaddq_rot90_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5426	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f32)))
5427	float32x4_t __arm_vcaddq_rot90_x(float32x4_t, float32x4_t, mve_pred16_t);
5428	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f16)))
5429	float16x8_t __arm_vcmlaq_f16(float16x8_t, float16x8_t, float16x8_t);
5430	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f16)))
5431	float16x8_t __arm_vcmlaq(float16x8_t, float16x8_t, float16x8_t);
5432	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f32)))
5433	float32x4_t __arm_vcmlaq_f32(float32x4_t, float32x4_t, float32x4_t);
5434	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f32)))
5435	float32x4_t __arm_vcmlaq(float32x4_t, float32x4_t, float32x4_t);
5436	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f16)))
5437	float16x8_t __arm_vcmlaq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5438	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f16)))
5439	float16x8_t __arm_vcmlaq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5440	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f32)))
5441	float32x4_t __arm_vcmlaq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5442	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f32)))
5443	float32x4_t __arm_vcmlaq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5444	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f16)))
5445	float16x8_t __arm_vcmlaq_rot180_f16(float16x8_t, float16x8_t, float16x8_t);
5446	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f16)))
5447	float16x8_t __arm_vcmlaq_rot180(float16x8_t, float16x8_t, float16x8_t);
5448	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f32)))
5449	float32x4_t __arm_vcmlaq_rot180_f32(float32x4_t, float32x4_t, float32x4_t);
5450	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f32)))
5451	float32x4_t __arm_vcmlaq_rot180(float32x4_t, float32x4_t, float32x4_t);
5452	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f16)))
5453	float16x8_t __arm_vcmlaq_rot180_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5454	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f16)))
5455	float16x8_t __arm_vcmlaq_rot180_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5456	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f32)))
5457	float32x4_t __arm_vcmlaq_rot180_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5458	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f32)))
5459	float32x4_t __arm_vcmlaq_rot180_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5460	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f16)))
5461	float16x8_t __arm_vcmlaq_rot270_f16(float16x8_t, float16x8_t, float16x8_t);
5462	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f16)))
5463	float16x8_t __arm_vcmlaq_rot270(float16x8_t, float16x8_t, float16x8_t);
5464	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f32)))
5465	float32x4_t __arm_vcmlaq_rot270_f32(float32x4_t, float32x4_t, float32x4_t);
5466	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f32)))
5467	float32x4_t __arm_vcmlaq_rot270(float32x4_t, float32x4_t, float32x4_t);
5468	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f16)))
5469	float16x8_t __arm_vcmlaq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5470	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f16)))
5471	float16x8_t __arm_vcmlaq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5472	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f32)))
5473	float32x4_t __arm_vcmlaq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5474	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f32)))
5475	float32x4_t __arm_vcmlaq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5476	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f16)))
5477	float16x8_t __arm_vcmlaq_rot90_f16(float16x8_t, float16x8_t, float16x8_t);
5478	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f16)))
5479	float16x8_t __arm_vcmlaq_rot90(float16x8_t, float16x8_t, float16x8_t);
5480	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f32)))
5481	float32x4_t __arm_vcmlaq_rot90_f32(float32x4_t, float32x4_t, float32x4_t);
5482	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f32)))
5483	float32x4_t __arm_vcmlaq_rot90(float32x4_t, float32x4_t, float32x4_t);
5484	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f16)))
5485	float16x8_t __arm_vcmlaq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5486	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f16)))
5487	float16x8_t __arm_vcmlaq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5488	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f32)))
5489	float32x4_t __arm_vcmlaq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5490	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f32)))
5491	float32x4_t __arm_vcmlaq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5492	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f16)))
5493	mve_pred16_t __arm_vcmpeqq_f16(float16x8_t, float16x8_t);
5494	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f16)))
5495	mve_pred16_t __arm_vcmpeqq(float16x8_t, float16x8_t);
5496	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f32)))
5497	mve_pred16_t __arm_vcmpeqq_f32(float32x4_t, float32x4_t);
5498	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f32)))
5499	mve_pred16_t __arm_vcmpeqq(float32x4_t, float32x4_t);
5500	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f16)))
5501	mve_pred16_t __arm_vcmpeqq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5502	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f16)))
5503	mve_pred16_t __arm_vcmpeqq_m(float16x8_t, float16x8_t, mve_pred16_t);
5504	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f32)))
5505	mve_pred16_t __arm_vcmpeqq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5506	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f32)))
5507	mve_pred16_t __arm_vcmpeqq_m(float32x4_t, float32x4_t, mve_pred16_t);
5508	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f16)))
5509	mve_pred16_t __arm_vcmpeqq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5510	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f16)))
5511	mve_pred16_t __arm_vcmpeqq_m(float16x8_t, float16_t, mve_pred16_t);
5512	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f32)))
5513	mve_pred16_t __arm_vcmpeqq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5514	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f32)))
5515	mve_pred16_t __arm_vcmpeqq_m(float32x4_t, float32_t, mve_pred16_t);
5516	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f16)))
5517	mve_pred16_t __arm_vcmpeqq_n_f16(float16x8_t, float16_t);
5518	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f16)))
5519	mve_pred16_t __arm_vcmpeqq(float16x8_t, float16_t);
5520	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f32)))
5521	mve_pred16_t __arm_vcmpeqq_n_f32(float32x4_t, float32_t);
5522	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f32)))
5523	mve_pred16_t __arm_vcmpeqq(float32x4_t, float32_t);
5524	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f16)))
5525	mve_pred16_t __arm_vcmpgeq_f16(float16x8_t, float16x8_t);
5526	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f16)))
5527	mve_pred16_t __arm_vcmpgeq(float16x8_t, float16x8_t);
5528	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f32)))
5529	mve_pred16_t __arm_vcmpgeq_f32(float32x4_t, float32x4_t);
5530	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f32)))
5531	mve_pred16_t __arm_vcmpgeq(float32x4_t, float32x4_t);
5532	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f16)))
5533	mve_pred16_t __arm_vcmpgeq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5534	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f16)))
5535	mve_pred16_t __arm_vcmpgeq_m(float16x8_t, float16x8_t, mve_pred16_t);
5536	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f32)))
5537	mve_pred16_t __arm_vcmpgeq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5538	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f32)))
5539	mve_pred16_t __arm_vcmpgeq_m(float32x4_t, float32x4_t, mve_pred16_t);
5540	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f16)))
5541	mve_pred16_t __arm_vcmpgeq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5542	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f16)))
5543	mve_pred16_t __arm_vcmpgeq_m(float16x8_t, float16_t, mve_pred16_t);
5544	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f32)))
5545	mve_pred16_t __arm_vcmpgeq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5546	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f32)))
5547	mve_pred16_t __arm_vcmpgeq_m(float32x4_t, float32_t, mve_pred16_t);
5548	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f16)))
5549	mve_pred16_t __arm_vcmpgeq_n_f16(float16x8_t, float16_t);
5550	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f16)))
5551	mve_pred16_t __arm_vcmpgeq(float16x8_t, float16_t);
5552	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f32)))
5553	mve_pred16_t __arm_vcmpgeq_n_f32(float32x4_t, float32_t);
5554	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f32)))
5555	mve_pred16_t __arm_vcmpgeq(float32x4_t, float32_t);
5556	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f16)))
5557	mve_pred16_t __arm_vcmpgtq_f16(float16x8_t, float16x8_t);
5558	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f16)))
5559	mve_pred16_t __arm_vcmpgtq(float16x8_t, float16x8_t);
5560	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f32)))
5561	mve_pred16_t __arm_vcmpgtq_f32(float32x4_t, float32x4_t);
5562	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f32)))
5563	mve_pred16_t __arm_vcmpgtq(float32x4_t, float32x4_t);
5564	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f16)))
5565	mve_pred16_t __arm_vcmpgtq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5566	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f16)))
5567	mve_pred16_t __arm_vcmpgtq_m(float16x8_t, float16x8_t, mve_pred16_t);
5568	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f32)))
5569	mve_pred16_t __arm_vcmpgtq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5570	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f32)))
5571	mve_pred16_t __arm_vcmpgtq_m(float32x4_t, float32x4_t, mve_pred16_t);
5572	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f16)))
5573	mve_pred16_t __arm_vcmpgtq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5574	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f16)))
5575	mve_pred16_t __arm_vcmpgtq_m(float16x8_t, float16_t, mve_pred16_t);
5576	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f32)))
5577	mve_pred16_t __arm_vcmpgtq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5578	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f32)))
5579	mve_pred16_t __arm_vcmpgtq_m(float32x4_t, float32_t, mve_pred16_t);
5580	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f16)))
5581	mve_pred16_t __arm_vcmpgtq_n_f16(float16x8_t, float16_t);
5582	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f16)))
5583	mve_pred16_t __arm_vcmpgtq(float16x8_t, float16_t);
5584	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f32)))
5585	mve_pred16_t __arm_vcmpgtq_n_f32(float32x4_t, float32_t);
5586	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f32)))
5587	mve_pred16_t __arm_vcmpgtq(float32x4_t, float32_t);
5588	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f16)))
5589	mve_pred16_t __arm_vcmpleq_f16(float16x8_t, float16x8_t);
5590	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f16)))
5591	mve_pred16_t __arm_vcmpleq(float16x8_t, float16x8_t);
5592	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f32)))
5593	mve_pred16_t __arm_vcmpleq_f32(float32x4_t, float32x4_t);
5594	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f32)))
5595	mve_pred16_t __arm_vcmpleq(float32x4_t, float32x4_t);
5596	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f16)))
5597	mve_pred16_t __arm_vcmpleq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5598	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f16)))
5599	mve_pred16_t __arm_vcmpleq_m(float16x8_t, float16x8_t, mve_pred16_t);
5600	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f32)))
5601	mve_pred16_t __arm_vcmpleq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5602	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f32)))
5603	mve_pred16_t __arm_vcmpleq_m(float32x4_t, float32x4_t, mve_pred16_t);
5604	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f16)))
5605	mve_pred16_t __arm_vcmpleq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5606	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f16)))
5607	mve_pred16_t __arm_vcmpleq_m(float16x8_t, float16_t, mve_pred16_t);
5608	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f32)))
5609	mve_pred16_t __arm_vcmpleq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5610	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f32)))
5611	mve_pred16_t __arm_vcmpleq_m(float32x4_t, float32_t, mve_pred16_t);
5612	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f16)))
5613	mve_pred16_t __arm_vcmpleq_n_f16(float16x8_t, float16_t);
5614	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f16)))
5615	mve_pred16_t __arm_vcmpleq(float16x8_t, float16_t);
5616	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f32)))
5617	mve_pred16_t __arm_vcmpleq_n_f32(float32x4_t, float32_t);
5618	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f32)))
5619	mve_pred16_t __arm_vcmpleq(float32x4_t, float32_t);
5620	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f16)))
5621	mve_pred16_t __arm_vcmpltq_f16(float16x8_t, float16x8_t);
5622	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f16)))
5623	mve_pred16_t __arm_vcmpltq(float16x8_t, float16x8_t);
5624	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f32)))
5625	mve_pred16_t __arm_vcmpltq_f32(float32x4_t, float32x4_t);
5626	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f32)))
5627	mve_pred16_t __arm_vcmpltq(float32x4_t, float32x4_t);
5628	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f16)))
5629	mve_pred16_t __arm_vcmpltq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5630	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f16)))
5631	mve_pred16_t __arm_vcmpltq_m(float16x8_t, float16x8_t, mve_pred16_t);
5632	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f32)))
5633	mve_pred16_t __arm_vcmpltq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5634	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f32)))
5635	mve_pred16_t __arm_vcmpltq_m(float32x4_t, float32x4_t, mve_pred16_t);
5636	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f16)))
5637	mve_pred16_t __arm_vcmpltq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5638	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f16)))
5639	mve_pred16_t __arm_vcmpltq_m(float16x8_t, float16_t, mve_pred16_t);
5640	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f32)))
5641	mve_pred16_t __arm_vcmpltq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5642	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f32)))
5643	mve_pred16_t __arm_vcmpltq_m(float32x4_t, float32_t, mve_pred16_t);
5644	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f16)))
5645	mve_pred16_t __arm_vcmpltq_n_f16(float16x8_t, float16_t);
5646	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f16)))
5647	mve_pred16_t __arm_vcmpltq(float16x8_t, float16_t);
5648	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f32)))
5649	mve_pred16_t __arm_vcmpltq_n_f32(float32x4_t, float32_t);
5650	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f32)))
5651	mve_pred16_t __arm_vcmpltq(float32x4_t, float32_t);
5652	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f16)))
5653	mve_pred16_t __arm_vcmpneq_f16(float16x8_t, float16x8_t);
5654	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f16)))
5655	mve_pred16_t __arm_vcmpneq(float16x8_t, float16x8_t);
5656	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f32)))
5657	mve_pred16_t __arm_vcmpneq_f32(float32x4_t, float32x4_t);
5658	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f32)))
5659	mve_pred16_t __arm_vcmpneq(float32x4_t, float32x4_t);
5660	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f16)))
5661	mve_pred16_t __arm_vcmpneq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
5662	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f16)))
5663	mve_pred16_t __arm_vcmpneq_m(float16x8_t, float16x8_t, mve_pred16_t);
5664	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f32)))
5665	mve_pred16_t __arm_vcmpneq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
5666	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f32)))
5667	mve_pred16_t __arm_vcmpneq_m(float32x4_t, float32x4_t, mve_pred16_t);
5668	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f16)))
5669	mve_pred16_t __arm_vcmpneq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
5670	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f16)))
5671	mve_pred16_t __arm_vcmpneq_m(float16x8_t, float16_t, mve_pred16_t);
5672	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f32)))
5673	mve_pred16_t __arm_vcmpneq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
5674	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f32)))
5675	mve_pred16_t __arm_vcmpneq_m(float32x4_t, float32_t, mve_pred16_t);
5676	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f16)))
5677	mve_pred16_t __arm_vcmpneq_n_f16(float16x8_t, float16_t);
5678	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f16)))
5679	mve_pred16_t __arm_vcmpneq(float16x8_t, float16_t);
5680	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f32)))
5681	mve_pred16_t __arm_vcmpneq_n_f32(float32x4_t, float32_t);
5682	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f32)))
5683	mve_pred16_t __arm_vcmpneq(float32x4_t, float32_t);
5684	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f16)))
5685	float16x8_t __arm_vcmulq_f16(float16x8_t, float16x8_t);
5686	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f16)))
5687	float16x8_t __arm_vcmulq(float16x8_t, float16x8_t);
5688	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f32)))
5689	float32x4_t __arm_vcmulq_f32(float32x4_t, float32x4_t);
5690	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f32)))
5691	float32x4_t __arm_vcmulq(float32x4_t, float32x4_t);
5692	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f16)))
5693	float16x8_t __arm_vcmulq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5694	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f16)))
5695	float16x8_t __arm_vcmulq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5696	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f32)))
5697	float32x4_t __arm_vcmulq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5698	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f32)))
5699	float32x4_t __arm_vcmulq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5700	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f16)))
5701	float16x8_t __arm_vcmulq_rot180_f16(float16x8_t, float16x8_t);
5702	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f16)))
5703	float16x8_t __arm_vcmulq_rot180(float16x8_t, float16x8_t);
5704	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f32)))
5705	float32x4_t __arm_vcmulq_rot180_f32(float32x4_t, float32x4_t);
5706	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f32)))
5707	float32x4_t __arm_vcmulq_rot180(float32x4_t, float32x4_t);
5708	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f16)))
5709	float16x8_t __arm_vcmulq_rot180_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5710	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f16)))
5711	float16x8_t __arm_vcmulq_rot180_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5712	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f32)))
5713	float32x4_t __arm_vcmulq_rot180_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5714	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f32)))
5715	float32x4_t __arm_vcmulq_rot180_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5716	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f16)))
5717	float16x8_t __arm_vcmulq_rot180_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5718	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f16)))
5719	float16x8_t __arm_vcmulq_rot180_x(float16x8_t, float16x8_t, mve_pred16_t);
5720	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f32)))
5721	float32x4_t __arm_vcmulq_rot180_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5722	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f32)))
5723	float32x4_t __arm_vcmulq_rot180_x(float32x4_t, float32x4_t, mve_pred16_t);
5724	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f16)))
5725	float16x8_t __arm_vcmulq_rot270_f16(float16x8_t, float16x8_t);
5726	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f16)))
5727	float16x8_t __arm_vcmulq_rot270(float16x8_t, float16x8_t);
5728	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f32)))
5729	float32x4_t __arm_vcmulq_rot270_f32(float32x4_t, float32x4_t);
5730	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f32)))
5731	float32x4_t __arm_vcmulq_rot270(float32x4_t, float32x4_t);
5732	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f16)))
5733	float16x8_t __arm_vcmulq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5734	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f16)))
5735	float16x8_t __arm_vcmulq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5736	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f32)))
5737	float32x4_t __arm_vcmulq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5738	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f32)))
5739	float32x4_t __arm_vcmulq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5740	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f16)))
5741	float16x8_t __arm_vcmulq_rot270_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5742	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f16)))
5743	float16x8_t __arm_vcmulq_rot270_x(float16x8_t, float16x8_t, mve_pred16_t);
5744	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f32)))
5745	float32x4_t __arm_vcmulq_rot270_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5746	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f32)))
5747	float32x4_t __arm_vcmulq_rot270_x(float32x4_t, float32x4_t, mve_pred16_t);
5748	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f16)))
5749	float16x8_t __arm_vcmulq_rot90_f16(float16x8_t, float16x8_t);
5750	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f16)))
5751	float16x8_t __arm_vcmulq_rot90(float16x8_t, float16x8_t);
5752	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f32)))
5753	float32x4_t __arm_vcmulq_rot90_f32(float32x4_t, float32x4_t);
5754	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f32)))
5755	float32x4_t __arm_vcmulq_rot90(float32x4_t, float32x4_t);
5756	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f16)))
5757	float16x8_t __arm_vcmulq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5758	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f16)))
5759	float16x8_t __arm_vcmulq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5760	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f32)))
5761	float32x4_t __arm_vcmulq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5762	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f32)))
5763	float32x4_t __arm_vcmulq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5764	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f16)))
5765	float16x8_t __arm_vcmulq_rot90_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5766	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f16)))
5767	float16x8_t __arm_vcmulq_rot90_x(float16x8_t, float16x8_t, mve_pred16_t);
5768	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f32)))
5769	float32x4_t __arm_vcmulq_rot90_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5770	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f32)))
5771	float32x4_t __arm_vcmulq_rot90_x(float32x4_t, float32x4_t, mve_pred16_t);
5772	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f16)))
5773	float16x8_t __arm_vcmulq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5774	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f16)))
5775	float16x8_t __arm_vcmulq_x(float16x8_t, float16x8_t, mve_pred16_t);
5776	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f32)))
5777	float32x4_t __arm_vcmulq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5778	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f32)))
5779	float32x4_t __arm_vcmulq_x(float32x4_t, float32x4_t, mve_pred16_t);
5780	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_f16)))
5781	float16x8_t __arm_vcreateq_f16(uint64_t, uint64_t);
5782	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_f32)))
5783	float32x4_t __arm_vcreateq_f32(uint64_t, uint64_t);
5784	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvtbq_f16_f32)))
5785	float16x8_t __arm_vcvtbq_f16_f32(float16x8_t, float32x4_t);
5786	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvtbq_m_f16_f32)))
5787	float16x8_t __arm_vcvtbq_m_f16_f32(float16x8_t, float32x4_t, mve_pred16_t);
5788	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvttq_f16_f32)))
5789	float16x8_t __arm_vcvttq_f16_f32(float16x8_t, float32x4_t);
5790	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvttq_m_f16_f32)))
5791	float16x8_t __arm_vcvttq_m_f16_f32(float16x8_t, float32x4_t, mve_pred16_t);
5792	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_f16)))
5793	float16x8_t __arm_veorq_f16(float16x8_t, float16x8_t);
5794	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_f16)))
5795	float16x8_t __arm_veorq(float16x8_t, float16x8_t);
5796	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_f32)))
5797	float32x4_t __arm_veorq_f32(float32x4_t, float32x4_t);
5798	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_f32)))
5799	float32x4_t __arm_veorq(float32x4_t, float32x4_t);
5800	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f16)))
5801	float16x8_t __arm_veorq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5802	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f16)))
5803	float16x8_t __arm_veorq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5804	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f32)))
5805	float32x4_t __arm_veorq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5806	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f32)))
5807	float32x4_t __arm_veorq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5808	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f16)))
5809	float16x8_t __arm_veorq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5810	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f16)))
5811	float16x8_t __arm_veorq_x(float16x8_t, float16x8_t, mve_pred16_t);
5812	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f32)))
5813	float32x4_t __arm_veorq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5814	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f32)))
5815	float32x4_t __arm_veorq_x(float32x4_t, float32x4_t, mve_pred16_t);
5816	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f16)))
5817	float16_t __arm_vgetq_lane_f16(float16x8_t, int);
5818	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f16)))
5819	float16_t __arm_vgetq_lane(float16x8_t, int);
5820	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f32)))
5821	float32_t __arm_vgetq_lane_f32(float32x4_t, int);
5822	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f32)))
5823	float32_t __arm_vgetq_lane(float32x4_t, int);
5824	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_f16)))
5825	float16x8_t __arm_vld1q_f16(const float16_t *);
5826	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_f16)))
5827	float16x8_t __arm_vld1q(const float16_t *);
5828	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_f32)))
5829	float32x4_t __arm_vld1q_f32(const float32_t *);
5830	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_f32)))
5831	float32x4_t __arm_vld1q(const float32_t *);
5832	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f16)))
5833	float16x8_t __arm_vld1q_z_f16(const float16_t *, mve_pred16_t);
5834	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f16)))
5835	float16x8_t __arm_vld1q_z(const float16_t *, mve_pred16_t);
5836	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f32)))
5837	float32x4_t __arm_vld1q_z_f32(const float32_t *, mve_pred16_t);
5838	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f32)))
5839	float32x4_t __arm_vld1q_z(const float32_t *, mve_pred16_t);
5840	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_f16)))
5841	float16x8x2_t __arm_vld2q_f16(const float16_t *);
5842	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_f16)))
5843	float16x8x2_t __arm_vld2q(const float16_t *);
5844	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_f32)))
5845	float32x4x2_t __arm_vld2q_f32(const float32_t *);
5846	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_f32)))
5847	float32x4x2_t __arm_vld2q(const float32_t *);
5848	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_f16)))
5849	float16x8x4_t __arm_vld4q_f16(const float16_t *);
5850	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_f16)))
5851	float16x8x4_t __arm_vld4q(const float16_t *);
5852	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_f32)))
5853	float32x4x4_t __arm_vld4q_f32(const float32_t *);
5854	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_f32)))
5855	float32x4x4_t __arm_vld4q(const float32_t *);
5856	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_f16)))
5857	float16x8_t __arm_vldrhq_f16(const float16_t *);
5858	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_f16)))
5859	float16x8_t __arm_vldrhq_gather_offset_f16(const float16_t *, uint16x8_t);
5860	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_f16)))
5861	float16x8_t __arm_vldrhq_gather_offset(const float16_t *, uint16x8_t);
5862	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_f16)))
5863	float16x8_t __arm_vldrhq_gather_offset_z_f16(const float16_t *, uint16x8_t, mve_pred16_t);
5864	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_f16)))
5865	float16x8_t __arm_vldrhq_gather_offset_z(const float16_t *, uint16x8_t, mve_pred16_t);
5866	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_f16)))
5867	float16x8_t __arm_vldrhq_gather_shifted_offset_f16(const float16_t *, uint16x8_t);
5868	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_f16)))
5869	float16x8_t __arm_vldrhq_gather_shifted_offset(const float16_t *, uint16x8_t);
5870	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_f16)))
5871	float16x8_t __arm_vldrhq_gather_shifted_offset_z_f16(const float16_t *, uint16x8_t, mve_pred16_t);
5872	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_f16)))
5873	float16x8_t __arm_vldrhq_gather_shifted_offset_z(const float16_t *, uint16x8_t, mve_pred16_t);
5874	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_f16)))
5875	float16x8_t __arm_vldrhq_z_f16(const float16_t *, mve_pred16_t);
5876	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_f32)))
5877	float32x4_t __arm_vldrwq_f32(const float32_t *);
5878	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_f32)))
5879	float32x4_t __arm_vldrwq_gather_base_f32(uint32x4_t, int);
5880	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_f32)))
5881	float32x4_t __arm_vldrwq_gather_base_wb_f32(uint32x4_t *, int);
5882	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_f32)))
5883	float32x4_t __arm_vldrwq_gather_base_wb_z_f32(uint32x4_t *, int, mve_pred16_t);
5884	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_f32)))
5885	float32x4_t __arm_vldrwq_gather_base_z_f32(uint32x4_t, int, mve_pred16_t);
5886	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_f32)))
5887	float32x4_t __arm_vldrwq_gather_offset_f32(const float32_t *, uint32x4_t);
5888	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_f32)))
5889	float32x4_t __arm_vldrwq_gather_offset(const float32_t *, uint32x4_t);
5890	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_f32)))
5891	float32x4_t __arm_vldrwq_gather_offset_z_f32(const float32_t *, uint32x4_t, mve_pred16_t);
5892	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_f32)))
5893	float32x4_t __arm_vldrwq_gather_offset_z(const float32_t *, uint32x4_t, mve_pred16_t);
5894	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_f32)))
5895	float32x4_t __arm_vldrwq_gather_shifted_offset_f32(const float32_t *, uint32x4_t);
5896	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_f32)))
5897	float32x4_t __arm_vldrwq_gather_shifted_offset(const float32_t *, uint32x4_t);
5898	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_f32)))
5899	float32x4_t __arm_vldrwq_gather_shifted_offset_z_f32(const float32_t *, uint32x4_t, mve_pred16_t);
5900	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_f32)))
5901	float32x4_t __arm_vldrwq_gather_shifted_offset_z(const float32_t *, uint32x4_t, mve_pred16_t);
5902	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_f32)))
5903	float32x4_t __arm_vldrwq_z_f32(const float32_t *, mve_pred16_t);
5904	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f16)))
5905	float16x8_t __arm_vmaxnmq_f16(float16x8_t, float16x8_t);
5906	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f16)))
5907	float16x8_t __arm_vmaxnmq(float16x8_t, float16x8_t);
5908	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f32)))
5909	float32x4_t __arm_vmaxnmq_f32(float32x4_t, float32x4_t);
5910	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f32)))
5911	float32x4_t __arm_vmaxnmq(float32x4_t, float32x4_t);
5912	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f16)))
5913	float16x8_t __arm_vmaxnmq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5914	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f16)))
5915	float16x8_t __arm_vmaxnmq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5916	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f32)))
5917	float32x4_t __arm_vmaxnmq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5918	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f32)))
5919	float32x4_t __arm_vmaxnmq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5920	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f16)))
5921	float16x8_t __arm_vmaxnmq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5922	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f16)))
5923	float16x8_t __arm_vmaxnmq_x(float16x8_t, float16x8_t, mve_pred16_t);
5924	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f32)))
5925	float32x4_t __arm_vmaxnmq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5926	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f32)))
5927	float32x4_t __arm_vmaxnmq_x(float32x4_t, float32x4_t, mve_pred16_t);
5928	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f16)))
5929	float16x8_t __arm_vminnmq_f16(float16x8_t, float16x8_t);
5930	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f16)))
5931	float16x8_t __arm_vminnmq(float16x8_t, float16x8_t);
5932	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f32)))
5933	float32x4_t __arm_vminnmq_f32(float32x4_t, float32x4_t);
5934	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f32)))
5935	float32x4_t __arm_vminnmq(float32x4_t, float32x4_t);
5936	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f16)))
5937	float16x8_t __arm_vminnmq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5938	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f16)))
5939	float16x8_t __arm_vminnmq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5940	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f32)))
5941	float32x4_t __arm_vminnmq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5942	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f32)))
5943	float32x4_t __arm_vminnmq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5944	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f16)))
5945	float16x8_t __arm_vminnmq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5946	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f16)))
5947	float16x8_t __arm_vminnmq_x(float16x8_t, float16x8_t, mve_pred16_t);
5948	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f32)))
5949	float32x4_t __arm_vminnmq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5950	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f32)))
5951	float32x4_t __arm_vminnmq_x(float32x4_t, float32x4_t, mve_pred16_t);
5952	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_f16)))
5953	float16x8_t __arm_vmulq_f16(float16x8_t, float16x8_t);
5954	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_f16)))
5955	float16x8_t __arm_vmulq(float16x8_t, float16x8_t);
5956	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_f32)))
5957	float32x4_t __arm_vmulq_f32(float32x4_t, float32x4_t);
5958	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_f32)))
5959	float32x4_t __arm_vmulq(float32x4_t, float32x4_t);
5960	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f16)))
5961	float16x8_t __arm_vmulq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5962	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f16)))
5963	float16x8_t __arm_vmulq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5964	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f32)))
5965	float32x4_t __arm_vmulq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5966	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f32)))
5967	float32x4_t __arm_vmulq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5968	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f16)))
5969	float16x8_t __arm_vmulq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5970	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f16)))
5971	float16x8_t __arm_vmulq_x(float16x8_t, float16x8_t, mve_pred16_t);
5972	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f32)))
5973	float32x4_t __arm_vmulq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5974	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f32)))
5975	float32x4_t __arm_vmulq_x(float32x4_t, float32x4_t, mve_pred16_t);
5976	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_f16)))
5977	float16x8_t __arm_vornq_f16(float16x8_t, float16x8_t);
5978	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_f16)))
5979	float16x8_t __arm_vornq(float16x8_t, float16x8_t);
5980	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_f32)))
5981	float32x4_t __arm_vornq_f32(float32x4_t, float32x4_t);
5982	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_f32)))
5983	float32x4_t __arm_vornq(float32x4_t, float32x4_t);
5984	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f16)))
5985	float16x8_t __arm_vornq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5986	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f16)))
5987	float16x8_t __arm_vornq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
5988	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f32)))
5989	float32x4_t __arm_vornq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5990	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f32)))
5991	float32x4_t __arm_vornq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
5992	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f16)))
5993	float16x8_t __arm_vornq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
5994	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f16)))
5995	float16x8_t __arm_vornq_x(float16x8_t, float16x8_t, mve_pred16_t);
5996	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f32)))
5997	float32x4_t __arm_vornq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
5998	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f32)))
5999	float32x4_t __arm_vornq_x(float32x4_t, float32x4_t, mve_pred16_t);
6000	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_f16)))
6001	float16x8_t __arm_vorrq_f16(float16x8_t, float16x8_t);
6002	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_f16)))
6003	float16x8_t __arm_vorrq(float16x8_t, float16x8_t);
6004	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_f32)))
6005	float32x4_t __arm_vorrq_f32(float32x4_t, float32x4_t);
6006	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_f32)))
6007	float32x4_t __arm_vorrq(float32x4_t, float32x4_t);
6008	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f16)))
6009	float16x8_t __arm_vorrq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
6010	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f16)))
6011	float16x8_t __arm_vorrq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
6012	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f32)))
6013	float32x4_t __arm_vorrq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
6014	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f32)))
6015	float32x4_t __arm_vorrq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
6016	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f16)))
6017	float16x8_t __arm_vorrq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
6018	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f16)))
6019	float16x8_t __arm_vorrq_x(float16x8_t, float16x8_t, mve_pred16_t);
6020	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f32)))
6021	float32x4_t __arm_vorrq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
6022	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f32)))
6023	float32x4_t __arm_vorrq_x(float32x4_t, float32x4_t, mve_pred16_t);
6024	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_f16)))
6025	float16x8_t __arm_vpselq_f16(float16x8_t, float16x8_t, mve_pred16_t);
6026	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_f16)))
6027	float16x8_t __arm_vpselq(float16x8_t, float16x8_t, mve_pred16_t);
6028	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_f32)))
6029	float32x4_t __arm_vpselq_f32(float32x4_t, float32x4_t, mve_pred16_t);
6030	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_f32)))
6031	float32x4_t __arm_vpselq(float32x4_t, float32x4_t, mve_pred16_t);
6032	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_f32)))
6033	float16x8_t __arm_vreinterpretq_f16_f32(float32x4_t);
6034	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_f32)))
6035	float16x8_t __arm_vreinterpretq_f16(float32x4_t);
6036	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s16)))
6037	float16x8_t __arm_vreinterpretq_f16_s16(int16x8_t);
6038	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s16)))
6039	float16x8_t __arm_vreinterpretq_f16(int16x8_t);
6040	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s32)))
6041	float16x8_t __arm_vreinterpretq_f16_s32(int32x4_t);
6042	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s32)))
6043	float16x8_t __arm_vreinterpretq_f16(int32x4_t);
6044	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s64)))
6045	float16x8_t __arm_vreinterpretq_f16_s64(int64x2_t);
6046	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s64)))
6047	float16x8_t __arm_vreinterpretq_f16(int64x2_t);
6048	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s8)))
6049	float16x8_t __arm_vreinterpretq_f16_s8(int8x16_t);
6050	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s8)))
6051	float16x8_t __arm_vreinterpretq_f16(int8x16_t);
6052	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u16)))
6053	float16x8_t __arm_vreinterpretq_f16_u16(uint16x8_t);
6054	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u16)))
6055	float16x8_t __arm_vreinterpretq_f16(uint16x8_t);
6056	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u32)))
6057	float16x8_t __arm_vreinterpretq_f16_u32(uint32x4_t);
6058	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u32)))
6059	float16x8_t __arm_vreinterpretq_f16(uint32x4_t);
6060	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u64)))
6061	float16x8_t __arm_vreinterpretq_f16_u64(uint64x2_t);
6062	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u64)))
6063	float16x8_t __arm_vreinterpretq_f16(uint64x2_t);
6064	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u8)))
6065	float16x8_t __arm_vreinterpretq_f16_u8(uint8x16_t);
6066	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u8)))
6067	float16x8_t __arm_vreinterpretq_f16(uint8x16_t);
6068	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_f16)))
6069	float32x4_t __arm_vreinterpretq_f32_f16(float16x8_t);
6070	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_f16)))
6071	float32x4_t __arm_vreinterpretq_f32(float16x8_t);
6072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s16)))
6073	float32x4_t __arm_vreinterpretq_f32_s16(int16x8_t);
6074	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s16)))
6075	float32x4_t __arm_vreinterpretq_f32(int16x8_t);
6076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s32)))
6077	float32x4_t __arm_vreinterpretq_f32_s32(int32x4_t);
6078	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s32)))
6079	float32x4_t __arm_vreinterpretq_f32(int32x4_t);
6080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s64)))
6081	float32x4_t __arm_vreinterpretq_f32_s64(int64x2_t);
6082	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s64)))
6083	float32x4_t __arm_vreinterpretq_f32(int64x2_t);
6084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s8)))
6085	float32x4_t __arm_vreinterpretq_f32_s8(int8x16_t);
6086	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s8)))
6087	float32x4_t __arm_vreinterpretq_f32(int8x16_t);
6088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u16)))
6089	float32x4_t __arm_vreinterpretq_f32_u16(uint16x8_t);
6090	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u16)))
6091	float32x4_t __arm_vreinterpretq_f32(uint16x8_t);
6092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u32)))
6093	float32x4_t __arm_vreinterpretq_f32_u32(uint32x4_t);
6094	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u32)))
6095	float32x4_t __arm_vreinterpretq_f32(uint32x4_t);
6096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u64)))
6097	float32x4_t __arm_vreinterpretq_f32_u64(uint64x2_t);
6098	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u64)))
6099	float32x4_t __arm_vreinterpretq_f32(uint64x2_t);
6100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u8)))
6101	float32x4_t __arm_vreinterpretq_f32_u8(uint8x16_t);
6102	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u8)))
6103	float32x4_t __arm_vreinterpretq_f32(uint8x16_t);
6104	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f16)))
6105	int16x8_t __arm_vreinterpretq_s16_f16(float16x8_t);
6106	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f16)))
6107	int16x8_t __arm_vreinterpretq_s16(float16x8_t);
6108	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f32)))
6109	int16x8_t __arm_vreinterpretq_s16_f32(float32x4_t);
6110	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f32)))
6111	int16x8_t __arm_vreinterpretq_s16(float32x4_t);
6112	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f16)))
6113	int32x4_t __arm_vreinterpretq_s32_f16(float16x8_t);
6114	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f16)))
6115	int32x4_t __arm_vreinterpretq_s32(float16x8_t);
6116	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f32)))
6117	int32x4_t __arm_vreinterpretq_s32_f32(float32x4_t);
6118	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f32)))
6119	int32x4_t __arm_vreinterpretq_s32(float32x4_t);
6120	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f16)))
6121	int64x2_t __arm_vreinterpretq_s64_f16(float16x8_t);
6122	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f16)))
6123	int64x2_t __arm_vreinterpretq_s64(float16x8_t);
6124	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f32)))
6125	int64x2_t __arm_vreinterpretq_s64_f32(float32x4_t);
6126	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f32)))
6127	int64x2_t __arm_vreinterpretq_s64(float32x4_t);
6128	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f16)))
6129	int8x16_t __arm_vreinterpretq_s8_f16(float16x8_t);
6130	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f16)))
6131	int8x16_t __arm_vreinterpretq_s8(float16x8_t);
6132	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f32)))
6133	int8x16_t __arm_vreinterpretq_s8_f32(float32x4_t);
6134	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f32)))
6135	int8x16_t __arm_vreinterpretq_s8(float32x4_t);
6136	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f16)))
6137	uint16x8_t __arm_vreinterpretq_u16_f16(float16x8_t);
6138	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f16)))
6139	uint16x8_t __arm_vreinterpretq_u16(float16x8_t);
6140	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f32)))
6141	uint16x8_t __arm_vreinterpretq_u16_f32(float32x4_t);
6142	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f32)))
6143	uint16x8_t __arm_vreinterpretq_u16(float32x4_t);
6144	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f16)))
6145	uint32x4_t __arm_vreinterpretq_u32_f16(float16x8_t);
6146	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f16)))
6147	uint32x4_t __arm_vreinterpretq_u32(float16x8_t);
6148	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f32)))
6149	uint32x4_t __arm_vreinterpretq_u32_f32(float32x4_t);
6150	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f32)))
6151	uint32x4_t __arm_vreinterpretq_u32(float32x4_t);
6152	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f16)))
6153	uint64x2_t __arm_vreinterpretq_u64_f16(float16x8_t);
6154	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f16)))
6155	uint64x2_t __arm_vreinterpretq_u64(float16x8_t);
6156	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f32)))
6157	uint64x2_t __arm_vreinterpretq_u64_f32(float32x4_t);
6158	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f32)))
6159	uint64x2_t __arm_vreinterpretq_u64(float32x4_t);
6160	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f16)))
6161	uint8x16_t __arm_vreinterpretq_u8_f16(float16x8_t);
6162	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f16)))
6163	uint8x16_t __arm_vreinterpretq_u8(float16x8_t);
6164	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f32)))
6165	uint8x16_t __arm_vreinterpretq_u8_f32(float32x4_t);
6166	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f32)))
6167	uint8x16_t __arm_vreinterpretq_u8(float32x4_t);
6168	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f16)))
6169	float16x8_t __arm_vsetq_lane_f16(float16_t, float16x8_t, int);
6170	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f16)))
6171	float16x8_t __arm_vsetq_lane(float16_t, float16x8_t, int);
6172	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f32)))
6173	float32x4_t __arm_vsetq_lane_f32(float32_t, float32x4_t, int);
6174	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f32)))
6175	float32x4_t __arm_vsetq_lane(float32_t, float32x4_t, int);
6176	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_f16)))
6177	void __arm_vst1q_f16(float16_t *, float16x8_t);
6178	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_f16)))
6179	void __arm_vst1q(float16_t *, float16x8_t);
6180	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_f32)))
6181	void __arm_vst1q_f32(float32_t *, float32x4_t);
6182	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_f32)))
6183	void __arm_vst1q(float32_t *, float32x4_t);
6184	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f16)))
6185	void __arm_vst1q_p_f16(float16_t *, float16x8_t, mve_pred16_t);
6186	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f16)))
6187	void __arm_vst1q_p(float16_t *, float16x8_t, mve_pred16_t);
6188	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f32)))
6189	void __arm_vst1q_p_f32(float32_t *, float32x4_t, mve_pred16_t);
6190	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f32)))
6191	void __arm_vst1q_p(float32_t *, float32x4_t, mve_pred16_t);
6192	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_f16)))
6193	void __arm_vst2q_f16(float16_t *, float16x8x2_t);
6194	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_f16)))
6195	void __arm_vst2q(float16_t *, float16x8x2_t);
6196	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_f32)))
6197	void __arm_vst2q_f32(float32_t *, float32x4x2_t);
6198	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_f32)))
6199	void __arm_vst2q(float32_t *, float32x4x2_t);
6200	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_f16)))
6201	void __arm_vst4q_f16(float16_t *, float16x8x4_t);
6202	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_f16)))
6203	void __arm_vst4q(float16_t *, float16x8x4_t);
6204	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_f32)))
6205	void __arm_vst4q_f32(float32_t *, float32x4x4_t);
6206	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_f32)))
6207	void __arm_vst4q(float32_t *, float32x4x4_t);
6208	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_f16)))
6209	void __arm_vstrhq_f16(float16_t *, float16x8_t);
6210	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_f16)))
6211	void __arm_vstrhq(float16_t *, float16x8_t);
6212	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_f16)))
6213	void __arm_vstrhq_p_f16(float16_t *, float16x8_t, mve_pred16_t);
6214	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_f16)))
6215	void __arm_vstrhq_p(float16_t *, float16x8_t, mve_pred16_t);
6216	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_f16)))
6217	void __arm_vstrhq_scatter_offset_f16(float16_t *, uint16x8_t, float16x8_t);
6218	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_f16)))
6219	void __arm_vstrhq_scatter_offset(float16_t *, uint16x8_t, float16x8_t);
6220	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_f16)))
6221	void __arm_vstrhq_scatter_offset_p_f16(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
6222	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_f16)))
6223	void __arm_vstrhq_scatter_offset_p(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
6224	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_f16)))
6225	void __arm_vstrhq_scatter_shifted_offset_f16(float16_t *, uint16x8_t, float16x8_t);
6226	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_f16)))
6227	void __arm_vstrhq_scatter_shifted_offset(float16_t *, uint16x8_t, float16x8_t);
6228	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_f16)))
6229	void __arm_vstrhq_scatter_shifted_offset_p_f16(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
6230	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_f16)))
6231	void __arm_vstrhq_scatter_shifted_offset_p(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
6232	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_f32)))
6233	void __arm_vstrwq_f32(float32_t *, float32x4_t);
6234	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_f32)))
6235	void __arm_vstrwq(float32_t *, float32x4_t);
6236	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_f32)))
6237	void __arm_vstrwq_p_f32(float32_t *, float32x4_t, mve_pred16_t);
6238	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_f32)))
6239	void __arm_vstrwq_p(float32_t *, float32x4_t, mve_pred16_t);
6240	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_f32)))
6241	void __arm_vstrwq_scatter_base_f32(uint32x4_t, int, float32x4_t);
6242	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_f32)))
6243	void __arm_vstrwq_scatter_base(uint32x4_t, int, float32x4_t);
6244	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_f32)))
6245	void __arm_vstrwq_scatter_base_p_f32(uint32x4_t, int, float32x4_t, mve_pred16_t);
6246	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_f32)))
6247	void __arm_vstrwq_scatter_base_p(uint32x4_t, int, float32x4_t, mve_pred16_t);
6248	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_f32)))
6249	void __arm_vstrwq_scatter_base_wb_f32(uint32x4_t *, int, float32x4_t);
6250	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_f32)))
6251	void __arm_vstrwq_scatter_base_wb(uint32x4_t *, int, float32x4_t);
6252	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_f32)))
6253	void __arm_vstrwq_scatter_base_wb_p_f32(uint32x4_t *, int, float32x4_t, mve_pred16_t);
6254	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_f32)))
6255	void __arm_vstrwq_scatter_base_wb_p(uint32x4_t *, int, float32x4_t, mve_pred16_t);
6256	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_f32)))
6257	void __arm_vstrwq_scatter_offset_f32(float32_t *, uint32x4_t, float32x4_t);
6258	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_f32)))
6259	void __arm_vstrwq_scatter_offset(float32_t *, uint32x4_t, float32x4_t);
6260	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_f32)))
6261	void __arm_vstrwq_scatter_offset_p_f32(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
6262	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_f32)))
6263	void __arm_vstrwq_scatter_offset_p(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
6264	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_f32)))
6265	void __arm_vstrwq_scatter_shifted_offset_f32(float32_t *, uint32x4_t, float32x4_t);
6266	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_f32)))
6267	void __arm_vstrwq_scatter_shifted_offset(float32_t *, uint32x4_t, float32x4_t);
6268	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_f32)))
6269	void __arm_vstrwq_scatter_shifted_offset_p_f32(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
6270	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_f32)))
6271	void __arm_vstrwq_scatter_shifted_offset_p(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
6272	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_f16)))
6273	float16x8_t __arm_vsubq_f16(float16x8_t, float16x8_t);
6274	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_f16)))
6275	float16x8_t __arm_vsubq(float16x8_t, float16x8_t);
6276	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_f32)))
6277	float32x4_t __arm_vsubq_f32(float32x4_t, float32x4_t);
6278	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_f32)))
6279	float32x4_t __arm_vsubq(float32x4_t, float32x4_t);
6280	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f16)))
6281	float16x8_t __arm_vsubq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
6282	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f16)))
6283	float16x8_t __arm_vsubq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
6284	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f32)))
6285	float32x4_t __arm_vsubq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
6286	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f32)))
6287	float32x4_t __arm_vsubq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
6288	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f16)))
6289	float16x8_t __arm_vsubq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
6290	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f16)))
6291	float16x8_t __arm_vsubq_x(float16x8_t, float16x8_t, mve_pred16_t);
6292	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f32)))
6293	float32x4_t __arm_vsubq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
6294	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f32)))
6295	float32x4_t __arm_vsubq_x(float32x4_t, float32x4_t, mve_pred16_t);
6296	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_f16)))
6297	float16x8_t __arm_vuninitializedq_f16();
6298	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_f32)))
6299	float32x4_t __arm_vuninitializedq_f32();
6300	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_f16)))
6301	float16x8_t __arm_vuninitializedq(float16x8_t);
6302	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_f32)))
6303	float32x4_t __arm_vuninitializedq(float32x4_t);
6304
6305	#endif /* (__ARM_FEATURE_MVE & 2) */
6306
6307	#if (!defined __ARM_MVE_PRESERVE_USER_NAMESPACE)
6308
6309	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_asrl)))
6310	int64_t asrl(int64_t, int32_t);
6311	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_lsll)))
6312	uint64_t lsll(uint64_t, int32_t);
6313	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshr)))
6314	int32_t sqrshr(int32_t, int32_t);
6315	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshrl)))
6316	int64_t sqrshrl(int64_t, int32_t);
6317	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqrshrl_sat48)))
6318	int64_t sqrshrl_sat48(int64_t, int32_t);
6319	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqshl)))
6320	int32_t sqshl(int32_t, int);
6321	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_sqshll)))
6322	int64_t sqshll(int64_t, int);
6323	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_srshr)))
6324	int32_t srshr(int32_t, int);
6325	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_srshrl)))
6326	int64_t srshrl(int64_t, int);
6327	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshl)))
6328	uint32_t uqrshl(uint32_t, int32_t);
6329	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshll)))
6330	uint64_t uqrshll(uint64_t, int32_t);
6331	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqrshll_sat48)))
6332	uint64_t uqrshll_sat48(uint64_t, int32_t);
6333	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqshl)))
6334	uint32_t uqshl(uint32_t, int);
6335	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_uqshll)))
6336	uint64_t uqshll(uint64_t, int);
6337	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_urshr)))
6338	uint32_t urshr(uint32_t, int);
6339	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_urshrl)))
6340	uint64_t urshrl(uint64_t, int);
6341	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s16)))
6342	uint32_t vabavq_p_s16(uint32_t, int16x8_t, int16x8_t, mve_pred16_t);
6343	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s16)))
6344	uint32_t vabavq_p(uint32_t, int16x8_t, int16x8_t, mve_pred16_t);
6345	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s32)))
6346	uint32_t vabavq_p_s32(uint32_t, int32x4_t, int32x4_t, mve_pred16_t);
6347	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s32)))
6348	uint32_t vabavq_p(uint32_t, int32x4_t, int32x4_t, mve_pred16_t);
6349	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s8)))
6350	uint32_t vabavq_p_s8(uint32_t, int8x16_t, int8x16_t, mve_pred16_t);
6351	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_s8)))
6352	uint32_t vabavq_p(uint32_t, int8x16_t, int8x16_t, mve_pred16_t);
6353	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u16)))
6354	uint32_t vabavq_p_u16(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6355	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u16)))
6356	uint32_t vabavq_p(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6357	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u32)))
6358	uint32_t vabavq_p_u32(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6359	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u32)))
6360	uint32_t vabavq_p(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6361	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u8)))
6362	uint32_t vabavq_p_u8(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6363	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_p_u8)))
6364	uint32_t vabavq_p(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6365	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s16)))
6366	uint32_t vabavq_s16(uint32_t, int16x8_t, int16x8_t);
6367	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s16)))
6368	uint32_t vabavq(uint32_t, int16x8_t, int16x8_t);
6369	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s32)))
6370	uint32_t vabavq_s32(uint32_t, int32x4_t, int32x4_t);
6371	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s32)))
6372	uint32_t vabavq(uint32_t, int32x4_t, int32x4_t);
6373	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_s8)))
6374	uint32_t vabavq_s8(uint32_t, int8x16_t, int8x16_t);
6375	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_s8)))
6376	uint32_t vabavq(uint32_t, int8x16_t, int8x16_t);
6377	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u16)))
6378	uint32_t vabavq_u16(uint32_t, uint16x8_t, uint16x8_t);
6379	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u16)))
6380	uint32_t vabavq(uint32_t, uint16x8_t, uint16x8_t);
6381	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u32)))
6382	uint32_t vabavq_u32(uint32_t, uint32x4_t, uint32x4_t);
6383	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u32)))
6384	uint32_t vabavq(uint32_t, uint32x4_t, uint32x4_t);
6385	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabavq_u8)))
6386	uint32_t vabavq_u8(uint32_t, uint8x16_t, uint8x16_t);
6387	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabavq_u8)))
6388	uint32_t vabavq(uint32_t, uint8x16_t, uint8x16_t);
6389	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s16)))
6390	int16x8_t vabdq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6391	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s16)))
6392	int16x8_t vabdq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6393	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s32)))
6394	int32x4_t vabdq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6395	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s32)))
6396	int32x4_t vabdq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6397	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s8)))
6398	int8x16_t vabdq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6399	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_s8)))
6400	int8x16_t vabdq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6401	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u16)))
6402	uint16x8_t vabdq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6403	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u16)))
6404	uint16x8_t vabdq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6405	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u32)))
6406	uint32x4_t vabdq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6407	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u32)))
6408	uint32x4_t vabdq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6409	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u8)))
6410	uint8x16_t vabdq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6411	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_u8)))
6412	uint8x16_t vabdq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6413	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s16)))
6414	int16x8_t vabdq_s16(int16x8_t, int16x8_t);
6415	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s16)))
6416	int16x8_t vabdq(int16x8_t, int16x8_t);
6417	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s32)))
6418	int32x4_t vabdq_s32(int32x4_t, int32x4_t);
6419	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s32)))
6420	int32x4_t vabdq(int32x4_t, int32x4_t);
6421	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_s8)))
6422	int8x16_t vabdq_s8(int8x16_t, int8x16_t);
6423	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_s8)))
6424	int8x16_t vabdq(int8x16_t, int8x16_t);
6425	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u16)))
6426	uint16x8_t vabdq_u16(uint16x8_t, uint16x8_t);
6427	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u16)))
6428	uint16x8_t vabdq(uint16x8_t, uint16x8_t);
6429	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u32)))
6430	uint32x4_t vabdq_u32(uint32x4_t, uint32x4_t);
6431	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u32)))
6432	uint32x4_t vabdq(uint32x4_t, uint32x4_t);
6433	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_u8)))
6434	uint8x16_t vabdq_u8(uint8x16_t, uint8x16_t);
6435	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_u8)))
6436	uint8x16_t vabdq(uint8x16_t, uint8x16_t);
6437	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s16)))
6438	int16x8_t vabdq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6439	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s16)))
6440	int16x8_t vabdq_x(int16x8_t, int16x8_t, mve_pred16_t);
6441	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s32)))
6442	int32x4_t vabdq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6443	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s32)))
6444	int32x4_t vabdq_x(int32x4_t, int32x4_t, mve_pred16_t);
6445	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s8)))
6446	int8x16_t vabdq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6447	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_s8)))
6448	int8x16_t vabdq_x(int8x16_t, int8x16_t, mve_pred16_t);
6449	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u16)))
6450	uint16x8_t vabdq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6451	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u16)))
6452	uint16x8_t vabdq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6453	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u32)))
6454	uint32x4_t vabdq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6455	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u32)))
6456	uint32x4_t vabdq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6457	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u8)))
6458	uint8x16_t vabdq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6459	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_u8)))
6460	uint8x16_t vabdq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6461	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_s32)))
6462	int32x4_t vadciq_m_s32(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
6463	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_s32)))
6464	int32x4_t vadciq_m(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
6465	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_u32)))
6466	uint32x4_t vadciq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
6467	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_m_u32)))
6468	uint32x4_t vadciq_m(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
6469	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_s32)))
6470	int32x4_t vadciq_s32(int32x4_t, int32x4_t, unsigned *);
6471	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_s32)))
6472	int32x4_t vadciq(int32x4_t, int32x4_t, unsigned *);
6473	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadciq_u32)))
6474	uint32x4_t vadciq_u32(uint32x4_t, uint32x4_t, unsigned *);
6475	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadciq_u32)))
6476	uint32x4_t vadciq(uint32x4_t, uint32x4_t, unsigned *);
6477	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_s32)))
6478	int32x4_t vadcq_m_s32(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
6479	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_s32)))
6480	int32x4_t vadcq_m(int32x4_t, int32x4_t, int32x4_t, unsigned *, mve_pred16_t);
6481	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_u32)))
6482	uint32x4_t vadcq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
6483	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_m_u32)))
6484	uint32x4_t vadcq_m(uint32x4_t, uint32x4_t, uint32x4_t, unsigned *, mve_pred16_t);
6485	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_s32)))
6486	int32x4_t vadcq_s32(int32x4_t, int32x4_t, unsigned *);
6487	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_s32)))
6488	int32x4_t vadcq(int32x4_t, int32x4_t, unsigned *);
6489	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vadcq_u32)))
6490	uint32x4_t vadcq_u32(uint32x4_t, uint32x4_t, unsigned *);
6491	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vadcq_u32)))
6492	uint32x4_t vadcq(uint32x4_t, uint32x4_t, unsigned *);
6493	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s16)))
6494	int16x8_t vaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6495	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s16)))
6496	int16x8_t vaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6497	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s32)))
6498	int32x4_t vaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6499	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s32)))
6500	int32x4_t vaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6501	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s8)))
6502	int8x16_t vaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6503	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_s8)))
6504	int8x16_t vaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6505	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u16)))
6506	uint16x8_t vaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6507	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u16)))
6508	uint16x8_t vaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6509	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u32)))
6510	uint32x4_t vaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6511	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u32)))
6512	uint32x4_t vaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6513	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u8)))
6514	uint8x16_t vaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6515	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_u8)))
6516	uint8x16_t vaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6517	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s16)))
6518	int16x8_t vaddq_s16(int16x8_t, int16x8_t);
6519	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s16)))
6520	int16x8_t vaddq(int16x8_t, int16x8_t);
6521	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s32)))
6522	int32x4_t vaddq_s32(int32x4_t, int32x4_t);
6523	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s32)))
6524	int32x4_t vaddq(int32x4_t, int32x4_t);
6525	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_s8)))
6526	int8x16_t vaddq_s8(int8x16_t, int8x16_t);
6527	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_s8)))
6528	int8x16_t vaddq(int8x16_t, int8x16_t);
6529	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u16)))
6530	uint16x8_t vaddq_u16(uint16x8_t, uint16x8_t);
6531	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u16)))
6532	uint16x8_t vaddq(uint16x8_t, uint16x8_t);
6533	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u32)))
6534	uint32x4_t vaddq_u32(uint32x4_t, uint32x4_t);
6535	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u32)))
6536	uint32x4_t vaddq(uint32x4_t, uint32x4_t);
6537	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_u8)))
6538	uint8x16_t vaddq_u8(uint8x16_t, uint8x16_t);
6539	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_u8)))
6540	uint8x16_t vaddq(uint8x16_t, uint8x16_t);
6541	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s16)))
6542	int16x8_t vaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6543	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s16)))
6544	int16x8_t vaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
6545	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s32)))
6546	int32x4_t vaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6547	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s32)))
6548	int32x4_t vaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
6549	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s8)))
6550	int8x16_t vaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6551	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_s8)))
6552	int8x16_t vaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
6553	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u16)))
6554	uint16x8_t vaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6555	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u16)))
6556	uint16x8_t vaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6557	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u32)))
6558	uint32x4_t vaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6559	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u32)))
6560	uint32x4_t vaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6561	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u8)))
6562	uint8x16_t vaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6563	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_u8)))
6564	uint8x16_t vaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6565	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s16)))
6566	int16x8_t vandq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6567	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s16)))
6568	int16x8_t vandq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6569	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s32)))
6570	int32x4_t vandq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6571	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s32)))
6572	int32x4_t vandq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6573	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s8)))
6574	int8x16_t vandq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6575	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_s8)))
6576	int8x16_t vandq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6577	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u16)))
6578	uint16x8_t vandq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6579	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u16)))
6580	uint16x8_t vandq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6581	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u32)))
6582	uint32x4_t vandq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6583	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u32)))
6584	uint32x4_t vandq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6585	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u8)))
6586	uint8x16_t vandq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6587	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_u8)))
6588	uint8x16_t vandq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6589	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s16)))
6590	int16x8_t vandq_s16(int16x8_t, int16x8_t);
6591	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s16)))
6592	int16x8_t vandq(int16x8_t, int16x8_t);
6593	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s32)))
6594	int32x4_t vandq_s32(int32x4_t, int32x4_t);
6595	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s32)))
6596	int32x4_t vandq(int32x4_t, int32x4_t);
6597	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_s8)))
6598	int8x16_t vandq_s8(int8x16_t, int8x16_t);
6599	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_s8)))
6600	int8x16_t vandq(int8x16_t, int8x16_t);
6601	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u16)))
6602	uint16x8_t vandq_u16(uint16x8_t, uint16x8_t);
6603	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u16)))
6604	uint16x8_t vandq(uint16x8_t, uint16x8_t);
6605	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u32)))
6606	uint32x4_t vandq_u32(uint32x4_t, uint32x4_t);
6607	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u32)))
6608	uint32x4_t vandq(uint32x4_t, uint32x4_t);
6609	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_u8)))
6610	uint8x16_t vandq_u8(uint8x16_t, uint8x16_t);
6611	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_u8)))
6612	uint8x16_t vandq(uint8x16_t, uint8x16_t);
6613	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s16)))
6614	int16x8_t vandq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6615	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s16)))
6616	int16x8_t vandq_x(int16x8_t, int16x8_t, mve_pred16_t);
6617	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s32)))
6618	int32x4_t vandq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6619	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s32)))
6620	int32x4_t vandq_x(int32x4_t, int32x4_t, mve_pred16_t);
6621	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s8)))
6622	int8x16_t vandq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6623	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_s8)))
6624	int8x16_t vandq_x(int8x16_t, int8x16_t, mve_pred16_t);
6625	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u16)))
6626	uint16x8_t vandq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6627	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u16)))
6628	uint16x8_t vandq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6629	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u32)))
6630	uint32x4_t vandq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6631	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u32)))
6632	uint32x4_t vandq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6633	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u8)))
6634	uint8x16_t vandq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6635	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_u8)))
6636	uint8x16_t vandq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6637	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s16)))
6638	int16x8_t vbicq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6639	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s16)))
6640	int16x8_t vbicq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6641	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s32)))
6642	int32x4_t vbicq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6643	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s32)))
6644	int32x4_t vbicq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6645	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s8)))
6646	int8x16_t vbicq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6647	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_s8)))
6648	int8x16_t vbicq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6649	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u16)))
6650	uint16x8_t vbicq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6651	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u16)))
6652	uint16x8_t vbicq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6653	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u32)))
6654	uint32x4_t vbicq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6655	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u32)))
6656	uint32x4_t vbicq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6657	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u8)))
6658	uint8x16_t vbicq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6659	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_u8)))
6660	uint8x16_t vbicq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6661	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s16)))
6662	int16x8_t vbicq_s16(int16x8_t, int16x8_t);
6663	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s16)))
6664	int16x8_t vbicq(int16x8_t, int16x8_t);
6665	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s32)))
6666	int32x4_t vbicq_s32(int32x4_t, int32x4_t);
6667	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s32)))
6668	int32x4_t vbicq(int32x4_t, int32x4_t);
6669	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_s8)))
6670	int8x16_t vbicq_s8(int8x16_t, int8x16_t);
6671	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_s8)))
6672	int8x16_t vbicq(int8x16_t, int8x16_t);
6673	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u16)))
6674	uint16x8_t vbicq_u16(uint16x8_t, uint16x8_t);
6675	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u16)))
6676	uint16x8_t vbicq(uint16x8_t, uint16x8_t);
6677	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u32)))
6678	uint32x4_t vbicq_u32(uint32x4_t, uint32x4_t);
6679	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u32)))
6680	uint32x4_t vbicq(uint32x4_t, uint32x4_t);
6681	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_u8)))
6682	uint8x16_t vbicq_u8(uint8x16_t, uint8x16_t);
6683	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_u8)))
6684	uint8x16_t vbicq(uint8x16_t, uint8x16_t);
6685	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s16)))
6686	int16x8_t vbicq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6687	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s16)))
6688	int16x8_t vbicq_x(int16x8_t, int16x8_t, mve_pred16_t);
6689	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s32)))
6690	int32x4_t vbicq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6691	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s32)))
6692	int32x4_t vbicq_x(int32x4_t, int32x4_t, mve_pred16_t);
6693	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s8)))
6694	int8x16_t vbicq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6695	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_s8)))
6696	int8x16_t vbicq_x(int8x16_t, int8x16_t, mve_pred16_t);
6697	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u16)))
6698	uint16x8_t vbicq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6699	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u16)))
6700	uint16x8_t vbicq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6701	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u32)))
6702	uint32x4_t vbicq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6703	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u32)))
6704	uint32x4_t vbicq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6705	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u8)))
6706	uint8x16_t vbicq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6707	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_u8)))
6708	uint8x16_t vbicq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6709	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s16)))
6710	int16x8_t vcaddq_rot270_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6711	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s16)))
6712	int16x8_t vcaddq_rot270_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6713	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s32)))
6714	int32x4_t vcaddq_rot270_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6715	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s32)))
6716	int32x4_t vcaddq_rot270_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6717	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s8)))
6718	int8x16_t vcaddq_rot270_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6719	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_s8)))
6720	int8x16_t vcaddq_rot270_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6721	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u16)))
6722	uint16x8_t vcaddq_rot270_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6723	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u16)))
6724	uint16x8_t vcaddq_rot270_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6725	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u32)))
6726	uint32x4_t vcaddq_rot270_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6727	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u32)))
6728	uint32x4_t vcaddq_rot270_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6729	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u8)))
6730	uint8x16_t vcaddq_rot270_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6731	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_u8)))
6732	uint8x16_t vcaddq_rot270_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6733	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s16)))
6734	int16x8_t vcaddq_rot270_s16(int16x8_t, int16x8_t);
6735	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s16)))
6736	int16x8_t vcaddq_rot270(int16x8_t, int16x8_t);
6737	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s32)))
6738	int32x4_t vcaddq_rot270_s32(int32x4_t, int32x4_t);
6739	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s32)))
6740	int32x4_t vcaddq_rot270(int32x4_t, int32x4_t);
6741	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s8)))
6742	int8x16_t vcaddq_rot270_s8(int8x16_t, int8x16_t);
6743	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_s8)))
6744	int8x16_t vcaddq_rot270(int8x16_t, int8x16_t);
6745	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u16)))
6746	uint16x8_t vcaddq_rot270_u16(uint16x8_t, uint16x8_t);
6747	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u16)))
6748	uint16x8_t vcaddq_rot270(uint16x8_t, uint16x8_t);
6749	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u32)))
6750	uint32x4_t vcaddq_rot270_u32(uint32x4_t, uint32x4_t);
6751	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u32)))
6752	uint32x4_t vcaddq_rot270(uint32x4_t, uint32x4_t);
6753	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u8)))
6754	uint8x16_t vcaddq_rot270_u8(uint8x16_t, uint8x16_t);
6755	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_u8)))
6756	uint8x16_t vcaddq_rot270(uint8x16_t, uint8x16_t);
6757	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s16)))
6758	int16x8_t vcaddq_rot270_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6759	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s16)))
6760	int16x8_t vcaddq_rot270_x(int16x8_t, int16x8_t, mve_pred16_t);
6761	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s32)))
6762	int32x4_t vcaddq_rot270_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6763	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s32)))
6764	int32x4_t vcaddq_rot270_x(int32x4_t, int32x4_t, mve_pred16_t);
6765	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s8)))
6766	int8x16_t vcaddq_rot270_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6767	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_s8)))
6768	int8x16_t vcaddq_rot270_x(int8x16_t, int8x16_t, mve_pred16_t);
6769	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u16)))
6770	uint16x8_t vcaddq_rot270_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6771	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u16)))
6772	uint16x8_t vcaddq_rot270_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6773	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u32)))
6774	uint32x4_t vcaddq_rot270_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6775	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u32)))
6776	uint32x4_t vcaddq_rot270_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6777	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u8)))
6778	uint8x16_t vcaddq_rot270_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6779	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_u8)))
6780	uint8x16_t vcaddq_rot270_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6781	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s16)))
6782	int16x8_t vcaddq_rot90_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6783	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s16)))
6784	int16x8_t vcaddq_rot90_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
6785	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s32)))
6786	int32x4_t vcaddq_rot90_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6787	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s32)))
6788	int32x4_t vcaddq_rot90_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
6789	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s8)))
6790	int8x16_t vcaddq_rot90_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6791	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_s8)))
6792	int8x16_t vcaddq_rot90_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
6793	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u16)))
6794	uint16x8_t vcaddq_rot90_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6795	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u16)))
6796	uint16x8_t vcaddq_rot90_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
6797	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u32)))
6798	uint32x4_t vcaddq_rot90_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6799	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u32)))
6800	uint32x4_t vcaddq_rot90_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
6801	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u8)))
6802	uint8x16_t vcaddq_rot90_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6803	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_u8)))
6804	uint8x16_t vcaddq_rot90_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
6805	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s16)))
6806	int16x8_t vcaddq_rot90_s16(int16x8_t, int16x8_t);
6807	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s16)))
6808	int16x8_t vcaddq_rot90(int16x8_t, int16x8_t);
6809	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s32)))
6810	int32x4_t vcaddq_rot90_s32(int32x4_t, int32x4_t);
6811	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s32)))
6812	int32x4_t vcaddq_rot90(int32x4_t, int32x4_t);
6813	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s8)))
6814	int8x16_t vcaddq_rot90_s8(int8x16_t, int8x16_t);
6815	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_s8)))
6816	int8x16_t vcaddq_rot90(int8x16_t, int8x16_t);
6817	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u16)))
6818	uint16x8_t vcaddq_rot90_u16(uint16x8_t, uint16x8_t);
6819	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u16)))
6820	uint16x8_t vcaddq_rot90(uint16x8_t, uint16x8_t);
6821	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u32)))
6822	uint32x4_t vcaddq_rot90_u32(uint32x4_t, uint32x4_t);
6823	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u32)))
6824	uint32x4_t vcaddq_rot90(uint32x4_t, uint32x4_t);
6825	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u8)))
6826	uint8x16_t vcaddq_rot90_u8(uint8x16_t, uint8x16_t);
6827	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_u8)))
6828	uint8x16_t vcaddq_rot90(uint8x16_t, uint8x16_t);
6829	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s16)))
6830	int16x8_t vcaddq_rot90_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
6831	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s16)))
6832	int16x8_t vcaddq_rot90_x(int16x8_t, int16x8_t, mve_pred16_t);
6833	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s32)))
6834	int32x4_t vcaddq_rot90_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
6835	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s32)))
6836	int32x4_t vcaddq_rot90_x(int32x4_t, int32x4_t, mve_pred16_t);
6837	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s8)))
6838	int8x16_t vcaddq_rot90_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
6839	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_s8)))
6840	int8x16_t vcaddq_rot90_x(int8x16_t, int8x16_t, mve_pred16_t);
6841	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u16)))
6842	uint16x8_t vcaddq_rot90_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6843	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u16)))
6844	uint16x8_t vcaddq_rot90_x(uint16x8_t, uint16x8_t, mve_pred16_t);
6845	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u32)))
6846	uint32x4_t vcaddq_rot90_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6847	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u32)))
6848	uint32x4_t vcaddq_rot90_x(uint32x4_t, uint32x4_t, mve_pred16_t);
6849	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u8)))
6850	uint8x16_t vcaddq_rot90_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6851	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_u8)))
6852	uint8x16_t vcaddq_rot90_x(uint8x16_t, uint8x16_t, mve_pred16_t);
6853	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u16)))
6854	mve_pred16_t vcmpcsq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
6855	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u16)))
6856	mve_pred16_t vcmpcsq_m(uint16x8_t, uint16_t, mve_pred16_t);
6857	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u32)))
6858	mve_pred16_t vcmpcsq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
6859	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u32)))
6860	mve_pred16_t vcmpcsq_m(uint32x4_t, uint32_t, mve_pred16_t);
6861	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u8)))
6862	mve_pred16_t vcmpcsq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
6863	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_n_u8)))
6864	mve_pred16_t vcmpcsq_m(uint8x16_t, uint8_t, mve_pred16_t);
6865	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u16)))
6866	mve_pred16_t vcmpcsq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6867	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u16)))
6868	mve_pred16_t vcmpcsq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
6869	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u32)))
6870	mve_pred16_t vcmpcsq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6871	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u32)))
6872	mve_pred16_t vcmpcsq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
6873	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u8)))
6874	mve_pred16_t vcmpcsq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6875	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_m_u8)))
6876	mve_pred16_t vcmpcsq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
6877	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u16)))
6878	mve_pred16_t vcmpcsq_n_u16(uint16x8_t, uint16_t);
6879	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u16)))
6880	mve_pred16_t vcmpcsq(uint16x8_t, uint16_t);
6881	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u32)))
6882	mve_pred16_t vcmpcsq_n_u32(uint32x4_t, uint32_t);
6883	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u32)))
6884	mve_pred16_t vcmpcsq(uint32x4_t, uint32_t);
6885	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u8)))
6886	mve_pred16_t vcmpcsq_n_u8(uint8x16_t, uint8_t);
6887	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_n_u8)))
6888	mve_pred16_t vcmpcsq(uint8x16_t, uint8_t);
6889	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u16)))
6890	mve_pred16_t vcmpcsq_u16(uint16x8_t, uint16x8_t);
6891	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u16)))
6892	mve_pred16_t vcmpcsq(uint16x8_t, uint16x8_t);
6893	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u32)))
6894	mve_pred16_t vcmpcsq_u32(uint32x4_t, uint32x4_t);
6895	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u32)))
6896	mve_pred16_t vcmpcsq(uint32x4_t, uint32x4_t);
6897	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u8)))
6898	mve_pred16_t vcmpcsq_u8(uint8x16_t, uint8x16_t);
6899	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpcsq_u8)))
6900	mve_pred16_t vcmpcsq(uint8x16_t, uint8x16_t);
6901	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s16)))
6902	mve_pred16_t vcmpeqq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
6903	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s16)))
6904	mve_pred16_t vcmpeqq_m(int16x8_t, int16_t, mve_pred16_t);
6905	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s32)))
6906	mve_pred16_t vcmpeqq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
6907	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s32)))
6908	mve_pred16_t vcmpeqq_m(int32x4_t, int32_t, mve_pred16_t);
6909	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s8)))
6910	mve_pred16_t vcmpeqq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
6911	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_s8)))
6912	mve_pred16_t vcmpeqq_m(int8x16_t, int8_t, mve_pred16_t);
6913	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u16)))
6914	mve_pred16_t vcmpeqq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
6915	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u16)))
6916	mve_pred16_t vcmpeqq_m(uint16x8_t, uint16_t, mve_pred16_t);
6917	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u32)))
6918	mve_pred16_t vcmpeqq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
6919	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u32)))
6920	mve_pred16_t vcmpeqq_m(uint32x4_t, uint32_t, mve_pred16_t);
6921	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u8)))
6922	mve_pred16_t vcmpeqq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
6923	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_u8)))
6924	mve_pred16_t vcmpeqq_m(uint8x16_t, uint8_t, mve_pred16_t);
6925	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s16)))
6926	mve_pred16_t vcmpeqq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
6927	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s16)))
6928	mve_pred16_t vcmpeqq_m(int16x8_t, int16x8_t, mve_pred16_t);
6929	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s32)))
6930	mve_pred16_t vcmpeqq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
6931	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s32)))
6932	mve_pred16_t vcmpeqq_m(int32x4_t, int32x4_t, mve_pred16_t);
6933	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s8)))
6934	mve_pred16_t vcmpeqq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
6935	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_s8)))
6936	mve_pred16_t vcmpeqq_m(int8x16_t, int8x16_t, mve_pred16_t);
6937	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u16)))
6938	mve_pred16_t vcmpeqq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
6939	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u16)))
6940	mve_pred16_t vcmpeqq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
6941	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u32)))
6942	mve_pred16_t vcmpeqq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
6943	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u32)))
6944	mve_pred16_t vcmpeqq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
6945	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u8)))
6946	mve_pred16_t vcmpeqq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
6947	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_u8)))
6948	mve_pred16_t vcmpeqq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
6949	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s16)))
6950	mve_pred16_t vcmpeqq_n_s16(int16x8_t, int16_t);
6951	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s16)))
6952	mve_pred16_t vcmpeqq(int16x8_t, int16_t);
6953	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s32)))
6954	mve_pred16_t vcmpeqq_n_s32(int32x4_t, int32_t);
6955	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s32)))
6956	mve_pred16_t vcmpeqq(int32x4_t, int32_t);
6957	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s8)))
6958	mve_pred16_t vcmpeqq_n_s8(int8x16_t, int8_t);
6959	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_s8)))
6960	mve_pred16_t vcmpeqq(int8x16_t, int8_t);
6961	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u16)))
6962	mve_pred16_t vcmpeqq_n_u16(uint16x8_t, uint16_t);
6963	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u16)))
6964	mve_pred16_t vcmpeqq(uint16x8_t, uint16_t);
6965	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u32)))
6966	mve_pred16_t vcmpeqq_n_u32(uint32x4_t, uint32_t);
6967	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u32)))
6968	mve_pred16_t vcmpeqq(uint32x4_t, uint32_t);
6969	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u8)))
6970	mve_pred16_t vcmpeqq_n_u8(uint8x16_t, uint8_t);
6971	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_u8)))
6972	mve_pred16_t vcmpeqq(uint8x16_t, uint8_t);
6973	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s16)))
6974	mve_pred16_t vcmpeqq_s16(int16x8_t, int16x8_t);
6975	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s16)))
6976	mve_pred16_t vcmpeqq(int16x8_t, int16x8_t);
6977	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s32)))
6978	mve_pred16_t vcmpeqq_s32(int32x4_t, int32x4_t);
6979	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s32)))
6980	mve_pred16_t vcmpeqq(int32x4_t, int32x4_t);
6981	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s8)))
6982	mve_pred16_t vcmpeqq_s8(int8x16_t, int8x16_t);
6983	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_s8)))
6984	mve_pred16_t vcmpeqq(int8x16_t, int8x16_t);
6985	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u16)))
6986	mve_pred16_t vcmpeqq_u16(uint16x8_t, uint16x8_t);
6987	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u16)))
6988	mve_pred16_t vcmpeqq(uint16x8_t, uint16x8_t);
6989	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u32)))
6990	mve_pred16_t vcmpeqq_u32(uint32x4_t, uint32x4_t);
6991	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u32)))
6992	mve_pred16_t vcmpeqq(uint32x4_t, uint32x4_t);
6993	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u8)))
6994	mve_pred16_t vcmpeqq_u8(uint8x16_t, uint8x16_t);
6995	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_u8)))
6996	mve_pred16_t vcmpeqq(uint8x16_t, uint8x16_t);
6997	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s16)))
6998	mve_pred16_t vcmpgeq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
6999	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s16)))
7000	mve_pred16_t vcmpgeq_m(int16x8_t, int16_t, mve_pred16_t);
7001	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s32)))
7002	mve_pred16_t vcmpgeq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
7003	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s32)))
7004	mve_pred16_t vcmpgeq_m(int32x4_t, int32_t, mve_pred16_t);
7005	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s8)))
7006	mve_pred16_t vcmpgeq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
7007	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_s8)))
7008	mve_pred16_t vcmpgeq_m(int8x16_t, int8_t, mve_pred16_t);
7009	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s16)))
7010	mve_pred16_t vcmpgeq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
7011	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s16)))
7012	mve_pred16_t vcmpgeq_m(int16x8_t, int16x8_t, mve_pred16_t);
7013	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s32)))
7014	mve_pred16_t vcmpgeq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
7015	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s32)))
7016	mve_pred16_t vcmpgeq_m(int32x4_t, int32x4_t, mve_pred16_t);
7017	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s8)))
7018	mve_pred16_t vcmpgeq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
7019	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_s8)))
7020	mve_pred16_t vcmpgeq_m(int8x16_t, int8x16_t, mve_pred16_t);
7021	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s16)))
7022	mve_pred16_t vcmpgeq_n_s16(int16x8_t, int16_t);
7023	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s16)))
7024	mve_pred16_t vcmpgeq(int16x8_t, int16_t);
7025	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s32)))
7026	mve_pred16_t vcmpgeq_n_s32(int32x4_t, int32_t);
7027	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s32)))
7028	mve_pred16_t vcmpgeq(int32x4_t, int32_t);
7029	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s8)))
7030	mve_pred16_t vcmpgeq_n_s8(int8x16_t, int8_t);
7031	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_s8)))
7032	mve_pred16_t vcmpgeq(int8x16_t, int8_t);
7033	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s16)))
7034	mve_pred16_t vcmpgeq_s16(int16x8_t, int16x8_t);
7035	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s16)))
7036	mve_pred16_t vcmpgeq(int16x8_t, int16x8_t);
7037	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s32)))
7038	mve_pred16_t vcmpgeq_s32(int32x4_t, int32x4_t);
7039	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s32)))
7040	mve_pred16_t vcmpgeq(int32x4_t, int32x4_t);
7041	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s8)))
7042	mve_pred16_t vcmpgeq_s8(int8x16_t, int8x16_t);
7043	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_s8)))
7044	mve_pred16_t vcmpgeq(int8x16_t, int8x16_t);
7045	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s16)))
7046	mve_pred16_t vcmpgtq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
7047	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s16)))
7048	mve_pred16_t vcmpgtq_m(int16x8_t, int16_t, mve_pred16_t);
7049	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s32)))
7050	mve_pred16_t vcmpgtq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
7051	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s32)))
7052	mve_pred16_t vcmpgtq_m(int32x4_t, int32_t, mve_pred16_t);
7053	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s8)))
7054	mve_pred16_t vcmpgtq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
7055	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_s8)))
7056	mve_pred16_t vcmpgtq_m(int8x16_t, int8_t, mve_pred16_t);
7057	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s16)))
7058	mve_pred16_t vcmpgtq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
7059	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s16)))
7060	mve_pred16_t vcmpgtq_m(int16x8_t, int16x8_t, mve_pred16_t);
7061	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s32)))
7062	mve_pred16_t vcmpgtq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
7063	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s32)))
7064	mve_pred16_t vcmpgtq_m(int32x4_t, int32x4_t, mve_pred16_t);
7065	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s8)))
7066	mve_pred16_t vcmpgtq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
7067	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_s8)))
7068	mve_pred16_t vcmpgtq_m(int8x16_t, int8x16_t, mve_pred16_t);
7069	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s16)))
7070	mve_pred16_t vcmpgtq_n_s16(int16x8_t, int16_t);
7071	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s16)))
7072	mve_pred16_t vcmpgtq(int16x8_t, int16_t);
7073	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s32)))
7074	mve_pred16_t vcmpgtq_n_s32(int32x4_t, int32_t);
7075	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s32)))
7076	mve_pred16_t vcmpgtq(int32x4_t, int32_t);
7077	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s8)))
7078	mve_pred16_t vcmpgtq_n_s8(int8x16_t, int8_t);
7079	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_s8)))
7080	mve_pred16_t vcmpgtq(int8x16_t, int8_t);
7081	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s16)))
7082	mve_pred16_t vcmpgtq_s16(int16x8_t, int16x8_t);
7083	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s16)))
7084	mve_pred16_t vcmpgtq(int16x8_t, int16x8_t);
7085	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s32)))
7086	mve_pred16_t vcmpgtq_s32(int32x4_t, int32x4_t);
7087	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s32)))
7088	mve_pred16_t vcmpgtq(int32x4_t, int32x4_t);
7089	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s8)))
7090	mve_pred16_t vcmpgtq_s8(int8x16_t, int8x16_t);
7091	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_s8)))
7092	mve_pred16_t vcmpgtq(int8x16_t, int8x16_t);
7093	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u16)))
7094	mve_pred16_t vcmphiq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
7095	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u16)))
7096	mve_pred16_t vcmphiq_m(uint16x8_t, uint16_t, mve_pred16_t);
7097	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u32)))
7098	mve_pred16_t vcmphiq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
7099	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u32)))
7100	mve_pred16_t vcmphiq_m(uint32x4_t, uint32_t, mve_pred16_t);
7101	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u8)))
7102	mve_pred16_t vcmphiq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
7103	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_n_u8)))
7104	mve_pred16_t vcmphiq_m(uint8x16_t, uint8_t, mve_pred16_t);
7105	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u16)))
7106	mve_pred16_t vcmphiq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
7107	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u16)))
7108	mve_pred16_t vcmphiq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
7109	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u32)))
7110	mve_pred16_t vcmphiq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
7111	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u32)))
7112	mve_pred16_t vcmphiq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
7113	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u8)))
7114	mve_pred16_t vcmphiq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
7115	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_m_u8)))
7116	mve_pred16_t vcmphiq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
7117	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u16)))
7118	mve_pred16_t vcmphiq_n_u16(uint16x8_t, uint16_t);
7119	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u16)))
7120	mve_pred16_t vcmphiq(uint16x8_t, uint16_t);
7121	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u32)))
7122	mve_pred16_t vcmphiq_n_u32(uint32x4_t, uint32_t);
7123	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u32)))
7124	mve_pred16_t vcmphiq(uint32x4_t, uint32_t);
7125	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u8)))
7126	mve_pred16_t vcmphiq_n_u8(uint8x16_t, uint8_t);
7127	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_n_u8)))
7128	mve_pred16_t vcmphiq(uint8x16_t, uint8_t);
7129	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u16)))
7130	mve_pred16_t vcmphiq_u16(uint16x8_t, uint16x8_t);
7131	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u16)))
7132	mve_pred16_t vcmphiq(uint16x8_t, uint16x8_t);
7133	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u32)))
7134	mve_pred16_t vcmphiq_u32(uint32x4_t, uint32x4_t);
7135	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u32)))
7136	mve_pred16_t vcmphiq(uint32x4_t, uint32x4_t);
7137	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u8)))
7138	mve_pred16_t vcmphiq_u8(uint8x16_t, uint8x16_t);
7139	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmphiq_u8)))
7140	mve_pred16_t vcmphiq(uint8x16_t, uint8x16_t);
7141	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s16)))
7142	mve_pred16_t vcmpleq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
7143	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s16)))
7144	mve_pred16_t vcmpleq_m(int16x8_t, int16_t, mve_pred16_t);
7145	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s32)))
7146	mve_pred16_t vcmpleq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
7147	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s32)))
7148	mve_pred16_t vcmpleq_m(int32x4_t, int32_t, mve_pred16_t);
7149	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s8)))
7150	mve_pred16_t vcmpleq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
7151	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_s8)))
7152	mve_pred16_t vcmpleq_m(int8x16_t, int8_t, mve_pred16_t);
7153	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s16)))
7154	mve_pred16_t vcmpleq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
7155	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s16)))
7156	mve_pred16_t vcmpleq_m(int16x8_t, int16x8_t, mve_pred16_t);
7157	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s32)))
7158	mve_pred16_t vcmpleq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
7159	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s32)))
7160	mve_pred16_t vcmpleq_m(int32x4_t, int32x4_t, mve_pred16_t);
7161	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s8)))
7162	mve_pred16_t vcmpleq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
7163	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_s8)))
7164	mve_pred16_t vcmpleq_m(int8x16_t, int8x16_t, mve_pred16_t);
7165	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s16)))
7166	mve_pred16_t vcmpleq_n_s16(int16x8_t, int16_t);
7167	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s16)))
7168	mve_pred16_t vcmpleq(int16x8_t, int16_t);
7169	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s32)))
7170	mve_pred16_t vcmpleq_n_s32(int32x4_t, int32_t);
7171	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s32)))
7172	mve_pred16_t vcmpleq(int32x4_t, int32_t);
7173	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s8)))
7174	mve_pred16_t vcmpleq_n_s8(int8x16_t, int8_t);
7175	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_s8)))
7176	mve_pred16_t vcmpleq(int8x16_t, int8_t);
7177	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s16)))
7178	mve_pred16_t vcmpleq_s16(int16x8_t, int16x8_t);
7179	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s16)))
7180	mve_pred16_t vcmpleq(int16x8_t, int16x8_t);
7181	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s32)))
7182	mve_pred16_t vcmpleq_s32(int32x4_t, int32x4_t);
7183	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s32)))
7184	mve_pred16_t vcmpleq(int32x4_t, int32x4_t);
7185	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s8)))
7186	mve_pred16_t vcmpleq_s8(int8x16_t, int8x16_t);
7187	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_s8)))
7188	mve_pred16_t vcmpleq(int8x16_t, int8x16_t);
7189	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s16)))
7190	mve_pred16_t vcmpltq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
7191	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s16)))
7192	mve_pred16_t vcmpltq_m(int16x8_t, int16_t, mve_pred16_t);
7193	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s32)))
7194	mve_pred16_t vcmpltq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
7195	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s32)))
7196	mve_pred16_t vcmpltq_m(int32x4_t, int32_t, mve_pred16_t);
7197	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s8)))
7198	mve_pred16_t vcmpltq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
7199	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_s8)))
7200	mve_pred16_t vcmpltq_m(int8x16_t, int8_t, mve_pred16_t);
7201	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s16)))
7202	mve_pred16_t vcmpltq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
7203	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s16)))
7204	mve_pred16_t vcmpltq_m(int16x8_t, int16x8_t, mve_pred16_t);
7205	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s32)))
7206	mve_pred16_t vcmpltq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
7207	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s32)))
7208	mve_pred16_t vcmpltq_m(int32x4_t, int32x4_t, mve_pred16_t);
7209	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s8)))
7210	mve_pred16_t vcmpltq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
7211	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_s8)))
7212	mve_pred16_t vcmpltq_m(int8x16_t, int8x16_t, mve_pred16_t);
7213	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s16)))
7214	mve_pred16_t vcmpltq_n_s16(int16x8_t, int16_t);
7215	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s16)))
7216	mve_pred16_t vcmpltq(int16x8_t, int16_t);
7217	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s32)))
7218	mve_pred16_t vcmpltq_n_s32(int32x4_t, int32_t);
7219	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s32)))
7220	mve_pred16_t vcmpltq(int32x4_t, int32_t);
7221	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s8)))
7222	mve_pred16_t vcmpltq_n_s8(int8x16_t, int8_t);
7223	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_s8)))
7224	mve_pred16_t vcmpltq(int8x16_t, int8_t);
7225	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s16)))
7226	mve_pred16_t vcmpltq_s16(int16x8_t, int16x8_t);
7227	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s16)))
7228	mve_pred16_t vcmpltq(int16x8_t, int16x8_t);
7229	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s32)))
7230	mve_pred16_t vcmpltq_s32(int32x4_t, int32x4_t);
7231	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s32)))
7232	mve_pred16_t vcmpltq(int32x4_t, int32x4_t);
7233	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s8)))
7234	mve_pred16_t vcmpltq_s8(int8x16_t, int8x16_t);
7235	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_s8)))
7236	mve_pred16_t vcmpltq(int8x16_t, int8x16_t);
7237	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s16)))
7238	mve_pred16_t vcmpneq_m_n_s16(int16x8_t, int16_t, mve_pred16_t);
7239	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s16)))
7240	mve_pred16_t vcmpneq_m(int16x8_t, int16_t, mve_pred16_t);
7241	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s32)))
7242	mve_pred16_t vcmpneq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
7243	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s32)))
7244	mve_pred16_t vcmpneq_m(int32x4_t, int32_t, mve_pred16_t);
7245	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s8)))
7246	mve_pred16_t vcmpneq_m_n_s8(int8x16_t, int8_t, mve_pred16_t);
7247	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_s8)))
7248	mve_pred16_t vcmpneq_m(int8x16_t, int8_t, mve_pred16_t);
7249	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u16)))
7250	mve_pred16_t vcmpneq_m_n_u16(uint16x8_t, uint16_t, mve_pred16_t);
7251	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u16)))
7252	mve_pred16_t vcmpneq_m(uint16x8_t, uint16_t, mve_pred16_t);
7253	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u32)))
7254	mve_pred16_t vcmpneq_m_n_u32(uint32x4_t, uint32_t, mve_pred16_t);
7255	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u32)))
7256	mve_pred16_t vcmpneq_m(uint32x4_t, uint32_t, mve_pred16_t);
7257	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u8)))
7258	mve_pred16_t vcmpneq_m_n_u8(uint8x16_t, uint8_t, mve_pred16_t);
7259	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_u8)))
7260	mve_pred16_t vcmpneq_m(uint8x16_t, uint8_t, mve_pred16_t);
7261	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s16)))
7262	mve_pred16_t vcmpneq_m_s16(int16x8_t, int16x8_t, mve_pred16_t);
7263	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s16)))
7264	mve_pred16_t vcmpneq_m(int16x8_t, int16x8_t, mve_pred16_t);
7265	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s32)))
7266	mve_pred16_t vcmpneq_m_s32(int32x4_t, int32x4_t, mve_pred16_t);
7267	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s32)))
7268	mve_pred16_t vcmpneq_m(int32x4_t, int32x4_t, mve_pred16_t);
7269	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s8)))
7270	mve_pred16_t vcmpneq_m_s8(int8x16_t, int8x16_t, mve_pred16_t);
7271	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_s8)))
7272	mve_pred16_t vcmpneq_m(int8x16_t, int8x16_t, mve_pred16_t);
7273	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u16)))
7274	mve_pred16_t vcmpneq_m_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
7275	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u16)))
7276	mve_pred16_t vcmpneq_m(uint16x8_t, uint16x8_t, mve_pred16_t);
7277	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u32)))
7278	mve_pred16_t vcmpneq_m_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
7279	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u32)))
7280	mve_pred16_t vcmpneq_m(uint32x4_t, uint32x4_t, mve_pred16_t);
7281	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u8)))
7282	mve_pred16_t vcmpneq_m_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
7283	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_u8)))
7284	mve_pred16_t vcmpneq_m(uint8x16_t, uint8x16_t, mve_pred16_t);
7285	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s16)))
7286	mve_pred16_t vcmpneq_n_s16(int16x8_t, int16_t);
7287	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s16)))
7288	mve_pred16_t vcmpneq(int16x8_t, int16_t);
7289	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s32)))
7290	mve_pred16_t vcmpneq_n_s32(int32x4_t, int32_t);
7291	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s32)))
7292	mve_pred16_t vcmpneq(int32x4_t, int32_t);
7293	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s8)))
7294	mve_pred16_t vcmpneq_n_s8(int8x16_t, int8_t);
7295	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_s8)))
7296	mve_pred16_t vcmpneq(int8x16_t, int8_t);
7297	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u16)))
7298	mve_pred16_t vcmpneq_n_u16(uint16x8_t, uint16_t);
7299	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u16)))
7300	mve_pred16_t vcmpneq(uint16x8_t, uint16_t);
7301	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u32)))
7302	mve_pred16_t vcmpneq_n_u32(uint32x4_t, uint32_t);
7303	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u32)))
7304	mve_pred16_t vcmpneq(uint32x4_t, uint32_t);
7305	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u8)))
7306	mve_pred16_t vcmpneq_n_u8(uint8x16_t, uint8_t);
7307	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_u8)))
7308	mve_pred16_t vcmpneq(uint8x16_t, uint8_t);
7309	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s16)))
7310	mve_pred16_t vcmpneq_s16(int16x8_t, int16x8_t);
7311	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s16)))
7312	mve_pred16_t vcmpneq(int16x8_t, int16x8_t);
7313	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s32)))
7314	mve_pred16_t vcmpneq_s32(int32x4_t, int32x4_t);
7315	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s32)))
7316	mve_pred16_t vcmpneq(int32x4_t, int32x4_t);
7317	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s8)))
7318	mve_pred16_t vcmpneq_s8(int8x16_t, int8x16_t);
7319	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_s8)))
7320	mve_pred16_t vcmpneq(int8x16_t, int8x16_t);
7321	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u16)))
7322	mve_pred16_t vcmpneq_u16(uint16x8_t, uint16x8_t);
7323	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u16)))
7324	mve_pred16_t vcmpneq(uint16x8_t, uint16x8_t);
7325	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u32)))
7326	mve_pred16_t vcmpneq_u32(uint32x4_t, uint32x4_t);
7327	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u32)))
7328	mve_pred16_t vcmpneq(uint32x4_t, uint32x4_t);
7329	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u8)))
7330	mve_pred16_t vcmpneq_u8(uint8x16_t, uint8x16_t);
7331	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_u8)))
7332	mve_pred16_t vcmpneq(uint8x16_t, uint8x16_t);
7333	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s16)))
7334	int16x8_t vcreateq_s16(uint64_t, uint64_t);
7335	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s32)))
7336	int32x4_t vcreateq_s32(uint64_t, uint64_t);
7337	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s64)))
7338	int64x2_t vcreateq_s64(uint64_t, uint64_t);
7339	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_s8)))
7340	int8x16_t vcreateq_s8(uint64_t, uint64_t);
7341	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u16)))
7342	uint16x8_t vcreateq_u16(uint64_t, uint64_t);
7343	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u32)))
7344	uint32x4_t vcreateq_u32(uint64_t, uint64_t);
7345	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u64)))
7346	uint64x2_t vcreateq_u64(uint64_t, uint64_t);
7347	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_u8)))
7348	uint8x16_t vcreateq_u8(uint64_t, uint64_t);
7349	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp16q)))
7350	mve_pred16_t vctp16q(uint32_t);
7351	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp16q_m)))
7352	mve_pred16_t vctp16q_m(uint32_t, mve_pred16_t);
7353	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp32q)))
7354	mve_pred16_t vctp32q(uint32_t);
7355	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp32q_m)))
7356	mve_pred16_t vctp32q_m(uint32_t, mve_pred16_t);
7357	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp64q)))
7358	mve_pred16_t vctp64q(uint32_t);
7359	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp64q_m)))
7360	mve_pred16_t vctp64q_m(uint32_t, mve_pred16_t);
7361	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp8q)))
7362	mve_pred16_t vctp8q(uint32_t);
7363	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vctp8q_m)))
7364	mve_pred16_t vctp8q_m(uint32_t, mve_pred16_t);
7365	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s16)))
7366	int16x8_t veorq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7367	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s16)))
7368	int16x8_t veorq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7369	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s32)))
7370	int32x4_t veorq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7371	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s32)))
7372	int32x4_t veorq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7373	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s8)))
7374	int8x16_t veorq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7375	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_s8)))
7376	int8x16_t veorq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7377	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u16)))
7378	uint16x8_t veorq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7379	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u16)))
7380	uint16x8_t veorq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7381	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u32)))
7382	uint32x4_t veorq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7383	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u32)))
7384	uint32x4_t veorq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7385	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u8)))
7386	uint8x16_t veorq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7387	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_u8)))
7388	uint8x16_t veorq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7389	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s16)))
7390	int16x8_t veorq_s16(int16x8_t, int16x8_t);
7391	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s16)))
7392	int16x8_t veorq(int16x8_t, int16x8_t);
7393	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s32)))
7394	int32x4_t veorq_s32(int32x4_t, int32x4_t);
7395	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s32)))
7396	int32x4_t veorq(int32x4_t, int32x4_t);
7397	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_s8)))
7398	int8x16_t veorq_s8(int8x16_t, int8x16_t);
7399	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_s8)))
7400	int8x16_t veorq(int8x16_t, int8x16_t);
7401	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u16)))
7402	uint16x8_t veorq_u16(uint16x8_t, uint16x8_t);
7403	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u16)))
7404	uint16x8_t veorq(uint16x8_t, uint16x8_t);
7405	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u32)))
7406	uint32x4_t veorq_u32(uint32x4_t, uint32x4_t);
7407	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u32)))
7408	uint32x4_t veorq(uint32x4_t, uint32x4_t);
7409	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_u8)))
7410	uint8x16_t veorq_u8(uint8x16_t, uint8x16_t);
7411	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_u8)))
7412	uint8x16_t veorq(uint8x16_t, uint8x16_t);
7413	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s16)))
7414	int16x8_t veorq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
7415	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s16)))
7416	int16x8_t veorq_x(int16x8_t, int16x8_t, mve_pred16_t);
7417	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s32)))
7418	int32x4_t veorq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
7419	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s32)))
7420	int32x4_t veorq_x(int32x4_t, int32x4_t, mve_pred16_t);
7421	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s8)))
7422	int8x16_t veorq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
7423	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_s8)))
7424	int8x16_t veorq_x(int8x16_t, int8x16_t, mve_pred16_t);
7425	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u16)))
7426	uint16x8_t veorq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
7427	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u16)))
7428	uint16x8_t veorq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
7429	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u32)))
7430	uint32x4_t veorq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
7431	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u32)))
7432	uint32x4_t veorq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
7433	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u8)))
7434	uint8x16_t veorq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
7435	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_u8)))
7436	uint8x16_t veorq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
7437	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s16)))
7438	int16_t vgetq_lane_s16(int16x8_t, int);
7439	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s16)))
7440	int16_t vgetq_lane(int16x8_t, int);
7441	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s32)))
7442	int32_t vgetq_lane_s32(int32x4_t, int);
7443	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s32)))
7444	int32_t vgetq_lane(int32x4_t, int);
7445	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s64)))
7446	int64_t vgetq_lane_s64(int64x2_t, int);
7447	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s64)))
7448	int64_t vgetq_lane(int64x2_t, int);
7449	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s8)))
7450	int8_t vgetq_lane_s8(int8x16_t, int);
7451	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_s8)))
7452	int8_t vgetq_lane(int8x16_t, int);
7453	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u16)))
7454	uint16_t vgetq_lane_u16(uint16x8_t, int);
7455	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u16)))
7456	uint16_t vgetq_lane(uint16x8_t, int);
7457	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u32)))
7458	uint32_t vgetq_lane_u32(uint32x4_t, int);
7459	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u32)))
7460	uint32_t vgetq_lane(uint32x4_t, int);
7461	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u64)))
7462	uint64_t vgetq_lane_u64(uint64x2_t, int);
7463	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u64)))
7464	uint64_t vgetq_lane(uint64x2_t, int);
7465	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u8)))
7466	uint8_t vgetq_lane_u8(uint8x16_t, int);
7467	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_u8)))
7468	uint8_t vgetq_lane(uint8x16_t, int);
7469	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s16)))
7470	int16x8_t vhaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7471	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s16)))
7472	int16x8_t vhaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7473	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s32)))
7474	int32x4_t vhaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7475	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s32)))
7476	int32x4_t vhaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7477	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s8)))
7478	int8x16_t vhaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7479	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_s8)))
7480	int8x16_t vhaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7481	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u16)))
7482	uint16x8_t vhaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7483	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u16)))
7484	uint16x8_t vhaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7485	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u32)))
7486	uint32x4_t vhaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7487	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u32)))
7488	uint32x4_t vhaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7489	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u8)))
7490	uint8x16_t vhaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7491	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_m_u8)))
7492	uint8x16_t vhaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7493	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s16)))
7494	int16x8_t vhaddq_s16(int16x8_t, int16x8_t);
7495	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s16)))
7496	int16x8_t vhaddq(int16x8_t, int16x8_t);
7497	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s32)))
7498	int32x4_t vhaddq_s32(int32x4_t, int32x4_t);
7499	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s32)))
7500	int32x4_t vhaddq(int32x4_t, int32x4_t);
7501	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s8)))
7502	int8x16_t vhaddq_s8(int8x16_t, int8x16_t);
7503	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_s8)))
7504	int8x16_t vhaddq(int8x16_t, int8x16_t);
7505	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u16)))
7506	uint16x8_t vhaddq_u16(uint16x8_t, uint16x8_t);
7507	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u16)))
7508	uint16x8_t vhaddq(uint16x8_t, uint16x8_t);
7509	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u32)))
7510	uint32x4_t vhaddq_u32(uint32x4_t, uint32x4_t);
7511	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u32)))
7512	uint32x4_t vhaddq(uint32x4_t, uint32x4_t);
7513	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u8)))
7514	uint8x16_t vhaddq_u8(uint8x16_t, uint8x16_t);
7515	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_u8)))
7516	uint8x16_t vhaddq(uint8x16_t, uint8x16_t);
7517	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s16)))
7518	int16x8_t vhaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
7519	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s16)))
7520	int16x8_t vhaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
7521	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s32)))
7522	int32x4_t vhaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
7523	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s32)))
7524	int32x4_t vhaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
7525	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s8)))
7526	int8x16_t vhaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
7527	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_s8)))
7528	int8x16_t vhaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
7529	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u16)))
7530	uint16x8_t vhaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
7531	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u16)))
7532	uint16x8_t vhaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
7533	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u32)))
7534	uint32x4_t vhaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
7535	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u32)))
7536	uint32x4_t vhaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
7537	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u8)))
7538	uint8x16_t vhaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
7539	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhaddq_x_u8)))
7540	uint8x16_t vhaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
7541	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s16)))
7542	int16x8_t vhcaddq_rot270_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7543	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s16)))
7544	int16x8_t vhcaddq_rot270_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7545	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s32)))
7546	int32x4_t vhcaddq_rot270_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7547	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s32)))
7548	int32x4_t vhcaddq_rot270_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7549	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s8)))
7550	int8x16_t vhcaddq_rot270_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7551	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_m_s8)))
7552	int8x16_t vhcaddq_rot270_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7553	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s16)))
7554	int16x8_t vhcaddq_rot270_s16(int16x8_t, int16x8_t);
7555	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s16)))
7556	int16x8_t vhcaddq_rot270(int16x8_t, int16x8_t);
7557	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s32)))
7558	int32x4_t vhcaddq_rot270_s32(int32x4_t, int32x4_t);
7559	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s32)))
7560	int32x4_t vhcaddq_rot270(int32x4_t, int32x4_t);
7561	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s8)))
7562	int8x16_t vhcaddq_rot270_s8(int8x16_t, int8x16_t);
7563	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_s8)))
7564	int8x16_t vhcaddq_rot270(int8x16_t, int8x16_t);
7565	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s16)))
7566	int16x8_t vhcaddq_rot270_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
7567	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s16)))
7568	int16x8_t vhcaddq_rot270_x(int16x8_t, int16x8_t, mve_pred16_t);
7569	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s32)))
7570	int32x4_t vhcaddq_rot270_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
7571	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s32)))
7572	int32x4_t vhcaddq_rot270_x(int32x4_t, int32x4_t, mve_pred16_t);
7573	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s8)))
7574	int8x16_t vhcaddq_rot270_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
7575	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot270_x_s8)))
7576	int8x16_t vhcaddq_rot270_x(int8x16_t, int8x16_t, mve_pred16_t);
7577	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s16)))
7578	int16x8_t vhcaddq_rot90_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7579	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s16)))
7580	int16x8_t vhcaddq_rot90_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7581	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s32)))
7582	int32x4_t vhcaddq_rot90_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7583	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s32)))
7584	int32x4_t vhcaddq_rot90_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7585	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s8)))
7586	int8x16_t vhcaddq_rot90_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7587	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_m_s8)))
7588	int8x16_t vhcaddq_rot90_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7589	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s16)))
7590	int16x8_t vhcaddq_rot90_s16(int16x8_t, int16x8_t);
7591	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s16)))
7592	int16x8_t vhcaddq_rot90(int16x8_t, int16x8_t);
7593	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s32)))
7594	int32x4_t vhcaddq_rot90_s32(int32x4_t, int32x4_t);
7595	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s32)))
7596	int32x4_t vhcaddq_rot90(int32x4_t, int32x4_t);
7597	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s8)))
7598	int8x16_t vhcaddq_rot90_s8(int8x16_t, int8x16_t);
7599	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_s8)))
7600	int8x16_t vhcaddq_rot90(int8x16_t, int8x16_t);
7601	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s16)))
7602	int16x8_t vhcaddq_rot90_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
7603	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s16)))
7604	int16x8_t vhcaddq_rot90_x(int16x8_t, int16x8_t, mve_pred16_t);
7605	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s32)))
7606	int32x4_t vhcaddq_rot90_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
7607	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s32)))
7608	int32x4_t vhcaddq_rot90_x(int32x4_t, int32x4_t, mve_pred16_t);
7609	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s8)))
7610	int8x16_t vhcaddq_rot90_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
7611	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhcaddq_rot90_x_s8)))
7612	int8x16_t vhcaddq_rot90_x(int8x16_t, int8x16_t, mve_pred16_t);
7613	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s16)))
7614	int16x8_t vhsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7615	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s16)))
7616	int16x8_t vhsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
7617	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s32)))
7618	int32x4_t vhsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7619	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s32)))
7620	int32x4_t vhsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
7621	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s8)))
7622	int8x16_t vhsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7623	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_s8)))
7624	int8x16_t vhsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
7625	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u16)))
7626	uint16x8_t vhsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7627	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u16)))
7628	uint16x8_t vhsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
7629	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u32)))
7630	uint32x4_t vhsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7631	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u32)))
7632	uint32x4_t vhsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
7633	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u8)))
7634	uint8x16_t vhsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7635	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_m_u8)))
7636	uint8x16_t vhsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
7637	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s16)))
7638	int16x8_t vhsubq_s16(int16x8_t, int16x8_t);
7639	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s16)))
7640	int16x8_t vhsubq(int16x8_t, int16x8_t);
7641	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s32)))
7642	int32x4_t vhsubq_s32(int32x4_t, int32x4_t);
7643	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s32)))
7644	int32x4_t vhsubq(int32x4_t, int32x4_t);
7645	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s8)))
7646	int8x16_t vhsubq_s8(int8x16_t, int8x16_t);
7647	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_s8)))
7648	int8x16_t vhsubq(int8x16_t, int8x16_t);
7649	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u16)))
7650	uint16x8_t vhsubq_u16(uint16x8_t, uint16x8_t);
7651	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u16)))
7652	uint16x8_t vhsubq(uint16x8_t, uint16x8_t);
7653	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u32)))
7654	uint32x4_t vhsubq_u32(uint32x4_t, uint32x4_t);
7655	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u32)))
7656	uint32x4_t vhsubq(uint32x4_t, uint32x4_t);
7657	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u8)))
7658	uint8x16_t vhsubq_u8(uint8x16_t, uint8x16_t);
7659	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_u8)))
7660	uint8x16_t vhsubq(uint8x16_t, uint8x16_t);
7661	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s16)))
7662	int16x8_t vhsubq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
7663	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s16)))
7664	int16x8_t vhsubq_x(int16x8_t, int16x8_t, mve_pred16_t);
7665	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s32)))
7666	int32x4_t vhsubq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
7667	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s32)))
7668	int32x4_t vhsubq_x(int32x4_t, int32x4_t, mve_pred16_t);
7669	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s8)))
7670	int8x16_t vhsubq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
7671	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_s8)))
7672	int8x16_t vhsubq_x(int8x16_t, int8x16_t, mve_pred16_t);
7673	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u16)))
7674	uint16x8_t vhsubq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
7675	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u16)))
7676	uint16x8_t vhsubq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
7677	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u32)))
7678	uint32x4_t vhsubq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
7679	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u32)))
7680	uint32x4_t vhsubq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
7681	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u8)))
7682	uint8x16_t vhsubq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
7683	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vhsubq_x_u8)))
7684	uint8x16_t vhsubq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
7685	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s16)))
7686	int16x8_t vld1q_s16(const int16_t *);
7687	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s16)))
7688	int16x8_t vld1q(const int16_t *);
7689	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s32)))
7690	int32x4_t vld1q_s32(const int32_t *);
7691	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s32)))
7692	int32x4_t vld1q(const int32_t *);
7693	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_s8)))
7694	int8x16_t vld1q_s8(const int8_t *);
7695	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_s8)))
7696	int8x16_t vld1q(const int8_t *);
7697	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u16)))
7698	uint16x8_t vld1q_u16(const uint16_t *);
7699	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u16)))
7700	uint16x8_t vld1q(const uint16_t *);
7701	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u32)))
7702	uint32x4_t vld1q_u32(const uint32_t *);
7703	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u32)))
7704	uint32x4_t vld1q(const uint32_t *);
7705	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_u8)))
7706	uint8x16_t vld1q_u8(const uint8_t *);
7707	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_u8)))
7708	uint8x16_t vld1q(const uint8_t *);
7709	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s16)))
7710	int16x8_t vld1q_z_s16(const int16_t *, mve_pred16_t);
7711	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s16)))
7712	int16x8_t vld1q_z(const int16_t *, mve_pred16_t);
7713	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s32)))
7714	int32x4_t vld1q_z_s32(const int32_t *, mve_pred16_t);
7715	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s32)))
7716	int32x4_t vld1q_z(const int32_t *, mve_pred16_t);
7717	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s8)))
7718	int8x16_t vld1q_z_s8(const int8_t *, mve_pred16_t);
7719	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_s8)))
7720	int8x16_t vld1q_z(const int8_t *, mve_pred16_t);
7721	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u16)))
7722	uint16x8_t vld1q_z_u16(const uint16_t *, mve_pred16_t);
7723	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u16)))
7724	uint16x8_t vld1q_z(const uint16_t *, mve_pred16_t);
7725	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u32)))
7726	uint32x4_t vld1q_z_u32(const uint32_t *, mve_pred16_t);
7727	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u32)))
7728	uint32x4_t vld1q_z(const uint32_t *, mve_pred16_t);
7729	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u8)))
7730	uint8x16_t vld1q_z_u8(const uint8_t *, mve_pred16_t);
7731	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_u8)))
7732	uint8x16_t vld1q_z(const uint8_t *, mve_pred16_t);
7733	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s16)))
7734	int16x8x2_t vld2q_s16(const int16_t *);
7735	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s16)))
7736	int16x8x2_t vld2q(const int16_t *);
7737	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s32)))
7738	int32x4x2_t vld2q_s32(const int32_t *);
7739	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s32)))
7740	int32x4x2_t vld2q(const int32_t *);
7741	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_s8)))
7742	int8x16x2_t vld2q_s8(const int8_t *);
7743	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_s8)))
7744	int8x16x2_t vld2q(const int8_t *);
7745	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u16)))
7746	uint16x8x2_t vld2q_u16(const uint16_t *);
7747	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u16)))
7748	uint16x8x2_t vld2q(const uint16_t *);
7749	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u32)))
7750	uint32x4x2_t vld2q_u32(const uint32_t *);
7751	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u32)))
7752	uint32x4x2_t vld2q(const uint32_t *);
7753	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_u8)))
7754	uint8x16x2_t vld2q_u8(const uint8_t *);
7755	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_u8)))
7756	uint8x16x2_t vld2q(const uint8_t *);
7757	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s16)))
7758	int16x8x4_t vld4q_s16(const int16_t *);
7759	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s16)))
7760	int16x8x4_t vld4q(const int16_t *);
7761	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s32)))
7762	int32x4x4_t vld4q_s32(const int32_t *);
7763	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s32)))
7764	int32x4x4_t vld4q(const int32_t *);
7765	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_s8)))
7766	int8x16x4_t vld4q_s8(const int8_t *);
7767	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_s8)))
7768	int8x16x4_t vld4q(const int8_t *);
7769	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u16)))
7770	uint16x8x4_t vld4q_u16(const uint16_t *);
7771	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u16)))
7772	uint16x8x4_t vld4q(const uint16_t *);
7773	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u32)))
7774	uint32x4x4_t vld4q_u32(const uint32_t *);
7775	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u32)))
7776	uint32x4x4_t vld4q(const uint32_t *);
7777	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_u8)))
7778	uint8x16x4_t vld4q_u8(const uint8_t *);
7779	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_u8)))
7780	uint8x16x4_t vld4q(const uint8_t *);
7781	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s16)))
7782	int16x8_t vldrbq_gather_offset_s16(const int8_t *, uint16x8_t);
7783	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s16)))
7784	int16x8_t vldrbq_gather_offset(const int8_t *, uint16x8_t);
7785	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s32)))
7786	int32x4_t vldrbq_gather_offset_s32(const int8_t *, uint32x4_t);
7787	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s32)))
7788	int32x4_t vldrbq_gather_offset(const int8_t *, uint32x4_t);
7789	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s8)))
7790	int8x16_t vldrbq_gather_offset_s8(const int8_t *, uint8x16_t);
7791	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_s8)))
7792	int8x16_t vldrbq_gather_offset(const int8_t *, uint8x16_t);
7793	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u16)))
7794	uint16x8_t vldrbq_gather_offset_u16(const uint8_t *, uint16x8_t);
7795	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u16)))
7796	uint16x8_t vldrbq_gather_offset(const uint8_t *, uint16x8_t);
7797	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u32)))
7798	uint32x4_t vldrbq_gather_offset_u32(const uint8_t *, uint32x4_t);
7799	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u32)))
7800	uint32x4_t vldrbq_gather_offset(const uint8_t *, uint32x4_t);
7801	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u8)))
7802	uint8x16_t vldrbq_gather_offset_u8(const uint8_t *, uint8x16_t);
7803	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_u8)))
7804	uint8x16_t vldrbq_gather_offset(const uint8_t *, uint8x16_t);
7805	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s16)))
7806	int16x8_t vldrbq_gather_offset_z_s16(const int8_t *, uint16x8_t, mve_pred16_t);
7807	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s16)))
7808	int16x8_t vldrbq_gather_offset_z(const int8_t *, uint16x8_t, mve_pred16_t);
7809	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s32)))
7810	int32x4_t vldrbq_gather_offset_z_s32(const int8_t *, uint32x4_t, mve_pred16_t);
7811	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s32)))
7812	int32x4_t vldrbq_gather_offset_z(const int8_t *, uint32x4_t, mve_pred16_t);
7813	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s8)))
7814	int8x16_t vldrbq_gather_offset_z_s8(const int8_t *, uint8x16_t, mve_pred16_t);
7815	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_s8)))
7816	int8x16_t vldrbq_gather_offset_z(const int8_t *, uint8x16_t, mve_pred16_t);
7817	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u16)))
7818	uint16x8_t vldrbq_gather_offset_z_u16(const uint8_t *, uint16x8_t, mve_pred16_t);
7819	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u16)))
7820	uint16x8_t vldrbq_gather_offset_z(const uint8_t *, uint16x8_t, mve_pred16_t);
7821	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u32)))
7822	uint32x4_t vldrbq_gather_offset_z_u32(const uint8_t *, uint32x4_t, mve_pred16_t);
7823	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u32)))
7824	uint32x4_t vldrbq_gather_offset_z(const uint8_t *, uint32x4_t, mve_pred16_t);
7825	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u8)))
7826	uint8x16_t vldrbq_gather_offset_z_u8(const uint8_t *, uint8x16_t, mve_pred16_t);
7827	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrbq_gather_offset_z_u8)))
7828	uint8x16_t vldrbq_gather_offset_z(const uint8_t *, uint8x16_t, mve_pred16_t);
7829	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s16)))
7830	int16x8_t vldrbq_s16(const int8_t *);
7831	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s32)))
7832	int32x4_t vldrbq_s32(const int8_t *);
7833	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_s8)))
7834	int8x16_t vldrbq_s8(const int8_t *);
7835	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u16)))
7836	uint16x8_t vldrbq_u16(const uint8_t *);
7837	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u32)))
7838	uint32x4_t vldrbq_u32(const uint8_t *);
7839	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_u8)))
7840	uint8x16_t vldrbq_u8(const uint8_t *);
7841	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s16)))
7842	int16x8_t vldrbq_z_s16(const int8_t *, mve_pred16_t);
7843	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s32)))
7844	int32x4_t vldrbq_z_s32(const int8_t *, mve_pred16_t);
7845	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_s8)))
7846	int8x16_t vldrbq_z_s8(const int8_t *, mve_pred16_t);
7847	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u16)))
7848	uint16x8_t vldrbq_z_u16(const uint8_t *, mve_pred16_t);
7849	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u32)))
7850	uint32x4_t vldrbq_z_u32(const uint8_t *, mve_pred16_t);
7851	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrbq_z_u8)))
7852	uint8x16_t vldrbq_z_u8(const uint8_t *, mve_pred16_t);
7853	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_s64)))
7854	int64x2_t vldrdq_gather_base_s64(uint64x2_t, int);
7855	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_u64)))
7856	uint64x2_t vldrdq_gather_base_u64(uint64x2_t, int);
7857	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_s64)))
7858	int64x2_t vldrdq_gather_base_wb_s64(uint64x2_t *, int);
7859	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_u64)))
7860	uint64x2_t vldrdq_gather_base_wb_u64(uint64x2_t *, int);
7861	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_z_s64)))
7862	int64x2_t vldrdq_gather_base_wb_z_s64(uint64x2_t *, int, mve_pred16_t);
7863	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_wb_z_u64)))
7864	uint64x2_t vldrdq_gather_base_wb_z_u64(uint64x2_t *, int, mve_pred16_t);
7865	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_z_s64)))
7866	int64x2_t vldrdq_gather_base_z_s64(uint64x2_t, int, mve_pred16_t);
7867	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_base_z_u64)))
7868	uint64x2_t vldrdq_gather_base_z_u64(uint64x2_t, int, mve_pred16_t);
7869	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_s64)))
7870	int64x2_t vldrdq_gather_offset_s64(const int64_t *, uint64x2_t);
7871	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_s64)))
7872	int64x2_t vldrdq_gather_offset(const int64_t *, uint64x2_t);
7873	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_u64)))
7874	uint64x2_t vldrdq_gather_offset_u64(const uint64_t *, uint64x2_t);
7875	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_u64)))
7876	uint64x2_t vldrdq_gather_offset(const uint64_t *, uint64x2_t);
7877	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_s64)))
7878	int64x2_t vldrdq_gather_offset_z_s64(const int64_t *, uint64x2_t, mve_pred16_t);
7879	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_s64)))
7880	int64x2_t vldrdq_gather_offset_z(const int64_t *, uint64x2_t, mve_pred16_t);
7881	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_u64)))
7882	uint64x2_t vldrdq_gather_offset_z_u64(const uint64_t *, uint64x2_t, mve_pred16_t);
7883	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_offset_z_u64)))
7884	uint64x2_t vldrdq_gather_offset_z(const uint64_t *, uint64x2_t, mve_pred16_t);
7885	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_s64)))
7886	int64x2_t vldrdq_gather_shifted_offset_s64(const int64_t *, uint64x2_t);
7887	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_s64)))
7888	int64x2_t vldrdq_gather_shifted_offset(const int64_t *, uint64x2_t);
7889	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_u64)))
7890	uint64x2_t vldrdq_gather_shifted_offset_u64(const uint64_t *, uint64x2_t);
7891	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_u64)))
7892	uint64x2_t vldrdq_gather_shifted_offset(const uint64_t *, uint64x2_t);
7893	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_s64)))
7894	int64x2_t vldrdq_gather_shifted_offset_z_s64(const int64_t *, uint64x2_t, mve_pred16_t);
7895	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_s64)))
7896	int64x2_t vldrdq_gather_shifted_offset_z(const int64_t *, uint64x2_t, mve_pred16_t);
7897	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_u64)))
7898	uint64x2_t vldrdq_gather_shifted_offset_z_u64(const uint64_t *, uint64x2_t, mve_pred16_t);
7899	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrdq_gather_shifted_offset_z_u64)))
7900	uint64x2_t vldrdq_gather_shifted_offset_z(const uint64_t *, uint64x2_t, mve_pred16_t);
7901	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s16)))
7902	int16x8_t vldrhq_gather_offset_s16(const int16_t *, uint16x8_t);
7903	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s16)))
7904	int16x8_t vldrhq_gather_offset(const int16_t *, uint16x8_t);
7905	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s32)))
7906	int32x4_t vldrhq_gather_offset_s32(const int16_t *, uint32x4_t);
7907	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_s32)))
7908	int32x4_t vldrhq_gather_offset(const int16_t *, uint32x4_t);
7909	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u16)))
7910	uint16x8_t vldrhq_gather_offset_u16(const uint16_t *, uint16x8_t);
7911	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u16)))
7912	uint16x8_t vldrhq_gather_offset(const uint16_t *, uint16x8_t);
7913	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u32)))
7914	uint32x4_t vldrhq_gather_offset_u32(const uint16_t *, uint32x4_t);
7915	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_u32)))
7916	uint32x4_t vldrhq_gather_offset(const uint16_t *, uint32x4_t);
7917	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s16)))
7918	int16x8_t vldrhq_gather_offset_z_s16(const int16_t *, uint16x8_t, mve_pred16_t);
7919	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s16)))
7920	int16x8_t vldrhq_gather_offset_z(const int16_t *, uint16x8_t, mve_pred16_t);
7921	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s32)))
7922	int32x4_t vldrhq_gather_offset_z_s32(const int16_t *, uint32x4_t, mve_pred16_t);
7923	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_s32)))
7924	int32x4_t vldrhq_gather_offset_z(const int16_t *, uint32x4_t, mve_pred16_t);
7925	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u16)))
7926	uint16x8_t vldrhq_gather_offset_z_u16(const uint16_t *, uint16x8_t, mve_pred16_t);
7927	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u16)))
7928	uint16x8_t vldrhq_gather_offset_z(const uint16_t *, uint16x8_t, mve_pred16_t);
7929	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u32)))
7930	uint32x4_t vldrhq_gather_offset_z_u32(const uint16_t *, uint32x4_t, mve_pred16_t);
7931	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_u32)))
7932	uint32x4_t vldrhq_gather_offset_z(const uint16_t *, uint32x4_t, mve_pred16_t);
7933	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s16)))
7934	int16x8_t vldrhq_gather_shifted_offset_s16(const int16_t *, uint16x8_t);
7935	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s16)))
7936	int16x8_t vldrhq_gather_shifted_offset(const int16_t *, uint16x8_t);
7937	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s32)))
7938	int32x4_t vldrhq_gather_shifted_offset_s32(const int16_t *, uint32x4_t);
7939	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_s32)))
7940	int32x4_t vldrhq_gather_shifted_offset(const int16_t *, uint32x4_t);
7941	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u16)))
7942	uint16x8_t vldrhq_gather_shifted_offset_u16(const uint16_t *, uint16x8_t);
7943	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u16)))
7944	uint16x8_t vldrhq_gather_shifted_offset(const uint16_t *, uint16x8_t);
7945	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u32)))
7946	uint32x4_t vldrhq_gather_shifted_offset_u32(const uint16_t *, uint32x4_t);
7947	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_u32)))
7948	uint32x4_t vldrhq_gather_shifted_offset(const uint16_t *, uint32x4_t);
7949	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s16)))
7950	int16x8_t vldrhq_gather_shifted_offset_z_s16(const int16_t *, uint16x8_t, mve_pred16_t);
7951	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s16)))
7952	int16x8_t vldrhq_gather_shifted_offset_z(const int16_t *, uint16x8_t, mve_pred16_t);
7953	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s32)))
7954	int32x4_t vldrhq_gather_shifted_offset_z_s32(const int16_t *, uint32x4_t, mve_pred16_t);
7955	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_s32)))
7956	int32x4_t vldrhq_gather_shifted_offset_z(const int16_t *, uint32x4_t, mve_pred16_t);
7957	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u16)))
7958	uint16x8_t vldrhq_gather_shifted_offset_z_u16(const uint16_t *, uint16x8_t, mve_pred16_t);
7959	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u16)))
7960	uint16x8_t vldrhq_gather_shifted_offset_z(const uint16_t *, uint16x8_t, mve_pred16_t);
7961	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u32)))
7962	uint32x4_t vldrhq_gather_shifted_offset_z_u32(const uint16_t *, uint32x4_t, mve_pred16_t);
7963	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_u32)))
7964	uint32x4_t vldrhq_gather_shifted_offset_z(const uint16_t *, uint32x4_t, mve_pred16_t);
7965	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_s16)))
7966	int16x8_t vldrhq_s16(const int16_t *);
7967	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_s32)))
7968	int32x4_t vldrhq_s32(const int16_t *);
7969	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_u16)))
7970	uint16x8_t vldrhq_u16(const uint16_t *);
7971	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_u32)))
7972	uint32x4_t vldrhq_u32(const uint16_t *);
7973	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_s16)))
7974	int16x8_t vldrhq_z_s16(const int16_t *, mve_pred16_t);
7975	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_s32)))
7976	int32x4_t vldrhq_z_s32(const int16_t *, mve_pred16_t);
7977	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_u16)))
7978	uint16x8_t vldrhq_z_u16(const uint16_t *, mve_pred16_t);
7979	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_u32)))
7980	uint32x4_t vldrhq_z_u32(const uint16_t *, mve_pred16_t);
7981	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_s32)))
7982	int32x4_t vldrwq_gather_base_s32(uint32x4_t, int);
7983	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_u32)))
7984	uint32x4_t vldrwq_gather_base_u32(uint32x4_t, int);
7985	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_s32)))
7986	int32x4_t vldrwq_gather_base_wb_s32(uint32x4_t *, int);
7987	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_u32)))
7988	uint32x4_t vldrwq_gather_base_wb_u32(uint32x4_t *, int);
7989	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_s32)))
7990	int32x4_t vldrwq_gather_base_wb_z_s32(uint32x4_t *, int, mve_pred16_t);
7991	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_u32)))
7992	uint32x4_t vldrwq_gather_base_wb_z_u32(uint32x4_t *, int, mve_pred16_t);
7993	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_s32)))
7994	int32x4_t vldrwq_gather_base_z_s32(uint32x4_t, int, mve_pred16_t);
7995	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_u32)))
7996	uint32x4_t vldrwq_gather_base_z_u32(uint32x4_t, int, mve_pred16_t);
7997	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_s32)))
7998	int32x4_t vldrwq_gather_offset_s32(const int32_t *, uint32x4_t);
7999	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_s32)))
8000	int32x4_t vldrwq_gather_offset(const int32_t *, uint32x4_t);
8001	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_u32)))
8002	uint32x4_t vldrwq_gather_offset_u32(const uint32_t *, uint32x4_t);
8003	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_u32)))
8004	uint32x4_t vldrwq_gather_offset(const uint32_t *, uint32x4_t);
8005	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_s32)))
8006	int32x4_t vldrwq_gather_offset_z_s32(const int32_t *, uint32x4_t, mve_pred16_t);
8007	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_s32)))
8008	int32x4_t vldrwq_gather_offset_z(const int32_t *, uint32x4_t, mve_pred16_t);
8009	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_u32)))
8010	uint32x4_t vldrwq_gather_offset_z_u32(const uint32_t *, uint32x4_t, mve_pred16_t);
8011	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_u32)))
8012	uint32x4_t vldrwq_gather_offset_z(const uint32_t *, uint32x4_t, mve_pred16_t);
8013	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_s32)))
8014	int32x4_t vldrwq_gather_shifted_offset_s32(const int32_t *, uint32x4_t);
8015	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_s32)))
8016	int32x4_t vldrwq_gather_shifted_offset(const int32_t *, uint32x4_t);
8017	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_u32)))
8018	uint32x4_t vldrwq_gather_shifted_offset_u32(const uint32_t *, uint32x4_t);
8019	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_u32)))
8020	uint32x4_t vldrwq_gather_shifted_offset(const uint32_t *, uint32x4_t);
8021	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_s32)))
8022	int32x4_t vldrwq_gather_shifted_offset_z_s32(const int32_t *, uint32x4_t, mve_pred16_t);
8023	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_s32)))
8024	int32x4_t vldrwq_gather_shifted_offset_z(const int32_t *, uint32x4_t, mve_pred16_t);
8025	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_u32)))
8026	uint32x4_t vldrwq_gather_shifted_offset_z_u32(const uint32_t *, uint32x4_t, mve_pred16_t);
8027	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_u32)))
8028	uint32x4_t vldrwq_gather_shifted_offset_z(const uint32_t *, uint32x4_t, mve_pred16_t);
8029	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_s32)))
8030	int32x4_t vldrwq_s32(const int32_t *);
8031	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_u32)))
8032	uint32x4_t vldrwq_u32(const uint32_t *);
8033	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_s32)))
8034	int32x4_t vldrwq_z_s32(const int32_t *, mve_pred16_t);
8035	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_u32)))
8036	uint32x4_t vldrwq_z_u32(const uint32_t *, mve_pred16_t);
8037	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s16)))
8038	int16x8_t vmaxq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8039	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s16)))
8040	int16x8_t vmaxq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8041	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s32)))
8042	int32x4_t vmaxq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8043	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s32)))
8044	int32x4_t vmaxq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8045	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s8)))
8046	int8x16_t vmaxq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8047	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_s8)))
8048	int8x16_t vmaxq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8049	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u16)))
8050	uint16x8_t vmaxq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8051	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u16)))
8052	uint16x8_t vmaxq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8053	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u32)))
8054	uint32x4_t vmaxq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8055	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u32)))
8056	uint32x4_t vmaxq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8057	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u8)))
8058	uint8x16_t vmaxq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8059	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_m_u8)))
8060	uint8x16_t vmaxq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8061	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s16)))
8062	int16x8_t vmaxq_s16(int16x8_t, int16x8_t);
8063	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s16)))
8064	int16x8_t vmaxq(int16x8_t, int16x8_t);
8065	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s32)))
8066	int32x4_t vmaxq_s32(int32x4_t, int32x4_t);
8067	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s32)))
8068	int32x4_t vmaxq(int32x4_t, int32x4_t);
8069	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s8)))
8070	int8x16_t vmaxq_s8(int8x16_t, int8x16_t);
8071	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_s8)))
8072	int8x16_t vmaxq(int8x16_t, int8x16_t);
8073	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u16)))
8074	uint16x8_t vmaxq_u16(uint16x8_t, uint16x8_t);
8075	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u16)))
8076	uint16x8_t vmaxq(uint16x8_t, uint16x8_t);
8077	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u32)))
8078	uint32x4_t vmaxq_u32(uint32x4_t, uint32x4_t);
8079	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u32)))
8080	uint32x4_t vmaxq(uint32x4_t, uint32x4_t);
8081	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u8)))
8082	uint8x16_t vmaxq_u8(uint8x16_t, uint8x16_t);
8083	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_u8)))
8084	uint8x16_t vmaxq(uint8x16_t, uint8x16_t);
8085	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s16)))
8086	int16x8_t vmaxq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8087	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s16)))
8088	int16x8_t vmaxq_x(int16x8_t, int16x8_t, mve_pred16_t);
8089	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s32)))
8090	int32x4_t vmaxq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8091	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s32)))
8092	int32x4_t vmaxq_x(int32x4_t, int32x4_t, mve_pred16_t);
8093	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s8)))
8094	int8x16_t vmaxq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8095	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_s8)))
8096	int8x16_t vmaxq_x(int8x16_t, int8x16_t, mve_pred16_t);
8097	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u16)))
8098	uint16x8_t vmaxq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8099	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u16)))
8100	uint16x8_t vmaxq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8101	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u32)))
8102	uint32x4_t vmaxq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8103	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u32)))
8104	uint32x4_t vmaxq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8105	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u8)))
8106	uint8x16_t vmaxq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8107	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxq_x_u8)))
8108	uint8x16_t vmaxq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8109	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s16)))
8110	int16_t vmaxvq_s16(int16_t, int16x8_t);
8111	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s16)))
8112	int16_t vmaxvq(int16_t, int16x8_t);
8113	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s32)))
8114	int32_t vmaxvq_s32(int32_t, int32x4_t);
8115	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s32)))
8116	int32_t vmaxvq(int32_t, int32x4_t);
8117	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s8)))
8118	int8_t vmaxvq_s8(int8_t, int8x16_t);
8119	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_s8)))
8120	int8_t vmaxvq(int8_t, int8x16_t);
8121	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u16)))
8122	uint16_t vmaxvq_u16(uint16_t, uint16x8_t);
8123	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u16)))
8124	uint16_t vmaxvq(uint16_t, uint16x8_t);
8125	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u32)))
8126	uint32_t vmaxvq_u32(uint32_t, uint32x4_t);
8127	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u32)))
8128	uint32_t vmaxvq(uint32_t, uint32x4_t);
8129	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u8)))
8130	uint8_t vmaxvq_u8(uint8_t, uint8x16_t);
8131	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxvq_u8)))
8132	uint8_t vmaxvq(uint8_t, uint8x16_t);
8133	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s16)))
8134	int16x8_t vminq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8135	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s16)))
8136	int16x8_t vminq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8137	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s32)))
8138	int32x4_t vminq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8139	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s32)))
8140	int32x4_t vminq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8141	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s8)))
8142	int8x16_t vminq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8143	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_s8)))
8144	int8x16_t vminq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8145	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u16)))
8146	uint16x8_t vminq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8147	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u16)))
8148	uint16x8_t vminq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8149	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u32)))
8150	uint32x4_t vminq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8151	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u32)))
8152	uint32x4_t vminq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8153	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u8)))
8154	uint8x16_t vminq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8155	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_m_u8)))
8156	uint8x16_t vminq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8157	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s16)))
8158	int16x8_t vminq_s16(int16x8_t, int16x8_t);
8159	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s16)))
8160	int16x8_t vminq(int16x8_t, int16x8_t);
8161	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s32)))
8162	int32x4_t vminq_s32(int32x4_t, int32x4_t);
8163	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s32)))
8164	int32x4_t vminq(int32x4_t, int32x4_t);
8165	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_s8)))
8166	int8x16_t vminq_s8(int8x16_t, int8x16_t);
8167	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_s8)))
8168	int8x16_t vminq(int8x16_t, int8x16_t);
8169	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u16)))
8170	uint16x8_t vminq_u16(uint16x8_t, uint16x8_t);
8171	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u16)))
8172	uint16x8_t vminq(uint16x8_t, uint16x8_t);
8173	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u32)))
8174	uint32x4_t vminq_u32(uint32x4_t, uint32x4_t);
8175	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u32)))
8176	uint32x4_t vminq(uint32x4_t, uint32x4_t);
8177	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_u8)))
8178	uint8x16_t vminq_u8(uint8x16_t, uint8x16_t);
8179	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_u8)))
8180	uint8x16_t vminq(uint8x16_t, uint8x16_t);
8181	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s16)))
8182	int16x8_t vminq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8183	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s16)))
8184	int16x8_t vminq_x(int16x8_t, int16x8_t, mve_pred16_t);
8185	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s32)))
8186	int32x4_t vminq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8187	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s32)))
8188	int32x4_t vminq_x(int32x4_t, int32x4_t, mve_pred16_t);
8189	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s8)))
8190	int8x16_t vminq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8191	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_s8)))
8192	int8x16_t vminq_x(int8x16_t, int8x16_t, mve_pred16_t);
8193	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u16)))
8194	uint16x8_t vminq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8195	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u16)))
8196	uint16x8_t vminq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8197	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u32)))
8198	uint32x4_t vminq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8199	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u32)))
8200	uint32x4_t vminq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8201	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u8)))
8202	uint8x16_t vminq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8203	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminq_x_u8)))
8204	uint8x16_t vminq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8205	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s16)))
8206	int16_t vminvq_s16(int16_t, int16x8_t);
8207	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s16)))
8208	int16_t vminvq(int16_t, int16x8_t);
8209	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s32)))
8210	int32_t vminvq_s32(int32_t, int32x4_t);
8211	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s32)))
8212	int32_t vminvq(int32_t, int32x4_t);
8213	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_s8)))
8214	int8_t vminvq_s8(int8_t, int8x16_t);
8215	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_s8)))
8216	int8_t vminvq(int8_t, int8x16_t);
8217	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u16)))
8218	uint16_t vminvq_u16(uint16_t, uint16x8_t);
8219	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u16)))
8220	uint16_t vminvq(uint16_t, uint16x8_t);
8221	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u32)))
8222	uint32_t vminvq_u32(uint32_t, uint32x4_t);
8223	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u32)))
8224	uint32_t vminvq(uint32_t, uint32x4_t);
8225	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminvq_u8)))
8226	uint8_t vminvq_u8(uint8_t, uint8x16_t);
8227	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminvq_u8)))
8228	uint8_t vminvq(uint8_t, uint8x16_t);
8229	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s16)))
8230	int32_t vmladavaq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8231	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s16)))
8232	int32_t vmladavaq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8233	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s32)))
8234	int32_t vmladavaq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8235	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s32)))
8236	int32_t vmladavaq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8237	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s8)))
8238	int32_t vmladavaq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8239	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_s8)))
8240	int32_t vmladavaq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8241	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u16)))
8242	uint32_t vmladavaq_p_u16(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8243	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u16)))
8244	uint32_t vmladavaq_p(uint32_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8245	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u32)))
8246	uint32_t vmladavaq_p_u32(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8247	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u32)))
8248	uint32_t vmladavaq_p(uint32_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8249	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u8)))
8250	uint32_t vmladavaq_p_u8(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8251	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_p_u8)))
8252	uint32_t vmladavaq_p(uint32_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8253	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s16)))
8254	int32_t vmladavaq_s16(int32_t, int16x8_t, int16x8_t);
8255	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s16)))
8256	int32_t vmladavaq(int32_t, int16x8_t, int16x8_t);
8257	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s32)))
8258	int32_t vmladavaq_s32(int32_t, int32x4_t, int32x4_t);
8259	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s32)))
8260	int32_t vmladavaq(int32_t, int32x4_t, int32x4_t);
8261	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s8)))
8262	int32_t vmladavaq_s8(int32_t, int8x16_t, int8x16_t);
8263	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_s8)))
8264	int32_t vmladavaq(int32_t, int8x16_t, int8x16_t);
8265	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u16)))
8266	uint32_t vmladavaq_u16(uint32_t, uint16x8_t, uint16x8_t);
8267	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u16)))
8268	uint32_t vmladavaq(uint32_t, uint16x8_t, uint16x8_t);
8269	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u32)))
8270	uint32_t vmladavaq_u32(uint32_t, uint32x4_t, uint32x4_t);
8271	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u32)))
8272	uint32_t vmladavaq(uint32_t, uint32x4_t, uint32x4_t);
8273	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u8)))
8274	uint32_t vmladavaq_u8(uint32_t, uint8x16_t, uint8x16_t);
8275	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaq_u8)))
8276	uint32_t vmladavaq(uint32_t, uint8x16_t, uint8x16_t);
8277	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s16)))
8278	int32_t vmladavaxq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8279	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s16)))
8280	int32_t vmladavaxq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8281	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s32)))
8282	int32_t vmladavaxq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8283	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s32)))
8284	int32_t vmladavaxq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8285	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s8)))
8286	int32_t vmladavaxq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8287	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_p_s8)))
8288	int32_t vmladavaxq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8289	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s16)))
8290	int32_t vmladavaxq_s16(int32_t, int16x8_t, int16x8_t);
8291	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s16)))
8292	int32_t vmladavaxq(int32_t, int16x8_t, int16x8_t);
8293	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s32)))
8294	int32_t vmladavaxq_s32(int32_t, int32x4_t, int32x4_t);
8295	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s32)))
8296	int32_t vmladavaxq(int32_t, int32x4_t, int32x4_t);
8297	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s8)))
8298	int32_t vmladavaxq_s8(int32_t, int8x16_t, int8x16_t);
8299	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavaxq_s8)))
8300	int32_t vmladavaxq(int32_t, int8x16_t, int8x16_t);
8301	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s16)))
8302	int32_t vmladavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8303	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s16)))
8304	int32_t vmladavq_p(int16x8_t, int16x8_t, mve_pred16_t);
8305	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s32)))
8306	int32_t vmladavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8307	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s32)))
8308	int32_t vmladavq_p(int32x4_t, int32x4_t, mve_pred16_t);
8309	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s8)))
8310	int32_t vmladavq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
8311	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_s8)))
8312	int32_t vmladavq_p(int8x16_t, int8x16_t, mve_pred16_t);
8313	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u16)))
8314	uint32_t vmladavq_p_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8315	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u16)))
8316	uint32_t vmladavq_p(uint16x8_t, uint16x8_t, mve_pred16_t);
8317	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u32)))
8318	uint32_t vmladavq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8319	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u32)))
8320	uint32_t vmladavq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
8321	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u8)))
8322	uint32_t vmladavq_p_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8323	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_p_u8)))
8324	uint32_t vmladavq_p(uint8x16_t, uint8x16_t, mve_pred16_t);
8325	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s16)))
8326	int32_t vmladavq_s16(int16x8_t, int16x8_t);
8327	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s16)))
8328	int32_t vmladavq(int16x8_t, int16x8_t);
8329	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s32)))
8330	int32_t vmladavq_s32(int32x4_t, int32x4_t);
8331	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s32)))
8332	int32_t vmladavq(int32x4_t, int32x4_t);
8333	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s8)))
8334	int32_t vmladavq_s8(int8x16_t, int8x16_t);
8335	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_s8)))
8336	int32_t vmladavq(int8x16_t, int8x16_t);
8337	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u16)))
8338	uint32_t vmladavq_u16(uint16x8_t, uint16x8_t);
8339	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u16)))
8340	uint32_t vmladavq(uint16x8_t, uint16x8_t);
8341	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u32)))
8342	uint32_t vmladavq_u32(uint32x4_t, uint32x4_t);
8343	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u32)))
8344	uint32_t vmladavq(uint32x4_t, uint32x4_t);
8345	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u8)))
8346	uint32_t vmladavq_u8(uint8x16_t, uint8x16_t);
8347	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavq_u8)))
8348	uint32_t vmladavq(uint8x16_t, uint8x16_t);
8349	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s16)))
8350	int32_t vmladavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8351	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s16)))
8352	int32_t vmladavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
8353	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s32)))
8354	int32_t vmladavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8355	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s32)))
8356	int32_t vmladavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
8357	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s8)))
8358	int32_t vmladavxq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
8359	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_p_s8)))
8360	int32_t vmladavxq_p(int8x16_t, int8x16_t, mve_pred16_t);
8361	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s16)))
8362	int32_t vmladavxq_s16(int16x8_t, int16x8_t);
8363	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s16)))
8364	int32_t vmladavxq(int16x8_t, int16x8_t);
8365	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s32)))
8366	int32_t vmladavxq_s32(int32x4_t, int32x4_t);
8367	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s32)))
8368	int32_t vmladavxq(int32x4_t, int32x4_t);
8369	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s8)))
8370	int32_t vmladavxq_s8(int8x16_t, int8x16_t);
8371	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmladavxq_s8)))
8372	int32_t vmladavxq(int8x16_t, int8x16_t);
8373	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s16)))
8374	int64_t vmlaldavaq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8375	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s16)))
8376	int64_t vmlaldavaq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8377	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s32)))
8378	int64_t vmlaldavaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8379	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_s32)))
8380	int64_t vmlaldavaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8381	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u16)))
8382	uint64_t vmlaldavaq_p_u16(uint64_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8383	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u16)))
8384	uint64_t vmlaldavaq_p(uint64_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8385	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u32)))
8386	uint64_t vmlaldavaq_p_u32(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8387	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_p_u32)))
8388	uint64_t vmlaldavaq_p(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8389	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s16)))
8390	int64_t vmlaldavaq_s16(int64_t, int16x8_t, int16x8_t);
8391	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s16)))
8392	int64_t vmlaldavaq(int64_t, int16x8_t, int16x8_t);
8393	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s32)))
8394	int64_t vmlaldavaq_s32(int64_t, int32x4_t, int32x4_t);
8395	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_s32)))
8396	int64_t vmlaldavaq(int64_t, int32x4_t, int32x4_t);
8397	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u16)))
8398	uint64_t vmlaldavaq_u16(uint64_t, uint16x8_t, uint16x8_t);
8399	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u16)))
8400	uint64_t vmlaldavaq(uint64_t, uint16x8_t, uint16x8_t);
8401	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u32)))
8402	uint64_t vmlaldavaq_u32(uint64_t, uint32x4_t, uint32x4_t);
8403	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaq_u32)))
8404	uint64_t vmlaldavaq(uint64_t, uint32x4_t, uint32x4_t);
8405	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s16)))
8406	int64_t vmlaldavaxq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8407	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s16)))
8408	int64_t vmlaldavaxq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8409	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s32)))
8410	int64_t vmlaldavaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8411	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_p_s32)))
8412	int64_t vmlaldavaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8413	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s16)))
8414	int64_t vmlaldavaxq_s16(int64_t, int16x8_t, int16x8_t);
8415	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s16)))
8416	int64_t vmlaldavaxq(int64_t, int16x8_t, int16x8_t);
8417	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s32)))
8418	int64_t vmlaldavaxq_s32(int64_t, int32x4_t, int32x4_t);
8419	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavaxq_s32)))
8420	int64_t vmlaldavaxq(int64_t, int32x4_t, int32x4_t);
8421	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s16)))
8422	int64_t vmlaldavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8423	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s16)))
8424	int64_t vmlaldavq_p(int16x8_t, int16x8_t, mve_pred16_t);
8425	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s32)))
8426	int64_t vmlaldavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8427	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_s32)))
8428	int64_t vmlaldavq_p(int32x4_t, int32x4_t, mve_pred16_t);
8429	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u16)))
8430	uint64_t vmlaldavq_p_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8431	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u16)))
8432	uint64_t vmlaldavq_p(uint16x8_t, uint16x8_t, mve_pred16_t);
8433	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u32)))
8434	uint64_t vmlaldavq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8435	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_p_u32)))
8436	uint64_t vmlaldavq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
8437	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s16)))
8438	int64_t vmlaldavq_s16(int16x8_t, int16x8_t);
8439	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s16)))
8440	int64_t vmlaldavq(int16x8_t, int16x8_t);
8441	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s32)))
8442	int64_t vmlaldavq_s32(int32x4_t, int32x4_t);
8443	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_s32)))
8444	int64_t vmlaldavq(int32x4_t, int32x4_t);
8445	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u16)))
8446	uint64_t vmlaldavq_u16(uint16x8_t, uint16x8_t);
8447	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u16)))
8448	uint64_t vmlaldavq(uint16x8_t, uint16x8_t);
8449	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u32)))
8450	uint64_t vmlaldavq_u32(uint32x4_t, uint32x4_t);
8451	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavq_u32)))
8452	uint64_t vmlaldavq(uint32x4_t, uint32x4_t);
8453	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s16)))
8454	int64_t vmlaldavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8455	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s16)))
8456	int64_t vmlaldavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
8457	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s32)))
8458	int64_t vmlaldavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8459	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_p_s32)))
8460	int64_t vmlaldavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
8461	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s16)))
8462	int64_t vmlaldavxq_s16(int16x8_t, int16x8_t);
8463	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s16)))
8464	int64_t vmlaldavxq(int16x8_t, int16x8_t);
8465	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s32)))
8466	int64_t vmlaldavxq_s32(int32x4_t, int32x4_t);
8467	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlaldavxq_s32)))
8468	int64_t vmlaldavxq(int32x4_t, int32x4_t);
8469	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s16)))
8470	int32_t vmlsdavaq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8471	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s16)))
8472	int32_t vmlsdavaq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8473	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s32)))
8474	int32_t vmlsdavaq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8475	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s32)))
8476	int32_t vmlsdavaq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8477	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s8)))
8478	int32_t vmlsdavaq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8479	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_p_s8)))
8480	int32_t vmlsdavaq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8481	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s16)))
8482	int32_t vmlsdavaq_s16(int32_t, int16x8_t, int16x8_t);
8483	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s16)))
8484	int32_t vmlsdavaq(int32_t, int16x8_t, int16x8_t);
8485	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s32)))
8486	int32_t vmlsdavaq_s32(int32_t, int32x4_t, int32x4_t);
8487	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s32)))
8488	int32_t vmlsdavaq(int32_t, int32x4_t, int32x4_t);
8489	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s8)))
8490	int32_t vmlsdavaq_s8(int32_t, int8x16_t, int8x16_t);
8491	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaq_s8)))
8492	int32_t vmlsdavaq(int32_t, int8x16_t, int8x16_t);
8493	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s16)))
8494	int32_t vmlsdavaxq_p_s16(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8495	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s16)))
8496	int32_t vmlsdavaxq_p(int32_t, int16x8_t, int16x8_t, mve_pred16_t);
8497	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s32)))
8498	int32_t vmlsdavaxq_p_s32(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8499	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s32)))
8500	int32_t vmlsdavaxq_p(int32_t, int32x4_t, int32x4_t, mve_pred16_t);
8501	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s8)))
8502	int32_t vmlsdavaxq_p_s8(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8503	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_p_s8)))
8504	int32_t vmlsdavaxq_p(int32_t, int8x16_t, int8x16_t, mve_pred16_t);
8505	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s16)))
8506	int32_t vmlsdavaxq_s16(int32_t, int16x8_t, int16x8_t);
8507	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s16)))
8508	int32_t vmlsdavaxq(int32_t, int16x8_t, int16x8_t);
8509	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s32)))
8510	int32_t vmlsdavaxq_s32(int32_t, int32x4_t, int32x4_t);
8511	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s32)))
8512	int32_t vmlsdavaxq(int32_t, int32x4_t, int32x4_t);
8513	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s8)))
8514	int32_t vmlsdavaxq_s8(int32_t, int8x16_t, int8x16_t);
8515	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavaxq_s8)))
8516	int32_t vmlsdavaxq(int32_t, int8x16_t, int8x16_t);
8517	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s16)))
8518	int32_t vmlsdavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8519	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s16)))
8520	int32_t vmlsdavq_p(int16x8_t, int16x8_t, mve_pred16_t);
8521	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s32)))
8522	int32_t vmlsdavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8523	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s32)))
8524	int32_t vmlsdavq_p(int32x4_t, int32x4_t, mve_pred16_t);
8525	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s8)))
8526	int32_t vmlsdavq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
8527	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_p_s8)))
8528	int32_t vmlsdavq_p(int8x16_t, int8x16_t, mve_pred16_t);
8529	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s16)))
8530	int32_t vmlsdavq_s16(int16x8_t, int16x8_t);
8531	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s16)))
8532	int32_t vmlsdavq(int16x8_t, int16x8_t);
8533	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s32)))
8534	int32_t vmlsdavq_s32(int32x4_t, int32x4_t);
8535	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s32)))
8536	int32_t vmlsdavq(int32x4_t, int32x4_t);
8537	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s8)))
8538	int32_t vmlsdavq_s8(int8x16_t, int8x16_t);
8539	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavq_s8)))
8540	int32_t vmlsdavq(int8x16_t, int8x16_t);
8541	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s16)))
8542	int32_t vmlsdavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8543	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s16)))
8544	int32_t vmlsdavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
8545	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s32)))
8546	int32_t vmlsdavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8547	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s32)))
8548	int32_t vmlsdavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
8549	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s8)))
8550	int32_t vmlsdavxq_p_s8(int8x16_t, int8x16_t, mve_pred16_t);
8551	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_p_s8)))
8552	int32_t vmlsdavxq_p(int8x16_t, int8x16_t, mve_pred16_t);
8553	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s16)))
8554	int32_t vmlsdavxq_s16(int16x8_t, int16x8_t);
8555	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s16)))
8556	int32_t vmlsdavxq(int16x8_t, int16x8_t);
8557	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s32)))
8558	int32_t vmlsdavxq_s32(int32x4_t, int32x4_t);
8559	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s32)))
8560	int32_t vmlsdavxq(int32x4_t, int32x4_t);
8561	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s8)))
8562	int32_t vmlsdavxq_s8(int8x16_t, int8x16_t);
8563	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsdavxq_s8)))
8564	int32_t vmlsdavxq(int8x16_t, int8x16_t);
8565	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s16)))
8566	int64_t vmlsldavaq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8567	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s16)))
8568	int64_t vmlsldavaq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8569	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s32)))
8570	int64_t vmlsldavaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8571	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_p_s32)))
8572	int64_t vmlsldavaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8573	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s16)))
8574	int64_t vmlsldavaq_s16(int64_t, int16x8_t, int16x8_t);
8575	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s16)))
8576	int64_t vmlsldavaq(int64_t, int16x8_t, int16x8_t);
8577	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s32)))
8578	int64_t vmlsldavaq_s32(int64_t, int32x4_t, int32x4_t);
8579	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaq_s32)))
8580	int64_t vmlsldavaq(int64_t, int32x4_t, int32x4_t);
8581	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s16)))
8582	int64_t vmlsldavaxq_p_s16(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8583	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s16)))
8584	int64_t vmlsldavaxq_p(int64_t, int16x8_t, int16x8_t, mve_pred16_t);
8585	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s32)))
8586	int64_t vmlsldavaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8587	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_p_s32)))
8588	int64_t vmlsldavaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
8589	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s16)))
8590	int64_t vmlsldavaxq_s16(int64_t, int16x8_t, int16x8_t);
8591	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s16)))
8592	int64_t vmlsldavaxq(int64_t, int16x8_t, int16x8_t);
8593	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s32)))
8594	int64_t vmlsldavaxq_s32(int64_t, int32x4_t, int32x4_t);
8595	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavaxq_s32)))
8596	int64_t vmlsldavaxq(int64_t, int32x4_t, int32x4_t);
8597	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s16)))
8598	int64_t vmlsldavq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8599	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s16)))
8600	int64_t vmlsldavq_p(int16x8_t, int16x8_t, mve_pred16_t);
8601	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s32)))
8602	int64_t vmlsldavq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8603	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_p_s32)))
8604	int64_t vmlsldavq_p(int32x4_t, int32x4_t, mve_pred16_t);
8605	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s16)))
8606	int64_t vmlsldavq_s16(int16x8_t, int16x8_t);
8607	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s16)))
8608	int64_t vmlsldavq(int16x8_t, int16x8_t);
8609	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s32)))
8610	int64_t vmlsldavq_s32(int32x4_t, int32x4_t);
8611	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavq_s32)))
8612	int64_t vmlsldavq(int32x4_t, int32x4_t);
8613	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s16)))
8614	int64_t vmlsldavxq_p_s16(int16x8_t, int16x8_t, mve_pred16_t);
8615	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s16)))
8616	int64_t vmlsldavxq_p(int16x8_t, int16x8_t, mve_pred16_t);
8617	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s32)))
8618	int64_t vmlsldavxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
8619	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_p_s32)))
8620	int64_t vmlsldavxq_p(int32x4_t, int32x4_t, mve_pred16_t);
8621	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s16)))
8622	int64_t vmlsldavxq_s16(int16x8_t, int16x8_t);
8623	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s16)))
8624	int64_t vmlsldavxq(int16x8_t, int16x8_t);
8625	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s32)))
8626	int64_t vmlsldavxq_s32(int32x4_t, int32x4_t);
8627	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmlsldavxq_s32)))
8628	int64_t vmlsldavxq(int32x4_t, int32x4_t);
8629	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s16)))
8630	int16x8_t vmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8631	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s16)))
8632	int16x8_t vmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8633	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s32)))
8634	int32x4_t vmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8635	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s32)))
8636	int32x4_t vmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8637	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s8)))
8638	int8x16_t vmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8639	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_s8)))
8640	int8x16_t vmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8641	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u16)))
8642	uint16x8_t vmulhq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8643	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u16)))
8644	uint16x8_t vmulhq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8645	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u32)))
8646	uint32x4_t vmulhq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8647	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u32)))
8648	uint32x4_t vmulhq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8649	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u8)))
8650	uint8x16_t vmulhq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8651	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_m_u8)))
8652	uint8x16_t vmulhq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8653	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s16)))
8654	int16x8_t vmulhq_s16(int16x8_t, int16x8_t);
8655	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s16)))
8656	int16x8_t vmulhq(int16x8_t, int16x8_t);
8657	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s32)))
8658	int32x4_t vmulhq_s32(int32x4_t, int32x4_t);
8659	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s32)))
8660	int32x4_t vmulhq(int32x4_t, int32x4_t);
8661	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s8)))
8662	int8x16_t vmulhq_s8(int8x16_t, int8x16_t);
8663	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_s8)))
8664	int8x16_t vmulhq(int8x16_t, int8x16_t);
8665	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u16)))
8666	uint16x8_t vmulhq_u16(uint16x8_t, uint16x8_t);
8667	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u16)))
8668	uint16x8_t vmulhq(uint16x8_t, uint16x8_t);
8669	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u32)))
8670	uint32x4_t vmulhq_u32(uint32x4_t, uint32x4_t);
8671	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u32)))
8672	uint32x4_t vmulhq(uint32x4_t, uint32x4_t);
8673	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u8)))
8674	uint8x16_t vmulhq_u8(uint8x16_t, uint8x16_t);
8675	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_u8)))
8676	uint8x16_t vmulhq(uint8x16_t, uint8x16_t);
8677	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s16)))
8678	int16x8_t vmulhq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8679	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s16)))
8680	int16x8_t vmulhq_x(int16x8_t, int16x8_t, mve_pred16_t);
8681	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s32)))
8682	int32x4_t vmulhq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8683	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s32)))
8684	int32x4_t vmulhq_x(int32x4_t, int32x4_t, mve_pred16_t);
8685	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s8)))
8686	int8x16_t vmulhq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8687	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_s8)))
8688	int8x16_t vmulhq_x(int8x16_t, int8x16_t, mve_pred16_t);
8689	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u16)))
8690	uint16x8_t vmulhq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8691	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u16)))
8692	uint16x8_t vmulhq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8693	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u32)))
8694	uint32x4_t vmulhq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8695	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u32)))
8696	uint32x4_t vmulhq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8697	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u8)))
8698	uint8x16_t vmulhq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8699	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulhq_x_u8)))
8700	uint8x16_t vmulhq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8701	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s16)))
8702	int32x4_t vmullbq_int_m_s16(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
8703	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s16)))
8704	int32x4_t vmullbq_int_m(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
8705	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s32)))
8706	int64x2_t vmullbq_int_m_s32(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
8707	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s32)))
8708	int64x2_t vmullbq_int_m(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
8709	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s8)))
8710	int16x8_t vmullbq_int_m_s8(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
8711	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_s8)))
8712	int16x8_t vmullbq_int_m(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
8713	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u16)))
8714	uint32x4_t vmullbq_int_m_u16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8715	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u16)))
8716	uint32x4_t vmullbq_int_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8717	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u32)))
8718	uint64x2_t vmullbq_int_m_u32(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8719	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u32)))
8720	uint64x2_t vmullbq_int_m(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8721	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u8)))
8722	uint16x8_t vmullbq_int_m_u8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8723	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_m_u8)))
8724	uint16x8_t vmullbq_int_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8725	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s16)))
8726	int32x4_t vmullbq_int_s16(int16x8_t, int16x8_t);
8727	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s16)))
8728	int32x4_t vmullbq_int(int16x8_t, int16x8_t);
8729	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s32)))
8730	int64x2_t vmullbq_int_s32(int32x4_t, int32x4_t);
8731	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s32)))
8732	int64x2_t vmullbq_int(int32x4_t, int32x4_t);
8733	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s8)))
8734	int16x8_t vmullbq_int_s8(int8x16_t, int8x16_t);
8735	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_s8)))
8736	int16x8_t vmullbq_int(int8x16_t, int8x16_t);
8737	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u16)))
8738	uint32x4_t vmullbq_int_u16(uint16x8_t, uint16x8_t);
8739	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u16)))
8740	uint32x4_t vmullbq_int(uint16x8_t, uint16x8_t);
8741	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u32)))
8742	uint64x2_t vmullbq_int_u32(uint32x4_t, uint32x4_t);
8743	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u32)))
8744	uint64x2_t vmullbq_int(uint32x4_t, uint32x4_t);
8745	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u8)))
8746	uint16x8_t vmullbq_int_u8(uint8x16_t, uint8x16_t);
8747	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_u8)))
8748	uint16x8_t vmullbq_int(uint8x16_t, uint8x16_t);
8749	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s16)))
8750	int32x4_t vmullbq_int_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8751	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s16)))
8752	int32x4_t vmullbq_int_x(int16x8_t, int16x8_t, mve_pred16_t);
8753	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s32)))
8754	int64x2_t vmullbq_int_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8755	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s32)))
8756	int64x2_t vmullbq_int_x(int32x4_t, int32x4_t, mve_pred16_t);
8757	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s8)))
8758	int16x8_t vmullbq_int_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8759	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_s8)))
8760	int16x8_t vmullbq_int_x(int8x16_t, int8x16_t, mve_pred16_t);
8761	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u16)))
8762	uint32x4_t vmullbq_int_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8763	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u16)))
8764	uint32x4_t vmullbq_int_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8765	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u32)))
8766	uint64x2_t vmullbq_int_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8767	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u32)))
8768	uint64x2_t vmullbq_int_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8769	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u8)))
8770	uint16x8_t vmullbq_int_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8771	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_int_x_u8)))
8772	uint16x8_t vmullbq_int_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8773	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p16)))
8774	uint32x4_t vmullbq_poly_m_p16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8775	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p16)))
8776	uint32x4_t vmullbq_poly_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8777	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p8)))
8778	uint16x8_t vmullbq_poly_m_p8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8779	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_m_p8)))
8780	uint16x8_t vmullbq_poly_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8781	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p16)))
8782	uint32x4_t vmullbq_poly_p16(uint16x8_t, uint16x8_t);
8783	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p16)))
8784	uint32x4_t vmullbq_poly(uint16x8_t, uint16x8_t);
8785	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p8)))
8786	uint16x8_t vmullbq_poly_p8(uint8x16_t, uint8x16_t);
8787	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_p8)))
8788	uint16x8_t vmullbq_poly(uint8x16_t, uint8x16_t);
8789	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p16)))
8790	uint32x4_t vmullbq_poly_x_p16(uint16x8_t, uint16x8_t, mve_pred16_t);
8791	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p16)))
8792	uint32x4_t vmullbq_poly_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8793	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p8)))
8794	uint16x8_t vmullbq_poly_x_p8(uint8x16_t, uint8x16_t, mve_pred16_t);
8795	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmullbq_poly_x_p8)))
8796	uint16x8_t vmullbq_poly_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8797	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s16)))
8798	int32x4_t vmulltq_int_m_s16(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
8799	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s16)))
8800	int32x4_t vmulltq_int_m(int32x4_t, int16x8_t, int16x8_t, mve_pred16_t);
8801	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s32)))
8802	int64x2_t vmulltq_int_m_s32(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
8803	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s32)))
8804	int64x2_t vmulltq_int_m(int64x2_t, int32x4_t, int32x4_t, mve_pred16_t);
8805	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s8)))
8806	int16x8_t vmulltq_int_m_s8(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
8807	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_s8)))
8808	int16x8_t vmulltq_int_m(int16x8_t, int8x16_t, int8x16_t, mve_pred16_t);
8809	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u16)))
8810	uint32x4_t vmulltq_int_m_u16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8811	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u16)))
8812	uint32x4_t vmulltq_int_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8813	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u32)))
8814	uint64x2_t vmulltq_int_m_u32(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8815	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u32)))
8816	uint64x2_t vmulltq_int_m(uint64x2_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8817	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u8)))
8818	uint16x8_t vmulltq_int_m_u8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8819	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_m_u8)))
8820	uint16x8_t vmulltq_int_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8821	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s16)))
8822	int32x4_t vmulltq_int_s16(int16x8_t, int16x8_t);
8823	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s16)))
8824	int32x4_t vmulltq_int(int16x8_t, int16x8_t);
8825	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s32)))
8826	int64x2_t vmulltq_int_s32(int32x4_t, int32x4_t);
8827	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s32)))
8828	int64x2_t vmulltq_int(int32x4_t, int32x4_t);
8829	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s8)))
8830	int16x8_t vmulltq_int_s8(int8x16_t, int8x16_t);
8831	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_s8)))
8832	int16x8_t vmulltq_int(int8x16_t, int8x16_t);
8833	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u16)))
8834	uint32x4_t vmulltq_int_u16(uint16x8_t, uint16x8_t);
8835	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u16)))
8836	uint32x4_t vmulltq_int(uint16x8_t, uint16x8_t);
8837	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u32)))
8838	uint64x2_t vmulltq_int_u32(uint32x4_t, uint32x4_t);
8839	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u32)))
8840	uint64x2_t vmulltq_int(uint32x4_t, uint32x4_t);
8841	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u8)))
8842	uint16x8_t vmulltq_int_u8(uint8x16_t, uint8x16_t);
8843	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_u8)))
8844	uint16x8_t vmulltq_int(uint8x16_t, uint8x16_t);
8845	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s16)))
8846	int32x4_t vmulltq_int_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8847	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s16)))
8848	int32x4_t vmulltq_int_x(int16x8_t, int16x8_t, mve_pred16_t);
8849	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s32)))
8850	int64x2_t vmulltq_int_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8851	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s32)))
8852	int64x2_t vmulltq_int_x(int32x4_t, int32x4_t, mve_pred16_t);
8853	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s8)))
8854	int16x8_t vmulltq_int_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8855	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_s8)))
8856	int16x8_t vmulltq_int_x(int8x16_t, int8x16_t, mve_pred16_t);
8857	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u16)))
8858	uint32x4_t vmulltq_int_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8859	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u16)))
8860	uint32x4_t vmulltq_int_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8861	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u32)))
8862	uint64x2_t vmulltq_int_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8863	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u32)))
8864	uint64x2_t vmulltq_int_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8865	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u8)))
8866	uint16x8_t vmulltq_int_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8867	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_int_x_u8)))
8868	uint16x8_t vmulltq_int_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8869	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p16)))
8870	uint32x4_t vmulltq_poly_m_p16(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8871	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p16)))
8872	uint32x4_t vmulltq_poly_m(uint32x4_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8873	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p8)))
8874	uint16x8_t vmulltq_poly_m_p8(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8875	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_m_p8)))
8876	uint16x8_t vmulltq_poly_m(uint16x8_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8877	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p16)))
8878	uint32x4_t vmulltq_poly_p16(uint16x8_t, uint16x8_t);
8879	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p16)))
8880	uint32x4_t vmulltq_poly(uint16x8_t, uint16x8_t);
8881	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p8)))
8882	uint16x8_t vmulltq_poly_p8(uint8x16_t, uint8x16_t);
8883	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_p8)))
8884	uint16x8_t vmulltq_poly(uint8x16_t, uint8x16_t);
8885	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p16)))
8886	uint32x4_t vmulltq_poly_x_p16(uint16x8_t, uint16x8_t, mve_pred16_t);
8887	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p16)))
8888	uint32x4_t vmulltq_poly_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8889	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p8)))
8890	uint16x8_t vmulltq_poly_x_p8(uint8x16_t, uint8x16_t, mve_pred16_t);
8891	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulltq_poly_x_p8)))
8892	uint16x8_t vmulltq_poly_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8893	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s16)))
8894	int16x8_t vmulq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8895	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s16)))
8896	int16x8_t vmulq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8897	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s32)))
8898	int32x4_t vmulq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8899	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s32)))
8900	int32x4_t vmulq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8901	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s8)))
8902	int8x16_t vmulq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8903	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_s8)))
8904	int8x16_t vmulq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8905	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u16)))
8906	uint16x8_t vmulq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8907	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u16)))
8908	uint16x8_t vmulq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8909	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u32)))
8910	uint32x4_t vmulq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8911	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u32)))
8912	uint32x4_t vmulq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8913	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u8)))
8914	uint8x16_t vmulq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8915	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_u8)))
8916	uint8x16_t vmulq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8917	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s16)))
8918	int16x8_t vmulq_s16(int16x8_t, int16x8_t);
8919	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s16)))
8920	int16x8_t vmulq(int16x8_t, int16x8_t);
8921	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s32)))
8922	int32x4_t vmulq_s32(int32x4_t, int32x4_t);
8923	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s32)))
8924	int32x4_t vmulq(int32x4_t, int32x4_t);
8925	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_s8)))
8926	int8x16_t vmulq_s8(int8x16_t, int8x16_t);
8927	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_s8)))
8928	int8x16_t vmulq(int8x16_t, int8x16_t);
8929	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u16)))
8930	uint16x8_t vmulq_u16(uint16x8_t, uint16x8_t);
8931	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u16)))
8932	uint16x8_t vmulq(uint16x8_t, uint16x8_t);
8933	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u32)))
8934	uint32x4_t vmulq_u32(uint32x4_t, uint32x4_t);
8935	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u32)))
8936	uint32x4_t vmulq(uint32x4_t, uint32x4_t);
8937	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_u8)))
8938	uint8x16_t vmulq_u8(uint8x16_t, uint8x16_t);
8939	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_u8)))
8940	uint8x16_t vmulq(uint8x16_t, uint8x16_t);
8941	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s16)))
8942	int16x8_t vmulq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
8943	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s16)))
8944	int16x8_t vmulq_x(int16x8_t, int16x8_t, mve_pred16_t);
8945	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s32)))
8946	int32x4_t vmulq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
8947	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s32)))
8948	int32x4_t vmulq_x(int32x4_t, int32x4_t, mve_pred16_t);
8949	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s8)))
8950	int8x16_t vmulq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
8951	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_s8)))
8952	int8x16_t vmulq_x(int8x16_t, int8x16_t, mve_pred16_t);
8953	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u16)))
8954	uint16x8_t vmulq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
8955	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u16)))
8956	uint16x8_t vmulq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
8957	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u32)))
8958	uint32x4_t vmulq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
8959	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u32)))
8960	uint32x4_t vmulq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
8961	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u8)))
8962	uint8x16_t vmulq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
8963	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_u8)))
8964	uint8x16_t vmulq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
8965	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s16)))
8966	int16x8_t vornq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8967	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s16)))
8968	int16x8_t vornq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
8969	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s32)))
8970	int32x4_t vornq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8971	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s32)))
8972	int32x4_t vornq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
8973	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s8)))
8974	int8x16_t vornq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8975	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_s8)))
8976	int8x16_t vornq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
8977	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u16)))
8978	uint16x8_t vornq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8979	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u16)))
8980	uint16x8_t vornq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
8981	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u32)))
8982	uint32x4_t vornq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8983	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u32)))
8984	uint32x4_t vornq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
8985	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u8)))
8986	uint8x16_t vornq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8987	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_u8)))
8988	uint8x16_t vornq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
8989	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s16)))
8990	int16x8_t vornq_s16(int16x8_t, int16x8_t);
8991	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s16)))
8992	int16x8_t vornq(int16x8_t, int16x8_t);
8993	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s32)))
8994	int32x4_t vornq_s32(int32x4_t, int32x4_t);
8995	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s32)))
8996	int32x4_t vornq(int32x4_t, int32x4_t);
8997	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_s8)))
8998	int8x16_t vornq_s8(int8x16_t, int8x16_t);
8999	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_s8)))
9000	int8x16_t vornq(int8x16_t, int8x16_t);
9001	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u16)))
9002	uint16x8_t vornq_u16(uint16x8_t, uint16x8_t);
9003	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u16)))
9004	uint16x8_t vornq(uint16x8_t, uint16x8_t);
9005	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u32)))
9006	uint32x4_t vornq_u32(uint32x4_t, uint32x4_t);
9007	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u32)))
9008	uint32x4_t vornq(uint32x4_t, uint32x4_t);
9009	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_u8)))
9010	uint8x16_t vornq_u8(uint8x16_t, uint8x16_t);
9011	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_u8)))
9012	uint8x16_t vornq(uint8x16_t, uint8x16_t);
9013	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s16)))
9014	int16x8_t vornq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
9015	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s16)))
9016	int16x8_t vornq_x(int16x8_t, int16x8_t, mve_pred16_t);
9017	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s32)))
9018	int32x4_t vornq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
9019	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s32)))
9020	int32x4_t vornq_x(int32x4_t, int32x4_t, mve_pred16_t);
9021	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s8)))
9022	int8x16_t vornq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
9023	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_s8)))
9024	int8x16_t vornq_x(int8x16_t, int8x16_t, mve_pred16_t);
9025	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u16)))
9026	uint16x8_t vornq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
9027	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u16)))
9028	uint16x8_t vornq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
9029	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u32)))
9030	uint32x4_t vornq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
9031	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u32)))
9032	uint32x4_t vornq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
9033	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u8)))
9034	uint8x16_t vornq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
9035	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_u8)))
9036	uint8x16_t vornq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
9037	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s16)))
9038	int16x8_t vorrq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9039	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s16)))
9040	int16x8_t vorrq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9041	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s32)))
9042	int32x4_t vorrq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9043	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s32)))
9044	int32x4_t vorrq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9045	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s8)))
9046	int8x16_t vorrq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9047	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_s8)))
9048	int8x16_t vorrq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9049	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u16)))
9050	uint16x8_t vorrq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9051	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u16)))
9052	uint16x8_t vorrq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9053	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u32)))
9054	uint32x4_t vorrq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9055	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u32)))
9056	uint32x4_t vorrq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9057	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u8)))
9058	uint8x16_t vorrq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9059	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_u8)))
9060	uint8x16_t vorrq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9061	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s16)))
9062	int16x8_t vorrq_s16(int16x8_t, int16x8_t);
9063	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s16)))
9064	int16x8_t vorrq(int16x8_t, int16x8_t);
9065	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s32)))
9066	int32x4_t vorrq_s32(int32x4_t, int32x4_t);
9067	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s32)))
9068	int32x4_t vorrq(int32x4_t, int32x4_t);
9069	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_s8)))
9070	int8x16_t vorrq_s8(int8x16_t, int8x16_t);
9071	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_s8)))
9072	int8x16_t vorrq(int8x16_t, int8x16_t);
9073	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u16)))
9074	uint16x8_t vorrq_u16(uint16x8_t, uint16x8_t);
9075	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u16)))
9076	uint16x8_t vorrq(uint16x8_t, uint16x8_t);
9077	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u32)))
9078	uint32x4_t vorrq_u32(uint32x4_t, uint32x4_t);
9079	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u32)))
9080	uint32x4_t vorrq(uint32x4_t, uint32x4_t);
9081	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_u8)))
9082	uint8x16_t vorrq_u8(uint8x16_t, uint8x16_t);
9083	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_u8)))
9084	uint8x16_t vorrq(uint8x16_t, uint8x16_t);
9085	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s16)))
9086	int16x8_t vorrq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
9087	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s16)))
9088	int16x8_t vorrq_x(int16x8_t, int16x8_t, mve_pred16_t);
9089	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s32)))
9090	int32x4_t vorrq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
9091	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s32)))
9092	int32x4_t vorrq_x(int32x4_t, int32x4_t, mve_pred16_t);
9093	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s8)))
9094	int8x16_t vorrq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
9095	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_s8)))
9096	int8x16_t vorrq_x(int8x16_t, int8x16_t, mve_pred16_t);
9097	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u16)))
9098	uint16x8_t vorrq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
9099	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u16)))
9100	uint16x8_t vorrq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
9101	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u32)))
9102	uint32x4_t vorrq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
9103	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u32)))
9104	uint32x4_t vorrq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
9105	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u8)))
9106	uint8x16_t vorrq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
9107	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_u8)))
9108	uint8x16_t vorrq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
9109	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpnot)))
9110	mve_pred16_t vpnot(mve_pred16_t);
9111	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s16)))
9112	int16x8_t vpselq_s16(int16x8_t, int16x8_t, mve_pred16_t);
9113	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s16)))
9114	int16x8_t vpselq(int16x8_t, int16x8_t, mve_pred16_t);
9115	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s32)))
9116	int32x4_t vpselq_s32(int32x4_t, int32x4_t, mve_pred16_t);
9117	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s32)))
9118	int32x4_t vpselq(int32x4_t, int32x4_t, mve_pred16_t);
9119	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s64)))
9120	int64x2_t vpselq_s64(int64x2_t, int64x2_t, mve_pred16_t);
9121	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s64)))
9122	int64x2_t vpselq(int64x2_t, int64x2_t, mve_pred16_t);
9123	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_s8)))
9124	int8x16_t vpselq_s8(int8x16_t, int8x16_t, mve_pred16_t);
9125	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_s8)))
9126	int8x16_t vpselq(int8x16_t, int8x16_t, mve_pred16_t);
9127	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u16)))
9128	uint16x8_t vpselq_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
9129	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u16)))
9130	uint16x8_t vpselq(uint16x8_t, uint16x8_t, mve_pred16_t);
9131	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u32)))
9132	uint32x4_t vpselq_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
9133	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u32)))
9134	uint32x4_t vpselq(uint32x4_t, uint32x4_t, mve_pred16_t);
9135	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u64)))
9136	uint64x2_t vpselq_u64(uint64x2_t, uint64x2_t, mve_pred16_t);
9137	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u64)))
9138	uint64x2_t vpselq(uint64x2_t, uint64x2_t, mve_pred16_t);
9139	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_u8)))
9140	uint8x16_t vpselq_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
9141	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_u8)))
9142	uint8x16_t vpselq(uint8x16_t, uint8x16_t, mve_pred16_t);
9143	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s16)))
9144	int16x8_t vqaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9145	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s16)))
9146	int16x8_t vqaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9147	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s32)))
9148	int32x4_t vqaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9149	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s32)))
9150	int32x4_t vqaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9151	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s8)))
9152	int8x16_t vqaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9153	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_s8)))
9154	int8x16_t vqaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9155	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u16)))
9156	uint16x8_t vqaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9157	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u16)))
9158	uint16x8_t vqaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9159	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u32)))
9160	uint32x4_t vqaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9161	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u32)))
9162	uint32x4_t vqaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9163	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u8)))
9164	uint8x16_t vqaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9165	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_m_u8)))
9166	uint8x16_t vqaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9167	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s16)))
9168	int16x8_t vqaddq_s16(int16x8_t, int16x8_t);
9169	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s16)))
9170	int16x8_t vqaddq(int16x8_t, int16x8_t);
9171	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s32)))
9172	int32x4_t vqaddq_s32(int32x4_t, int32x4_t);
9173	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s32)))
9174	int32x4_t vqaddq(int32x4_t, int32x4_t);
9175	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s8)))
9176	int8x16_t vqaddq_s8(int8x16_t, int8x16_t);
9177	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_s8)))
9178	int8x16_t vqaddq(int8x16_t, int8x16_t);
9179	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u16)))
9180	uint16x8_t vqaddq_u16(uint16x8_t, uint16x8_t);
9181	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u16)))
9182	uint16x8_t vqaddq(uint16x8_t, uint16x8_t);
9183	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u32)))
9184	uint32x4_t vqaddq_u32(uint32x4_t, uint32x4_t);
9185	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u32)))
9186	uint32x4_t vqaddq(uint32x4_t, uint32x4_t);
9187	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u8)))
9188	uint8x16_t vqaddq_u8(uint8x16_t, uint8x16_t);
9189	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqaddq_u8)))
9190	uint8x16_t vqaddq(uint8x16_t, uint8x16_t);
9191	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s16)))
9192	int16x8_t vqdmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9193	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s16)))
9194	int16x8_t vqdmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9195	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s32)))
9196	int32x4_t vqdmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9197	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s32)))
9198	int32x4_t vqdmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9199	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s8)))
9200	int8x16_t vqdmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9201	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_m_s8)))
9202	int8x16_t vqdmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9203	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s16)))
9204	int16x8_t vqdmulhq_s16(int16x8_t, int16x8_t);
9205	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s16)))
9206	int16x8_t vqdmulhq(int16x8_t, int16x8_t);
9207	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s32)))
9208	int32x4_t vqdmulhq_s32(int32x4_t, int32x4_t);
9209	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s32)))
9210	int32x4_t vqdmulhq(int32x4_t, int32x4_t);
9211	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s8)))
9212	int8x16_t vqdmulhq_s8(int8x16_t, int8x16_t);
9213	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqdmulhq_s8)))
9214	int8x16_t vqdmulhq(int8x16_t, int8x16_t);
9215	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s16)))
9216	int16x8_t vqrdmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9217	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s16)))
9218	int16x8_t vqrdmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9219	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s32)))
9220	int32x4_t vqrdmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9221	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s32)))
9222	int32x4_t vqrdmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9223	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s8)))
9224	int8x16_t vqrdmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9225	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_m_s8)))
9226	int8x16_t vqrdmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9227	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s16)))
9228	int16x8_t vqrdmulhq_s16(int16x8_t, int16x8_t);
9229	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s16)))
9230	int16x8_t vqrdmulhq(int16x8_t, int16x8_t);
9231	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s32)))
9232	int32x4_t vqrdmulhq_s32(int32x4_t, int32x4_t);
9233	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s32)))
9234	int32x4_t vqrdmulhq(int32x4_t, int32x4_t);
9235	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s8)))
9236	int8x16_t vqrdmulhq_s8(int8x16_t, int8x16_t);
9237	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrdmulhq_s8)))
9238	int8x16_t vqrdmulhq(int8x16_t, int8x16_t);
9239	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s16)))
9240	int16x8_t vqrshlq_m_n_s16(int16x8_t, int32_t, mve_pred16_t);
9241	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s16)))
9242	int16x8_t vqrshlq_m_n(int16x8_t, int32_t, mve_pred16_t);
9243	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s32)))
9244	int32x4_t vqrshlq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
9245	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s32)))
9246	int32x4_t vqrshlq_m_n(int32x4_t, int32_t, mve_pred16_t);
9247	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s8)))
9248	int8x16_t vqrshlq_m_n_s8(int8x16_t, int32_t, mve_pred16_t);
9249	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_s8)))
9250	int8x16_t vqrshlq_m_n(int8x16_t, int32_t, mve_pred16_t);
9251	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u16)))
9252	uint16x8_t vqrshlq_m_n_u16(uint16x8_t, int32_t, mve_pred16_t);
9253	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u16)))
9254	uint16x8_t vqrshlq_m_n(uint16x8_t, int32_t, mve_pred16_t);
9255	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u32)))
9256	uint32x4_t vqrshlq_m_n_u32(uint32x4_t, int32_t, mve_pred16_t);
9257	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u32)))
9258	uint32x4_t vqrshlq_m_n(uint32x4_t, int32_t, mve_pred16_t);
9259	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u8)))
9260	uint8x16_t vqrshlq_m_n_u8(uint8x16_t, int32_t, mve_pred16_t);
9261	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_n_u8)))
9262	uint8x16_t vqrshlq_m_n(uint8x16_t, int32_t, mve_pred16_t);
9263	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s16)))
9264	int16x8_t vqrshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9265	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s16)))
9266	int16x8_t vqrshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9267	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s32)))
9268	int32x4_t vqrshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9269	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s32)))
9270	int32x4_t vqrshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9271	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s8)))
9272	int8x16_t vqrshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9273	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_s8)))
9274	int8x16_t vqrshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9275	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u16)))
9276	uint16x8_t vqrshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
9277	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u16)))
9278	uint16x8_t vqrshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
9279	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u32)))
9280	uint32x4_t vqrshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
9281	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u32)))
9282	uint32x4_t vqrshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
9283	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u8)))
9284	uint8x16_t vqrshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
9285	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_m_u8)))
9286	uint8x16_t vqrshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
9287	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s16)))
9288	int16x8_t vqrshlq_n_s16(int16x8_t, int32_t);
9289	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s16)))
9290	int16x8_t vqrshlq(int16x8_t, int32_t);
9291	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s32)))
9292	int32x4_t vqrshlq_n_s32(int32x4_t, int32_t);
9293	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s32)))
9294	int32x4_t vqrshlq(int32x4_t, int32_t);
9295	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s8)))
9296	int8x16_t vqrshlq_n_s8(int8x16_t, int32_t);
9297	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_s8)))
9298	int8x16_t vqrshlq(int8x16_t, int32_t);
9299	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u16)))
9300	uint16x8_t vqrshlq_n_u16(uint16x8_t, int32_t);
9301	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u16)))
9302	uint16x8_t vqrshlq(uint16x8_t, int32_t);
9303	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u32)))
9304	uint32x4_t vqrshlq_n_u32(uint32x4_t, int32_t);
9305	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u32)))
9306	uint32x4_t vqrshlq(uint32x4_t, int32_t);
9307	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u8)))
9308	uint8x16_t vqrshlq_n_u8(uint8x16_t, int32_t);
9309	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_n_u8)))
9310	uint8x16_t vqrshlq(uint8x16_t, int32_t);
9311	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s16)))
9312	int16x8_t vqrshlq_s16(int16x8_t, int16x8_t);
9313	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s16)))
9314	int16x8_t vqrshlq(int16x8_t, int16x8_t);
9315	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s32)))
9316	int32x4_t vqrshlq_s32(int32x4_t, int32x4_t);
9317	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s32)))
9318	int32x4_t vqrshlq(int32x4_t, int32x4_t);
9319	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s8)))
9320	int8x16_t vqrshlq_s8(int8x16_t, int8x16_t);
9321	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_s8)))
9322	int8x16_t vqrshlq(int8x16_t, int8x16_t);
9323	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u16)))
9324	uint16x8_t vqrshlq_u16(uint16x8_t, int16x8_t);
9325	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u16)))
9326	uint16x8_t vqrshlq(uint16x8_t, int16x8_t);
9327	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u32)))
9328	uint32x4_t vqrshlq_u32(uint32x4_t, int32x4_t);
9329	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u32)))
9330	uint32x4_t vqrshlq(uint32x4_t, int32x4_t);
9331	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u8)))
9332	uint8x16_t vqrshlq_u8(uint8x16_t, int8x16_t);
9333	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshlq_u8)))
9334	uint8x16_t vqrshlq(uint8x16_t, int8x16_t);
9335	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s16)))
9336	int8x16_t vqrshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
9337	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s16)))
9338	int8x16_t vqrshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
9339	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s32)))
9340	int16x8_t vqrshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
9341	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_s32)))
9342	int16x8_t vqrshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
9343	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u16)))
9344	uint8x16_t vqrshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9345	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u16)))
9346	uint8x16_t vqrshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9347	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u32)))
9348	uint16x8_t vqrshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9349	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_m_n_u32)))
9350	uint16x8_t vqrshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9351	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s16)))
9352	int8x16_t vqrshrnbq_n_s16(int8x16_t, int16x8_t, int);
9353	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s16)))
9354	int8x16_t vqrshrnbq(int8x16_t, int16x8_t, int);
9355	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s32)))
9356	int16x8_t vqrshrnbq_n_s32(int16x8_t, int32x4_t, int);
9357	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_s32)))
9358	int16x8_t vqrshrnbq(int16x8_t, int32x4_t, int);
9359	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u16)))
9360	uint8x16_t vqrshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
9361	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u16)))
9362	uint8x16_t vqrshrnbq(uint8x16_t, uint16x8_t, int);
9363	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u32)))
9364	uint16x8_t vqrshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
9365	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrnbq_n_u32)))
9366	uint16x8_t vqrshrnbq(uint16x8_t, uint32x4_t, int);
9367	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s16)))
9368	int8x16_t vqrshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
9369	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s16)))
9370	int8x16_t vqrshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
9371	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s32)))
9372	int16x8_t vqrshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
9373	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_s32)))
9374	int16x8_t vqrshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
9375	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u16)))
9376	uint8x16_t vqrshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9377	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u16)))
9378	uint8x16_t vqrshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9379	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u32)))
9380	uint16x8_t vqrshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9381	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_m_n_u32)))
9382	uint16x8_t vqrshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9383	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s16)))
9384	int8x16_t vqrshrntq_n_s16(int8x16_t, int16x8_t, int);
9385	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s16)))
9386	int8x16_t vqrshrntq(int8x16_t, int16x8_t, int);
9387	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s32)))
9388	int16x8_t vqrshrntq_n_s32(int16x8_t, int32x4_t, int);
9389	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_s32)))
9390	int16x8_t vqrshrntq(int16x8_t, int32x4_t, int);
9391	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u16)))
9392	uint8x16_t vqrshrntq_n_u16(uint8x16_t, uint16x8_t, int);
9393	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u16)))
9394	uint8x16_t vqrshrntq(uint8x16_t, uint16x8_t, int);
9395	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u32)))
9396	uint16x8_t vqrshrntq_n_u32(uint16x8_t, uint32x4_t, int);
9397	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrntq_n_u32)))
9398	uint16x8_t vqrshrntq(uint16x8_t, uint32x4_t, int);
9399	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s16)))
9400	uint8x16_t vqrshrunbq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
9401	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s16)))
9402	uint8x16_t vqrshrunbq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
9403	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s32)))
9404	uint16x8_t vqrshrunbq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
9405	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_m_n_s32)))
9406	uint16x8_t vqrshrunbq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
9407	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s16)))
9408	uint8x16_t vqrshrunbq_n_s16(uint8x16_t, int16x8_t, int);
9409	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s16)))
9410	uint8x16_t vqrshrunbq(uint8x16_t, int16x8_t, int);
9411	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s32)))
9412	uint16x8_t vqrshrunbq_n_s32(uint16x8_t, int32x4_t, int);
9413	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshrunbq_n_s32)))
9414	uint16x8_t vqrshrunbq(uint16x8_t, int32x4_t, int);
9415	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s16)))
9416	uint8x16_t vqrshruntq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
9417	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s16)))
9418	uint8x16_t vqrshruntq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
9419	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s32)))
9420	uint16x8_t vqrshruntq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
9421	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_m_n_s32)))
9422	uint16x8_t vqrshruntq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
9423	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s16)))
9424	uint8x16_t vqrshruntq_n_s16(uint8x16_t, int16x8_t, int);
9425	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s16)))
9426	uint8x16_t vqrshruntq(uint8x16_t, int16x8_t, int);
9427	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s32)))
9428	uint16x8_t vqrshruntq_n_s32(uint16x8_t, int32x4_t, int);
9429	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqrshruntq_n_s32)))
9430	uint16x8_t vqrshruntq(uint16x8_t, int32x4_t, int);
9431	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s16)))
9432	int16x8_t vqshlq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
9433	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s16)))
9434	int16x8_t vqshlq_m_n(int16x8_t, int16x8_t, int, mve_pred16_t);
9435	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s32)))
9436	int32x4_t vqshlq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
9437	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s32)))
9438	int32x4_t vqshlq_m_n(int32x4_t, int32x4_t, int, mve_pred16_t);
9439	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s8)))
9440	int8x16_t vqshlq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
9441	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_s8)))
9442	int8x16_t vqshlq_m_n(int8x16_t, int8x16_t, int, mve_pred16_t);
9443	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u16)))
9444	uint16x8_t vqshlq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
9445	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u16)))
9446	uint16x8_t vqshlq_m_n(uint16x8_t, uint16x8_t, int, mve_pred16_t);
9447	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u32)))
9448	uint32x4_t vqshlq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
9449	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u32)))
9450	uint32x4_t vqshlq_m_n(uint32x4_t, uint32x4_t, int, mve_pred16_t);
9451	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u8)))
9452	uint8x16_t vqshlq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
9453	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_n_u8)))
9454	uint8x16_t vqshlq_m_n(uint8x16_t, uint8x16_t, int, mve_pred16_t);
9455	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s16)))
9456	int16x8_t vqshlq_m_r_s16(int16x8_t, int32_t, mve_pred16_t);
9457	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s16)))
9458	int16x8_t vqshlq_m_r(int16x8_t, int32_t, mve_pred16_t);
9459	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s32)))
9460	int32x4_t vqshlq_m_r_s32(int32x4_t, int32_t, mve_pred16_t);
9461	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s32)))
9462	int32x4_t vqshlq_m_r(int32x4_t, int32_t, mve_pred16_t);
9463	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s8)))
9464	int8x16_t vqshlq_m_r_s8(int8x16_t, int32_t, mve_pred16_t);
9465	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_s8)))
9466	int8x16_t vqshlq_m_r(int8x16_t, int32_t, mve_pred16_t);
9467	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u16)))
9468	uint16x8_t vqshlq_m_r_u16(uint16x8_t, int32_t, mve_pred16_t);
9469	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u16)))
9470	uint16x8_t vqshlq_m_r(uint16x8_t, int32_t, mve_pred16_t);
9471	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u32)))
9472	uint32x4_t vqshlq_m_r_u32(uint32x4_t, int32_t, mve_pred16_t);
9473	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u32)))
9474	uint32x4_t vqshlq_m_r(uint32x4_t, int32_t, mve_pred16_t);
9475	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u8)))
9476	uint8x16_t vqshlq_m_r_u8(uint8x16_t, int32_t, mve_pred16_t);
9477	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_r_u8)))
9478	uint8x16_t vqshlq_m_r(uint8x16_t, int32_t, mve_pred16_t);
9479	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s16)))
9480	int16x8_t vqshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9481	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s16)))
9482	int16x8_t vqshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9483	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s32)))
9484	int32x4_t vqshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9485	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s32)))
9486	int32x4_t vqshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9487	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s8)))
9488	int8x16_t vqshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9489	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_s8)))
9490	int8x16_t vqshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9491	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u16)))
9492	uint16x8_t vqshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
9493	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u16)))
9494	uint16x8_t vqshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
9495	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u32)))
9496	uint32x4_t vqshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
9497	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u32)))
9498	uint32x4_t vqshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
9499	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u8)))
9500	uint8x16_t vqshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
9501	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_m_u8)))
9502	uint8x16_t vqshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
9503	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s16)))
9504	int16x8_t vqshlq_n_s16(int16x8_t, int);
9505	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s16)))
9506	int16x8_t vqshlq_n(int16x8_t, int);
9507	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s32)))
9508	int32x4_t vqshlq_n_s32(int32x4_t, int);
9509	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s32)))
9510	int32x4_t vqshlq_n(int32x4_t, int);
9511	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s8)))
9512	int8x16_t vqshlq_n_s8(int8x16_t, int);
9513	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_s8)))
9514	int8x16_t vqshlq_n(int8x16_t, int);
9515	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u16)))
9516	uint16x8_t vqshlq_n_u16(uint16x8_t, int);
9517	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u16)))
9518	uint16x8_t vqshlq_n(uint16x8_t, int);
9519	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u32)))
9520	uint32x4_t vqshlq_n_u32(uint32x4_t, int);
9521	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u32)))
9522	uint32x4_t vqshlq_n(uint32x4_t, int);
9523	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u8)))
9524	uint8x16_t vqshlq_n_u8(uint8x16_t, int);
9525	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_n_u8)))
9526	uint8x16_t vqshlq_n(uint8x16_t, int);
9527	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s16)))
9528	int16x8_t vqshlq_r_s16(int16x8_t, int32_t);
9529	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s16)))
9530	int16x8_t vqshlq_r(int16x8_t, int32_t);
9531	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s32)))
9532	int32x4_t vqshlq_r_s32(int32x4_t, int32_t);
9533	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s32)))
9534	int32x4_t vqshlq_r(int32x4_t, int32_t);
9535	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s8)))
9536	int8x16_t vqshlq_r_s8(int8x16_t, int32_t);
9537	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_s8)))
9538	int8x16_t vqshlq_r(int8x16_t, int32_t);
9539	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u16)))
9540	uint16x8_t vqshlq_r_u16(uint16x8_t, int32_t);
9541	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u16)))
9542	uint16x8_t vqshlq_r(uint16x8_t, int32_t);
9543	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u32)))
9544	uint32x4_t vqshlq_r_u32(uint32x4_t, int32_t);
9545	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u32)))
9546	uint32x4_t vqshlq_r(uint32x4_t, int32_t);
9547	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u8)))
9548	uint8x16_t vqshlq_r_u8(uint8x16_t, int32_t);
9549	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_r_u8)))
9550	uint8x16_t vqshlq_r(uint8x16_t, int32_t);
9551	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s16)))
9552	int16x8_t vqshlq_s16(int16x8_t, int16x8_t);
9553	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s16)))
9554	int16x8_t vqshlq(int16x8_t, int16x8_t);
9555	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s32)))
9556	int32x4_t vqshlq_s32(int32x4_t, int32x4_t);
9557	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s32)))
9558	int32x4_t vqshlq(int32x4_t, int32x4_t);
9559	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s8)))
9560	int8x16_t vqshlq_s8(int8x16_t, int8x16_t);
9561	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_s8)))
9562	int8x16_t vqshlq(int8x16_t, int8x16_t);
9563	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u16)))
9564	uint16x8_t vqshlq_u16(uint16x8_t, int16x8_t);
9565	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u16)))
9566	uint16x8_t vqshlq(uint16x8_t, int16x8_t);
9567	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u32)))
9568	uint32x4_t vqshlq_u32(uint32x4_t, int32x4_t);
9569	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u32)))
9570	uint32x4_t vqshlq(uint32x4_t, int32x4_t);
9571	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u8)))
9572	uint8x16_t vqshlq_u8(uint8x16_t, int8x16_t);
9573	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshlq_u8)))
9574	uint8x16_t vqshlq(uint8x16_t, int8x16_t);
9575	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s16)))
9576	uint16x8_t vqshluq_m_n_s16(uint16x8_t, int16x8_t, int, mve_pred16_t);
9577	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s16)))
9578	uint16x8_t vqshluq_m(uint16x8_t, int16x8_t, int, mve_pred16_t);
9579	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s32)))
9580	uint32x4_t vqshluq_m_n_s32(uint32x4_t, int32x4_t, int, mve_pred16_t);
9581	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s32)))
9582	uint32x4_t vqshluq_m(uint32x4_t, int32x4_t, int, mve_pred16_t);
9583	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s8)))
9584	uint8x16_t vqshluq_m_n_s8(uint8x16_t, int8x16_t, int, mve_pred16_t);
9585	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_m_n_s8)))
9586	uint8x16_t vqshluq_m(uint8x16_t, int8x16_t, int, mve_pred16_t);
9587	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s16)))
9588	uint16x8_t vqshluq_n_s16(int16x8_t, int);
9589	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s16)))
9590	uint16x8_t vqshluq(int16x8_t, int);
9591	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s32)))
9592	uint32x4_t vqshluq_n_s32(int32x4_t, int);
9593	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s32)))
9594	uint32x4_t vqshluq(int32x4_t, int);
9595	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s8)))
9596	uint8x16_t vqshluq_n_s8(int8x16_t, int);
9597	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshluq_n_s8)))
9598	uint8x16_t vqshluq(int8x16_t, int);
9599	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s16)))
9600	int8x16_t vqshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
9601	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s16)))
9602	int8x16_t vqshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
9603	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s32)))
9604	int16x8_t vqshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
9605	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_s32)))
9606	int16x8_t vqshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
9607	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u16)))
9608	uint8x16_t vqshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9609	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u16)))
9610	uint8x16_t vqshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9611	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u32)))
9612	uint16x8_t vqshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9613	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_m_n_u32)))
9614	uint16x8_t vqshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9615	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s16)))
9616	int8x16_t vqshrnbq_n_s16(int8x16_t, int16x8_t, int);
9617	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s16)))
9618	int8x16_t vqshrnbq(int8x16_t, int16x8_t, int);
9619	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s32)))
9620	int16x8_t vqshrnbq_n_s32(int16x8_t, int32x4_t, int);
9621	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_s32)))
9622	int16x8_t vqshrnbq(int16x8_t, int32x4_t, int);
9623	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u16)))
9624	uint8x16_t vqshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
9625	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u16)))
9626	uint8x16_t vqshrnbq(uint8x16_t, uint16x8_t, int);
9627	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u32)))
9628	uint16x8_t vqshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
9629	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrnbq_n_u32)))
9630	uint16x8_t vqshrnbq(uint16x8_t, uint32x4_t, int);
9631	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s16)))
9632	int8x16_t vqshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
9633	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s16)))
9634	int8x16_t vqshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
9635	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s32)))
9636	int16x8_t vqshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
9637	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_s32)))
9638	int16x8_t vqshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
9639	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u16)))
9640	uint8x16_t vqshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9641	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u16)))
9642	uint8x16_t vqshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
9643	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u32)))
9644	uint16x8_t vqshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9645	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_m_n_u32)))
9646	uint16x8_t vqshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
9647	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s16)))
9648	int8x16_t vqshrntq_n_s16(int8x16_t, int16x8_t, int);
9649	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s16)))
9650	int8x16_t vqshrntq(int8x16_t, int16x8_t, int);
9651	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s32)))
9652	int16x8_t vqshrntq_n_s32(int16x8_t, int32x4_t, int);
9653	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_s32)))
9654	int16x8_t vqshrntq(int16x8_t, int32x4_t, int);
9655	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u16)))
9656	uint8x16_t vqshrntq_n_u16(uint8x16_t, uint16x8_t, int);
9657	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u16)))
9658	uint8x16_t vqshrntq(uint8x16_t, uint16x8_t, int);
9659	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u32)))
9660	uint16x8_t vqshrntq_n_u32(uint16x8_t, uint32x4_t, int);
9661	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrntq_n_u32)))
9662	uint16x8_t vqshrntq(uint16x8_t, uint32x4_t, int);
9663	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s16)))
9664	uint8x16_t vqshrunbq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
9665	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s16)))
9666	uint8x16_t vqshrunbq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
9667	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s32)))
9668	uint16x8_t vqshrunbq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
9669	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_m_n_s32)))
9670	uint16x8_t vqshrunbq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
9671	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s16)))
9672	uint8x16_t vqshrunbq_n_s16(uint8x16_t, int16x8_t, int);
9673	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s16)))
9674	uint8x16_t vqshrunbq(uint8x16_t, int16x8_t, int);
9675	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s32)))
9676	uint16x8_t vqshrunbq_n_s32(uint16x8_t, int32x4_t, int);
9677	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshrunbq_n_s32)))
9678	uint16x8_t vqshrunbq(uint16x8_t, int32x4_t, int);
9679	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s16)))
9680	uint8x16_t vqshruntq_m_n_s16(uint8x16_t, int16x8_t, int, mve_pred16_t);
9681	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s16)))
9682	uint8x16_t vqshruntq_m(uint8x16_t, int16x8_t, int, mve_pred16_t);
9683	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s32)))
9684	uint16x8_t vqshruntq_m_n_s32(uint16x8_t, int32x4_t, int, mve_pred16_t);
9685	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_m_n_s32)))
9686	uint16x8_t vqshruntq_m(uint16x8_t, int32x4_t, int, mve_pred16_t);
9687	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s16)))
9688	uint8x16_t vqshruntq_n_s16(uint8x16_t, int16x8_t, int);
9689	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s16)))
9690	uint8x16_t vqshruntq(uint8x16_t, int16x8_t, int);
9691	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s32)))
9692	uint16x8_t vqshruntq_n_s32(uint16x8_t, int32x4_t, int);
9693	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqshruntq_n_s32)))
9694	uint16x8_t vqshruntq(uint16x8_t, int32x4_t, int);
9695	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s16)))
9696	int16x8_t vqsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9697	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s16)))
9698	int16x8_t vqsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9699	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s32)))
9700	int32x4_t vqsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9701	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s32)))
9702	int32x4_t vqsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9703	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s8)))
9704	int8x16_t vqsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9705	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_s8)))
9706	int8x16_t vqsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9707	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u16)))
9708	uint16x8_t vqsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9709	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u16)))
9710	uint16x8_t vqsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9711	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u32)))
9712	uint32x4_t vqsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9713	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u32)))
9714	uint32x4_t vqsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9715	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u8)))
9716	uint8x16_t vqsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9717	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_m_u8)))
9718	uint8x16_t vqsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9719	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s16)))
9720	int16x8_t vqsubq_s16(int16x8_t, int16x8_t);
9721	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s16)))
9722	int16x8_t vqsubq(int16x8_t, int16x8_t);
9723	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s32)))
9724	int32x4_t vqsubq_s32(int32x4_t, int32x4_t);
9725	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s32)))
9726	int32x4_t vqsubq(int32x4_t, int32x4_t);
9727	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s8)))
9728	int8x16_t vqsubq_s8(int8x16_t, int8x16_t);
9729	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_s8)))
9730	int8x16_t vqsubq(int8x16_t, int8x16_t);
9731	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u16)))
9732	uint16x8_t vqsubq_u16(uint16x8_t, uint16x8_t);
9733	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u16)))
9734	uint16x8_t vqsubq(uint16x8_t, uint16x8_t);
9735	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u32)))
9736	uint32x4_t vqsubq_u32(uint32x4_t, uint32x4_t);
9737	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u32)))
9738	uint32x4_t vqsubq(uint32x4_t, uint32x4_t);
9739	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u8)))
9740	uint8x16_t vqsubq_u8(uint8x16_t, uint8x16_t);
9741	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vqsubq_u8)))
9742	uint8x16_t vqsubq(uint8x16_t, uint8x16_t);
9743	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s32)))
9744	int16x8_t vreinterpretq_s16_s32(int32x4_t);
9745	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s32)))
9746	int16x8_t vreinterpretq_s16(int32x4_t);
9747	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s64)))
9748	int16x8_t vreinterpretq_s16_s64(int64x2_t);
9749	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s64)))
9750	int16x8_t vreinterpretq_s16(int64x2_t);
9751	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s8)))
9752	int16x8_t vreinterpretq_s16_s8(int8x16_t);
9753	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_s8)))
9754	int16x8_t vreinterpretq_s16(int8x16_t);
9755	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u16)))
9756	int16x8_t vreinterpretq_s16_u16(uint16x8_t);
9757	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u16)))
9758	int16x8_t vreinterpretq_s16(uint16x8_t);
9759	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u32)))
9760	int16x8_t vreinterpretq_s16_u32(uint32x4_t);
9761	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u32)))
9762	int16x8_t vreinterpretq_s16(uint32x4_t);
9763	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u64)))
9764	int16x8_t vreinterpretq_s16_u64(uint64x2_t);
9765	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u64)))
9766	int16x8_t vreinterpretq_s16(uint64x2_t);
9767	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u8)))
9768	int16x8_t vreinterpretq_s16_u8(uint8x16_t);
9769	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_u8)))
9770	int16x8_t vreinterpretq_s16(uint8x16_t);
9771	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s16)))
9772	int32x4_t vreinterpretq_s32_s16(int16x8_t);
9773	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s16)))
9774	int32x4_t vreinterpretq_s32(int16x8_t);
9775	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s64)))
9776	int32x4_t vreinterpretq_s32_s64(int64x2_t);
9777	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s64)))
9778	int32x4_t vreinterpretq_s32(int64x2_t);
9779	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s8)))
9780	int32x4_t vreinterpretq_s32_s8(int8x16_t);
9781	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_s8)))
9782	int32x4_t vreinterpretq_s32(int8x16_t);
9783	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u16)))
9784	int32x4_t vreinterpretq_s32_u16(uint16x8_t);
9785	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u16)))
9786	int32x4_t vreinterpretq_s32(uint16x8_t);
9787	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u32)))
9788	int32x4_t vreinterpretq_s32_u32(uint32x4_t);
9789	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u32)))
9790	int32x4_t vreinterpretq_s32(uint32x4_t);
9791	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u64)))
9792	int32x4_t vreinterpretq_s32_u64(uint64x2_t);
9793	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u64)))
9794	int32x4_t vreinterpretq_s32(uint64x2_t);
9795	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u8)))
9796	int32x4_t vreinterpretq_s32_u8(uint8x16_t);
9797	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_u8)))
9798	int32x4_t vreinterpretq_s32(uint8x16_t);
9799	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s16)))
9800	int64x2_t vreinterpretq_s64_s16(int16x8_t);
9801	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s16)))
9802	int64x2_t vreinterpretq_s64(int16x8_t);
9803	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s32)))
9804	int64x2_t vreinterpretq_s64_s32(int32x4_t);
9805	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s32)))
9806	int64x2_t vreinterpretq_s64(int32x4_t);
9807	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s8)))
9808	int64x2_t vreinterpretq_s64_s8(int8x16_t);
9809	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_s8)))
9810	int64x2_t vreinterpretq_s64(int8x16_t);
9811	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u16)))
9812	int64x2_t vreinterpretq_s64_u16(uint16x8_t);
9813	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u16)))
9814	int64x2_t vreinterpretq_s64(uint16x8_t);
9815	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u32)))
9816	int64x2_t vreinterpretq_s64_u32(uint32x4_t);
9817	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u32)))
9818	int64x2_t vreinterpretq_s64(uint32x4_t);
9819	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u64)))
9820	int64x2_t vreinterpretq_s64_u64(uint64x2_t);
9821	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u64)))
9822	int64x2_t vreinterpretq_s64(uint64x2_t);
9823	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u8)))
9824	int64x2_t vreinterpretq_s64_u8(uint8x16_t);
9825	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_u8)))
9826	int64x2_t vreinterpretq_s64(uint8x16_t);
9827	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s16)))
9828	int8x16_t vreinterpretq_s8_s16(int16x8_t);
9829	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s16)))
9830	int8x16_t vreinterpretq_s8(int16x8_t);
9831	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s32)))
9832	int8x16_t vreinterpretq_s8_s32(int32x4_t);
9833	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s32)))
9834	int8x16_t vreinterpretq_s8(int32x4_t);
9835	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s64)))
9836	int8x16_t vreinterpretq_s8_s64(int64x2_t);
9837	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_s64)))
9838	int8x16_t vreinterpretq_s8(int64x2_t);
9839	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u16)))
9840	int8x16_t vreinterpretq_s8_u16(uint16x8_t);
9841	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u16)))
9842	int8x16_t vreinterpretq_s8(uint16x8_t);
9843	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u32)))
9844	int8x16_t vreinterpretq_s8_u32(uint32x4_t);
9845	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u32)))
9846	int8x16_t vreinterpretq_s8(uint32x4_t);
9847	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u64)))
9848	int8x16_t vreinterpretq_s8_u64(uint64x2_t);
9849	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u64)))
9850	int8x16_t vreinterpretq_s8(uint64x2_t);
9851	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u8)))
9852	int8x16_t vreinterpretq_s8_u8(uint8x16_t);
9853	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_u8)))
9854	int8x16_t vreinterpretq_s8(uint8x16_t);
9855	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s16)))
9856	uint16x8_t vreinterpretq_u16_s16(int16x8_t);
9857	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s16)))
9858	uint16x8_t vreinterpretq_u16(int16x8_t);
9859	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s32)))
9860	uint16x8_t vreinterpretq_u16_s32(int32x4_t);
9861	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s32)))
9862	uint16x8_t vreinterpretq_u16(int32x4_t);
9863	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s64)))
9864	uint16x8_t vreinterpretq_u16_s64(int64x2_t);
9865	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s64)))
9866	uint16x8_t vreinterpretq_u16(int64x2_t);
9867	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s8)))
9868	uint16x8_t vreinterpretq_u16_s8(int8x16_t);
9869	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_s8)))
9870	uint16x8_t vreinterpretq_u16(int8x16_t);
9871	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u32)))
9872	uint16x8_t vreinterpretq_u16_u32(uint32x4_t);
9873	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u32)))
9874	uint16x8_t vreinterpretq_u16(uint32x4_t);
9875	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u64)))
9876	uint16x8_t vreinterpretq_u16_u64(uint64x2_t);
9877	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u64)))
9878	uint16x8_t vreinterpretq_u16(uint64x2_t);
9879	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u8)))
9880	uint16x8_t vreinterpretq_u16_u8(uint8x16_t);
9881	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_u8)))
9882	uint16x8_t vreinterpretq_u16(uint8x16_t);
9883	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s16)))
9884	uint32x4_t vreinterpretq_u32_s16(int16x8_t);
9885	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s16)))
9886	uint32x4_t vreinterpretq_u32(int16x8_t);
9887	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s32)))
9888	uint32x4_t vreinterpretq_u32_s32(int32x4_t);
9889	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s32)))
9890	uint32x4_t vreinterpretq_u32(int32x4_t);
9891	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s64)))
9892	uint32x4_t vreinterpretq_u32_s64(int64x2_t);
9893	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s64)))
9894	uint32x4_t vreinterpretq_u32(int64x2_t);
9895	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s8)))
9896	uint32x4_t vreinterpretq_u32_s8(int8x16_t);
9897	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_s8)))
9898	uint32x4_t vreinterpretq_u32(int8x16_t);
9899	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u16)))
9900	uint32x4_t vreinterpretq_u32_u16(uint16x8_t);
9901	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u16)))
9902	uint32x4_t vreinterpretq_u32(uint16x8_t);
9903	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u64)))
9904	uint32x4_t vreinterpretq_u32_u64(uint64x2_t);
9905	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u64)))
9906	uint32x4_t vreinterpretq_u32(uint64x2_t);
9907	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u8)))
9908	uint32x4_t vreinterpretq_u32_u8(uint8x16_t);
9909	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_u8)))
9910	uint32x4_t vreinterpretq_u32(uint8x16_t);
9911	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s16)))
9912	uint64x2_t vreinterpretq_u64_s16(int16x8_t);
9913	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s16)))
9914	uint64x2_t vreinterpretq_u64(int16x8_t);
9915	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s32)))
9916	uint64x2_t vreinterpretq_u64_s32(int32x4_t);
9917	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s32)))
9918	uint64x2_t vreinterpretq_u64(int32x4_t);
9919	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s64)))
9920	uint64x2_t vreinterpretq_u64_s64(int64x2_t);
9921	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s64)))
9922	uint64x2_t vreinterpretq_u64(int64x2_t);
9923	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s8)))
9924	uint64x2_t vreinterpretq_u64_s8(int8x16_t);
9925	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_s8)))
9926	uint64x2_t vreinterpretq_u64(int8x16_t);
9927	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u16)))
9928	uint64x2_t vreinterpretq_u64_u16(uint16x8_t);
9929	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u16)))
9930	uint64x2_t vreinterpretq_u64(uint16x8_t);
9931	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u32)))
9932	uint64x2_t vreinterpretq_u64_u32(uint32x4_t);
9933	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u32)))
9934	uint64x2_t vreinterpretq_u64(uint32x4_t);
9935	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u8)))
9936	uint64x2_t vreinterpretq_u64_u8(uint8x16_t);
9937	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_u8)))
9938	uint64x2_t vreinterpretq_u64(uint8x16_t);
9939	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s16)))
9940	uint8x16_t vreinterpretq_u8_s16(int16x8_t);
9941	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s16)))
9942	uint8x16_t vreinterpretq_u8(int16x8_t);
9943	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s32)))
9944	uint8x16_t vreinterpretq_u8_s32(int32x4_t);
9945	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s32)))
9946	uint8x16_t vreinterpretq_u8(int32x4_t);
9947	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s64)))
9948	uint8x16_t vreinterpretq_u8_s64(int64x2_t);
9949	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s64)))
9950	uint8x16_t vreinterpretq_u8(int64x2_t);
9951	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s8)))
9952	uint8x16_t vreinterpretq_u8_s8(int8x16_t);
9953	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_s8)))
9954	uint8x16_t vreinterpretq_u8(int8x16_t);
9955	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u16)))
9956	uint8x16_t vreinterpretq_u8_u16(uint16x8_t);
9957	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u16)))
9958	uint8x16_t vreinterpretq_u8(uint16x8_t);
9959	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u32)))
9960	uint8x16_t vreinterpretq_u8_u32(uint32x4_t);
9961	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u32)))
9962	uint8x16_t vreinterpretq_u8(uint32x4_t);
9963	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u64)))
9964	uint8x16_t vreinterpretq_u8_u64(uint64x2_t);
9965	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_u64)))
9966	uint8x16_t vreinterpretq_u8(uint64x2_t);
9967	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s16)))
9968	int16x8_t vrhaddq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9969	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s16)))
9970	int16x8_t vrhaddq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
9971	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s32)))
9972	int32x4_t vrhaddq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9973	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s32)))
9974	int32x4_t vrhaddq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
9975	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s8)))
9976	int8x16_t vrhaddq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9977	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_s8)))
9978	int8x16_t vrhaddq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
9979	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u16)))
9980	uint16x8_t vrhaddq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9981	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u16)))
9982	uint16x8_t vrhaddq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
9983	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u32)))
9984	uint32x4_t vrhaddq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9985	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u32)))
9986	uint32x4_t vrhaddq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
9987	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u8)))
9988	uint8x16_t vrhaddq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9989	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_m_u8)))
9990	uint8x16_t vrhaddq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
9991	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s16)))
9992	int16x8_t vrhaddq_s16(int16x8_t, int16x8_t);
9993	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s16)))
9994	int16x8_t vrhaddq(int16x8_t, int16x8_t);
9995	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s32)))
9996	int32x4_t vrhaddq_s32(int32x4_t, int32x4_t);
9997	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s32)))
9998	int32x4_t vrhaddq(int32x4_t, int32x4_t);
9999	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s8)))
10000	int8x16_t vrhaddq_s8(int8x16_t, int8x16_t);
10001	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_s8)))
10002	int8x16_t vrhaddq(int8x16_t, int8x16_t);
10003	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u16)))
10004	uint16x8_t vrhaddq_u16(uint16x8_t, uint16x8_t);
10005	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u16)))
10006	uint16x8_t vrhaddq(uint16x8_t, uint16x8_t);
10007	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u32)))
10008	uint32x4_t vrhaddq_u32(uint32x4_t, uint32x4_t);
10009	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u32)))
10010	uint32x4_t vrhaddq(uint32x4_t, uint32x4_t);
10011	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u8)))
10012	uint8x16_t vrhaddq_u8(uint8x16_t, uint8x16_t);
10013	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_u8)))
10014	uint8x16_t vrhaddq(uint8x16_t, uint8x16_t);
10015	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s16)))
10016	int16x8_t vrhaddq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
10017	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s16)))
10018	int16x8_t vrhaddq_x(int16x8_t, int16x8_t, mve_pred16_t);
10019	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s32)))
10020	int32x4_t vrhaddq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
10021	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s32)))
10022	int32x4_t vrhaddq_x(int32x4_t, int32x4_t, mve_pred16_t);
10023	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s8)))
10024	int8x16_t vrhaddq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
10025	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_s8)))
10026	int8x16_t vrhaddq_x(int8x16_t, int8x16_t, mve_pred16_t);
10027	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u16)))
10028	uint16x8_t vrhaddq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
10029	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u16)))
10030	uint16x8_t vrhaddq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
10031	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u32)))
10032	uint32x4_t vrhaddq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
10033	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u32)))
10034	uint32x4_t vrhaddq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
10035	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u8)))
10036	uint8x16_t vrhaddq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
10037	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrhaddq_x_u8)))
10038	uint8x16_t vrhaddq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
10039	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_s32)))
10040	int64_t vrmlaldavhaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10041	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_s32)))
10042	int64_t vrmlaldavhaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10043	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_u32)))
10044	uint64_t vrmlaldavhaq_p_u32(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
10045	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_p_u32)))
10046	uint64_t vrmlaldavhaq_p(uint64_t, uint32x4_t, uint32x4_t, mve_pred16_t);
10047	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_s32)))
10048	int64_t vrmlaldavhaq_s32(int64_t, int32x4_t, int32x4_t);
10049	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_s32)))
10050	int64_t vrmlaldavhaq(int64_t, int32x4_t, int32x4_t);
10051	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_u32)))
10052	uint64_t vrmlaldavhaq_u32(uint64_t, uint32x4_t, uint32x4_t);
10053	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaq_u32)))
10054	uint64_t vrmlaldavhaq(uint64_t, uint32x4_t, uint32x4_t);
10055	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_p_s32)))
10056	int64_t vrmlaldavhaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10057	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_p_s32)))
10058	int64_t vrmlaldavhaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10059	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_s32)))
10060	int64_t vrmlaldavhaxq_s32(int64_t, int32x4_t, int32x4_t);
10061	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhaxq_s32)))
10062	int64_t vrmlaldavhaxq(int64_t, int32x4_t, int32x4_t);
10063	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_s32)))
10064	int64_t vrmlaldavhq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
10065	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_s32)))
10066	int64_t vrmlaldavhq_p(int32x4_t, int32x4_t, mve_pred16_t);
10067	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_u32)))
10068	uint64_t vrmlaldavhq_p_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
10069	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_p_u32)))
10070	uint64_t vrmlaldavhq_p(uint32x4_t, uint32x4_t, mve_pred16_t);
10071	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_s32)))
10072	int64_t vrmlaldavhq_s32(int32x4_t, int32x4_t);
10073	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_s32)))
10074	int64_t vrmlaldavhq(int32x4_t, int32x4_t);
10075	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_u32)))
10076	uint64_t vrmlaldavhq_u32(uint32x4_t, uint32x4_t);
10077	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhq_u32)))
10078	uint64_t vrmlaldavhq(uint32x4_t, uint32x4_t);
10079	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_p_s32)))
10080	int64_t vrmlaldavhxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
10081	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_p_s32)))
10082	int64_t vrmlaldavhxq_p(int32x4_t, int32x4_t, mve_pred16_t);
10083	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_s32)))
10084	int64_t vrmlaldavhxq_s32(int32x4_t, int32x4_t);
10085	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlaldavhxq_s32)))
10086	int64_t vrmlaldavhxq(int32x4_t, int32x4_t);
10087	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_p_s32)))
10088	int64_t vrmlsldavhaq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10089	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_p_s32)))
10090	int64_t vrmlsldavhaq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10091	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_s32)))
10092	int64_t vrmlsldavhaq_s32(int64_t, int32x4_t, int32x4_t);
10093	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaq_s32)))
10094	int64_t vrmlsldavhaq(int64_t, int32x4_t, int32x4_t);
10095	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_p_s32)))
10096	int64_t vrmlsldavhaxq_p_s32(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10097	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_p_s32)))
10098	int64_t vrmlsldavhaxq_p(int64_t, int32x4_t, int32x4_t, mve_pred16_t);
10099	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_s32)))
10100	int64_t vrmlsldavhaxq_s32(int64_t, int32x4_t, int32x4_t);
10101	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhaxq_s32)))
10102	int64_t vrmlsldavhaxq(int64_t, int32x4_t, int32x4_t);
10103	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_p_s32)))
10104	int64_t vrmlsldavhq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
10105	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_p_s32)))
10106	int64_t vrmlsldavhq_p(int32x4_t, int32x4_t, mve_pred16_t);
10107	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_s32)))
10108	int64_t vrmlsldavhq_s32(int32x4_t, int32x4_t);
10109	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhq_s32)))
10110	int64_t vrmlsldavhq(int32x4_t, int32x4_t);
10111	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_p_s32)))
10112	int64_t vrmlsldavhxq_p_s32(int32x4_t, int32x4_t, mve_pred16_t);
10113	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_p_s32)))
10114	int64_t vrmlsldavhxq_p(int32x4_t, int32x4_t, mve_pred16_t);
10115	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_s32)))
10116	int64_t vrmlsldavhxq_s32(int32x4_t, int32x4_t);
10117	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmlsldavhxq_s32)))
10118	int64_t vrmlsldavhxq(int32x4_t, int32x4_t);
10119	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s16)))
10120	int16x8_t vrmulhq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10121	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s16)))
10122	int16x8_t vrmulhq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10123	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s32)))
10124	int32x4_t vrmulhq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10125	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s32)))
10126	int32x4_t vrmulhq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10127	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s8)))
10128	int8x16_t vrmulhq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10129	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_s8)))
10130	int8x16_t vrmulhq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10131	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u16)))
10132	uint16x8_t vrmulhq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
10133	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u16)))
10134	uint16x8_t vrmulhq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
10135	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u32)))
10136	uint32x4_t vrmulhq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
10137	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u32)))
10138	uint32x4_t vrmulhq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
10139	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u8)))
10140	uint8x16_t vrmulhq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
10141	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_m_u8)))
10142	uint8x16_t vrmulhq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
10143	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s16)))
10144	int16x8_t vrmulhq_s16(int16x8_t, int16x8_t);
10145	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s16)))
10146	int16x8_t vrmulhq(int16x8_t, int16x8_t);
10147	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s32)))
10148	int32x4_t vrmulhq_s32(int32x4_t, int32x4_t);
10149	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s32)))
10150	int32x4_t vrmulhq(int32x4_t, int32x4_t);
10151	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s8)))
10152	int8x16_t vrmulhq_s8(int8x16_t, int8x16_t);
10153	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_s8)))
10154	int8x16_t vrmulhq(int8x16_t, int8x16_t);
10155	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u16)))
10156	uint16x8_t vrmulhq_u16(uint16x8_t, uint16x8_t);
10157	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u16)))
10158	uint16x8_t vrmulhq(uint16x8_t, uint16x8_t);
10159	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u32)))
10160	uint32x4_t vrmulhq_u32(uint32x4_t, uint32x4_t);
10161	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u32)))
10162	uint32x4_t vrmulhq(uint32x4_t, uint32x4_t);
10163	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u8)))
10164	uint8x16_t vrmulhq_u8(uint8x16_t, uint8x16_t);
10165	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_u8)))
10166	uint8x16_t vrmulhq(uint8x16_t, uint8x16_t);
10167	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s16)))
10168	int16x8_t vrmulhq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
10169	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s16)))
10170	int16x8_t vrmulhq_x(int16x8_t, int16x8_t, mve_pred16_t);
10171	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s32)))
10172	int32x4_t vrmulhq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
10173	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s32)))
10174	int32x4_t vrmulhq_x(int32x4_t, int32x4_t, mve_pred16_t);
10175	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s8)))
10176	int8x16_t vrmulhq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
10177	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_s8)))
10178	int8x16_t vrmulhq_x(int8x16_t, int8x16_t, mve_pred16_t);
10179	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u16)))
10180	uint16x8_t vrmulhq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
10181	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u16)))
10182	uint16x8_t vrmulhq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
10183	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u32)))
10184	uint32x4_t vrmulhq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
10185	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u32)))
10186	uint32x4_t vrmulhq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
10187	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u8)))
10188	uint8x16_t vrmulhq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
10189	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrmulhq_x_u8)))
10190	uint8x16_t vrmulhq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
10191	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s16)))
10192	int16x8_t vrshlq_m_n_s16(int16x8_t, int32_t, mve_pred16_t);
10193	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s16)))
10194	int16x8_t vrshlq_m_n(int16x8_t, int32_t, mve_pred16_t);
10195	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s32)))
10196	int32x4_t vrshlq_m_n_s32(int32x4_t, int32_t, mve_pred16_t);
10197	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s32)))
10198	int32x4_t vrshlq_m_n(int32x4_t, int32_t, mve_pred16_t);
10199	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s8)))
10200	int8x16_t vrshlq_m_n_s8(int8x16_t, int32_t, mve_pred16_t);
10201	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_s8)))
10202	int8x16_t vrshlq_m_n(int8x16_t, int32_t, mve_pred16_t);
10203	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u16)))
10204	uint16x8_t vrshlq_m_n_u16(uint16x8_t, int32_t, mve_pred16_t);
10205	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u16)))
10206	uint16x8_t vrshlq_m_n(uint16x8_t, int32_t, mve_pred16_t);
10207	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u32)))
10208	uint32x4_t vrshlq_m_n_u32(uint32x4_t, int32_t, mve_pred16_t);
10209	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u32)))
10210	uint32x4_t vrshlq_m_n(uint32x4_t, int32_t, mve_pred16_t);
10211	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u8)))
10212	uint8x16_t vrshlq_m_n_u8(uint8x16_t, int32_t, mve_pred16_t);
10213	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_n_u8)))
10214	uint8x16_t vrshlq_m_n(uint8x16_t, int32_t, mve_pred16_t);
10215	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s16)))
10216	int16x8_t vrshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10217	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s16)))
10218	int16x8_t vrshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10219	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s32)))
10220	int32x4_t vrshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10221	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s32)))
10222	int32x4_t vrshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10223	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s8)))
10224	int8x16_t vrshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10225	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_s8)))
10226	int8x16_t vrshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10227	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u16)))
10228	uint16x8_t vrshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
10229	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u16)))
10230	uint16x8_t vrshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
10231	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u32)))
10232	uint32x4_t vrshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
10233	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u32)))
10234	uint32x4_t vrshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
10235	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u8)))
10236	uint8x16_t vrshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
10237	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_m_u8)))
10238	uint8x16_t vrshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
10239	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s16)))
10240	int16x8_t vrshlq_n_s16(int16x8_t, int32_t);
10241	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s16)))
10242	int16x8_t vrshlq(int16x8_t, int32_t);
10243	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s32)))
10244	int32x4_t vrshlq_n_s32(int32x4_t, int32_t);
10245	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s32)))
10246	int32x4_t vrshlq(int32x4_t, int32_t);
10247	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s8)))
10248	int8x16_t vrshlq_n_s8(int8x16_t, int32_t);
10249	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_s8)))
10250	int8x16_t vrshlq(int8x16_t, int32_t);
10251	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u16)))
10252	uint16x8_t vrshlq_n_u16(uint16x8_t, int32_t);
10253	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u16)))
10254	uint16x8_t vrshlq(uint16x8_t, int32_t);
10255	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u32)))
10256	uint32x4_t vrshlq_n_u32(uint32x4_t, int32_t);
10257	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u32)))
10258	uint32x4_t vrshlq(uint32x4_t, int32_t);
10259	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u8)))
10260	uint8x16_t vrshlq_n_u8(uint8x16_t, int32_t);
10261	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_n_u8)))
10262	uint8x16_t vrshlq(uint8x16_t, int32_t);
10263	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s16)))
10264	int16x8_t vrshlq_s16(int16x8_t, int16x8_t);
10265	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s16)))
10266	int16x8_t vrshlq(int16x8_t, int16x8_t);
10267	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s32)))
10268	int32x4_t vrshlq_s32(int32x4_t, int32x4_t);
10269	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s32)))
10270	int32x4_t vrshlq(int32x4_t, int32x4_t);
10271	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s8)))
10272	int8x16_t vrshlq_s8(int8x16_t, int8x16_t);
10273	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_s8)))
10274	int8x16_t vrshlq(int8x16_t, int8x16_t);
10275	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u16)))
10276	uint16x8_t vrshlq_u16(uint16x8_t, int16x8_t);
10277	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u16)))
10278	uint16x8_t vrshlq(uint16x8_t, int16x8_t);
10279	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u32)))
10280	uint32x4_t vrshlq_u32(uint32x4_t, int32x4_t);
10281	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u32)))
10282	uint32x4_t vrshlq(uint32x4_t, int32x4_t);
10283	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u8)))
10284	uint8x16_t vrshlq_u8(uint8x16_t, int8x16_t);
10285	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_u8)))
10286	uint8x16_t vrshlq(uint8x16_t, int8x16_t);
10287	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s16)))
10288	int16x8_t vrshlq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
10289	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s16)))
10290	int16x8_t vrshlq_x(int16x8_t, int16x8_t, mve_pred16_t);
10291	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s32)))
10292	int32x4_t vrshlq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
10293	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s32)))
10294	int32x4_t vrshlq_x(int32x4_t, int32x4_t, mve_pred16_t);
10295	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s8)))
10296	int8x16_t vrshlq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
10297	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_s8)))
10298	int8x16_t vrshlq_x(int8x16_t, int8x16_t, mve_pred16_t);
10299	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u16)))
10300	uint16x8_t vrshlq_x_u16(uint16x8_t, int16x8_t, mve_pred16_t);
10301	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u16)))
10302	uint16x8_t vrshlq_x(uint16x8_t, int16x8_t, mve_pred16_t);
10303	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u32)))
10304	uint32x4_t vrshlq_x_u32(uint32x4_t, int32x4_t, mve_pred16_t);
10305	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u32)))
10306	uint32x4_t vrshlq_x(uint32x4_t, int32x4_t, mve_pred16_t);
10307	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u8)))
10308	uint8x16_t vrshlq_x_u8(uint8x16_t, int8x16_t, mve_pred16_t);
10309	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshlq_x_u8)))
10310	uint8x16_t vrshlq_x(uint8x16_t, int8x16_t, mve_pred16_t);
10311	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s16)))
10312	int8x16_t vrshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
10313	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s16)))
10314	int8x16_t vrshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
10315	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s32)))
10316	int16x8_t vrshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
10317	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_s32)))
10318	int16x8_t vrshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
10319	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u16)))
10320	uint8x16_t vrshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10321	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u16)))
10322	uint8x16_t vrshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10323	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u32)))
10324	uint16x8_t vrshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10325	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_m_n_u32)))
10326	uint16x8_t vrshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10327	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s16)))
10328	int8x16_t vrshrnbq_n_s16(int8x16_t, int16x8_t, int);
10329	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s16)))
10330	int8x16_t vrshrnbq(int8x16_t, int16x8_t, int);
10331	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s32)))
10332	int16x8_t vrshrnbq_n_s32(int16x8_t, int32x4_t, int);
10333	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_s32)))
10334	int16x8_t vrshrnbq(int16x8_t, int32x4_t, int);
10335	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u16)))
10336	uint8x16_t vrshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
10337	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u16)))
10338	uint8x16_t vrshrnbq(uint8x16_t, uint16x8_t, int);
10339	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u32)))
10340	uint16x8_t vrshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
10341	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrnbq_n_u32)))
10342	uint16x8_t vrshrnbq(uint16x8_t, uint32x4_t, int);
10343	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s16)))
10344	int8x16_t vrshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
10345	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s16)))
10346	int8x16_t vrshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
10347	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s32)))
10348	int16x8_t vrshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
10349	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_s32)))
10350	int16x8_t vrshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
10351	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u16)))
10352	uint8x16_t vrshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10353	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u16)))
10354	uint8x16_t vrshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10355	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u32)))
10356	uint16x8_t vrshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10357	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_m_n_u32)))
10358	uint16x8_t vrshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10359	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s16)))
10360	int8x16_t vrshrntq_n_s16(int8x16_t, int16x8_t, int);
10361	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s16)))
10362	int8x16_t vrshrntq(int8x16_t, int16x8_t, int);
10363	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s32)))
10364	int16x8_t vrshrntq_n_s32(int16x8_t, int32x4_t, int);
10365	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_s32)))
10366	int16x8_t vrshrntq(int16x8_t, int32x4_t, int);
10367	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u16)))
10368	uint8x16_t vrshrntq_n_u16(uint8x16_t, uint16x8_t, int);
10369	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u16)))
10370	uint8x16_t vrshrntq(uint8x16_t, uint16x8_t, int);
10371	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u32)))
10372	uint16x8_t vrshrntq_n_u32(uint16x8_t, uint32x4_t, int);
10373	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrntq_n_u32)))
10374	uint16x8_t vrshrntq(uint16x8_t, uint32x4_t, int);
10375	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s16)))
10376	int16x8_t vrshrq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
10377	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s16)))
10378	int16x8_t vrshrq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
10379	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s32)))
10380	int32x4_t vrshrq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
10381	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s32)))
10382	int32x4_t vrshrq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
10383	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s8)))
10384	int8x16_t vrshrq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
10385	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_s8)))
10386	int8x16_t vrshrq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
10387	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u16)))
10388	uint16x8_t vrshrq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10389	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u16)))
10390	uint16x8_t vrshrq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10391	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u32)))
10392	uint32x4_t vrshrq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10393	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u32)))
10394	uint32x4_t vrshrq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10395	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u8)))
10396	uint8x16_t vrshrq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10397	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_m_n_u8)))
10398	uint8x16_t vrshrq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10399	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s16)))
10400	int16x8_t vrshrq_n_s16(int16x8_t, int);
10401	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s16)))
10402	int16x8_t vrshrq(int16x8_t, int);
10403	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s32)))
10404	int32x4_t vrshrq_n_s32(int32x4_t, int);
10405	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s32)))
10406	int32x4_t vrshrq(int32x4_t, int);
10407	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s8)))
10408	int8x16_t vrshrq_n_s8(int8x16_t, int);
10409	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_s8)))
10410	int8x16_t vrshrq(int8x16_t, int);
10411	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u16)))
10412	uint16x8_t vrshrq_n_u16(uint16x8_t, int);
10413	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u16)))
10414	uint16x8_t vrshrq(uint16x8_t, int);
10415	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u32)))
10416	uint32x4_t vrshrq_n_u32(uint32x4_t, int);
10417	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u32)))
10418	uint32x4_t vrshrq(uint32x4_t, int);
10419	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u8)))
10420	uint8x16_t vrshrq_n_u8(uint8x16_t, int);
10421	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_n_u8)))
10422	uint8x16_t vrshrq(uint8x16_t, int);
10423	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s16)))
10424	int16x8_t vrshrq_x_n_s16(int16x8_t, int, mve_pred16_t);
10425	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s16)))
10426	int16x8_t vrshrq_x(int16x8_t, int, mve_pred16_t);
10427	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s32)))
10428	int32x4_t vrshrq_x_n_s32(int32x4_t, int, mve_pred16_t);
10429	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s32)))
10430	int32x4_t vrshrq_x(int32x4_t, int, mve_pred16_t);
10431	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s8)))
10432	int8x16_t vrshrq_x_n_s8(int8x16_t, int, mve_pred16_t);
10433	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_s8)))
10434	int8x16_t vrshrq_x(int8x16_t, int, mve_pred16_t);
10435	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u16)))
10436	uint16x8_t vrshrq_x_n_u16(uint16x8_t, int, mve_pred16_t);
10437	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u16)))
10438	uint16x8_t vrshrq_x(uint16x8_t, int, mve_pred16_t);
10439	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u32)))
10440	uint32x4_t vrshrq_x_n_u32(uint32x4_t, int, mve_pred16_t);
10441	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u32)))
10442	uint32x4_t vrshrq_x(uint32x4_t, int, mve_pred16_t);
10443	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u8)))
10444	uint8x16_t vrshrq_x_n_u8(uint8x16_t, int, mve_pred16_t);
10445	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vrshrq_x_n_u8)))
10446	uint8x16_t vrshrq_x(uint8x16_t, int, mve_pred16_t);
10447	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s16)))
10448	int16x8_t vsetq_lane_s16(int16_t, int16x8_t, int);
10449	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s16)))
10450	int16x8_t vsetq_lane(int16_t, int16x8_t, int);
10451	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s32)))
10452	int32x4_t vsetq_lane_s32(int32_t, int32x4_t, int);
10453	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s32)))
10454	int32x4_t vsetq_lane(int32_t, int32x4_t, int);
10455	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s64)))
10456	int64x2_t vsetq_lane_s64(int64_t, int64x2_t, int);
10457	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s64)))
10458	int64x2_t vsetq_lane(int64_t, int64x2_t, int);
10459	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s8)))
10460	int8x16_t vsetq_lane_s8(int8_t, int8x16_t, int);
10461	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_s8)))
10462	int8x16_t vsetq_lane(int8_t, int8x16_t, int);
10463	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u16)))
10464	uint16x8_t vsetq_lane_u16(uint16_t, uint16x8_t, int);
10465	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u16)))
10466	uint16x8_t vsetq_lane(uint16_t, uint16x8_t, int);
10467	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u32)))
10468	uint32x4_t vsetq_lane_u32(uint32_t, uint32x4_t, int);
10469	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u32)))
10470	uint32x4_t vsetq_lane(uint32_t, uint32x4_t, int);
10471	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u64)))
10472	uint64x2_t vsetq_lane_u64(uint64_t, uint64x2_t, int);
10473	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u64)))
10474	uint64x2_t vsetq_lane(uint64_t, uint64x2_t, int);
10475	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u8)))
10476	uint8x16_t vsetq_lane_u8(uint8_t, uint8x16_t, int);
10477	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_u8)))
10478	uint8x16_t vsetq_lane(uint8_t, uint8x16_t, int);
10479	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s16)))
10480	int32x4_t vshllbq_m_n_s16(int32x4_t, int16x8_t, int, mve_pred16_t);
10481	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s16)))
10482	int32x4_t vshllbq_m(int32x4_t, int16x8_t, int, mve_pred16_t);
10483	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s8)))
10484	int16x8_t vshllbq_m_n_s8(int16x8_t, int8x16_t, int, mve_pred16_t);
10485	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_s8)))
10486	int16x8_t vshllbq_m(int16x8_t, int8x16_t, int, mve_pred16_t);
10487	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u16)))
10488	uint32x4_t vshllbq_m_n_u16(uint32x4_t, uint16x8_t, int, mve_pred16_t);
10489	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u16)))
10490	uint32x4_t vshllbq_m(uint32x4_t, uint16x8_t, int, mve_pred16_t);
10491	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u8)))
10492	uint16x8_t vshllbq_m_n_u8(uint16x8_t, uint8x16_t, int, mve_pred16_t);
10493	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_m_n_u8)))
10494	uint16x8_t vshllbq_m(uint16x8_t, uint8x16_t, int, mve_pred16_t);
10495	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s16)))
10496	int32x4_t vshllbq_n_s16(int16x8_t, int);
10497	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s16)))
10498	int32x4_t vshllbq(int16x8_t, int);
10499	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s8)))
10500	int16x8_t vshllbq_n_s8(int8x16_t, int);
10501	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_s8)))
10502	int16x8_t vshllbq(int8x16_t, int);
10503	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u16)))
10504	uint32x4_t vshllbq_n_u16(uint16x8_t, int);
10505	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u16)))
10506	uint32x4_t vshllbq(uint16x8_t, int);
10507	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u8)))
10508	uint16x8_t vshllbq_n_u8(uint8x16_t, int);
10509	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_n_u8)))
10510	uint16x8_t vshllbq(uint8x16_t, int);
10511	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s16)))
10512	int32x4_t vshllbq_x_n_s16(int16x8_t, int, mve_pred16_t);
10513	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s16)))
10514	int32x4_t vshllbq_x(int16x8_t, int, mve_pred16_t);
10515	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s8)))
10516	int16x8_t vshllbq_x_n_s8(int8x16_t, int, mve_pred16_t);
10517	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_s8)))
10518	int16x8_t vshllbq_x(int8x16_t, int, mve_pred16_t);
10519	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u16)))
10520	uint32x4_t vshllbq_x_n_u16(uint16x8_t, int, mve_pred16_t);
10521	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u16)))
10522	uint32x4_t vshllbq_x(uint16x8_t, int, mve_pred16_t);
10523	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u8)))
10524	uint16x8_t vshllbq_x_n_u8(uint8x16_t, int, mve_pred16_t);
10525	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshllbq_x_n_u8)))
10526	uint16x8_t vshllbq_x(uint8x16_t, int, mve_pred16_t);
10527	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s16)))
10528	int32x4_t vshlltq_m_n_s16(int32x4_t, int16x8_t, int, mve_pred16_t);
10529	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s16)))
10530	int32x4_t vshlltq_m(int32x4_t, int16x8_t, int, mve_pred16_t);
10531	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s8)))
10532	int16x8_t vshlltq_m_n_s8(int16x8_t, int8x16_t, int, mve_pred16_t);
10533	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_s8)))
10534	int16x8_t vshlltq_m(int16x8_t, int8x16_t, int, mve_pred16_t);
10535	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u16)))
10536	uint32x4_t vshlltq_m_n_u16(uint32x4_t, uint16x8_t, int, mve_pred16_t);
10537	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u16)))
10538	uint32x4_t vshlltq_m(uint32x4_t, uint16x8_t, int, mve_pred16_t);
10539	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u8)))
10540	uint16x8_t vshlltq_m_n_u8(uint16x8_t, uint8x16_t, int, mve_pred16_t);
10541	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_m_n_u8)))
10542	uint16x8_t vshlltq_m(uint16x8_t, uint8x16_t, int, mve_pred16_t);
10543	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s16)))
10544	int32x4_t vshlltq_n_s16(int16x8_t, int);
10545	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s16)))
10546	int32x4_t vshlltq(int16x8_t, int);
10547	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s8)))
10548	int16x8_t vshlltq_n_s8(int8x16_t, int);
10549	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_s8)))
10550	int16x8_t vshlltq(int8x16_t, int);
10551	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u16)))
10552	uint32x4_t vshlltq_n_u16(uint16x8_t, int);
10553	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u16)))
10554	uint32x4_t vshlltq(uint16x8_t, int);
10555	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u8)))
10556	uint16x8_t vshlltq_n_u8(uint8x16_t, int);
10557	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_n_u8)))
10558	uint16x8_t vshlltq(uint8x16_t, int);
10559	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s16)))
10560	int32x4_t vshlltq_x_n_s16(int16x8_t, int, mve_pred16_t);
10561	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s16)))
10562	int32x4_t vshlltq_x(int16x8_t, int, mve_pred16_t);
10563	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s8)))
10564	int16x8_t vshlltq_x_n_s8(int8x16_t, int, mve_pred16_t);
10565	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_s8)))
10566	int16x8_t vshlltq_x(int8x16_t, int, mve_pred16_t);
10567	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u16)))
10568	uint32x4_t vshlltq_x_n_u16(uint16x8_t, int, mve_pred16_t);
10569	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u16)))
10570	uint32x4_t vshlltq_x(uint16x8_t, int, mve_pred16_t);
10571	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u8)))
10572	uint16x8_t vshlltq_x_n_u8(uint8x16_t, int, mve_pred16_t);
10573	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlltq_x_n_u8)))
10574	uint16x8_t vshlltq_x(uint8x16_t, int, mve_pred16_t);
10575	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s16)))
10576	int16x8_t vshlq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
10577	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s16)))
10578	int16x8_t vshlq_m_n(int16x8_t, int16x8_t, int, mve_pred16_t);
10579	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s32)))
10580	int32x4_t vshlq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
10581	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s32)))
10582	int32x4_t vshlq_m_n(int32x4_t, int32x4_t, int, mve_pred16_t);
10583	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s8)))
10584	int8x16_t vshlq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
10585	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_s8)))
10586	int8x16_t vshlq_m_n(int8x16_t, int8x16_t, int, mve_pred16_t);
10587	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u16)))
10588	uint16x8_t vshlq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10589	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u16)))
10590	uint16x8_t vshlq_m_n(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10591	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u32)))
10592	uint32x4_t vshlq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10593	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u32)))
10594	uint32x4_t vshlq_m_n(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10595	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u8)))
10596	uint8x16_t vshlq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10597	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_n_u8)))
10598	uint8x16_t vshlq_m_n(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10599	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s16)))
10600	int16x8_t vshlq_m_r_s16(int16x8_t, int32_t, mve_pred16_t);
10601	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s16)))
10602	int16x8_t vshlq_m_r(int16x8_t, int32_t, mve_pred16_t);
10603	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s32)))
10604	int32x4_t vshlq_m_r_s32(int32x4_t, int32_t, mve_pred16_t);
10605	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s32)))
10606	int32x4_t vshlq_m_r(int32x4_t, int32_t, mve_pred16_t);
10607	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s8)))
10608	int8x16_t vshlq_m_r_s8(int8x16_t, int32_t, mve_pred16_t);
10609	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_s8)))
10610	int8x16_t vshlq_m_r(int8x16_t, int32_t, mve_pred16_t);
10611	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u16)))
10612	uint16x8_t vshlq_m_r_u16(uint16x8_t, int32_t, mve_pred16_t);
10613	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u16)))
10614	uint16x8_t vshlq_m_r(uint16x8_t, int32_t, mve_pred16_t);
10615	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u32)))
10616	uint32x4_t vshlq_m_r_u32(uint32x4_t, int32_t, mve_pred16_t);
10617	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u32)))
10618	uint32x4_t vshlq_m_r(uint32x4_t, int32_t, mve_pred16_t);
10619	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u8)))
10620	uint8x16_t vshlq_m_r_u8(uint8x16_t, int32_t, mve_pred16_t);
10621	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_r_u8)))
10622	uint8x16_t vshlq_m_r(uint8x16_t, int32_t, mve_pred16_t);
10623	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s16)))
10624	int16x8_t vshlq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10625	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s16)))
10626	int16x8_t vshlq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
10627	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s32)))
10628	int32x4_t vshlq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10629	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s32)))
10630	int32x4_t vshlq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
10631	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s8)))
10632	int8x16_t vshlq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10633	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_s8)))
10634	int8x16_t vshlq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
10635	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u16)))
10636	uint16x8_t vshlq_m_u16(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
10637	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u16)))
10638	uint16x8_t vshlq_m(uint16x8_t, uint16x8_t, int16x8_t, mve_pred16_t);
10639	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u32)))
10640	uint32x4_t vshlq_m_u32(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
10641	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u32)))
10642	uint32x4_t vshlq_m(uint32x4_t, uint32x4_t, int32x4_t, mve_pred16_t);
10643	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u8)))
10644	uint8x16_t vshlq_m_u8(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
10645	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_m_u8)))
10646	uint8x16_t vshlq_m(uint8x16_t, uint8x16_t, int8x16_t, mve_pred16_t);
10647	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s16)))
10648	int16x8_t vshlq_n_s16(int16x8_t, int);
10649	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s16)))
10650	int16x8_t vshlq_n(int16x8_t, int);
10651	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s32)))
10652	int32x4_t vshlq_n_s32(int32x4_t, int);
10653	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s32)))
10654	int32x4_t vshlq_n(int32x4_t, int);
10655	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s8)))
10656	int8x16_t vshlq_n_s8(int8x16_t, int);
10657	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_s8)))
10658	int8x16_t vshlq_n(int8x16_t, int);
10659	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u16)))
10660	uint16x8_t vshlq_n_u16(uint16x8_t, int);
10661	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u16)))
10662	uint16x8_t vshlq_n(uint16x8_t, int);
10663	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u32)))
10664	uint32x4_t vshlq_n_u32(uint32x4_t, int);
10665	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u32)))
10666	uint32x4_t vshlq_n(uint32x4_t, int);
10667	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u8)))
10668	uint8x16_t vshlq_n_u8(uint8x16_t, int);
10669	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_n_u8)))
10670	uint8x16_t vshlq_n(uint8x16_t, int);
10671	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s16)))
10672	int16x8_t vshlq_r_s16(int16x8_t, int32_t);
10673	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s16)))
10674	int16x8_t vshlq_r(int16x8_t, int32_t);
10675	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s32)))
10676	int32x4_t vshlq_r_s32(int32x4_t, int32_t);
10677	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s32)))
10678	int32x4_t vshlq_r(int32x4_t, int32_t);
10679	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s8)))
10680	int8x16_t vshlq_r_s8(int8x16_t, int32_t);
10681	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_s8)))
10682	int8x16_t vshlq_r(int8x16_t, int32_t);
10683	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u16)))
10684	uint16x8_t vshlq_r_u16(uint16x8_t, int32_t);
10685	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u16)))
10686	uint16x8_t vshlq_r(uint16x8_t, int32_t);
10687	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u32)))
10688	uint32x4_t vshlq_r_u32(uint32x4_t, int32_t);
10689	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u32)))
10690	uint32x4_t vshlq_r(uint32x4_t, int32_t);
10691	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u8)))
10692	uint8x16_t vshlq_r_u8(uint8x16_t, int32_t);
10693	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_r_u8)))
10694	uint8x16_t vshlq_r(uint8x16_t, int32_t);
10695	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s16)))
10696	int16x8_t vshlq_s16(int16x8_t, int16x8_t);
10697	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s16)))
10698	int16x8_t vshlq(int16x8_t, int16x8_t);
10699	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s32)))
10700	int32x4_t vshlq_s32(int32x4_t, int32x4_t);
10701	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s32)))
10702	int32x4_t vshlq(int32x4_t, int32x4_t);
10703	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_s8)))
10704	int8x16_t vshlq_s8(int8x16_t, int8x16_t);
10705	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_s8)))
10706	int8x16_t vshlq(int8x16_t, int8x16_t);
10707	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u16)))
10708	uint16x8_t vshlq_u16(uint16x8_t, int16x8_t);
10709	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u16)))
10710	uint16x8_t vshlq(uint16x8_t, int16x8_t);
10711	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u32)))
10712	uint32x4_t vshlq_u32(uint32x4_t, int32x4_t);
10713	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u32)))
10714	uint32x4_t vshlq(uint32x4_t, int32x4_t);
10715	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_u8)))
10716	uint8x16_t vshlq_u8(uint8x16_t, int8x16_t);
10717	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_u8)))
10718	uint8x16_t vshlq(uint8x16_t, int8x16_t);
10719	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s16)))
10720	int16x8_t vshlq_x_n_s16(int16x8_t, int, mve_pred16_t);
10721	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s16)))
10722	int16x8_t vshlq_x_n(int16x8_t, int, mve_pred16_t);
10723	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s32)))
10724	int32x4_t vshlq_x_n_s32(int32x4_t, int, mve_pred16_t);
10725	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s32)))
10726	int32x4_t vshlq_x_n(int32x4_t, int, mve_pred16_t);
10727	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s8)))
10728	int8x16_t vshlq_x_n_s8(int8x16_t, int, mve_pred16_t);
10729	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_s8)))
10730	int8x16_t vshlq_x_n(int8x16_t, int, mve_pred16_t);
10731	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u16)))
10732	uint16x8_t vshlq_x_n_u16(uint16x8_t, int, mve_pred16_t);
10733	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u16)))
10734	uint16x8_t vshlq_x_n(uint16x8_t, int, mve_pred16_t);
10735	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u32)))
10736	uint32x4_t vshlq_x_n_u32(uint32x4_t, int, mve_pred16_t);
10737	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u32)))
10738	uint32x4_t vshlq_x_n(uint32x4_t, int, mve_pred16_t);
10739	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u8)))
10740	uint8x16_t vshlq_x_n_u8(uint8x16_t, int, mve_pred16_t);
10741	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_n_u8)))
10742	uint8x16_t vshlq_x_n(uint8x16_t, int, mve_pred16_t);
10743	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s16)))
10744	int16x8_t vshlq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
10745	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s16)))
10746	int16x8_t vshlq_x(int16x8_t, int16x8_t, mve_pred16_t);
10747	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s32)))
10748	int32x4_t vshlq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
10749	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s32)))
10750	int32x4_t vshlq_x(int32x4_t, int32x4_t, mve_pred16_t);
10751	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s8)))
10752	int8x16_t vshlq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
10753	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_s8)))
10754	int8x16_t vshlq_x(int8x16_t, int8x16_t, mve_pred16_t);
10755	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u16)))
10756	uint16x8_t vshlq_x_u16(uint16x8_t, int16x8_t, mve_pred16_t);
10757	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u16)))
10758	uint16x8_t vshlq_x(uint16x8_t, int16x8_t, mve_pred16_t);
10759	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u32)))
10760	uint32x4_t vshlq_x_u32(uint32x4_t, int32x4_t, mve_pred16_t);
10761	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u32)))
10762	uint32x4_t vshlq_x(uint32x4_t, int32x4_t, mve_pred16_t);
10763	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u8)))
10764	uint8x16_t vshlq_x_u8(uint8x16_t, int8x16_t, mve_pred16_t);
10765	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshlq_x_u8)))
10766	uint8x16_t vshlq_x(uint8x16_t, int8x16_t, mve_pred16_t);
10767	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s16)))
10768	int8x16_t vshrnbq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
10769	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s16)))
10770	int8x16_t vshrnbq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
10771	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s32)))
10772	int16x8_t vshrnbq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
10773	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_s32)))
10774	int16x8_t vshrnbq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
10775	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u16)))
10776	uint8x16_t vshrnbq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10777	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u16)))
10778	uint8x16_t vshrnbq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10779	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u32)))
10780	uint16x8_t vshrnbq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10781	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_m_n_u32)))
10782	uint16x8_t vshrnbq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10783	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s16)))
10784	int8x16_t vshrnbq_n_s16(int8x16_t, int16x8_t, int);
10785	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s16)))
10786	int8x16_t vshrnbq(int8x16_t, int16x8_t, int);
10787	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s32)))
10788	int16x8_t vshrnbq_n_s32(int16x8_t, int32x4_t, int);
10789	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_s32)))
10790	int16x8_t vshrnbq(int16x8_t, int32x4_t, int);
10791	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u16)))
10792	uint8x16_t vshrnbq_n_u16(uint8x16_t, uint16x8_t, int);
10793	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u16)))
10794	uint8x16_t vshrnbq(uint8x16_t, uint16x8_t, int);
10795	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u32)))
10796	uint16x8_t vshrnbq_n_u32(uint16x8_t, uint32x4_t, int);
10797	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrnbq_n_u32)))
10798	uint16x8_t vshrnbq(uint16x8_t, uint32x4_t, int);
10799	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s16)))
10800	int8x16_t vshrntq_m_n_s16(int8x16_t, int16x8_t, int, mve_pred16_t);
10801	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s16)))
10802	int8x16_t vshrntq_m(int8x16_t, int16x8_t, int, mve_pred16_t);
10803	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s32)))
10804	int16x8_t vshrntq_m_n_s32(int16x8_t, int32x4_t, int, mve_pred16_t);
10805	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_s32)))
10806	int16x8_t vshrntq_m(int16x8_t, int32x4_t, int, mve_pred16_t);
10807	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u16)))
10808	uint8x16_t vshrntq_m_n_u16(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10809	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u16)))
10810	uint8x16_t vshrntq_m(uint8x16_t, uint16x8_t, int, mve_pred16_t);
10811	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u32)))
10812	uint16x8_t vshrntq_m_n_u32(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10813	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_m_n_u32)))
10814	uint16x8_t vshrntq_m(uint16x8_t, uint32x4_t, int, mve_pred16_t);
10815	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s16)))
10816	int8x16_t vshrntq_n_s16(int8x16_t, int16x8_t, int);
10817	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s16)))
10818	int8x16_t vshrntq(int8x16_t, int16x8_t, int);
10819	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s32)))
10820	int16x8_t vshrntq_n_s32(int16x8_t, int32x4_t, int);
10821	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_s32)))
10822	int16x8_t vshrntq(int16x8_t, int32x4_t, int);
10823	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u16)))
10824	uint8x16_t vshrntq_n_u16(uint8x16_t, uint16x8_t, int);
10825	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u16)))
10826	uint8x16_t vshrntq(uint8x16_t, uint16x8_t, int);
10827	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u32)))
10828	uint16x8_t vshrntq_n_u32(uint16x8_t, uint32x4_t, int);
10829	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrntq_n_u32)))
10830	uint16x8_t vshrntq(uint16x8_t, uint32x4_t, int);
10831	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s16)))
10832	int16x8_t vshrq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
10833	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s16)))
10834	int16x8_t vshrq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
10835	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s32)))
10836	int32x4_t vshrq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
10837	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s32)))
10838	int32x4_t vshrq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
10839	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s8)))
10840	int8x16_t vshrq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
10841	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_s8)))
10842	int8x16_t vshrq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
10843	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u16)))
10844	uint16x8_t vshrq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10845	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u16)))
10846	uint16x8_t vshrq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10847	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u32)))
10848	uint32x4_t vshrq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10849	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u32)))
10850	uint32x4_t vshrq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10851	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u8)))
10852	uint8x16_t vshrq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10853	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_m_n_u8)))
10854	uint8x16_t vshrq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10855	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s16)))
10856	int16x8_t vshrq_n_s16(int16x8_t, int);
10857	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s16)))
10858	int16x8_t vshrq(int16x8_t, int);
10859	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s32)))
10860	int32x4_t vshrq_n_s32(int32x4_t, int);
10861	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s32)))
10862	int32x4_t vshrq(int32x4_t, int);
10863	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s8)))
10864	int8x16_t vshrq_n_s8(int8x16_t, int);
10865	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_s8)))
10866	int8x16_t vshrq(int8x16_t, int);
10867	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u16)))
10868	uint16x8_t vshrq_n_u16(uint16x8_t, int);
10869	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u16)))
10870	uint16x8_t vshrq(uint16x8_t, int);
10871	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u32)))
10872	uint32x4_t vshrq_n_u32(uint32x4_t, int);
10873	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u32)))
10874	uint32x4_t vshrq(uint32x4_t, int);
10875	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u8)))
10876	uint8x16_t vshrq_n_u8(uint8x16_t, int);
10877	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_n_u8)))
10878	uint8x16_t vshrq(uint8x16_t, int);
10879	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s16)))
10880	int16x8_t vshrq_x_n_s16(int16x8_t, int, mve_pred16_t);
10881	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s16)))
10882	int16x8_t vshrq_x(int16x8_t, int, mve_pred16_t);
10883	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s32)))
10884	int32x4_t vshrq_x_n_s32(int32x4_t, int, mve_pred16_t);
10885	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s32)))
10886	int32x4_t vshrq_x(int32x4_t, int, mve_pred16_t);
10887	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s8)))
10888	int8x16_t vshrq_x_n_s8(int8x16_t, int, mve_pred16_t);
10889	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_s8)))
10890	int8x16_t vshrq_x(int8x16_t, int, mve_pred16_t);
10891	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u16)))
10892	uint16x8_t vshrq_x_n_u16(uint16x8_t, int, mve_pred16_t);
10893	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u16)))
10894	uint16x8_t vshrq_x(uint16x8_t, int, mve_pred16_t);
10895	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u32)))
10896	uint32x4_t vshrq_x_n_u32(uint32x4_t, int, mve_pred16_t);
10897	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u32)))
10898	uint32x4_t vshrq_x(uint32x4_t, int, mve_pred16_t);
10899	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u8)))
10900	uint8x16_t vshrq_x_n_u8(uint8x16_t, int, mve_pred16_t);
10901	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vshrq_x_n_u8)))
10902	uint8x16_t vshrq_x(uint8x16_t, int, mve_pred16_t);
10903	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s16)))
10904	int16x8_t vsliq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
10905	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s16)))
10906	int16x8_t vsliq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
10907	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s32)))
10908	int32x4_t vsliq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
10909	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s32)))
10910	int32x4_t vsliq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
10911	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s8)))
10912	int8x16_t vsliq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
10913	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_s8)))
10914	int8x16_t vsliq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
10915	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u16)))
10916	uint16x8_t vsliq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10917	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u16)))
10918	uint16x8_t vsliq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10919	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u32)))
10920	uint32x4_t vsliq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10921	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u32)))
10922	uint32x4_t vsliq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10923	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u8)))
10924	uint8x16_t vsliq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10925	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_m_n_u8)))
10926	uint8x16_t vsliq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10927	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s16)))
10928	int16x8_t vsliq_n_s16(int16x8_t, int16x8_t, int);
10929	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s16)))
10930	int16x8_t vsliq(int16x8_t, int16x8_t, int);
10931	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s32)))
10932	int32x4_t vsliq_n_s32(int32x4_t, int32x4_t, int);
10933	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s32)))
10934	int32x4_t vsliq(int32x4_t, int32x4_t, int);
10935	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s8)))
10936	int8x16_t vsliq_n_s8(int8x16_t, int8x16_t, int);
10937	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_s8)))
10938	int8x16_t vsliq(int8x16_t, int8x16_t, int);
10939	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u16)))
10940	uint16x8_t vsliq_n_u16(uint16x8_t, uint16x8_t, int);
10941	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u16)))
10942	uint16x8_t vsliq(uint16x8_t, uint16x8_t, int);
10943	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u32)))
10944	uint32x4_t vsliq_n_u32(uint32x4_t, uint32x4_t, int);
10945	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u32)))
10946	uint32x4_t vsliq(uint32x4_t, uint32x4_t, int);
10947	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u8)))
10948	uint8x16_t vsliq_n_u8(uint8x16_t, uint8x16_t, int);
10949	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsliq_n_u8)))
10950	uint8x16_t vsliq(uint8x16_t, uint8x16_t, int);
10951	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s16)))
10952	int16x8_t vsriq_m_n_s16(int16x8_t, int16x8_t, int, mve_pred16_t);
10953	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s16)))
10954	int16x8_t vsriq_m(int16x8_t, int16x8_t, int, mve_pred16_t);
10955	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s32)))
10956	int32x4_t vsriq_m_n_s32(int32x4_t, int32x4_t, int, mve_pred16_t);
10957	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s32)))
10958	int32x4_t vsriq_m(int32x4_t, int32x4_t, int, mve_pred16_t);
10959	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s8)))
10960	int8x16_t vsriq_m_n_s8(int8x16_t, int8x16_t, int, mve_pred16_t);
10961	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_s8)))
10962	int8x16_t vsriq_m(int8x16_t, int8x16_t, int, mve_pred16_t);
10963	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u16)))
10964	uint16x8_t vsriq_m_n_u16(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10965	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u16)))
10966	uint16x8_t vsriq_m(uint16x8_t, uint16x8_t, int, mve_pred16_t);
10967	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u32)))
10968	uint32x4_t vsriq_m_n_u32(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10969	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u32)))
10970	uint32x4_t vsriq_m(uint32x4_t, uint32x4_t, int, mve_pred16_t);
10971	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u8)))
10972	uint8x16_t vsriq_m_n_u8(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10973	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_m_n_u8)))
10974	uint8x16_t vsriq_m(uint8x16_t, uint8x16_t, int, mve_pred16_t);
10975	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s16)))
10976	int16x8_t vsriq_n_s16(int16x8_t, int16x8_t, int);
10977	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s16)))
10978	int16x8_t vsriq(int16x8_t, int16x8_t, int);
10979	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s32)))
10980	int32x4_t vsriq_n_s32(int32x4_t, int32x4_t, int);
10981	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s32)))
10982	int32x4_t vsriq(int32x4_t, int32x4_t, int);
10983	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s8)))
10984	int8x16_t vsriq_n_s8(int8x16_t, int8x16_t, int);
10985	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_s8)))
10986	int8x16_t vsriq(int8x16_t, int8x16_t, int);
10987	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u16)))
10988	uint16x8_t vsriq_n_u16(uint16x8_t, uint16x8_t, int);
10989	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u16)))
10990	uint16x8_t vsriq(uint16x8_t, uint16x8_t, int);
10991	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u32)))
10992	uint32x4_t vsriq_n_u32(uint32x4_t, uint32x4_t, int);
10993	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u32)))
10994	uint32x4_t vsriq(uint32x4_t, uint32x4_t, int);
10995	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u8)))
10996	uint8x16_t vsriq_n_u8(uint8x16_t, uint8x16_t, int);
10997	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsriq_n_u8)))
10998	uint8x16_t vsriq(uint8x16_t, uint8x16_t, int);
10999	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s16)))
11000	void vst1q_p_s16(int16_t *, int16x8_t, mve_pred16_t);
11001	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s16)))
11002	void vst1q_p(int16_t *, int16x8_t, mve_pred16_t);
11003	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s32)))
11004	void vst1q_p_s32(int32_t *, int32x4_t, mve_pred16_t);
11005	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s32)))
11006	void vst1q_p(int32_t *, int32x4_t, mve_pred16_t);
11007	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s8)))
11008	void vst1q_p_s8(int8_t *, int8x16_t, mve_pred16_t);
11009	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_s8)))
11010	void vst1q_p(int8_t *, int8x16_t, mve_pred16_t);
11011	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u16)))
11012	void vst1q_p_u16(uint16_t *, uint16x8_t, mve_pred16_t);
11013	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u16)))
11014	void vst1q_p(uint16_t *, uint16x8_t, mve_pred16_t);
11015	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u32)))
11016	void vst1q_p_u32(uint32_t *, uint32x4_t, mve_pred16_t);
11017	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u32)))
11018	void vst1q_p(uint32_t *, uint32x4_t, mve_pred16_t);
11019	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u8)))
11020	void vst1q_p_u8(uint8_t *, uint8x16_t, mve_pred16_t);
11021	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_u8)))
11022	void vst1q_p(uint8_t *, uint8x16_t, mve_pred16_t);
11023	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s16)))
11024	void vst1q_s16(int16_t *, int16x8_t);
11025	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s16)))
11026	void vst1q(int16_t *, int16x8_t);
11027	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s32)))
11028	void vst1q_s32(int32_t *, int32x4_t);
11029	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s32)))
11030	void vst1q(int32_t *, int32x4_t);
11031	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_s8)))
11032	void vst1q_s8(int8_t *, int8x16_t);
11033	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_s8)))
11034	void vst1q(int8_t *, int8x16_t);
11035	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u16)))
11036	void vst1q_u16(uint16_t *, uint16x8_t);
11037	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u16)))
11038	void vst1q(uint16_t *, uint16x8_t);
11039	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u32)))
11040	void vst1q_u32(uint32_t *, uint32x4_t);
11041	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u32)))
11042	void vst1q(uint32_t *, uint32x4_t);
11043	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_u8)))
11044	void vst1q_u8(uint8_t *, uint8x16_t);
11045	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_u8)))
11046	void vst1q(uint8_t *, uint8x16_t);
11047	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s16)))
11048	void vst2q_s16(int16_t *, int16x8x2_t);
11049	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s16)))
11050	void vst2q(int16_t *, int16x8x2_t);
11051	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s32)))
11052	void vst2q_s32(int32_t *, int32x4x2_t);
11053	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s32)))
11054	void vst2q(int32_t *, int32x4x2_t);
11055	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_s8)))
11056	void vst2q_s8(int8_t *, int8x16x2_t);
11057	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_s8)))
11058	void vst2q(int8_t *, int8x16x2_t);
11059	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u16)))
11060	void vst2q_u16(uint16_t *, uint16x8x2_t);
11061	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u16)))
11062	void vst2q(uint16_t *, uint16x8x2_t);
11063	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u32)))
11064	void vst2q_u32(uint32_t *, uint32x4x2_t);
11065	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u32)))
11066	void vst2q(uint32_t *, uint32x4x2_t);
11067	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_u8)))
11068	void vst2q_u8(uint8_t *, uint8x16x2_t);
11069	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_u8)))
11070	void vst2q(uint8_t *, uint8x16x2_t);
11071	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s16)))
11072	void vst4q_s16(int16_t *, int16x8x4_t);
11073	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s16)))
11074	void vst4q(int16_t *, int16x8x4_t);
11075	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s32)))
11076	void vst4q_s32(int32_t *, int32x4x4_t);
11077	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s32)))
11078	void vst4q(int32_t *, int32x4x4_t);
11079	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_s8)))
11080	void vst4q_s8(int8_t *, int8x16x4_t);
11081	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_s8)))
11082	void vst4q(int8_t *, int8x16x4_t);
11083	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u16)))
11084	void vst4q_u16(uint16_t *, uint16x8x4_t);
11085	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u16)))
11086	void vst4q(uint16_t *, uint16x8x4_t);
11087	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u32)))
11088	void vst4q_u32(uint32_t *, uint32x4x4_t);
11089	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u32)))
11090	void vst4q(uint32_t *, uint32x4x4_t);
11091	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_u8)))
11092	void vst4q_u8(uint8_t *, uint8x16x4_t);
11093	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_u8)))
11094	void vst4q(uint8_t *, uint8x16x4_t);
11095	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s16)))
11096	void vstrbq_p_s16(int8_t *, int16x8_t, mve_pred16_t);
11097	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s16)))
11098	void vstrbq_p(int8_t *, int16x8_t, mve_pred16_t);
11099	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s32)))
11100	void vstrbq_p_s32(int8_t *, int32x4_t, mve_pred16_t);
11101	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s32)))
11102	void vstrbq_p(int8_t *, int32x4_t, mve_pred16_t);
11103	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s8)))
11104	void vstrbq_p_s8(int8_t *, int8x16_t, mve_pred16_t);
11105	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_s8)))
11106	void vstrbq_p(int8_t *, int8x16_t, mve_pred16_t);
11107	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u16)))
11108	void vstrbq_p_u16(uint8_t *, uint16x8_t, mve_pred16_t);
11109	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u16)))
11110	void vstrbq_p(uint8_t *, uint16x8_t, mve_pred16_t);
11111	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u32)))
11112	void vstrbq_p_u32(uint8_t *, uint32x4_t, mve_pred16_t);
11113	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u32)))
11114	void vstrbq_p(uint8_t *, uint32x4_t, mve_pred16_t);
11115	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u8)))
11116	void vstrbq_p_u8(uint8_t *, uint8x16_t, mve_pred16_t);
11117	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_p_u8)))
11118	void vstrbq_p(uint8_t *, uint8x16_t, mve_pred16_t);
11119	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s16)))
11120	void vstrbq_s16(int8_t *, int16x8_t);
11121	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s16)))
11122	void vstrbq(int8_t *, int16x8_t);
11123	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s32)))
11124	void vstrbq_s32(int8_t *, int32x4_t);
11125	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s32)))
11126	void vstrbq(int8_t *, int32x4_t);
11127	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s8)))
11128	void vstrbq_s8(int8_t *, int8x16_t);
11129	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_s8)))
11130	void vstrbq(int8_t *, int8x16_t);
11131	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s16)))
11132	void vstrbq_scatter_offset_p_s16(int8_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11133	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s16)))
11134	void vstrbq_scatter_offset_p(int8_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11135	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s32)))
11136	void vstrbq_scatter_offset_p_s32(int8_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11137	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s32)))
11138	void vstrbq_scatter_offset_p(int8_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11139	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s8)))
11140	void vstrbq_scatter_offset_p_s8(int8_t *, uint8x16_t, int8x16_t, mve_pred16_t);
11141	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_s8)))
11142	void vstrbq_scatter_offset_p(int8_t *, uint8x16_t, int8x16_t, mve_pred16_t);
11143	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u16)))
11144	void vstrbq_scatter_offset_p_u16(uint8_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11145	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u16)))
11146	void vstrbq_scatter_offset_p(uint8_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11147	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u32)))
11148	void vstrbq_scatter_offset_p_u32(uint8_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11149	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u32)))
11150	void vstrbq_scatter_offset_p(uint8_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11151	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u8)))
11152	void vstrbq_scatter_offset_p_u8(uint8_t *, uint8x16_t, uint8x16_t, mve_pred16_t);
11153	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_p_u8)))
11154	void vstrbq_scatter_offset_p(uint8_t *, uint8x16_t, uint8x16_t, mve_pred16_t);
11155	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s16)))
11156	void vstrbq_scatter_offset_s16(int8_t *, uint16x8_t, int16x8_t);
11157	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s16)))
11158	void vstrbq_scatter_offset(int8_t *, uint16x8_t, int16x8_t);
11159	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s32)))
11160	void vstrbq_scatter_offset_s32(int8_t *, uint32x4_t, int32x4_t);
11161	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s32)))
11162	void vstrbq_scatter_offset(int8_t *, uint32x4_t, int32x4_t);
11163	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s8)))
11164	void vstrbq_scatter_offset_s8(int8_t *, uint8x16_t, int8x16_t);
11165	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_s8)))
11166	void vstrbq_scatter_offset(int8_t *, uint8x16_t, int8x16_t);
11167	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u16)))
11168	void vstrbq_scatter_offset_u16(uint8_t *, uint16x8_t, uint16x8_t);
11169	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u16)))
11170	void vstrbq_scatter_offset(uint8_t *, uint16x8_t, uint16x8_t);
11171	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u32)))
11172	void vstrbq_scatter_offset_u32(uint8_t *, uint32x4_t, uint32x4_t);
11173	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u32)))
11174	void vstrbq_scatter_offset(uint8_t *, uint32x4_t, uint32x4_t);
11175	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u8)))
11176	void vstrbq_scatter_offset_u8(uint8_t *, uint8x16_t, uint8x16_t);
11177	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_scatter_offset_u8)))
11178	void vstrbq_scatter_offset(uint8_t *, uint8x16_t, uint8x16_t);
11179	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u16)))
11180	void vstrbq_u16(uint8_t *, uint16x8_t);
11181	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u16)))
11182	void vstrbq(uint8_t *, uint16x8_t);
11183	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u32)))
11184	void vstrbq_u32(uint8_t *, uint32x4_t);
11185	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u32)))
11186	void vstrbq(uint8_t *, uint32x4_t);
11187	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u8)))
11188	void vstrbq_u8(uint8_t *, uint8x16_t);
11189	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrbq_u8)))
11190	void vstrbq(uint8_t *, uint8x16_t);
11191	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_s64)))
11192	void vstrdq_scatter_base_p_s64(uint64x2_t, int, int64x2_t, mve_pred16_t);
11193	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_s64)))
11194	void vstrdq_scatter_base_p(uint64x2_t, int, int64x2_t, mve_pred16_t);
11195	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_u64)))
11196	void vstrdq_scatter_base_p_u64(uint64x2_t, int, uint64x2_t, mve_pred16_t);
11197	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_p_u64)))
11198	void vstrdq_scatter_base_p(uint64x2_t, int, uint64x2_t, mve_pred16_t);
11199	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_s64)))
11200	void vstrdq_scatter_base_s64(uint64x2_t, int, int64x2_t);
11201	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_s64)))
11202	void vstrdq_scatter_base(uint64x2_t, int, int64x2_t);
11203	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_u64)))
11204	void vstrdq_scatter_base_u64(uint64x2_t, int, uint64x2_t);
11205	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_u64)))
11206	void vstrdq_scatter_base(uint64x2_t, int, uint64x2_t);
11207	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_s64)))
11208	void vstrdq_scatter_base_wb_p_s64(uint64x2_t *, int, int64x2_t, mve_pred16_t);
11209	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_s64)))
11210	void vstrdq_scatter_base_wb_p(uint64x2_t *, int, int64x2_t, mve_pred16_t);
11211	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_u64)))
11212	void vstrdq_scatter_base_wb_p_u64(uint64x2_t *, int, uint64x2_t, mve_pred16_t);
11213	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_p_u64)))
11214	void vstrdq_scatter_base_wb_p(uint64x2_t *, int, uint64x2_t, mve_pred16_t);
11215	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_s64)))
11216	void vstrdq_scatter_base_wb_s64(uint64x2_t *, int, int64x2_t);
11217	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_s64)))
11218	void vstrdq_scatter_base_wb(uint64x2_t *, int, int64x2_t);
11219	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_u64)))
11220	void vstrdq_scatter_base_wb_u64(uint64x2_t *, int, uint64x2_t);
11221	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_base_wb_u64)))
11222	void vstrdq_scatter_base_wb(uint64x2_t *, int, uint64x2_t);
11223	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_s64)))
11224	void vstrdq_scatter_offset_p_s64(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
11225	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_s64)))
11226	void vstrdq_scatter_offset_p(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
11227	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_u64)))
11228	void vstrdq_scatter_offset_p_u64(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
11229	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_p_u64)))
11230	void vstrdq_scatter_offset_p(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
11231	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_s64)))
11232	void vstrdq_scatter_offset_s64(int64_t *, uint64x2_t, int64x2_t);
11233	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_s64)))
11234	void vstrdq_scatter_offset(int64_t *, uint64x2_t, int64x2_t);
11235	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_u64)))
11236	void vstrdq_scatter_offset_u64(uint64_t *, uint64x2_t, uint64x2_t);
11237	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_offset_u64)))
11238	void vstrdq_scatter_offset(uint64_t *, uint64x2_t, uint64x2_t);
11239	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_s64)))
11240	void vstrdq_scatter_shifted_offset_p_s64(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
11241	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_s64)))
11242	void vstrdq_scatter_shifted_offset_p(int64_t *, uint64x2_t, int64x2_t, mve_pred16_t);
11243	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_u64)))
11244	void vstrdq_scatter_shifted_offset_p_u64(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
11245	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_p_u64)))
11246	void vstrdq_scatter_shifted_offset_p(uint64_t *, uint64x2_t, uint64x2_t, mve_pred16_t);
11247	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_s64)))
11248	void vstrdq_scatter_shifted_offset_s64(int64_t *, uint64x2_t, int64x2_t);
11249	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_s64)))
11250	void vstrdq_scatter_shifted_offset(int64_t *, uint64x2_t, int64x2_t);
11251	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_u64)))
11252	void vstrdq_scatter_shifted_offset_u64(uint64_t *, uint64x2_t, uint64x2_t);
11253	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrdq_scatter_shifted_offset_u64)))
11254	void vstrdq_scatter_shifted_offset(uint64_t *, uint64x2_t, uint64x2_t);
11255	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s16)))
11256	void vstrhq_p_s16(int16_t *, int16x8_t, mve_pred16_t);
11257	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s16)))
11258	void vstrhq_p(int16_t *, int16x8_t, mve_pred16_t);
11259	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s32)))
11260	void vstrhq_p_s32(int16_t *, int32x4_t, mve_pred16_t);
11261	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_s32)))
11262	void vstrhq_p(int16_t *, int32x4_t, mve_pred16_t);
11263	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u16)))
11264	void vstrhq_p_u16(uint16_t *, uint16x8_t, mve_pred16_t);
11265	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u16)))
11266	void vstrhq_p(uint16_t *, uint16x8_t, mve_pred16_t);
11267	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u32)))
11268	void vstrhq_p_u32(uint16_t *, uint32x4_t, mve_pred16_t);
11269	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_u32)))
11270	void vstrhq_p(uint16_t *, uint32x4_t, mve_pred16_t);
11271	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s16)))
11272	void vstrhq_s16(int16_t *, int16x8_t);
11273	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s16)))
11274	void vstrhq(int16_t *, int16x8_t);
11275	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s32)))
11276	void vstrhq_s32(int16_t *, int32x4_t);
11277	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_s32)))
11278	void vstrhq(int16_t *, int32x4_t);
11279	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s16)))
11280	void vstrhq_scatter_offset_p_s16(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11281	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s16)))
11282	void vstrhq_scatter_offset_p(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11283	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s32)))
11284	void vstrhq_scatter_offset_p_s32(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11285	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_s32)))
11286	void vstrhq_scatter_offset_p(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11287	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u16)))
11288	void vstrhq_scatter_offset_p_u16(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11289	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u16)))
11290	void vstrhq_scatter_offset_p(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11291	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u32)))
11292	void vstrhq_scatter_offset_p_u32(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11293	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_u32)))
11294	void vstrhq_scatter_offset_p(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11295	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s16)))
11296	void vstrhq_scatter_offset_s16(int16_t *, uint16x8_t, int16x8_t);
11297	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s16)))
11298	void vstrhq_scatter_offset(int16_t *, uint16x8_t, int16x8_t);
11299	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s32)))
11300	void vstrhq_scatter_offset_s32(int16_t *, uint32x4_t, int32x4_t);
11301	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_s32)))
11302	void vstrhq_scatter_offset(int16_t *, uint32x4_t, int32x4_t);
11303	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u16)))
11304	void vstrhq_scatter_offset_u16(uint16_t *, uint16x8_t, uint16x8_t);
11305	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u16)))
11306	void vstrhq_scatter_offset(uint16_t *, uint16x8_t, uint16x8_t);
11307	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u32)))
11308	void vstrhq_scatter_offset_u32(uint16_t *, uint32x4_t, uint32x4_t);
11309	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_u32)))
11310	void vstrhq_scatter_offset(uint16_t *, uint32x4_t, uint32x4_t);
11311	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s16)))
11312	void vstrhq_scatter_shifted_offset_p_s16(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11313	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s16)))
11314	void vstrhq_scatter_shifted_offset_p(int16_t *, uint16x8_t, int16x8_t, mve_pred16_t);
11315	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s32)))
11316	void vstrhq_scatter_shifted_offset_p_s32(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11317	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_s32)))
11318	void vstrhq_scatter_shifted_offset_p(int16_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11319	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u16)))
11320	void vstrhq_scatter_shifted_offset_p_u16(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11321	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u16)))
11322	void vstrhq_scatter_shifted_offset_p(uint16_t *, uint16x8_t, uint16x8_t, mve_pred16_t);
11323	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u32)))
11324	void vstrhq_scatter_shifted_offset_p_u32(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11325	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_u32)))
11326	void vstrhq_scatter_shifted_offset_p(uint16_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11327	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s16)))
11328	void vstrhq_scatter_shifted_offset_s16(int16_t *, uint16x8_t, int16x8_t);
11329	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s16)))
11330	void vstrhq_scatter_shifted_offset(int16_t *, uint16x8_t, int16x8_t);
11331	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s32)))
11332	void vstrhq_scatter_shifted_offset_s32(int16_t *, uint32x4_t, int32x4_t);
11333	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_s32)))
11334	void vstrhq_scatter_shifted_offset(int16_t *, uint32x4_t, int32x4_t);
11335	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u16)))
11336	void vstrhq_scatter_shifted_offset_u16(uint16_t *, uint16x8_t, uint16x8_t);
11337	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u16)))
11338	void vstrhq_scatter_shifted_offset(uint16_t *, uint16x8_t, uint16x8_t);
11339	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u32)))
11340	void vstrhq_scatter_shifted_offset_u32(uint16_t *, uint32x4_t, uint32x4_t);
11341	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_u32)))
11342	void vstrhq_scatter_shifted_offset(uint16_t *, uint32x4_t, uint32x4_t);
11343	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u16)))
11344	void vstrhq_u16(uint16_t *, uint16x8_t);
11345	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u16)))
11346	void vstrhq(uint16_t *, uint16x8_t);
11347	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u32)))
11348	void vstrhq_u32(uint16_t *, uint32x4_t);
11349	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_u32)))
11350	void vstrhq(uint16_t *, uint32x4_t);
11351	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_s32)))
11352	void vstrwq_p_s32(int32_t *, int32x4_t, mve_pred16_t);
11353	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_s32)))
11354	void vstrwq_p(int32_t *, int32x4_t, mve_pred16_t);
11355	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_u32)))
11356	void vstrwq_p_u32(uint32_t *, uint32x4_t, mve_pred16_t);
11357	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_u32)))
11358	void vstrwq_p(uint32_t *, uint32x4_t, mve_pred16_t);
11359	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_s32)))
11360	void vstrwq_s32(int32_t *, int32x4_t);
11361	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_s32)))
11362	void vstrwq(int32_t *, int32x4_t);
11363	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_s32)))
11364	void vstrwq_scatter_base_p_s32(uint32x4_t, int, int32x4_t, mve_pred16_t);
11365	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_s32)))
11366	void vstrwq_scatter_base_p(uint32x4_t, int, int32x4_t, mve_pred16_t);
11367	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_u32)))
11368	void vstrwq_scatter_base_p_u32(uint32x4_t, int, uint32x4_t, mve_pred16_t);
11369	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_u32)))
11370	void vstrwq_scatter_base_p(uint32x4_t, int, uint32x4_t, mve_pred16_t);
11371	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_s32)))
11372	void vstrwq_scatter_base_s32(uint32x4_t, int, int32x4_t);
11373	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_s32)))
11374	void vstrwq_scatter_base(uint32x4_t, int, int32x4_t);
11375	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_u32)))
11376	void vstrwq_scatter_base_u32(uint32x4_t, int, uint32x4_t);
11377	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_u32)))
11378	void vstrwq_scatter_base(uint32x4_t, int, uint32x4_t);
11379	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_s32)))
11380	void vstrwq_scatter_base_wb_p_s32(uint32x4_t *, int, int32x4_t, mve_pred16_t);
11381	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_s32)))
11382	void vstrwq_scatter_base_wb_p(uint32x4_t *, int, int32x4_t, mve_pred16_t);
11383	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_u32)))
11384	void vstrwq_scatter_base_wb_p_u32(uint32x4_t *, int, uint32x4_t, mve_pred16_t);
11385	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_u32)))
11386	void vstrwq_scatter_base_wb_p(uint32x4_t *, int, uint32x4_t, mve_pred16_t);
11387	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_s32)))
11388	void vstrwq_scatter_base_wb_s32(uint32x4_t *, int, int32x4_t);
11389	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_s32)))
11390	void vstrwq_scatter_base_wb(uint32x4_t *, int, int32x4_t);
11391	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_u32)))
11392	void vstrwq_scatter_base_wb_u32(uint32x4_t *, int, uint32x4_t);
11393	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_u32)))
11394	void vstrwq_scatter_base_wb(uint32x4_t *, int, uint32x4_t);
11395	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_s32)))
11396	void vstrwq_scatter_offset_p_s32(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11397	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_s32)))
11398	void vstrwq_scatter_offset_p(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11399	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_u32)))
11400	void vstrwq_scatter_offset_p_u32(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11401	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_u32)))
11402	void vstrwq_scatter_offset_p(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11403	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_s32)))
11404	void vstrwq_scatter_offset_s32(int32_t *, uint32x4_t, int32x4_t);
11405	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_s32)))
11406	void vstrwq_scatter_offset(int32_t *, uint32x4_t, int32x4_t);
11407	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_u32)))
11408	void vstrwq_scatter_offset_u32(uint32_t *, uint32x4_t, uint32x4_t);
11409	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_u32)))
11410	void vstrwq_scatter_offset(uint32_t *, uint32x4_t, uint32x4_t);
11411	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_s32)))
11412	void vstrwq_scatter_shifted_offset_p_s32(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11413	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_s32)))
11414	void vstrwq_scatter_shifted_offset_p(int32_t *, uint32x4_t, int32x4_t, mve_pred16_t);
11415	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_u32)))
11416	void vstrwq_scatter_shifted_offset_p_u32(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11417	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_u32)))
11418	void vstrwq_scatter_shifted_offset_p(uint32_t *, uint32x4_t, uint32x4_t, mve_pred16_t);
11419	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_s32)))
11420	void vstrwq_scatter_shifted_offset_s32(int32_t *, uint32x4_t, int32x4_t);
11421	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_s32)))
11422	void vstrwq_scatter_shifted_offset(int32_t *, uint32x4_t, int32x4_t);
11423	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_u32)))
11424	void vstrwq_scatter_shifted_offset_u32(uint32_t *, uint32x4_t, uint32x4_t);
11425	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_u32)))
11426	void vstrwq_scatter_shifted_offset(uint32_t *, uint32x4_t, uint32x4_t);
11427	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_u32)))
11428	void vstrwq_u32(uint32_t *, uint32x4_t);
11429	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_u32)))
11430	void vstrwq(uint32_t *, uint32x4_t);
11431	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s16)))
11432	int16x8_t vsubq_m_s16(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
11433	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s16)))
11434	int16x8_t vsubq_m(int16x8_t, int16x8_t, int16x8_t, mve_pred16_t);
11435	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s32)))
11436	int32x4_t vsubq_m_s32(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
11437	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s32)))
11438	int32x4_t vsubq_m(int32x4_t, int32x4_t, int32x4_t, mve_pred16_t);
11439	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s8)))
11440	int8x16_t vsubq_m_s8(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
11441	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_s8)))
11442	int8x16_t vsubq_m(int8x16_t, int8x16_t, int8x16_t, mve_pred16_t);
11443	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u16)))
11444	uint16x8_t vsubq_m_u16(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
11445	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u16)))
11446	uint16x8_t vsubq_m(uint16x8_t, uint16x8_t, uint16x8_t, mve_pred16_t);
11447	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u32)))
11448	uint32x4_t vsubq_m_u32(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
11449	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u32)))
11450	uint32x4_t vsubq_m(uint32x4_t, uint32x4_t, uint32x4_t, mve_pred16_t);
11451	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u8)))
11452	uint8x16_t vsubq_m_u8(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
11453	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_u8)))
11454	uint8x16_t vsubq_m(uint8x16_t, uint8x16_t, uint8x16_t, mve_pred16_t);
11455	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s16)))
11456	int16x8_t vsubq_s16(int16x8_t, int16x8_t);
11457	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s16)))
11458	int16x8_t vsubq(int16x8_t, int16x8_t);
11459	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s32)))
11460	int32x4_t vsubq_s32(int32x4_t, int32x4_t);
11461	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s32)))
11462	int32x4_t vsubq(int32x4_t, int32x4_t);
11463	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_s8)))
11464	int8x16_t vsubq_s8(int8x16_t, int8x16_t);
11465	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_s8)))
11466	int8x16_t vsubq(int8x16_t, int8x16_t);
11467	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u16)))
11468	uint16x8_t vsubq_u16(uint16x8_t, uint16x8_t);
11469	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u16)))
11470	uint16x8_t vsubq(uint16x8_t, uint16x8_t);
11471	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u32)))
11472	uint32x4_t vsubq_u32(uint32x4_t, uint32x4_t);
11473	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u32)))
11474	uint32x4_t vsubq(uint32x4_t, uint32x4_t);
11475	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_u8)))
11476	uint8x16_t vsubq_u8(uint8x16_t, uint8x16_t);
11477	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_u8)))
11478	uint8x16_t vsubq(uint8x16_t, uint8x16_t);
11479	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s16)))
11480	int16x8_t vsubq_x_s16(int16x8_t, int16x8_t, mve_pred16_t);
11481	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s16)))
11482	int16x8_t vsubq_x(int16x8_t, int16x8_t, mve_pred16_t);
11483	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s32)))
11484	int32x4_t vsubq_x_s32(int32x4_t, int32x4_t, mve_pred16_t);
11485	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s32)))
11486	int32x4_t vsubq_x(int32x4_t, int32x4_t, mve_pred16_t);
11487	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s8)))
11488	int8x16_t vsubq_x_s8(int8x16_t, int8x16_t, mve_pred16_t);
11489	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_s8)))
11490	int8x16_t vsubq_x(int8x16_t, int8x16_t, mve_pred16_t);
11491	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u16)))
11492	uint16x8_t vsubq_x_u16(uint16x8_t, uint16x8_t, mve_pred16_t);
11493	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u16)))
11494	uint16x8_t vsubq_x(uint16x8_t, uint16x8_t, mve_pred16_t);
11495	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u32)))
11496	uint32x4_t vsubq_x_u32(uint32x4_t, uint32x4_t, mve_pred16_t);
11497	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u32)))
11498	uint32x4_t vsubq_x(uint32x4_t, uint32x4_t, mve_pred16_t);
11499	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u8)))
11500	uint8x16_t vsubq_x_u8(uint8x16_t, uint8x16_t, mve_pred16_t);
11501	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_u8)))
11502	uint8x16_t vsubq_x(uint8x16_t, uint8x16_t, mve_pred16_t);
11503	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s16)))
11504	int16x8_t vuninitializedq(int16x8_t);
11505	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s32)))
11506	int32x4_t vuninitializedq(int32x4_t);
11507	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s64)))
11508	int64x2_t vuninitializedq(int64x2_t);
11509	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_s8)))
11510	int8x16_t vuninitializedq(int8x16_t);
11511	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u16)))
11512	uint16x8_t vuninitializedq(uint16x8_t);
11513	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u32)))
11514	uint32x4_t vuninitializedq(uint32x4_t);
11515	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u64)))
11516	uint64x2_t vuninitializedq(uint64x2_t);
11517	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_u8)))
11518	uint8x16_t vuninitializedq(uint8x16_t);
11519	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s16)))
11520	int16x8_t vuninitializedq_s16();
11521	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s32)))
11522	int32x4_t vuninitializedq_s32();
11523	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s64)))
11524	int64x2_t vuninitializedq_s64();
11525	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_s8)))
11526	int8x16_t vuninitializedq_s8();
11527	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u16)))
11528	uint16x8_t vuninitializedq_u16();
11529	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u32)))
11530	uint32x4_t vuninitializedq_u32();
11531	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u64)))
11532	uint64x2_t vuninitializedq_u64();
11533	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_u8)))
11534	uint8x16_t vuninitializedq_u8();
11535
11536	#endif /* (!defined __ARM_MVE_PRESERVE_USER_NAMESPACE) */
11537
11538	#if (__ARM_FEATURE_MVE & 2) && (!defined __ARM_MVE_PRESERVE_USER_NAMESPACE)
11539
11540	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_f16)))
11541	float16x8_t vabdq_f16(float16x8_t, float16x8_t);
11542	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_f16)))
11543	float16x8_t vabdq(float16x8_t, float16x8_t);
11544	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_f32)))
11545	float32x4_t vabdq_f32(float32x4_t, float32x4_t);
11546	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_f32)))
11547	float32x4_t vabdq(float32x4_t, float32x4_t);
11548	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f16)))
11549	float16x8_t vabdq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11550	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f16)))
11551	float16x8_t vabdq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11552	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f32)))
11553	float32x4_t vabdq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11554	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_m_f32)))
11555	float32x4_t vabdq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11556	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f16)))
11557	float16x8_t vabdq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11558	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f16)))
11559	float16x8_t vabdq_x(float16x8_t, float16x8_t, mve_pred16_t);
11560	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f32)))
11561	float32x4_t vabdq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11562	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vabdq_x_f32)))
11563	float32x4_t vabdq_x(float32x4_t, float32x4_t, mve_pred16_t);
11564	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_f16)))
11565	float16x8_t vaddq_f16(float16x8_t, float16x8_t);
11566	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_f16)))
11567	float16x8_t vaddq(float16x8_t, float16x8_t);
11568	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_f32)))
11569	float32x4_t vaddq_f32(float32x4_t, float32x4_t);
11570	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_f32)))
11571	float32x4_t vaddq(float32x4_t, float32x4_t);
11572	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f16)))
11573	float16x8_t vaddq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11574	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f16)))
11575	float16x8_t vaddq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11576	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f32)))
11577	float32x4_t vaddq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11578	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_m_f32)))
11579	float32x4_t vaddq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11580	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f16)))
11581	float16x8_t vaddq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11582	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f16)))
11583	float16x8_t vaddq_x(float16x8_t, float16x8_t, mve_pred16_t);
11584	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f32)))
11585	float32x4_t vaddq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11586	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vaddq_x_f32)))
11587	float32x4_t vaddq_x(float32x4_t, float32x4_t, mve_pred16_t);
11588	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_f16)))
11589	float16x8_t vandq_f16(float16x8_t, float16x8_t);
11590	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_f16)))
11591	float16x8_t vandq(float16x8_t, float16x8_t);
11592	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_f32)))
11593	float32x4_t vandq_f32(float32x4_t, float32x4_t);
11594	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_f32)))
11595	float32x4_t vandq(float32x4_t, float32x4_t);
11596	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f16)))
11597	float16x8_t vandq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11598	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f16)))
11599	float16x8_t vandq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11600	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f32)))
11601	float32x4_t vandq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11602	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_m_f32)))
11603	float32x4_t vandq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11604	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f16)))
11605	float16x8_t vandq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11606	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f16)))
11607	float16x8_t vandq_x(float16x8_t, float16x8_t, mve_pred16_t);
11608	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f32)))
11609	float32x4_t vandq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11610	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vandq_x_f32)))
11611	float32x4_t vandq_x(float32x4_t, float32x4_t, mve_pred16_t);
11612	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_f16)))
11613	float16x8_t vbicq_f16(float16x8_t, float16x8_t);
11614	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_f16)))
11615	float16x8_t vbicq(float16x8_t, float16x8_t);
11616	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_f32)))
11617	float32x4_t vbicq_f32(float32x4_t, float32x4_t);
11618	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_f32)))
11619	float32x4_t vbicq(float32x4_t, float32x4_t);
11620	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f16)))
11621	float16x8_t vbicq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11622	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f16)))
11623	float16x8_t vbicq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11624	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f32)))
11625	float32x4_t vbicq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11626	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_m_f32)))
11627	float32x4_t vbicq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11628	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f16)))
11629	float16x8_t vbicq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11630	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f16)))
11631	float16x8_t vbicq_x(float16x8_t, float16x8_t, mve_pred16_t);
11632	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f32)))
11633	float32x4_t vbicq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11634	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vbicq_x_f32)))
11635	float32x4_t vbicq_x(float32x4_t, float32x4_t, mve_pred16_t);
11636	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f16)))
11637	float16x8_t vcaddq_rot270_f16(float16x8_t, float16x8_t);
11638	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f16)))
11639	float16x8_t vcaddq_rot270(float16x8_t, float16x8_t);
11640	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f32)))
11641	float32x4_t vcaddq_rot270_f32(float32x4_t, float32x4_t);
11642	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_f32)))
11643	float32x4_t vcaddq_rot270(float32x4_t, float32x4_t);
11644	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f16)))
11645	float16x8_t vcaddq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11646	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f16)))
11647	float16x8_t vcaddq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11648	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f32)))
11649	float32x4_t vcaddq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11650	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_m_f32)))
11651	float32x4_t vcaddq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11652	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f16)))
11653	float16x8_t vcaddq_rot270_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11654	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f16)))
11655	float16x8_t vcaddq_rot270_x(float16x8_t, float16x8_t, mve_pred16_t);
11656	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f32)))
11657	float32x4_t vcaddq_rot270_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11658	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot270_x_f32)))
11659	float32x4_t vcaddq_rot270_x(float32x4_t, float32x4_t, mve_pred16_t);
11660	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f16)))
11661	float16x8_t vcaddq_rot90_f16(float16x8_t, float16x8_t);
11662	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f16)))
11663	float16x8_t vcaddq_rot90(float16x8_t, float16x8_t);
11664	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f32)))
11665	float32x4_t vcaddq_rot90_f32(float32x4_t, float32x4_t);
11666	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_f32)))
11667	float32x4_t vcaddq_rot90(float32x4_t, float32x4_t);
11668	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f16)))
11669	float16x8_t vcaddq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11670	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f16)))
11671	float16x8_t vcaddq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11672	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f32)))
11673	float32x4_t vcaddq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11674	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_m_f32)))
11675	float32x4_t vcaddq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11676	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f16)))
11677	float16x8_t vcaddq_rot90_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11678	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f16)))
11679	float16x8_t vcaddq_rot90_x(float16x8_t, float16x8_t, mve_pred16_t);
11680	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f32)))
11681	float32x4_t vcaddq_rot90_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11682	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcaddq_rot90_x_f32)))
11683	float32x4_t vcaddq_rot90_x(float32x4_t, float32x4_t, mve_pred16_t);
11684	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f16)))
11685	float16x8_t vcmlaq_f16(float16x8_t, float16x8_t, float16x8_t);
11686	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f16)))
11687	float16x8_t vcmlaq(float16x8_t, float16x8_t, float16x8_t);
11688	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f32)))
11689	float32x4_t vcmlaq_f32(float32x4_t, float32x4_t, float32x4_t);
11690	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_f32)))
11691	float32x4_t vcmlaq(float32x4_t, float32x4_t, float32x4_t);
11692	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f16)))
11693	float16x8_t vcmlaq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11694	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f16)))
11695	float16x8_t vcmlaq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11696	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f32)))
11697	float32x4_t vcmlaq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11698	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_m_f32)))
11699	float32x4_t vcmlaq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11700	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f16)))
11701	float16x8_t vcmlaq_rot180_f16(float16x8_t, float16x8_t, float16x8_t);
11702	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f16)))
11703	float16x8_t vcmlaq_rot180(float16x8_t, float16x8_t, float16x8_t);
11704	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f32)))
11705	float32x4_t vcmlaq_rot180_f32(float32x4_t, float32x4_t, float32x4_t);
11706	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_f32)))
11707	float32x4_t vcmlaq_rot180(float32x4_t, float32x4_t, float32x4_t);
11708	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f16)))
11709	float16x8_t vcmlaq_rot180_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11710	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f16)))
11711	float16x8_t vcmlaq_rot180_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11712	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f32)))
11713	float32x4_t vcmlaq_rot180_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11714	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot180_m_f32)))
11715	float32x4_t vcmlaq_rot180_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11716	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f16)))
11717	float16x8_t vcmlaq_rot270_f16(float16x8_t, float16x8_t, float16x8_t);
11718	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f16)))
11719	float16x8_t vcmlaq_rot270(float16x8_t, float16x8_t, float16x8_t);
11720	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f32)))
11721	float32x4_t vcmlaq_rot270_f32(float32x4_t, float32x4_t, float32x4_t);
11722	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_f32)))
11723	float32x4_t vcmlaq_rot270(float32x4_t, float32x4_t, float32x4_t);
11724	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f16)))
11725	float16x8_t vcmlaq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11726	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f16)))
11727	float16x8_t vcmlaq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11728	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f32)))
11729	float32x4_t vcmlaq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11730	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot270_m_f32)))
11731	float32x4_t vcmlaq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11732	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f16)))
11733	float16x8_t vcmlaq_rot90_f16(float16x8_t, float16x8_t, float16x8_t);
11734	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f16)))
11735	float16x8_t vcmlaq_rot90(float16x8_t, float16x8_t, float16x8_t);
11736	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f32)))
11737	float32x4_t vcmlaq_rot90_f32(float32x4_t, float32x4_t, float32x4_t);
11738	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_f32)))
11739	float32x4_t vcmlaq_rot90(float32x4_t, float32x4_t, float32x4_t);
11740	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f16)))
11741	float16x8_t vcmlaq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11742	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f16)))
11743	float16x8_t vcmlaq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11744	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f32)))
11745	float32x4_t vcmlaq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11746	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmlaq_rot90_m_f32)))
11747	float32x4_t vcmlaq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11748	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f16)))
11749	mve_pred16_t vcmpeqq_f16(float16x8_t, float16x8_t);
11750	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f16)))
11751	mve_pred16_t vcmpeqq(float16x8_t, float16x8_t);
11752	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f32)))
11753	mve_pred16_t vcmpeqq_f32(float32x4_t, float32x4_t);
11754	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_f32)))
11755	mve_pred16_t vcmpeqq(float32x4_t, float32x4_t);
11756	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f16)))
11757	mve_pred16_t vcmpeqq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11758	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f16)))
11759	mve_pred16_t vcmpeqq_m(float16x8_t, float16x8_t, mve_pred16_t);
11760	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f32)))
11761	mve_pred16_t vcmpeqq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11762	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_f32)))
11763	mve_pred16_t vcmpeqq_m(float32x4_t, float32x4_t, mve_pred16_t);
11764	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f16)))
11765	mve_pred16_t vcmpeqq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11766	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f16)))
11767	mve_pred16_t vcmpeqq_m(float16x8_t, float16_t, mve_pred16_t);
11768	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f32)))
11769	mve_pred16_t vcmpeqq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11770	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_m_n_f32)))
11771	mve_pred16_t vcmpeqq_m(float32x4_t, float32_t, mve_pred16_t);
11772	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f16)))
11773	mve_pred16_t vcmpeqq_n_f16(float16x8_t, float16_t);
11774	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f16)))
11775	mve_pred16_t vcmpeqq(float16x8_t, float16_t);
11776	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f32)))
11777	mve_pred16_t vcmpeqq_n_f32(float32x4_t, float32_t);
11778	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpeqq_n_f32)))
11779	mve_pred16_t vcmpeqq(float32x4_t, float32_t);
11780	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f16)))
11781	mve_pred16_t vcmpgeq_f16(float16x8_t, float16x8_t);
11782	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f16)))
11783	mve_pred16_t vcmpgeq(float16x8_t, float16x8_t);
11784	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f32)))
11785	mve_pred16_t vcmpgeq_f32(float32x4_t, float32x4_t);
11786	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_f32)))
11787	mve_pred16_t vcmpgeq(float32x4_t, float32x4_t);
11788	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f16)))
11789	mve_pred16_t vcmpgeq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11790	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f16)))
11791	mve_pred16_t vcmpgeq_m(float16x8_t, float16x8_t, mve_pred16_t);
11792	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f32)))
11793	mve_pred16_t vcmpgeq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11794	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_f32)))
11795	mve_pred16_t vcmpgeq_m(float32x4_t, float32x4_t, mve_pred16_t);
11796	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f16)))
11797	mve_pred16_t vcmpgeq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11798	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f16)))
11799	mve_pred16_t vcmpgeq_m(float16x8_t, float16_t, mve_pred16_t);
11800	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f32)))
11801	mve_pred16_t vcmpgeq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11802	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_m_n_f32)))
11803	mve_pred16_t vcmpgeq_m(float32x4_t, float32_t, mve_pred16_t);
11804	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f16)))
11805	mve_pred16_t vcmpgeq_n_f16(float16x8_t, float16_t);
11806	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f16)))
11807	mve_pred16_t vcmpgeq(float16x8_t, float16_t);
11808	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f32)))
11809	mve_pred16_t vcmpgeq_n_f32(float32x4_t, float32_t);
11810	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgeq_n_f32)))
11811	mve_pred16_t vcmpgeq(float32x4_t, float32_t);
11812	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f16)))
11813	mve_pred16_t vcmpgtq_f16(float16x8_t, float16x8_t);
11814	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f16)))
11815	mve_pred16_t vcmpgtq(float16x8_t, float16x8_t);
11816	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f32)))
11817	mve_pred16_t vcmpgtq_f32(float32x4_t, float32x4_t);
11818	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_f32)))
11819	mve_pred16_t vcmpgtq(float32x4_t, float32x4_t);
11820	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f16)))
11821	mve_pred16_t vcmpgtq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11822	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f16)))
11823	mve_pred16_t vcmpgtq_m(float16x8_t, float16x8_t, mve_pred16_t);
11824	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f32)))
11825	mve_pred16_t vcmpgtq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11826	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_f32)))
11827	mve_pred16_t vcmpgtq_m(float32x4_t, float32x4_t, mve_pred16_t);
11828	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f16)))
11829	mve_pred16_t vcmpgtq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11830	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f16)))
11831	mve_pred16_t vcmpgtq_m(float16x8_t, float16_t, mve_pred16_t);
11832	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f32)))
11833	mve_pred16_t vcmpgtq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11834	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_m_n_f32)))
11835	mve_pred16_t vcmpgtq_m(float32x4_t, float32_t, mve_pred16_t);
11836	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f16)))
11837	mve_pred16_t vcmpgtq_n_f16(float16x8_t, float16_t);
11838	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f16)))
11839	mve_pred16_t vcmpgtq(float16x8_t, float16_t);
11840	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f32)))
11841	mve_pred16_t vcmpgtq_n_f32(float32x4_t, float32_t);
11842	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpgtq_n_f32)))
11843	mve_pred16_t vcmpgtq(float32x4_t, float32_t);
11844	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f16)))
11845	mve_pred16_t vcmpleq_f16(float16x8_t, float16x8_t);
11846	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f16)))
11847	mve_pred16_t vcmpleq(float16x8_t, float16x8_t);
11848	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f32)))
11849	mve_pred16_t vcmpleq_f32(float32x4_t, float32x4_t);
11850	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_f32)))
11851	mve_pred16_t vcmpleq(float32x4_t, float32x4_t);
11852	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f16)))
11853	mve_pred16_t vcmpleq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11854	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f16)))
11855	mve_pred16_t vcmpleq_m(float16x8_t, float16x8_t, mve_pred16_t);
11856	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f32)))
11857	mve_pred16_t vcmpleq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11858	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_f32)))
11859	mve_pred16_t vcmpleq_m(float32x4_t, float32x4_t, mve_pred16_t);
11860	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f16)))
11861	mve_pred16_t vcmpleq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11862	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f16)))
11863	mve_pred16_t vcmpleq_m(float16x8_t, float16_t, mve_pred16_t);
11864	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f32)))
11865	mve_pred16_t vcmpleq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11866	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_m_n_f32)))
11867	mve_pred16_t vcmpleq_m(float32x4_t, float32_t, mve_pred16_t);
11868	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f16)))
11869	mve_pred16_t vcmpleq_n_f16(float16x8_t, float16_t);
11870	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f16)))
11871	mve_pred16_t vcmpleq(float16x8_t, float16_t);
11872	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f32)))
11873	mve_pred16_t vcmpleq_n_f32(float32x4_t, float32_t);
11874	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpleq_n_f32)))
11875	mve_pred16_t vcmpleq(float32x4_t, float32_t);
11876	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f16)))
11877	mve_pred16_t vcmpltq_f16(float16x8_t, float16x8_t);
11878	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f16)))
11879	mve_pred16_t vcmpltq(float16x8_t, float16x8_t);
11880	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f32)))
11881	mve_pred16_t vcmpltq_f32(float32x4_t, float32x4_t);
11882	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_f32)))
11883	mve_pred16_t vcmpltq(float32x4_t, float32x4_t);
11884	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f16)))
11885	mve_pred16_t vcmpltq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11886	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f16)))
11887	mve_pred16_t vcmpltq_m(float16x8_t, float16x8_t, mve_pred16_t);
11888	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f32)))
11889	mve_pred16_t vcmpltq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11890	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_f32)))
11891	mve_pred16_t vcmpltq_m(float32x4_t, float32x4_t, mve_pred16_t);
11892	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f16)))
11893	mve_pred16_t vcmpltq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11894	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f16)))
11895	mve_pred16_t vcmpltq_m(float16x8_t, float16_t, mve_pred16_t);
11896	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f32)))
11897	mve_pred16_t vcmpltq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11898	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_m_n_f32)))
11899	mve_pred16_t vcmpltq_m(float32x4_t, float32_t, mve_pred16_t);
11900	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f16)))
11901	mve_pred16_t vcmpltq_n_f16(float16x8_t, float16_t);
11902	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f16)))
11903	mve_pred16_t vcmpltq(float16x8_t, float16_t);
11904	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f32)))
11905	mve_pred16_t vcmpltq_n_f32(float32x4_t, float32_t);
11906	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpltq_n_f32)))
11907	mve_pred16_t vcmpltq(float32x4_t, float32_t);
11908	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f16)))
11909	mve_pred16_t vcmpneq_f16(float16x8_t, float16x8_t);
11910	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f16)))
11911	mve_pred16_t vcmpneq(float16x8_t, float16x8_t);
11912	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f32)))
11913	mve_pred16_t vcmpneq_f32(float32x4_t, float32x4_t);
11914	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_f32)))
11915	mve_pred16_t vcmpneq(float32x4_t, float32x4_t);
11916	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f16)))
11917	mve_pred16_t vcmpneq_m_f16(float16x8_t, float16x8_t, mve_pred16_t);
11918	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f16)))
11919	mve_pred16_t vcmpneq_m(float16x8_t, float16x8_t, mve_pred16_t);
11920	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f32)))
11921	mve_pred16_t vcmpneq_m_f32(float32x4_t, float32x4_t, mve_pred16_t);
11922	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_f32)))
11923	mve_pred16_t vcmpneq_m(float32x4_t, float32x4_t, mve_pred16_t);
11924	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f16)))
11925	mve_pred16_t vcmpneq_m_n_f16(float16x8_t, float16_t, mve_pred16_t);
11926	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f16)))
11927	mve_pred16_t vcmpneq_m(float16x8_t, float16_t, mve_pred16_t);
11928	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f32)))
11929	mve_pred16_t vcmpneq_m_n_f32(float32x4_t, float32_t, mve_pred16_t);
11930	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_m_n_f32)))
11931	mve_pred16_t vcmpneq_m(float32x4_t, float32_t, mve_pred16_t);
11932	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f16)))
11933	mve_pred16_t vcmpneq_n_f16(float16x8_t, float16_t);
11934	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f16)))
11935	mve_pred16_t vcmpneq(float16x8_t, float16_t);
11936	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f32)))
11937	mve_pred16_t vcmpneq_n_f32(float32x4_t, float32_t);
11938	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmpneq_n_f32)))
11939	mve_pred16_t vcmpneq(float32x4_t, float32_t);
11940	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f16)))
11941	float16x8_t vcmulq_f16(float16x8_t, float16x8_t);
11942	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f16)))
11943	float16x8_t vcmulq(float16x8_t, float16x8_t);
11944	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f32)))
11945	float32x4_t vcmulq_f32(float32x4_t, float32x4_t);
11946	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_f32)))
11947	float32x4_t vcmulq(float32x4_t, float32x4_t);
11948	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f16)))
11949	float16x8_t vcmulq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11950	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f16)))
11951	float16x8_t vcmulq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11952	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f32)))
11953	float32x4_t vcmulq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11954	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_m_f32)))
11955	float32x4_t vcmulq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11956	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f16)))
11957	float16x8_t vcmulq_rot180_f16(float16x8_t, float16x8_t);
11958	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f16)))
11959	float16x8_t vcmulq_rot180(float16x8_t, float16x8_t);
11960	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f32)))
11961	float32x4_t vcmulq_rot180_f32(float32x4_t, float32x4_t);
11962	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_f32)))
11963	float32x4_t vcmulq_rot180(float32x4_t, float32x4_t);
11964	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f16)))
11965	float16x8_t vcmulq_rot180_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11966	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f16)))
11967	float16x8_t vcmulq_rot180_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11968	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f32)))
11969	float32x4_t vcmulq_rot180_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11970	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_m_f32)))
11971	float32x4_t vcmulq_rot180_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11972	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f16)))
11973	float16x8_t vcmulq_rot180_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11974	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f16)))
11975	float16x8_t vcmulq_rot180_x(float16x8_t, float16x8_t, mve_pred16_t);
11976	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f32)))
11977	float32x4_t vcmulq_rot180_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
11978	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot180_x_f32)))
11979	float32x4_t vcmulq_rot180_x(float32x4_t, float32x4_t, mve_pred16_t);
11980	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f16)))
11981	float16x8_t vcmulq_rot270_f16(float16x8_t, float16x8_t);
11982	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f16)))
11983	float16x8_t vcmulq_rot270(float16x8_t, float16x8_t);
11984	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f32)))
11985	float32x4_t vcmulq_rot270_f32(float32x4_t, float32x4_t);
11986	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_f32)))
11987	float32x4_t vcmulq_rot270(float32x4_t, float32x4_t);
11988	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f16)))
11989	float16x8_t vcmulq_rot270_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11990	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f16)))
11991	float16x8_t vcmulq_rot270_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
11992	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f32)))
11993	float32x4_t vcmulq_rot270_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11994	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_m_f32)))
11995	float32x4_t vcmulq_rot270_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
11996	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f16)))
11997	float16x8_t vcmulq_rot270_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
11998	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f16)))
11999	float16x8_t vcmulq_rot270_x(float16x8_t, float16x8_t, mve_pred16_t);
12000	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f32)))
12001	float32x4_t vcmulq_rot270_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12002	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot270_x_f32)))
12003	float32x4_t vcmulq_rot270_x(float32x4_t, float32x4_t, mve_pred16_t);
12004	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f16)))
12005	float16x8_t vcmulq_rot90_f16(float16x8_t, float16x8_t);
12006	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f16)))
12007	float16x8_t vcmulq_rot90(float16x8_t, float16x8_t);
12008	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f32)))
12009	float32x4_t vcmulq_rot90_f32(float32x4_t, float32x4_t);
12010	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_f32)))
12011	float32x4_t vcmulq_rot90(float32x4_t, float32x4_t);
12012	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f16)))
12013	float16x8_t vcmulq_rot90_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12014	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f16)))
12015	float16x8_t vcmulq_rot90_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12016	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f32)))
12017	float32x4_t vcmulq_rot90_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12018	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_m_f32)))
12019	float32x4_t vcmulq_rot90_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12020	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f16)))
12021	float16x8_t vcmulq_rot90_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12022	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f16)))
12023	float16x8_t vcmulq_rot90_x(float16x8_t, float16x8_t, mve_pred16_t);
12024	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f32)))
12025	float32x4_t vcmulq_rot90_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12026	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_rot90_x_f32)))
12027	float32x4_t vcmulq_rot90_x(float32x4_t, float32x4_t, mve_pred16_t);
12028	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f16)))
12029	float16x8_t vcmulq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12030	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f16)))
12031	float16x8_t vcmulq_x(float16x8_t, float16x8_t, mve_pred16_t);
12032	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f32)))
12033	float32x4_t vcmulq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12034	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vcmulq_x_f32)))
12035	float32x4_t vcmulq_x(float32x4_t, float32x4_t, mve_pred16_t);
12036	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_f16)))
12037	float16x8_t vcreateq_f16(uint64_t, uint64_t);
12038	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcreateq_f32)))
12039	float32x4_t vcreateq_f32(uint64_t, uint64_t);
12040	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvtbq_f16_f32)))
12041	float16x8_t vcvtbq_f16_f32(float16x8_t, float32x4_t);
12042	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvtbq_m_f16_f32)))
12043	float16x8_t vcvtbq_m_f16_f32(float16x8_t, float32x4_t, mve_pred16_t);
12044	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvttq_f16_f32)))
12045	float16x8_t vcvttq_f16_f32(float16x8_t, float32x4_t);
12046	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vcvttq_m_f16_f32)))
12047	float16x8_t vcvttq_m_f16_f32(float16x8_t, float32x4_t, mve_pred16_t);
12048	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_f16)))
12049	float16x8_t veorq_f16(float16x8_t, float16x8_t);
12050	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_f16)))
12051	float16x8_t veorq(float16x8_t, float16x8_t);
12052	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_f32)))
12053	float32x4_t veorq_f32(float32x4_t, float32x4_t);
12054	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_f32)))
12055	float32x4_t veorq(float32x4_t, float32x4_t);
12056	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f16)))
12057	float16x8_t veorq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12058	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f16)))
12059	float16x8_t veorq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12060	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f32)))
12061	float32x4_t veorq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12062	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_m_f32)))
12063	float32x4_t veorq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12064	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f16)))
12065	float16x8_t veorq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12066	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f16)))
12067	float16x8_t veorq_x(float16x8_t, float16x8_t, mve_pred16_t);
12068	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f32)))
12069	float32x4_t veorq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12070	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_veorq_x_f32)))
12071	float32x4_t veorq_x(float32x4_t, float32x4_t, mve_pred16_t);
12072	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f16)))
12073	float16_t vgetq_lane_f16(float16x8_t, int);
12074	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f16)))
12075	float16_t vgetq_lane(float16x8_t, int);
12076	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f32)))
12077	float32_t vgetq_lane_f32(float32x4_t, int);
12078	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vgetq_lane_f32)))
12079	float32_t vgetq_lane(float32x4_t, int);
12080	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_f16)))
12081	float16x8_t vld1q_f16(const float16_t *);
12082	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_f16)))
12083	float16x8_t vld1q(const float16_t *);
12084	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_f32)))
12085	float32x4_t vld1q_f32(const float32_t *);
12086	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_f32)))
12087	float32x4_t vld1q(const float32_t *);
12088	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f16)))
12089	float16x8_t vld1q_z_f16(const float16_t *, mve_pred16_t);
12090	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f16)))
12091	float16x8_t vld1q_z(const float16_t *, mve_pred16_t);
12092	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f32)))
12093	float32x4_t vld1q_z_f32(const float32_t *, mve_pred16_t);
12094	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld1q_z_f32)))
12095	float32x4_t vld1q_z(const float32_t *, mve_pred16_t);
12096	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_f16)))
12097	float16x8x2_t vld2q_f16(const float16_t *);
12098	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_f16)))
12099	float16x8x2_t vld2q(const float16_t *);
12100	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld2q_f32)))
12101	float32x4x2_t vld2q_f32(const float32_t *);
12102	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld2q_f32)))
12103	float32x4x2_t vld2q(const float32_t *);
12104	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_f16)))
12105	float16x8x4_t vld4q_f16(const float16_t *);
12106	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_f16)))
12107	float16x8x4_t vld4q(const float16_t *);
12108	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vld4q_f32)))
12109	float32x4x4_t vld4q_f32(const float32_t *);
12110	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vld4q_f32)))
12111	float32x4x4_t vld4q(const float32_t *);
12112	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_f16)))
12113	float16x8_t vldrhq_f16(const float16_t *);
12114	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_f16)))
12115	float16x8_t vldrhq_gather_offset_f16(const float16_t *, uint16x8_t);
12116	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_f16)))
12117	float16x8_t vldrhq_gather_offset(const float16_t *, uint16x8_t);
12118	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_f16)))
12119	float16x8_t vldrhq_gather_offset_z_f16(const float16_t *, uint16x8_t, mve_pred16_t);
12120	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_offset_z_f16)))
12121	float16x8_t vldrhq_gather_offset_z(const float16_t *, uint16x8_t, mve_pred16_t);
12122	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_f16)))
12123	float16x8_t vldrhq_gather_shifted_offset_f16(const float16_t *, uint16x8_t);
12124	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_f16)))
12125	float16x8_t vldrhq_gather_shifted_offset(const float16_t *, uint16x8_t);
12126	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_f16)))
12127	float16x8_t vldrhq_gather_shifted_offset_z_f16(const float16_t *, uint16x8_t, mve_pred16_t);
12128	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrhq_gather_shifted_offset_z_f16)))
12129	float16x8_t vldrhq_gather_shifted_offset_z(const float16_t *, uint16x8_t, mve_pred16_t);
12130	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrhq_z_f16)))
12131	float16x8_t vldrhq_z_f16(const float16_t *, mve_pred16_t);
12132	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_f32)))
12133	float32x4_t vldrwq_f32(const float32_t *);
12134	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_f32)))
12135	float32x4_t vldrwq_gather_base_f32(uint32x4_t, int);
12136	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_f32)))
12137	float32x4_t vldrwq_gather_base_wb_f32(uint32x4_t *, int);
12138	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_wb_z_f32)))
12139	float32x4_t vldrwq_gather_base_wb_z_f32(uint32x4_t *, int, mve_pred16_t);
12140	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_base_z_f32)))
12141	float32x4_t vldrwq_gather_base_z_f32(uint32x4_t, int, mve_pred16_t);
12142	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_f32)))
12143	float32x4_t vldrwq_gather_offset_f32(const float32_t *, uint32x4_t);
12144	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_f32)))
12145	float32x4_t vldrwq_gather_offset(const float32_t *, uint32x4_t);
12146	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_f32)))
12147	float32x4_t vldrwq_gather_offset_z_f32(const float32_t *, uint32x4_t, mve_pred16_t);
12148	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_offset_z_f32)))
12149	float32x4_t vldrwq_gather_offset_z(const float32_t *, uint32x4_t, mve_pred16_t);
12150	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_f32)))
12151	float32x4_t vldrwq_gather_shifted_offset_f32(const float32_t *, uint32x4_t);
12152	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_f32)))
12153	float32x4_t vldrwq_gather_shifted_offset(const float32_t *, uint32x4_t);
12154	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_f32)))
12155	float32x4_t vldrwq_gather_shifted_offset_z_f32(const float32_t *, uint32x4_t, mve_pred16_t);
12156	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vldrwq_gather_shifted_offset_z_f32)))
12157	float32x4_t vldrwq_gather_shifted_offset_z(const float32_t *, uint32x4_t, mve_pred16_t);
12158	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vldrwq_z_f32)))
12159	float32x4_t vldrwq_z_f32(const float32_t *, mve_pred16_t);
12160	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f16)))
12161	float16x8_t vmaxnmq_f16(float16x8_t, float16x8_t);
12162	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f16)))
12163	float16x8_t vmaxnmq(float16x8_t, float16x8_t);
12164	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f32)))
12165	float32x4_t vmaxnmq_f32(float32x4_t, float32x4_t);
12166	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_f32)))
12167	float32x4_t vmaxnmq(float32x4_t, float32x4_t);
12168	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f16)))
12169	float16x8_t vmaxnmq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12170	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f16)))
12171	float16x8_t vmaxnmq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12172	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f32)))
12173	float32x4_t vmaxnmq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12174	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_m_f32)))
12175	float32x4_t vmaxnmq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12176	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f16)))
12177	float16x8_t vmaxnmq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12178	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f16)))
12179	float16x8_t vmaxnmq_x(float16x8_t, float16x8_t, mve_pred16_t);
12180	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f32)))
12181	float32x4_t vmaxnmq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12182	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmaxnmq_x_f32)))
12183	float32x4_t vmaxnmq_x(float32x4_t, float32x4_t, mve_pred16_t);
12184	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f16)))
12185	float16x8_t vminnmq_f16(float16x8_t, float16x8_t);
12186	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f16)))
12187	float16x8_t vminnmq(float16x8_t, float16x8_t);
12188	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f32)))
12189	float32x4_t vminnmq_f32(float32x4_t, float32x4_t);
12190	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_f32)))
12191	float32x4_t vminnmq(float32x4_t, float32x4_t);
12192	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f16)))
12193	float16x8_t vminnmq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12194	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f16)))
12195	float16x8_t vminnmq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12196	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f32)))
12197	float32x4_t vminnmq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12198	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_m_f32)))
12199	float32x4_t vminnmq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12200	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f16)))
12201	float16x8_t vminnmq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12202	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f16)))
12203	float16x8_t vminnmq_x(float16x8_t, float16x8_t, mve_pred16_t);
12204	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f32)))
12205	float32x4_t vminnmq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12206	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vminnmq_x_f32)))
12207	float32x4_t vminnmq_x(float32x4_t, float32x4_t, mve_pred16_t);
12208	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_f16)))
12209	float16x8_t vmulq_f16(float16x8_t, float16x8_t);
12210	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_f16)))
12211	float16x8_t vmulq(float16x8_t, float16x8_t);
12212	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_f32)))
12213	float32x4_t vmulq_f32(float32x4_t, float32x4_t);
12214	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_f32)))
12215	float32x4_t vmulq(float32x4_t, float32x4_t);
12216	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f16)))
12217	float16x8_t vmulq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12218	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f16)))
12219	float16x8_t vmulq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12220	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f32)))
12221	float32x4_t vmulq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12222	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_m_f32)))
12223	float32x4_t vmulq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12224	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f16)))
12225	float16x8_t vmulq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12226	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f16)))
12227	float16x8_t vmulq_x(float16x8_t, float16x8_t, mve_pred16_t);
12228	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f32)))
12229	float32x4_t vmulq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12230	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vmulq_x_f32)))
12231	float32x4_t vmulq_x(float32x4_t, float32x4_t, mve_pred16_t);
12232	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_f16)))
12233	float16x8_t vornq_f16(float16x8_t, float16x8_t);
12234	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_f16)))
12235	float16x8_t vornq(float16x8_t, float16x8_t);
12236	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_f32)))
12237	float32x4_t vornq_f32(float32x4_t, float32x4_t);
12238	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_f32)))
12239	float32x4_t vornq(float32x4_t, float32x4_t);
12240	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f16)))
12241	float16x8_t vornq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12242	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f16)))
12243	float16x8_t vornq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12244	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f32)))
12245	float32x4_t vornq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12246	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_m_f32)))
12247	float32x4_t vornq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12248	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f16)))
12249	float16x8_t vornq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12250	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f16)))
12251	float16x8_t vornq_x(float16x8_t, float16x8_t, mve_pred16_t);
12252	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f32)))
12253	float32x4_t vornq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12254	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vornq_x_f32)))
12255	float32x4_t vornq_x(float32x4_t, float32x4_t, mve_pred16_t);
12256	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_f16)))
12257	float16x8_t vorrq_f16(float16x8_t, float16x8_t);
12258	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_f16)))
12259	float16x8_t vorrq(float16x8_t, float16x8_t);
12260	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_f32)))
12261	float32x4_t vorrq_f32(float32x4_t, float32x4_t);
12262	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_f32)))
12263	float32x4_t vorrq(float32x4_t, float32x4_t);
12264	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f16)))
12265	float16x8_t vorrq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12266	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f16)))
12267	float16x8_t vorrq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12268	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f32)))
12269	float32x4_t vorrq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12270	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_m_f32)))
12271	float32x4_t vorrq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12272	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f16)))
12273	float16x8_t vorrq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12274	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f16)))
12275	float16x8_t vorrq_x(float16x8_t, float16x8_t, mve_pred16_t);
12276	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f32)))
12277	float32x4_t vorrq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12278	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vorrq_x_f32)))
12279	float32x4_t vorrq_x(float32x4_t, float32x4_t, mve_pred16_t);
12280	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_f16)))
12281	float16x8_t vpselq_f16(float16x8_t, float16x8_t, mve_pred16_t);
12282	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_f16)))
12283	float16x8_t vpselq(float16x8_t, float16x8_t, mve_pred16_t);
12284	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vpselq_f32)))
12285	float32x4_t vpselq_f32(float32x4_t, float32x4_t, mve_pred16_t);
12286	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vpselq_f32)))
12287	float32x4_t vpselq(float32x4_t, float32x4_t, mve_pred16_t);
12288	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_f32)))
12289	float16x8_t vreinterpretq_f16_f32(float32x4_t);
12290	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_f32)))
12291	float16x8_t vreinterpretq_f16(float32x4_t);
12292	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s16)))
12293	float16x8_t vreinterpretq_f16_s16(int16x8_t);
12294	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s16)))
12295	float16x8_t vreinterpretq_f16(int16x8_t);
12296	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s32)))
12297	float16x8_t vreinterpretq_f16_s32(int32x4_t);
12298	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s32)))
12299	float16x8_t vreinterpretq_f16(int32x4_t);
12300	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s64)))
12301	float16x8_t vreinterpretq_f16_s64(int64x2_t);
12302	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s64)))
12303	float16x8_t vreinterpretq_f16(int64x2_t);
12304	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s8)))
12305	float16x8_t vreinterpretq_f16_s8(int8x16_t);
12306	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_s8)))
12307	float16x8_t vreinterpretq_f16(int8x16_t);
12308	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u16)))
12309	float16x8_t vreinterpretq_f16_u16(uint16x8_t);
12310	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u16)))
12311	float16x8_t vreinterpretq_f16(uint16x8_t);
12312	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u32)))
12313	float16x8_t vreinterpretq_f16_u32(uint32x4_t);
12314	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u32)))
12315	float16x8_t vreinterpretq_f16(uint32x4_t);
12316	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u64)))
12317	float16x8_t vreinterpretq_f16_u64(uint64x2_t);
12318	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u64)))
12319	float16x8_t vreinterpretq_f16(uint64x2_t);
12320	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u8)))
12321	float16x8_t vreinterpretq_f16_u8(uint8x16_t);
12322	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f16_u8)))
12323	float16x8_t vreinterpretq_f16(uint8x16_t);
12324	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_f16)))
12325	float32x4_t vreinterpretq_f32_f16(float16x8_t);
12326	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_f16)))
12327	float32x4_t vreinterpretq_f32(float16x8_t);
12328	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s16)))
12329	float32x4_t vreinterpretq_f32_s16(int16x8_t);
12330	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s16)))
12331	float32x4_t vreinterpretq_f32(int16x8_t);
12332	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s32)))
12333	float32x4_t vreinterpretq_f32_s32(int32x4_t);
12334	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s32)))
12335	float32x4_t vreinterpretq_f32(int32x4_t);
12336	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s64)))
12337	float32x4_t vreinterpretq_f32_s64(int64x2_t);
12338	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s64)))
12339	float32x4_t vreinterpretq_f32(int64x2_t);
12340	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s8)))
12341	float32x4_t vreinterpretq_f32_s8(int8x16_t);
12342	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_s8)))
12343	float32x4_t vreinterpretq_f32(int8x16_t);
12344	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u16)))
12345	float32x4_t vreinterpretq_f32_u16(uint16x8_t);
12346	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u16)))
12347	float32x4_t vreinterpretq_f32(uint16x8_t);
12348	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u32)))
12349	float32x4_t vreinterpretq_f32_u32(uint32x4_t);
12350	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u32)))
12351	float32x4_t vreinterpretq_f32(uint32x4_t);
12352	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u64)))
12353	float32x4_t vreinterpretq_f32_u64(uint64x2_t);
12354	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u64)))
12355	float32x4_t vreinterpretq_f32(uint64x2_t);
12356	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u8)))
12357	float32x4_t vreinterpretq_f32_u8(uint8x16_t);
12358	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_f32_u8)))
12359	float32x4_t vreinterpretq_f32(uint8x16_t);
12360	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f16)))
12361	int16x8_t vreinterpretq_s16_f16(float16x8_t);
12362	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f16)))
12363	int16x8_t vreinterpretq_s16(float16x8_t);
12364	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f32)))
12365	int16x8_t vreinterpretq_s16_f32(float32x4_t);
12366	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s16_f32)))
12367	int16x8_t vreinterpretq_s16(float32x4_t);
12368	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f16)))
12369	int32x4_t vreinterpretq_s32_f16(float16x8_t);
12370	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f16)))
12371	int32x4_t vreinterpretq_s32(float16x8_t);
12372	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f32)))
12373	int32x4_t vreinterpretq_s32_f32(float32x4_t);
12374	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s32_f32)))
12375	int32x4_t vreinterpretq_s32(float32x4_t);
12376	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f16)))
12377	int64x2_t vreinterpretq_s64_f16(float16x8_t);
12378	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f16)))
12379	int64x2_t vreinterpretq_s64(float16x8_t);
12380	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f32)))
12381	int64x2_t vreinterpretq_s64_f32(float32x4_t);
12382	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s64_f32)))
12383	int64x2_t vreinterpretq_s64(float32x4_t);
12384	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f16)))
12385	int8x16_t vreinterpretq_s8_f16(float16x8_t);
12386	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f16)))
12387	int8x16_t vreinterpretq_s8(float16x8_t);
12388	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f32)))
12389	int8x16_t vreinterpretq_s8_f32(float32x4_t);
12390	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_s8_f32)))
12391	int8x16_t vreinterpretq_s8(float32x4_t);
12392	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f16)))
12393	uint16x8_t vreinterpretq_u16_f16(float16x8_t);
12394	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f16)))
12395	uint16x8_t vreinterpretq_u16(float16x8_t);
12396	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f32)))
12397	uint16x8_t vreinterpretq_u16_f32(float32x4_t);
12398	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u16_f32)))
12399	uint16x8_t vreinterpretq_u16(float32x4_t);
12400	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f16)))
12401	uint32x4_t vreinterpretq_u32_f16(float16x8_t);
12402	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f16)))
12403	uint32x4_t vreinterpretq_u32(float16x8_t);
12404	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f32)))
12405	uint32x4_t vreinterpretq_u32_f32(float32x4_t);
12406	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u32_f32)))
12407	uint32x4_t vreinterpretq_u32(float32x4_t);
12408	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f16)))
12409	uint64x2_t vreinterpretq_u64_f16(float16x8_t);
12410	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f16)))
12411	uint64x2_t vreinterpretq_u64(float16x8_t);
12412	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f32)))
12413	uint64x2_t vreinterpretq_u64_f32(float32x4_t);
12414	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u64_f32)))
12415	uint64x2_t vreinterpretq_u64(float32x4_t);
12416	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f16)))
12417	uint8x16_t vreinterpretq_u8_f16(float16x8_t);
12418	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f16)))
12419	uint8x16_t vreinterpretq_u8(float16x8_t);
12420	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f32)))
12421	uint8x16_t vreinterpretq_u8_f32(float32x4_t);
12422	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vreinterpretq_u8_f32)))
12423	uint8x16_t vreinterpretq_u8(float32x4_t);
12424	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f16)))
12425	float16x8_t vsetq_lane_f16(float16_t, float16x8_t, int);
12426	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f16)))
12427	float16x8_t vsetq_lane(float16_t, float16x8_t, int);
12428	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f32)))
12429	float32x4_t vsetq_lane_f32(float32_t, float32x4_t, int);
12430	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsetq_lane_f32)))
12431	float32x4_t vsetq_lane(float32_t, float32x4_t, int);
12432	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_f16)))
12433	void vst1q_f16(float16_t *, float16x8_t);
12434	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_f16)))
12435	void vst1q(float16_t *, float16x8_t);
12436	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_f32)))
12437	void vst1q_f32(float32_t *, float32x4_t);
12438	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_f32)))
12439	void vst1q(float32_t *, float32x4_t);
12440	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f16)))
12441	void vst1q_p_f16(float16_t *, float16x8_t, mve_pred16_t);
12442	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f16)))
12443	void vst1q_p(float16_t *, float16x8_t, mve_pred16_t);
12444	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f32)))
12445	void vst1q_p_f32(float32_t *, float32x4_t, mve_pred16_t);
12446	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst1q_p_f32)))
12447	void vst1q_p(float32_t *, float32x4_t, mve_pred16_t);
12448	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_f16)))
12449	void vst2q_f16(float16_t *, float16x8x2_t);
12450	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_f16)))
12451	void vst2q(float16_t *, float16x8x2_t);
12452	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst2q_f32)))
12453	void vst2q_f32(float32_t *, float32x4x2_t);
12454	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst2q_f32)))
12455	void vst2q(float32_t *, float32x4x2_t);
12456	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_f16)))
12457	void vst4q_f16(float16_t *, float16x8x4_t);
12458	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_f16)))
12459	void vst4q(float16_t *, float16x8x4_t);
12460	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vst4q_f32)))
12461	void vst4q_f32(float32_t *, float32x4x4_t);
12462	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vst4q_f32)))
12463	void vst4q(float32_t *, float32x4x4_t);
12464	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_f16)))
12465	void vstrhq_f16(float16_t *, float16x8_t);
12466	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_f16)))
12467	void vstrhq(float16_t *, float16x8_t);
12468	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_f16)))
12469	void vstrhq_p_f16(float16_t *, float16x8_t, mve_pred16_t);
12470	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_p_f16)))
12471	void vstrhq_p(float16_t *, float16x8_t, mve_pred16_t);
12472	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_f16)))
12473	void vstrhq_scatter_offset_f16(float16_t *, uint16x8_t, float16x8_t);
12474	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_f16)))
12475	void vstrhq_scatter_offset(float16_t *, uint16x8_t, float16x8_t);
12476	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_f16)))
12477	void vstrhq_scatter_offset_p_f16(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
12478	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_offset_p_f16)))
12479	void vstrhq_scatter_offset_p(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
12480	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_f16)))
12481	void vstrhq_scatter_shifted_offset_f16(float16_t *, uint16x8_t, float16x8_t);
12482	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_f16)))
12483	void vstrhq_scatter_shifted_offset(float16_t *, uint16x8_t, float16x8_t);
12484	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_f16)))
12485	void vstrhq_scatter_shifted_offset_p_f16(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
12486	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrhq_scatter_shifted_offset_p_f16)))
12487	void vstrhq_scatter_shifted_offset_p(float16_t *, uint16x8_t, float16x8_t, mve_pred16_t);
12488	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_f32)))
12489	void vstrwq_f32(float32_t *, float32x4_t);
12490	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_f32)))
12491	void vstrwq(float32_t *, float32x4_t);
12492	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_f32)))
12493	void vstrwq_p_f32(float32_t *, float32x4_t, mve_pred16_t);
12494	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_p_f32)))
12495	void vstrwq_p(float32_t *, float32x4_t, mve_pred16_t);
12496	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_f32)))
12497	void vstrwq_scatter_base_f32(uint32x4_t, int, float32x4_t);
12498	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_f32)))
12499	void vstrwq_scatter_base(uint32x4_t, int, float32x4_t);
12500	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_f32)))
12501	void vstrwq_scatter_base_p_f32(uint32x4_t, int, float32x4_t, mve_pred16_t);
12502	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_p_f32)))
12503	void vstrwq_scatter_base_p(uint32x4_t, int, float32x4_t, mve_pred16_t);
12504	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_f32)))
12505	void vstrwq_scatter_base_wb_f32(uint32x4_t *, int, float32x4_t);
12506	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_f32)))
12507	void vstrwq_scatter_base_wb(uint32x4_t *, int, float32x4_t);
12508	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_f32)))
12509	void vstrwq_scatter_base_wb_p_f32(uint32x4_t *, int, float32x4_t, mve_pred16_t);
12510	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_base_wb_p_f32)))
12511	void vstrwq_scatter_base_wb_p(uint32x4_t *, int, float32x4_t, mve_pred16_t);
12512	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_f32)))
12513	void vstrwq_scatter_offset_f32(float32_t *, uint32x4_t, float32x4_t);
12514	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_f32)))
12515	void vstrwq_scatter_offset(float32_t *, uint32x4_t, float32x4_t);
12516	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_f32)))
12517	void vstrwq_scatter_offset_p_f32(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
12518	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_offset_p_f32)))
12519	void vstrwq_scatter_offset_p(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
12520	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_f32)))
12521	void vstrwq_scatter_shifted_offset_f32(float32_t *, uint32x4_t, float32x4_t);
12522	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_f32)))
12523	void vstrwq_scatter_shifted_offset(float32_t *, uint32x4_t, float32x4_t);
12524	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_f32)))
12525	void vstrwq_scatter_shifted_offset_p_f32(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
12526	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vstrwq_scatter_shifted_offset_p_f32)))
12527	void vstrwq_scatter_shifted_offset_p(float32_t *, uint32x4_t, float32x4_t, mve_pred16_t);
12528	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_f16)))
12529	float16x8_t vsubq_f16(float16x8_t, float16x8_t);
12530	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_f16)))
12531	float16x8_t vsubq(float16x8_t, float16x8_t);
12532	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_f32)))
12533	float32x4_t vsubq_f32(float32x4_t, float32x4_t);
12534	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_f32)))
12535	float32x4_t vsubq(float32x4_t, float32x4_t);
12536	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f16)))
12537	float16x8_t vsubq_m_f16(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12538	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f16)))
12539	float16x8_t vsubq_m(float16x8_t, float16x8_t, float16x8_t, mve_pred16_t);
12540	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f32)))
12541	float32x4_t vsubq_m_f32(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12542	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_m_f32)))
12543	float32x4_t vsubq_m(float32x4_t, float32x4_t, float32x4_t, mve_pred16_t);
12544	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f16)))
12545	float16x8_t vsubq_x_f16(float16x8_t, float16x8_t, mve_pred16_t);
12546	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f16)))
12547	float16x8_t vsubq_x(float16x8_t, float16x8_t, mve_pred16_t);
12548	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f32)))
12549	float32x4_t vsubq_x_f32(float32x4_t, float32x4_t, mve_pred16_t);
12550	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vsubq_x_f32)))
12551	float32x4_t vsubq_x(float32x4_t, float32x4_t, mve_pred16_t);
12552	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_f16)))
12553	float16x8_t vuninitializedq_f16();
12554	static __inline__ __attribute__((__clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_f32)))
12555	float32x4_t vuninitializedq_f32();
12556	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_f16)))
12557	float16x8_t vuninitializedq(float16x8_t);
12558	static __inline__ __attribute__((overloadable, __clang_arm_mve_alias(__builtin_arm_mve_vuninitializedq_polymorphic_f32)))
12559	float32x4_t vuninitializedq(float32x4_t);
12560
12561	#endif /* (__ARM_FEATURE_MVE & 2) && (!defined __ARM_MVE_PRESERVE_USER_NAMESPACE) */
12562
12563	#endif /* __ARM_MVE_H */

lib/include/arm_neon.h+3011-13638

...	@@ -1042,20 +1042,11 @@ __ai uint32x2_t vadd_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -1042,20 +1042,11 @@ __ai uint32x2_t vadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
1042	}	1042	}
1043	#endif	1043	#endif
1044		1044
1045	#ifdef __LITTLE_ENDIAN__
1046	__ai uint64x1_t vadd_u64(uint64x1_t __p0, uint64x1_t __p1) {	1045	__ai uint64x1_t vadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
1047	uint64x1_t __ret;	1046	uint64x1_t __ret;
1048	__ret = __p0 + __p1;	1047	__ret = __p0 + __p1;
1049	return __ret;	1048	return __ret;
1050	}	1049	}
1051	#else
1052	__ai uint64x1_t vadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
1053	uint64x1_t __ret;
1054	__ret = __p0 + __p1;
1055	return __ret;
1056	}
1057	#endif
1058
1059	#ifdef __LITTLE_ENDIAN__	1050	#ifdef __LITTLE_ENDIAN__
1060	__ai uint16x4_t vadd_u16(uint16x4_t __p0, uint16x4_t __p1) {	1051	__ai uint16x4_t vadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
1061	uint16x4_t __ret;	1052	uint16x4_t __ret;
...	@@ -1124,20 +1115,11 @@ __ai int32x2_t vadd_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -1124,20 +1115,11 @@ __ai int32x2_t vadd_s32(int32x2_t __p0, int32x2_t __p1) {
1124	}	1115	}
1125	#endif	1116	#endif
1126		1117
1127	#ifdef __LITTLE_ENDIAN__
1128	__ai int64x1_t vadd_s64(int64x1_t __p0, int64x1_t __p1) {
1129	int64x1_t __ret;
1130	__ret = __p0 + __p1;
1131	return __ret;
1132	}
1133	#else
1134	__ai int64x1_t vadd_s64(int64x1_t __p0, int64x1_t __p1) {	1118	__ai int64x1_t vadd_s64(int64x1_t __p0, int64x1_t __p1) {
1135	int64x1_t __ret;	1119	int64x1_t __ret;
1136	__ret = __p0 + __p1;	1120	__ret = __p0 + __p1;
1137	return __ret;	1121	return __ret;
1138	}	1122	}
1139	#endif
1140
1141	#ifdef __LITTLE_ENDIAN__	1123	#ifdef __LITTLE_ENDIAN__
1142	__ai int16x4_t vadd_s16(int16x4_t __p0, int16x4_t __p1) {	1124	__ai int16x4_t vadd_s16(int16x4_t __p0, int16x4_t __p1) {
1143	int16x4_t __ret;	1125	int16x4_t __ret;
...	@@ -1457,20 +1439,11 @@ __ai uint32x2_t vand_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -1457,20 +1439,11 @@ __ai uint32x2_t vand_u32(uint32x2_t __p0, uint32x2_t __p1) {
1457	}	1439	}
1458	#endif	1440	#endif
1459		1441
1460	#ifdef __LITTLE_ENDIAN__
1461	__ai uint64x1_t vand_u64(uint64x1_t __p0, uint64x1_t __p1) {
1462	uint64x1_t __ret;
1463	__ret = __p0 & __p1;
1464	return __ret;
1465	}
1466	#else
1467	__ai uint64x1_t vand_u64(uint64x1_t __p0, uint64x1_t __p1) {	1442	__ai uint64x1_t vand_u64(uint64x1_t __p0, uint64x1_t __p1) {
1468	uint64x1_t __ret;	1443	uint64x1_t __ret;
1469	__ret = __p0 & __p1;	1444	__ret = __p0 & __p1;
1470	return __ret;	1445	return __ret;
1471	}	1446	}
1472	#endif
1473
1474	#ifdef __LITTLE_ENDIAN__	1447	#ifdef __LITTLE_ENDIAN__
1475	__ai uint16x4_t vand_u16(uint16x4_t __p0, uint16x4_t __p1) {	1448	__ai uint16x4_t vand_u16(uint16x4_t __p0, uint16x4_t __p1) {
1476	uint16x4_t __ret;	1449	uint16x4_t __ret;
...	@@ -1522,20 +1495,11 @@ __ai int32x2_t vand_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -1522,20 +1495,11 @@ __ai int32x2_t vand_s32(int32x2_t __p0, int32x2_t __p1) {
1522	}	1495	}
1523	#endif	1496	#endif
1524		1497
1525	#ifdef __LITTLE_ENDIAN__
1526	__ai int64x1_t vand_s64(int64x1_t __p0, int64x1_t __p1) {
1527	int64x1_t __ret;
1528	__ret = __p0 & __p1;
1529	return __ret;
1530	}
1531	#else
1532	__ai int64x1_t vand_s64(int64x1_t __p0, int64x1_t __p1) {	1498	__ai int64x1_t vand_s64(int64x1_t __p0, int64x1_t __p1) {
1533	int64x1_t __ret;	1499	int64x1_t __ret;
1534	__ret = __p0 & __p1;	1500	__ret = __p0 & __p1;
1535	return __ret;	1501	return __ret;
1536	}	1502	}
1537	#endif
1538
1539	#ifdef __LITTLE_ENDIAN__	1503	#ifdef __LITTLE_ENDIAN__
1540	__ai int16x4_t vand_s16(int16x4_t __p0, int16x4_t __p1) {	1504	__ai int16x4_t vand_s16(int16x4_t __p0, int16x4_t __p1) {
1541	int16x4_t __ret;	1505	int16x4_t __ret;
...	@@ -1723,20 +1687,11 @@ __ai uint32x2_t vbic_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -1723,20 +1687,11 @@ __ai uint32x2_t vbic_u32(uint32x2_t __p0, uint32x2_t __p1) {
1723	}	1687	}
1724	#endif	1688	#endif
1725		1689
1726	#ifdef __LITTLE_ENDIAN__
1727	__ai uint64x1_t vbic_u64(uint64x1_t __p0, uint64x1_t __p1) {	1690	__ai uint64x1_t vbic_u64(uint64x1_t __p0, uint64x1_t __p1) {
1728	uint64x1_t __ret;	1691	uint64x1_t __ret;
1729	__ret = __p0 & ~__p1;	1692	__ret = __p0 & ~__p1;
1730	return __ret;	1693	return __ret;
1731	}	1694	}
1732	#else
1733	__ai uint64x1_t vbic_u64(uint64x1_t __p0, uint64x1_t __p1) {
1734	uint64x1_t __ret;
1735	__ret = __p0 & ~__p1;
1736	return __ret;
1737	}
1738	#endif
1739
1740	#ifdef __LITTLE_ENDIAN__	1695	#ifdef __LITTLE_ENDIAN__
1741	__ai uint16x4_t vbic_u16(uint16x4_t __p0, uint16x4_t __p1) {	1696	__ai uint16x4_t vbic_u16(uint16x4_t __p0, uint16x4_t __p1) {
1742	uint16x4_t __ret;	1697	uint16x4_t __ret;
...	@@ -1788,20 +1743,11 @@ __ai int32x2_t vbic_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -1788,20 +1743,11 @@ __ai int32x2_t vbic_s32(int32x2_t __p0, int32x2_t __p1) {
1788	}	1743	}
1789	#endif	1744	#endif
1790		1745
1791	#ifdef __LITTLE_ENDIAN__
1792	__ai int64x1_t vbic_s64(int64x1_t __p0, int64x1_t __p1) {	1746	__ai int64x1_t vbic_s64(int64x1_t __p0, int64x1_t __p1) {
1793	int64x1_t __ret;	1747	int64x1_t __ret;
1794	__ret = __p0 & ~__p1;	1748	__ret = __p0 & ~__p1;
1795	return __ret;	1749	return __ret;
1796	}	1750	}
1797	#else
1798	__ai int64x1_t vbic_s64(int64x1_t __p0, int64x1_t __p1) {
1799	int64x1_t __ret;
1800	__ret = __p0 & ~__p1;
1801	return __ret;
1802	}
1803	#endif
1804
1805	#ifdef __LITTLE_ENDIAN__	1751	#ifdef __LITTLE_ENDIAN__
1806	__ai int16x4_t vbic_s16(int16x4_t __p0, int16x4_t __p1) {	1752	__ai int16x4_t vbic_s16(int16x4_t __p0, int16x4_t __p1) {
1807	int16x4_t __ret;	1753	int16x4_t __ret;
...	@@ -2089,20 +2035,11 @@ __ai uint32x2_t vbsl_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {	...	@@ -2089,20 +2035,11 @@ __ai uint32x2_t vbsl_u32(uint32x2_t __p0, uint32x2_t __p1, uint32x2_t __p2) {
2089	}	2035	}
2090	#endif	2036	#endif
2091		2037
2092	#ifdef __LITTLE_ENDIAN__
2093	__ai uint64x1_t vbsl_u64(uint64x1_t __p0, uint64x1_t __p1, uint64x1_t __p2) {
2094	uint64x1_t __ret;
2095	__ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2096	return __ret;
2097	}
2098	#else
2099	__ai uint64x1_t vbsl_u64(uint64x1_t __p0, uint64x1_t __p1, uint64x1_t __p2) {	2038	__ai uint64x1_t vbsl_u64(uint64x1_t __p0, uint64x1_t __p1, uint64x1_t __p2) {
2100	uint64x1_t __ret;	2039	uint64x1_t __ret;
2101	__ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);	2040	__ret = (uint64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 19);
2102	return __ret;	2041	return __ret;
2103	}	2042	}
2104	#endif
2105
2106	#ifdef __LITTLE_ENDIAN__	2043	#ifdef __LITTLE_ENDIAN__
2107	__ai uint16x4_t vbsl_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {	2044	__ai uint16x4_t vbsl_u16(uint16x4_t __p0, uint16x4_t __p1, uint16x4_t __p2) {
2108	uint16x4_t __ret;	2045	uint16x4_t __ret;
...	@@ -2175,20 +2112,11 @@ __ai int32x2_t vbsl_s32(uint32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {	...	@@ -2175,20 +2112,11 @@ __ai int32x2_t vbsl_s32(uint32x2_t __p0, int32x2_t __p1, int32x2_t __p2) {
2175	}	2112	}
2176	#endif	2113	#endif
2177		2114
2178	#ifdef __LITTLE_ENDIAN__
2179	__ai int64x1_t vbsl_s64(uint64x1_t __p0, int64x1_t __p1, int64x1_t __p2) {	2115	__ai int64x1_t vbsl_s64(uint64x1_t __p0, int64x1_t __p1, int64x1_t __p2) {
2180	int64x1_t __ret;	2116	int64x1_t __ret;
2181	__ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);	2117	__ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2182	return __ret;	2118	return __ret;
2183	}	2119	}
2184	#else
2185	__ai int64x1_t vbsl_s64(uint64x1_t __p0, int64x1_t __p1, int64x1_t __p2) {
2186	int64x1_t __ret;
2187	__ret = (int64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 3);
2188	return __ret;
2189	}
2190	#endif
2191
2192	#ifdef __LITTLE_ENDIAN__	2120	#ifdef __LITTLE_ENDIAN__
2193	__ai int16x4_t vbsl_s16(uint16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {	2121	__ai int16x4_t vbsl_s16(uint16x4_t __p0, int16x4_t __p1, int16x4_t __p2) {
2194	int16x4_t __ret;	2122	int16x4_t __ret;
...	@@ -4191,174 +4119,78 @@ __ai int16x8_t __noswap_vcombine_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -4191,174 +4119,78 @@ __ai int16x8_t __noswap_vcombine_s16(int16x4_t __p0, int16x4_t __p1) {
4191	}	4119	}
4192	#endif	4120	#endif
4193		4121
4194	#ifdef __LITTLE_ENDIAN__	4122	#define vcreate_p8(__p0) __extension__ ({ \
4195	__ai poly8x8_t vcreate_p8(uint64_t __p0) {	4123	poly8x8_t __ret; \
4196	poly8x8_t __ret;	4124	uint64_t __promote = __p0; \
4197	__ret = (poly8x8_t)(__p0);	4125	__ret = (poly8x8_t)(__promote); \
4198	return __ret;	4126	__ret; \
4199	}	4127	})
4200	#else	4128	#define vcreate_p16(__p0) __extension__ ({ \
4201	__ai poly8x8_t vcreate_p8(uint64_t __p0) {	4129	poly16x4_t __ret; \
4202	poly8x8_t __ret;	4130	uint64_t __promote = __p0; \
4203	__ret = (poly8x8_t)(__p0);	4131	__ret = (poly16x4_t)(__promote); \
4204	return __ret;	4132	__ret; \
4205	}	4133	})
4206	#endif	4134	#define vcreate_u8(__p0) __extension__ ({ \
4207		4135	uint8x8_t __ret; \
4208	#ifdef __LITTLE_ENDIAN__	4136	uint64_t __promote = __p0; \
4209	__ai poly16x4_t vcreate_p16(uint64_t __p0) {	4137	__ret = (uint8x8_t)(__promote); \
4210	poly16x4_t __ret;	4138	__ret; \
4211	__ret = (poly16x4_t)(__p0);	4139	})
4212	return __ret;	4140	#define vcreate_u32(__p0) __extension__ ({ \
4213	}	4141	uint32x2_t __ret; \
4214	#else	4142	uint64_t __promote = __p0; \
4215	__ai poly16x4_t vcreate_p16(uint64_t __p0) {	4143	__ret = (uint32x2_t)(__promote); \
4216	poly16x4_t __ret;	4144	__ret; \
4217	__ret = (poly16x4_t)(__p0);	4145	})
4218	return __ret;	4146	#define vcreate_u64(__p0) __extension__ ({ \
4219	}	4147	uint64x1_t __ret; \
4220	#endif	4148	uint64_t __promote = __p0; \
4221		4149	__ret = (uint64x1_t)(__promote); \
4222	#ifdef __LITTLE_ENDIAN__	4150	__ret; \
4223	__ai uint8x8_t vcreate_u8(uint64_t __p0) {	4151	})
4224	uint8x8_t __ret;	4152	#define vcreate_u16(__p0) __extension__ ({ \
4225	__ret = (uint8x8_t)(__p0);	4153	uint16x4_t __ret; \
4226	return __ret;	4154	uint64_t __promote = __p0; \
4227	}	4155	__ret = (uint16x4_t)(__promote); \
4228	#else	4156	__ret; \
4229	__ai uint8x8_t vcreate_u8(uint64_t __p0) {	4157	})
4230	uint8x8_t __ret;	4158	#define vcreate_s8(__p0) __extension__ ({ \
4231	__ret = (uint8x8_t)(__p0);	4159	int8x8_t __ret; \
4232	return __ret;	4160	uint64_t __promote = __p0; \
4233	}	4161	__ret = (int8x8_t)(__promote); \
4234	#endif	4162	__ret; \
4235		4163	})
4236	#ifdef __LITTLE_ENDIAN__	4164	#define vcreate_f32(__p0) __extension__ ({ \
4237	__ai uint32x2_t vcreate_u32(uint64_t __p0) {	4165	float32x2_t __ret; \
4238	uint32x2_t __ret;	4166	uint64_t __promote = __p0; \
4239	__ret = (uint32x2_t)(__p0);	4167	__ret = (float32x2_t)(__promote); \
4240	return __ret;	4168	__ret; \
4241	}	4169	})
4242	#else	4170	#define vcreate_f16(__p0) __extension__ ({ \
4243	__ai uint32x2_t vcreate_u32(uint64_t __p0) {	4171	float16x4_t __ret; \
4244	uint32x2_t __ret;	4172	uint64_t __promote = __p0; \
4245	__ret = (uint32x2_t)(__p0);	4173	__ret = (float16x4_t)(__promote); \
4246	return __ret;	4174	__ret; \
4247	}	4175	})
4248	#endif	4176	#define vcreate_s32(__p0) __extension__ ({ \
4249		4177	int32x2_t __ret; \
4250	#ifdef __LITTLE_ENDIAN__	4178	uint64_t __promote = __p0; \
4251	__ai uint64x1_t vcreate_u64(uint64_t __p0) {	4179	__ret = (int32x2_t)(__promote); \
4252	uint64x1_t __ret;	4180	__ret; \
4253	__ret = (uint64x1_t)(__p0);	4181	})
4254	return __ret;	4182	#define vcreate_s64(__p0) __extension__ ({ \
4255	}	4183	int64x1_t __ret; \
4256	#else	4184	uint64_t __promote = __p0; \
4257	__ai uint64x1_t vcreate_u64(uint64_t __p0) {	4185	__ret = (int64x1_t)(__promote); \
4258	uint64x1_t __ret;	4186	__ret; \
4259	__ret = (uint64x1_t)(__p0);	4187	})
4260	return __ret;	4188	#define vcreate_s16(__p0) __extension__ ({ \
4261	}	4189	int16x4_t __ret; \
4262	#endif	4190	uint64_t __promote = __p0; \
4263		4191	__ret = (int16x4_t)(__promote); \
4264	#ifdef __LITTLE_ENDIAN__	4192	__ret; \
4265	__ai uint16x4_t vcreate_u16(uint64_t __p0) {	4193	})
4266	uint16x4_t __ret;
4267	__ret = (uint16x4_t)(__p0);
4268	return __ret;
4269	}
4270	#else
4271	__ai uint16x4_t vcreate_u16(uint64_t __p0) {
4272	uint16x4_t __ret;
4273	__ret = (uint16x4_t)(__p0);
4274	return __ret;
4275	}
4276	#endif
4277
4278	#ifdef __LITTLE_ENDIAN__
4279	__ai int8x8_t vcreate_s8(uint64_t __p0) {
4280	int8x8_t __ret;
4281	__ret = (int8x8_t)(__p0);
4282	return __ret;
4283	}
4284	#else
4285	__ai int8x8_t vcreate_s8(uint64_t __p0) {
4286	int8x8_t __ret;
4287	__ret = (int8x8_t)(__p0);
4288	return __ret;
4289	}
4290	#endif
4291
4292	#ifdef __LITTLE_ENDIAN__
4293	__ai float32x2_t vcreate_f32(uint64_t __p0) {
4294	float32x2_t __ret;
4295	__ret = (float32x2_t)(__p0);
4296	return __ret;
4297	}
4298	#else
4299	__ai float32x2_t vcreate_f32(uint64_t __p0) {
4300	float32x2_t __ret;
4301	__ret = (float32x2_t)(__p0);
4302	return __ret;
4303	}
4304	#endif
4305
4306	#ifdef __LITTLE_ENDIAN__
4307	__ai float16x4_t vcreate_f16(uint64_t __p0) {
4308	float16x4_t __ret;
4309	__ret = (float16x4_t)(__p0);
4310	return __ret;
4311	}
4312	#else
4313	__ai float16x4_t vcreate_f16(uint64_t __p0) {
4314	float16x4_t __ret;
4315	__ret = (float16x4_t)(__p0);
4316	return __ret;
4317	}
4318	#endif
4319
4320	#ifdef __LITTLE_ENDIAN__
4321	__ai int32x2_t vcreate_s32(uint64_t __p0) {
4322	int32x2_t __ret;
4323	__ret = (int32x2_t)(__p0);
4324	return __ret;
4325	}
4326	#else
4327	__ai int32x2_t vcreate_s32(uint64_t __p0) {
4328	int32x2_t __ret;
4329	__ret = (int32x2_t)(__p0);
4330	return __ret;
4331	}
4332	#endif
4333
4334	#ifdef __LITTLE_ENDIAN__
4335	__ai int64x1_t vcreate_s64(uint64_t __p0) {
4336	int64x1_t __ret;
4337	__ret = (int64x1_t)(__p0);
4338	return __ret;
4339	}
4340	#else
4341	__ai int64x1_t vcreate_s64(uint64_t __p0) {
4342	int64x1_t __ret;
4343	__ret = (int64x1_t)(__p0);
4344	return __ret;
4345	}
4346	#endif
4347
4348	#ifdef __LITTLE_ENDIAN__
4349	__ai int16x4_t vcreate_s16(uint64_t __p0) {
4350	int16x4_t __ret;
4351	__ret = (int16x4_t)(__p0);
4352	return __ret;
4353	}
4354	#else
4355	__ai int16x4_t vcreate_s16(uint64_t __p0) {
4356	int16x4_t __ret;
4357	__ret = (int16x4_t)(__p0);
4358	return __ret;
4359	}
4360	#endif
4361
4362	#ifdef __LITTLE_ENDIAN__	4194	#ifdef __LITTLE_ENDIAN__
4363	__ai float32x4_t vcvtq_f32_u32(uint32x4_t __p0) {	4195	__ai float32x4_t vcvtq_f32_u32(uint32x4_t __p0) {
4364	float32x4_t __ret;	4196	float32x4_t __ret;
...	@@ -4899,22 +4731,12 @@ __ai uint32x2_t vcvt_u32_f32(float32x2_t __p0) {	...	@@ -4899,22 +4731,12 @@ __ai uint32x2_t vcvt_u32_f32(float32x2_t __p0) {
4899	})	4731	})
4900	#endif	4732	#endif
4901		4733
4902	#ifdef __LITTLE_ENDIAN__
4903	#define vdup_lane_u64(__p0, __p1) __extension__ ({ \
4904	uint64x1_t __s0 = __p0; \
4905	uint64x1_t __ret; \
4906	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
4907	__ret; \
4908	})
4909	#else
4910	#define vdup_lane_u64(__p0, __p1) __extension__ ({ \	4734	#define vdup_lane_u64(__p0, __p1) __extension__ ({ \
4911	uint64x1_t __s0 = __p0; \	4735	uint64x1_t __s0 = __p0; \
4912	uint64x1_t __ret; \	4736	uint64x1_t __ret; \
4913	__ret = __builtin_shufflevector(__s0, __s0, __p1); \	4737	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
4914	__ret; \	4738	__ret; \
4915	})	4739	})
4916	#endif
4917
4918	#ifdef __LITTLE_ENDIAN__	4740	#ifdef __LITTLE_ENDIAN__
4919	#define vdup_lane_u16(__p0, __p1) __extension__ ({ \	4741	#define vdup_lane_u16(__p0, __p1) __extension__ ({ \
4920	uint16x4_t __s0 = __p0; \	4742	uint16x4_t __s0 = __p0; \
...	@@ -4987,22 +4809,12 @@ __ai uint32x2_t vcvt_u32_f32(float32x2_t __p0) {	...	@@ -4987,22 +4809,12 @@ __ai uint32x2_t vcvt_u32_f32(float32x2_t __p0) {
4987	})	4809	})
4988	#endif	4810	#endif
4989		4811
4990	#ifdef __LITTLE_ENDIAN__
4991	#define vdup_lane_s64(__p0, __p1) __extension__ ({ \	4812	#define vdup_lane_s64(__p0, __p1) __extension__ ({ \
4992	int64x1_t __s0 = __p0; \	4813	int64x1_t __s0 = __p0; \
4993	int64x1_t __ret; \	4814	int64x1_t __ret; \
4994	__ret = __builtin_shufflevector(__s0, __s0, __p1); \	4815	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
4995	__ret; \	4816	__ret; \
4996	})	4817	})
4997	#else
4998	#define vdup_lane_s64(__p0, __p1) __extension__ ({ \
4999	int64x1_t __s0 = __p0; \
5000	int64x1_t __ret; \
5001	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
5002	__ret; \
5003	})
5004	#endif
5005
5006	#ifdef __LITTLE_ENDIAN__	4818	#ifdef __LITTLE_ENDIAN__
5007	#define vdup_lane_s16(__p0, __p1) __extension__ ({ \	4819	#define vdup_lane_s16(__p0, __p1) __extension__ ({ \
5008	int16x4_t __s0 = __p0; \	4820	int16x4_t __s0 = __p0; \
...	@@ -5263,20 +5075,11 @@ __ai uint32x2_t vdup_n_u32(uint32_t __p0) {	...	@@ -5263,20 +5075,11 @@ __ai uint32x2_t vdup_n_u32(uint32_t __p0) {
5263	}	5075	}
5264	#endif	5076	#endif
5265		5077
5266	#ifdef __LITTLE_ENDIAN__
5267	__ai uint64x1_t vdup_n_u64(uint64_t __p0) {
5268	uint64x1_t __ret;
5269	__ret = (uint64x1_t) {__p0};
5270	return __ret;
5271	}
5272	#else
5273	__ai uint64x1_t vdup_n_u64(uint64_t __p0) {	5078	__ai uint64x1_t vdup_n_u64(uint64_t __p0) {
5274	uint64x1_t __ret;	5079	uint64x1_t __ret;
5275	__ret = (uint64x1_t) {__p0};	5080	__ret = (uint64x1_t) {__p0};
5276	return __ret;	5081	return __ret;
5277	}	5082	}
5278	#endif
5279
5280	#ifdef __LITTLE_ENDIAN__	5083	#ifdef __LITTLE_ENDIAN__
5281	__ai uint16x4_t vdup_n_u16(uint16_t __p0) {	5084	__ai uint16x4_t vdup_n_u16(uint16_t __p0) {
5282	uint16x4_t __ret;	5085	uint16x4_t __ret;
...	@@ -5354,20 +5157,11 @@ __ai int32x2_t vdup_n_s32(int32_t __p0) {	...	@@ -5354,20 +5157,11 @@ __ai int32x2_t vdup_n_s32(int32_t __p0) {
5354	}	5157	}
5355	#endif	5158	#endif
5356		5159
5357	#ifdef __LITTLE_ENDIAN__
5358	__ai int64x1_t vdup_n_s64(int64_t __p0) {
5359	int64x1_t __ret;
5360	__ret = (int64x1_t) {__p0};
5361	return __ret;
5362	}
5363	#else
5364	__ai int64x1_t vdup_n_s64(int64_t __p0) {	5160	__ai int64x1_t vdup_n_s64(int64_t __p0) {
5365	int64x1_t __ret;	5161	int64x1_t __ret;
5366	__ret = (int64x1_t) {__p0};	5162	__ret = (int64x1_t) {__p0};
5367	return __ret;	5163	return __ret;
5368	}	5164	}
5369	#endif
5370
5371	#ifdef __LITTLE_ENDIAN__	5165	#ifdef __LITTLE_ENDIAN__
5372	__ai int16x4_t vdup_n_s16(int16_t __p0) {	5166	__ai int16x4_t vdup_n_s16(int16_t __p0) {
5373	int16x4_t __ret;	5167	int16x4_t __ret;
...	@@ -5553,20 +5347,11 @@ __ai uint32x2_t veor_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -5553,20 +5347,11 @@ __ai uint32x2_t veor_u32(uint32x2_t __p0, uint32x2_t __p1) {
5553	}	5347	}
5554	#endif	5348	#endif
5555		5349
5556	#ifdef __LITTLE_ENDIAN__
5557	__ai uint64x1_t veor_u64(uint64x1_t __p0, uint64x1_t __p1) {	5350	__ai uint64x1_t veor_u64(uint64x1_t __p0, uint64x1_t __p1) {
5558	uint64x1_t __ret;	5351	uint64x1_t __ret;
5559	__ret = __p0 ^ __p1;	5352	__ret = __p0 ^ __p1;
5560	return __ret;	5353	return __ret;
5561	}	5354	}
5562	#else
5563	__ai uint64x1_t veor_u64(uint64x1_t __p0, uint64x1_t __p1) {
5564	uint64x1_t __ret;
5565	__ret = __p0 ^ __p1;
5566	return __ret;
5567	}
5568	#endif
5569
5570	#ifdef __LITTLE_ENDIAN__	5355	#ifdef __LITTLE_ENDIAN__
5571	__ai uint16x4_t veor_u16(uint16x4_t __p0, uint16x4_t __p1) {	5356	__ai uint16x4_t veor_u16(uint16x4_t __p0, uint16x4_t __p1) {
5572	uint16x4_t __ret;	5357	uint16x4_t __ret;
...	@@ -5618,20 +5403,11 @@ __ai int32x2_t veor_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -5618,20 +5403,11 @@ __ai int32x2_t veor_s32(int32x2_t __p0, int32x2_t __p1) {
5618	}	5403	}
5619	#endif	5404	#endif
5620		5405
5621	#ifdef __LITTLE_ENDIAN__
5622	__ai int64x1_t veor_s64(int64x1_t __p0, int64x1_t __p1) {
5623	int64x1_t __ret;
5624	__ret = __p0 ^ __p1;
5625	return __ret;
5626	}
5627	#else
5628	__ai int64x1_t veor_s64(int64x1_t __p0, int64x1_t __p1) {	5406	__ai int64x1_t veor_s64(int64x1_t __p0, int64x1_t __p1) {
5629	int64x1_t __ret;	5407	int64x1_t __ret;
5630	__ret = __p0 ^ __p1;	5408	__ret = __p0 ^ __p1;
5631	return __ret;	5409	return __ret;
5632	}	5410	}
5633	#endif
5634
5635	#ifdef __LITTLE_ENDIAN__	5411	#ifdef __LITTLE_ENDIAN__
5636	__ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {	5412	__ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
5637	int16x4_t __ret;	5413	int16x4_t __ret;
...	@@ -5964,15 +5740,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -5964,15 +5740,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
5964	})	5740	})
5965	#endif	5741	#endif
5966		5742
5967	#ifdef __LITTLE_ENDIAN__
5968	#define vext_u64(__p0, __p1, __p2) __extension__ ({ \
5969	uint64x1_t __s0 = __p0; \
5970	uint64x1_t __s1 = __p1; \
5971	uint64x1_t __ret; \
5972	__ret = (uint64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
5973	__ret; \
5974	})
5975	#else
5976	#define vext_u64(__p0, __p1, __p2) __extension__ ({ \	5743	#define vext_u64(__p0, __p1, __p2) __extension__ ({ \
5977	uint64x1_t __s0 = __p0; \	5744	uint64x1_t __s0 = __p0; \
5978	uint64x1_t __s1 = __p1; \	5745	uint64x1_t __s1 = __p1; \
...	@@ -5980,8 +5747,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -5980,8 +5747,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
5980	__ret = (uint64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \	5747	__ret = (uint64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
5981	__ret; \	5748	__ret; \
5982	})	5749	})
5983	#endif
5984
5985	#ifdef __LITTLE_ENDIAN__	5750	#ifdef __LITTLE_ENDIAN__
5986	#define vext_u16(__p0, __p1, __p2) __extension__ ({ \	5751	#define vext_u16(__p0, __p1, __p2) __extension__ ({ \
5987	uint16x4_t __s0 = __p0; \	5752	uint16x4_t __s0 = __p0; \
...	@@ -6066,7 +5831,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -6066,7 +5831,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
6066	})	5831	})
6067	#endif	5832	#endif
6068		5833
6069	#ifdef __LITTLE_ENDIAN__
6070	#define vext_s64(__p0, __p1, __p2) __extension__ ({ \	5834	#define vext_s64(__p0, __p1, __p2) __extension__ ({ \
6071	int64x1_t __s0 = __p0; \	5835	int64x1_t __s0 = __p0; \
6072	int64x1_t __s1 = __p1; \	5836	int64x1_t __s1 = __p1; \
...	@@ -6074,16 +5838,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -6074,16 +5838,6 @@ __ai int16x4_t veor_s16(int16x4_t __p0, int16x4_t __p1) {
6074	__ret = (int64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \	5838	__ret = (int64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
6075	__ret; \	5839	__ret; \
6076	})	5840	})
6077	#else
6078	#define vext_s64(__p0, __p1, __p2) __extension__ ({ \
6079	int64x1_t __s0 = __p0; \
6080	int64x1_t __s1 = __p1; \
6081	int64x1_t __ret; \
6082	__ret = (int64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
6083	__ret; \
6084	})
6085	#endif
6086
6087	#ifdef __LITTLE_ENDIAN__	5841	#ifdef __LITTLE_ENDIAN__
6088	#define vext_s16(__p0, __p1, __p2) __extension__ ({ \	5842	#define vext_s16(__p0, __p1, __p2) __extension__ ({ \
6089	int16x4_t __s0 = __p0; \	5843	int16x4_t __s0 = __p0; \
...	@@ -6344,7 +6098,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6344,7 +6098,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6344	#define vget_lane_p8(__p0, __p1) __extension__ ({ \	6098	#define vget_lane_p8(__p0, __p1) __extension__ ({ \
6345	poly8x8_t __s0 = __p0; \	6099	poly8x8_t __s0 = __p0; \
6346	poly8_t __ret; \	6100	poly8_t __ret; \
6347	__ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \	6101	__ret = (poly8_t) __builtin_neon_vget_lane_i8((poly8x8_t)__s0, __p1); \
6348	__ret; \	6102	__ret; \
6349	})	6103	})
6350	#else	6104	#else
...	@@ -6352,13 +6106,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6352,13 +6106,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6352	poly8x8_t __s0 = __p0; \	6106	poly8x8_t __s0 = __p0; \
6353	poly8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	6107	poly8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6354	poly8_t __ret; \	6108	poly8_t __ret; \
6355	__ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__rev0, __p1); \	6109	__ret = (poly8_t) __builtin_neon_vget_lane_i8((poly8x8_t)__rev0, __p1); \
6356	__ret; \	6110	__ret; \
6357	})	6111	})
6358	#define __noswap_vget_lane_p8(__p0, __p1) __extension__ ({ \	6112	#define __noswap_vget_lane_p8(__p0, __p1) __extension__ ({ \
6359	poly8x8_t __s0 = __p0; \	6113	poly8x8_t __s0 = __p0; \
6360	poly8_t __ret; \	6114	poly8_t __ret; \
6361	__ret = (poly8_t) __builtin_neon_vget_lane_i8((int8x8_t)__s0, __p1); \	6115	__ret = (poly8_t) __builtin_neon_vget_lane_i8((poly8x8_t)__s0, __p1); \
6362	__ret; \	6116	__ret; \
6363	})	6117	})
6364	#endif	6118	#endif
...	@@ -6367,7 +6121,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6367,7 +6121,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6367	#define vget_lane_p16(__p0, __p1) __extension__ ({ \	6121	#define vget_lane_p16(__p0, __p1) __extension__ ({ \
6368	poly16x4_t __s0 = __p0; \	6122	poly16x4_t __s0 = __p0; \
6369	poly16_t __ret; \	6123	poly16_t __ret; \
6370	__ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6124	__ret = (poly16_t) __builtin_neon_vget_lane_i16((poly16x4_t)__s0, __p1); \
6371	__ret; \	6125	__ret; \
6372	})	6126	})
6373	#else	6127	#else
...	@@ -6375,13 +6129,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6375,13 +6129,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6375	poly16x4_t __s0 = __p0; \	6129	poly16x4_t __s0 = __p0; \
6376	poly16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6130	poly16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6377	poly16_t __ret; \	6131	poly16_t __ret; \
6378	__ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \	6132	__ret = (poly16_t) __builtin_neon_vget_lane_i16((poly16x4_t)__rev0, __p1); \
6379	__ret; \	6133	__ret; \
6380	})	6134	})
6381	#define __noswap_vget_lane_p16(__p0, __p1) __extension__ ({ \	6135	#define __noswap_vget_lane_p16(__p0, __p1) __extension__ ({ \
6382	poly16x4_t __s0 = __p0; \	6136	poly16x4_t __s0 = __p0; \
6383	poly16_t __ret; \	6137	poly16_t __ret; \
6384	__ret = (poly16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6138	__ret = (poly16_t) __builtin_neon_vget_lane_i16((poly16x4_t)__s0, __p1); \
6385	__ret; \	6139	__ret; \
6386	})	6140	})
6387	#endif	6141	#endif
...	@@ -6390,7 +6144,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6390,7 +6144,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6390	#define vgetq_lane_p8(__p0, __p1) __extension__ ({ \	6144	#define vgetq_lane_p8(__p0, __p1) __extension__ ({ \
6391	poly8x16_t __s0 = __p0; \	6145	poly8x16_t __s0 = __p0; \
6392	poly8_t __ret; \	6146	poly8_t __ret; \
6393	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \	6147	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((poly8x16_t)__s0, __p1); \
6394	__ret; \	6148	__ret; \
6395	})	6149	})
6396	#else	6150	#else
...	@@ -6398,13 +6152,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6398,13 +6152,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6398	poly8x16_t __s0 = __p0; \	6152	poly8x16_t __s0 = __p0; \
6399	poly8x16_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	6153	poly8x16_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
6400	poly8_t __ret; \	6154	poly8_t __ret; \
6401	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__rev0, __p1); \	6155	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((poly8x16_t)__rev0, __p1); \
6402	__ret; \	6156	__ret; \
6403	})	6157	})
6404	#define __noswap_vgetq_lane_p8(__p0, __p1) __extension__ ({ \	6158	#define __noswap_vgetq_lane_p8(__p0, __p1) __extension__ ({ \
6405	poly8x16_t __s0 = __p0; \	6159	poly8x16_t __s0 = __p0; \
6406	poly8_t __ret; \	6160	poly8_t __ret; \
6407	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((int8x16_t)__s0, __p1); \	6161	__ret = (poly8_t) __builtin_neon_vgetq_lane_i8((poly8x16_t)__s0, __p1); \
6408	__ret; \	6162	__ret; \
6409	})	6163	})
6410	#endif	6164	#endif
...	@@ -6413,7 +6167,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6413,7 +6167,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6413	#define vgetq_lane_p16(__p0, __p1) __extension__ ({ \	6167	#define vgetq_lane_p16(__p0, __p1) __extension__ ({ \
6414	poly16x8_t __s0 = __p0; \	6168	poly16x8_t __s0 = __p0; \
6415	poly16_t __ret; \	6169	poly16_t __ret; \
6416	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6170	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((poly16x8_t)__s0, __p1); \
6417	__ret; \	6171	__ret; \
6418	})	6172	})
6419	#else	6173	#else
...	@@ -6421,13 +6175,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6421,13 +6175,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6421	poly16x8_t __s0 = __p0; \	6175	poly16x8_t __s0 = __p0; \
6422	poly16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	6176	poly16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6423	poly16_t __ret; \	6177	poly16_t __ret; \
6424	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \	6178	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((poly16x8_t)__rev0, __p1); \
6425	__ret; \	6179	__ret; \
6426	})	6180	})
6427	#define __noswap_vgetq_lane_p16(__p0, __p1) __extension__ ({ \	6181	#define __noswap_vgetq_lane_p16(__p0, __p1) __extension__ ({ \
6428	poly16x8_t __s0 = __p0; \	6182	poly16x8_t __s0 = __p0; \
6429	poly16_t __ret; \	6183	poly16_t __ret; \
6430	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6184	__ret = (poly16_t) __builtin_neon_vgetq_lane_i16((poly16x8_t)__s0, __p1); \
6431	__ret; \	6185	__ret; \
6432	})	6186	})
6433	#endif	6187	#endif
...	@@ -6459,7 +6213,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6459,7 +6213,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6459	#define vgetq_lane_u32(__p0, __p1) __extension__ ({ \	6213	#define vgetq_lane_u32(__p0, __p1) __extension__ ({ \
6460	uint32x4_t __s0 = __p0; \	6214	uint32x4_t __s0 = __p0; \
6461	uint32_t __ret; \	6215	uint32_t __ret; \
6462	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \	6216	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__s0, __p1); \
6463	__ret; \	6217	__ret; \
6464	})	6218	})
6465	#else	6219	#else
...	@@ -6467,13 +6221,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6467,13 +6221,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6467	uint32x4_t __s0 = __p0; \	6221	uint32x4_t __s0 = __p0; \
6468	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6222	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6469	uint32_t __ret; \	6223	uint32_t __ret; \
6470	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__rev0, __p1); \	6224	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__rev0, __p1); \
6471	__ret; \	6225	__ret; \
6472	})	6226	})
6473	#define __noswap_vgetq_lane_u32(__p0, __p1) __extension__ ({ \	6227	#define __noswap_vgetq_lane_u32(__p0, __p1) __extension__ ({ \
6474	uint32x4_t __s0 = __p0; \	6228	uint32x4_t __s0 = __p0; \
6475	uint32_t __ret; \	6229	uint32_t __ret; \
6476	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \	6230	__ret = (uint32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__s0, __p1); \
6477	__ret; \	6231	__ret; \
6478	})	6232	})
6479	#endif	6233	#endif
...	@@ -6482,7 +6236,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6482,7 +6236,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6482	#define vgetq_lane_u64(__p0, __p1) __extension__ ({ \	6236	#define vgetq_lane_u64(__p0, __p1) __extension__ ({ \
6483	uint64x2_t __s0 = __p0; \	6237	uint64x2_t __s0 = __p0; \
6484	uint64_t __ret; \	6238	uint64_t __ret; \
6485	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	6239	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__s0, __p1); \
6486	__ret; \	6240	__ret; \
6487	})	6241	})
6488	#else	6242	#else
...	@@ -6490,13 +6244,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6490,13 +6244,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6490	uint64x2_t __s0 = __p0; \	6244	uint64x2_t __s0 = __p0; \
6491	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	6245	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
6492	uint64_t __ret; \	6246	uint64_t __ret; \
6493	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \	6247	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__rev0, __p1); \
6494	__ret; \	6248	__ret; \
6495	})	6249	})
6496	#define __noswap_vgetq_lane_u64(__p0, __p1) __extension__ ({ \	6250	#define __noswap_vgetq_lane_u64(__p0, __p1) __extension__ ({ \
6497	uint64x2_t __s0 = __p0; \	6251	uint64x2_t __s0 = __p0; \
6498	uint64_t __ret; \	6252	uint64_t __ret; \
6499	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	6253	__ret = (uint64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__s0, __p1); \
6500	__ret; \	6254	__ret; \
6501	})	6255	})
6502	#endif	6256	#endif
...	@@ -6505,7 +6259,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6505,7 +6259,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6505	#define vgetq_lane_u16(__p0, __p1) __extension__ ({ \	6259	#define vgetq_lane_u16(__p0, __p1) __extension__ ({ \
6506	uint16x8_t __s0 = __p0; \	6260	uint16x8_t __s0 = __p0; \
6507	uint16_t __ret; \	6261	uint16_t __ret; \
6508	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6262	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__s0, __p1); \
6509	__ret; \	6263	__ret; \
6510	})	6264	})
6511	#else	6265	#else
...	@@ -6513,13 +6267,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6513,13 +6267,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6513	uint16x8_t __s0 = __p0; \	6267	uint16x8_t __s0 = __p0; \
6514	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	6268	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6515	uint16_t __ret; \	6269	uint16_t __ret; \
6516	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \	6270	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__rev0, __p1); \
6517	__ret; \	6271	__ret; \
6518	})	6272	})
6519	#define __noswap_vgetq_lane_u16(__p0, __p1) __extension__ ({ \	6273	#define __noswap_vgetq_lane_u16(__p0, __p1) __extension__ ({ \
6520	uint16x8_t __s0 = __p0; \	6274	uint16x8_t __s0 = __p0; \
6521	uint16_t __ret; \	6275	uint16_t __ret; \
6522	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6276	__ret = (uint16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__s0, __p1); \
6523	__ret; \	6277	__ret; \
6524	})	6278	})
6525	#endif	6279	#endif
...	@@ -6551,7 +6305,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6551,7 +6305,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6551	#define vgetq_lane_f32(__p0, __p1) __extension__ ({ \	6305	#define vgetq_lane_f32(__p0, __p1) __extension__ ({ \
6552	float32x4_t __s0 = __p0; \	6306	float32x4_t __s0 = __p0; \
6553	float32_t __ret; \	6307	float32_t __ret; \
6554	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__s0, __p1); \	6308	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((float32x4_t)__s0, __p1); \
6555	__ret; \	6309	__ret; \
6556	})	6310	})
6557	#else	6311	#else
...	@@ -6559,13 +6313,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6559,13 +6313,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6559	float32x4_t __s0 = __p0; \	6313	float32x4_t __s0 = __p0; \
6560	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6314	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6561	float32_t __ret; \	6315	float32_t __ret; \
6562	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__rev0, __p1); \	6316	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((float32x4_t)__rev0, __p1); \
6563	__ret; \	6317	__ret; \
6564	})	6318	})
6565	#define __noswap_vgetq_lane_f32(__p0, __p1) __extension__ ({ \	6319	#define __noswap_vgetq_lane_f32(__p0, __p1) __extension__ ({ \
6566	float32x4_t __s0 = __p0; \	6320	float32x4_t __s0 = __p0; \
6567	float32_t __ret; \	6321	float32_t __ret; \
6568	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((int8x16_t)__s0, __p1); \	6322	__ret = (float32_t) __builtin_neon_vgetq_lane_f32((float32x4_t)__s0, __p1); \
6569	__ret; \	6323	__ret; \
6570	})	6324	})
6571	#endif	6325	#endif
...	@@ -6574,7 +6328,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6574,7 +6328,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6574	#define vgetq_lane_s32(__p0, __p1) __extension__ ({ \	6328	#define vgetq_lane_s32(__p0, __p1) __extension__ ({ \
6575	int32x4_t __s0 = __p0; \	6329	int32x4_t __s0 = __p0; \
6576	int32_t __ret; \	6330	int32_t __ret; \
6577	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \	6331	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__s0, __p1); \
6578	__ret; \	6332	__ret; \
6579	})	6333	})
6580	#else	6334	#else
...	@@ -6582,13 +6336,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6582,13 +6336,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6582	int32x4_t __s0 = __p0; \	6336	int32x4_t __s0 = __p0; \
6583	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6337	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6584	int32_t __ret; \	6338	int32_t __ret; \
6585	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__rev0, __p1); \	6339	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__rev0, __p1); \
6586	__ret; \	6340	__ret; \
6587	})	6341	})
6588	#define __noswap_vgetq_lane_s32(__p0, __p1) __extension__ ({ \	6342	#define __noswap_vgetq_lane_s32(__p0, __p1) __extension__ ({ \
6589	int32x4_t __s0 = __p0; \	6343	int32x4_t __s0 = __p0; \
6590	int32_t __ret; \	6344	int32_t __ret; \
6591	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int8x16_t)__s0, __p1); \	6345	__ret = (int32_t) __builtin_neon_vgetq_lane_i32((int32x4_t)__s0, __p1); \
6592	__ret; \	6346	__ret; \
6593	})	6347	})
6594	#endif	6348	#endif
...	@@ -6597,7 +6351,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6597,7 +6351,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6597	#define vgetq_lane_s64(__p0, __p1) __extension__ ({ \	6351	#define vgetq_lane_s64(__p0, __p1) __extension__ ({ \
6598	int64x2_t __s0 = __p0; \	6352	int64x2_t __s0 = __p0; \
6599	int64_t __ret; \	6353	int64_t __ret; \
6600	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	6354	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__s0, __p1); \
6601	__ret; \	6355	__ret; \
6602	})	6356	})
6603	#else	6357	#else
...	@@ -6605,13 +6359,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6605,13 +6359,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6605	int64x2_t __s0 = __p0; \	6359	int64x2_t __s0 = __p0; \
6606	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	6360	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
6607	int64_t __ret; \	6361	int64_t __ret; \
6608	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \	6362	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__rev0, __p1); \
6609	__ret; \	6363	__ret; \
6610	})	6364	})
6611	#define __noswap_vgetq_lane_s64(__p0, __p1) __extension__ ({ \	6365	#define __noswap_vgetq_lane_s64(__p0, __p1) __extension__ ({ \
6612	int64x2_t __s0 = __p0; \	6366	int64x2_t __s0 = __p0; \
6613	int64_t __ret; \	6367	int64_t __ret; \
6614	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	6368	__ret = (int64_t) __builtin_neon_vgetq_lane_i64((int64x2_t)__s0, __p1); \
6615	__ret; \	6369	__ret; \
6616	})	6370	})
6617	#endif	6371	#endif
...	@@ -6620,7 +6374,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6620,7 +6374,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6620	#define vgetq_lane_s16(__p0, __p1) __extension__ ({ \	6374	#define vgetq_lane_s16(__p0, __p1) __extension__ ({ \
6621	int16x8_t __s0 = __p0; \	6375	int16x8_t __s0 = __p0; \
6622	int16_t __ret; \	6376	int16_t __ret; \
6623	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6377	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__s0, __p1); \
6624	__ret; \	6378	__ret; \
6625	})	6379	})
6626	#else	6380	#else
...	@@ -6628,13 +6382,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6628,13 +6382,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6628	int16x8_t __s0 = __p0; \	6382	int16x8_t __s0 = __p0; \
6629	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	6383	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
6630	int16_t __ret; \	6384	int16_t __ret; \
6631	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__rev0, __p1); \	6385	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__rev0, __p1); \
6632	__ret; \	6386	__ret; \
6633	})	6387	})
6634	#define __noswap_vgetq_lane_s16(__p0, __p1) __extension__ ({ \	6388	#define __noswap_vgetq_lane_s16(__p0, __p1) __extension__ ({ \
6635	int16x8_t __s0 = __p0; \	6389	int16x8_t __s0 = __p0; \
6636	int16_t __ret; \	6390	int16_t __ret; \
6637	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int8x16_t)__s0, __p1); \	6391	__ret = (int16_t) __builtin_neon_vgetq_lane_i16((int16x8_t)__s0, __p1); \
6638	__ret; \	6392	__ret; \
6639	})	6393	})
6640	#endif	6394	#endif
...	@@ -6666,7 +6420,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6666,7 +6420,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6666	#define vget_lane_u32(__p0, __p1) __extension__ ({ \	6420	#define vget_lane_u32(__p0, __p1) __extension__ ({ \
6667	uint32x2_t __s0 = __p0; \	6421	uint32x2_t __s0 = __p0; \
6668	uint32_t __ret; \	6422	uint32_t __ret; \
6669	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \	6423	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int32x2_t)__s0, __p1); \
6670	__ret; \	6424	__ret; \
6671	})	6425	})
6672	#else	6426	#else
...	@@ -6674,44 +6428,28 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6674,44 +6428,28 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6674	uint32x2_t __s0 = __p0; \	6428	uint32x2_t __s0 = __p0; \
6675	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	6429	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
6676	uint32_t __ret; \	6430	uint32_t __ret; \
6677	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \	6431	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int32x2_t)__rev0, __p1); \
6678	__ret; \	6432	__ret; \
6679	})	6433	})
6680	#define __noswap_vget_lane_u32(__p0, __p1) __extension__ ({ \	6434	#define __noswap_vget_lane_u32(__p0, __p1) __extension__ ({ \
6681	uint32x2_t __s0 = __p0; \	6435	uint32x2_t __s0 = __p0; \
6682	uint32_t __ret; \	6436	uint32_t __ret; \
6683	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \	6437	__ret = (uint32_t) __builtin_neon_vget_lane_i32((int32x2_t)__s0, __p1); \
6684	__ret; \	6438	__ret; \
6685	})	6439	})
6686	#endif	6440	#endif
6687		6441
6688	#ifdef __LITTLE_ENDIAN__
6689	#define vget_lane_u64(__p0, __p1) __extension__ ({ \
6690	uint64x1_t __s0 = __p0; \
6691	uint64_t __ret; \
6692	__ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6693	__ret; \
6694	})
6695	#else
6696	#define vget_lane_u64(__p0, __p1) __extension__ ({ \	6442	#define vget_lane_u64(__p0, __p1) __extension__ ({ \
6697	uint64x1_t __s0 = __p0; \	6443	uint64x1_t __s0 = __p0; \
6698	uint64_t __ret; \	6444	uint64_t __ret; \
6699	__ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \	6445	__ret = (uint64_t) __builtin_neon_vget_lane_i64((int64x1_t)__s0, __p1); \
6700	__ret; \
6701	})
6702	#define __noswap_vget_lane_u64(__p0, __p1) __extension__ ({ \
6703	uint64x1_t __s0 = __p0; \
6704	uint64_t __ret; \
6705	__ret = (uint64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6706	__ret; \	6446	__ret; \
6707	})	6447	})
6708	#endif
6709
6710	#ifdef __LITTLE_ENDIAN__	6448	#ifdef __LITTLE_ENDIAN__
6711	#define vget_lane_u16(__p0, __p1) __extension__ ({ \	6449	#define vget_lane_u16(__p0, __p1) __extension__ ({ \
6712	uint16x4_t __s0 = __p0; \	6450	uint16x4_t __s0 = __p0; \
6713	uint16_t __ret; \	6451	uint16_t __ret; \
6714	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6452	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int16x4_t)__s0, __p1); \
6715	__ret; \	6453	__ret; \
6716	})	6454	})
6717	#else	6455	#else
...	@@ -6719,13 +6457,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6719,13 +6457,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6719	uint16x4_t __s0 = __p0; \	6457	uint16x4_t __s0 = __p0; \
6720	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6458	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6721	uint16_t __ret; \	6459	uint16_t __ret; \
6722	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \	6460	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int16x4_t)__rev0, __p1); \
6723	__ret; \	6461	__ret; \
6724	})	6462	})
6725	#define __noswap_vget_lane_u16(__p0, __p1) __extension__ ({ \	6463	#define __noswap_vget_lane_u16(__p0, __p1) __extension__ ({ \
6726	uint16x4_t __s0 = __p0; \	6464	uint16x4_t __s0 = __p0; \
6727	uint16_t __ret; \	6465	uint16_t __ret; \
6728	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6466	__ret = (uint16_t) __builtin_neon_vget_lane_i16((int16x4_t)__s0, __p1); \
6729	__ret; \	6467	__ret; \
6730	})	6468	})
6731	#endif	6469	#endif
...	@@ -6757,7 +6495,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6757,7 +6495,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6757	#define vget_lane_f32(__p0, __p1) __extension__ ({ \	6495	#define vget_lane_f32(__p0, __p1) __extension__ ({ \
6758	float32x2_t __s0 = __p0; \	6496	float32x2_t __s0 = __p0; \
6759	float32_t __ret; \	6497	float32_t __ret; \
6760	__ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \	6498	__ret = (float32_t) __builtin_neon_vget_lane_f32((float32x2_t)__s0, __p1); \
6761	__ret; \	6499	__ret; \
6762	})	6500	})
6763	#else	6501	#else
...	@@ -6765,13 +6503,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6765,13 +6503,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6765	float32x2_t __s0 = __p0; \	6503	float32x2_t __s0 = __p0; \
6766	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	6504	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
6767	float32_t __ret; \	6505	float32_t __ret; \
6768	__ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__rev0, __p1); \	6506	__ret = (float32_t) __builtin_neon_vget_lane_f32((float32x2_t)__rev0, __p1); \
6769	__ret; \	6507	__ret; \
6770	})	6508	})
6771	#define __noswap_vget_lane_f32(__p0, __p1) __extension__ ({ \	6509	#define __noswap_vget_lane_f32(__p0, __p1) __extension__ ({ \
6772	float32x2_t __s0 = __p0; \	6510	float32x2_t __s0 = __p0; \
6773	float32_t __ret; \	6511	float32_t __ret; \
6774	__ret = (float32_t) __builtin_neon_vget_lane_f32((int8x8_t)__s0, __p1); \	6512	__ret = (float32_t) __builtin_neon_vget_lane_f32((float32x2_t)__s0, __p1); \
6775	__ret; \	6513	__ret; \
6776	})	6514	})
6777	#endif	6515	#endif
...	@@ -6780,7 +6518,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6780,7 +6518,7 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6780	#define vget_lane_s32(__p0, __p1) __extension__ ({ \	6518	#define vget_lane_s32(__p0, __p1) __extension__ ({ \
6781	int32x2_t __s0 = __p0; \	6519	int32x2_t __s0 = __p0; \
6782	int32_t __ret; \	6520	int32_t __ret; \
6783	__ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \	6521	__ret = (int32_t) __builtin_neon_vget_lane_i32((int32x2_t)__s0, __p1); \
6784	__ret; \	6522	__ret; \
6785	})	6523	})
6786	#else	6524	#else
...	@@ -6788,44 +6526,28 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6788,44 +6526,28 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6788	int32x2_t __s0 = __p0; \	6526	int32x2_t __s0 = __p0; \
6789	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	6527	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
6790	int32_t __ret; \	6528	int32_t __ret; \
6791	__ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__rev0, __p1); \	6529	__ret = (int32_t) __builtin_neon_vget_lane_i32((int32x2_t)__rev0, __p1); \
6792	__ret; \	6530	__ret; \
6793	})	6531	})
6794	#define __noswap_vget_lane_s32(__p0, __p1) __extension__ ({ \	6532	#define __noswap_vget_lane_s32(__p0, __p1) __extension__ ({ \
6795	int32x2_t __s0 = __p0; \	6533	int32x2_t __s0 = __p0; \
6796	int32_t __ret; \	6534	int32_t __ret; \
6797	__ret = (int32_t) __builtin_neon_vget_lane_i32((int8x8_t)__s0, __p1); \	6535	__ret = (int32_t) __builtin_neon_vget_lane_i32((int32x2_t)__s0, __p1); \
6798	__ret; \	6536	__ret; \
6799	})	6537	})
6800	#endif	6538	#endif
6801		6539
6802	#ifdef __LITTLE_ENDIAN__
6803	#define vget_lane_s64(__p0, __p1) __extension__ ({ \
6804	int64x1_t __s0 = __p0; \
6805	int64_t __ret; \
6806	__ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6807	__ret; \
6808	})
6809	#else
6810	#define vget_lane_s64(__p0, __p1) __extension__ ({ \	6540	#define vget_lane_s64(__p0, __p1) __extension__ ({ \
6811	int64x1_t __s0 = __p0; \	6541	int64x1_t __s0 = __p0; \
6812	int64_t __ret; \	6542	int64_t __ret; \
6813	__ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \	6543	__ret = (int64_t) __builtin_neon_vget_lane_i64((int64x1_t)__s0, __p1); \
6814	__ret; \
6815	})
6816	#define __noswap_vget_lane_s64(__p0, __p1) __extension__ ({ \
6817	int64x1_t __s0 = __p0; \
6818	int64_t __ret; \
6819	__ret = (int64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
6820	__ret; \	6544	__ret; \
6821	})	6545	})
6822	#endif
6823
6824	#ifdef __LITTLE_ENDIAN__	6546	#ifdef __LITTLE_ENDIAN__
6825	#define vget_lane_s16(__p0, __p1) __extension__ ({ \	6547	#define vget_lane_s16(__p0, __p1) __extension__ ({ \
6826	int16x4_t __s0 = __p0; \	6548	int16x4_t __s0 = __p0; \
6827	int16_t __ret; \	6549	int16_t __ret; \
6828	__ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6550	__ret = (int16_t) __builtin_neon_vget_lane_i16((int16x4_t)__s0, __p1); \
6829	__ret; \	6551	__ret; \
6830	})	6552	})
6831	#else	6553	#else
...	@@ -6833,13 +6555,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {	...	@@ -6833,13 +6555,13 @@ __ai int16x4_t __noswap_vget_high_s16(int16x8_t __p0) {
6833	int16x4_t __s0 = __p0; \	6555	int16x4_t __s0 = __p0; \
6834	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	6556	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
6835	int16_t __ret; \	6557	int16_t __ret; \
6836	__ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__rev0, __p1); \	6558	__ret = (int16_t) __builtin_neon_vget_lane_i16((int16x4_t)__rev0, __p1); \
6837	__ret; \	6559	__ret; \
6838	})	6560	})
6839	#define __noswap_vget_lane_s16(__p0, __p1) __extension__ ({ \	6561	#define __noswap_vget_lane_s16(__p0, __p1) __extension__ ({ \
6840	int16x4_t __s0 = __p0; \	6562	int16x4_t __s0 = __p0; \
6841	int16_t __ret; \	6563	int16_t __ret; \
6842	__ret = (int16_t) __builtin_neon_vget_lane_i16((int8x8_t)__s0, __p1); \	6564	__ret = (int16_t) __builtin_neon_vget_lane_i16((int16x4_t)__s0, __p1); \
6843	__ret; \	6565	__ret; \
6844	})	6566	})
6845	#endif	6567	#endif
...	@@ -7667,20 +7389,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -7667,20 +7389,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
7667	})	7389	})
7668	#endif	7390	#endif
7669		7391
7670	#ifdef __LITTLE_ENDIAN__
7671	#define vld1_u64(__p0) __extension__ ({ \
7672	uint64x1_t __ret; \
7673	__ret = (uint64x1_t) __builtin_neon_vld1_v(__p0, 19); \
7674	__ret; \
7675	})
7676	#else
7677	#define vld1_u64(__p0) __extension__ ({ \	7392	#define vld1_u64(__p0) __extension__ ({ \
7678	uint64x1_t __ret; \	7393	uint64x1_t __ret; \
7679	__ret = (uint64x1_t) __builtin_neon_vld1_v(__p0, 19); \	7394	__ret = (uint64x1_t) __builtin_neon_vld1_v(__p0, 19); \
7680	__ret; \	7395	__ret; \
7681	})	7396	})
7682	#endif
7683
7684	#ifdef __LITTLE_ENDIAN__	7397	#ifdef __LITTLE_ENDIAN__
7685	#define vld1_u16(__p0) __extension__ ({ \	7398	#define vld1_u16(__p0) __extension__ ({ \
7686	uint16x4_t __ret; \	7399	uint16x4_t __ret; \
...	@@ -7741,20 +7454,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -7741,20 +7454,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
7741	})	7454	})
7742	#endif	7455	#endif
7743		7456
7744	#ifdef __LITTLE_ENDIAN__
7745	#define vld1_s64(__p0) __extension__ ({ \
7746	int64x1_t __ret; \
7747	__ret = (int64x1_t) __builtin_neon_vld1_v(__p0, 3); \
7748	__ret; \
7749	})
7750	#else
7751	#define vld1_s64(__p0) __extension__ ({ \	7457	#define vld1_s64(__p0) __extension__ ({ \
7752	int64x1_t __ret; \	7458	int64x1_t __ret; \
7753	__ret = (int64x1_t) __builtin_neon_vld1_v(__p0, 3); \	7459	__ret = (int64x1_t) __builtin_neon_vld1_v(__p0, 3); \
7754	__ret; \	7460	__ret; \
7755	})	7461	})
7756	#endif
7757
7758	#ifdef __LITTLE_ENDIAN__	7462	#ifdef __LITTLE_ENDIAN__
7759	#define vld1_s16(__p0) __extension__ ({ \	7463	#define vld1_s16(__p0) __extension__ ({ \
7760	int16x4_t __ret; \	7464	int16x4_t __ret; \
...	@@ -7995,20 +7699,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -7995,20 +7699,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
7995	})	7699	})
7996	#endif	7700	#endif
7997		7701
7998	#ifdef __LITTLE_ENDIAN__
7999	#define vld1_dup_u64(__p0) __extension__ ({ \	7702	#define vld1_dup_u64(__p0) __extension__ ({ \
8000	uint64x1_t __ret; \	7703	uint64x1_t __ret; \
8001	__ret = (uint64x1_t) __builtin_neon_vld1_dup_v(__p0, 19); \	7704	__ret = (uint64x1_t) __builtin_neon_vld1_dup_v(__p0, 19); \
8002	__ret; \	7705	__ret; \
8003	})	7706	})
8004	#else
8005	#define vld1_dup_u64(__p0) __extension__ ({ \
8006	uint64x1_t __ret; \
8007	__ret = (uint64x1_t) __builtin_neon_vld1_dup_v(__p0, 19); \
8008	__ret; \
8009	})
8010	#endif
8011
8012	#ifdef __LITTLE_ENDIAN__	7707	#ifdef __LITTLE_ENDIAN__
8013	#define vld1_dup_u16(__p0) __extension__ ({ \	7708	#define vld1_dup_u16(__p0) __extension__ ({ \
8014	uint16x4_t __ret; \	7709	uint16x4_t __ret; \
...	@@ -8069,20 +7764,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -8069,20 +7764,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
8069	})	7764	})
8070	#endif	7765	#endif
8071		7766
8072	#ifdef __LITTLE_ENDIAN__
8073	#define vld1_dup_s64(__p0) __extension__ ({ \
8074	int64x1_t __ret; \
8075	__ret = (int64x1_t) __builtin_neon_vld1_dup_v(__p0, 3); \
8076	__ret; \
8077	})
8078	#else
8079	#define vld1_dup_s64(__p0) __extension__ ({ \	7767	#define vld1_dup_s64(__p0) __extension__ ({ \
8080	int64x1_t __ret; \	7768	int64x1_t __ret; \
8081	__ret = (int64x1_t) __builtin_neon_vld1_dup_v(__p0, 3); \	7769	__ret = (int64x1_t) __builtin_neon_vld1_dup_v(__p0, 3); \
8082	__ret; \	7770	__ret; \
8083	})	7771	})
8084	#endif
8085
8086	#ifdef __LITTLE_ENDIAN__	7772	#ifdef __LITTLE_ENDIAN__
8087	#define vld1_dup_s16(__p0) __extension__ ({ \	7773	#define vld1_dup_s16(__p0) __extension__ ({ \
8088	int16x4_t __ret; \	7774	int16x4_t __ret; \
...	@@ -8368,22 +8054,12 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -8368,22 +8054,12 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
8368	})	8054	})
8369	#endif	8055	#endif
8370		8056
8371	#ifdef __LITTLE_ENDIAN__
8372	#define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8373	uint64x1_t __s1 = __p1; \
8374	uint64x1_t __ret; \
8375	__ret = (uint64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
8376	__ret; \
8377	})
8378	#else
8379	#define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({ \	8057	#define vld1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
8380	uint64x1_t __s1 = __p1; \	8058	uint64x1_t __s1 = __p1; \
8381	uint64x1_t __ret; \	8059	uint64x1_t __ret; \
8382	__ret = (uint64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \	8060	__ret = (uint64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
8383	__ret; \	8061	__ret; \
8384	})	8062	})
8385	#endif
8386
8387	#ifdef __LITTLE_ENDIAN__	8063	#ifdef __LITTLE_ENDIAN__
8388	#define vld1_lane_u16(__p0, __p1, __p2) __extension__ ({ \	8064	#define vld1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
8389	uint16x4_t __s1 = __p1; \	8065	uint16x4_t __s1 = __p1; \
...	@@ -8456,22 +8132,12 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -8456,22 +8132,12 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
8456	})	8132	})
8457	#endif	8133	#endif
8458		8134
8459	#ifdef __LITTLE_ENDIAN__
8460	#define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({ \	8135	#define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8461	int64x1_t __s1 = __p1; \	8136	int64x1_t __s1 = __p1; \
8462	int64x1_t __ret; \	8137	int64x1_t __ret; \
8463	__ret = (int64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \	8138	__ret = (int64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
8464	__ret; \	8139	__ret; \
8465	})	8140	})
8466	#else
8467	#define vld1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
8468	int64x1_t __s1 = __p1; \
8469	int64x1_t __ret; \
8470	__ret = (int64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
8471	__ret; \
8472	})
8473	#endif
8474
8475	#ifdef __LITTLE_ENDIAN__	8141	#ifdef __LITTLE_ENDIAN__
8476	#define vld1_lane_s16(__p0, __p1, __p2) __extension__ ({ \	8142	#define vld1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
8477	int16x4_t __s1 = __p1; \	8143	int16x4_t __s1 = __p1; \
...	@@ -8745,20 +8411,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -8745,20 +8411,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
8745	})	8411	})
8746	#endif	8412	#endif
8747		8413
8748	#ifdef __LITTLE_ENDIAN__
8749	#define vld1_u64_x2(__p0) __extension__ ({ \
8750	uint64x1x2_t __ret; \
8751	__builtin_neon_vld1_x2_v(&__ret, __p0, 19); \
8752	__ret; \
8753	})
8754	#else
8755	#define vld1_u64_x2(__p0) __extension__ ({ \	8414	#define vld1_u64_x2(__p0) __extension__ ({ \
8756	uint64x1x2_t __ret; \	8415	uint64x1x2_t __ret; \
8757	__builtin_neon_vld1_x2_v(&__ret, __p0, 19); \	8416	__builtin_neon_vld1_x2_v(&__ret, __p0, 19); \
8758	__ret; \	8417	__ret; \
8759	})	8418	})
8760	#endif
8761
8762	#ifdef __LITTLE_ENDIAN__	8419	#ifdef __LITTLE_ENDIAN__
8763	#define vld1_u16_x2(__p0) __extension__ ({ \	8420	#define vld1_u16_x2(__p0) __extension__ ({ \
8764	uint16x4x2_t __ret; \	8421	uint16x4x2_t __ret; \
...	@@ -8827,20 +8484,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -8827,20 +8484,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
8827	})	8484	})
8828	#endif	8485	#endif
8829		8486
8830	#ifdef __LITTLE_ENDIAN__
8831	#define vld1_s64_x2(__p0) __extension__ ({ \	8487	#define vld1_s64_x2(__p0) __extension__ ({ \
8832	int64x1x2_t __ret; \	8488	int64x1x2_t __ret; \
8833	__builtin_neon_vld1_x2_v(&__ret, __p0, 3); \	8489	__builtin_neon_vld1_x2_v(&__ret, __p0, 3); \
8834	__ret; \	8490	__ret; \
8835	})	8491	})
8836	#else
8837	#define vld1_s64_x2(__p0) __extension__ ({ \
8838	int64x1x2_t __ret; \
8839	__builtin_neon_vld1_x2_v(&__ret, __p0, 3); \
8840	__ret; \
8841	})
8842	#endif
8843
8844	#ifdef __LITTLE_ENDIAN__	8492	#ifdef __LITTLE_ENDIAN__
8845	#define vld1_s16_x2(__p0) __extension__ ({ \	8493	#define vld1_s16_x2(__p0) __extension__ ({ \
8846	int16x4x2_t __ret; \	8494	int16x4x2_t __ret; \
...	@@ -9128,20 +8776,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9128,20 +8776,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9128	})	8776	})
9129	#endif	8777	#endif
9130		8778
9131	#ifdef __LITTLE_ENDIAN__
9132	#define vld1_u64_x3(__p0) __extension__ ({ \
9133	uint64x1x3_t __ret; \
9134	__builtin_neon_vld1_x3_v(&__ret, __p0, 19); \
9135	__ret; \
9136	})
9137	#else
9138	#define vld1_u64_x3(__p0) __extension__ ({ \	8779	#define vld1_u64_x3(__p0) __extension__ ({ \
9139	uint64x1x3_t __ret; \	8780	uint64x1x3_t __ret; \
9140	__builtin_neon_vld1_x3_v(&__ret, __p0, 19); \	8781	__builtin_neon_vld1_x3_v(&__ret, __p0, 19); \
9141	__ret; \	8782	__ret; \
9142	})	8783	})
9143	#endif
9144
9145	#ifdef __LITTLE_ENDIAN__	8784	#ifdef __LITTLE_ENDIAN__
9146	#define vld1_u16_x3(__p0) __extension__ ({ \	8785	#define vld1_u16_x3(__p0) __extension__ ({ \
9147	uint16x4x3_t __ret; \	8786	uint16x4x3_t __ret; \
...	@@ -9214,20 +8853,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9214,20 +8853,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9214	})	8853	})
9215	#endif	8854	#endif
9216		8855
9217	#ifdef __LITTLE_ENDIAN__
9218	#define vld1_s64_x3(__p0) __extension__ ({ \	8856	#define vld1_s64_x3(__p0) __extension__ ({ \
9219	int64x1x3_t __ret; \	8857	int64x1x3_t __ret; \
9220	__builtin_neon_vld1_x3_v(&__ret, __p0, 3); \	8858	__builtin_neon_vld1_x3_v(&__ret, __p0, 3); \
9221	__ret; \	8859	__ret; \
9222	})	8860	})
9223	#else
9224	#define vld1_s64_x3(__p0) __extension__ ({ \
9225	int64x1x3_t __ret; \
9226	__builtin_neon_vld1_x3_v(&__ret, __p0, 3); \
9227	__ret; \
9228	})
9229	#endif
9230
9231	#ifdef __LITTLE_ENDIAN__	8861	#ifdef __LITTLE_ENDIAN__
9232	#define vld1_s16_x3(__p0) __extension__ ({ \	8862	#define vld1_s16_x3(__p0) __extension__ ({ \
9233	int16x4x3_t __ret; \	8863	int16x4x3_t __ret; \
...	@@ -9531,20 +9161,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9531,20 +9161,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9531	})	9161	})
9532	#endif	9162	#endif
9533		9163
9534	#ifdef __LITTLE_ENDIAN__
9535	#define vld1_u64_x4(__p0) __extension__ ({ \
9536	uint64x1x4_t __ret; \
9537	__builtin_neon_vld1_x4_v(&__ret, __p0, 19); \
9538	__ret; \
9539	})
9540	#else
9541	#define vld1_u64_x4(__p0) __extension__ ({ \	9164	#define vld1_u64_x4(__p0) __extension__ ({ \
9542	uint64x1x4_t __ret; \	9165	uint64x1x4_t __ret; \
9543	__builtin_neon_vld1_x4_v(&__ret, __p0, 19); \	9166	__builtin_neon_vld1_x4_v(&__ret, __p0, 19); \
9544	__ret; \	9167	__ret; \
9545	})	9168	})
9546	#endif
9547
9548	#ifdef __LITTLE_ENDIAN__	9169	#ifdef __LITTLE_ENDIAN__
9549	#define vld1_u16_x4(__p0) __extension__ ({ \	9170	#define vld1_u16_x4(__p0) __extension__ ({ \
9550	uint16x4x4_t __ret; \	9171	uint16x4x4_t __ret; \
...	@@ -9621,20 +9242,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9621,20 +9242,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9621	})	9242	})
9622	#endif	9243	#endif
9623		9244
9624	#ifdef __LITTLE_ENDIAN__
9625	#define vld1_s64_x4(__p0) __extension__ ({ \
9626	int64x1x4_t __ret; \
9627	__builtin_neon_vld1_x4_v(&__ret, __p0, 3); \
9628	__ret; \
9629	})
9630	#else
9631	#define vld1_s64_x4(__p0) __extension__ ({ \	9245	#define vld1_s64_x4(__p0) __extension__ ({ \
9632	int64x1x4_t __ret; \	9246	int64x1x4_t __ret; \
9633	__builtin_neon_vld1_x4_v(&__ret, __p0, 3); \	9247	__builtin_neon_vld1_x4_v(&__ret, __p0, 3); \
9634	__ret; \	9248	__ret; \
9635	})	9249	})
9636	#endif
9637
9638	#ifdef __LITTLE_ENDIAN__	9250	#ifdef __LITTLE_ENDIAN__
9639	#define vld1_s16_x4(__p0) __extension__ ({ \	9251	#define vld1_s16_x4(__p0) __extension__ ({ \
9640	int16x4x4_t __ret; \	9252	int16x4x4_t __ret; \
...	@@ -9875,20 +9487,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9875,20 +9487,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9875	})	9487	})
9876	#endif	9488	#endif
9877		9489
9878	#ifdef __LITTLE_ENDIAN__
9879	#define vld2_u64(__p0) __extension__ ({ \
9880	uint64x1x2_t __ret; \
9881	__builtin_neon_vld2_v(&__ret, __p0, 19); \
9882	__ret; \
9883	})
9884	#else
9885	#define vld2_u64(__p0) __extension__ ({ \	9490	#define vld2_u64(__p0) __extension__ ({ \
9886	uint64x1x2_t __ret; \	9491	uint64x1x2_t __ret; \
9887	__builtin_neon_vld2_v(&__ret, __p0, 19); \	9492	__builtin_neon_vld2_v(&__ret, __p0, 19); \
9888	__ret; \	9493	__ret; \
9889	})	9494	})
9890	#endif
9891
9892	#ifdef __LITTLE_ENDIAN__	9495	#ifdef __LITTLE_ENDIAN__
9893	#define vld2_u16(__p0) __extension__ ({ \	9496	#define vld2_u16(__p0) __extension__ ({ \
9894	uint16x4x2_t __ret; \	9497	uint16x4x2_t __ret; \
...	@@ -9957,20 +9560,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -9957,20 +9560,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
9957	})	9560	})
9958	#endif	9561	#endif
9959		9562
9960	#ifdef __LITTLE_ENDIAN__
9961	#define vld2_s64(__p0) __extension__ ({ \
9962	int64x1x2_t __ret; \
9963	__builtin_neon_vld2_v(&__ret, __p0, 3); \
9964	__ret; \
9965	})
9966	#else
9967	#define vld2_s64(__p0) __extension__ ({ \	9563	#define vld2_s64(__p0) __extension__ ({ \
9968	int64x1x2_t __ret; \	9564	int64x1x2_t __ret; \
9969	__builtin_neon_vld2_v(&__ret, __p0, 3); \	9565	__builtin_neon_vld2_v(&__ret, __p0, 3); \
9970	__ret; \	9566	__ret; \
9971	})	9567	})
9972	#endif
9973
9974	#ifdef __LITTLE_ENDIAN__	9568	#ifdef __LITTLE_ENDIAN__
9975	#define vld2_s16(__p0) __extension__ ({ \	9569	#define vld2_s16(__p0) __extension__ ({ \
9976	int16x4x2_t __ret; \	9570	int16x4x2_t __ret; \
...	@@ -10243,20 +9837,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10243,20 +9837,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10243	})	9837	})
10244	#endif	9838	#endif
10245		9839
10246	#ifdef __LITTLE_ENDIAN__
10247	#define vld2_dup_u64(__p0) __extension__ ({ \
10248	uint64x1x2_t __ret; \
10249	__builtin_neon_vld2_dup_v(&__ret, __p0, 19); \
10250	__ret; \
10251	})
10252	#else
10253	#define vld2_dup_u64(__p0) __extension__ ({ \	9840	#define vld2_dup_u64(__p0) __extension__ ({ \
10254	uint64x1x2_t __ret; \	9841	uint64x1x2_t __ret; \
10255	__builtin_neon_vld2_dup_v(&__ret, __p0, 19); \	9842	__builtin_neon_vld2_dup_v(&__ret, __p0, 19); \
10256	__ret; \	9843	__ret; \
10257	})	9844	})
10258	#endif
10259
10260	#ifdef __LITTLE_ENDIAN__	9845	#ifdef __LITTLE_ENDIAN__
10261	#define vld2_dup_u16(__p0) __extension__ ({ \	9846	#define vld2_dup_u16(__p0) __extension__ ({ \
10262	uint16x4x2_t __ret; \	9847	uint16x4x2_t __ret; \
...	@@ -10325,20 +9910,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10325,20 +9910,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10325	})	9910	})
10326	#endif	9911	#endif
10327		9912
10328	#ifdef __LITTLE_ENDIAN__
10329	#define vld2_dup_s64(__p0) __extension__ ({ \
10330	int64x1x2_t __ret; \
10331	__builtin_neon_vld2_dup_v(&__ret, __p0, 3); \
10332	__ret; \
10333	})
10334	#else
10335	#define vld2_dup_s64(__p0) __extension__ ({ \	9913	#define vld2_dup_s64(__p0) __extension__ ({ \
10336	int64x1x2_t __ret; \	9914	int64x1x2_t __ret; \
10337	__builtin_neon_vld2_dup_v(&__ret, __p0, 3); \	9915	__builtin_neon_vld2_dup_v(&__ret, __p0, 3); \
10338	__ret; \	9916	__ret; \
10339	})	9917	})
10340	#endif
10341
10342	#ifdef __LITTLE_ENDIAN__	9918	#ifdef __LITTLE_ENDIAN__
10343	#define vld2_dup_s16(__p0) __extension__ ({ \	9919	#define vld2_dup_s16(__p0) __extension__ ({ \
10344	int16x4x2_t __ret; \	9920	int16x4x2_t __ret; \
...	@@ -10470,7 +10046,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10470,7 +10046,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10470	#define vld2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	10046	#define vld2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10471	float32x4x2_t __s1 = __p1; \	10047	float32x4x2_t __s1 = __p1; \
10472	float32x4x2_t __ret; \	10048	float32x4x2_t __ret; \
10473	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 41); \	10049	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 41); \
10474	__ret; \	10050	__ret; \
10475	})	10051	})
10476	#else	10052	#else
...	@@ -10480,7 +10056,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10480,7 +10056,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10480	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	10056	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
10481	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	10057	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
10482	float32x4x2_t __ret; \	10058	float32x4x2_t __ret; \
10483	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 41); \	10059	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 41); \
10484	\	10060	\
10485	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	10061	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
10486	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	10062	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -10492,7 +10068,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10492,7 +10068,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10492	#define vld2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	10068	#define vld2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10493	int32x4x2_t __s1 = __p1; \	10069	int32x4x2_t __s1 = __p1; \
10494	int32x4x2_t __ret; \	10070	int32x4x2_t __ret; \
10495	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 34); \	10071	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 34); \
10496	__ret; \	10072	__ret; \
10497	})	10073	})
10498	#else	10074	#else
...	@@ -10502,7 +10078,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10502,7 +10078,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10502	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	10078	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
10503	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	10079	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
10504	int32x4x2_t __ret; \	10080	int32x4x2_t __ret; \
10505	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 34); \	10081	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 34); \
10506	\	10082	\
10507	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	10083	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
10508	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	10084	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -10514,7 +10090,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10514,7 +10090,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10514	#define vld2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	10090	#define vld2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10515	int16x8x2_t __s1 = __p1; \	10091	int16x8x2_t __s1 = __p1; \
10516	int16x8x2_t __ret; \	10092	int16x8x2_t __ret; \
10517	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 33); \	10093	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 33); \
10518	__ret; \	10094	__ret; \
10519	})	10095	})
10520	#else	10096	#else
...	@@ -10524,7 +10100,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10524,7 +10100,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10524	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	10100	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
10525	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	10101	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
10526	int16x8x2_t __ret; \	10102	int16x8x2_t __ret; \
10527	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 33); \	10103	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 33); \
10528	\	10104	\
10529	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	10105	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
10530	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	10106	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -10624,7 +10200,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10624,7 +10200,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10624	#define vld2_lane_f32(__p0, __p1, __p2) __extension__ ({ \	10200	#define vld2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
10625	float32x2x2_t __s1 = __p1; \	10201	float32x2x2_t __s1 = __p1; \
10626	float32x2x2_t __ret; \	10202	float32x2x2_t __ret; \
10627	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 9); \	10203	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 9); \
10628	__ret; \	10204	__ret; \
10629	})	10205	})
10630	#else	10206	#else
...	@@ -10634,7 +10210,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10634,7 +10210,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10634	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	10210	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
10635	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	10211	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
10636	float32x2x2_t __ret; \	10212	float32x2x2_t __ret; \
10637	__builtin_neon_vld2_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 9); \	10213	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 9); \
10638	\	10214	\
10639	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	10215	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
10640	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	10216	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -10646,7 +10222,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10646,7 +10222,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10646	#define vld2_lane_s32(__p0, __p1, __p2) __extension__ ({ \	10222	#define vld2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
10647	int32x2x2_t __s1 = __p1; \	10223	int32x2x2_t __s1 = __p1; \
10648	int32x2x2_t __ret; \	10224	int32x2x2_t __ret; \
10649	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 2); \	10225	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 2); \
10650	__ret; \	10226	__ret; \
10651	})	10227	})
10652	#else	10228	#else
...	@@ -10656,7 +10232,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10656,7 +10232,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10656	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	10232	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
10657	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	10233	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
10658	int32x2x2_t __ret; \	10234	int32x2x2_t __ret; \
10659	__builtin_neon_vld2_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 2); \	10235	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 2); \
10660	\	10236	\
10661	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	10237	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
10662	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	10238	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -10668,7 +10244,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10668,7 +10244,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10668	#define vld2_lane_s16(__p0, __p1, __p2) __extension__ ({ \	10244	#define vld2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
10669	int16x4x2_t __s1 = __p1; \	10245	int16x4x2_t __s1 = __p1; \
10670	int16x4x2_t __ret; \	10246	int16x4x2_t __ret; \
10671	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 1); \	10247	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 1); \
10672	__ret; \	10248	__ret; \
10673	})	10249	})
10674	#else	10250	#else
...	@@ -10678,7 +10254,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10678,7 +10254,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10678	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	10254	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
10679	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	10255	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
10680	int16x4x2_t __ret; \	10256	int16x4x2_t __ret; \
10681	__builtin_neon_vld2_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 1); \	10257	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 1); \
10682	\	10258	\
10683	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	10259	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
10684	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	10260	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -10920,20 +10496,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -10920,20 +10496,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
10920	})	10496	})
10921	#endif	10497	#endif
10922		10498
10923	#ifdef __LITTLE_ENDIAN__
10924	#define vld3_u64(__p0) __extension__ ({ \
10925	uint64x1x3_t __ret; \
10926	__builtin_neon_vld3_v(&__ret, __p0, 19); \
10927	__ret; \
10928	})
10929	#else
10930	#define vld3_u64(__p0) __extension__ ({ \	10499	#define vld3_u64(__p0) __extension__ ({ \
10931	uint64x1x3_t __ret; \	10500	uint64x1x3_t __ret; \
10932	__builtin_neon_vld3_v(&__ret, __p0, 19); \	10501	__builtin_neon_vld3_v(&__ret, __p0, 19); \
10933	__ret; \	10502	__ret; \
10934	})	10503	})
10935	#endif
10936
10937	#ifdef __LITTLE_ENDIAN__	10504	#ifdef __LITTLE_ENDIAN__
10938	#define vld3_u16(__p0) __extension__ ({ \	10505	#define vld3_u16(__p0) __extension__ ({ \
10939	uint16x4x3_t __ret; \	10506	uint16x4x3_t __ret; \
...	@@ -11006,20 +10573,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11006,20 +10573,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11006	})	10573	})
11007	#endif	10574	#endif
11008		10575
11009	#ifdef __LITTLE_ENDIAN__
11010	#define vld3_s64(__p0) __extension__ ({ \	10576	#define vld3_s64(__p0) __extension__ ({ \
11011	int64x1x3_t __ret; \	10577	int64x1x3_t __ret; \
11012	__builtin_neon_vld3_v(&__ret, __p0, 3); \	10578	__builtin_neon_vld3_v(&__ret, __p0, 3); \
11013	__ret; \	10579	__ret; \
11014	})	10580	})
11015	#else
11016	#define vld3_s64(__p0) __extension__ ({ \
11017	int64x1x3_t __ret; \
11018	__builtin_neon_vld3_v(&__ret, __p0, 3); \
11019	__ret; \
11020	})
11021	#endif
11022
11023	#ifdef __LITTLE_ENDIAN__	10581	#ifdef __LITTLE_ENDIAN__
11024	#define vld3_s16(__p0) __extension__ ({ \	10582	#define vld3_s16(__p0) __extension__ ({ \
11025	int16x4x3_t __ret; \	10583	int16x4x3_t __ret; \
...	@@ -11308,20 +10866,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11308,20 +10866,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11308	})	10866	})
11309	#endif	10867	#endif
11310		10868
11311	#ifdef __LITTLE_ENDIAN__
11312	#define vld3_dup_u64(__p0) __extension__ ({ \	10869	#define vld3_dup_u64(__p0) __extension__ ({ \
11313	uint64x1x3_t __ret; \	10870	uint64x1x3_t __ret; \
11314	__builtin_neon_vld3_dup_v(&__ret, __p0, 19); \	10871	__builtin_neon_vld3_dup_v(&__ret, __p0, 19); \
11315	__ret; \	10872	__ret; \
11316	})	10873	})
11317	#else
11318	#define vld3_dup_u64(__p0) __extension__ ({ \
11319	uint64x1x3_t __ret; \
11320	__builtin_neon_vld3_dup_v(&__ret, __p0, 19); \
11321	__ret; \
11322	})
11323	#endif
11324
11325	#ifdef __LITTLE_ENDIAN__	10874	#ifdef __LITTLE_ENDIAN__
11326	#define vld3_dup_u16(__p0) __extension__ ({ \	10875	#define vld3_dup_u16(__p0) __extension__ ({ \
11327	uint16x4x3_t __ret; \	10876	uint16x4x3_t __ret; \
...	@@ -11394,20 +10943,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11394,20 +10943,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11394	})	10943	})
11395	#endif	10944	#endif
11396		10945
11397	#ifdef __LITTLE_ENDIAN__
11398	#define vld3_dup_s64(__p0) __extension__ ({ \
11399	int64x1x3_t __ret; \
11400	__builtin_neon_vld3_dup_v(&__ret, __p0, 3); \
11401	__ret; \
11402	})
11403	#else
11404	#define vld3_dup_s64(__p0) __extension__ ({ \	10946	#define vld3_dup_s64(__p0) __extension__ ({ \
11405	int64x1x3_t __ret; \	10947	int64x1x3_t __ret; \
11406	__builtin_neon_vld3_dup_v(&__ret, __p0, 3); \	10948	__builtin_neon_vld3_dup_v(&__ret, __p0, 3); \
11407	__ret; \	10949	__ret; \
11408	})	10950	})
11409	#endif
11410
11411	#ifdef __LITTLE_ENDIAN__	10951	#ifdef __LITTLE_ENDIAN__
11412	#define vld3_dup_s16(__p0) __extension__ ({ \	10952	#define vld3_dup_s16(__p0) __extension__ ({ \
11413	int16x4x3_t __ret; \	10953	int16x4x3_t __ret; \
...	@@ -11550,7 +11090,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11550,7 +11090,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11550	#define vld3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	11090	#define vld3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11551	float32x4x3_t __s1 = __p1; \	11091	float32x4x3_t __s1 = __p1; \
11552	float32x4x3_t __ret; \	11092	float32x4x3_t __ret; \
11553	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 41); \	11093	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 41); \
11554	__ret; \	11094	__ret; \
11555	})	11095	})
11556	#else	11096	#else
...	@@ -11561,7 +11101,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11561,7 +11101,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11561	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	11101	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
11562	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	11102	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
11563	float32x4x3_t __ret; \	11103	float32x4x3_t __ret; \
11564	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 41); \	11104	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 41); \
11565	\	11105	\
11566	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	11106	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
11567	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	11107	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -11574,7 +11114,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11574,7 +11114,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11574	#define vld3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	11114	#define vld3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11575	int32x4x3_t __s1 = __p1; \	11115	int32x4x3_t __s1 = __p1; \
11576	int32x4x3_t __ret; \	11116	int32x4x3_t __ret; \
11577	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 34); \	11117	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 34); \
11578	__ret; \	11118	__ret; \
11579	})	11119	})
11580	#else	11120	#else
...	@@ -11585,7 +11125,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11585,7 +11125,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11585	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	11125	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
11586	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	11126	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
11587	int32x4x3_t __ret; \	11127	int32x4x3_t __ret; \
11588	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 34); \	11128	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 34); \
11589	\	11129	\
11590	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	11130	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
11591	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	11131	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -11598,7 +11138,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11598,7 +11138,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11598	#define vld3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	11138	#define vld3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11599	int16x8x3_t __s1 = __p1; \	11139	int16x8x3_t __s1 = __p1; \
11600	int16x8x3_t __ret; \	11140	int16x8x3_t __ret; \
11601	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 33); \	11141	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 33); \
11602	__ret; \	11142	__ret; \
11603	})	11143	})
11604	#else	11144	#else
...	@@ -11609,7 +11149,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11609,7 +11149,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11609	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	11149	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
11610	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	11150	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
11611	int16x8x3_t __ret; \	11151	int16x8x3_t __ret; \
11612	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 33); \	11152	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 33); \
11613	\	11153	\
11614	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	11154	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
11615	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	11155	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -11718,7 +11258,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11718,7 +11258,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11718	#define vld3_lane_f32(__p0, __p1, __p2) __extension__ ({ \	11258	#define vld3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
11719	float32x2x3_t __s1 = __p1; \	11259	float32x2x3_t __s1 = __p1; \
11720	float32x2x3_t __ret; \	11260	float32x2x3_t __ret; \
11721	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 9); \	11261	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 9); \
11722	__ret; \	11262	__ret; \
11723	})	11263	})
11724	#else	11264	#else
...	@@ -11729,7 +11269,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11729,7 +11269,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11729	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	11269	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
11730	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	11270	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
11731	float32x2x3_t __ret; \	11271	float32x2x3_t __ret; \
11732	__builtin_neon_vld3_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 9); \	11272	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 9); \
11733	\	11273	\
11734	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	11274	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
11735	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	11275	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -11742,7 +11282,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11742,7 +11282,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11742	#define vld3_lane_s32(__p0, __p1, __p2) __extension__ ({ \	11282	#define vld3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
11743	int32x2x3_t __s1 = __p1; \	11283	int32x2x3_t __s1 = __p1; \
11744	int32x2x3_t __ret; \	11284	int32x2x3_t __ret; \
11745	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 2); \	11285	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 2); \
11746	__ret; \	11286	__ret; \
11747	})	11287	})
11748	#else	11288	#else
...	@@ -11753,7 +11293,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11753,7 +11293,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11753	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	11293	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
11754	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	11294	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
11755	int32x2x3_t __ret; \	11295	int32x2x3_t __ret; \
11756	__builtin_neon_vld3_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 2); \	11296	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 2); \
11757	\	11297	\
11758	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	11298	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
11759	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	11299	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -11766,7 +11306,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11766,7 +11306,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11766	#define vld3_lane_s16(__p0, __p1, __p2) __extension__ ({ \	11306	#define vld3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
11767	int16x4x3_t __s1 = __p1; \	11307	int16x4x3_t __s1 = __p1; \
11768	int16x4x3_t __ret; \	11308	int16x4x3_t __ret; \
11769	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 1); \	11309	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 1); \
11770	__ret; \	11310	__ret; \
11771	})	11311	})
11772	#else	11312	#else
...	@@ -11777,7 +11317,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -11777,7 +11317,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
11777	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	11317	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
11778	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	11318	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
11779	int16x4x3_t __ret; \	11319	int16x4x3_t __ret; \
11780	__builtin_neon_vld3_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 1); \	11320	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 1); \
11781	\	11321	\
11782	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	11322	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
11783	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	11323	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -12033,20 +11573,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12033,20 +11573,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12033	})	11573	})
12034	#endif	11574	#endif
12035		11575
12036	#ifdef __LITTLE_ENDIAN__
12037	#define vld4_u64(__p0) __extension__ ({ \
12038	uint64x1x4_t __ret; \
12039	__builtin_neon_vld4_v(&__ret, __p0, 19); \
12040	__ret; \
12041	})
12042	#else
12043	#define vld4_u64(__p0) __extension__ ({ \	11576	#define vld4_u64(__p0) __extension__ ({ \
12044	uint64x1x4_t __ret; \	11577	uint64x1x4_t __ret; \
12045	__builtin_neon_vld4_v(&__ret, __p0, 19); \	11578	__builtin_neon_vld4_v(&__ret, __p0, 19); \
12046	__ret; \	11579	__ret; \
12047	})	11580	})
12048	#endif
12049
12050	#ifdef __LITTLE_ENDIAN__	11581	#ifdef __LITTLE_ENDIAN__
12051	#define vld4_u16(__p0) __extension__ ({ \	11582	#define vld4_u16(__p0) __extension__ ({ \
12052	uint16x4x4_t __ret; \	11583	uint16x4x4_t __ret; \
...	@@ -12123,20 +11654,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12123,20 +11654,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12123	})	11654	})
12124	#endif	11655	#endif
12125		11656
12126	#ifdef __LITTLE_ENDIAN__
12127	#define vld4_s64(__p0) __extension__ ({ \	11657	#define vld4_s64(__p0) __extension__ ({ \
12128	int64x1x4_t __ret; \	11658	int64x1x4_t __ret; \
12129	__builtin_neon_vld4_v(&__ret, __p0, 3); \	11659	__builtin_neon_vld4_v(&__ret, __p0, 3); \
12130	__ret; \	11660	__ret; \
12131	})	11661	})
12132	#else
12133	#define vld4_s64(__p0) __extension__ ({ \
12134	int64x1x4_t __ret; \
12135	__builtin_neon_vld4_v(&__ret, __p0, 3); \
12136	__ret; \
12137	})
12138	#endif
12139
12140	#ifdef __LITTLE_ENDIAN__	11662	#ifdef __LITTLE_ENDIAN__
12141	#define vld4_s16(__p0) __extension__ ({ \	11663	#define vld4_s16(__p0) __extension__ ({ \
12142	int16x4x4_t __ret; \	11664	int16x4x4_t __ret; \
...	@@ -12441,20 +11963,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12441,20 +11963,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12441	})	11963	})
12442	#endif	11964	#endif
12443		11965
12444	#ifdef __LITTLE_ENDIAN__
12445	#define vld4_dup_u64(__p0) __extension__ ({ \
12446	uint64x1x4_t __ret; \
12447	__builtin_neon_vld4_dup_v(&__ret, __p0, 19); \
12448	__ret; \
12449	})
12450	#else
12451	#define vld4_dup_u64(__p0) __extension__ ({ \	11966	#define vld4_dup_u64(__p0) __extension__ ({ \
12452	uint64x1x4_t __ret; \	11967	uint64x1x4_t __ret; \
12453	__builtin_neon_vld4_dup_v(&__ret, __p0, 19); \	11968	__builtin_neon_vld4_dup_v(&__ret, __p0, 19); \
12454	__ret; \	11969	__ret; \
12455	})	11970	})
12456	#endif
12457
12458	#ifdef __LITTLE_ENDIAN__	11971	#ifdef __LITTLE_ENDIAN__
12459	#define vld4_dup_u16(__p0) __extension__ ({ \	11972	#define vld4_dup_u16(__p0) __extension__ ({ \
12460	uint16x4x4_t __ret; \	11973	uint16x4x4_t __ret; \
...	@@ -12531,20 +12044,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12531,20 +12044,11 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12531	})	12044	})
12532	#endif	12045	#endif
12533		12046
12534	#ifdef __LITTLE_ENDIAN__
12535	#define vld4_dup_s64(__p0) __extension__ ({ \
12536	int64x1x4_t __ret; \
12537	__builtin_neon_vld4_dup_v(&__ret, __p0, 3); \
12538	__ret; \
12539	})
12540	#else
12541	#define vld4_dup_s64(__p0) __extension__ ({ \	12047	#define vld4_dup_s64(__p0) __extension__ ({ \
12542	int64x1x4_t __ret; \	12048	int64x1x4_t __ret; \
12543	__builtin_neon_vld4_dup_v(&__ret, __p0, 3); \	12049	__builtin_neon_vld4_dup_v(&__ret, __p0, 3); \
12544	__ret; \	12050	__ret; \
12545	})	12051	})
12546	#endif
12547
12548	#ifdef __LITTLE_ENDIAN__	12052	#ifdef __LITTLE_ENDIAN__
12549	#define vld4_dup_s16(__p0) __extension__ ({ \	12053	#define vld4_dup_s16(__p0) __extension__ ({ \
12550	int16x4x4_t __ret; \	12054	int16x4x4_t __ret; \
...	@@ -12698,7 +12202,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12698,7 +12202,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12698	#define vld4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	12202	#define vld4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
12699	float32x4x4_t __s1 = __p1; \	12203	float32x4x4_t __s1 = __p1; \
12700	float32x4x4_t __ret; \	12204	float32x4x4_t __ret; \
12701	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 41); \	12205	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 41); \
12702	__ret; \	12206	__ret; \
12703	})	12207	})
12704	#else	12208	#else
...	@@ -12710,7 +12214,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12710,7 +12214,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12710	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	12214	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
12711	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	12215	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
12712	float32x4x4_t __ret; \	12216	float32x4x4_t __ret; \
12713	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 41); \	12217	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 41); \
12714	\	12218	\
12715	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	12219	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
12716	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	12220	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -12724,7 +12228,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12724,7 +12228,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12724	#define vld4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	12228	#define vld4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
12725	int32x4x4_t __s1 = __p1; \	12229	int32x4x4_t __s1 = __p1; \
12726	int32x4x4_t __ret; \	12230	int32x4x4_t __ret; \
12727	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 34); \	12231	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 34); \
12728	__ret; \	12232	__ret; \
12729	})	12233	})
12730	#else	12234	#else
...	@@ -12736,7 +12240,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12736,7 +12240,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12736	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	12240	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
12737	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	12241	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
12738	int32x4x4_t __ret; \	12242	int32x4x4_t __ret; \
12739	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 34); \	12243	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 34); \
12740	\	12244	\
12741	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	12245	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
12742	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	12246	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -12750,7 +12254,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12750,7 +12254,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12750	#define vld4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	12254	#define vld4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
12751	int16x8x4_t __s1 = __p1; \	12255	int16x8x4_t __s1 = __p1; \
12752	int16x8x4_t __ret; \	12256	int16x8x4_t __ret; \
12753	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 33); \	12257	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 33); \
12754	__ret; \	12258	__ret; \
12755	})	12259	})
12756	#else	12260	#else
...	@@ -12762,7 +12266,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12762,7 +12266,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12762	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	12266	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
12763	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	12267	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
12764	int16x8x4_t __ret; \	12268	int16x8x4_t __ret; \
12765	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 33); \	12269	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 33); \
12766	\	12270	\
12767	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	12271	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
12768	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	12272	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -12880,7 +12384,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12880,7 +12384,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12880	#define vld4_lane_f32(__p0, __p1, __p2) __extension__ ({ \	12384	#define vld4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
12881	float32x2x4_t __s1 = __p1; \	12385	float32x2x4_t __s1 = __p1; \
12882	float32x2x4_t __ret; \	12386	float32x2x4_t __ret; \
12883	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 9); \	12387	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 9); \
12884	__ret; \	12388	__ret; \
12885	})	12389	})
12886	#else	12390	#else
...	@@ -12892,7 +12396,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12892,7 +12396,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12892	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	12396	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
12893	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	12397	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
12894	float32x2x4_t __ret; \	12398	float32x2x4_t __ret; \
12895	__builtin_neon_vld4_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 9); \	12399	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 9); \
12896	\	12400	\
12897	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	12401	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
12898	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	12402	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -12906,7 +12410,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12906,7 +12410,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12906	#define vld4_lane_s32(__p0, __p1, __p2) __extension__ ({ \	12410	#define vld4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
12907	int32x2x4_t __s1 = __p1; \	12411	int32x2x4_t __s1 = __p1; \
12908	int32x2x4_t __ret; \	12412	int32x2x4_t __ret; \
12909	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 2); \	12413	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 2); \
12910	__ret; \	12414	__ret; \
12911	})	12415	})
12912	#else	12416	#else
...	@@ -12918,7 +12422,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12918,7 +12422,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12918	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	12422	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
12919	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	12423	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
12920	int32x2x4_t __ret; \	12424	int32x2x4_t __ret; \
12921	__builtin_neon_vld4_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 2); \	12425	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 2); \
12922	\	12426	\
12923	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	12427	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
12924	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	12428	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -12932,7 +12436,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12932,7 +12436,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12932	#define vld4_lane_s16(__p0, __p1, __p2) __extension__ ({ \	12436	#define vld4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
12933	int16x4x4_t __s1 = __p1; \	12437	int16x4x4_t __s1 = __p1; \
12934	int16x4x4_t __ret; \	12438	int16x4x4_t __ret; \
12935	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 1); \	12439	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 1); \
12936	__ret; \	12440	__ret; \
12937	})	12441	})
12938	#else	12442	#else
...	@@ -12944,7 +12448,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -12944,7 +12448,7 @@ __ai int16x4_t vhsub_s16(int16x4_t __p0, int16x4_t __p1) {
12944	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	12448	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
12945	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	12449	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
12946	int16x4x4_t __ret; \	12450	int16x4x4_t __ret; \
12947	__builtin_neon_vld4_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 1); \	12451	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 1); \
12948	\	12452	\
12949	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	12453	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
12950	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	12454	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -14996,20 +14500,11 @@ __ai uint32x2_t vmov_n_u32(uint32_t __p0) {	...	@@ -14996,20 +14500,11 @@ __ai uint32x2_t vmov_n_u32(uint32_t __p0) {
14996	}	14500	}
14997	#endif	14501	#endif
14998		14502
14999	#ifdef __LITTLE_ENDIAN__
15000	__ai uint64x1_t vmov_n_u64(uint64_t __p0) {
15001	uint64x1_t __ret;
15002	__ret = (uint64x1_t) {__p0};
15003	return __ret;
15004	}
15005	#else
15006	__ai uint64x1_t vmov_n_u64(uint64_t __p0) {	14503	__ai uint64x1_t vmov_n_u64(uint64_t __p0) {
15007	uint64x1_t __ret;	14504	uint64x1_t __ret;
15008	__ret = (uint64x1_t) {__p0};	14505	__ret = (uint64x1_t) {__p0};
15009	return __ret;	14506	return __ret;
15010	}	14507	}
15011	#endif
15012
15013	#ifdef __LITTLE_ENDIAN__	14508	#ifdef __LITTLE_ENDIAN__
15014	__ai uint16x4_t vmov_n_u16(uint16_t __p0) {	14509	__ai uint16x4_t vmov_n_u16(uint16_t __p0) {
15015	uint16x4_t __ret;	14510	uint16x4_t __ret;
...	@@ -15087,20 +14582,11 @@ __ai int32x2_t vmov_n_s32(int32_t __p0) {	...	@@ -15087,20 +14582,11 @@ __ai int32x2_t vmov_n_s32(int32_t __p0) {
15087	}	14582	}
15088	#endif	14583	#endif
15089		14584
15090	#ifdef __LITTLE_ENDIAN__
15091	__ai int64x1_t vmov_n_s64(int64_t __p0) {
15092	int64x1_t __ret;
15093	__ret = (int64x1_t) {__p0};
15094	return __ret;
15095	}
15096	#else
15097	__ai int64x1_t vmov_n_s64(int64_t __p0) {	14585	__ai int64x1_t vmov_n_s64(int64_t __p0) {
15098	int64x1_t __ret;	14586	int64x1_t __ret;
15099	__ret = (int64x1_t) {__p0};	14587	__ret = (int64x1_t) {__p0};
15100	return __ret;	14588	return __ret;
15101	}	14589	}
15102	#endif
15103
15104	#ifdef __LITTLE_ENDIAN__	14590	#ifdef __LITTLE_ENDIAN__
15105	__ai int16x4_t vmov_n_s16(int16_t __p0) {	14591	__ai int16x4_t vmov_n_s16(int16_t __p0) {
15106	int16x4_t __ret;	14592	int16x4_t __ret;
...	@@ -16251,20 +15737,20 @@ __ai int32x4_t __noswap_vmull_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -16251,20 +15737,20 @@ __ai int32x4_t __noswap_vmull_s16(int16x4_t __p0, int16x4_t __p1) {
16251	#ifdef __LITTLE_ENDIAN__	15737	#ifdef __LITTLE_ENDIAN__
16252	__ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {	15738	__ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
16253	uint64x2_t __ret;	15739	uint64x2_t __ret;
16254	__ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);	15740	__ret = vmull_u32(__p0, (uint32x2_t) {__p1, __p1});
16255	return __ret;	15741	return __ret;
16256	}	15742	}
16257	#else	15743	#else
16258	__ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {	15744	__ai uint64x2_t vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
16259	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	15745	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
16260	uint64x2_t __ret;	15746	uint64x2_t __ret;
16261	__ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);	15747	__ret = __noswap_vmull_u32(__rev0, (uint32x2_t) {__p1, __p1});
16262	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	15748	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
16263	return __ret;	15749	return __ret;
16264	}	15750	}
16265	__ai uint64x2_t __noswap_vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {	15751	__ai uint64x2_t __noswap_vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
16266	uint64x2_t __ret;	15752	uint64x2_t __ret;
16267	__ret = (uint64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint32x2_t) {__p1, __p1}, 51);	15753	__ret = __noswap_vmull_u32(__p0, (uint32x2_t) {__p1, __p1});
16268	return __ret;	15754	return __ret;
16269	}	15755	}
16270	#endif	15756	#endif
...	@@ -16272,20 +15758,20 @@ __ai uint64x2_t __noswap_vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {	...	@@ -16272,20 +15758,20 @@ __ai uint64x2_t __noswap_vmull_n_u32(uint32x2_t __p0, uint32_t __p1) {
16272	#ifdef __LITTLE_ENDIAN__	15758	#ifdef __LITTLE_ENDIAN__
16273	__ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {	15759	__ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
16274	uint32x4_t __ret;	15760	uint32x4_t __ret;
16275	__ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);	15761	__ret = vmull_u16(__p0, (uint16x4_t) {__p1, __p1, __p1, __p1});
16276	return __ret;	15762	return __ret;
16277	}	15763	}
16278	#else	15764	#else
16279	__ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {	15765	__ai uint32x4_t vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
16280	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	15766	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
16281	uint32x4_t __ret;	15767	uint32x4_t __ret;
16282	__ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);	15768	__ret = __noswap_vmull_u16(__rev0, (uint16x4_t) {__p1, __p1, __p1, __p1});
16283	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	15769	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
16284	return __ret;	15770	return __ret;
16285	}	15771	}
16286	__ai uint32x4_t __noswap_vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {	15772	__ai uint32x4_t __noswap_vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
16287	uint32x4_t __ret;	15773	uint32x4_t __ret;
16288	__ret = (uint32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(uint16x4_t) {__p1, __p1, __p1, __p1}, 50);	15774	__ret = __noswap_vmull_u16(__p0, (uint16x4_t) {__p1, __p1, __p1, __p1});
16289	return __ret;	15775	return __ret;
16290	}	15776	}
16291	#endif	15777	#endif
...	@@ -16293,20 +15779,20 @@ __ai uint32x4_t __noswap_vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {	...	@@ -16293,20 +15779,20 @@ __ai uint32x4_t __noswap_vmull_n_u16(uint16x4_t __p0, uint16_t __p1) {
16293	#ifdef __LITTLE_ENDIAN__	15779	#ifdef __LITTLE_ENDIAN__
16294	__ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {	15780	__ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {
16295	int64x2_t __ret;	15781	int64x2_t __ret;
16296	__ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	15782	__ret = vmull_s32(__p0, (int32x2_t) {__p1, __p1});
16297	return __ret;	15783	return __ret;
16298	}	15784	}
16299	#else	15785	#else
16300	__ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {	15786	__ai int64x2_t vmull_n_s32(int32x2_t __p0, int32_t __p1) {
16301	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	15787	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
16302	int64x2_t __ret;	15788	int64x2_t __ret;
16303	__ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	15789	__ret = __noswap_vmull_s32(__rev0, (int32x2_t) {__p1, __p1});
16304	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	15790	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
16305	return __ret;	15791	return __ret;
16306	}	15792	}
16307	__ai int64x2_t __noswap_vmull_n_s32(int32x2_t __p0, int32_t __p1) {	15793	__ai int64x2_t __noswap_vmull_n_s32(int32x2_t __p0, int32_t __p1) {
16308	int64x2_t __ret;	15794	int64x2_t __ret;
16309	__ret = (int64x2_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	15795	__ret = __noswap_vmull_s32(__p0, (int32x2_t) {__p1, __p1});
16310	return __ret;	15796	return __ret;
16311	}	15797	}
16312	#endif	15798	#endif
...	@@ -16314,20 +15800,20 @@ __ai int64x2_t __noswap_vmull_n_s32(int32x2_t __p0, int32_t __p1) {	...	@@ -16314,20 +15800,20 @@ __ai int64x2_t __noswap_vmull_n_s32(int32x2_t __p0, int32_t __p1) {
16314	#ifdef __LITTLE_ENDIAN__	15800	#ifdef __LITTLE_ENDIAN__
16315	__ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {	15801	__ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {
16316	int32x4_t __ret;	15802	int32x4_t __ret;
16317	__ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	15803	__ret = vmull_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
16318	return __ret;	15804	return __ret;
16319	}	15805	}
16320	#else	15806	#else
16321	__ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {	15807	__ai int32x4_t vmull_n_s16(int16x4_t __p0, int16_t __p1) {
16322	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	15808	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
16323	int32x4_t __ret;	15809	int32x4_t __ret;
16324	__ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	15810	__ret = __noswap_vmull_s16(__rev0, (int16x4_t) {__p1, __p1, __p1, __p1});
16325	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	15811	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
16326	return __ret;	15812	return __ret;
16327	}	15813	}
16328	__ai int32x4_t __noswap_vmull_n_s16(int16x4_t __p0, int16_t __p1) {	15814	__ai int32x4_t __noswap_vmull_n_s16(int16x4_t __p0, int16_t __p1) {
16329	int32x4_t __ret;	15815	int32x4_t __ret;
16330	__ret = (int32x4_t) __builtin_neon_vmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	15816	__ret = __noswap_vmull_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
16331	return __ret;	15817	return __ret;
16332	}	15818	}
16333	#endif	15819	#endif
...	@@ -16854,20 +16340,11 @@ __ai uint32x2_t vorn_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -16854,20 +16340,11 @@ __ai uint32x2_t vorn_u32(uint32x2_t __p0, uint32x2_t __p1) {
16854	}	16340	}
16855	#endif	16341	#endif
16856		16342
16857	#ifdef __LITTLE_ENDIAN__
16858	__ai uint64x1_t vorn_u64(uint64x1_t __p0, uint64x1_t __p1) {	16343	__ai uint64x1_t vorn_u64(uint64x1_t __p0, uint64x1_t __p1) {
16859	uint64x1_t __ret;	16344	uint64x1_t __ret;
16860	__ret = __p0 \| ~__p1;	16345	__ret = __p0 \| ~__p1;
16861	return __ret;	16346	return __ret;
16862	}	16347	}
16863	#else
16864	__ai uint64x1_t vorn_u64(uint64x1_t __p0, uint64x1_t __p1) {
16865	uint64x1_t __ret;
16866	__ret = __p0 \| ~__p1;
16867	return __ret;
16868	}
16869	#endif
16870
16871	#ifdef __LITTLE_ENDIAN__	16348	#ifdef __LITTLE_ENDIAN__
16872	__ai uint16x4_t vorn_u16(uint16x4_t __p0, uint16x4_t __p1) {	16349	__ai uint16x4_t vorn_u16(uint16x4_t __p0, uint16x4_t __p1) {
16873	uint16x4_t __ret;	16350	uint16x4_t __ret;
...	@@ -16919,20 +16396,11 @@ __ai int32x2_t vorn_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -16919,20 +16396,11 @@ __ai int32x2_t vorn_s32(int32x2_t __p0, int32x2_t __p1) {
16919	}	16396	}
16920	#endif	16397	#endif
16921		16398
16922	#ifdef __LITTLE_ENDIAN__
16923	__ai int64x1_t vorn_s64(int64x1_t __p0, int64x1_t __p1) {	16399	__ai int64x1_t vorn_s64(int64x1_t __p0, int64x1_t __p1) {
16924	int64x1_t __ret;	16400	int64x1_t __ret;
16925	__ret = __p0 \| ~__p1;	16401	__ret = __p0 \| ~__p1;
16926	return __ret;	16402	return __ret;
16927	}	16403	}
16928	#else
16929	__ai int64x1_t vorn_s64(int64x1_t __p0, int64x1_t __p1) {
16930	int64x1_t __ret;
16931	__ret = __p0 \| ~__p1;
16932	return __ret;
16933	}
16934	#endif
16935
16936	#ifdef __LITTLE_ENDIAN__	16404	#ifdef __LITTLE_ENDIAN__
16937	__ai int16x4_t vorn_s16(int16x4_t __p0, int16x4_t __p1) {	16405	__ai int16x4_t vorn_s16(int16x4_t __p0, int16x4_t __p1) {
16938	int16x4_t __ret;	16406	int16x4_t __ret;
...	@@ -17120,20 +16588,11 @@ __ai uint32x2_t vorr_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -17120,20 +16588,11 @@ __ai uint32x2_t vorr_u32(uint32x2_t __p0, uint32x2_t __p1) {
17120	}	16588	}
17121	#endif	16589	#endif
17122		16590
17123	#ifdef __LITTLE_ENDIAN__
17124	__ai uint64x1_t vorr_u64(uint64x1_t __p0, uint64x1_t __p1) {
17125	uint64x1_t __ret;
17126	__ret = __p0 \| __p1;
17127	return __ret;
17128	}
17129	#else
17130	__ai uint64x1_t vorr_u64(uint64x1_t __p0, uint64x1_t __p1) {	16591	__ai uint64x1_t vorr_u64(uint64x1_t __p0, uint64x1_t __p1) {
17131	uint64x1_t __ret;	16592	uint64x1_t __ret;
17132	__ret = __p0 \| __p1;	16593	__ret = __p0 \| __p1;
17133	return __ret;	16594	return __ret;
17134	}	16595	}
17135	#endif
17136
17137	#ifdef __LITTLE_ENDIAN__	16596	#ifdef __LITTLE_ENDIAN__
17138	__ai uint16x4_t vorr_u16(uint16x4_t __p0, uint16x4_t __p1) {	16597	__ai uint16x4_t vorr_u16(uint16x4_t __p0, uint16x4_t __p1) {
17139	uint16x4_t __ret;	16598	uint16x4_t __ret;
...	@@ -17185,20 +16644,11 @@ __ai int32x2_t vorr_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -17185,20 +16644,11 @@ __ai int32x2_t vorr_s32(int32x2_t __p0, int32x2_t __p1) {
17185	}	16644	}
17186	#endif	16645	#endif
17187		16646
17188	#ifdef __LITTLE_ENDIAN__
17189	__ai int64x1_t vorr_s64(int64x1_t __p0, int64x1_t __p1) {
17190	int64x1_t __ret;
17191	__ret = __p0 \| __p1;
17192	return __ret;
17193	}
17194	#else
17195	__ai int64x1_t vorr_s64(int64x1_t __p0, int64x1_t __p1) {	16647	__ai int64x1_t vorr_s64(int64x1_t __p0, int64x1_t __p1) {
17196	int64x1_t __ret;	16648	int64x1_t __ret;
17197	__ret = __p0 \| __p1;	16649	__ret = __p0 \| __p1;
17198	return __ret;	16650	return __ret;
17199	}	16651	}
17200	#endif
17201
17202	#ifdef __LITTLE_ENDIAN__	16652	#ifdef __LITTLE_ENDIAN__
17203	__ai int16x4_t vorr_s16(int16x4_t __p0, int16x4_t __p1) {	16653	__ai int16x4_t vorr_s16(int16x4_t __p0, int16x4_t __p1) {
17204	int16x4_t __ret;	16654	int16x4_t __ret;
...	@@ -18239,20 +17689,11 @@ __ai uint32x2_t vqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -18239,20 +17689,11 @@ __ai uint32x2_t vqadd_u32(uint32x2_t __p0, uint32x2_t __p1) {
18239	}	17689	}
18240	#endif	17690	#endif
18241		17691
18242	#ifdef __LITTLE_ENDIAN__
18243	__ai uint64x1_t vqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
18244	uint64x1_t __ret;
18245	__ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18246	return __ret;
18247	}
18248	#else
18249	__ai uint64x1_t vqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {	17692	__ai uint64x1_t vqadd_u64(uint64x1_t __p0, uint64x1_t __p1) {
18250	uint64x1_t __ret;	17693	uint64x1_t __ret;
18251	__ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	17694	__ret = (uint64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
18252	return __ret;	17695	return __ret;
18253	}	17696	}
18254	#endif
18255
18256	#ifdef __LITTLE_ENDIAN__	17697	#ifdef __LITTLE_ENDIAN__
18257	__ai uint16x4_t vqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {	17698	__ai uint16x4_t vqadd_u16(uint16x4_t __p0, uint16x4_t __p1) {
18258	uint16x4_t __ret;	17699	uint16x4_t __ret;
...	@@ -18309,20 +17750,11 @@ __ai int32x2_t __noswap_vqadd_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -18309,20 +17750,11 @@ __ai int32x2_t __noswap_vqadd_s32(int32x2_t __p0, int32x2_t __p1) {
18309	}	17750	}
18310	#endif	17751	#endif
18311		17752
18312	#ifdef __LITTLE_ENDIAN__
18313	__ai int64x1_t vqadd_s64(int64x1_t __p0, int64x1_t __p1) {
18314	int64x1_t __ret;
18315	__ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18316	return __ret;
18317	}
18318	#else
18319	__ai int64x1_t vqadd_s64(int64x1_t __p0, int64x1_t __p1) {	17753	__ai int64x1_t vqadd_s64(int64x1_t __p0, int64x1_t __p1) {
18320	int64x1_t __ret;	17754	int64x1_t __ret;
18321	__ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	17755	__ret = (int64x1_t) __builtin_neon_vqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
18322	return __ret;	17756	return __ret;
18323	}	17757	}
18324	#endif
18325
18326	#ifdef __LITTLE_ENDIAN__	17758	#ifdef __LITTLE_ENDIAN__
18327	__ai int16x4_t vqadd_s16(int16x4_t __p0, int16x4_t __p1) {	17759	__ai int16x4_t vqadd_s16(int16x4_t __p0, int16x4_t __p1) {
18328	int16x4_t __ret;	17760	int16x4_t __ret;
...	@@ -18442,7 +17874,7 @@ __ai int32x4_t __noswap_vqdmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __	...	@@ -18442,7 +17874,7 @@ __ai int32x4_t __noswap_vqdmlal_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __
18442	#ifdef __LITTLE_ENDIAN__	17874	#ifdef __LITTLE_ENDIAN__
18443	__ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	17875	__ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18444	int64x2_t __ret;	17876	int64x2_t __ret;
18445	__ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	17877	__ret = vqdmlal_s32(__p0, __p1, (int32x2_t) {__p2, __p2});
18446	return __ret;	17878	return __ret;
18447	}	17879	}
18448	#else	17880	#else
...	@@ -18450,13 +17882,13 @@ __ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	...	@@ -18450,13 +17882,13 @@ __ai int64x2_t vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18450	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	17882	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
18451	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);	17883	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18452	int64x2_t __ret;	17884	int64x2_t __ret;
18453	__ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	17885	__ret = __noswap_vqdmlal_s32(__rev0, __rev1, (int32x2_t) {__p2, __p2});
18454	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	17886	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
18455	return __ret;	17887	return __ret;
18456	}	17888	}
18457	__ai int64x2_t __noswap_vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	17889	__ai int64x2_t __noswap_vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18458	int64x2_t __ret;	17890	int64x2_t __ret;
18459	__ret = (int64x2_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	17891	__ret = __noswap_vqdmlal_s32(__p0, __p1, (int32x2_t) {__p2, __p2});
18460	return __ret;	17892	return __ret;
18461	}	17893	}
18462	#endif	17894	#endif
...	@@ -18464,7 +17896,7 @@ __ai int64x2_t __noswap_vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __	...	@@ -18464,7 +17896,7 @@ __ai int64x2_t __noswap_vqdmlal_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __
18464	#ifdef __LITTLE_ENDIAN__	17896	#ifdef __LITTLE_ENDIAN__
18465	__ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	17897	__ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18466	int32x4_t __ret;	17898	int32x4_t __ret;
18467	__ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	17899	__ret = vqdmlal_s16(__p0, __p1, (int16x4_t) {__p2, __p2, __p2, __p2});
18468	return __ret;	17900	return __ret;
18469	}	17901	}
18470	#else	17902	#else
...	@@ -18472,13 +17904,13 @@ __ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	...	@@ -18472,13 +17904,13 @@ __ai int32x4_t vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18472	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	17904	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
18473	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);	17905	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18474	int32x4_t __ret;	17906	int32x4_t __ret;
18475	__ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	17907	__ret = __noswap_vqdmlal_s16(__rev0, __rev1, (int16x4_t) {__p2, __p2, __p2, __p2});
18476	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	17908	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
18477	return __ret;	17909	return __ret;
18478	}	17910	}
18479	__ai int32x4_t __noswap_vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	17911	__ai int32x4_t __noswap_vqdmlal_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18480	int32x4_t __ret;	17912	int32x4_t __ret;
18481	__ret = (int32x4_t) __builtin_neon_vqdmlal_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	17913	__ret = __noswap_vqdmlal_s16(__p0, __p1, (int16x4_t) {__p2, __p2, __p2, __p2});
18482	return __ret;	17914	return __ret;
18483	}	17915	}
18484	#endif	17916	#endif
...	@@ -18580,7 +18012,7 @@ __ai int32x4_t __noswap_vqdmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __	...	@@ -18580,7 +18012,7 @@ __ai int32x4_t __noswap_vqdmlsl_s16(int32x4_t __p0, int16x4_t __p1, int16x4_t __
18580	#ifdef __LITTLE_ENDIAN__	18012	#ifdef __LITTLE_ENDIAN__
18581	__ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	18013	__ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18582	int64x2_t __ret;	18014	int64x2_t __ret;
18583	__ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	18015	__ret = vqdmlsl_s32(__p0, __p1, (int32x2_t) {__p2, __p2});
18584	return __ret;	18016	return __ret;
18585	}	18017	}
18586	#else	18018	#else
...	@@ -18588,13 +18020,13 @@ __ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	...	@@ -18588,13 +18020,13 @@ __ai int64x2_t vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18588	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	18020	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
18589	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);	18021	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
18590	int64x2_t __ret;	18022	int64x2_t __ret;
18591	__ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	18023	__ret = __noswap_vqdmlsl_s32(__rev0, __rev1, (int32x2_t) {__p2, __p2});
18592	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	18024	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
18593	return __ret;	18025	return __ret;
18594	}	18026	}
18595	__ai int64x2_t __noswap_vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {	18027	__ai int64x2_t __noswap_vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __p2) {
18596	int64x2_t __ret;	18028	int64x2_t __ret;
18597	__ret = (int64x2_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int32x2_t) {__p2, __p2}, 35);	18029	__ret = __noswap_vqdmlsl_s32(__p0, __p1, (int32x2_t) {__p2, __p2});
18598	return __ret;	18030	return __ret;
18599	}	18031	}
18600	#endif	18032	#endif
...	@@ -18602,7 +18034,7 @@ __ai int64x2_t __noswap_vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __	...	@@ -18602,7 +18034,7 @@ __ai int64x2_t __noswap_vqdmlsl_n_s32(int64x2_t __p0, int32x2_t __p1, int32_t __
18602	#ifdef __LITTLE_ENDIAN__	18034	#ifdef __LITTLE_ENDIAN__
18603	__ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	18035	__ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18604	int32x4_t __ret;	18036	int32x4_t __ret;
18605	__ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	18037	__ret = vqdmlsl_s16(__p0, __p1, (int16x4_t) {__p2, __p2, __p2, __p2});
18606	return __ret;	18038	return __ret;
18607	}	18039	}
18608	#else	18040	#else
...	@@ -18610,13 +18042,13 @@ __ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	...	@@ -18610,13 +18042,13 @@ __ai int32x4_t vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18610	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18042	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
18611	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);	18043	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
18612	int32x4_t __ret;	18044	int32x4_t __ret;
18613	__ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__rev0, (int8x8_t)__rev1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	18045	__ret = __noswap_vqdmlsl_s16(__rev0, __rev1, (int16x4_t) {__p2, __p2, __p2, __p2});
18614	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18046	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
18615	return __ret;	18047	return __ret;
18616	}	18048	}
18617	__ai int32x4_t __noswap_vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {	18049	__ai int32x4_t __noswap_vqdmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2) {
18618	int32x4_t __ret;	18050	int32x4_t __ret;
18619	__ret = (int32x4_t) __builtin_neon_vqdmlsl_v((int8x16_t)__p0, (int8x8_t)__p1, (int8x8_t)(int16x4_t) {__p2, __p2, __p2, __p2}, 34);	18051	__ret = __noswap_vqdmlsl_s16(__p0, __p1, (int16x4_t) {__p2, __p2, __p2, __p2});
18620	return __ret;	18052	return __ret;
18621	}	18053	}
18622	#endif	18054	#endif
...	@@ -18796,14 +18228,14 @@ __ai int16x4_t __noswap_vqdmulh_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -18796,14 +18228,14 @@ __ai int16x4_t __noswap_vqdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
18796	#ifdef __LITTLE_ENDIAN__	18228	#ifdef __LITTLE_ENDIAN__
18797	__ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	18229	__ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
18798	int32x4_t __ret;	18230	int32x4_t __ret;
18799	__ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);	18231	__ret = vqdmulhq_s32(__p0, (int32x4_t) {__p1, __p1, __p1, __p1});
18800	return __ret;	18232	return __ret;
18801	}	18233	}
18802	#else	18234	#else
18803	__ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	18235	__ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
18804	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18236	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
18805	int32x4_t __ret;	18237	int32x4_t __ret;
18806	__ret = (int32x4_t) __builtin_neon_vqdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);	18238	__ret = __noswap_vqdmulhq_s32(__rev0, (int32x4_t) {__p1, __p1, __p1, __p1});
18807	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18239	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
18808	return __ret;	18240	return __ret;
18809	}	18241	}
...	@@ -18812,14 +18244,14 @@ __ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	...	@@ -18812,14 +18244,14 @@ __ai int32x4_t vqdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
18812	#ifdef __LITTLE_ENDIAN__	18244	#ifdef __LITTLE_ENDIAN__
18813	__ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	18245	__ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
18814	int16x8_t __ret;	18246	int16x8_t __ret;
18815	__ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__p0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);	18247	__ret = vqdmulhq_s16(__p0, (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1});
18816	return __ret;	18248	return __ret;
18817	}	18249	}
18818	#else	18250	#else
18819	__ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	18251	__ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
18820	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	18252	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
18821	int16x8_t __ret;	18253	int16x8_t __ret;
18822	__ret = (int16x8_t) __builtin_neon_vqdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);	18254	__ret = __noswap_vqdmulhq_s16(__rev0, (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1});
18823	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);	18255	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);
18824	return __ret;	18256	return __ret;
18825	}	18257	}
...	@@ -18828,14 +18260,14 @@ __ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	...	@@ -18828,14 +18260,14 @@ __ai int16x8_t vqdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
18828	#ifdef __LITTLE_ENDIAN__	18260	#ifdef __LITTLE_ENDIAN__
18829	__ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	18261	__ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
18830	int32x2_t __ret;	18262	int32x2_t __ret;
18831	__ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);	18263	__ret = vqdmulh_s32(__p0, (int32x2_t) {__p1, __p1});
18832	return __ret;	18264	return __ret;
18833	}	18265	}
18834	#else	18266	#else
18835	__ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	18267	__ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
18836	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	18268	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
18837	int32x2_t __ret;	18269	int32x2_t __ret;
18838	__ret = (int32x2_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);	18270	__ret = __noswap_vqdmulh_s32(__rev0, (int32x2_t) {__p1, __p1});
18839	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	18271	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
18840	return __ret;	18272	return __ret;
18841	}	18273	}
...	@@ -18844,14 +18276,14 @@ __ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	...	@@ -18844,14 +18276,14 @@ __ai int32x2_t vqdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
18844	#ifdef __LITTLE_ENDIAN__	18276	#ifdef __LITTLE_ENDIAN__
18845	__ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {	18277	__ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
18846	int16x4_t __ret;	18278	int16x4_t __ret;
18847	__ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);	18279	__ret = vqdmulh_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
18848	return __ret;	18280	return __ret;
18849	}	18281	}
18850	#else	18282	#else
18851	__ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {	18283	__ai int16x4_t vqdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
18852	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18284	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
18853	int16x4_t __ret;	18285	int16x4_t __ret;
18854	__ret = (int16x4_t) __builtin_neon_vqdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);	18286	__ret = __noswap_vqdmulh_s16(__rev0, (int16x4_t) {__p1, __p1, __p1, __p1});
18855	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18287	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
18856	return __ret;	18288	return __ret;
18857	}	18289	}
...	@@ -18946,20 +18378,20 @@ __ai int32x4_t __noswap_vqdmull_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -18946,20 +18378,20 @@ __ai int32x4_t __noswap_vqdmull_s16(int16x4_t __p0, int16x4_t __p1) {
18946	#ifdef __LITTLE_ENDIAN__	18378	#ifdef __LITTLE_ENDIAN__
18947	__ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {	18379	__ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
18948	int64x2_t __ret;	18380	int64x2_t __ret;
18949	__ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	18381	__ret = vqdmull_s32(__p0, (int32x2_t) {__p1, __p1});
18950	return __ret;	18382	return __ret;
18951	}	18383	}
18952	#else	18384	#else
18953	__ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {	18385	__ai int64x2_t vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
18954	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	18386	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
18955	int64x2_t __ret;	18387	int64x2_t __ret;
18956	__ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	18388	__ret = __noswap_vqdmull_s32(__rev0, (int32x2_t) {__p1, __p1});
18957	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	18389	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
18958	return __ret;	18390	return __ret;
18959	}	18391	}
18960	__ai int64x2_t __noswap_vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {	18392	__ai int64x2_t __noswap_vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
18961	int64x2_t __ret;	18393	int64x2_t __ret;
18962	__ret = (int64x2_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 35);	18394	__ret = __noswap_vqdmull_s32(__p0, (int32x2_t) {__p1, __p1});
18963	return __ret;	18395	return __ret;
18964	}	18396	}
18965	#endif	18397	#endif
...	@@ -18967,20 +18399,20 @@ __ai int64x2_t __noswap_vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {	...	@@ -18967,20 +18399,20 @@ __ai int64x2_t __noswap_vqdmull_n_s32(int32x2_t __p0, int32_t __p1) {
18967	#ifdef __LITTLE_ENDIAN__	18399	#ifdef __LITTLE_ENDIAN__
18968	__ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {	18400	__ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
18969	int32x4_t __ret;	18401	int32x4_t __ret;
18970	__ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	18402	__ret = vqdmull_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
18971	return __ret;	18403	return __ret;
18972	}	18404	}
18973	#else	18405	#else
18974	__ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {	18406	__ai int32x4_t vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
18975	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18407	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
18976	int32x4_t __ret;	18408	int32x4_t __ret;
18977	__ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	18409	__ret = __noswap_vqdmull_s16(__rev0, (int16x4_t) {__p1, __p1, __p1, __p1});
18978	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18410	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
18979	return __ret;	18411	return __ret;
18980	}	18412	}
18981	__ai int32x4_t __noswap_vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {	18413	__ai int32x4_t __noswap_vqdmull_n_s16(int16x4_t __p0, int16_t __p1) {
18982	int32x4_t __ret;	18414	int32x4_t __ret;
18983	__ret = (int32x4_t) __builtin_neon_vqdmull_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 34);	18415	__ret = __noswap_vqdmull_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
18984	return __ret;	18416	return __ret;
18985	}	18417	}
18986	#endif	18418	#endif
...	@@ -19445,14 +18877,14 @@ __ai int16x4_t __noswap_vqrdmulh_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -19445,14 +18877,14 @@ __ai int16x4_t __noswap_vqrdmulh_s16(int16x4_t __p0, int16x4_t __p1) {
19445	#ifdef __LITTLE_ENDIAN__	18877	#ifdef __LITTLE_ENDIAN__
19446	__ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	18878	__ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
19447	int32x4_t __ret;	18879	int32x4_t __ret;
19448	__ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);	18880	__ret = vqrdmulhq_s32(__p0, (int32x4_t) {__p1, __p1, __p1, __p1});
19449	return __ret;	18881	return __ret;
19450	}	18882	}
19451	#else	18883	#else
19452	__ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	18884	__ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
19453	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18885	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
19454	int32x4_t __ret;	18886	int32x4_t __ret;
19455	__ret = (int32x4_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int32x4_t) {__p1, __p1, __p1, __p1}, 34);	18887	__ret = __noswap_vqrdmulhq_s32(__rev0, (int32x4_t) {__p1, __p1, __p1, __p1});
19456	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18888	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
19457	return __ret;	18889	return __ret;
19458	}	18890	}
...	@@ -19461,14 +18893,14 @@ __ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {	...	@@ -19461,14 +18893,14 @@ __ai int32x4_t vqrdmulhq_n_s32(int32x4_t __p0, int32_t __p1) {
19461	#ifdef __LITTLE_ENDIAN__	18893	#ifdef __LITTLE_ENDIAN__
19462	__ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	18894	__ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
19463	int16x8_t __ret;	18895	int16x8_t __ret;
19464	__ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__p0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);	18896	__ret = vqrdmulhq_s16(__p0, (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1});
19465	return __ret;	18897	return __ret;
19466	}	18898	}
19467	#else	18899	#else
19468	__ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	18900	__ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
19469	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	18901	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
19470	int16x8_t __ret;	18902	int16x8_t __ret;
19471	__ret = (int16x8_t) __builtin_neon_vqrdmulhq_v((int8x16_t)__rev0, (int8x16_t)(int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1}, 33);	18903	__ret = __noswap_vqrdmulhq_s16(__rev0, (int16x8_t) {__p1, __p1, __p1, __p1, __p1, __p1, __p1, __p1});
19472	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);	18904	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);
19473	return __ret;	18905	return __ret;
19474	}	18906	}
...	@@ -19477,14 +18909,14 @@ __ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {	...	@@ -19477,14 +18909,14 @@ __ai int16x8_t vqrdmulhq_n_s16(int16x8_t __p0, int16_t __p1) {
19477	#ifdef __LITTLE_ENDIAN__	18909	#ifdef __LITTLE_ENDIAN__
19478	__ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	18910	__ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
19479	int32x2_t __ret;	18911	int32x2_t __ret;
19480	__ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);	18912	__ret = vqrdmulh_s32(__p0, (int32x2_t) {__p1, __p1});
19481	return __ret;	18913	return __ret;
19482	}	18914	}
19483	#else	18915	#else
19484	__ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	18916	__ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
19485	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	18917	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
19486	int32x2_t __ret;	18918	int32x2_t __ret;
19487	__ret = (int32x2_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int32x2_t) {__p1, __p1}, 2);	18919	__ret = __noswap_vqrdmulh_s32(__rev0, (int32x2_t) {__p1, __p1});
19488	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);	18920	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
19489	return __ret;	18921	return __ret;
19490	}	18922	}
...	@@ -19493,14 +18925,14 @@ __ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {	...	@@ -19493,14 +18925,14 @@ __ai int32x2_t vqrdmulh_n_s32(int32x2_t __p0, int32_t __p1) {
19493	#ifdef __LITTLE_ENDIAN__	18925	#ifdef __LITTLE_ENDIAN__
19494	__ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {	18926	__ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
19495	int16x4_t __ret;	18927	int16x4_t __ret;
19496	__ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__p0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);	18928	__ret = vqrdmulh_s16(__p0, (int16x4_t) {__p1, __p1, __p1, __p1});
19497	return __ret;	18929	return __ret;
19498	}	18930	}
19499	#else	18931	#else
19500	__ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {	18932	__ai int16x4_t vqrdmulh_n_s16(int16x4_t __p0, int16_t __p1) {
19501	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	18933	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
19502	int16x4_t __ret;	18934	int16x4_t __ret;
19503	__ret = (int16x4_t) __builtin_neon_vqrdmulh_v((int8x8_t)__rev0, (int8x8_t)(int16x4_t) {__p1, __p1, __p1, __p1}, 1);	18935	__ret = __noswap_vqrdmulh_s16(__rev0, (int16x4_t) {__p1, __p1, __p1, __p1});
19504	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	18936	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
19505	return __ret;	18937	return __ret;
19506	}	18938	}
...	@@ -19676,20 +19108,11 @@ __ai uint32x2_t vqrshl_u32(uint32x2_t __p0, int32x2_t __p1) {	...	@@ -19676,20 +19108,11 @@ __ai uint32x2_t vqrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
19676	}	19108	}
19677	#endif	19109	#endif
19678		19110
19679	#ifdef __LITTLE_ENDIAN__
19680	__ai uint64x1_t vqrshl_u64(uint64x1_t __p0, int64x1_t __p1) {	19111	__ai uint64x1_t vqrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
19681	uint64x1_t __ret;	19112	uint64x1_t __ret;
19682	__ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	19113	__ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19683	return __ret;	19114	return __ret;
19684	}	19115	}
19685	#else
19686	__ai uint64x1_t vqrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
19687	uint64x1_t __ret;
19688	__ret = (uint64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
19689	return __ret;
19690	}
19691	#endif
19692
19693	#ifdef __LITTLE_ENDIAN__	19116	#ifdef __LITTLE_ENDIAN__
19694	__ai uint16x4_t vqrshl_u16(uint16x4_t __p0, int16x4_t __p1) {	19117	__ai uint16x4_t vqrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
19695	uint16x4_t __ret;	19118	uint16x4_t __ret;
...	@@ -19741,20 +19164,11 @@ __ai int32x2_t vqrshl_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -19741,20 +19164,11 @@ __ai int32x2_t vqrshl_s32(int32x2_t __p0, int32x2_t __p1) {
19741	}	19164	}
19742	#endif	19165	#endif
19743		19166
19744	#ifdef __LITTLE_ENDIAN__
19745	__ai int64x1_t vqrshl_s64(int64x1_t __p0, int64x1_t __p1) {	19167	__ai int64x1_t vqrshl_s64(int64x1_t __p0, int64x1_t __p1) {
19746	int64x1_t __ret;	19168	int64x1_t __ret;
19747	__ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	19169	__ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19748	return __ret;	19170	return __ret;
19749	}	19171	}
19750	#else
19751	__ai int64x1_t vqrshl_s64(int64x1_t __p0, int64x1_t __p1) {
19752	int64x1_t __ret;
19753	__ret = (int64x1_t) __builtin_neon_vqrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
19754	return __ret;
19755	}
19756	#endif
19757
19758	#ifdef __LITTLE_ENDIAN__	19172	#ifdef __LITTLE_ENDIAN__
19759	__ai int16x4_t vqrshl_s16(int16x4_t __p0, int16x4_t __p1) {	19173	__ai int16x4_t vqrshl_s16(int16x4_t __p0, int16x4_t __p1) {
19760	int16x4_t __ret;	19174	int16x4_t __ret;
...	@@ -20158,20 +19572,11 @@ __ai uint32x2_t vqshl_u32(uint32x2_t __p0, int32x2_t __p1) {	...	@@ -20158,20 +19572,11 @@ __ai uint32x2_t vqshl_u32(uint32x2_t __p0, int32x2_t __p1) {
20158	}	19572	}
20159	#endif	19573	#endif
20160		19574
20161	#ifdef __LITTLE_ENDIAN__
20162	__ai uint64x1_t vqshl_u64(uint64x1_t __p0, int64x1_t __p1) {	19575	__ai uint64x1_t vqshl_u64(uint64x1_t __p0, int64x1_t __p1) {
20163	uint64x1_t __ret;	19576	uint64x1_t __ret;
20164	__ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	19577	__ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
20165	return __ret;	19578	return __ret;
20166	}	19579	}
20167	#else
20168	__ai uint64x1_t vqshl_u64(uint64x1_t __p0, int64x1_t __p1) {
20169	uint64x1_t __ret;
20170	__ret = (uint64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
20171	return __ret;
20172	}
20173	#endif
20174
20175	#ifdef __LITTLE_ENDIAN__	19580	#ifdef __LITTLE_ENDIAN__
20176	__ai uint16x4_t vqshl_u16(uint16x4_t __p0, int16x4_t __p1) {	19581	__ai uint16x4_t vqshl_u16(uint16x4_t __p0, int16x4_t __p1) {
20177	uint16x4_t __ret;	19582	uint16x4_t __ret;
...	@@ -20223,20 +19628,11 @@ __ai int32x2_t vqshl_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -20223,20 +19628,11 @@ __ai int32x2_t vqshl_s32(int32x2_t __p0, int32x2_t __p1) {
20223	}	19628	}
20224	#endif	19629	#endif
20225		19630
20226	#ifdef __LITTLE_ENDIAN__
20227	__ai int64x1_t vqshl_s64(int64x1_t __p0, int64x1_t __p1) {
20228	int64x1_t __ret;
20229	__ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
20230	return __ret;
20231	}
20232	#else
20233	__ai int64x1_t vqshl_s64(int64x1_t __p0, int64x1_t __p1) {	19631	__ai int64x1_t vqshl_s64(int64x1_t __p0, int64x1_t __p1) {
20234	int64x1_t __ret;	19632	int64x1_t __ret;
20235	__ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	19633	__ret = (int64x1_t) __builtin_neon_vqshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
20236	return __ret;	19634	return __ret;
20237	}	19635	}
20238	#endif
20239
20240	#ifdef __LITTLE_ENDIAN__	19636	#ifdef __LITTLE_ENDIAN__
20241	__ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {	19637	__ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
20242	int16x4_t __ret;	19638	int16x4_t __ret;
...	@@ -20434,22 +19830,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -20434,22 +19830,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
20434	})	19830	})
20435	#endif	19831	#endif
20436		19832
20437	#ifdef __LITTLE_ENDIAN__
20438	#define vqshl_n_u64(__p0, __p1) __extension__ ({ \	19833	#define vqshl_n_u64(__p0, __p1) __extension__ ({ \
20439	uint64x1_t __s0 = __p0; \	19834	uint64x1_t __s0 = __p0; \
20440	uint64x1_t __ret; \	19835	uint64x1_t __ret; \
20441	__ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \	19836	__ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
20442	__ret; \	19837	__ret; \
20443	})	19838	})
20444	#else
20445	#define vqshl_n_u64(__p0, __p1) __extension__ ({ \
20446	uint64x1_t __s0 = __p0; \
20447	uint64x1_t __ret; \
20448	__ret = (uint64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 19); \
20449	__ret; \
20450	})
20451	#endif
20452
20453	#ifdef __LITTLE_ENDIAN__	19839	#ifdef __LITTLE_ENDIAN__
20454	#define vqshl_n_u16(__p0, __p1) __extension__ ({ \	19840	#define vqshl_n_u16(__p0, __p1) __extension__ ({ \
20455	uint16x4_t __s0 = __p0; \	19841	uint16x4_t __s0 = __p0; \
...	@@ -20504,22 +19890,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -20504,22 +19890,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
20504	})	19890	})
20505	#endif	19891	#endif
20506		19892
20507	#ifdef __LITTLE_ENDIAN__
20508	#define vqshl_n_s64(__p0, __p1) __extension__ ({ \
20509	int64x1_t __s0 = __p0; \
20510	int64x1_t __ret; \
20511	__ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
20512	__ret; \
20513	})
20514	#else
20515	#define vqshl_n_s64(__p0, __p1) __extension__ ({ \	19893	#define vqshl_n_s64(__p0, __p1) __extension__ ({ \
20516	int64x1_t __s0 = __p0; \	19894	int64x1_t __s0 = __p0; \
20517	int64x1_t __ret; \	19895	int64x1_t __ret; \
20518	__ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \	19896	__ret = (int64x1_t) __builtin_neon_vqshl_n_v((int8x8_t)__s0, __p1, 3); \
20519	__ret; \	19897	__ret; \
20520	})	19898	})
20521	#endif
20522
20523	#ifdef __LITTLE_ENDIAN__	19899	#ifdef __LITTLE_ENDIAN__
20524	#define vqshl_n_s16(__p0, __p1) __extension__ ({ \	19900	#define vqshl_n_s16(__p0, __p1) __extension__ ({ \
20525	int16x4_t __s0 = __p0; \	19901	int16x4_t __s0 = __p0; \
...	@@ -20646,22 +20022,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -20646,22 +20022,12 @@ __ai int16x4_t vqshl_s16(int16x4_t __p0, int16x4_t __p1) {
20646	})	20022	})
20647	#endif	20023	#endif
20648		20024
20649	#ifdef __LITTLE_ENDIAN__
20650	#define vqshlu_n_s64(__p0, __p1) __extension__ ({ \
20651	int64x1_t __s0 = __p0; \
20652	uint64x1_t __ret; \
20653	__ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
20654	__ret; \
20655	})
20656	#else
20657	#define vqshlu_n_s64(__p0, __p1) __extension__ ({ \	20025	#define vqshlu_n_s64(__p0, __p1) __extension__ ({ \
20658	int64x1_t __s0 = __p0; \	20026	int64x1_t __s0 = __p0; \
20659	uint64x1_t __ret; \	20027	uint64x1_t __ret; \
20660	__ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \	20028	__ret = (uint64x1_t) __builtin_neon_vqshlu_n_v((int8x8_t)__s0, __p1, 19); \
20661	__ret; \	20029	__ret; \
20662	})	20030	})
20663	#endif
20664
20665	#ifdef __LITTLE_ENDIAN__	20031	#ifdef __LITTLE_ENDIAN__
20666	#define vqshlu_n_s16(__p0, __p1) __extension__ ({ \	20032	#define vqshlu_n_s16(__p0, __p1) __extension__ ({ \
20667	int16x4_t __s0 = __p0; \	20033	int16x4_t __s0 = __p0; \
...	@@ -21076,20 +20442,11 @@ __ai uint32x2_t vqsub_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -21076,20 +20442,11 @@ __ai uint32x2_t vqsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
21076	}	20442	}
21077	#endif	20443	#endif
21078		20444
21079	#ifdef __LITTLE_ENDIAN__
21080	__ai uint64x1_t vqsub_u64(uint64x1_t __p0, uint64x1_t __p1) {	20445	__ai uint64x1_t vqsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
21081	uint64x1_t __ret;	20446	uint64x1_t __ret;
21082	__ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	20447	__ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21083	return __ret;	20448	return __ret;
21084	}	20449	}
21085	#else
21086	__ai uint64x1_t vqsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
21087	uint64x1_t __ret;
21088	__ret = (uint64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
21089	return __ret;
21090	}
21091	#endif
21092
21093	#ifdef __LITTLE_ENDIAN__	20450	#ifdef __LITTLE_ENDIAN__
21094	__ai uint16x4_t vqsub_u16(uint16x4_t __p0, uint16x4_t __p1) {	20451	__ai uint16x4_t vqsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
21095	uint16x4_t __ret;	20452	uint16x4_t __ret;
...	@@ -21146,20 +20503,11 @@ __ai int32x2_t __noswap_vqsub_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -21146,20 +20503,11 @@ __ai int32x2_t __noswap_vqsub_s32(int32x2_t __p0, int32x2_t __p1) {
21146	}	20503	}
21147	#endif	20504	#endif
21148		20505
21149	#ifdef __LITTLE_ENDIAN__
21150	__ai int64x1_t vqsub_s64(int64x1_t __p0, int64x1_t __p1) {
21151	int64x1_t __ret;
21152	__ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21153	return __ret;
21154	}
21155	#else
21156	__ai int64x1_t vqsub_s64(int64x1_t __p0, int64x1_t __p1) {	20506	__ai int64x1_t vqsub_s64(int64x1_t __p0, int64x1_t __p1) {
21157	int64x1_t __ret;	20507	int64x1_t __ret;
21158	__ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	20508	__ret = (int64x1_t) __builtin_neon_vqsub_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
21159	return __ret;	20509	return __ret;
21160	}	20510	}
21161	#endif
21162
21163	#ifdef __LITTLE_ENDIAN__	20511	#ifdef __LITTLE_ENDIAN__
21164	__ai int16x4_t vqsub_s16(int16x4_t __p0, int16x4_t __p1) {	20512	__ai int16x4_t vqsub_s16(int16x4_t __p0, int16x4_t __p1) {
21165	int16x4_t __ret;	20513	int16x4_t __ret;
...	@@ -22362,20 +21710,11 @@ __ai uint32x2_t vrshl_u32(uint32x2_t __p0, int32x2_t __p1) {	...	@@ -22362,20 +21710,11 @@ __ai uint32x2_t vrshl_u32(uint32x2_t __p0, int32x2_t __p1) {
22362	}	21710	}
22363	#endif	21711	#endif
22364		21712
22365	#ifdef __LITTLE_ENDIAN__
22366	__ai uint64x1_t vrshl_u64(uint64x1_t __p0, int64x1_t __p1) {	21713	__ai uint64x1_t vrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
22367	uint64x1_t __ret;	21714	uint64x1_t __ret;
22368	__ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	21715	__ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22369	return __ret;	21716	return __ret;
22370	}	21717	}
22371	#else
22372	__ai uint64x1_t vrshl_u64(uint64x1_t __p0, int64x1_t __p1) {
22373	uint64x1_t __ret;
22374	__ret = (uint64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
22375	return __ret;
22376	}
22377	#endif
22378
22379	#ifdef __LITTLE_ENDIAN__	21718	#ifdef __LITTLE_ENDIAN__
22380	__ai uint16x4_t vrshl_u16(uint16x4_t __p0, int16x4_t __p1) {	21719	__ai uint16x4_t vrshl_u16(uint16x4_t __p0, int16x4_t __p1) {
22381	uint16x4_t __ret;	21720	uint16x4_t __ret;
...	@@ -22427,20 +21766,11 @@ __ai int32x2_t vrshl_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -22427,20 +21766,11 @@ __ai int32x2_t vrshl_s32(int32x2_t __p0, int32x2_t __p1) {
22427	}	21766	}
22428	#endif	21767	#endif
22429		21768
22430	#ifdef __LITTLE_ENDIAN__
22431	__ai int64x1_t vrshl_s64(int64x1_t __p0, int64x1_t __p1) {
22432	int64x1_t __ret;
22433	__ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
22434	return __ret;
22435	}
22436	#else
22437	__ai int64x1_t vrshl_s64(int64x1_t __p0, int64x1_t __p1) {	21769	__ai int64x1_t vrshl_s64(int64x1_t __p0, int64x1_t __p1) {
22438	int64x1_t __ret;	21770	int64x1_t __ret;
22439	__ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	21771	__ret = (int64x1_t) __builtin_neon_vrshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
22440	return __ret;	21772	return __ret;
22441	}	21773	}
22442	#endif
22443
22444	#ifdef __LITTLE_ENDIAN__	21774	#ifdef __LITTLE_ENDIAN__
22445	__ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {	21775	__ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {
22446	int16x4_t __ret;	21776	int16x4_t __ret;
...	@@ -22638,22 +21968,12 @@ __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -22638,22 +21968,12 @@ __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {
22638	})	21968	})
22639	#endif	21969	#endif
22640		21970
22641	#ifdef __LITTLE_ENDIAN__
22642	#define vrshr_n_u64(__p0, __p1) __extension__ ({ \
22643	uint64x1_t __s0 = __p0; \
22644	uint64x1_t __ret; \
22645	__ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
22646	__ret; \
22647	})
22648	#else
22649	#define vrshr_n_u64(__p0, __p1) __extension__ ({ \	21971	#define vrshr_n_u64(__p0, __p1) __extension__ ({ \
22650	uint64x1_t __s0 = __p0; \	21972	uint64x1_t __s0 = __p0; \
22651	uint64x1_t __ret; \	21973	uint64x1_t __ret; \
22652	__ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \	21974	__ret = (uint64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 19); \
22653	__ret; \	21975	__ret; \
22654	})	21976	})
22655	#endif
22656
22657	#ifdef __LITTLE_ENDIAN__	21977	#ifdef __LITTLE_ENDIAN__
22658	#define vrshr_n_u16(__p0, __p1) __extension__ ({ \	21978	#define vrshr_n_u16(__p0, __p1) __extension__ ({ \
22659	uint16x4_t __s0 = __p0; \	21979	uint16x4_t __s0 = __p0; \
...	@@ -22708,22 +22028,12 @@ __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -22708,22 +22028,12 @@ __ai int16x4_t vrshl_s16(int16x4_t __p0, int16x4_t __p1) {
22708	})	22028	})
22709	#endif	22029	#endif
22710		22030
22711	#ifdef __LITTLE_ENDIAN__
22712	#define vrshr_n_s64(__p0, __p1) __extension__ ({ \
22713	int64x1_t __s0 = __p0; \
22714	int64x1_t __ret; \
22715	__ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
22716	__ret; \
22717	})
22718	#else
22719	#define vrshr_n_s64(__p0, __p1) __extension__ ({ \	22031	#define vrshr_n_s64(__p0, __p1) __extension__ ({ \
22720	int64x1_t __s0 = __p0; \	22032	int64x1_t __s0 = __p0; \
22721	int64x1_t __ret; \	22033	int64x1_t __ret; \
22722	__ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \	22034	__ret = (int64x1_t) __builtin_neon_vrshr_n_v((int8x8_t)__s0, __p1, 3); \
22723	__ret; \	22035	__ret; \
22724	})	22036	})
22725	#endif
22726
22727	#ifdef __LITTLE_ENDIAN__	22037	#ifdef __LITTLE_ENDIAN__
22728	#define vrshr_n_s16(__p0, __p1) __extension__ ({ \	22038	#define vrshr_n_s16(__p0, __p1) __extension__ ({ \
22729	int16x4_t __s0 = __p0; \	22039	int16x4_t __s0 = __p0; \
...	@@ -23194,15 +22504,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -23194,15 +22504,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
23194	})	22504	})
23195	#endif	22505	#endif
23196		22506
23197	#ifdef __LITTLE_ENDIAN__
23198	#define vrsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
23199	uint64x1_t __s0 = __p0; \
23200	uint64x1_t __s1 = __p1; \
23201	uint64x1_t __ret; \
23202	__ret = (uint64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
23203	__ret; \
23204	})
23205	#else
23206	#define vrsra_n_u64(__p0, __p1, __p2) __extension__ ({ \	22507	#define vrsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
23207	uint64x1_t __s0 = __p0; \	22508	uint64x1_t __s0 = __p0; \
23208	uint64x1_t __s1 = __p1; \	22509	uint64x1_t __s1 = __p1; \
...	@@ -23210,8 +22511,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -23210,8 +22511,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
23210	__ret = (uint64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \	22511	__ret = (uint64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
23211	__ret; \	22512	__ret; \
23212	})	22513	})
23213	#endif
23214
23215	#ifdef __LITTLE_ENDIAN__	22514	#ifdef __LITTLE_ENDIAN__
23216	#define vrsra_n_u16(__p0, __p1, __p2) __extension__ ({ \	22515	#define vrsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
23217	uint16x4_t __s0 = __p0; \	22516	uint16x4_t __s0 = __p0; \
...	@@ -23275,15 +22574,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -23275,15 +22574,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
23275	})	22574	})
23276	#endif	22575	#endif
23277		22576
23278	#ifdef __LITTLE_ENDIAN__
23279	#define vrsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
23280	int64x1_t __s0 = __p0; \
23281	int64x1_t __s1 = __p1; \
23282	int64x1_t __ret; \
23283	__ret = (int64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
23284	__ret; \
23285	})
23286	#else
23287	#define vrsra_n_s64(__p0, __p1, __p2) __extension__ ({ \	22577	#define vrsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
23288	int64x1_t __s0 = __p0; \	22578	int64x1_t __s0 = __p0; \
23289	int64x1_t __s1 = __p1; \	22579	int64x1_t __s1 = __p1; \
...	@@ -23291,8 +22581,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -23291,8 +22581,6 @@ __ai float32x2_t vrsqrts_f32(float32x2_t __p0, float32x2_t __p1) {
23291	__ret = (int64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \	22581	__ret = (int64x1_t) __builtin_neon_vrsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
23292	__ret; \	22582	__ret; \
23293	})	22583	})
23294	#endif
23295
23296	#ifdef __LITTLE_ENDIAN__	22584	#ifdef __LITTLE_ENDIAN__
23297	#define vrsra_n_s16(__p0, __p1, __p2) __extension__ ({ \	22585	#define vrsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
23298	int16x4_t __s0 = __p0; \	22586	int16x4_t __s0 = __p0; \
...	@@ -23451,7 +22739,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23451,7 +22739,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23451	poly8_t __s0 = __p0; \	22739	poly8_t __s0 = __p0; \
23452	poly8x8_t __s1 = __p1; \	22740	poly8x8_t __s1 = __p1; \
23453	poly8x8_t __ret; \	22741	poly8x8_t __ret; \
23454	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \	22742	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (poly8x8_t)__s1, __p2); \
23455	__ret; \	22743	__ret; \
23456	})	22744	})
23457	#else	22745	#else
...	@@ -23460,7 +22748,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23460,7 +22748,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23460	poly8x8_t __s1 = __p1; \	22748	poly8x8_t __s1 = __p1; \
23461	poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \	22749	poly8x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
23462	poly8x8_t __ret; \	22750	poly8x8_t __ret; \
23463	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__rev1, __p2); \	22751	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (poly8x8_t)__rev1, __p2); \
23464	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \	22752	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \
23465	__ret; \	22753	__ret; \
23466	})	22754	})
...	@@ -23468,7 +22756,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23468,7 +22756,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23468	poly8_t __s0 = __p0; \	22756	poly8_t __s0 = __p0; \
23469	poly8x8_t __s1 = __p1; \	22757	poly8x8_t __s1 = __p1; \
23470	poly8x8_t __ret; \	22758	poly8x8_t __ret; \
23471	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (int8x8_t)__s1, __p2); \	22759	__ret = (poly8x8_t) __builtin_neon_vset_lane_i8(__s0, (poly8x8_t)__s1, __p2); \
23472	__ret; \	22760	__ret; \
23473	})	22761	})
23474	#endif	22762	#endif
...	@@ -23478,7 +22766,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23478,7 +22766,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23478	poly16_t __s0 = __p0; \	22766	poly16_t __s0 = __p0; \
23479	poly16x4_t __s1 = __p1; \	22767	poly16x4_t __s1 = __p1; \
23480	poly16x4_t __ret; \	22768	poly16x4_t __ret; \
23481	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	22769	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (poly16x4_t)__s1, __p2); \
23482	__ret; \	22770	__ret; \
23483	})	22771	})
23484	#else	22772	#else
...	@@ -23487,7 +22775,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23487,7 +22775,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23487	poly16x4_t __s1 = __p1; \	22775	poly16x4_t __s1 = __p1; \
23488	poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	22776	poly16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
23489	poly16x4_t __ret; \	22777	poly16x4_t __ret; \
23490	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \	22778	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (poly16x4_t)__rev1, __p2); \
23491	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	22779	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
23492	__ret; \	22780	__ret; \
23493	})	22781	})
...	@@ -23495,7 +22783,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23495,7 +22783,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23495	poly16_t __s0 = __p0; \	22783	poly16_t __s0 = __p0; \
23496	poly16x4_t __s1 = __p1; \	22784	poly16x4_t __s1 = __p1; \
23497	poly16x4_t __ret; \	22785	poly16x4_t __ret; \
23498	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	22786	__ret = (poly16x4_t) __builtin_neon_vset_lane_i16(__s0, (poly16x4_t)__s1, __p2); \
23499	__ret; \	22787	__ret; \
23500	})	22788	})
23501	#endif	22789	#endif
...	@@ -23505,7 +22793,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23505,7 +22793,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23505	poly8_t __s0 = __p0; \	22793	poly8_t __s0 = __p0; \
23506	poly8x16_t __s1 = __p1; \	22794	poly8x16_t __s1 = __p1; \
23507	poly8x16_t __ret; \	22795	poly8x16_t __ret; \
23508	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (int8x16_t)__s1, __p2); \	22796	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (poly8x16_t)__s1, __p2); \
23509	__ret; \	22797	__ret; \
23510	})	22798	})
23511	#else	22799	#else
...	@@ -23514,7 +22802,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23514,7 +22802,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23514	poly8x16_t __s1 = __p1; \	22802	poly8x16_t __s1 = __p1; \
23515	poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	22803	poly8x16_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
23516	poly8x16_t __ret; \	22804	poly8x16_t __ret; \
23517	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (int8x16_t)__rev1, __p2); \	22805	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (poly8x16_t)__rev1, __p2); \
23518	__ret = __builtin_shufflevector(__ret, __ret, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	22806	__ret = __builtin_shufflevector(__ret, __ret, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
23519	__ret; \	22807	__ret; \
23520	})	22808	})
...	@@ -23522,7 +22810,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23522,7 +22810,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23522	poly8_t __s0 = __p0; \	22810	poly8_t __s0 = __p0; \
23523	poly8x16_t __s1 = __p1; \	22811	poly8x16_t __s1 = __p1; \
23524	poly8x16_t __ret; \	22812	poly8x16_t __ret; \
23525	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (int8x16_t)__s1, __p2); \	22813	__ret = (poly8x16_t) __builtin_neon_vsetq_lane_i8(__s0, (poly8x16_t)__s1, __p2); \
23526	__ret; \	22814	__ret; \
23527	})	22815	})
23528	#endif	22816	#endif
...	@@ -23532,7 +22820,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23532,7 +22820,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23532	poly16_t __s0 = __p0; \	22820	poly16_t __s0 = __p0; \
23533	poly16x8_t __s1 = __p1; \	22821	poly16x8_t __s1 = __p1; \
23534	poly16x8_t __ret; \	22822	poly16x8_t __ret; \
23535	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	22823	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (poly16x8_t)__s1, __p2); \
23536	__ret; \	22824	__ret; \
23537	})	22825	})
23538	#else	22826	#else
...	@@ -23541,7 +22829,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23541,7 +22829,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23541	poly16x8_t __s1 = __p1; \	22829	poly16x8_t __s1 = __p1; \
23542	poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \	22830	poly16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
23543	poly16x8_t __ret; \	22831	poly16x8_t __ret; \
23544	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__rev1, __p2); \	22832	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (poly16x8_t)__rev1, __p2); \
23545	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \	22833	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \
23546	__ret; \	22834	__ret; \
23547	})	22835	})
...	@@ -23549,7 +22837,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23549,7 +22837,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23549	poly16_t __s0 = __p0; \	22837	poly16_t __s0 = __p0; \
23550	poly16x8_t __s1 = __p1; \	22838	poly16x8_t __s1 = __p1; \
23551	poly16x8_t __ret; \	22839	poly16x8_t __ret; \
23552	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	22840	__ret = (poly16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (poly16x8_t)__s1, __p2); \
23553	__ret; \	22841	__ret; \
23554	})	22842	})
23555	#endif	22843	#endif
...	@@ -23586,7 +22874,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23586,7 +22874,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23586	uint32_t __s0 = __p0; \	22874	uint32_t __s0 = __p0; \
23587	uint32x4_t __s1 = __p1; \	22875	uint32x4_t __s1 = __p1; \
23588	uint32x4_t __ret; \	22876	uint32x4_t __ret; \
23589	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__s1, __p2); \	22877	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__s1, __p2); \
23590	__ret; \	22878	__ret; \
23591	})	22879	})
23592	#else	22880	#else
...	@@ -23595,7 +22883,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23595,7 +22883,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23595	uint32x4_t __s1 = __p1; \	22883	uint32x4_t __s1 = __p1; \
23596	uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	22884	uint32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
23597	uint32x4_t __ret; \	22885	uint32x4_t __ret; \
23598	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__rev1, __p2); \	22886	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__rev1, __p2); \
23599	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	22887	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
23600	__ret; \	22888	__ret; \
23601	})	22889	})
...	@@ -23603,7 +22891,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23603,7 +22891,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23603	uint32_t __s0 = __p0; \	22891	uint32_t __s0 = __p0; \
23604	uint32x4_t __s1 = __p1; \	22892	uint32x4_t __s1 = __p1; \
23605	uint32x4_t __ret; \	22893	uint32x4_t __ret; \
23606	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__s1, __p2); \	22894	__ret = (uint32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__s1, __p2); \
23607	__ret; \	22895	__ret; \
23608	})	22896	})
23609	#endif	22897	#endif
...	@@ -23613,7 +22901,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23613,7 +22901,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23613	uint64_t __s0 = __p0; \	22901	uint64_t __s0 = __p0; \
23614	uint64x2_t __s1 = __p1; \	22902	uint64x2_t __s1 = __p1; \
23615	uint64x2_t __ret; \	22903	uint64x2_t __ret; \
23616	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	22904	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__s1, __p2); \
23617	__ret; \	22905	__ret; \
23618	})	22906	})
23619	#else	22907	#else
...	@@ -23622,7 +22910,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23622,7 +22910,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23622	uint64x2_t __s1 = __p1; \	22910	uint64x2_t __s1 = __p1; \
23623	uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	22911	uint64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
23624	uint64x2_t __ret; \	22912	uint64x2_t __ret; \
23625	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__rev1, __p2); \	22913	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__rev1, __p2); \
23626	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	22914	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
23627	__ret; \	22915	__ret; \
23628	})	22916	})
...	@@ -23630,7 +22918,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23630,7 +22918,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23630	uint64_t __s0 = __p0; \	22918	uint64_t __s0 = __p0; \
23631	uint64x2_t __s1 = __p1; \	22919	uint64x2_t __s1 = __p1; \
23632	uint64x2_t __ret; \	22920	uint64x2_t __ret; \
23633	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	22921	__ret = (uint64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__s1, __p2); \
23634	__ret; \	22922	__ret; \
23635	})	22923	})
23636	#endif	22924	#endif
...	@@ -23640,7 +22928,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23640,7 +22928,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23640	uint16_t __s0 = __p0; \	22928	uint16_t __s0 = __p0; \
23641	uint16x8_t __s1 = __p1; \	22929	uint16x8_t __s1 = __p1; \
23642	uint16x8_t __ret; \	22930	uint16x8_t __ret; \
23643	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	22931	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__s1, __p2); \
23644	__ret; \	22932	__ret; \
23645	})	22933	})
23646	#else	22934	#else
...	@@ -23649,7 +22937,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23649,7 +22937,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23649	uint16x8_t __s1 = __p1; \	22937	uint16x8_t __s1 = __p1; \
23650	uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \	22938	uint16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
23651	uint16x8_t __ret; \	22939	uint16x8_t __ret; \
23652	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__rev1, __p2); \	22940	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__rev1, __p2); \
23653	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \	22941	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \
23654	__ret; \	22942	__ret; \
23655	})	22943	})
...	@@ -23657,7 +22945,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23657,7 +22945,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23657	uint16_t __s0 = __p0; \	22945	uint16_t __s0 = __p0; \
23658	uint16x8_t __s1 = __p1; \	22946	uint16x8_t __s1 = __p1; \
23659	uint16x8_t __ret; \	22947	uint16x8_t __ret; \
23660	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	22948	__ret = (uint16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__s1, __p2); \
23661	__ret; \	22949	__ret; \
23662	})	22950	})
23663	#endif	22951	#endif
...	@@ -23694,7 +22982,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23694,7 +22982,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23694	float32_t __s0 = __p0; \	22982	float32_t __s0 = __p0; \
23695	float32x4_t __s1 = __p1; \	22983	float32x4_t __s1 = __p1; \
23696	float32x4_t __ret; \	22984	float32x4_t __ret; \
23697	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (int8x16_t)__s1, __p2); \	22985	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (float32x4_t)__s1, __p2); \
23698	__ret; \	22986	__ret; \
23699	})	22987	})
23700	#else	22988	#else
...	@@ -23703,7 +22991,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23703,7 +22991,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23703	float32x4_t __s1 = __p1; \	22991	float32x4_t __s1 = __p1; \
23704	float32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	22992	float32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
23705	float32x4_t __ret; \	22993	float32x4_t __ret; \
23706	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (int8x16_t)__rev1, __p2); \	22994	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (float32x4_t)__rev1, __p2); \
23707	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	22995	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
23708	__ret; \	22996	__ret; \
23709	})	22997	})
...	@@ -23711,7 +22999,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23711,7 +22999,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23711	float32_t __s0 = __p0; \	22999	float32_t __s0 = __p0; \
23712	float32x4_t __s1 = __p1; \	23000	float32x4_t __s1 = __p1; \
23713	float32x4_t __ret; \	23001	float32x4_t __ret; \
23714	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (int8x16_t)__s1, __p2); \	23002	__ret = (float32x4_t) __builtin_neon_vsetq_lane_f32(__s0, (float32x4_t)__s1, __p2); \
23715	__ret; \	23003	__ret; \
23716	})	23004	})
23717	#endif	23005	#endif
...	@@ -23721,7 +23009,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23721,7 +23009,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23721	int32_t __s0 = __p0; \	23009	int32_t __s0 = __p0; \
23722	int32x4_t __s1 = __p1; \	23010	int32x4_t __s1 = __p1; \
23723	int32x4_t __ret; \	23011	int32x4_t __ret; \
23724	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__s1, __p2); \	23012	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__s1, __p2); \
23725	__ret; \	23013	__ret; \
23726	})	23014	})
23727	#else	23015	#else
...	@@ -23730,7 +23018,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23730,7 +23018,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23730	int32x4_t __s1 = __p1; \	23018	int32x4_t __s1 = __p1; \
23731	int32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	23019	int32x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
23732	int32x4_t __ret; \	23020	int32x4_t __ret; \
23733	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__rev1, __p2); \	23021	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__rev1, __p2); \
23734	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	23022	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
23735	__ret; \	23023	__ret; \
23736	})	23024	})
...	@@ -23738,7 +23026,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23738,7 +23026,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23738	int32_t __s0 = __p0; \	23026	int32_t __s0 = __p0; \
23739	int32x4_t __s1 = __p1; \	23027	int32x4_t __s1 = __p1; \
23740	int32x4_t __ret; \	23028	int32x4_t __ret; \
23741	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int8x16_t)__s1, __p2); \	23029	__ret = (int32x4_t) __builtin_neon_vsetq_lane_i32(__s0, (int32x4_t)__s1, __p2); \
23742	__ret; \	23030	__ret; \
23743	})	23031	})
23744	#endif	23032	#endif
...	@@ -23748,7 +23036,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23748,7 +23036,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23748	int64_t __s0 = __p0; \	23036	int64_t __s0 = __p0; \
23749	int64x2_t __s1 = __p1; \	23037	int64x2_t __s1 = __p1; \
23750	int64x2_t __ret; \	23038	int64x2_t __ret; \
23751	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	23039	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__s1, __p2); \
23752	__ret; \	23040	__ret; \
23753	})	23041	})
23754	#else	23042	#else
...	@@ -23757,7 +23045,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23757,7 +23045,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23757	int64x2_t __s1 = __p1; \	23045	int64x2_t __s1 = __p1; \
23758	int64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	23046	int64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
23759	int64x2_t __ret; \	23047	int64x2_t __ret; \
23760	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__rev1, __p2); \	23048	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__rev1, __p2); \
23761	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	23049	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
23762	__ret; \	23050	__ret; \
23763	})	23051	})
...	@@ -23765,7 +23053,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23765,7 +23053,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23765	int64_t __s0 = __p0; \	23053	int64_t __s0 = __p0; \
23766	int64x2_t __s1 = __p1; \	23054	int64x2_t __s1 = __p1; \
23767	int64x2_t __ret; \	23055	int64x2_t __ret; \
23768	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	23056	__ret = (int64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int64x2_t)__s1, __p2); \
23769	__ret; \	23057	__ret; \
23770	})	23058	})
23771	#endif	23059	#endif
...	@@ -23775,7 +23063,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23775,7 +23063,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23775	int16_t __s0 = __p0; \	23063	int16_t __s0 = __p0; \
23776	int16x8_t __s1 = __p1; \	23064	int16x8_t __s1 = __p1; \
23777	int16x8_t __ret; \	23065	int16x8_t __ret; \
23778	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	23066	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__s1, __p2); \
23779	__ret; \	23067	__ret; \
23780	})	23068	})
23781	#else	23069	#else
...	@@ -23784,7 +23072,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23784,7 +23072,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23784	int16x8_t __s1 = __p1; \	23072	int16x8_t __s1 = __p1; \
23785	int16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \	23073	int16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
23786	int16x8_t __ret; \	23074	int16x8_t __ret; \
23787	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__rev1, __p2); \	23075	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__rev1, __p2); \
23788	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \	23076	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0); \
23789	__ret; \	23077	__ret; \
23790	})	23078	})
...	@@ -23792,7 +23080,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23792,7 +23080,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23792	int16_t __s0 = __p0; \	23080	int16_t __s0 = __p0; \
23793	int16x8_t __s1 = __p1; \	23081	int16x8_t __s1 = __p1; \
23794	int16x8_t __ret; \	23082	int16x8_t __ret; \
23795	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int8x16_t)__s1, __p2); \	23083	__ret = (int16x8_t) __builtin_neon_vsetq_lane_i16(__s0, (int16x8_t)__s1, __p2); \
23796	__ret; \	23084	__ret; \
23797	})	23085	})
23798	#endif	23086	#endif
...	@@ -23829,7 +23117,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23829,7 +23117,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23829	uint32_t __s0 = __p0; \	23117	uint32_t __s0 = __p0; \
23830	uint32x2_t __s1 = __p1; \	23118	uint32x2_t __s1 = __p1; \
23831	uint32x2_t __ret; \	23119	uint32x2_t __ret; \
23832	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \	23120	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__s1, __p2); \
23833	__ret; \	23121	__ret; \
23834	})	23122	})
23835	#else	23123	#else
...	@@ -23838,7 +23126,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23838,7 +23126,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23838	uint32x2_t __s1 = __p1; \	23126	uint32x2_t __s1 = __p1; \
23839	uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	23127	uint32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
23840	uint32x2_t __ret; \	23128	uint32x2_t __ret; \
23841	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__rev1, __p2); \	23129	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__rev1, __p2); \
23842	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	23130	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
23843	__ret; \	23131	__ret; \
23844	})	23132	})
...	@@ -23846,42 +23134,24 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23846,42 +23134,24 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23846	uint32_t __s0 = __p0; \	23134	uint32_t __s0 = __p0; \
23847	uint32x2_t __s1 = __p1; \	23135	uint32x2_t __s1 = __p1; \
23848	uint32x2_t __ret; \	23136	uint32x2_t __ret; \
23849	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \	23137	__ret = (uint32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__s1, __p2); \
23850	__ret; \	23138	__ret; \
23851	})	23139	})
23852	#endif	23140	#endif
23853		23141
23854	#ifdef __LITTLE_ENDIAN__
23855	#define vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \	23142	#define vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
23856	uint64_t __s0 = __p0; \	23143	uint64_t __s0 = __p0; \
23857	uint64x1_t __s1 = __p1; \	23144	uint64x1_t __s1 = __p1; \
23858	uint64x1_t __ret; \	23145	uint64x1_t __ret; \
23859	__ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \	23146	__ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int64x1_t)__s1, __p2); \
23860	__ret; \	23147	__ret; \
23861	})	23148	})
23862	#else
23863	#define vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
23864	uint64_t __s0 = __p0; \
23865	uint64x1_t __s1 = __p1; \
23866	uint64x1_t __ret; \
23867	__ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
23868	__ret; \
23869	})
23870	#define __noswap_vset_lane_u64(__p0, __p1, __p2) __extension__ ({ \
23871	uint64_t __s0 = __p0; \
23872	uint64x1_t __s1 = __p1; \
23873	uint64x1_t __ret; \
23874	__ret = (uint64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
23875	__ret; \
23876	})
23877	#endif
23878
23879	#ifdef __LITTLE_ENDIAN__	23149	#ifdef __LITTLE_ENDIAN__
23880	#define vset_lane_u16(__p0, __p1, __p2) __extension__ ({ \	23150	#define vset_lane_u16(__p0, __p1, __p2) __extension__ ({ \
23881	uint16_t __s0 = __p0; \	23151	uint16_t __s0 = __p0; \
23882	uint16x4_t __s1 = __p1; \	23152	uint16x4_t __s1 = __p1; \
23883	uint16x4_t __ret; \	23153	uint16x4_t __ret; \
23884	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	23154	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__s1, __p2); \
23885	__ret; \	23155	__ret; \
23886	})	23156	})
23887	#else	23157	#else
...	@@ -23890,7 +23160,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23890,7 +23160,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23890	uint16x4_t __s1 = __p1; \	23160	uint16x4_t __s1 = __p1; \
23891	uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	23161	uint16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
23892	uint16x4_t __ret; \	23162	uint16x4_t __ret; \
23893	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \	23163	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__rev1, __p2); \
23894	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	23164	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
23895	__ret; \	23165	__ret; \
23896	})	23166	})
...	@@ -23898,7 +23168,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23898,7 +23168,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23898	uint16_t __s0 = __p0; \	23168	uint16_t __s0 = __p0; \
23899	uint16x4_t __s1 = __p1; \	23169	uint16x4_t __s1 = __p1; \
23900	uint16x4_t __ret; \	23170	uint16x4_t __ret; \
23901	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	23171	__ret = (uint16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__s1, __p2); \
23902	__ret; \	23172	__ret; \
23903	})	23173	})
23904	#endif	23174	#endif
...	@@ -23935,7 +23205,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23935,7 +23205,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23935	float32_t __s0 = __p0; \	23205	float32_t __s0 = __p0; \
23936	float32x2_t __s1 = __p1; \	23206	float32x2_t __s1 = __p1; \
23937	float32x2_t __ret; \	23207	float32x2_t __ret; \
23938	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__s1, __p2); \	23208	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (float32x2_t)__s1, __p2); \
23939	__ret; \	23209	__ret; \
23940	})	23210	})
23941	#else	23211	#else
...	@@ -23944,7 +23214,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23944,7 +23214,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23944	float32x2_t __s1 = __p1; \	23214	float32x2_t __s1 = __p1; \
23945	float32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	23215	float32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
23946	float32x2_t __ret; \	23216	float32x2_t __ret; \
23947	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__rev1, __p2); \	23217	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (float32x2_t)__rev1, __p2); \
23948	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	23218	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
23949	__ret; \	23219	__ret; \
23950	})	23220	})
...	@@ -23952,7 +23222,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23952,7 +23222,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23952	float32_t __s0 = __p0; \	23222	float32_t __s0 = __p0; \
23953	float32x2_t __s1 = __p1; \	23223	float32x2_t __s1 = __p1; \
23954	float32x2_t __ret; \	23224	float32x2_t __ret; \
23955	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (int8x8_t)__s1, __p2); \	23225	__ret = (float32x2_t) __builtin_neon_vset_lane_f32(__s0, (float32x2_t)__s1, __p2); \
23956	__ret; \	23226	__ret; \
23957	})	23227	})
23958	#endif	23228	#endif
...	@@ -23962,7 +23232,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23962,7 +23232,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23962	int32_t __s0 = __p0; \	23232	int32_t __s0 = __p0; \
23963	int32x2_t __s1 = __p1; \	23233	int32x2_t __s1 = __p1; \
23964	int32x2_t __ret; \	23234	int32x2_t __ret; \
23965	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \	23235	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__s1, __p2); \
23966	__ret; \	23236	__ret; \
23967	})	23237	})
23968	#else	23238	#else
...	@@ -23971,7 +23241,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23971,7 +23241,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23971	int32x2_t __s1 = __p1; \	23241	int32x2_t __s1 = __p1; \
23972	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	23242	int32x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
23973	int32x2_t __ret; \	23243	int32x2_t __ret; \
23974	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__rev1, __p2); \	23244	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__rev1, __p2); \
23975	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	23245	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
23976	__ret; \	23246	__ret; \
23977	})	23247	})
...	@@ -23979,42 +23249,24 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -23979,42 +23249,24 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
23979	int32_t __s0 = __p0; \	23249	int32_t __s0 = __p0; \
23980	int32x2_t __s1 = __p1; \	23250	int32x2_t __s1 = __p1; \
23981	int32x2_t __ret; \	23251	int32x2_t __ret; \
23982	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int8x8_t)__s1, __p2); \	23252	__ret = (int32x2_t) __builtin_neon_vset_lane_i32(__s0, (int32x2_t)__s1, __p2); \
23983	__ret; \	23253	__ret; \
23984	})	23254	})
23985	#endif	23255	#endif
23986		23256
23987	#ifdef __LITTLE_ENDIAN__
23988	#define vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \	23257	#define vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
23989	int64_t __s0 = __p0; \	23258	int64_t __s0 = __p0; \
23990	int64x1_t __s1 = __p1; \	23259	int64x1_t __s1 = __p1; \
23991	int64x1_t __ret; \	23260	int64x1_t __ret; \
23992	__ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \	23261	__ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int64x1_t)__s1, __p2); \
23993	__ret; \	23262	__ret; \
23994	})	23263	})
23995	#else
23996	#define vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
23997	int64_t __s0 = __p0; \
23998	int64x1_t __s1 = __p1; \
23999	int64x1_t __ret; \
24000	__ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
24001	__ret; \
24002	})
24003	#define __noswap_vset_lane_s64(__p0, __p1, __p2) __extension__ ({ \
24004	int64_t __s0 = __p0; \
24005	int64x1_t __s1 = __p1; \
24006	int64x1_t __ret; \
24007	__ret = (int64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
24008	__ret; \
24009	})
24010	#endif
24011
24012	#ifdef __LITTLE_ENDIAN__	23264	#ifdef __LITTLE_ENDIAN__
24013	#define vset_lane_s16(__p0, __p1, __p2) __extension__ ({ \	23265	#define vset_lane_s16(__p0, __p1, __p2) __extension__ ({ \
24014	int16_t __s0 = __p0; \	23266	int16_t __s0 = __p0; \
24015	int16x4_t __s1 = __p1; \	23267	int16x4_t __s1 = __p1; \
24016	int16x4_t __ret; \	23268	int16x4_t __ret; \
24017	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	23269	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__s1, __p2); \
24018	__ret; \	23270	__ret; \
24019	})	23271	})
24020	#else	23272	#else
...	@@ -24023,7 +23275,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -24023,7 +23275,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
24023	int16x4_t __s1 = __p1; \	23275	int16x4_t __s1 = __p1; \
24024	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	23276	int16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
24025	int16x4_t __ret; \	23277	int16x4_t __ret; \
24026	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__rev1, __p2); \	23278	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__rev1, __p2); \
24027	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \	23279	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0); \
24028	__ret; \	23280	__ret; \
24029	})	23281	})
...	@@ -24031,7 +23283,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -24031,7 +23283,7 @@ __ai int8x8_t __noswap_vrsubhn_s16(int16x8_t __p0, int16x8_t __p1) {
24031	int16_t __s0 = __p0; \	23283	int16_t __s0 = __p0; \
24032	int16x4_t __s1 = __p1; \	23284	int16x4_t __s1 = __p1; \
24033	int16x4_t __ret; \	23285	int16x4_t __ret; \
24034	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int8x8_t)__s1, __p2); \	23286	__ret = (int16x4_t) __builtin_neon_vset_lane_i16(__s0, (int16x4_t)__s1, __p2); \
24035	__ret; \	23287	__ret; \
24036	})	23288	})
24037	#endif	23289	#endif
...	@@ -24206,20 +23458,11 @@ __ai uint32x2_t vshl_u32(uint32x2_t __p0, int32x2_t __p1) {	...	@@ -24206,20 +23458,11 @@ __ai uint32x2_t vshl_u32(uint32x2_t __p0, int32x2_t __p1) {
24206	}	23458	}
24207	#endif	23459	#endif
24208		23460
24209	#ifdef __LITTLE_ENDIAN__
24210	__ai uint64x1_t vshl_u64(uint64x1_t __p0, int64x1_t __p1) {
24211	uint64x1_t __ret;
24212	__ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
24213	return __ret;
24214	}
24215	#else
24216	__ai uint64x1_t vshl_u64(uint64x1_t __p0, int64x1_t __p1) {	23461	__ai uint64x1_t vshl_u64(uint64x1_t __p0, int64x1_t __p1) {
24217	uint64x1_t __ret;	23462	uint64x1_t __ret;
24218	__ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	23463	__ret = (uint64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
24219	return __ret;	23464	return __ret;
24220	}	23465	}
24221	#endif
24222
24223	#ifdef __LITTLE_ENDIAN__	23466	#ifdef __LITTLE_ENDIAN__
24224	__ai uint16x4_t vshl_u16(uint16x4_t __p0, int16x4_t __p1) {	23467	__ai uint16x4_t vshl_u16(uint16x4_t __p0, int16x4_t __p1) {
24225	uint16x4_t __ret;	23468	uint16x4_t __ret;
...	@@ -24271,20 +23514,11 @@ __ai int32x2_t vshl_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -24271,20 +23514,11 @@ __ai int32x2_t vshl_s32(int32x2_t __p0, int32x2_t __p1) {
24271	}	23514	}
24272	#endif	23515	#endif
24273		23516
24274	#ifdef __LITTLE_ENDIAN__
24275	__ai int64x1_t vshl_s64(int64x1_t __p0, int64x1_t __p1) {
24276	int64x1_t __ret;
24277	__ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
24278	return __ret;
24279	}
24280	#else
24281	__ai int64x1_t vshl_s64(int64x1_t __p0, int64x1_t __p1) {	23517	__ai int64x1_t vshl_s64(int64x1_t __p0, int64x1_t __p1) {
24282	int64x1_t __ret;	23518	int64x1_t __ret;
24283	__ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	23519	__ret = (int64x1_t) __builtin_neon_vshl_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
24284	return __ret;	23520	return __ret;
24285	}	23521	}
24286	#endif
24287
24288	#ifdef __LITTLE_ENDIAN__	23522	#ifdef __LITTLE_ENDIAN__
24289	__ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	23523	__ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
24290	int16x4_t __ret;	23524	int16x4_t __ret;
...	@@ -24482,22 +23716,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -24482,22 +23716,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
24482	})	23716	})
24483	#endif	23717	#endif
24484		23718
24485	#ifdef __LITTLE_ENDIAN__
24486	#define vshl_n_u64(__p0, __p1) __extension__ ({ \	23719	#define vshl_n_u64(__p0, __p1) __extension__ ({ \
24487	uint64x1_t __s0 = __p0; \	23720	uint64x1_t __s0 = __p0; \
24488	uint64x1_t __ret; \	23721	uint64x1_t __ret; \
24489	__ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \	23722	__ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
24490	__ret; \	23723	__ret; \
24491	})	23724	})
24492	#else
24493	#define vshl_n_u64(__p0, __p1) __extension__ ({ \
24494	uint64x1_t __s0 = __p0; \
24495	uint64x1_t __ret; \
24496	__ret = (uint64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 19); \
24497	__ret; \
24498	})
24499	#endif
24500
24501	#ifdef __LITTLE_ENDIAN__	23725	#ifdef __LITTLE_ENDIAN__
24502	#define vshl_n_u16(__p0, __p1) __extension__ ({ \	23726	#define vshl_n_u16(__p0, __p1) __extension__ ({ \
24503	uint16x4_t __s0 = __p0; \	23727	uint16x4_t __s0 = __p0; \
...	@@ -24552,22 +23776,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -24552,22 +23776,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
24552	})	23776	})
24553	#endif	23777	#endif
24554		23778
24555	#ifdef __LITTLE_ENDIAN__
24556	#define vshl_n_s64(__p0, __p1) __extension__ ({ \
24557	int64x1_t __s0 = __p0; \
24558	int64x1_t __ret; \
24559	__ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
24560	__ret; \
24561	})
24562	#else
24563	#define vshl_n_s64(__p0, __p1) __extension__ ({ \	23779	#define vshl_n_s64(__p0, __p1) __extension__ ({ \
24564	int64x1_t __s0 = __p0; \	23780	int64x1_t __s0 = __p0; \
24565	int64x1_t __ret; \	23781	int64x1_t __ret; \
24566	__ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \	23782	__ret = (int64x1_t) __builtin_neon_vshl_n_v((int8x8_t)__s0, __p1, 3); \
24567	__ret; \	23783	__ret; \
24568	})	23784	})
24569	#endif
24570
24571	#ifdef __LITTLE_ENDIAN__	23785	#ifdef __LITTLE_ENDIAN__
24572	#define vshl_n_s16(__p0, __p1) __extension__ ({ \	23786	#define vshl_n_s16(__p0, __p1) __extension__ ({ \
24573	int16x4_t __s0 = __p0; \	23787	int16x4_t __s0 = __p0; \
...	@@ -24910,22 +24124,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -24910,22 +24124,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
24910	})	24124	})
24911	#endif	24125	#endif
24912		24126
24913	#ifdef __LITTLE_ENDIAN__
24914	#define vshr_n_u64(__p0, __p1) __extension__ ({ \
24915	uint64x1_t __s0 = __p0; \
24916	uint64x1_t __ret; \
24917	__ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
24918	__ret; \
24919	})
24920	#else
24921	#define vshr_n_u64(__p0, __p1) __extension__ ({ \	24127	#define vshr_n_u64(__p0, __p1) __extension__ ({ \
24922	uint64x1_t __s0 = __p0; \	24128	uint64x1_t __s0 = __p0; \
24923	uint64x1_t __ret; \	24129	uint64x1_t __ret; \
24924	__ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \	24130	__ret = (uint64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 19); \
24925	__ret; \	24131	__ret; \
24926	})	24132	})
24927	#endif
24928
24929	#ifdef __LITTLE_ENDIAN__	24133	#ifdef __LITTLE_ENDIAN__
24930	#define vshr_n_u16(__p0, __p1) __extension__ ({ \	24134	#define vshr_n_u16(__p0, __p1) __extension__ ({ \
24931	uint16x4_t __s0 = __p0; \	24135	uint16x4_t __s0 = __p0; \
...	@@ -24980,22 +24184,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -24980,22 +24184,12 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
24980	})	24184	})
24981	#endif	24185	#endif
24982		24186
24983	#ifdef __LITTLE_ENDIAN__
24984	#define vshr_n_s64(__p0, __p1) __extension__ ({ \
24985	int64x1_t __s0 = __p0; \
24986	int64x1_t __ret; \
24987	__ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
24988	__ret; \
24989	})
24990	#else
24991	#define vshr_n_s64(__p0, __p1) __extension__ ({ \	24187	#define vshr_n_s64(__p0, __p1) __extension__ ({ \
24992	int64x1_t __s0 = __p0; \	24188	int64x1_t __s0 = __p0; \
24993	int64x1_t __ret; \	24189	int64x1_t __ret; \
24994	__ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \	24190	__ret = (int64x1_t) __builtin_neon_vshr_n_v((int8x8_t)__s0, __p1, 3); \
24995	__ret; \	24191	__ret; \
24996	})	24192	})
24997	#endif
24998
24999	#ifdef __LITTLE_ENDIAN__	24193	#ifdef __LITTLE_ENDIAN__
25000	#define vshr_n_s16(__p0, __p1) __extension__ ({ \	24194	#define vshr_n_s16(__p0, __p1) __extension__ ({ \
25001	int16x4_t __s0 = __p0; \	24195	int16x4_t __s0 = __p0; \
...	@@ -25452,15 +24646,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25452,15 +24646,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25452	})	24646	})
25453	#endif	24647	#endif
25454		24648
25455	#ifdef __LITTLE_ENDIAN__
25456	#define vsli_n_u64(__p0, __p1, __p2) __extension__ ({ \
25457	uint64x1_t __s0 = __p0; \
25458	uint64x1_t __s1 = __p1; \
25459	uint64x1_t __ret; \
25460	__ret = (uint64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
25461	__ret; \
25462	})
25463	#else
25464	#define vsli_n_u64(__p0, __p1, __p2) __extension__ ({ \	24649	#define vsli_n_u64(__p0, __p1, __p2) __extension__ ({ \
25465	uint64x1_t __s0 = __p0; \	24650	uint64x1_t __s0 = __p0; \
25466	uint64x1_t __s1 = __p1; \	24651	uint64x1_t __s1 = __p1; \
...	@@ -25468,8 +24653,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25468,8 +24653,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25468	__ret = (uint64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \	24653	__ret = (uint64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
25469	__ret; \	24654	__ret; \
25470	})	24655	})
25471	#endif
25472
25473	#ifdef __LITTLE_ENDIAN__	24656	#ifdef __LITTLE_ENDIAN__
25474	#define vsli_n_u16(__p0, __p1, __p2) __extension__ ({ \	24657	#define vsli_n_u16(__p0, __p1, __p2) __extension__ ({ \
25475	uint16x4_t __s0 = __p0; \	24658	uint16x4_t __s0 = __p0; \
...	@@ -25533,15 +24716,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25533,15 +24716,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25533	})	24716	})
25534	#endif	24717	#endif
25535		24718
25536	#ifdef __LITTLE_ENDIAN__
25537	#define vsli_n_s64(__p0, __p1, __p2) __extension__ ({ \
25538	int64x1_t __s0 = __p0; \
25539	int64x1_t __s1 = __p1; \
25540	int64x1_t __ret; \
25541	__ret = (int64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25542	__ret; \
25543	})
25544	#else
25545	#define vsli_n_s64(__p0, __p1, __p2) __extension__ ({ \	24719	#define vsli_n_s64(__p0, __p1, __p2) __extension__ ({ \
25546	int64x1_t __s0 = __p0; \	24720	int64x1_t __s0 = __p0; \
25547	int64x1_t __s1 = __p1; \	24721	int64x1_t __s1 = __p1; \
...	@@ -25549,8 +24723,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25549,8 +24723,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25549	__ret = (int64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \	24723	__ret = (int64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25550	__ret; \	24724	__ret; \
25551	})	24725	})
25552	#endif
25553
25554	#ifdef __LITTLE_ENDIAN__	24726	#ifdef __LITTLE_ENDIAN__
25555	#define vsli_n_s16(__p0, __p1, __p2) __extension__ ({ \	24727	#define vsli_n_s16(__p0, __p1, __p2) __extension__ ({ \
25556	int16x4_t __s0 = __p0; \	24728	int16x4_t __s0 = __p0; \
...	@@ -25782,7 +24954,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25782,7 +24954,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25782	})	24954	})
25783	#endif	24955	#endif
25784		24956
25785	#ifdef __LITTLE_ENDIAN__
25786	#define vsra_n_u64(__p0, __p1, __p2) __extension__ ({ \	24957	#define vsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
25787	uint64x1_t __s0 = __p0; \	24958	uint64x1_t __s0 = __p0; \
25788	uint64x1_t __s1 = __p1; \	24959	uint64x1_t __s1 = __p1; \
...	@@ -25790,16 +24961,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25790,16 +24961,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25790	__ret = (uint64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \	24961	__ret = (uint64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
25791	__ret; \	24962	__ret; \
25792	})	24963	})
25793	#else
25794	#define vsra_n_u64(__p0, __p1, __p2) __extension__ ({ \
25795	uint64x1_t __s0 = __p0; \
25796	uint64x1_t __s1 = __p1; \
25797	uint64x1_t __ret; \
25798	__ret = (uint64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
25799	__ret; \
25800	})
25801	#endif
25802
25803	#ifdef __LITTLE_ENDIAN__	24964	#ifdef __LITTLE_ENDIAN__
25804	#define vsra_n_u16(__p0, __p1, __p2) __extension__ ({ \	24965	#define vsra_n_u16(__p0, __p1, __p2) __extension__ ({ \
25805	uint16x4_t __s0 = __p0; \	24966	uint16x4_t __s0 = __p0; \
...	@@ -25863,15 +25024,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25863,15 +25024,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25863	})	25024	})
25864	#endif	25025	#endif
25865		25026
25866	#ifdef __LITTLE_ENDIAN__
25867	#define vsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
25868	int64x1_t __s0 = __p0; \
25869	int64x1_t __s1 = __p1; \
25870	int64x1_t __ret; \
25871	__ret = (int64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25872	__ret; \
25873	})
25874	#else
25875	#define vsra_n_s64(__p0, __p1, __p2) __extension__ ({ \	25027	#define vsra_n_s64(__p0, __p1, __p2) __extension__ ({ \
25876	int64x1_t __s0 = __p0; \	25028	int64x1_t __s0 = __p0; \
25877	int64x1_t __s1 = __p1; \	25029	int64x1_t __s1 = __p1; \
...	@@ -25879,8 +25031,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -25879,8 +25031,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
25879	__ret = (int64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \	25031	__ret = (int64x1_t) __builtin_neon_vsra_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
25880	__ret; \	25032	__ret; \
25881	})	25033	})
25882	#endif
25883
25884	#ifdef __LITTLE_ENDIAN__	25034	#ifdef __LITTLE_ENDIAN__
25885	#define vsra_n_s16(__p0, __p1, __p2) __extension__ ({ \	25035	#define vsra_n_s16(__p0, __p1, __p2) __extension__ ({ \
25886	int16x4_t __s0 = __p0; \	25036	int16x4_t __s0 = __p0; \
...	@@ -26196,15 +25346,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26196,15 +25346,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26196	})	25346	})
26197	#endif	25347	#endif
26198		25348
26199	#ifdef __LITTLE_ENDIAN__
26200	#define vsri_n_u64(__p0, __p1, __p2) __extension__ ({ \
26201	uint64x1_t __s0 = __p0; \
26202	uint64x1_t __s1 = __p1; \
26203	uint64x1_t __ret; \
26204	__ret = (uint64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
26205	__ret; \
26206	})
26207	#else
26208	#define vsri_n_u64(__p0, __p1, __p2) __extension__ ({ \	25349	#define vsri_n_u64(__p0, __p1, __p2) __extension__ ({ \
26209	uint64x1_t __s0 = __p0; \	25350	uint64x1_t __s0 = __p0; \
26210	uint64x1_t __s1 = __p1; \	25351	uint64x1_t __s1 = __p1; \
...	@@ -26212,8 +25353,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26212,8 +25353,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26212	__ret = (uint64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \	25353	__ret = (uint64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 19); \
26213	__ret; \	25354	__ret; \
26214	})	25355	})
26215	#endif
26216
26217	#ifdef __LITTLE_ENDIAN__	25356	#ifdef __LITTLE_ENDIAN__
26218	#define vsri_n_u16(__p0, __p1, __p2) __extension__ ({ \	25357	#define vsri_n_u16(__p0, __p1, __p2) __extension__ ({ \
26219	uint16x4_t __s0 = __p0; \	25358	uint16x4_t __s0 = __p0; \
...	@@ -26277,15 +25416,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26277,15 +25416,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26277	})	25416	})
26278	#endif	25417	#endif
26279		25418
26280	#ifdef __LITTLE_ENDIAN__
26281	#define vsri_n_s64(__p0, __p1, __p2) __extension__ ({ \
26282	int64x1_t __s0 = __p0; \
26283	int64x1_t __s1 = __p1; \
26284	int64x1_t __ret; \
26285	__ret = (int64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
26286	__ret; \
26287	})
26288	#else
26289	#define vsri_n_s64(__p0, __p1, __p2) __extension__ ({ \	25419	#define vsri_n_s64(__p0, __p1, __p2) __extension__ ({ \
26290	int64x1_t __s0 = __p0; \	25420	int64x1_t __s0 = __p0; \
26291	int64x1_t __s1 = __p1; \	25421	int64x1_t __s1 = __p1; \
...	@@ -26293,8 +25423,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26293,8 +25423,6 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26293	__ret = (int64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \	25423	__ret = (int64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 3); \
26294	__ret; \	25424	__ret; \
26295	})	25425	})
26296	#endif
26297
26298	#ifdef __LITTLE_ENDIAN__	25426	#ifdef __LITTLE_ENDIAN__
26299	#define vsri_n_s16(__p0, __p1, __p2) __extension__ ({ \	25427	#define vsri_n_s16(__p0, __p1, __p2) __extension__ ({ \
26300	int16x4_t __s0 = __p0; \	25428	int16x4_t __s0 = __p0; \
...	@@ -26511,18 +25639,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26511,18 +25639,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26511	})	25639	})
26512	#endif	25640	#endif
26513		25641
26514	#ifdef __LITTLE_ENDIAN__
26515	#define vst1_u64(__p0, __p1) __extension__ ({ \
26516	uint64x1_t __s1 = __p1; \
26517	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 19); \
26518	})
26519	#else
26520	#define vst1_u64(__p0, __p1) __extension__ ({ \	25642	#define vst1_u64(__p0, __p1) __extension__ ({ \
26521	uint64x1_t __s1 = __p1; \	25643	uint64x1_t __s1 = __p1; \
26522	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 19); \	25644	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 19); \
26523	})	25645	})
26524	#endif
26525
26526	#ifdef __LITTLE_ENDIAN__	25646	#ifdef __LITTLE_ENDIAN__
26527	#define vst1_u16(__p0, __p1) __extension__ ({ \	25647	#define vst1_u16(__p0, __p1) __extension__ ({ \
26528	uint16x4_t __s1 = __p1; \	25648	uint16x4_t __s1 = __p1; \
...	@@ -26575,18 +25695,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26575,18 +25695,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26575	})	25695	})
26576	#endif	25696	#endif
26577		25697
26578	#ifdef __LITTLE_ENDIAN__
26579	#define vst1_s64(__p0, __p1) __extension__ ({ \
26580	int64x1_t __s1 = __p1; \
26581	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 3); \
26582	})
26583	#else
26584	#define vst1_s64(__p0, __p1) __extension__ ({ \	25698	#define vst1_s64(__p0, __p1) __extension__ ({ \
26585	int64x1_t __s1 = __p1; \	25699	int64x1_t __s1 = __p1; \
26586	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 3); \	25700	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 3); \
26587	})	25701	})
26588	#endif
26589
26590	#ifdef __LITTLE_ENDIAN__	25702	#ifdef __LITTLE_ENDIAN__
26591	#define vst1_s16(__p0, __p1) __extension__ ({ \	25703	#define vst1_s16(__p0, __p1) __extension__ ({ \
26592	int16x4_t __s1 = __p1; \	25704	int16x4_t __s1 = __p1; \
...	@@ -26795,18 +25907,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26795,18 +25907,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26795	})	25907	})
26796	#endif	25908	#endif
26797		25909
26798	#ifdef __LITTLE_ENDIAN__
26799	#define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
26800	uint64x1_t __s1 = __p1; \
26801	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
26802	})
26803	#else
26804	#define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({ \	25910	#define vst1_lane_u64(__p0, __p1, __p2) __extension__ ({ \
26805	uint64x1_t __s1 = __p1; \	25911	uint64x1_t __s1 = __p1; \
26806	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \	25912	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 19); \
26807	})	25913	})
26808	#endif
26809
26810	#ifdef __LITTLE_ENDIAN__	25914	#ifdef __LITTLE_ENDIAN__
26811	#define vst1_lane_u16(__p0, __p1, __p2) __extension__ ({ \	25915	#define vst1_lane_u16(__p0, __p1, __p2) __extension__ ({ \
26812	uint16x4_t __s1 = __p1; \	25916	uint16x4_t __s1 = __p1; \
...	@@ -26859,18 +25963,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -26859,18 +25963,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
26859	})	25963	})
26860	#endif	25964	#endif
26861		25965
26862	#ifdef __LITTLE_ENDIAN__
26863	#define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
26864	int64x1_t __s1 = __p1; \
26865	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
26866	})
26867	#else
26868	#define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({ \	25966	#define vst1_lane_s64(__p0, __p1, __p2) __extension__ ({ \
26869	int64x1_t __s1 = __p1; \	25967	int64x1_t __s1 = __p1; \
26870	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \	25968	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 3); \
26871	})	25969	})
26872	#endif
26873
26874	#ifdef __LITTLE_ENDIAN__	25970	#ifdef __LITTLE_ENDIAN__
26875	#define vst1_lane_s16(__p0, __p1, __p2) __extension__ ({ \	25971	#define vst1_lane_s16(__p0, __p1, __p2) __extension__ ({ \
26876	int16x4_t __s1 = __p1; \	25972	int16x4_t __s1 = __p1; \
...	@@ -27022,7 +26118,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27022,7 +26118,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27022	#ifdef __LITTLE_ENDIAN__	26118	#ifdef __LITTLE_ENDIAN__
27023	#define vst1q_f32_x2(__p0, __p1) __extension__ ({ \	26119	#define vst1q_f32_x2(__p0, __p1) __extension__ ({ \
27024	float32x4x2_t __s1 = __p1; \	26120	float32x4x2_t __s1 = __p1; \
27025	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 41); \	26121	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 41); \
27026	})	26122	})
27027	#else	26123	#else
27028	#define vst1q_f32_x2(__p0, __p1) __extension__ ({ \	26124	#define vst1q_f32_x2(__p0, __p1) __extension__ ({ \
...	@@ -27030,14 +26126,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27030,14 +26126,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27030	float32x4x2_t __rev1; \	26126	float32x4x2_t __rev1; \
27031	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26127	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27032	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26128	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27033	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 41); \	26129	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 41); \
27034	})	26130	})
27035	#endif	26131	#endif
27036		26132
27037	#ifdef __LITTLE_ENDIAN__	26133	#ifdef __LITTLE_ENDIAN__
27038	#define vst1q_s32_x2(__p0, __p1) __extension__ ({ \	26134	#define vst1q_s32_x2(__p0, __p1) __extension__ ({ \
27039	int32x4x2_t __s1 = __p1; \	26135	int32x4x2_t __s1 = __p1; \
27040	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 34); \	26136	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 34); \
27041	})	26137	})
27042	#else	26138	#else
27043	#define vst1q_s32_x2(__p0, __p1) __extension__ ({ \	26139	#define vst1q_s32_x2(__p0, __p1) __extension__ ({ \
...	@@ -27045,14 +26141,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27045,14 +26141,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27045	int32x4x2_t __rev1; \	26141	int32x4x2_t __rev1; \
27046	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26142	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27047	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26143	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27048	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 34); \	26144	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 34); \
27049	})	26145	})
27050	#endif	26146	#endif
27051		26147
27052	#ifdef __LITTLE_ENDIAN__	26148	#ifdef __LITTLE_ENDIAN__
27053	#define vst1q_s64_x2(__p0, __p1) __extension__ ({ \	26149	#define vst1q_s64_x2(__p0, __p1) __extension__ ({ \
27054	int64x2x2_t __s1 = __p1; \	26150	int64x2x2_t __s1 = __p1; \
27055	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 35); \	26151	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 35); \
27056	})	26152	})
27057	#else	26153	#else
27058	#define vst1q_s64_x2(__p0, __p1) __extension__ ({ \	26154	#define vst1q_s64_x2(__p0, __p1) __extension__ ({ \
...	@@ -27060,14 +26156,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27060,14 +26156,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27060	int64x2x2_t __rev1; \	26156	int64x2x2_t __rev1; \
27061	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26157	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27062	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26158	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27063	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 35); \	26159	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 35); \
27064	})	26160	})
27065	#endif	26161	#endif
27066		26162
27067	#ifdef __LITTLE_ENDIAN__	26163	#ifdef __LITTLE_ENDIAN__
27068	#define vst1q_s16_x2(__p0, __p1) __extension__ ({ \	26164	#define vst1q_s16_x2(__p0, __p1) __extension__ ({ \
27069	int16x8x2_t __s1 = __p1; \	26165	int16x8x2_t __s1 = __p1; \
27070	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 33); \	26166	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 33); \
27071	})	26167	})
27072	#else	26168	#else
27073	#define vst1q_s16_x2(__p0, __p1) __extension__ ({ \	26169	#define vst1q_s16_x2(__p0, __p1) __extension__ ({ \
...	@@ -27075,7 +26171,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27075,7 +26171,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27075	int16x8x2_t __rev1; \	26171	int16x8x2_t __rev1; \
27076	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	26172	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
27077	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	26173	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
27078	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 33); \	26174	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 33); \
27079	})	26175	})
27080	#endif	26176	#endif
27081		26177
...	@@ -27109,18 +26205,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27109,18 +26205,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27109	})	26205	})
27110	#endif	26206	#endif
27111		26207
27112	#ifdef __LITTLE_ENDIAN__
27113	#define vst1_u64_x2(__p0, __p1) __extension__ ({ \
27114	uint64x1x2_t __s1 = __p1; \
27115	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
27116	})
27117	#else
27118	#define vst1_u64_x2(__p0, __p1) __extension__ ({ \	26208	#define vst1_u64_x2(__p0, __p1) __extension__ ({ \
27119	uint64x1x2_t __s1 = __p1; \	26209	uint64x1x2_t __s1 = __p1; \
27120	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \	26210	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
27121	})	26211	})
27122	#endif
27123
27124	#ifdef __LITTLE_ENDIAN__	26212	#ifdef __LITTLE_ENDIAN__
27125	#define vst1_u16_x2(__p0, __p1) __extension__ ({ \	26213	#define vst1_u16_x2(__p0, __p1) __extension__ ({ \
27126	uint16x4x2_t __s1 = __p1; \	26214	uint16x4x2_t __s1 = __p1; \
...	@@ -27154,7 +26242,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27154,7 +26242,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27154	#ifdef __LITTLE_ENDIAN__	26242	#ifdef __LITTLE_ENDIAN__
27155	#define vst1_f32_x2(__p0, __p1) __extension__ ({ \	26243	#define vst1_f32_x2(__p0, __p1) __extension__ ({ \
27156	float32x2x2_t __s1 = __p1; \	26244	float32x2x2_t __s1 = __p1; \
27157	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 9); \	26245	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 9); \
27158	})	26246	})
27159	#else	26247	#else
27160	#define vst1_f32_x2(__p0, __p1) __extension__ ({ \	26248	#define vst1_f32_x2(__p0, __p1) __extension__ ({ \
...	@@ -27162,14 +26250,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27162,14 +26250,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27162	float32x2x2_t __rev1; \	26250	float32x2x2_t __rev1; \
27163	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26251	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27164	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26252	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27165	__builtin_neon_vst1_x2_v(__p0, __rev1.val[0], __rev1.val[1], 9); \	26253	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 9); \
27166	})	26254	})
27167	#endif	26255	#endif
27168		26256
27169	#ifdef __LITTLE_ENDIAN__	26257	#ifdef __LITTLE_ENDIAN__
27170	#define vst1_s32_x2(__p0, __p1) __extension__ ({ \	26258	#define vst1_s32_x2(__p0, __p1) __extension__ ({ \
27171	int32x2x2_t __s1 = __p1; \	26259	int32x2x2_t __s1 = __p1; \
27172	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 2); \	26260	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 2); \
27173	})	26261	})
27174	#else	26262	#else
27175	#define vst1_s32_x2(__p0, __p1) __extension__ ({ \	26263	#define vst1_s32_x2(__p0, __p1) __extension__ ({ \
...	@@ -27177,26 +26265,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27177,26 +26265,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27177	int32x2x2_t __rev1; \	26265	int32x2x2_t __rev1; \
27178	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26266	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27179	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26267	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27180	__builtin_neon_vst1_x2_v(__p0, __rev1.val[0], __rev1.val[1], 2); \	26268	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 2); \
27181	})	26269	})
27182	#endif	26270	#endif
27183		26271
27184	#ifdef __LITTLE_ENDIAN__
27185	#define vst1_s64_x2(__p0, __p1) __extension__ ({ \
27186	int64x1x2_t __s1 = __p1; \
27187	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 3); \
27188	})
27189	#else
27190	#define vst1_s64_x2(__p0, __p1) __extension__ ({ \	26272	#define vst1_s64_x2(__p0, __p1) __extension__ ({ \
27191	int64x1x2_t __s1 = __p1; \	26273	int64x1x2_t __s1 = __p1; \
27192	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 3); \	26274	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 3); \
27193	})	26275	})
27194	#endif
27195
27196	#ifdef __LITTLE_ENDIAN__	26276	#ifdef __LITTLE_ENDIAN__
27197	#define vst1_s16_x2(__p0, __p1) __extension__ ({ \	26277	#define vst1_s16_x2(__p0, __p1) __extension__ ({ \
27198	int16x4x2_t __s1 = __p1; \	26278	int16x4x2_t __s1 = __p1; \
27199	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 1); \	26279	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 1); \
27200	})	26280	})
27201	#else	26281	#else
27202	#define vst1_s16_x2(__p0, __p1) __extension__ ({ \	26282	#define vst1_s16_x2(__p0, __p1) __extension__ ({ \
...	@@ -27204,7 +26284,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27204,7 +26284,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27204	int16x4x2_t __rev1; \	26284	int16x4x2_t __rev1; \
27205	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26285	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27206	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26286	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27207	__builtin_neon_vst1_x2_v(__p0, __rev1.val[0], __rev1.val[1], 1); \	26287	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 1); \
27208	})	26288	})
27209	#endif	26289	#endif
27210		26290
...	@@ -27355,7 +26435,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27355,7 +26435,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27355	#ifdef __LITTLE_ENDIAN__	26435	#ifdef __LITTLE_ENDIAN__
27356	#define vst1q_f32_x3(__p0, __p1) __extension__ ({ \	26436	#define vst1q_f32_x3(__p0, __p1) __extension__ ({ \
27357	float32x4x3_t __s1 = __p1; \	26437	float32x4x3_t __s1 = __p1; \
27358	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 41); \	26438	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 41); \
27359	})	26439	})
27360	#else	26440	#else
27361	#define vst1q_f32_x3(__p0, __p1) __extension__ ({ \	26441	#define vst1q_f32_x3(__p0, __p1) __extension__ ({ \
...	@@ -27364,14 +26444,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27364,14 +26444,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27364	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26444	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27365	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26445	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27366	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26446	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27367	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 41); \	26447	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 41); \
27368	})	26448	})
27369	#endif	26449	#endif
27370		26450
27371	#ifdef __LITTLE_ENDIAN__	26451	#ifdef __LITTLE_ENDIAN__
27372	#define vst1q_s32_x3(__p0, __p1) __extension__ ({ \	26452	#define vst1q_s32_x3(__p0, __p1) __extension__ ({ \
27373	int32x4x3_t __s1 = __p1; \	26453	int32x4x3_t __s1 = __p1; \
27374	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 34); \	26454	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 34); \
27375	})	26455	})
27376	#else	26456	#else
27377	#define vst1q_s32_x3(__p0, __p1) __extension__ ({ \	26457	#define vst1q_s32_x3(__p0, __p1) __extension__ ({ \
...	@@ -27380,14 +26460,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27380,14 +26460,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27380	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26460	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27381	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26461	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27382	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26462	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27383	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 34); \	26463	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 34); \
27384	})	26464	})
27385	#endif	26465	#endif
27386		26466
27387	#ifdef __LITTLE_ENDIAN__	26467	#ifdef __LITTLE_ENDIAN__
27388	#define vst1q_s64_x3(__p0, __p1) __extension__ ({ \	26468	#define vst1q_s64_x3(__p0, __p1) __extension__ ({ \
27389	int64x2x3_t __s1 = __p1; \	26469	int64x2x3_t __s1 = __p1; \
27390	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 35); \	26470	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 35); \
27391	})	26471	})
27392	#else	26472	#else
27393	#define vst1q_s64_x3(__p0, __p1) __extension__ ({ \	26473	#define vst1q_s64_x3(__p0, __p1) __extension__ ({ \
...	@@ -27396,14 +26476,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27396,14 +26476,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27396	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26476	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27397	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26477	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27398	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26478	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27399	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 35); \	26479	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 35); \
27400	})	26480	})
27401	#endif	26481	#endif
27402		26482
27403	#ifdef __LITTLE_ENDIAN__	26483	#ifdef __LITTLE_ENDIAN__
27404	#define vst1q_s16_x3(__p0, __p1) __extension__ ({ \	26484	#define vst1q_s16_x3(__p0, __p1) __extension__ ({ \
27405	int16x8x3_t __s1 = __p1; \	26485	int16x8x3_t __s1 = __p1; \
27406	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 33); \	26486	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 33); \
27407	})	26487	})
27408	#else	26488	#else
27409	#define vst1q_s16_x3(__p0, __p1) __extension__ ({ \	26489	#define vst1q_s16_x3(__p0, __p1) __extension__ ({ \
...	@@ -27412,7 +26492,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27412,7 +26492,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27412	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	26492	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
27413	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	26493	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
27414	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	26494	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
27415	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 33); \	26495	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 33); \
27416	})	26496	})
27417	#endif	26497	#endif
27418		26498
...	@@ -27448,18 +26528,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27448,18 +26528,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27448	})	26528	})
27449	#endif	26529	#endif
27450		26530
27451	#ifdef __LITTLE_ENDIAN__
27452	#define vst1_u64_x3(__p0, __p1) __extension__ ({ \
27453	uint64x1x3_t __s1 = __p1; \
27454	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
27455	})
27456	#else
27457	#define vst1_u64_x3(__p0, __p1) __extension__ ({ \	26531	#define vst1_u64_x3(__p0, __p1) __extension__ ({ \
27458	uint64x1x3_t __s1 = __p1; \	26532	uint64x1x3_t __s1 = __p1; \
27459	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \	26533	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
27460	})	26534	})
27461	#endif
27462
27463	#ifdef __LITTLE_ENDIAN__	26535	#ifdef __LITTLE_ENDIAN__
27464	#define vst1_u16_x3(__p0, __p1) __extension__ ({ \	26536	#define vst1_u16_x3(__p0, __p1) __extension__ ({ \
27465	uint16x4x3_t __s1 = __p1; \	26537	uint16x4x3_t __s1 = __p1; \
...	@@ -27495,7 +26567,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27495,7 +26567,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27495	#ifdef __LITTLE_ENDIAN__	26567	#ifdef __LITTLE_ENDIAN__
27496	#define vst1_f32_x3(__p0, __p1) __extension__ ({ \	26568	#define vst1_f32_x3(__p0, __p1) __extension__ ({ \
27497	float32x2x3_t __s1 = __p1; \	26569	float32x2x3_t __s1 = __p1; \
27498	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 9); \	26570	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 9); \
27499	})	26571	})
27500	#else	26572	#else
27501	#define vst1_f32_x3(__p0, __p1) __extension__ ({ \	26573	#define vst1_f32_x3(__p0, __p1) __extension__ ({ \
...	@@ -27504,14 +26576,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27504,14 +26576,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27504	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26576	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27505	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26577	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27506	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26578	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27507	__builtin_neon_vst1_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 9); \	26579	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 9); \
27508	})	26580	})
27509	#endif	26581	#endif
27510		26582
27511	#ifdef __LITTLE_ENDIAN__	26583	#ifdef __LITTLE_ENDIAN__
27512	#define vst1_s32_x3(__p0, __p1) __extension__ ({ \	26584	#define vst1_s32_x3(__p0, __p1) __extension__ ({ \
27513	int32x2x3_t __s1 = __p1; \	26585	int32x2x3_t __s1 = __p1; \
27514	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 2); \	26586	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 2); \
27515	})	26587	})
27516	#else	26588	#else
27517	#define vst1_s32_x3(__p0, __p1) __extension__ ({ \	26589	#define vst1_s32_x3(__p0, __p1) __extension__ ({ \
...	@@ -27520,26 +26592,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27520,26 +26592,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27520	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	26592	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
27521	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26593	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27522	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26594	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27523	__builtin_neon_vst1_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 2); \	26595	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 2); \
27524	})	26596	})
27525	#endif	26597	#endif
27526		26598
27527	#ifdef __LITTLE_ENDIAN__
27528	#define vst1_s64_x3(__p0, __p1) __extension__ ({ \
27529	int64x1x3_t __s1 = __p1; \
27530	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 3); \
27531	})
27532	#else
27533	#define vst1_s64_x3(__p0, __p1) __extension__ ({ \	26599	#define vst1_s64_x3(__p0, __p1) __extension__ ({ \
27534	int64x1x3_t __s1 = __p1; \	26600	int64x1x3_t __s1 = __p1; \
27535	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 3); \	26601	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 3); \
27536	})	26602	})
27537	#endif
27538
27539	#ifdef __LITTLE_ENDIAN__	26603	#ifdef __LITTLE_ENDIAN__
27540	#define vst1_s16_x3(__p0, __p1) __extension__ ({ \	26604	#define vst1_s16_x3(__p0, __p1) __extension__ ({ \
27541	int16x4x3_t __s1 = __p1; \	26605	int16x4x3_t __s1 = __p1; \
27542	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 1); \	26606	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 1); \
27543	})	26607	})
27544	#else	26608	#else
27545	#define vst1_s16_x3(__p0, __p1) __extension__ ({ \	26609	#define vst1_s16_x3(__p0, __p1) __extension__ ({ \
...	@@ -27548,7 +26612,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27548,7 +26612,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27548	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	26612	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
27549	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26613	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27550	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26614	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27551	__builtin_neon_vst1_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 1); \	26615	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 1); \
27552	})	26616	})
27553	#endif	26617	#endif
27554		26618
...	@@ -27708,7 +26772,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27708,7 +26772,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27708	#ifdef __LITTLE_ENDIAN__	26772	#ifdef __LITTLE_ENDIAN__
27709	#define vst1q_f32_x4(__p0, __p1) __extension__ ({ \	26773	#define vst1q_f32_x4(__p0, __p1) __extension__ ({ \
27710	float32x4x4_t __s1 = __p1; \	26774	float32x4x4_t __s1 = __p1; \
27711	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 41); \	26775	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 41); \
27712	})	26776	})
27713	#else	26777	#else
27714	#define vst1q_f32_x4(__p0, __p1) __extension__ ({ \	26778	#define vst1q_f32_x4(__p0, __p1) __extension__ ({ \
...	@@ -27718,14 +26782,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27718,14 +26782,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27718	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26782	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27719	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26783	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27720	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	26784	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
27721	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 41); \	26785	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 41); \
27722	})	26786	})
27723	#endif	26787	#endif
27724		26788
27725	#ifdef __LITTLE_ENDIAN__	26789	#ifdef __LITTLE_ENDIAN__
27726	#define vst1q_s32_x4(__p0, __p1) __extension__ ({ \	26790	#define vst1q_s32_x4(__p0, __p1) __extension__ ({ \
27727	int32x4x4_t __s1 = __p1; \	26791	int32x4x4_t __s1 = __p1; \
27728	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 34); \	26792	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 34); \
27729	})	26793	})
27730	#else	26794	#else
27731	#define vst1q_s32_x4(__p0, __p1) __extension__ ({ \	26795	#define vst1q_s32_x4(__p0, __p1) __extension__ ({ \
...	@@ -27735,14 +26799,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27735,14 +26799,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27735	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26799	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27736	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26800	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27737	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	26801	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
27738	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 34); \	26802	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 34); \
27739	})	26803	})
27740	#endif	26804	#endif
27741		26805
27742	#ifdef __LITTLE_ENDIAN__	26806	#ifdef __LITTLE_ENDIAN__
27743	#define vst1q_s64_x4(__p0, __p1) __extension__ ({ \	26807	#define vst1q_s64_x4(__p0, __p1) __extension__ ({ \
27744	int64x2x4_t __s1 = __p1; \	26808	int64x2x4_t __s1 = __p1; \
27745	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 35); \	26809	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 35); \
27746	})	26810	})
27747	#else	26811	#else
27748	#define vst1q_s64_x4(__p0, __p1) __extension__ ({ \	26812	#define vst1q_s64_x4(__p0, __p1) __extension__ ({ \
...	@@ -27752,14 +26816,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27752,14 +26816,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27752	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26816	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27753	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26817	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27754	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	26818	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
27755	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 35); \	26819	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 35); \
27756	})	26820	})
27757	#endif	26821	#endif
27758		26822
27759	#ifdef __LITTLE_ENDIAN__	26823	#ifdef __LITTLE_ENDIAN__
27760	#define vst1q_s16_x4(__p0, __p1) __extension__ ({ \	26824	#define vst1q_s16_x4(__p0, __p1) __extension__ ({ \
27761	int16x8x4_t __s1 = __p1; \	26825	int16x8x4_t __s1 = __p1; \
27762	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 33); \	26826	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 33); \
27763	})	26827	})
27764	#else	26828	#else
27765	#define vst1q_s16_x4(__p0, __p1) __extension__ ({ \	26829	#define vst1q_s16_x4(__p0, __p1) __extension__ ({ \
...	@@ -27769,7 +26833,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27769,7 +26833,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27769	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	26833	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
27770	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	26834	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
27771	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	26835	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
27772	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 33); \	26836	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 33); \
27773	})	26837	})
27774	#endif	26838	#endif
27775		26839
...	@@ -27807,18 +26871,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27807,18 +26871,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27807	})	26871	})
27808	#endif	26872	#endif
27809		26873
27810	#ifdef __LITTLE_ENDIAN__
27811	#define vst1_u64_x4(__p0, __p1) __extension__ ({ \
27812	uint64x1x4_t __s1 = __p1; \
27813	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
27814	})
27815	#else
27816	#define vst1_u64_x4(__p0, __p1) __extension__ ({ \	26874	#define vst1_u64_x4(__p0, __p1) __extension__ ({ \
27817	uint64x1x4_t __s1 = __p1; \	26875	uint64x1x4_t __s1 = __p1; \
27818	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \	26876	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
27819	})	26877	})
27820	#endif
27821
27822	#ifdef __LITTLE_ENDIAN__	26878	#ifdef __LITTLE_ENDIAN__
27823	#define vst1_u16_x4(__p0, __p1) __extension__ ({ \	26879	#define vst1_u16_x4(__p0, __p1) __extension__ ({ \
27824	uint16x4x4_t __s1 = __p1; \	26880	uint16x4x4_t __s1 = __p1; \
...	@@ -27856,7 +26912,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27856,7 +26912,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27856	#ifdef __LITTLE_ENDIAN__	26912	#ifdef __LITTLE_ENDIAN__
27857	#define vst1_f32_x4(__p0, __p1) __extension__ ({ \	26913	#define vst1_f32_x4(__p0, __p1) __extension__ ({ \
27858	float32x2x4_t __s1 = __p1; \	26914	float32x2x4_t __s1 = __p1; \
27859	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 9); \	26915	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 9); \
27860	})	26916	})
27861	#else	26917	#else
27862	#define vst1_f32_x4(__p0, __p1) __extension__ ({ \	26918	#define vst1_f32_x4(__p0, __p1) __extension__ ({ \
...	@@ -27866,14 +26922,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27866,14 +26922,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27866	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26922	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27867	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26923	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27868	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	26924	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
27869	__builtin_neon_vst1_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 9); \	26925	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 9); \
27870	})	26926	})
27871	#endif	26927	#endif
27872		26928
27873	#ifdef __LITTLE_ENDIAN__	26929	#ifdef __LITTLE_ENDIAN__
27874	#define vst1_s32_x4(__p0, __p1) __extension__ ({ \	26930	#define vst1_s32_x4(__p0, __p1) __extension__ ({ \
27875	int32x2x4_t __s1 = __p1; \	26931	int32x2x4_t __s1 = __p1; \
27876	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 2); \	26932	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 2); \
27877	})	26933	})
27878	#else	26934	#else
27879	#define vst1_s32_x4(__p0, __p1) __extension__ ({ \	26935	#define vst1_s32_x4(__p0, __p1) __extension__ ({ \
...	@@ -27883,26 +26939,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27883,26 +26939,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27883	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	26939	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
27884	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	26940	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
27885	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	26941	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
27886	__builtin_neon_vst1_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 2); \	26942	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 2); \
27887	})	26943	})
27888	#endif	26944	#endif
27889		26945
27890	#ifdef __LITTLE_ENDIAN__
27891	#define vst1_s64_x4(__p0, __p1) __extension__ ({ \
27892	int64x1x4_t __s1 = __p1; \
27893	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 3); \
27894	})
27895	#else
27896	#define vst1_s64_x4(__p0, __p1) __extension__ ({ \	26946	#define vst1_s64_x4(__p0, __p1) __extension__ ({ \
27897	int64x1x4_t __s1 = __p1; \	26947	int64x1x4_t __s1 = __p1; \
27898	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 3); \	26948	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 3); \
27899	})	26949	})
27900	#endif
27901
27902	#ifdef __LITTLE_ENDIAN__	26950	#ifdef __LITTLE_ENDIAN__
27903	#define vst1_s16_x4(__p0, __p1) __extension__ ({ \	26951	#define vst1_s16_x4(__p0, __p1) __extension__ ({ \
27904	int16x4x4_t __s1 = __p1; \	26952	int16x4x4_t __s1 = __p1; \
27905	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 1); \	26953	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 1); \
27906	})	26954	})
27907	#else	26955	#else
27908	#define vst1_s16_x4(__p0, __p1) __extension__ ({ \	26956	#define vst1_s16_x4(__p0, __p1) __extension__ ({ \
...	@@ -27912,7 +26960,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -27912,7 +26960,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
27912	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	26960	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
27913	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	26961	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
27914	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	26962	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
27915	__builtin_neon_vst1_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 1); \	26963	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 1); \
27916	})	26964	})
27917	#endif	26965	#endif
27918		26966
...	@@ -28039,7 +27087,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28039,7 +27087,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28039	#ifdef __LITTLE_ENDIAN__	27087	#ifdef __LITTLE_ENDIAN__
28040	#define vst2q_f32(__p0, __p1) __extension__ ({ \	27088	#define vst2q_f32(__p0, __p1) __extension__ ({ \
28041	float32x4x2_t __s1 = __p1; \	27089	float32x4x2_t __s1 = __p1; \
28042	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 41); \	27090	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 41); \
28043	})	27091	})
28044	#else	27092	#else
28045	#define vst2q_f32(__p0, __p1) __extension__ ({ \	27093	#define vst2q_f32(__p0, __p1) __extension__ ({ \
...	@@ -28047,14 +27095,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28047,14 +27095,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28047	float32x4x2_t __rev1; \	27095	float32x4x2_t __rev1; \
28048	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27096	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28049	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27097	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28050	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 41); \	27098	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 41); \
28051	})	27099	})
28052	#endif	27100	#endif
28053		27101
28054	#ifdef __LITTLE_ENDIAN__	27102	#ifdef __LITTLE_ENDIAN__
28055	#define vst2q_s32(__p0, __p1) __extension__ ({ \	27103	#define vst2q_s32(__p0, __p1) __extension__ ({ \
28056	int32x4x2_t __s1 = __p1; \	27104	int32x4x2_t __s1 = __p1; \
28057	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 34); \	27105	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 34); \
28058	})	27106	})
28059	#else	27107	#else
28060	#define vst2q_s32(__p0, __p1) __extension__ ({ \	27108	#define vst2q_s32(__p0, __p1) __extension__ ({ \
...	@@ -28062,14 +27110,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28062,14 +27110,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28062	int32x4x2_t __rev1; \	27110	int32x4x2_t __rev1; \
28063	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27111	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28064	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27112	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28065	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 34); \	27113	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 34); \
28066	})	27114	})
28067	#endif	27115	#endif
28068		27116
28069	#ifdef __LITTLE_ENDIAN__	27117	#ifdef __LITTLE_ENDIAN__
28070	#define vst2q_s16(__p0, __p1) __extension__ ({ \	27118	#define vst2q_s16(__p0, __p1) __extension__ ({ \
28071	int16x8x2_t __s1 = __p1; \	27119	int16x8x2_t __s1 = __p1; \
28072	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 33); \	27120	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 33); \
28073	})	27121	})
28074	#else	27122	#else
28075	#define vst2q_s16(__p0, __p1) __extension__ ({ \	27123	#define vst2q_s16(__p0, __p1) __extension__ ({ \
...	@@ -28077,7 +27125,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28077,7 +27125,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28077	int16x8x2_t __rev1; \	27125	int16x8x2_t __rev1; \
28078	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	27126	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
28079	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	27127	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
28080	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 33); \	27128	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 33); \
28081	})	27129	})
28082	#endif	27130	#endif
28083		27131
...	@@ -28111,18 +27159,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28111,18 +27159,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28111	})	27159	})
28112	#endif	27160	#endif
28113		27161
28114	#ifdef __LITTLE_ENDIAN__
28115	#define vst2_u64(__p0, __p1) __extension__ ({ \
28116	uint64x1x2_t __s1 = __p1; \
28117	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
28118	})
28119	#else
28120	#define vst2_u64(__p0, __p1) __extension__ ({ \	27162	#define vst2_u64(__p0, __p1) __extension__ ({ \
28121	uint64x1x2_t __s1 = __p1; \	27163	uint64x1x2_t __s1 = __p1; \
28122	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \	27164	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 19); \
28123	})	27165	})
28124	#endif
28125
28126	#ifdef __LITTLE_ENDIAN__	27166	#ifdef __LITTLE_ENDIAN__
28127	#define vst2_u16(__p0, __p1) __extension__ ({ \	27167	#define vst2_u16(__p0, __p1) __extension__ ({ \
28128	uint16x4x2_t __s1 = __p1; \	27168	uint16x4x2_t __s1 = __p1; \
...	@@ -28156,7 +27196,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28156,7 +27196,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28156	#ifdef __LITTLE_ENDIAN__	27196	#ifdef __LITTLE_ENDIAN__
28157	#define vst2_f32(__p0, __p1) __extension__ ({ \	27197	#define vst2_f32(__p0, __p1) __extension__ ({ \
28158	float32x2x2_t __s1 = __p1; \	27198	float32x2x2_t __s1 = __p1; \
28159	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 9); \	27199	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 9); \
28160	})	27200	})
28161	#else	27201	#else
28162	#define vst2_f32(__p0, __p1) __extension__ ({ \	27202	#define vst2_f32(__p0, __p1) __extension__ ({ \
...	@@ -28164,14 +27204,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28164,14 +27204,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28164	float32x2x2_t __rev1; \	27204	float32x2x2_t __rev1; \
28165	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27205	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28166	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27206	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28167	__builtin_neon_vst2_v(__p0, __rev1.val[0], __rev1.val[1], 9); \	27207	__builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 9); \
28168	})	27208	})
28169	#endif	27209	#endif
28170		27210
28171	#ifdef __LITTLE_ENDIAN__	27211	#ifdef __LITTLE_ENDIAN__
28172	#define vst2_s32(__p0, __p1) __extension__ ({ \	27212	#define vst2_s32(__p0, __p1) __extension__ ({ \
28173	int32x2x2_t __s1 = __p1; \	27213	int32x2x2_t __s1 = __p1; \
28174	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 2); \	27214	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 2); \
28175	})	27215	})
28176	#else	27216	#else
28177	#define vst2_s32(__p0, __p1) __extension__ ({ \	27217	#define vst2_s32(__p0, __p1) __extension__ ({ \
...	@@ -28179,26 +27219,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28179,26 +27219,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28179	int32x2x2_t __rev1; \	27219	int32x2x2_t __rev1; \
28180	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27220	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28181	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27221	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28182	__builtin_neon_vst2_v(__p0, __rev1.val[0], __rev1.val[1], 2); \	27222	__builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 2); \
28183	})	27223	})
28184	#endif	27224	#endif
28185		27225
28186	#ifdef __LITTLE_ENDIAN__
28187	#define vst2_s64(__p0, __p1) __extension__ ({ \
28188	int64x1x2_t __s1 = __p1; \
28189	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 3); \
28190	})
28191	#else
28192	#define vst2_s64(__p0, __p1) __extension__ ({ \	27226	#define vst2_s64(__p0, __p1) __extension__ ({ \
28193	int64x1x2_t __s1 = __p1; \	27227	int64x1x2_t __s1 = __p1; \
28194	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 3); \	27228	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 3); \
28195	})	27229	})
28196	#endif
28197
28198	#ifdef __LITTLE_ENDIAN__	27230	#ifdef __LITTLE_ENDIAN__
28199	#define vst2_s16(__p0, __p1) __extension__ ({ \	27231	#define vst2_s16(__p0, __p1) __extension__ ({ \
28200	int16x4x2_t __s1 = __p1; \	27232	int16x4x2_t __s1 = __p1; \
28201	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 1); \	27233	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 1); \
28202	})	27234	})
28203	#else	27235	#else
28204	#define vst2_s16(__p0, __p1) __extension__ ({ \	27236	#define vst2_s16(__p0, __p1) __extension__ ({ \
...	@@ -28206,7 +27238,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28206,7 +27238,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28206	int16x4x2_t __rev1; \	27238	int16x4x2_t __rev1; \
28207	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27239	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28208	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27240	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28209	__builtin_neon_vst2_v(__p0, __rev1.val[0], __rev1.val[1], 1); \	27241	__builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 1); \
28210	})	27242	})
28211	#endif	27243	#endif
28212		27244
...	@@ -28288,7 +27320,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28288,7 +27320,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28288	#ifdef __LITTLE_ENDIAN__	27320	#ifdef __LITTLE_ENDIAN__
28289	#define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27321	#define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
28290	float32x4x2_t __s1 = __p1; \	27322	float32x4x2_t __s1 = __p1; \
28291	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 41); \	27323	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 41); \
28292	})	27324	})
28293	#else	27325	#else
28294	#define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27326	#define vst2q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28296,14 +27328,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28296,14 +27328,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28296	float32x4x2_t __rev1; \	27328	float32x4x2_t __rev1; \
28297	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27329	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28298	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27330	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28299	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 41); \	27331	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 41); \
28300	})	27332	})
28301	#endif	27333	#endif
28302		27334
28303	#ifdef __LITTLE_ENDIAN__	27335	#ifdef __LITTLE_ENDIAN__
28304	#define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27336	#define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
28305	int32x4x2_t __s1 = __p1; \	27337	int32x4x2_t __s1 = __p1; \
28306	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 34); \	27338	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 34); \
28307	})	27339	})
28308	#else	27340	#else
28309	#define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27341	#define vst2q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28311,14 +27343,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28311,14 +27343,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28311	int32x4x2_t __rev1; \	27343	int32x4x2_t __rev1; \
28312	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27344	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28313	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27345	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28314	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 34); \	27346	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 34); \
28315	})	27347	})
28316	#endif	27348	#endif
28317		27349
28318	#ifdef __LITTLE_ENDIAN__	27350	#ifdef __LITTLE_ENDIAN__
28319	#define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27351	#define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
28320	int16x8x2_t __s1 = __p1; \	27352	int16x8x2_t __s1 = __p1; \
28321	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 33); \	27353	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 33); \
28322	})	27354	})
28323	#else	27355	#else
28324	#define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27356	#define vst2q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28326,7 +27358,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28326,7 +27358,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28326	int16x8x2_t __rev1; \	27358	int16x8x2_t __rev1; \
28327	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	27359	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
28328	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	27360	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
28329	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 33); \	27361	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 33); \
28330	})	27362	})
28331	#endif	27363	#endif
28332		27364
...	@@ -28393,7 +27425,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28393,7 +27425,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28393	#ifdef __LITTLE_ENDIAN__	27425	#ifdef __LITTLE_ENDIAN__
28394	#define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27426	#define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
28395	float32x2x2_t __s1 = __p1; \	27427	float32x2x2_t __s1 = __p1; \
28396	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 9); \	27428	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 9); \
28397	})	27429	})
28398	#else	27430	#else
28399	#define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27431	#define vst2_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28401,14 +27433,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28401,14 +27433,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28401	float32x2x2_t __rev1; \	27433	float32x2x2_t __rev1; \
28402	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27434	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28403	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27435	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28404	__builtin_neon_vst2_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 9); \	27436	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 9); \
28405	})	27437	})
28406	#endif	27438	#endif
28407		27439
28408	#ifdef __LITTLE_ENDIAN__	27440	#ifdef __LITTLE_ENDIAN__
28409	#define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27441	#define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
28410	int32x2x2_t __s1 = __p1; \	27442	int32x2x2_t __s1 = __p1; \
28411	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 2); \	27443	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 2); \
28412	})	27444	})
28413	#else	27445	#else
28414	#define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27446	#define vst2_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28416,14 +27448,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28416,14 +27448,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28416	int32x2x2_t __rev1; \	27448	int32x2x2_t __rev1; \
28417	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27449	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28418	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27450	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28419	__builtin_neon_vst2_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 2); \	27451	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 2); \
28420	})	27452	})
28421	#endif	27453	#endif
28422		27454
28423	#ifdef __LITTLE_ENDIAN__	27455	#ifdef __LITTLE_ENDIAN__
28424	#define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27456	#define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
28425	int16x4x2_t __s1 = __p1; \	27457	int16x4x2_t __s1 = __p1; \
28426	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 1); \	27458	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 1); \
28427	})	27459	})
28428	#else	27460	#else
28429	#define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27461	#define vst2_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28431,7 +27463,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28431,7 +27463,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28431	int16x4x2_t __rev1; \	27463	int16x4x2_t __rev1; \
28432	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27464	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28433	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27465	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28434	__builtin_neon_vst2_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 1); \	27466	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 1); \
28435	})	27467	})
28436	#endif	27468	#endif
28437		27469
...	@@ -28566,7 +27598,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28566,7 +27598,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28566	#ifdef __LITTLE_ENDIAN__	27598	#ifdef __LITTLE_ENDIAN__
28567	#define vst3q_f32(__p0, __p1) __extension__ ({ \	27599	#define vst3q_f32(__p0, __p1) __extension__ ({ \
28568	float32x4x3_t __s1 = __p1; \	27600	float32x4x3_t __s1 = __p1; \
28569	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 41); \	27601	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 41); \
28570	})	27602	})
28571	#else	27603	#else
28572	#define vst3q_f32(__p0, __p1) __extension__ ({ \	27604	#define vst3q_f32(__p0, __p1) __extension__ ({ \
...	@@ -28575,14 +27607,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28575,14 +27607,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28575	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27607	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28576	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27608	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28577	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	27609	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28578	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 41); \	27610	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 41); \
28579	})	27611	})
28580	#endif	27612	#endif
28581		27613
28582	#ifdef __LITTLE_ENDIAN__	27614	#ifdef __LITTLE_ENDIAN__
28583	#define vst3q_s32(__p0, __p1) __extension__ ({ \	27615	#define vst3q_s32(__p0, __p1) __extension__ ({ \
28584	int32x4x3_t __s1 = __p1; \	27616	int32x4x3_t __s1 = __p1; \
28585	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 34); \	27617	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 34); \
28586	})	27618	})
28587	#else	27619	#else
28588	#define vst3q_s32(__p0, __p1) __extension__ ({ \	27620	#define vst3q_s32(__p0, __p1) __extension__ ({ \
...	@@ -28591,14 +27623,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28591,14 +27623,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28591	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27623	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28592	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27624	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28593	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	27625	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28594	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 34); \	27626	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 34); \
28595	})	27627	})
28596	#endif	27628	#endif
28597		27629
28598	#ifdef __LITTLE_ENDIAN__	27630	#ifdef __LITTLE_ENDIAN__
28599	#define vst3q_s16(__p0, __p1) __extension__ ({ \	27631	#define vst3q_s16(__p0, __p1) __extension__ ({ \
28600	int16x8x3_t __s1 = __p1; \	27632	int16x8x3_t __s1 = __p1; \
28601	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 33); \	27633	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 33); \
28602	})	27634	})
28603	#else	27635	#else
28604	#define vst3q_s16(__p0, __p1) __extension__ ({ \	27636	#define vst3q_s16(__p0, __p1) __extension__ ({ \
...	@@ -28607,7 +27639,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28607,7 +27639,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28607	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	27639	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
28608	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	27640	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
28609	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	27641	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
28610	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 33); \	27642	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 33); \
28611	})	27643	})
28612	#endif	27644	#endif
28613		27645
...	@@ -28643,18 +27675,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28643,18 +27675,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28643	})	27675	})
28644	#endif	27676	#endif
28645		27677
28646	#ifdef __LITTLE_ENDIAN__
28647	#define vst3_u64(__p0, __p1) __extension__ ({ \
28648	uint64x1x3_t __s1 = __p1; \
28649	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
28650	})
28651	#else
28652	#define vst3_u64(__p0, __p1) __extension__ ({ \	27678	#define vst3_u64(__p0, __p1) __extension__ ({ \
28653	uint64x1x3_t __s1 = __p1; \	27679	uint64x1x3_t __s1 = __p1; \
28654	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \	27680	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 19); \
28655	})	27681	})
28656	#endif
28657
28658	#ifdef __LITTLE_ENDIAN__	27682	#ifdef __LITTLE_ENDIAN__
28659	#define vst3_u16(__p0, __p1) __extension__ ({ \	27683	#define vst3_u16(__p0, __p1) __extension__ ({ \
28660	uint16x4x3_t __s1 = __p1; \	27684	uint16x4x3_t __s1 = __p1; \
...	@@ -28690,7 +27714,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28690,7 +27714,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28690	#ifdef __LITTLE_ENDIAN__	27714	#ifdef __LITTLE_ENDIAN__
28691	#define vst3_f32(__p0, __p1) __extension__ ({ \	27715	#define vst3_f32(__p0, __p1) __extension__ ({ \
28692	float32x2x3_t __s1 = __p1; \	27716	float32x2x3_t __s1 = __p1; \
28693	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 9); \	27717	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 9); \
28694	})	27718	})
28695	#else	27719	#else
28696	#define vst3_f32(__p0, __p1) __extension__ ({ \	27720	#define vst3_f32(__p0, __p1) __extension__ ({ \
...	@@ -28699,14 +27723,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28699,14 +27723,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28699	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27723	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28700	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27724	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28701	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	27725	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
28702	__builtin_neon_vst3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 9); \	27726	__builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 9); \
28703	})	27727	})
28704	#endif	27728	#endif
28705		27729
28706	#ifdef __LITTLE_ENDIAN__	27730	#ifdef __LITTLE_ENDIAN__
28707	#define vst3_s32(__p0, __p1) __extension__ ({ \	27731	#define vst3_s32(__p0, __p1) __extension__ ({ \
28708	int32x2x3_t __s1 = __p1; \	27732	int32x2x3_t __s1 = __p1; \
28709	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 2); \	27733	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 2); \
28710	})	27734	})
28711	#else	27735	#else
28712	#define vst3_s32(__p0, __p1) __extension__ ({ \	27736	#define vst3_s32(__p0, __p1) __extension__ ({ \
...	@@ -28715,26 +27739,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28715,26 +27739,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28715	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27739	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28716	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27740	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28717	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	27741	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
28718	__builtin_neon_vst3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 2); \	27742	__builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 2); \
28719	})	27743	})
28720	#endif	27744	#endif
28721		27745
28722	#ifdef __LITTLE_ENDIAN__
28723	#define vst3_s64(__p0, __p1) __extension__ ({ \
28724	int64x1x3_t __s1 = __p1; \
28725	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 3); \
28726	})
28727	#else
28728	#define vst3_s64(__p0, __p1) __extension__ ({ \	27746	#define vst3_s64(__p0, __p1) __extension__ ({ \
28729	int64x1x3_t __s1 = __p1; \	27747	int64x1x3_t __s1 = __p1; \
28730	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 3); \	27748	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 3); \
28731	})	27749	})
28732	#endif
28733
28734	#ifdef __LITTLE_ENDIAN__	27750	#ifdef __LITTLE_ENDIAN__
28735	#define vst3_s16(__p0, __p1) __extension__ ({ \	27751	#define vst3_s16(__p0, __p1) __extension__ ({ \
28736	int16x4x3_t __s1 = __p1; \	27752	int16x4x3_t __s1 = __p1; \
28737	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 1); \	27753	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 1); \
28738	})	27754	})
28739	#else	27755	#else
28740	#define vst3_s16(__p0, __p1) __extension__ ({ \	27756	#define vst3_s16(__p0, __p1) __extension__ ({ \
...	@@ -28743,7 +27759,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28743,7 +27759,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28743	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27759	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28744	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27760	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28745	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	27761	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28746	__builtin_neon_vst3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 1); \	27762	__builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 1); \
28747	})	27763	})
28748	#endif	27764	#endif
28749		27765
...	@@ -28830,7 +27846,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28830,7 +27846,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28830	#ifdef __LITTLE_ENDIAN__	27846	#ifdef __LITTLE_ENDIAN__
28831	#define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27847	#define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
28832	float32x4x3_t __s1 = __p1; \	27848	float32x4x3_t __s1 = __p1; \
28833	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 41); \	27849	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 41); \
28834	})	27850	})
28835	#else	27851	#else
28836	#define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27852	#define vst3q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28839,14 +27855,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28839,14 +27855,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28839	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27855	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28840	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27856	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28841	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	27857	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28842	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 41); \	27858	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 41); \
28843	})	27859	})
28844	#endif	27860	#endif
28845		27861
28846	#ifdef __LITTLE_ENDIAN__	27862	#ifdef __LITTLE_ENDIAN__
28847	#define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27863	#define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
28848	int32x4x3_t __s1 = __p1; \	27864	int32x4x3_t __s1 = __p1; \
28849	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 34); \	27865	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 34); \
28850	})	27866	})
28851	#else	27867	#else
28852	#define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27868	#define vst3q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28855,14 +27871,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28855,14 +27871,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28855	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27871	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28856	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	27872	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28857	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	27873	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28858	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 34); \	27874	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 34); \
28859	})	27875	})
28860	#endif	27876	#endif
28861		27877
28862	#ifdef __LITTLE_ENDIAN__	27878	#ifdef __LITTLE_ENDIAN__
28863	#define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27879	#define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
28864	int16x8x3_t __s1 = __p1; \	27880	int16x8x3_t __s1 = __p1; \
28865	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 33); \	27881	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 33); \
28866	})	27882	})
28867	#else	27883	#else
28868	#define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27884	#define vst3q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28871,7 +27887,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28871,7 +27887,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28871	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	27887	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
28872	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	27888	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
28873	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	27889	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
28874	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 33); \	27890	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 33); \
28875	})	27891	})
28876	#endif	27892	#endif
28877		27893
...	@@ -28942,7 +27958,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28942,7 +27958,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28942	#ifdef __LITTLE_ENDIAN__	27958	#ifdef __LITTLE_ENDIAN__
28943	#define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27959	#define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
28944	float32x2x3_t __s1 = __p1; \	27960	float32x2x3_t __s1 = __p1; \
28945	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 9); \	27961	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 9); \
28946	})	27962	})
28947	#else	27963	#else
28948	#define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \	27964	#define vst3_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28951,14 +27967,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28951,14 +27967,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28951	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27967	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28952	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27968	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28953	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	27969	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
28954	__builtin_neon_vst3_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 9); \	27970	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 9); \
28955	})	27971	})
28956	#endif	27972	#endif
28957		27973
28958	#ifdef __LITTLE_ENDIAN__	27974	#ifdef __LITTLE_ENDIAN__
28959	#define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27975	#define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
28960	int32x2x3_t __s1 = __p1; \	27976	int32x2x3_t __s1 = __p1; \
28961	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 2); \	27977	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 2); \
28962	})	27978	})
28963	#else	27979	#else
28964	#define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \	27980	#define vst3_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28967,14 +27983,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28967,14 +27983,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28967	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	27983	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
28968	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	27984	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
28969	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	27985	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
28970	__builtin_neon_vst3_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 2); \	27986	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 2); \
28971	})	27987	})
28972	#endif	27988	#endif
28973		27989
28974	#ifdef __LITTLE_ENDIAN__	27990	#ifdef __LITTLE_ENDIAN__
28975	#define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27991	#define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
28976	int16x4x3_t __s1 = __p1; \	27992	int16x4x3_t __s1 = __p1; \
28977	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 1); \	27993	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 1); \
28978	})	27994	})
28979	#else	27995	#else
28980	#define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \	27996	#define vst3_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -28983,7 +27999,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -28983,7 +27999,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
28983	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	27999	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
28984	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28000	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
28985	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28001	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
28986	__builtin_neon_vst3_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 1); \	28002	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 1); \
28987	})	28003	})
28988	#endif	28004	#endif
28989		28005
...	@@ -29126,7 +28142,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29126,7 +28142,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29126	#ifdef __LITTLE_ENDIAN__	28142	#ifdef __LITTLE_ENDIAN__
29127	#define vst4q_f32(__p0, __p1) __extension__ ({ \	28143	#define vst4q_f32(__p0, __p1) __extension__ ({ \
29128	float32x4x4_t __s1 = __p1; \	28144	float32x4x4_t __s1 = __p1; \
29129	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 41); \	28145	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 41); \
29130	})	28146	})
29131	#else	28147	#else
29132	#define vst4q_f32(__p0, __p1) __extension__ ({ \	28148	#define vst4q_f32(__p0, __p1) __extension__ ({ \
...	@@ -29136,14 +28152,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29136,14 +28152,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29136	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28152	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29137	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28153	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29138	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28154	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29139	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 41); \	28155	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 41); \
29140	})	28156	})
29141	#endif	28157	#endif
29142		28158
29143	#ifdef __LITTLE_ENDIAN__	28159	#ifdef __LITTLE_ENDIAN__
29144	#define vst4q_s32(__p0, __p1) __extension__ ({ \	28160	#define vst4q_s32(__p0, __p1) __extension__ ({ \
29145	int32x4x4_t __s1 = __p1; \	28161	int32x4x4_t __s1 = __p1; \
29146	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 34); \	28162	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 34); \
29147	})	28163	})
29148	#else	28164	#else
29149	#define vst4q_s32(__p0, __p1) __extension__ ({ \	28165	#define vst4q_s32(__p0, __p1) __extension__ ({ \
...	@@ -29153,14 +28169,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29153,14 +28169,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29153	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28169	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29154	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28170	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29155	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28171	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29156	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 34); \	28172	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 34); \
29157	})	28173	})
29158	#endif	28174	#endif
29159		28175
29160	#ifdef __LITTLE_ENDIAN__	28176	#ifdef __LITTLE_ENDIAN__
29161	#define vst4q_s16(__p0, __p1) __extension__ ({ \	28177	#define vst4q_s16(__p0, __p1) __extension__ ({ \
29162	int16x8x4_t __s1 = __p1; \	28178	int16x8x4_t __s1 = __p1; \
29163	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 33); \	28179	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 33); \
29164	})	28180	})
29165	#else	28181	#else
29166	#define vst4q_s16(__p0, __p1) __extension__ ({ \	28182	#define vst4q_s16(__p0, __p1) __extension__ ({ \
...	@@ -29170,7 +28186,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29170,7 +28186,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29170	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	28186	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
29171	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	28187	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
29172	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	28188	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
29173	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 33); \	28189	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 33); \
29174	})	28190	})
29175	#endif	28191	#endif
29176		28192
...	@@ -29208,18 +28224,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29208,18 +28224,10 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29208	})	28224	})
29209	#endif	28225	#endif
29210		28226
29211	#ifdef __LITTLE_ENDIAN__
29212	#define vst4_u64(__p0, __p1) __extension__ ({ \	28227	#define vst4_u64(__p0, __p1) __extension__ ({ \
29213	uint64x1x4_t __s1 = __p1; \	28228	uint64x1x4_t __s1 = __p1; \
29214	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \	28229	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
29215	})	28230	})
29216	#else
29217	#define vst4_u64(__p0, __p1) __extension__ ({ \
29218	uint64x1x4_t __s1 = __p1; \
29219	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 19); \
29220	})
29221	#endif
29222
29223	#ifdef __LITTLE_ENDIAN__	28231	#ifdef __LITTLE_ENDIAN__
29224	#define vst4_u16(__p0, __p1) __extension__ ({ \	28232	#define vst4_u16(__p0, __p1) __extension__ ({ \
29225	uint16x4x4_t __s1 = __p1; \	28233	uint16x4x4_t __s1 = __p1; \
...	@@ -29257,7 +28265,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29257,7 +28265,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29257	#ifdef __LITTLE_ENDIAN__	28265	#ifdef __LITTLE_ENDIAN__
29258	#define vst4_f32(__p0, __p1) __extension__ ({ \	28266	#define vst4_f32(__p0, __p1) __extension__ ({ \
29259	float32x2x4_t __s1 = __p1; \	28267	float32x2x4_t __s1 = __p1; \
29260	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 9); \	28268	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 9); \
29261	})	28269	})
29262	#else	28270	#else
29263	#define vst4_f32(__p0, __p1) __extension__ ({ \	28271	#define vst4_f32(__p0, __p1) __extension__ ({ \
...	@@ -29267,14 +28275,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29267,14 +28275,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29267	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	28275	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
29268	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	28276	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
29269	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	28277	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
29270	__builtin_neon_vst4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 9); \	28278	__builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 9); \
29271	})	28279	})
29272	#endif	28280	#endif
29273		28281
29274	#ifdef __LITTLE_ENDIAN__	28282	#ifdef __LITTLE_ENDIAN__
29275	#define vst4_s32(__p0, __p1) __extension__ ({ \	28283	#define vst4_s32(__p0, __p1) __extension__ ({ \
29276	int32x2x4_t __s1 = __p1; \	28284	int32x2x4_t __s1 = __p1; \
29277	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 2); \	28285	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 2); \
29278	})	28286	})
29279	#else	28287	#else
29280	#define vst4_s32(__p0, __p1) __extension__ ({ \	28288	#define vst4_s32(__p0, __p1) __extension__ ({ \
...	@@ -29284,26 +28292,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29284,26 +28292,18 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29284	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	28292	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
29285	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	28293	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
29286	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	28294	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
29287	__builtin_neon_vst4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 2); \	28295	__builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 2); \
29288	})	28296	})
29289	#endif	28297	#endif
29290		28298
29291	#ifdef __LITTLE_ENDIAN__
29292	#define vst4_s64(__p0, __p1) __extension__ ({ \	28299	#define vst4_s64(__p0, __p1) __extension__ ({ \
29293	int64x1x4_t __s1 = __p1; \	28300	int64x1x4_t __s1 = __p1; \
29294	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 3); \	28301	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 3); \
29295	})	28302	})
29296	#else
29297	#define vst4_s64(__p0, __p1) __extension__ ({ \
29298	int64x1x4_t __s1 = __p1; \
29299	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 3); \
29300	})
29301	#endif
29302
29303	#ifdef __LITTLE_ENDIAN__	28303	#ifdef __LITTLE_ENDIAN__
29304	#define vst4_s16(__p0, __p1) __extension__ ({ \	28304	#define vst4_s16(__p0, __p1) __extension__ ({ \
29305	int16x4x4_t __s1 = __p1; \	28305	int16x4x4_t __s1 = __p1; \
29306	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 1); \	28306	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 1); \
29307	})	28307	})
29308	#else	28308	#else
29309	#define vst4_s16(__p0, __p1) __extension__ ({ \	28309	#define vst4_s16(__p0, __p1) __extension__ ({ \
...	@@ -29313,7 +28313,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29313,7 +28313,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29313	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28313	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29314	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28314	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29315	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28315	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29316	__builtin_neon_vst4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 1); \	28316	__builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 1); \
29317	})	28317	})
29318	#endif	28318	#endif
29319		28319
...	@@ -29405,7 +28405,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29405,7 +28405,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29405	#ifdef __LITTLE_ENDIAN__	28405	#ifdef __LITTLE_ENDIAN__
29406	#define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	28406	#define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
29407	float32x4x4_t __s1 = __p1; \	28407	float32x4x4_t __s1 = __p1; \
29408	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 41); \	28408	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 41); \
29409	})	28409	})
29410	#else	28410	#else
29411	#define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \	28411	#define vst4q_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29415,14 +28415,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29415,14 +28415,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29415	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28415	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29416	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28416	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29417	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28417	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29418	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 41); \	28418	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 41); \
29419	})	28419	})
29420	#endif	28420	#endif
29421		28421
29422	#ifdef __LITTLE_ENDIAN__	28422	#ifdef __LITTLE_ENDIAN__
29423	#define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	28423	#define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
29424	int32x4x4_t __s1 = __p1; \	28424	int32x4x4_t __s1 = __p1; \
29425	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 34); \	28425	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 34); \
29426	})	28426	})
29427	#else	28427	#else
29428	#define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \	28428	#define vst4q_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29432,14 +28432,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29432,14 +28432,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29432	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28432	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29433	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28433	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29434	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28434	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29435	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 34); \	28435	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 34); \
29436	})	28436	})
29437	#endif	28437	#endif
29438		28438
29439	#ifdef __LITTLE_ENDIAN__	28439	#ifdef __LITTLE_ENDIAN__
29440	#define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	28440	#define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
29441	int16x8x4_t __s1 = __p1; \	28441	int16x8x4_t __s1 = __p1; \
29442	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 33); \	28442	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 33); \
29443	})	28443	})
29444	#else	28444	#else
29445	#define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \	28445	#define vst4q_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29449,7 +28449,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29449,7 +28449,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29449	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	28449	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
29450	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	28450	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
29451	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	28451	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
29452	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 33); \	28452	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 33); \
29453	})	28453	})
29454	#endif	28454	#endif
29455		28455
...	@@ -29524,7 +28524,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29524,7 +28524,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29524	#ifdef __LITTLE_ENDIAN__	28524	#ifdef __LITTLE_ENDIAN__
29525	#define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \	28525	#define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
29526	float32x2x4_t __s1 = __p1; \	28526	float32x2x4_t __s1 = __p1; \
29527	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 9); \	28527	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 9); \
29528	})	28528	})
29529	#else	28529	#else
29530	#define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \	28530	#define vst4_lane_f32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29534,14 +28534,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29534,14 +28534,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29534	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	28534	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
29535	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	28535	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
29536	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	28536	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
29537	__builtin_neon_vst4_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 9); \	28537	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 9); \
29538	})	28538	})
29539	#endif	28539	#endif
29540		28540
29541	#ifdef __LITTLE_ENDIAN__	28541	#ifdef __LITTLE_ENDIAN__
29542	#define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \	28542	#define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
29543	int32x2x4_t __s1 = __p1; \	28543	int32x2x4_t __s1 = __p1; \
29544	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 2); \	28544	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 2); \
29545	})	28545	})
29546	#else	28546	#else
29547	#define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \	28547	#define vst4_lane_s32(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29551,14 +28551,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29551,14 +28551,14 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29551	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	28551	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
29552	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	28552	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
29553	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	28553	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
29554	__builtin_neon_vst4_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 2); \	28554	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 2); \
29555	})	28555	})
29556	#endif	28556	#endif
29557		28557
29558	#ifdef __LITTLE_ENDIAN__	28558	#ifdef __LITTLE_ENDIAN__
29559	#define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \	28559	#define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
29560	int16x4x4_t __s1 = __p1; \	28560	int16x4x4_t __s1 = __p1; \
29561	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 1); \	28561	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 1); \
29562	})	28562	})
29563	#else	28563	#else
29564	#define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \	28564	#define vst4_lane_s16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -29568,7 +28568,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -29568,7 +28568,7 @@ __ai int16x4_t vshl_s16(int16x4_t __p0, int16x4_t __p1) {
29568	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	28568	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
29569	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	28569	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
29570	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	28570	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
29571	__builtin_neon_vst4_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 1); \	28571	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 1); \
29572	})	28572	})
29573	#endif	28573	#endif
29574		28574
...	@@ -29759,20 +28759,11 @@ __ai uint32x2_t vsub_u32(uint32x2_t __p0, uint32x2_t __p1) {	...	@@ -29759,20 +28759,11 @@ __ai uint32x2_t vsub_u32(uint32x2_t __p0, uint32x2_t __p1) {
29759	}	28759	}
29760	#endif	28760	#endif
29761		28761
29762	#ifdef __LITTLE_ENDIAN__
29763	__ai uint64x1_t vsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
29764	uint64x1_t __ret;
29765	__ret = __p0 - __p1;
29766	return __ret;
29767	}
29768	#else
29769	__ai uint64x1_t vsub_u64(uint64x1_t __p0, uint64x1_t __p1) {	28762	__ai uint64x1_t vsub_u64(uint64x1_t __p0, uint64x1_t __p1) {
29770	uint64x1_t __ret;	28763	uint64x1_t __ret;
29771	__ret = __p0 - __p1;	28764	__ret = __p0 - __p1;
29772	return __ret;	28765	return __ret;
29773	}	28766	}
29774	#endif
29775
29776	#ifdef __LITTLE_ENDIAN__	28767	#ifdef __LITTLE_ENDIAN__
29777	__ai uint16x4_t vsub_u16(uint16x4_t __p0, uint16x4_t __p1) {	28768	__ai uint16x4_t vsub_u16(uint16x4_t __p0, uint16x4_t __p1) {
29778	uint16x4_t __ret;	28769	uint16x4_t __ret;
...	@@ -29841,20 +28832,11 @@ __ai int32x2_t vsub_s32(int32x2_t __p0, int32x2_t __p1) {	...	@@ -29841,20 +28832,11 @@ __ai int32x2_t vsub_s32(int32x2_t __p0, int32x2_t __p1) {
29841	}	28832	}
29842	#endif	28833	#endif
29843		28834
29844	#ifdef __LITTLE_ENDIAN__
29845	__ai int64x1_t vsub_s64(int64x1_t __p0, int64x1_t __p1) {	28835	__ai int64x1_t vsub_s64(int64x1_t __p0, int64x1_t __p1) {
29846	int64x1_t __ret;	28836	int64x1_t __ret;
29847	__ret = __p0 - __p1;	28837	__ret = __p0 - __p1;
29848	return __ret;	28838	return __ret;
29849	}	28839	}
29850	#else
29851	__ai int64x1_t vsub_s64(int64x1_t __p0, int64x1_t __p1) {
29852	int64x1_t __ret;
29853	__ret = __p0 - __p1;
29854	return __ret;
29855	}
29856	#endif
29857
29858	#ifdef __LITTLE_ENDIAN__	28840	#ifdef __LITTLE_ENDIAN__
29859	__ai int16x4_t vsub_s16(int16x4_t __p0, int16x4_t __p1) {	28841	__ai int16x4_t vsub_s16(int16x4_t __p0, int16x4_t __p1) {
29860	int16x4_t __ret;	28842	int16x4_t __ret;
...	@@ -32085,3721 +31067,1345 @@ __ai int16x4x2_t vzip_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -32085,3721 +31067,1345 @@ __ai int16x4x2_t vzip_s16(int16x4_t __p0, int16x4_t __p1) {
32085	})	31067	})
32086	#endif	31068	#endif
32087		31069
32088	#ifdef __LITTLE_ENDIAN__
32089	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {
32090	poly8x8_t __ret;
32091	__ret = (poly8x8_t)(__p0);
32092	return __ret;
32093	}
32094	#else
32095	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {	31070	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {
32096	poly8x8_t __ret;	31071	poly8x8_t __ret;
32097	__ret = (poly8x8_t)(__p0);	31072	__ret = (poly8x8_t)(__p0);
32098	return __ret;	31073	return __ret;
32099	}	31074	}
32100	#endif
32101
32102	#ifdef __LITTLE_ENDIAN__
32103	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {
32104	poly8x8_t __ret;
32105	__ret = (poly8x8_t)(__p0);
32106	return __ret;
32107	}
32108	#else
32109	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {	31075	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {
32110	poly8x8_t __ret;	31076	poly8x8_t __ret;
32111	__ret = (poly8x8_t)(__p0);	31077	__ret = (poly8x8_t)(__p0);
32112	return __ret;	31078	return __ret;
32113	}	31079	}
32114	#endif
32115
32116	#ifdef __LITTLE_ENDIAN__
32117	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {
32118	poly8x8_t __ret;
32119	__ret = (poly8x8_t)(__p0);
32120	return __ret;
32121	}
32122	#else
32123	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {	31080	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {
32124	poly8x8_t __ret;	31081	poly8x8_t __ret;
32125	__ret = (poly8x8_t)(__p0);	31082	__ret = (poly8x8_t)(__p0);
32126	return __ret;	31083	return __ret;
32127	}	31084	}
32128	#endif
32129
32130	#ifdef __LITTLE_ENDIAN__
32131	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {
32132	poly8x8_t __ret;
32133	__ret = (poly8x8_t)(__p0);
32134	return __ret;
32135	}
32136	#else
32137	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {	31085	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {
32138	poly8x8_t __ret;	31086	poly8x8_t __ret;
32139	__ret = (poly8x8_t)(__p0);	31087	__ret = (poly8x8_t)(__p0);
32140	return __ret;	31088	return __ret;
32141	}	31089	}
32142	#endif
32143
32144	#ifdef __LITTLE_ENDIAN__
32145	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {
32146	poly8x8_t __ret;
32147	__ret = (poly8x8_t)(__p0);
32148	return __ret;
32149	}
32150	#else
32151	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {	31090	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {
32152	poly8x8_t __ret;	31091	poly8x8_t __ret;
32153	__ret = (poly8x8_t)(__p0);	31092	__ret = (poly8x8_t)(__p0);
32154	return __ret;	31093	return __ret;
32155	}	31094	}
32156	#endif
32157
32158	#ifdef __LITTLE_ENDIAN__
32159	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
32160	poly8x8_t __ret;
32161	__ret = (poly8x8_t)(__p0);
32162	return __ret;
32163	}
32164	#else
32165	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {	31095	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
32166	poly8x8_t __ret;	31096	poly8x8_t __ret;
32167	__ret = (poly8x8_t)(__p0);	31097	__ret = (poly8x8_t)(__p0);
32168	return __ret;	31098	return __ret;
32169	}	31099	}
32170	#endif
32171
32172	#ifdef __LITTLE_ENDIAN__
32173	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {
32174	poly8x8_t __ret;
32175	__ret = (poly8x8_t)(__p0);
32176	return __ret;
32177	}
32178	#else
32179	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {	31100	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {
32180	poly8x8_t __ret;	31101	poly8x8_t __ret;
32181	__ret = (poly8x8_t)(__p0);	31102	__ret = (poly8x8_t)(__p0);
32182	return __ret;	31103	return __ret;
32183	}	31104	}
32184	#endif
32185
32186	#ifdef __LITTLE_ENDIAN__
32187	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {
32188	poly8x8_t __ret;
32189	__ret = (poly8x8_t)(__p0);
32190	return __ret;
32191	}
32192	#else
32193	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {	31105	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {
32194	poly8x8_t __ret;	31106	poly8x8_t __ret;
32195	__ret = (poly8x8_t)(__p0);	31107	__ret = (poly8x8_t)(__p0);
32196	return __ret;	31108	return __ret;
32197	}	31109	}
32198	#endif
32199
32200	#ifdef __LITTLE_ENDIAN__
32201	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {
32202	poly8x8_t __ret;
32203	__ret = (poly8x8_t)(__p0);
32204	return __ret;
32205	}
32206	#else
32207	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {	31110	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {
32208	poly8x8_t __ret;	31111	poly8x8_t __ret;
32209	__ret = (poly8x8_t)(__p0);	31112	__ret = (poly8x8_t)(__p0);
32210	return __ret;	31113	return __ret;
32211	}	31114	}
32212	#endif
32213
32214	#ifdef __LITTLE_ENDIAN__
32215	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {
32216	poly8x8_t __ret;
32217	__ret = (poly8x8_t)(__p0);
32218	return __ret;
32219	}
32220	#else
32221	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {	31115	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {
32222	poly8x8_t __ret;	31116	poly8x8_t __ret;
32223	__ret = (poly8x8_t)(__p0);	31117	__ret = (poly8x8_t)(__p0);
32224	return __ret;	31118	return __ret;
32225	}	31119	}
32226	#endif
32227
32228	#ifdef __LITTLE_ENDIAN__
32229	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {
32230	poly8x8_t __ret;
32231	__ret = (poly8x8_t)(__p0);
32232	return __ret;
32233	}
32234	#else
32235	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {	31120	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {
32236	poly8x8_t __ret;	31121	poly8x8_t __ret;
32237	__ret = (poly8x8_t)(__p0);	31122	__ret = (poly8x8_t)(__p0);
32238	return __ret;	31123	return __ret;
32239	}	31124	}
32240	#endif
32241
32242	#ifdef __LITTLE_ENDIAN__
32243	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {
32244	poly16x4_t __ret;
32245	__ret = (poly16x4_t)(__p0);
32246	return __ret;
32247	}
32248	#else
32249	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {	31125	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {
32250	poly16x4_t __ret;	31126	poly16x4_t __ret;
32251	__ret = (poly16x4_t)(__p0);	31127	__ret = (poly16x4_t)(__p0);
32252	return __ret;	31128	return __ret;
32253	}	31129	}
32254	#endif
32255
32256	#ifdef __LITTLE_ENDIAN__
32257	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {
32258	poly16x4_t __ret;
32259	__ret = (poly16x4_t)(__p0);
32260	return __ret;
32261	}
32262	#else
32263	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {	31130	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {
32264	poly16x4_t __ret;	31131	poly16x4_t __ret;
32265	__ret = (poly16x4_t)(__p0);	31132	__ret = (poly16x4_t)(__p0);
32266	return __ret;	31133	return __ret;
32267	}	31134	}
32268	#endif
32269
32270	#ifdef __LITTLE_ENDIAN__
32271	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {
32272	poly16x4_t __ret;
32273	__ret = (poly16x4_t)(__p0);
32274	return __ret;
32275	}
32276	#else
32277	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {	31135	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {
32278	poly16x4_t __ret;	31136	poly16x4_t __ret;
32279	__ret = (poly16x4_t)(__p0);	31137	__ret = (poly16x4_t)(__p0);
32280	return __ret;	31138	return __ret;
32281	}	31139	}
32282	#endif
32283
32284	#ifdef __LITTLE_ENDIAN__
32285	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {
32286	poly16x4_t __ret;
32287	__ret = (poly16x4_t)(__p0);
32288	return __ret;
32289	}
32290	#else
32291	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {	31140	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {
32292	poly16x4_t __ret;	31141	poly16x4_t __ret;
32293	__ret = (poly16x4_t)(__p0);	31142	__ret = (poly16x4_t)(__p0);
32294	return __ret;	31143	return __ret;
32295	}	31144	}
32296	#endif
32297
32298	#ifdef __LITTLE_ENDIAN__
32299	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {
32300	poly16x4_t __ret;
32301	__ret = (poly16x4_t)(__p0);
32302	return __ret;
32303	}
32304	#else
32305	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {	31145	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {
32306	poly16x4_t __ret;	31146	poly16x4_t __ret;
32307	__ret = (poly16x4_t)(__p0);	31147	__ret = (poly16x4_t)(__p0);
32308	return __ret;	31148	return __ret;
32309	}	31149	}
32310	#endif
32311
32312	#ifdef __LITTLE_ENDIAN__
32313	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
32314	poly16x4_t __ret;
32315	__ret = (poly16x4_t)(__p0);
32316	return __ret;
32317	}
32318	#else
32319	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {	31150	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
32320	poly16x4_t __ret;	31151	poly16x4_t __ret;
32321	__ret = (poly16x4_t)(__p0);	31152	__ret = (poly16x4_t)(__p0);
32322	return __ret;	31153	return __ret;
32323	}	31154	}
32324	#endif
32325
32326	#ifdef __LITTLE_ENDIAN__
32327	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {
32328	poly16x4_t __ret;
32329	__ret = (poly16x4_t)(__p0);
32330	return __ret;
32331	}
32332	#else
32333	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {	31155	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {
32334	poly16x4_t __ret;	31156	poly16x4_t __ret;
32335	__ret = (poly16x4_t)(__p0);	31157	__ret = (poly16x4_t)(__p0);
32336	return __ret;	31158	return __ret;
32337	}	31159	}
32338	#endif
32339
32340	#ifdef __LITTLE_ENDIAN__
32341	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {
32342	poly16x4_t __ret;
32343	__ret = (poly16x4_t)(__p0);
32344	return __ret;
32345	}
32346	#else
32347	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {	31160	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {
32348	poly16x4_t __ret;	31161	poly16x4_t __ret;
32349	__ret = (poly16x4_t)(__p0);	31162	__ret = (poly16x4_t)(__p0);
32350	return __ret;	31163	return __ret;
32351	}	31164	}
32352	#endif
32353
32354	#ifdef __LITTLE_ENDIAN__
32355	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {
32356	poly16x4_t __ret;
32357	__ret = (poly16x4_t)(__p0);
32358	return __ret;
32359	}
32360	#else
32361	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {	31165	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {
32362	poly16x4_t __ret;	31166	poly16x4_t __ret;
32363	__ret = (poly16x4_t)(__p0);	31167	__ret = (poly16x4_t)(__p0);
32364	return __ret;	31168	return __ret;
32365	}	31169	}
32366	#endif
32367
32368	#ifdef __LITTLE_ENDIAN__
32369	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {
32370	poly16x4_t __ret;
32371	__ret = (poly16x4_t)(__p0);
32372	return __ret;
32373	}
32374	#else
32375	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {	31170	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {
32376	poly16x4_t __ret;	31171	poly16x4_t __ret;
32377	__ret = (poly16x4_t)(__p0);	31172	__ret = (poly16x4_t)(__p0);
32378	return __ret;	31173	return __ret;
32379	}	31174	}
32380	#endif
32381
32382	#ifdef __LITTLE_ENDIAN__
32383	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {
32384	poly16x4_t __ret;
32385	__ret = (poly16x4_t)(__p0);
32386	return __ret;
32387	}
32388	#else
32389	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {	31175	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {
32390	poly16x4_t __ret;	31176	poly16x4_t __ret;
32391	__ret = (poly16x4_t)(__p0);	31177	__ret = (poly16x4_t)(__p0);
32392	return __ret;	31178	return __ret;
32393	}	31179	}
32394	#endif
32395
32396	#ifdef __LITTLE_ENDIAN__
32397	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {
32398	poly8x16_t __ret;
32399	__ret = (poly8x16_t)(__p0);
32400	return __ret;
32401	}
32402	#else
32403	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {	31180	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {
32404	poly8x16_t __ret;	31181	poly8x16_t __ret;
32405	__ret = (poly8x16_t)(__p0);	31182	__ret = (poly8x16_t)(__p0);
32406	return __ret;	31183	return __ret;
32407	}	31184	}
32408	#endif
32409
32410	#ifdef __LITTLE_ENDIAN__
32411	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {
32412	poly8x16_t __ret;
32413	__ret = (poly8x16_t)(__p0);
32414	return __ret;
32415	}
32416	#else
32417	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {	31185	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {
32418	poly8x16_t __ret;	31186	poly8x16_t __ret;
32419	__ret = (poly8x16_t)(__p0);	31187	__ret = (poly8x16_t)(__p0);
32420	return __ret;	31188	return __ret;
32421	}	31189	}
32422	#endif
32423
32424	#ifdef __LITTLE_ENDIAN__
32425	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {
32426	poly8x16_t __ret;
32427	__ret = (poly8x16_t)(__p0);
32428	return __ret;
32429	}
32430	#else
32431	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {	31190	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {
32432	poly8x16_t __ret;	31191	poly8x16_t __ret;
32433	__ret = (poly8x16_t)(__p0);	31192	__ret = (poly8x16_t)(__p0);
32434	return __ret;	31193	return __ret;
32435	}	31194	}
32436	#endif
32437
32438	#ifdef __LITTLE_ENDIAN__
32439	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {
32440	poly8x16_t __ret;
32441	__ret = (poly8x16_t)(__p0);
32442	return __ret;
32443	}
32444	#else
32445	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {	31195	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {
32446	poly8x16_t __ret;	31196	poly8x16_t __ret;
32447	__ret = (poly8x16_t)(__p0);	31197	__ret = (poly8x16_t)(__p0);
32448	return __ret;	31198	return __ret;
32449	}	31199	}
32450	#endif
32451
32452	#ifdef __LITTLE_ENDIAN__
32453	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {
32454	poly8x16_t __ret;
32455	__ret = (poly8x16_t)(__p0);
32456	return __ret;
32457	}
32458	#else
32459	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {	31200	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {
32460	poly8x16_t __ret;	31201	poly8x16_t __ret;
32461	__ret = (poly8x16_t)(__p0);	31202	__ret = (poly8x16_t)(__p0);
32462	return __ret;	31203	return __ret;
32463	}	31204	}
32464	#endif
32465
32466	#ifdef __LITTLE_ENDIAN__
32467	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {
32468	poly8x16_t __ret;
32469	__ret = (poly8x16_t)(__p0);
32470	return __ret;
32471	}
32472	#else
32473	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {	31205	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {
32474	poly8x16_t __ret;	31206	poly8x16_t __ret;
32475	__ret = (poly8x16_t)(__p0);	31207	__ret = (poly8x16_t)(__p0);
32476	return __ret;	31208	return __ret;
32477	}	31209	}
32478	#endif
32479
32480	#ifdef __LITTLE_ENDIAN__
32481	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {
32482	poly8x16_t __ret;
32483	__ret = (poly8x16_t)(__p0);
32484	return __ret;
32485	}
32486	#else
32487	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {	31210	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {
32488	poly8x16_t __ret;	31211	poly8x16_t __ret;
32489	__ret = (poly8x16_t)(__p0);	31212	__ret = (poly8x16_t)(__p0);
32490	return __ret;	31213	return __ret;
32491	}	31214	}
32492	#endif
32493
32494	#ifdef __LITTLE_ENDIAN__
32495	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {
32496	poly8x16_t __ret;
32497	__ret = (poly8x16_t)(__p0);
32498	return __ret;
32499	}
32500	#else
32501	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {	31215	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {
32502	poly8x16_t __ret;	31216	poly8x16_t __ret;
32503	__ret = (poly8x16_t)(__p0);	31217	__ret = (poly8x16_t)(__p0);
32504	return __ret;	31218	return __ret;
32505	}	31219	}
32506	#endif
32507
32508	#ifdef __LITTLE_ENDIAN__
32509	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {
32510	poly8x16_t __ret;
32511	__ret = (poly8x16_t)(__p0);
32512	return __ret;
32513	}
32514	#else
32515	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {	31220	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {
32516	poly8x16_t __ret;	31221	poly8x16_t __ret;
32517	__ret = (poly8x16_t)(__p0);	31222	__ret = (poly8x16_t)(__p0);
32518	return __ret;	31223	return __ret;
32519	}	31224	}
32520	#endif
32521
32522	#ifdef __LITTLE_ENDIAN__
32523	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {
32524	poly8x16_t __ret;
32525	__ret = (poly8x16_t)(__p0);
32526	return __ret;
32527	}
32528	#else
32529	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {	31225	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {
32530	poly8x16_t __ret;	31226	poly8x16_t __ret;
32531	__ret = (poly8x16_t)(__p0);	31227	__ret = (poly8x16_t)(__p0);
32532	return __ret;	31228	return __ret;
32533	}	31229	}
32534	#endif
32535
32536	#ifdef __LITTLE_ENDIAN__
32537	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {
32538	poly8x16_t __ret;
32539	__ret = (poly8x16_t)(__p0);
32540	return __ret;
32541	}
32542	#else
32543	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {	31230	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {
32544	poly8x16_t __ret;	31231	poly8x16_t __ret;
32545	__ret = (poly8x16_t)(__p0);	31232	__ret = (poly8x16_t)(__p0);
32546	return __ret;	31233	return __ret;
32547	}	31234	}
32548	#endif
32549
32550	#ifdef __LITTLE_ENDIAN__
32551	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {
32552	poly16x8_t __ret;
32553	__ret = (poly16x8_t)(__p0);
32554	return __ret;
32555	}
32556	#else
32557	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {	31235	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {
32558	poly16x8_t __ret;	31236	poly16x8_t __ret;
32559	__ret = (poly16x8_t)(__p0);	31237	__ret = (poly16x8_t)(__p0);
32560	return __ret;	31238	return __ret;
32561	}	31239	}
32562	#endif
32563
32564	#ifdef __LITTLE_ENDIAN__
32565	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {
32566	poly16x8_t __ret;
32567	__ret = (poly16x8_t)(__p0);
32568	return __ret;
32569	}
32570	#else
32571	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {	31240	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {
32572	poly16x8_t __ret;	31241	poly16x8_t __ret;
32573	__ret = (poly16x8_t)(__p0);	31242	__ret = (poly16x8_t)(__p0);
32574	return __ret;	31243	return __ret;
32575	}	31244	}
32576	#endif
32577
32578	#ifdef __LITTLE_ENDIAN__
32579	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {
32580	poly16x8_t __ret;
32581	__ret = (poly16x8_t)(__p0);
32582	return __ret;
32583	}
32584	#else
32585	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {	31245	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {
32586	poly16x8_t __ret;	31246	poly16x8_t __ret;
32587	__ret = (poly16x8_t)(__p0);	31247	__ret = (poly16x8_t)(__p0);
32588	return __ret;	31248	return __ret;
32589	}	31249	}
32590	#endif
32591
32592	#ifdef __LITTLE_ENDIAN__
32593	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {
32594	poly16x8_t __ret;
32595	__ret = (poly16x8_t)(__p0);
32596	return __ret;
32597	}
32598	#else
32599	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {	31250	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {
32600	poly16x8_t __ret;	31251	poly16x8_t __ret;
32601	__ret = (poly16x8_t)(__p0);	31252	__ret = (poly16x8_t)(__p0);
32602	return __ret;	31253	return __ret;
32603	}	31254	}
32604	#endif
32605
32606	#ifdef __LITTLE_ENDIAN__
32607	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {
32608	poly16x8_t __ret;
32609	__ret = (poly16x8_t)(__p0);
32610	return __ret;
32611	}
32612	#else
32613	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {	31255	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {
32614	poly16x8_t __ret;	31256	poly16x8_t __ret;
32615	__ret = (poly16x8_t)(__p0);	31257	__ret = (poly16x8_t)(__p0);
32616	return __ret;	31258	return __ret;
32617	}	31259	}
32618	#endif
32619
32620	#ifdef __LITTLE_ENDIAN__
32621	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {
32622	poly16x8_t __ret;
32623	__ret = (poly16x8_t)(__p0);
32624	return __ret;
32625	}
32626	#else
32627	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {	31260	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {
32628	poly16x8_t __ret;	31261	poly16x8_t __ret;
32629	__ret = (poly16x8_t)(__p0);	31262	__ret = (poly16x8_t)(__p0);
32630	return __ret;	31263	return __ret;
32631	}	31264	}
32632	#endif
32633
32634	#ifdef __LITTLE_ENDIAN__
32635	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {
32636	poly16x8_t __ret;
32637	__ret = (poly16x8_t)(__p0);
32638	return __ret;
32639	}
32640	#else
32641	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {	31265	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {
32642	poly16x8_t __ret;	31266	poly16x8_t __ret;
32643	__ret = (poly16x8_t)(__p0);	31267	__ret = (poly16x8_t)(__p0);
32644	return __ret;	31268	return __ret;
32645	}	31269	}
32646	#endif
32647
32648	#ifdef __LITTLE_ENDIAN__
32649	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {
32650	poly16x8_t __ret;
32651	__ret = (poly16x8_t)(__p0);
32652	return __ret;
32653	}
32654	#else
32655	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {	31270	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {
32656	poly16x8_t __ret;	31271	poly16x8_t __ret;
32657	__ret = (poly16x8_t)(__p0);	31272	__ret = (poly16x8_t)(__p0);
32658	return __ret;	31273	return __ret;
32659	}	31274	}
32660	#endif
32661
32662	#ifdef __LITTLE_ENDIAN__
32663	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {
32664	poly16x8_t __ret;
32665	__ret = (poly16x8_t)(__p0);
32666	return __ret;
32667	}
32668	#else
32669	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {	31275	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {
32670	poly16x8_t __ret;	31276	poly16x8_t __ret;
32671	__ret = (poly16x8_t)(__p0);	31277	__ret = (poly16x8_t)(__p0);
32672	return __ret;	31278	return __ret;
32673	}	31279	}
32674	#endif
32675
32676	#ifdef __LITTLE_ENDIAN__
32677	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {
32678	poly16x8_t __ret;
32679	__ret = (poly16x8_t)(__p0);
32680	return __ret;
32681	}
32682	#else
32683	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {	31280	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {
32684	poly16x8_t __ret;	31281	poly16x8_t __ret;
32685	__ret = (poly16x8_t)(__p0);	31282	__ret = (poly16x8_t)(__p0);
32686	return __ret;	31283	return __ret;
32687	}	31284	}
32688	#endif
32689
32690	#ifdef __LITTLE_ENDIAN__
32691	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {
32692	poly16x8_t __ret;
32693	__ret = (poly16x8_t)(__p0);
32694	return __ret;
32695	}
32696	#else
32697	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {	31285	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {
32698	poly16x8_t __ret;	31286	poly16x8_t __ret;
32699	__ret = (poly16x8_t)(__p0);	31287	__ret = (poly16x8_t)(__p0);
32700	return __ret;	31288	return __ret;
32701	}	31289	}
32702	#endif
32703
32704	#ifdef __LITTLE_ENDIAN__
32705	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {
32706	uint8x16_t __ret;
32707	__ret = (uint8x16_t)(__p0);
32708	return __ret;
32709	}
32710	#else
32711	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {	31290	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {
32712	uint8x16_t __ret;	31291	uint8x16_t __ret;
32713	__ret = (uint8x16_t)(__p0);	31292	__ret = (uint8x16_t)(__p0);
32714	return __ret;	31293	return __ret;
32715	}	31294	}
32716	#endif
32717
32718	#ifdef __LITTLE_ENDIAN__
32719	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {
32720	uint8x16_t __ret;
32721	__ret = (uint8x16_t)(__p0);
32722	return __ret;
32723	}
32724	#else
32725	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {	31295	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {
32726	uint8x16_t __ret;	31296	uint8x16_t __ret;
32727	__ret = (uint8x16_t)(__p0);	31297	__ret = (uint8x16_t)(__p0);
32728	return __ret;	31298	return __ret;
32729	}	31299	}
32730	#endif
32731
32732	#ifdef __LITTLE_ENDIAN__
32733	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {
32734	uint8x16_t __ret;
32735	__ret = (uint8x16_t)(__p0);
32736	return __ret;
32737	}
32738	#else
32739	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {	31300	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {
32740	uint8x16_t __ret;	31301	uint8x16_t __ret;
32741	__ret = (uint8x16_t)(__p0);	31302	__ret = (uint8x16_t)(__p0);
32742	return __ret;	31303	return __ret;
32743	}	31304	}
32744	#endif
32745
32746	#ifdef __LITTLE_ENDIAN__
32747	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {
32748	uint8x16_t __ret;
32749	__ret = (uint8x16_t)(__p0);
32750	return __ret;
32751	}
32752	#else
32753	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {	31305	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {
32754	uint8x16_t __ret;	31306	uint8x16_t __ret;
32755	__ret = (uint8x16_t)(__p0);	31307	__ret = (uint8x16_t)(__p0);
32756	return __ret;	31308	return __ret;
32757	}	31309	}
32758	#endif
32759
32760	#ifdef __LITTLE_ENDIAN__
32761	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {	31310	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {
32762	uint8x16_t __ret;	31311	uint8x16_t __ret;
32763	__ret = (uint8x16_t)(__p0);	31312	__ret = (uint8x16_t)(__p0);
32764	return __ret;	31313	return __ret;
32765	}	31314	}
32766	#else	31315	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
32767	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {
32768	uint8x16_t __ret;	31316	uint8x16_t __ret;
32769	__ret = (uint8x16_t)(__p0);	31317	__ret = (uint8x16_t)(__p0);
32770	return __ret;	31318	return __ret;
32771	}	31319	}
32772	#endif	31320	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
32773
32774	#ifdef __LITTLE_ENDIAN__
32775	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
32776	uint8x16_t __ret;	31321	uint8x16_t __ret;
32777	__ret = (uint8x16_t)(__p0);	31322	__ret = (uint8x16_t)(__p0);
32778	return __ret;	31323	return __ret;
32779	}	31324	}
32780	#else	31325	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {
32781	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
32782	uint8x16_t __ret;	31326	uint8x16_t __ret;
32783	__ret = (uint8x16_t)(__p0);	31327	__ret = (uint8x16_t)(__p0);
32784	return __ret;	31328	return __ret;
32785	}	31329	}
32786	#endif	31330	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
32787
32788	#ifdef __LITTLE_ENDIAN__
32789	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
32790	uint8x16_t __ret;	31331	uint8x16_t __ret;
32791	__ret = (uint8x16_t)(__p0);	31332	__ret = (uint8x16_t)(__p0);
32792	return __ret;	31333	return __ret;
32793	}	31334	}
32794	#else	31335	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
32795	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
32796	uint8x16_t __ret;	31336	uint8x16_t __ret;
32797	__ret = (uint8x16_t)(__p0);	31337	__ret = (uint8x16_t)(__p0);
32798	return __ret;	31338	return __ret;
32799	}	31339	}
32800	#endif	31340	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {
32801
32802	#ifdef __LITTLE_ENDIAN__
32803	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {
32804	uint8x16_t __ret;	31341	uint8x16_t __ret;
32805	__ret = (uint8x16_t)(__p0);	31342	__ret = (uint8x16_t)(__p0);
32806	return __ret;	31343	return __ret;
32807	}	31344	}
32808	#else	31345	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {
32809	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {	31346	uint32x4_t __ret;
32810	uint8x16_t __ret;	31347	__ret = (uint32x4_t)(__p0);
32811	__ret = (uint8x16_t)(__p0);
32812	return __ret;	31348	return __ret;
32813	}	31349	}
32814	#endif
32815
32816	#ifdef __LITTLE_ENDIAN__
32817	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
32818	uint8x16_t __ret;
32819	__ret = (uint8x16_t)(__p0);
32820	return __ret;
32821	}
32822	#else
32823	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
32824	uint8x16_t __ret;
32825	__ret = (uint8x16_t)(__p0);
32826	return __ret;
32827	}
32828	#endif
32829
32830	#ifdef __LITTLE_ENDIAN__
32831	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
32832	uint8x16_t __ret;
32833	__ret = (uint8x16_t)(__p0);
32834	return __ret;
32835	}
32836	#else
32837	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
32838	uint8x16_t __ret;
32839	__ret = (uint8x16_t)(__p0);
32840	return __ret;
32841	}
32842	#endif
32843
32844	#ifdef __LITTLE_ENDIAN__
32845	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {
32846	uint8x16_t __ret;
32847	__ret = (uint8x16_t)(__p0);
32848	return __ret;
32849	}
32850	#else
32851	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {
32852	uint8x16_t __ret;
32853	__ret = (uint8x16_t)(__p0);
32854	return __ret;
32855	}
32856	#endif
32857
32858	#ifdef __LITTLE_ENDIAN__
32859	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {
32860	uint32x4_t __ret;
32861	__ret = (uint32x4_t)(__p0);
32862	return __ret;
32863	}
32864	#else
32865	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {
32866	uint32x4_t __ret;
32867	__ret = (uint32x4_t)(__p0);
32868	return __ret;
32869	}
32870	#endif
32871
32872	#ifdef __LITTLE_ENDIAN__
32873	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {
32874	uint32x4_t __ret;
32875	__ret = (uint32x4_t)(__p0);
32876	return __ret;
32877	}
32878	#else
32879	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {	31350	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {
32880	uint32x4_t __ret;	31351	uint32x4_t __ret;
32881	__ret = (uint32x4_t)(__p0);	31352	__ret = (uint32x4_t)(__p0);
32882	return __ret;	31353	return __ret;
32883	}	31354	}
32884	#endif
32885
32886	#ifdef __LITTLE_ENDIAN__
32887	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
32888	uint32x4_t __ret;
32889	__ret = (uint32x4_t)(__p0);
32890	return __ret;
32891	}
32892	#else
32893	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {	31355	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
32894	uint32x4_t __ret;	31356	uint32x4_t __ret;
32895	__ret = (uint32x4_t)(__p0);	31357	__ret = (uint32x4_t)(__p0);
32896	return __ret;	31358	return __ret;
32897	}	31359	}
32898	#endif
32899
32900	#ifdef __LITTLE_ENDIAN__
32901	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {
32902	uint32x4_t __ret;
32903	__ret = (uint32x4_t)(__p0);
32904	return __ret;
32905	}
32906	#else
32907	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {	31360	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {
32908	uint32x4_t __ret;	31361	uint32x4_t __ret;
32909	__ret = (uint32x4_t)(__p0);	31362	__ret = (uint32x4_t)(__p0);
32910	return __ret;	31363	return __ret;
32911	}	31364	}
32912	#endif
32913
32914	#ifdef __LITTLE_ENDIAN__
32915	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {
32916	uint32x4_t __ret;
32917	__ret = (uint32x4_t)(__p0);
32918	return __ret;
32919	}
32920	#else
32921	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {	31365	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {
32922	uint32x4_t __ret;	31366	uint32x4_t __ret;
32923	__ret = (uint32x4_t)(__p0);	31367	__ret = (uint32x4_t)(__p0);
32924	return __ret;	31368	return __ret;
32925	}	31369	}
32926	#endif
32927
32928	#ifdef __LITTLE_ENDIAN__
32929	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {
32930	uint32x4_t __ret;
32931	__ret = (uint32x4_t)(__p0);
32932	return __ret;
32933	}
32934	#else
32935	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {	31370	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {
32936	uint32x4_t __ret;	31371	uint32x4_t __ret;
32937	__ret = (uint32x4_t)(__p0);	31372	__ret = (uint32x4_t)(__p0);
32938	return __ret;	31373	return __ret;
32939	}	31374	}
32940	#endif
32941
32942	#ifdef __LITTLE_ENDIAN__
32943	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {
32944	uint32x4_t __ret;
32945	__ret = (uint32x4_t)(__p0);
32946	return __ret;
32947	}
32948	#else
32949	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {	31375	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {
32950	uint32x4_t __ret;	31376	uint32x4_t __ret;
32951	__ret = (uint32x4_t)(__p0);	31377	__ret = (uint32x4_t)(__p0);
32952	return __ret;	31378	return __ret;
32953	}	31379	}
32954	#endif
32955
32956	#ifdef __LITTLE_ENDIAN__
32957	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {
32958	uint32x4_t __ret;
32959	__ret = (uint32x4_t)(__p0);
32960	return __ret;
32961	}
32962	#else
32963	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {	31380	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {
32964	uint32x4_t __ret;	31381	uint32x4_t __ret;
32965	__ret = (uint32x4_t)(__p0);	31382	__ret = (uint32x4_t)(__p0);
32966	return __ret;	31383	return __ret;
32967	}	31384	}
32968	#endif
32969
32970	#ifdef __LITTLE_ENDIAN__
32971	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {
32972	uint32x4_t __ret;
32973	__ret = (uint32x4_t)(__p0);
32974	return __ret;
32975	}
32976	#else
32977	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {	31385	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {
32978	uint32x4_t __ret;	31386	uint32x4_t __ret;
32979	__ret = (uint32x4_t)(__p0);	31387	__ret = (uint32x4_t)(__p0);
32980	return __ret;	31388	return __ret;
32981	}	31389	}
32982	#endif
32983
32984	#ifdef __LITTLE_ENDIAN__
32985	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {
32986	uint32x4_t __ret;
32987	__ret = (uint32x4_t)(__p0);
32988	return __ret;
32989	}
32990	#else
32991	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {	31390	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {
32992	uint32x4_t __ret;	31391	uint32x4_t __ret;
32993	__ret = (uint32x4_t)(__p0);	31392	__ret = (uint32x4_t)(__p0);
32994	return __ret;	31393	return __ret;
32995	}	31394	}
32996	#endif
32997
32998	#ifdef __LITTLE_ENDIAN__
32999	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {
33000	uint32x4_t __ret;
33001	__ret = (uint32x4_t)(__p0);
33002	return __ret;
33003	}
33004	#else
33005	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {	31395	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {
33006	uint32x4_t __ret;	31396	uint32x4_t __ret;
33007	__ret = (uint32x4_t)(__p0);	31397	__ret = (uint32x4_t)(__p0);
33008	return __ret;	31398	return __ret;
33009	}	31399	}
33010	#endif
33011
33012	#ifdef __LITTLE_ENDIAN__
33013	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {
33014	uint64x2_t __ret;
33015	__ret = (uint64x2_t)(__p0);
33016	return __ret;
33017	}
33018	#else
33019	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {	31400	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {
33020	uint64x2_t __ret;	31401	uint64x2_t __ret;
33021	__ret = (uint64x2_t)(__p0);	31402	__ret = (uint64x2_t)(__p0);
33022	return __ret;	31403	return __ret;
33023	}	31404	}
33024	#endif
33025
33026	#ifdef __LITTLE_ENDIAN__
33027	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {
33028	uint64x2_t __ret;
33029	__ret = (uint64x2_t)(__p0);
33030	return __ret;
33031	}
33032	#else
33033	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {	31405	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {
33034	uint64x2_t __ret;	31406	uint64x2_t __ret;
33035	__ret = (uint64x2_t)(__p0);	31407	__ret = (uint64x2_t)(__p0);
33036	return __ret;	31408	return __ret;
33037	}	31409	}
33038	#endif
33039
33040	#ifdef __LITTLE_ENDIAN__
33041	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {
33042	uint64x2_t __ret;
33043	__ret = (uint64x2_t)(__p0);
33044	return __ret;
33045	}
33046	#else
33047	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {	31410	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {
33048	uint64x2_t __ret;	31411	uint64x2_t __ret;
33049	__ret = (uint64x2_t)(__p0);	31412	__ret = (uint64x2_t)(__p0);
33050	return __ret;	31413	return __ret;
33051	}	31414	}
33052	#endif
33053
33054	#ifdef __LITTLE_ENDIAN__
33055	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {
33056	uint64x2_t __ret;
33057	__ret = (uint64x2_t)(__p0);
33058	return __ret;
33059	}
33060	#else
33061	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {	31415	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {
33062	uint64x2_t __ret;	31416	uint64x2_t __ret;
33063	__ret = (uint64x2_t)(__p0);	31417	__ret = (uint64x2_t)(__p0);
33064	return __ret;	31418	return __ret;
33065	}	31419	}
33066	#endif
33067
33068	#ifdef __LITTLE_ENDIAN__
33069	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {
33070	uint64x2_t __ret;
33071	__ret = (uint64x2_t)(__p0);
33072	return __ret;
33073	}
33074	#else
33075	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {	31420	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {
33076	uint64x2_t __ret;	31421	uint64x2_t __ret;
33077	__ret = (uint64x2_t)(__p0);	31422	__ret = (uint64x2_t)(__p0);
33078	return __ret;	31423	return __ret;
33079	}	31424	}
33080	#endif
33081
33082	#ifdef __LITTLE_ENDIAN__
33083	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {
33084	uint64x2_t __ret;
33085	__ret = (uint64x2_t)(__p0);
33086	return __ret;
33087	}
33088	#else
33089	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {	31425	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {
33090	uint64x2_t __ret;	31426	uint64x2_t __ret;
33091	__ret = (uint64x2_t)(__p0);	31427	__ret = (uint64x2_t)(__p0);
33092	return __ret;	31428	return __ret;
33093	}	31429	}
33094	#endif
33095
33096	#ifdef __LITTLE_ENDIAN__
33097	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {
33098	uint64x2_t __ret;
33099	__ret = (uint64x2_t)(__p0);
33100	return __ret;
33101	}
33102	#else
33103	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {	31430	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {
33104	uint64x2_t __ret;	31431	uint64x2_t __ret;
33105	__ret = (uint64x2_t)(__p0);	31432	__ret = (uint64x2_t)(__p0);
33106	return __ret;	31433	return __ret;
33107	}	31434	}
33108	#endif
33109
33110	#ifdef __LITTLE_ENDIAN__
33111	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {
33112	uint64x2_t __ret;
33113	__ret = (uint64x2_t)(__p0);
33114	return __ret;
33115	}
33116	#else
33117	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {	31435	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {
33118	uint64x2_t __ret;	31436	uint64x2_t __ret;
33119	__ret = (uint64x2_t)(__p0);	31437	__ret = (uint64x2_t)(__p0);
33120	return __ret;	31438	return __ret;
33121	}	31439	}
33122	#endif
33123
33124	#ifdef __LITTLE_ENDIAN__
33125	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {
33126	uint64x2_t __ret;
33127	__ret = (uint64x2_t)(__p0);
33128	return __ret;
33129	}
33130	#else
33131	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {	31440	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {
33132	uint64x2_t __ret;	31441	uint64x2_t __ret;
33133	__ret = (uint64x2_t)(__p0);	31442	__ret = (uint64x2_t)(__p0);
33134	return __ret;	31443	return __ret;
33135	}	31444	}
33136	#endif
33137
33138	#ifdef __LITTLE_ENDIAN__
33139	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {
33140	uint64x2_t __ret;
33141	__ret = (uint64x2_t)(__p0);
33142	return __ret;
33143	}
33144	#else
33145	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {	31445	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {
33146	uint64x2_t __ret;	31446	uint64x2_t __ret;
33147	__ret = (uint64x2_t)(__p0);	31447	__ret = (uint64x2_t)(__p0);
33148	return __ret;	31448	return __ret;
33149	}	31449	}
33150	#endif
33151
33152	#ifdef __LITTLE_ENDIAN__
33153	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {
33154	uint64x2_t __ret;
33155	__ret = (uint64x2_t)(__p0);
33156	return __ret;
33157	}
33158	#else
33159	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {	31450	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {
33160	uint64x2_t __ret;	31451	uint64x2_t __ret;
33161	__ret = (uint64x2_t)(__p0);	31452	__ret = (uint64x2_t)(__p0);
33162	return __ret;	31453	return __ret;
33163	}	31454	}
33164	#endif
33165
33166	#ifdef __LITTLE_ENDIAN__
33167	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {
33168	uint16x8_t __ret;
33169	__ret = (uint16x8_t)(__p0);
33170	return __ret;
33171	}
33172	#else
33173	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {	31455	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {
33174	uint16x8_t __ret;	31456	uint16x8_t __ret;
33175	__ret = (uint16x8_t)(__p0);	31457	__ret = (uint16x8_t)(__p0);
33176	return __ret;	31458	return __ret;
33177	}	31459	}
33178	#endif
33179
33180	#ifdef __LITTLE_ENDIAN__
33181	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {
33182	uint16x8_t __ret;
33183	__ret = (uint16x8_t)(__p0);
33184	return __ret;
33185	}
33186	#else
33187	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {	31460	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {
33188	uint16x8_t __ret;	31461	uint16x8_t __ret;
33189	__ret = (uint16x8_t)(__p0);	31462	__ret = (uint16x8_t)(__p0);
33190	return __ret;	31463	return __ret;
33191	}	31464	}
33192	#endif
33193
33194	#ifdef __LITTLE_ENDIAN__
33195	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {
33196	uint16x8_t __ret;
33197	__ret = (uint16x8_t)(__p0);
33198	return __ret;
33199	}
33200	#else
33201	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {	31465	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {
33202	uint16x8_t __ret;	31466	uint16x8_t __ret;
33203	__ret = (uint16x8_t)(__p0);	31467	__ret = (uint16x8_t)(__p0);
33204	return __ret;	31468	return __ret;
33205	}	31469	}
33206	#endif
33207
33208	#ifdef __LITTLE_ENDIAN__
33209	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {
33210	uint16x8_t __ret;
33211	__ret = (uint16x8_t)(__p0);
33212	return __ret;
33213	}
33214	#else
33215	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {	31470	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {
33216	uint16x8_t __ret;	31471	uint16x8_t __ret;
33217	__ret = (uint16x8_t)(__p0);	31472	__ret = (uint16x8_t)(__p0);
33218	return __ret;	31473	return __ret;
33219	}	31474	}
33220	#endif
33221
33222	#ifdef __LITTLE_ENDIAN__
33223	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {
33224	uint16x8_t __ret;
33225	__ret = (uint16x8_t)(__p0);
33226	return __ret;
33227	}
33228	#else
33229	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {	31475	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {
33230	uint16x8_t __ret;	31476	uint16x8_t __ret;
33231	__ret = (uint16x8_t)(__p0);	31477	__ret = (uint16x8_t)(__p0);
33232	return __ret;	31478	return __ret;
33233	}	31479	}
33234	#endif
33235
33236	#ifdef __LITTLE_ENDIAN__
33237	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {
33238	uint16x8_t __ret;
33239	__ret = (uint16x8_t)(__p0);
33240	return __ret;
33241	}
33242	#else
33243	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {	31480	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {
33244	uint16x8_t __ret;	31481	uint16x8_t __ret;
33245	__ret = (uint16x8_t)(__p0);	31482	__ret = (uint16x8_t)(__p0);
33246	return __ret;	31483	return __ret;
33247	}	31484	}
33248	#endif
33249
33250	#ifdef __LITTLE_ENDIAN__
33251	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {
33252	uint16x8_t __ret;
33253	__ret = (uint16x8_t)(__p0);
33254	return __ret;
33255	}
33256	#else
33257	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {	31485	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {
33258	uint16x8_t __ret;	31486	uint16x8_t __ret;
33259	__ret = (uint16x8_t)(__p0);	31487	__ret = (uint16x8_t)(__p0);
33260	return __ret;	31488	return __ret;
33261	}	31489	}
33262	#endif
33263
33264	#ifdef __LITTLE_ENDIAN__
33265	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {
33266	uint16x8_t __ret;
33267	__ret = (uint16x8_t)(__p0);
33268	return __ret;
33269	}
33270	#else
33271	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {	31490	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {
33272	uint16x8_t __ret;	31491	uint16x8_t __ret;
33273	__ret = (uint16x8_t)(__p0);	31492	__ret = (uint16x8_t)(__p0);
33274	return __ret;	31493	return __ret;
33275	}	31494	}
33276	#endif
33277
33278	#ifdef __LITTLE_ENDIAN__
33279	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {
33280	uint16x8_t __ret;
33281	__ret = (uint16x8_t)(__p0);
33282	return __ret;
33283	}
33284	#else
33285	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {	31495	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {
33286	uint16x8_t __ret;	31496	uint16x8_t __ret;
33287	__ret = (uint16x8_t)(__p0);	31497	__ret = (uint16x8_t)(__p0);
33288	return __ret;	31498	return __ret;
33289	}	31499	}
33290	#endif
33291
33292	#ifdef __LITTLE_ENDIAN__
33293	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {
33294	uint16x8_t __ret;
33295	__ret = (uint16x8_t)(__p0);
33296	return __ret;
33297	}
33298	#else
33299	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {	31500	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {
33300	uint16x8_t __ret;	31501	uint16x8_t __ret;
33301	__ret = (uint16x8_t)(__p0);	31502	__ret = (uint16x8_t)(__p0);
33302	return __ret;	31503	return __ret;
33303	}	31504	}
33304	#endif
33305
33306	#ifdef __LITTLE_ENDIAN__
33307	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {
33308	uint16x8_t __ret;
33309	__ret = (uint16x8_t)(__p0);
33310	return __ret;
33311	}
33312	#else
33313	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {	31505	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {
33314	uint16x8_t __ret;	31506	uint16x8_t __ret;
33315	__ret = (uint16x8_t)(__p0);	31507	__ret = (uint16x8_t)(__p0);
33316	return __ret;	31508	return __ret;
33317	}	31509	}
33318	#endif
33319
33320	#ifdef __LITTLE_ENDIAN__
33321	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {
33322	int8x16_t __ret;
33323	__ret = (int8x16_t)(__p0);
33324	return __ret;
33325	}
33326	#else
33327	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {	31510	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {
33328	int8x16_t __ret;	31511	int8x16_t __ret;
33329	__ret = (int8x16_t)(__p0);	31512	__ret = (int8x16_t)(__p0);
33330	return __ret;	31513	return __ret;
33331	}	31514	}
33332	#endif
33333
33334	#ifdef __LITTLE_ENDIAN__
33335	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {
33336	int8x16_t __ret;
33337	__ret = (int8x16_t)(__p0);
33338	return __ret;
33339	}
33340	#else
33341	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {	31515	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {
33342	int8x16_t __ret;	31516	int8x16_t __ret;
33343	__ret = (int8x16_t)(__p0);	31517	__ret = (int8x16_t)(__p0);
33344	return __ret;	31518	return __ret;
33345	}	31519	}
33346	#endif
33347
33348	#ifdef __LITTLE_ENDIAN__
33349	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {
33350	int8x16_t __ret;
33351	__ret = (int8x16_t)(__p0);
33352	return __ret;
33353	}
33354	#else
33355	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {	31520	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {
33356	int8x16_t __ret;	31521	int8x16_t __ret;
33357	__ret = (int8x16_t)(__p0);	31522	__ret = (int8x16_t)(__p0);
33358	return __ret;	31523	return __ret;
33359	}	31524	}
33360	#endif
33361
33362	#ifdef __LITTLE_ENDIAN__
33363	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {
33364	int8x16_t __ret;
33365	__ret = (int8x16_t)(__p0);
33366	return __ret;
33367	}
33368	#else
33369	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {	31525	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {
33370	int8x16_t __ret;	31526	int8x16_t __ret;
33371	__ret = (int8x16_t)(__p0);	31527	__ret = (int8x16_t)(__p0);
33372	return __ret;	31528	return __ret;
33373	}	31529	}
33374	#endif
33375
33376	#ifdef __LITTLE_ENDIAN__
33377	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {
33378	int8x16_t __ret;
33379	__ret = (int8x16_t)(__p0);
33380	return __ret;
33381	}
33382	#else
33383	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {	31530	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {
33384	int8x16_t __ret;	31531	int8x16_t __ret;
33385	__ret = (int8x16_t)(__p0);	31532	__ret = (int8x16_t)(__p0);
33386	return __ret;	31533	return __ret;
33387	}	31534	}
33388	#endif
33389
33390	#ifdef __LITTLE_ENDIAN__
33391	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {
33392	int8x16_t __ret;
33393	__ret = (int8x16_t)(__p0);
33394	return __ret;
33395	}
33396	#else
33397	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {	31535	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {
33398	int8x16_t __ret;	31536	int8x16_t __ret;
33399	__ret = (int8x16_t)(__p0);	31537	__ret = (int8x16_t)(__p0);
33400	return __ret;	31538	return __ret;
33401	}	31539	}
33402	#endif
33403
33404	#ifdef __LITTLE_ENDIAN__
33405	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {
33406	int8x16_t __ret;
33407	__ret = (int8x16_t)(__p0);
33408	return __ret;
33409	}
33410	#else
33411	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {	31540	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {
33412	int8x16_t __ret;	31541	int8x16_t __ret;
33413	__ret = (int8x16_t)(__p0);	31542	__ret = (int8x16_t)(__p0);
33414	return __ret;	31543	return __ret;
33415	}	31544	}
33416	#endif
33417
33418	#ifdef __LITTLE_ENDIAN__
33419	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {
33420	int8x16_t __ret;
33421	__ret = (int8x16_t)(__p0);
33422	return __ret;
33423	}
33424	#else
33425	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {	31545	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {
33426	int8x16_t __ret;	31546	int8x16_t __ret;
33427	__ret = (int8x16_t)(__p0);	31547	__ret = (int8x16_t)(__p0);
33428	return __ret;	31548	return __ret;
33429	}	31549	}
33430	#endif
33431
33432	#ifdef __LITTLE_ENDIAN__
33433	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {
33434	int8x16_t __ret;
33435	__ret = (int8x16_t)(__p0);
33436	return __ret;
33437	}
33438	#else
33439	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {	31550	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {
33440	int8x16_t __ret;	31551	int8x16_t __ret;
33441	__ret = (int8x16_t)(__p0);	31552	__ret = (int8x16_t)(__p0);
33442	return __ret;	31553	return __ret;
33443	}	31554	}
33444	#endif
33445
33446	#ifdef __LITTLE_ENDIAN__
33447	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {
33448	int8x16_t __ret;
33449	__ret = (int8x16_t)(__p0);
33450	return __ret;
33451	}
33452	#else
33453	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {	31555	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {
33454	int8x16_t __ret;	31556	int8x16_t __ret;
33455	__ret = (int8x16_t)(__p0);	31557	__ret = (int8x16_t)(__p0);
33456	return __ret;	31558	return __ret;
33457	}	31559	}
33458	#endif
33459
33460	#ifdef __LITTLE_ENDIAN__
33461	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {
33462	int8x16_t __ret;
33463	__ret = (int8x16_t)(__p0);
33464	return __ret;
33465	}
33466	#else
33467	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {	31560	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {
33468	int8x16_t __ret;	31561	int8x16_t __ret;
33469	__ret = (int8x16_t)(__p0);	31562	__ret = (int8x16_t)(__p0);
33470	return __ret;	31563	return __ret;
33471	}	31564	}
33472	#endif
33473
33474	#ifdef __LITTLE_ENDIAN__
33475	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {
33476	float32x4_t __ret;
33477	__ret = (float32x4_t)(__p0);
33478	return __ret;
33479	}
33480	#else
33481	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {	31565	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {
33482	float32x4_t __ret;	31566	float32x4_t __ret;
33483	__ret = (float32x4_t)(__p0);	31567	__ret = (float32x4_t)(__p0);
33484	return __ret;	31568	return __ret;
33485	}	31569	}
33486	#endif
33487
33488	#ifdef __LITTLE_ENDIAN__
33489	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {
33490	float32x4_t __ret;
33491	__ret = (float32x4_t)(__p0);
33492	return __ret;
33493	}
33494	#else
33495	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {	31570	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {
33496	float32x4_t __ret;	31571	float32x4_t __ret;
33497	__ret = (float32x4_t)(__p0);	31572	__ret = (float32x4_t)(__p0);
33498	return __ret;	31573	return __ret;
33499	}	31574	}
33500	#endif
33501
33502	#ifdef __LITTLE_ENDIAN__
33503	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {	31575	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {
33504	float32x4_t __ret;	31576	float32x4_t __ret;
33505	__ret = (float32x4_t)(__p0);	31577	__ret = (float32x4_t)(__p0);
33506	return __ret;	31578	return __ret;
33507	}	31579	}
33508	#else	31580	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {
33509	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {
33510	float32x4_t __ret;	31581	float32x4_t __ret;
33511	__ret = (float32x4_t)(__p0);	31582	__ret = (float32x4_t)(__p0);
33512	return __ret;	31583	return __ret;
33513	}	31584	}
33514	#endif	31585	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {
33515
33516	#ifdef __LITTLE_ENDIAN__
33517	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {
33518	float32x4_t __ret;	31586	float32x4_t __ret;
33519	__ret = (float32x4_t)(__p0);	31587	__ret = (float32x4_t)(__p0);
33520	return __ret;	31588	return __ret;
33521	}	31589	}
33522	#else	31590	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {
33523	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {
33524	float32x4_t __ret;	31591	float32x4_t __ret;
33525	__ret = (float32x4_t)(__p0);	31592	__ret = (float32x4_t)(__p0);
33526	return __ret;	31593	return __ret;
33527	}	31594	}
33528	#endif	31595	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {
33529
33530	#ifdef __LITTLE_ENDIAN__
33531	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {
33532	float32x4_t __ret;	31596	float32x4_t __ret;
33533	__ret = (float32x4_t)(__p0);	31597	__ret = (float32x4_t)(__p0);
33534	return __ret;	31598	return __ret;
33535	}	31599	}
33536	#else	31600	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {
33537	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {
33538	float32x4_t __ret;	31601	float32x4_t __ret;
33539	__ret = (float32x4_t)(__p0);	31602	__ret = (float32x4_t)(__p0);
33540	return __ret;	31603	return __ret;
33541	}	31604	}
33542	#endif	31605	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {
33543
33544	#ifdef __LITTLE_ENDIAN__
33545	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {
33546	float32x4_t __ret;	31606	float32x4_t __ret;
33547	__ret = (float32x4_t)(__p0);	31607	__ret = (float32x4_t)(__p0);
33548	return __ret;	31608	return __ret;
33549	}	31609	}
33550	#else	31610	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {
33551	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {
33552	float32x4_t __ret;	31611	float32x4_t __ret;
33553	__ret = (float32x4_t)(__p0);	31612	__ret = (float32x4_t)(__p0);
33554	return __ret;	31613	return __ret;
33555	}	31614	}
33556	#endif	31615	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {
33557
33558	#ifdef __LITTLE_ENDIAN__
33559	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {
33560	float32x4_t __ret;	31616	float32x4_t __ret;
33561	__ret = (float32x4_t)(__p0);	31617	__ret = (float32x4_t)(__p0);
33562	return __ret;	31618	return __ret;
33563	}	31619	}
33564	#else	31620	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {
33565	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {	31621	float16x8_t __ret;
33566	float32x4_t __ret;	31622	__ret = (float16x8_t)(__p0);
33567	__ret = (float32x4_t)(__p0);
33568	return __ret;	31623	return __ret;
33569	}	31624	}
33570	#endif	31625	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {
33571		31626	float16x8_t __ret;
33572	#ifdef __LITTLE_ENDIAN__	31627	__ret = (float16x8_t)(__p0);
33573	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {
33574	float32x4_t __ret;
33575	__ret = (float32x4_t)(__p0);
33576	return __ret;	31628	return __ret;
33577	}	31629	}
33578	#else
33579	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {
33580	float32x4_t __ret;
33581	__ret = (float32x4_t)(__p0);
33582	return __ret;
33583	}
33584	#endif
33585
33586	#ifdef __LITTLE_ENDIAN__
33587	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {
33588	float32x4_t __ret;
33589	__ret = (float32x4_t)(__p0);
33590	return __ret;
33591	}
33592	#else
33593	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {
33594	float32x4_t __ret;
33595	__ret = (float32x4_t)(__p0);
33596	return __ret;
33597	}
33598	#endif
33599
33600	#ifdef __LITTLE_ENDIAN__
33601	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {
33602	float32x4_t __ret;
33603	__ret = (float32x4_t)(__p0);
33604	return __ret;
33605	}
33606	#else
33607	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {
33608	float32x4_t __ret;
33609	__ret = (float32x4_t)(__p0);
33610	return __ret;
33611	}
33612	#endif
33613
33614	#ifdef __LITTLE_ENDIAN__
33615	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {
33616	float32x4_t __ret;
33617	__ret = (float32x4_t)(__p0);
33618	return __ret;
33619	}
33620	#else
33621	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {
33622	float32x4_t __ret;
33623	__ret = (float32x4_t)(__p0);
33624	return __ret;
33625	}
33626	#endif
33627
33628	#ifdef __LITTLE_ENDIAN__
33629	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {
33630	float16x8_t __ret;
33631	__ret = (float16x8_t)(__p0);
33632	return __ret;
33633	}
33634	#else
33635	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {
33636	float16x8_t __ret;
33637	__ret = (float16x8_t)(__p0);
33638	return __ret;
33639	}
33640	#endif
33641
33642	#ifdef __LITTLE_ENDIAN__
33643	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {
33644	float16x8_t __ret;
33645	__ret = (float16x8_t)(__p0);
33646	return __ret;
33647	}
33648	#else
33649	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {
33650	float16x8_t __ret;
33651	__ret = (float16x8_t)(__p0);
33652	return __ret;
33653	}
33654	#endif
33655
33656	#ifdef __LITTLE_ENDIAN__
33657	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {
33658	float16x8_t __ret;
33659	__ret = (float16x8_t)(__p0);
33660	return __ret;
33661	}
33662	#else
33663	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {	31630	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {
33664	float16x8_t __ret;	31631	float16x8_t __ret;
33665	__ret = (float16x8_t)(__p0);	31632	__ret = (float16x8_t)(__p0);
33666	return __ret;	31633	return __ret;
33667	}	31634	}
33668	#endif
33669
33670	#ifdef __LITTLE_ENDIAN__
33671	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {
33672	float16x8_t __ret;
33673	__ret = (float16x8_t)(__p0);
33674	return __ret;
33675	}
33676	#else
33677	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {	31635	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {
33678	float16x8_t __ret;	31636	float16x8_t __ret;
33679	__ret = (float16x8_t)(__p0);	31637	__ret = (float16x8_t)(__p0);
33680	return __ret;	31638	return __ret;
33681	}	31639	}
33682	#endif
33683
33684	#ifdef __LITTLE_ENDIAN__
33685	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {
33686	float16x8_t __ret;
33687	__ret = (float16x8_t)(__p0);
33688	return __ret;
33689	}
33690	#else
33691	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {	31640	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {
33692	float16x8_t __ret;	31641	float16x8_t __ret;
33693	__ret = (float16x8_t)(__p0);	31642	__ret = (float16x8_t)(__p0);
33694	return __ret;	31643	return __ret;
33695	}	31644	}
33696	#endif
33697
33698	#ifdef __LITTLE_ENDIAN__
33699	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {
33700	float16x8_t __ret;
33701	__ret = (float16x8_t)(__p0);
33702	return __ret;
33703	}
33704	#else
33705	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {	31645	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {
33706	float16x8_t __ret;	31646	float16x8_t __ret;
33707	__ret = (float16x8_t)(__p0);	31647	__ret = (float16x8_t)(__p0);
33708	return __ret;	31648	return __ret;
33709	}	31649	}
33710	#endif
33711
33712	#ifdef __LITTLE_ENDIAN__
33713	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {
33714	float16x8_t __ret;
33715	__ret = (float16x8_t)(__p0);
33716	return __ret;
33717	}
33718	#else
33719	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {	31650	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {
33720	float16x8_t __ret;	31651	float16x8_t __ret;
33721	__ret = (float16x8_t)(__p0);	31652	__ret = (float16x8_t)(__p0);
33722	return __ret;	31653	return __ret;
33723	}	31654	}
33724	#endif
33725
33726	#ifdef __LITTLE_ENDIAN__
33727	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {
33728	float16x8_t __ret;
33729	__ret = (float16x8_t)(__p0);
33730	return __ret;
33731	}
33732	#else
33733	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {	31655	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {
33734	float16x8_t __ret;	31656	float16x8_t __ret;
33735	__ret = (float16x8_t)(__p0);	31657	__ret = (float16x8_t)(__p0);
33736	return __ret;	31658	return __ret;
33737	}	31659	}
33738	#endif
33739
33740	#ifdef __LITTLE_ENDIAN__
33741	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {
33742	float16x8_t __ret;
33743	__ret = (float16x8_t)(__p0);
33744	return __ret;
33745	}
33746	#else
33747	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {	31660	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {
33748	float16x8_t __ret;	31661	float16x8_t __ret;
33749	__ret = (float16x8_t)(__p0);	31662	__ret = (float16x8_t)(__p0);
33750	return __ret;	31663	return __ret;
33751	}	31664	}
33752	#endif
33753
33754	#ifdef __LITTLE_ENDIAN__
33755	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {
33756	float16x8_t __ret;
33757	__ret = (float16x8_t)(__p0);
33758	return __ret;
33759	}
33760	#else
33761	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {	31665	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {
33762	float16x8_t __ret;	31666	float16x8_t __ret;
33763	__ret = (float16x8_t)(__p0);	31667	__ret = (float16x8_t)(__p0);
33764	return __ret;	31668	return __ret;
33765	}	31669	}
33766	#endif
33767
33768	#ifdef __LITTLE_ENDIAN__
33769	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {
33770	float16x8_t __ret;
33771	__ret = (float16x8_t)(__p0);
33772	return __ret;
33773	}
33774	#else
33775	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {	31670	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {
33776	float16x8_t __ret;	31671	float16x8_t __ret;
33777	__ret = (float16x8_t)(__p0);	31672	__ret = (float16x8_t)(__p0);
33778	return __ret;	31673	return __ret;
33779	}	31674	}
33780	#endif
33781
33782	#ifdef __LITTLE_ENDIAN__
33783	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {
33784	int32x4_t __ret;
33785	__ret = (int32x4_t)(__p0);
33786	return __ret;
33787	}
33788	#else
33789	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {	31675	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {
33790	int32x4_t __ret;	31676	int32x4_t __ret;
33791	__ret = (int32x4_t)(__p0);	31677	__ret = (int32x4_t)(__p0);
33792	return __ret;	31678	return __ret;
33793	}	31679	}
33794	#endif
33795
33796	#ifdef __LITTLE_ENDIAN__
33797	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {
33798	int32x4_t __ret;
33799	__ret = (int32x4_t)(__p0);
33800	return __ret;
33801	}
33802	#else
33803	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {	31680	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {
33804	int32x4_t __ret;	31681	int32x4_t __ret;
33805	__ret = (int32x4_t)(__p0);	31682	__ret = (int32x4_t)(__p0);
33806	return __ret;	31683	return __ret;
33807	}	31684	}
33808	#endif
33809
33810	#ifdef __LITTLE_ENDIAN__
33811	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {
33812	int32x4_t __ret;
33813	__ret = (int32x4_t)(__p0);
33814	return __ret;
33815	}
33816	#else
33817	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {	31685	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {
33818	int32x4_t __ret;	31686	int32x4_t __ret;
33819	__ret = (int32x4_t)(__p0);	31687	__ret = (int32x4_t)(__p0);
33820	return __ret;	31688	return __ret;
33821	}	31689	}
33822	#endif
33823
33824	#ifdef __LITTLE_ENDIAN__
33825	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {
33826	int32x4_t __ret;
33827	__ret = (int32x4_t)(__p0);
33828	return __ret;
33829	}
33830	#else
33831	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {	31690	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {
33832	int32x4_t __ret;	31691	int32x4_t __ret;
33833	__ret = (int32x4_t)(__p0);	31692	__ret = (int32x4_t)(__p0);
33834	return __ret;	31693	return __ret;
33835	}	31694	}
33836	#endif
33837
33838	#ifdef __LITTLE_ENDIAN__
33839	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {
33840	int32x4_t __ret;
33841	__ret = (int32x4_t)(__p0);
33842	return __ret;
33843	}
33844	#else
33845	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {	31695	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {
33846	int32x4_t __ret;	31696	int32x4_t __ret;
33847	__ret = (int32x4_t)(__p0);	31697	__ret = (int32x4_t)(__p0);
33848	return __ret;	31698	return __ret;
33849	}	31699	}
33850	#endif
33851
33852	#ifdef __LITTLE_ENDIAN__
33853	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {
33854	int32x4_t __ret;
33855	__ret = (int32x4_t)(__p0);
33856	return __ret;
33857	}
33858	#else
33859	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {	31700	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {
33860	int32x4_t __ret;	31701	int32x4_t __ret;
33861	__ret = (int32x4_t)(__p0);	31702	__ret = (int32x4_t)(__p0);
33862	return __ret;	31703	return __ret;
33863	}	31704	}
33864	#endif
33865
33866	#ifdef __LITTLE_ENDIAN__
33867	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {
33868	int32x4_t __ret;
33869	__ret = (int32x4_t)(__p0);
33870	return __ret;
33871	}
33872	#else
33873	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {	31705	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {
33874	int32x4_t __ret;	31706	int32x4_t __ret;
33875	__ret = (int32x4_t)(__p0);	31707	__ret = (int32x4_t)(__p0);
33876	return __ret;	31708	return __ret;
33877	}	31709	}
33878	#endif
33879
33880	#ifdef __LITTLE_ENDIAN__
33881	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {
33882	int32x4_t __ret;
33883	__ret = (int32x4_t)(__p0);
33884	return __ret;
33885	}
33886	#else
33887	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {	31710	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {
33888	int32x4_t __ret;	31711	int32x4_t __ret;
33889	__ret = (int32x4_t)(__p0);	31712	__ret = (int32x4_t)(__p0);
33890	return __ret;	31713	return __ret;
33891	}	31714	}
33892	#endif
33893
33894	#ifdef __LITTLE_ENDIAN__
33895	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {
33896	int32x4_t __ret;
33897	__ret = (int32x4_t)(__p0);
33898	return __ret;
33899	}
33900	#else
33901	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {	31715	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {
33902	int32x4_t __ret;	31716	int32x4_t __ret;
33903	__ret = (int32x4_t)(__p0);	31717	__ret = (int32x4_t)(__p0);
33904	return __ret;	31718	return __ret;
33905	}	31719	}
33906	#endif
33907
33908	#ifdef __LITTLE_ENDIAN__
33909	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {
33910	int32x4_t __ret;
33911	__ret = (int32x4_t)(__p0);
33912	return __ret;
33913	}
33914	#else
33915	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {	31720	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {
33916	int32x4_t __ret;	31721	int32x4_t __ret;
33917	__ret = (int32x4_t)(__p0);	31722	__ret = (int32x4_t)(__p0);
33918	return __ret;	31723	return __ret;
33919	}	31724	}
33920	#endif
33921
33922	#ifdef __LITTLE_ENDIAN__
33923	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {
33924	int32x4_t __ret;
33925	__ret = (int32x4_t)(__p0);
33926	return __ret;
33927	}
33928	#else
33929	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {	31725	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {
33930	int32x4_t __ret;	31726	int32x4_t __ret;
33931	__ret = (int32x4_t)(__p0);	31727	__ret = (int32x4_t)(__p0);
33932	return __ret;	31728	return __ret;
33933	}	31729	}
33934	#endif
33935
33936	#ifdef __LITTLE_ENDIAN__
33937	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {
33938	int64x2_t __ret;
33939	__ret = (int64x2_t)(__p0);
33940	return __ret;
33941	}
33942	#else
33943	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {	31730	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {
33944	int64x2_t __ret;	31731	int64x2_t __ret;
33945	__ret = (int64x2_t)(__p0);	31732	__ret = (int64x2_t)(__p0);
33946	return __ret;	31733	return __ret;
33947	}	31734	}
33948	#endif
33949
33950	#ifdef __LITTLE_ENDIAN__
33951	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {
33952	int64x2_t __ret;
33953	__ret = (int64x2_t)(__p0);
33954	return __ret;
33955	}
33956	#else
33957	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {	31735	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {
33958	int64x2_t __ret;	31736	int64x2_t __ret;
33959	__ret = (int64x2_t)(__p0);	31737	__ret = (int64x2_t)(__p0);
33960	return __ret;	31738	return __ret;
33961	}	31739	}
33962	#endif
33963
33964	#ifdef __LITTLE_ENDIAN__
33965	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {
33966	int64x2_t __ret;
33967	__ret = (int64x2_t)(__p0);
33968	return __ret;
33969	}
33970	#else
33971	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {	31740	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {
33972	int64x2_t __ret;	31741	int64x2_t __ret;
33973	__ret = (int64x2_t)(__p0);	31742	__ret = (int64x2_t)(__p0);
33974	return __ret;	31743	return __ret;
33975	}	31744	}
33976	#endif
33977
33978	#ifdef __LITTLE_ENDIAN__
33979	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {
33980	int64x2_t __ret;
33981	__ret = (int64x2_t)(__p0);
33982	return __ret;
33983	}
33984	#else
33985	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {	31745	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {
33986	int64x2_t __ret;	31746	int64x2_t __ret;
33987	__ret = (int64x2_t)(__p0);	31747	__ret = (int64x2_t)(__p0);
33988	return __ret;	31748	return __ret;
33989	}	31749	}
33990	#endif
33991
33992	#ifdef __LITTLE_ENDIAN__
33993	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {
33994	int64x2_t __ret;
33995	__ret = (int64x2_t)(__p0);
33996	return __ret;
33997	}
33998	#else
33999	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {	31750	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {
34000	int64x2_t __ret;	31751	int64x2_t __ret;
34001	__ret = (int64x2_t)(__p0);	31752	__ret = (int64x2_t)(__p0);
34002	return __ret;	31753	return __ret;
34003	}	31754	}
34004	#endif
34005
34006	#ifdef __LITTLE_ENDIAN__
34007	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {
34008	int64x2_t __ret;
34009	__ret = (int64x2_t)(__p0);
34010	return __ret;
34011	}
34012	#else
34013	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {	31755	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {
34014	int64x2_t __ret;	31756	int64x2_t __ret;
34015	__ret = (int64x2_t)(__p0);	31757	__ret = (int64x2_t)(__p0);
34016	return __ret;	31758	return __ret;
34017	}	31759	}
34018	#endif
34019
34020	#ifdef __LITTLE_ENDIAN__
34021	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {
34022	int64x2_t __ret;
34023	__ret = (int64x2_t)(__p0);
34024	return __ret;
34025	}
34026	#else
34027	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {	31760	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {
34028	int64x2_t __ret;	31761	int64x2_t __ret;
34029	__ret = (int64x2_t)(__p0);	31762	__ret = (int64x2_t)(__p0);
34030	return __ret;	31763	return __ret;
34031	}	31764	}
34032	#endif
34033
34034	#ifdef __LITTLE_ENDIAN__
34035	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {
34036	int64x2_t __ret;
34037	__ret = (int64x2_t)(__p0);
34038	return __ret;
34039	}
34040	#else
34041	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {	31765	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {
34042	int64x2_t __ret;	31766	int64x2_t __ret;
34043	__ret = (int64x2_t)(__p0);	31767	__ret = (int64x2_t)(__p0);
34044	return __ret;	31768	return __ret;
34045	}	31769	}
34046	#endif
34047
34048	#ifdef __LITTLE_ENDIAN__
34049	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {
34050	int64x2_t __ret;
34051	__ret = (int64x2_t)(__p0);
34052	return __ret;
34053	}
34054	#else
34055	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {	31770	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {
34056	int64x2_t __ret;	31771	int64x2_t __ret;
34057	__ret = (int64x2_t)(__p0);	31772	__ret = (int64x2_t)(__p0);
34058	return __ret;	31773	return __ret;
34059	}	31774	}
34060	#endif
34061
34062	#ifdef __LITTLE_ENDIAN__
34063	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {
34064	int64x2_t __ret;
34065	__ret = (int64x2_t)(__p0);
34066	return __ret;
34067	}
34068	#else
34069	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {	31775	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {
34070	int64x2_t __ret;	31776	int64x2_t __ret;
34071	__ret = (int64x2_t)(__p0);	31777	__ret = (int64x2_t)(__p0);
34072	return __ret;	31778	return __ret;
34073	}	31779	}
34074	#endif
34075
34076	#ifdef __LITTLE_ENDIAN__
34077	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {
34078	int64x2_t __ret;
34079	__ret = (int64x2_t)(__p0);
34080	return __ret;
34081	}
34082	#else
34083	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {	31780	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {
34084	int64x2_t __ret;	31781	int64x2_t __ret;
34085	__ret = (int64x2_t)(__p0);	31782	__ret = (int64x2_t)(__p0);
34086	return __ret;	31783	return __ret;
34087	}	31784	}
34088	#endif
34089
34090	#ifdef __LITTLE_ENDIAN__
34091	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {
34092	int16x8_t __ret;
34093	__ret = (int16x8_t)(__p0);
34094	return __ret;
34095	}
34096	#else
34097	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {	31785	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {
34098	int16x8_t __ret;	31786	int16x8_t __ret;
34099	__ret = (int16x8_t)(__p0);	31787	__ret = (int16x8_t)(__p0);
34100	return __ret;	31788	return __ret;
34101	}	31789	}
34102	#endif
34103
34104	#ifdef __LITTLE_ENDIAN__
34105	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {
34106	int16x8_t __ret;
34107	__ret = (int16x8_t)(__p0);
34108	return __ret;
34109	}
34110	#else
34111	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {	31790	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {
34112	int16x8_t __ret;	31791	int16x8_t __ret;
34113	__ret = (int16x8_t)(__p0);	31792	__ret = (int16x8_t)(__p0);
34114	return __ret;	31793	return __ret;
34115	}	31794	}
34116	#endif
34117
34118	#ifdef __LITTLE_ENDIAN__
34119	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {
34120	int16x8_t __ret;
34121	__ret = (int16x8_t)(__p0);
34122	return __ret;
34123	}
34124	#else
34125	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {	31795	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {
34126	int16x8_t __ret;	31796	int16x8_t __ret;
34127	__ret = (int16x8_t)(__p0);	31797	__ret = (int16x8_t)(__p0);
34128	return __ret;	31798	return __ret;
34129	}	31799	}
34130	#endif
34131
34132	#ifdef __LITTLE_ENDIAN__
34133	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {
34134	int16x8_t __ret;
34135	__ret = (int16x8_t)(__p0);
34136	return __ret;
34137	}
34138	#else
34139	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {	31800	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {
34140	int16x8_t __ret;	31801	int16x8_t __ret;
34141	__ret = (int16x8_t)(__p0);	31802	__ret = (int16x8_t)(__p0);
34142	return __ret;	31803	return __ret;
34143	}	31804	}
34144	#endif
34145
34146	#ifdef __LITTLE_ENDIAN__
34147	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {
34148	int16x8_t __ret;
34149	__ret = (int16x8_t)(__p0);
34150	return __ret;
34151	}
34152	#else
34153	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {	31805	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {
34154	int16x8_t __ret;	31806	int16x8_t __ret;
34155	__ret = (int16x8_t)(__p0);	31807	__ret = (int16x8_t)(__p0);
34156	return __ret;	31808	return __ret;
34157	}	31809	}
34158	#endif
34159
34160	#ifdef __LITTLE_ENDIAN__
34161	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {
34162	int16x8_t __ret;
34163	__ret = (int16x8_t)(__p0);
34164	return __ret;
34165	}
34166	#else
34167	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {	31810	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {
34168	int16x8_t __ret;	31811	int16x8_t __ret;
34169	__ret = (int16x8_t)(__p0);	31812	__ret = (int16x8_t)(__p0);
34170	return __ret;	31813	return __ret;
34171	}	31814	}
34172	#endif
34173
34174	#ifdef __LITTLE_ENDIAN__
34175	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {
34176	int16x8_t __ret;
34177	__ret = (int16x8_t)(__p0);
34178	return __ret;
34179	}
34180	#else
34181	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {	31815	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {
34182	int16x8_t __ret;	31816	int16x8_t __ret;
34183	__ret = (int16x8_t)(__p0);	31817	__ret = (int16x8_t)(__p0);
34184	return __ret;	31818	return __ret;
34185	}	31819	}
34186	#endif
34187
34188	#ifdef __LITTLE_ENDIAN__
34189	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {
34190	int16x8_t __ret;
34191	__ret = (int16x8_t)(__p0);
34192	return __ret;
34193	}
34194	#else
34195	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {	31820	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {
34196	int16x8_t __ret;	31821	int16x8_t __ret;
34197	__ret = (int16x8_t)(__p0);	31822	__ret = (int16x8_t)(__p0);
34198	return __ret;	31823	return __ret;
34199	}	31824	}
34200	#endif
34201
34202	#ifdef __LITTLE_ENDIAN__
34203	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {
34204	int16x8_t __ret;
34205	__ret = (int16x8_t)(__p0);
34206	return __ret;
34207	}
34208	#else
34209	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {	31825	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {
34210	int16x8_t __ret;	31826	int16x8_t __ret;
34211	__ret = (int16x8_t)(__p0);	31827	__ret = (int16x8_t)(__p0);
34212	return __ret;	31828	return __ret;
34213	}	31829	}
34214	#endif
34215
34216	#ifdef __LITTLE_ENDIAN__
34217	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {
34218	int16x8_t __ret;
34219	__ret = (int16x8_t)(__p0);
34220	return __ret;
34221	}
34222	#else
34223	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {	31830	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {
34224	int16x8_t __ret;	31831	int16x8_t __ret;
34225	__ret = (int16x8_t)(__p0);	31832	__ret = (int16x8_t)(__p0);
34226	return __ret;	31833	return __ret;
34227	}	31834	}
34228	#endif
34229
34230	#ifdef __LITTLE_ENDIAN__
34231	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {
34232	int16x8_t __ret;
34233	__ret = (int16x8_t)(__p0);
34234	return __ret;
34235	}
34236	#else
34237	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {	31835	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {
34238	int16x8_t __ret;	31836	int16x8_t __ret;
34239	__ret = (int16x8_t)(__p0);	31837	__ret = (int16x8_t)(__p0);
34240	return __ret;	31838	return __ret;
34241	}	31839	}
34242	#endif
34243
34244	#ifdef __LITTLE_ENDIAN__
34245	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {
34246	uint8x8_t __ret;
34247	__ret = (uint8x8_t)(__p0);
34248	return __ret;
34249	}
34250	#else
34251	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {	31840	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {
34252	uint8x8_t __ret;	31841	uint8x8_t __ret;
34253	__ret = (uint8x8_t)(__p0);	31842	__ret = (uint8x8_t)(__p0);
34254	return __ret;	31843	return __ret;
34255	}	31844	}
34256	#endif
34257
34258	#ifdef __LITTLE_ENDIAN__
34259	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {
34260	uint8x8_t __ret;
34261	__ret = (uint8x8_t)(__p0);
34262	return __ret;
34263	}
34264	#else
34265	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {	31845	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {
34266	uint8x8_t __ret;	31846	uint8x8_t __ret;
34267	__ret = (uint8x8_t)(__p0);	31847	__ret = (uint8x8_t)(__p0);
34268	return __ret;	31848	return __ret;
34269	}	31849	}
34270	#endif
34271
34272	#ifdef __LITTLE_ENDIAN__
34273	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {
34274	uint8x8_t __ret;
34275	__ret = (uint8x8_t)(__p0);
34276	return __ret;
34277	}
34278	#else
34279	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {	31850	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {
34280	uint8x8_t __ret;	31851	uint8x8_t __ret;
34281	__ret = (uint8x8_t)(__p0);	31852	__ret = (uint8x8_t)(__p0);
34282	return __ret;	31853	return __ret;
34283	}	31854	}
34284	#endif
34285
34286	#ifdef __LITTLE_ENDIAN__
34287	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {	31855	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {
34288	uint8x8_t __ret;	31856	uint8x8_t __ret;
34289	__ret = (uint8x8_t)(__p0);	31857	__ret = (uint8x8_t)(__p0);
34290	return __ret;	31858	return __ret;
34291	}	31859	}
34292	#else	31860	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {
34293	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {
34294	uint8x8_t __ret;	31861	uint8x8_t __ret;
34295	__ret = (uint8x8_t)(__p0);	31862	__ret = (uint8x8_t)(__p0);
34296	return __ret;	31863	return __ret;
34297	}	31864	}
34298	#endif	31865	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
34299
34300	#ifdef __LITTLE_ENDIAN__
34301	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {
34302	uint8x8_t __ret;	31866	uint8x8_t __ret;
34303	__ret = (uint8x8_t)(__p0);	31867	__ret = (uint8x8_t)(__p0);
34304	return __ret;	31868	return __ret;
34305	}	31869	}
34306	#else	31870	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {
34307	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {
34308	uint8x8_t __ret;	31871	uint8x8_t __ret;
34309	__ret = (uint8x8_t)(__p0);	31872	__ret = (uint8x8_t)(__p0);
34310	return __ret;	31873	return __ret;
34311	}	31874	}
34312	#endif	31875	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {
34313
34314	#ifdef __LITTLE_ENDIAN__
34315	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
34316	uint8x8_t __ret;	31876	uint8x8_t __ret;
34317	__ret = (uint8x8_t)(__p0);	31877	__ret = (uint8x8_t)(__p0);
34318	return __ret;	31878	return __ret;
34319	}	31879	}
34320	#else	31880	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {
34321	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
34322	uint8x8_t __ret;	31881	uint8x8_t __ret;
34323	__ret = (uint8x8_t)(__p0);	31882	__ret = (uint8x8_t)(__p0);
34324	return __ret;	31883	return __ret;
34325	}	31884	}
34326	#endif	31885	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {
34327
34328	#ifdef __LITTLE_ENDIAN__
34329	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {
34330	uint8x8_t __ret;	31886	uint8x8_t __ret;
34331	__ret = (uint8x8_t)(__p0);	31887	__ret = (uint8x8_t)(__p0);
34332	return __ret;	31888	return __ret;
34333	}	31889	}
34334	#else	31890	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {
34335	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {
34336	uint8x8_t __ret;	31891	uint8x8_t __ret;
34337	__ret = (uint8x8_t)(__p0);	31892	__ret = (uint8x8_t)(__p0);
34338	return __ret;	31893	return __ret;
34339	}	31894	}
34340	#endif
34341
34342	#ifdef __LITTLE_ENDIAN__
34343	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {
34344	uint8x8_t __ret;
34345	__ret = (uint8x8_t)(__p0);
34346	return __ret;
34347	}
34348	#else
34349	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {
34350	uint8x8_t __ret;
34351	__ret = (uint8x8_t)(__p0);
34352	return __ret;
34353	}
34354	#endif
34355
34356	#ifdef __LITTLE_ENDIAN__
34357	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {
34358	uint8x8_t __ret;
34359	__ret = (uint8x8_t)(__p0);
34360	return __ret;
34361	}
34362	#else
34363	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {
34364	uint8x8_t __ret;
34365	__ret = (uint8x8_t)(__p0);
34366	return __ret;
34367	}
34368	#endif
34369
34370	#ifdef __LITTLE_ENDIAN__
34371	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {
34372	uint8x8_t __ret;
34373	__ret = (uint8x8_t)(__p0);
34374	return __ret;
34375	}
34376	#else
34377	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {
34378	uint8x8_t __ret;
34379	__ret = (uint8x8_t)(__p0);
34380	return __ret;
34381	}
34382	#endif
34383
34384	#ifdef __LITTLE_ENDIAN__
34385	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {
34386	uint8x8_t __ret;
34387	__ret = (uint8x8_t)(__p0);
34388	return __ret;
34389	}
34390	#else
34391	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {
34392	uint8x8_t __ret;
34393	__ret = (uint8x8_t)(__p0);
34394	return __ret;
34395	}
34396	#endif
34397
34398	#ifdef __LITTLE_ENDIAN__
34399	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {
34400	uint32x2_t __ret;
34401	__ret = (uint32x2_t)(__p0);
34402	return __ret;
34403	}
34404	#else
34405	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {	31895	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {
34406	uint32x2_t __ret;	31896	uint32x2_t __ret;
34407	__ret = (uint32x2_t)(__p0);	31897	__ret = (uint32x2_t)(__p0);
34408	return __ret;	31898	return __ret;
34409	}	31899	}
34410	#endif
34411
34412	#ifdef __LITTLE_ENDIAN__
34413	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {
34414	uint32x2_t __ret;
34415	__ret = (uint32x2_t)(__p0);
34416	return __ret;
34417	}
34418	#else
34419	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {	31900	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {
34420	uint32x2_t __ret;	31901	uint32x2_t __ret;
34421	__ret = (uint32x2_t)(__p0);	31902	__ret = (uint32x2_t)(__p0);
34422	return __ret;	31903	return __ret;
34423	}	31904	}
34424	#endif
34425
34426	#ifdef __LITTLE_ENDIAN__
34427	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {
34428	uint32x2_t __ret;
34429	__ret = (uint32x2_t)(__p0);
34430	return __ret;
34431	}
34432	#else
34433	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {	31905	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {
34434	uint32x2_t __ret;	31906	uint32x2_t __ret;
34435	__ret = (uint32x2_t)(__p0);	31907	__ret = (uint32x2_t)(__p0);
34436	return __ret;	31908	return __ret;
34437	}	31909	}
34438	#endif
34439
34440	#ifdef __LITTLE_ENDIAN__
34441	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {
34442	uint32x2_t __ret;
34443	__ret = (uint32x2_t)(__p0);
34444	return __ret;
34445	}
34446	#else
34447	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {	31910	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {
34448	uint32x2_t __ret;	31911	uint32x2_t __ret;
34449	__ret = (uint32x2_t)(__p0);	31912	__ret = (uint32x2_t)(__p0);
34450	return __ret;	31913	return __ret;
34451	}	31914	}
34452	#endif
34453
34454	#ifdef __LITTLE_ENDIAN__
34455	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {
34456	uint32x2_t __ret;
34457	__ret = (uint32x2_t)(__p0);
34458	return __ret;
34459	}
34460	#else
34461	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {	31915	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {
34462	uint32x2_t __ret;	31916	uint32x2_t __ret;
34463	__ret = (uint32x2_t)(__p0);	31917	__ret = (uint32x2_t)(__p0);
34464	return __ret;	31918	return __ret;
34465	}	31919	}
34466	#endif
34467
34468	#ifdef __LITTLE_ENDIAN__
34469	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
34470	uint32x2_t __ret;
34471	__ret = (uint32x2_t)(__p0);
34472	return __ret;
34473	}
34474	#else
34475	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {	31920	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
34476	uint32x2_t __ret;	31921	uint32x2_t __ret;
34477	__ret = (uint32x2_t)(__p0);	31922	__ret = (uint32x2_t)(__p0);
34478	return __ret;	31923	return __ret;
34479	}	31924	}
34480	#endif
34481
34482	#ifdef __LITTLE_ENDIAN__
34483	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {
34484	uint32x2_t __ret;
34485	__ret = (uint32x2_t)(__p0);
34486	return __ret;
34487	}
34488	#else
34489	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {	31925	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {
34490	uint32x2_t __ret;	31926	uint32x2_t __ret;
34491	__ret = (uint32x2_t)(__p0);	31927	__ret = (uint32x2_t)(__p0);
34492	return __ret;	31928	return __ret;
34493	}	31929	}
34494	#endif
34495
34496	#ifdef __LITTLE_ENDIAN__
34497	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {
34498	uint32x2_t __ret;
34499	__ret = (uint32x2_t)(__p0);
34500	return __ret;
34501	}
34502	#else
34503	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {	31930	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {
34504	uint32x2_t __ret;	31931	uint32x2_t __ret;
34505	__ret = (uint32x2_t)(__p0);	31932	__ret = (uint32x2_t)(__p0);
34506	return __ret;	31933	return __ret;
34507	}	31934	}
34508	#endif
34509
34510	#ifdef __LITTLE_ENDIAN__
34511	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {
34512	uint32x2_t __ret;
34513	__ret = (uint32x2_t)(__p0);
34514	return __ret;
34515	}
34516	#else
34517	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {	31935	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {
34518	uint32x2_t __ret;	31936	uint32x2_t __ret;
34519	__ret = (uint32x2_t)(__p0);	31937	__ret = (uint32x2_t)(__p0);
34520	return __ret;	31938	return __ret;
34521	}	31939	}
34522	#endif
34523
34524	#ifdef __LITTLE_ENDIAN__
34525	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {
34526	uint32x2_t __ret;
34527	__ret = (uint32x2_t)(__p0);
34528	return __ret;
34529	}
34530	#else
34531	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {	31940	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {
34532	uint32x2_t __ret;	31941	uint32x2_t __ret;
34533	__ret = (uint32x2_t)(__p0);	31942	__ret = (uint32x2_t)(__p0);
34534	return __ret;	31943	return __ret;
34535	}	31944	}
34536	#endif
34537
34538	#ifdef __LITTLE_ENDIAN__
34539	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {
34540	uint32x2_t __ret;
34541	__ret = (uint32x2_t)(__p0);
34542	return __ret;
34543	}
34544	#else
34545	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {	31945	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {
34546	uint32x2_t __ret;	31946	uint32x2_t __ret;
34547	__ret = (uint32x2_t)(__p0);	31947	__ret = (uint32x2_t)(__p0);
34548	return __ret;	31948	return __ret;
34549	}	31949	}
34550	#endif
34551
34552	#ifdef __LITTLE_ENDIAN__
34553	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {
34554	uint64x1_t __ret;
34555	__ret = (uint64x1_t)(__p0);
34556	return __ret;
34557	}
34558	#else
34559	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {	31950	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {
34560	uint64x1_t __ret;	31951	uint64x1_t __ret;
34561	__ret = (uint64x1_t)(__p0);	31952	__ret = (uint64x1_t)(__p0);
34562	return __ret;	31953	return __ret;
34563	}	31954	}
34564	#endif
34565
34566	#ifdef __LITTLE_ENDIAN__
34567	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {
34568	uint64x1_t __ret;
34569	__ret = (uint64x1_t)(__p0);
34570	return __ret;
34571	}
34572	#else
34573	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {	31955	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {
34574	uint64x1_t __ret;	31956	uint64x1_t __ret;
34575	__ret = (uint64x1_t)(__p0);	31957	__ret = (uint64x1_t)(__p0);
34576	return __ret;	31958	return __ret;
34577	}	31959	}
34578	#endif
34579
34580	#ifdef __LITTLE_ENDIAN__
34581	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {
34582	uint64x1_t __ret;
34583	__ret = (uint64x1_t)(__p0);
34584	return __ret;
34585	}
34586	#else
34587	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {	31960	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {
34588	uint64x1_t __ret;	31961	uint64x1_t __ret;
34589	__ret = (uint64x1_t)(__p0);	31962	__ret = (uint64x1_t)(__p0);
34590	return __ret;	31963	return __ret;
34591	}	31964	}
34592	#endif
34593
34594	#ifdef __LITTLE_ENDIAN__
34595	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {
34596	uint64x1_t __ret;
34597	__ret = (uint64x1_t)(__p0);
34598	return __ret;
34599	}
34600	#else
34601	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {	31965	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {
34602	uint64x1_t __ret;	31966	uint64x1_t __ret;
34603	__ret = (uint64x1_t)(__p0);	31967	__ret = (uint64x1_t)(__p0);
34604	return __ret;	31968	return __ret;
34605	}	31969	}
34606	#endif
34607
34608	#ifdef __LITTLE_ENDIAN__
34609	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {
34610	uint64x1_t __ret;
34611	__ret = (uint64x1_t)(__p0);
34612	return __ret;
34613	}
34614	#else
34615	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {	31970	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {
34616	uint64x1_t __ret;	31971	uint64x1_t __ret;
34617	__ret = (uint64x1_t)(__p0);	31972	__ret = (uint64x1_t)(__p0);
34618	return __ret;	31973	return __ret;
34619	}	31974	}
34620	#endif
34621
34622	#ifdef __LITTLE_ENDIAN__
34623	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
34624	uint64x1_t __ret;
34625	__ret = (uint64x1_t)(__p0);
34626	return __ret;
34627	}
34628	#else
34629	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {	31975	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
34630	uint64x1_t __ret;	31976	uint64x1_t __ret;
34631	__ret = (uint64x1_t)(__p0);	31977	__ret = (uint64x1_t)(__p0);
34632	return __ret;	31978	return __ret;
34633	}	31979	}
34634	#endif
34635
34636	#ifdef __LITTLE_ENDIAN__
34637	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {
34638	uint64x1_t __ret;
34639	__ret = (uint64x1_t)(__p0);
34640	return __ret;
34641	}
34642	#else
34643	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {	31980	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {
34644	uint64x1_t __ret;	31981	uint64x1_t __ret;
34645	__ret = (uint64x1_t)(__p0);	31982	__ret = (uint64x1_t)(__p0);
34646	return __ret;	31983	return __ret;
34647	}	31984	}
34648	#endif
34649
34650	#ifdef __LITTLE_ENDIAN__
34651	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {
34652	uint64x1_t __ret;
34653	__ret = (uint64x1_t)(__p0);
34654	return __ret;
34655	}
34656	#else
34657	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {	31985	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {
34658	uint64x1_t __ret;	31986	uint64x1_t __ret;
34659	__ret = (uint64x1_t)(__p0);	31987	__ret = (uint64x1_t)(__p0);
34660	return __ret;	31988	return __ret;
34661	}	31989	}
34662	#endif
34663
34664	#ifdef __LITTLE_ENDIAN__
34665	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {
34666	uint64x1_t __ret;
34667	__ret = (uint64x1_t)(__p0);
34668	return __ret;
34669	}
34670	#else
34671	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {	31990	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {
34672	uint64x1_t __ret;	31991	uint64x1_t __ret;
34673	__ret = (uint64x1_t)(__p0);	31992	__ret = (uint64x1_t)(__p0);
34674	return __ret;	31993	return __ret;
34675	}	31994	}
34676	#endif
34677
34678	#ifdef __LITTLE_ENDIAN__
34679	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {
34680	uint64x1_t __ret;
34681	__ret = (uint64x1_t)(__p0);
34682	return __ret;
34683	}
34684	#else
34685	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {	31995	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {
34686	uint64x1_t __ret;	31996	uint64x1_t __ret;
34687	__ret = (uint64x1_t)(__p0);	31997	__ret = (uint64x1_t)(__p0);
34688	return __ret;	31998	return __ret;
34689	}	31999	}
34690	#endif
34691
34692	#ifdef __LITTLE_ENDIAN__
34693	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {
34694	uint64x1_t __ret;
34695	__ret = (uint64x1_t)(__p0);
34696	return __ret;
34697	}
34698	#else
34699	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {	32000	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {
34700	uint64x1_t __ret;	32001	uint64x1_t __ret;
34701	__ret = (uint64x1_t)(__p0);	32002	__ret = (uint64x1_t)(__p0);
34702	return __ret;	32003	return __ret;
34703	}	32004	}
34704	#endif
34705
34706	#ifdef __LITTLE_ENDIAN__
34707	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {
34708	uint16x4_t __ret;
34709	__ret = (uint16x4_t)(__p0);
34710	return __ret;
34711	}
34712	#else
34713	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {	32005	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {
34714	uint16x4_t __ret;	32006	uint16x4_t __ret;
34715	__ret = (uint16x4_t)(__p0);	32007	__ret = (uint16x4_t)(__p0);
34716	return __ret;	32008	return __ret;
34717	}	32009	}
34718	#endif
34719
34720	#ifdef __LITTLE_ENDIAN__
34721	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {
34722	uint16x4_t __ret;
34723	__ret = (uint16x4_t)(__p0);
34724	return __ret;
34725	}
34726	#else
34727	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {	32010	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {
34728	uint16x4_t __ret;	32011	uint16x4_t __ret;
34729	__ret = (uint16x4_t)(__p0);	32012	__ret = (uint16x4_t)(__p0);
34730	return __ret;	32013	return __ret;
34731	}	32014	}
34732	#endif
34733
34734	#ifdef __LITTLE_ENDIAN__
34735	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {
34736	uint16x4_t __ret;
34737	__ret = (uint16x4_t)(__p0);
34738	return __ret;
34739	}
34740	#else
34741	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {	32015	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {
34742	uint16x4_t __ret;	32016	uint16x4_t __ret;
34743	__ret = (uint16x4_t)(__p0);	32017	__ret = (uint16x4_t)(__p0);
34744	return __ret;	32018	return __ret;
34745	}	32019	}
34746	#endif
34747
34748	#ifdef __LITTLE_ENDIAN__
34749	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {
34750	uint16x4_t __ret;
34751	__ret = (uint16x4_t)(__p0);
34752	return __ret;
34753	}
34754	#else
34755	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {	32020	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {
34756	uint16x4_t __ret;	32021	uint16x4_t __ret;
34757	__ret = (uint16x4_t)(__p0);	32022	__ret = (uint16x4_t)(__p0);
34758	return __ret;	32023	return __ret;
34759	}	32024	}
34760	#endif
34761
34762	#ifdef __LITTLE_ENDIAN__
34763	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {
34764	uint16x4_t __ret;
34765	__ret = (uint16x4_t)(__p0);
34766	return __ret;
34767	}
34768	#else
34769	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {	32025	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {
34770	uint16x4_t __ret;	32026	uint16x4_t __ret;
34771	__ret = (uint16x4_t)(__p0);	32027	__ret = (uint16x4_t)(__p0);
34772	return __ret;	32028	return __ret;
34773	}	32029	}
34774	#endif
34775
34776	#ifdef __LITTLE_ENDIAN__
34777	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
34778	uint16x4_t __ret;
34779	__ret = (uint16x4_t)(__p0);
34780	return __ret;
34781	}
34782	#else
34783	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {	32030	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
34784	uint16x4_t __ret;	32031	uint16x4_t __ret;
34785	__ret = (uint16x4_t)(__p0);	32032	__ret = (uint16x4_t)(__p0);
34786	return __ret;	32033	return __ret;
34787	}	32034	}
34788	#endif
34789
34790	#ifdef __LITTLE_ENDIAN__
34791	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {
34792	uint16x4_t __ret;
34793	__ret = (uint16x4_t)(__p0);
34794	return __ret;
34795	}
34796	#else
34797	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {	32035	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {
34798	uint16x4_t __ret;	32036	uint16x4_t __ret;
34799	__ret = (uint16x4_t)(__p0);	32037	__ret = (uint16x4_t)(__p0);
34800	return __ret;	32038	return __ret;
34801	}	32039	}
34802	#endif
34803
34804	#ifdef __LITTLE_ENDIAN__
34805	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {
34806	uint16x4_t __ret;
34807	__ret = (uint16x4_t)(__p0);
34808	return __ret;
34809	}
34810	#else
34811	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {	32040	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {
34812	uint16x4_t __ret;	32041	uint16x4_t __ret;
34813	__ret = (uint16x4_t)(__p0);	32042	__ret = (uint16x4_t)(__p0);
34814	return __ret;	32043	return __ret;
34815	}	32044	}
34816	#endif
34817
34818	#ifdef __LITTLE_ENDIAN__
34819	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {
34820	uint16x4_t __ret;
34821	__ret = (uint16x4_t)(__p0);
34822	return __ret;
34823	}
34824	#else
34825	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {	32045	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {
34826	uint16x4_t __ret;	32046	uint16x4_t __ret;
34827	__ret = (uint16x4_t)(__p0);	32047	__ret = (uint16x4_t)(__p0);
34828	return __ret;	32048	return __ret;
34829	}	32049	}
34830	#endif
34831
34832	#ifdef __LITTLE_ENDIAN__
34833	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {
34834	uint16x4_t __ret;
34835	__ret = (uint16x4_t)(__p0);
34836	return __ret;
34837	}
34838	#else
34839	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {	32050	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {
34840	uint16x4_t __ret;	32051	uint16x4_t __ret;
34841	__ret = (uint16x4_t)(__p0);	32052	__ret = (uint16x4_t)(__p0);
34842	return __ret;	32053	return __ret;
34843	}	32054	}
34844	#endif
34845
34846	#ifdef __LITTLE_ENDIAN__
34847	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {
34848	uint16x4_t __ret;
34849	__ret = (uint16x4_t)(__p0);
34850	return __ret;
34851	}
34852	#else
34853	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {	32055	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {
34854	uint16x4_t __ret;	32056	uint16x4_t __ret;
34855	__ret = (uint16x4_t)(__p0);	32057	__ret = (uint16x4_t)(__p0);
34856	return __ret;	32058	return __ret;
34857	}	32059	}
34858	#endif
34859
34860	#ifdef __LITTLE_ENDIAN__
34861	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
34862	int8x8_t __ret;
34863	__ret = (int8x8_t)(__p0);
34864	return __ret;
34865	}
34866	#else
34867	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {	32060	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
34868	int8x8_t __ret;	32061	int8x8_t __ret;
34869	__ret = (int8x8_t)(__p0);	32062	__ret = (int8x8_t)(__p0);
34870	return __ret;	32063	return __ret;
34871	}	32064	}
34872	#endif
34873
34874	#ifdef __LITTLE_ENDIAN__
34875	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
34876	int8x8_t __ret;
34877	__ret = (int8x8_t)(__p0);
34878	return __ret;
34879	}
34880	#else
34881	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {	32065	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
34882	int8x8_t __ret;	32066	int8x8_t __ret;
34883	__ret = (int8x8_t)(__p0);	32067	__ret = (int8x8_t)(__p0);
34884	return __ret;	32068	return __ret;
34885	}	32069	}
34886	#endif
34887
34888	#ifdef __LITTLE_ENDIAN__
34889	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
34890	int8x8_t __ret;
34891	__ret = (int8x8_t)(__p0);
34892	return __ret;
34893	}
34894	#else
34895	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {	32070	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
34896	int8x8_t __ret;	32071	int8x8_t __ret;
34897	__ret = (int8x8_t)(__p0);	32072	__ret = (int8x8_t)(__p0);
34898	return __ret;	32073	return __ret;
34899	}	32074	}
34900	#endif
34901
34902	#ifdef __LITTLE_ENDIAN__
34903	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
34904	int8x8_t __ret;
34905	__ret = (int8x8_t)(__p0);
34906	return __ret;
34907	}
34908	#else
34909	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {	32075	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
34910	int8x8_t __ret;	32076	int8x8_t __ret;
34911	__ret = (int8x8_t)(__p0);	32077	__ret = (int8x8_t)(__p0);
34912	return __ret;	32078	return __ret;
34913	}	32079	}
34914	#endif
34915
34916	#ifdef __LITTLE_ENDIAN__
34917	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
34918	int8x8_t __ret;
34919	__ret = (int8x8_t)(__p0);
34920	return __ret;
34921	}
34922	#else
34923	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {	32080	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
34924	int8x8_t __ret;	32081	int8x8_t __ret;
34925	__ret = (int8x8_t)(__p0);	32082	__ret = (int8x8_t)(__p0);
34926	return __ret;	32083	return __ret;
34927	}	32084	}
34928	#endif
34929
34930	#ifdef __LITTLE_ENDIAN__
34931	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
34932	int8x8_t __ret;
34933	__ret = (int8x8_t)(__p0);
34934	return __ret;
34935	}
34936	#else
34937	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {	32085	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
34938	int8x8_t __ret;	32086	int8x8_t __ret;
34939	__ret = (int8x8_t)(__p0);	32087	__ret = (int8x8_t)(__p0);
34940	return __ret;	32088	return __ret;
34941	}	32089	}
34942	#endif
34943
34944	#ifdef __LITTLE_ENDIAN__
34945	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
34946	int8x8_t __ret;
34947	__ret = (int8x8_t)(__p0);
34948	return __ret;
34949	}
34950	#else
34951	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {	32090	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
34952	int8x8_t __ret;	32091	int8x8_t __ret;
34953	__ret = (int8x8_t)(__p0);	32092	__ret = (int8x8_t)(__p0);
34954	return __ret;	32093	return __ret;
34955	}	32094	}
34956	#endif
34957
34958	#ifdef __LITTLE_ENDIAN__
34959	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
34960	int8x8_t __ret;
34961	__ret = (int8x8_t)(__p0);
34962	return __ret;
34963	}
34964	#else
34965	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {	32095	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
34966	int8x8_t __ret;	32096	int8x8_t __ret;
34967	__ret = (int8x8_t)(__p0);	32097	__ret = (int8x8_t)(__p0);
34968	return __ret;	32098	return __ret;
34969	}	32099	}
34970	#endif
34971
34972	#ifdef __LITTLE_ENDIAN__
34973	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
34974	int8x8_t __ret;
34975	__ret = (int8x8_t)(__p0);
34976	return __ret;
34977	}
34978	#else
34979	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {	32100	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
34980	int8x8_t __ret;	32101	int8x8_t __ret;
34981	__ret = (int8x8_t)(__p0);	32102	__ret = (int8x8_t)(__p0);
34982	return __ret;	32103	return __ret;
34983	}	32104	}
34984	#endif
34985
34986	#ifdef __LITTLE_ENDIAN__
34987	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
34988	int8x8_t __ret;
34989	__ret = (int8x8_t)(__p0);
34990	return __ret;
34991	}
34992	#else
34993	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {	32105	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
34994	int8x8_t __ret;	32106	int8x8_t __ret;
34995	__ret = (int8x8_t)(__p0);	32107	__ret = (int8x8_t)(__p0);
34996	return __ret;	32108	return __ret;
34997	}	32109	}
34998	#endif
34999
35000	#ifdef __LITTLE_ENDIAN__
35001	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
35002	int8x8_t __ret;
35003	__ret = (int8x8_t)(__p0);
35004	return __ret;
35005	}
35006	#else
35007	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {	32110	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
35008	int8x8_t __ret;	32111	int8x8_t __ret;
35009	__ret = (int8x8_t)(__p0);	32112	__ret = (int8x8_t)(__p0);
35010	return __ret;	32113	return __ret;
35011	}	32114	}
35012	#endif
35013
35014	#ifdef __LITTLE_ENDIAN__
35015	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {
35016	float32x2_t __ret;
35017	__ret = (float32x2_t)(__p0);
35018	return __ret;
35019	}
35020	#else
35021	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {	32115	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {
35022	float32x2_t __ret;	32116	float32x2_t __ret;
35023	__ret = (float32x2_t)(__p0);	32117	__ret = (float32x2_t)(__p0);
35024	return __ret;	32118	return __ret;
35025	}	32119	}
35026	#endif
35027
35028	#ifdef __LITTLE_ENDIAN__
35029	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {
35030	float32x2_t __ret;
35031	__ret = (float32x2_t)(__p0);
35032	return __ret;
35033	}
35034	#else
35035	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {	32120	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {
35036	float32x2_t __ret;	32121	float32x2_t __ret;
35037	__ret = (float32x2_t)(__p0);	32122	__ret = (float32x2_t)(__p0);
35038	return __ret;	32123	return __ret;
35039	}	32124	}
35040	#endif
35041
35042	#ifdef __LITTLE_ENDIAN__
35043	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {	32125	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {
35044	float32x2_t __ret;	32126	float32x2_t __ret;
35045	__ret = (float32x2_t)(__p0);	32127	__ret = (float32x2_t)(__p0);
35046	return __ret;	32128	return __ret;
35047	}	32129	}
35048	#else	32130	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {
35049	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {
35050	float32x2_t __ret;	32131	float32x2_t __ret;
35051	__ret = (float32x2_t)(__p0);	32132	__ret = (float32x2_t)(__p0);
35052	return __ret;	32133	return __ret;
35053	}	32134	}
35054	#endif	32135	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {
35055
35056	#ifdef __LITTLE_ENDIAN__
35057	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {
35058	float32x2_t __ret;	32136	float32x2_t __ret;
35059	__ret = (float32x2_t)(__p0);	32137	__ret = (float32x2_t)(__p0);
35060	return __ret;	32138	return __ret;
35061	}	32139	}
35062	#else	32140	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {
35063	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {
35064	float32x2_t __ret;	32141	float32x2_t __ret;
35065	__ret = (float32x2_t)(__p0);	32142	__ret = (float32x2_t)(__p0);
35066	return __ret;	32143	return __ret;
35067	}	32144	}
35068	#endif	32145	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
35069
35070	#ifdef __LITTLE_ENDIAN__
35071	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {
35072	float32x2_t __ret;	32146	float32x2_t __ret;
35073	__ret = (float32x2_t)(__p0);	32147	__ret = (float32x2_t)(__p0);
35074	return __ret;	32148	return __ret;
35075	}	32149	}
35076	#else	32150	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {
35077	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {
35078	float32x2_t __ret;	32151	float32x2_t __ret;
35079	__ret = (float32x2_t)(__p0);	32152	__ret = (float32x2_t)(__p0);
35080	return __ret;	32153	return __ret;
35081	}	32154	}
35082	#endif	32155	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {
35083
35084	#ifdef __LITTLE_ENDIAN__
35085	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {
35086	float32x2_t __ret;	32156	float32x2_t __ret;
35087	__ret = (float32x2_t)(__p0);	32157	__ret = (float32x2_t)(__p0);
35088	return __ret;	32158	return __ret;
35089	}	32159	}
35090	#else	32160	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {
35091	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {
35092	float32x2_t __ret;	32161	float32x2_t __ret;
35093	__ret = (float32x2_t)(__p0);	32162	__ret = (float32x2_t)(__p0);
35094	return __ret;	32163	return __ret;
35095	}	32164	}
35096	#endif	32165	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {
35097
35098	#ifdef __LITTLE_ENDIAN__
35099	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
35100	float32x2_t __ret;	32166	float32x2_t __ret;
35101	__ret = (float32x2_t)(__p0);	32167	__ret = (float32x2_t)(__p0);
35102	return __ret;	32168	return __ret;
35103	}	32169	}
35104	#else	32170	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {
35105	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {	32171	float16x4_t __ret;
35106	float32x2_t __ret;	32172	__ret = (float16x4_t)(__p0);
35107	__ret = (float32x2_t)(__p0);
35108	return __ret;	32173	return __ret;
35109	}	32174	}
35110	#endif
35111
35112	#ifdef __LITTLE_ENDIAN__
35113	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {
35114	float32x2_t __ret;
35115	__ret = (float32x2_t)(__p0);
35116	return __ret;
35117	}
35118	#else
35119	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {
35120	float32x2_t __ret;
35121	__ret = (float32x2_t)(__p0);
35122	return __ret;
35123	}
35124	#endif
35125
35126	#ifdef __LITTLE_ENDIAN__
35127	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {
35128	float32x2_t __ret;
35129	__ret = (float32x2_t)(__p0);
35130	return __ret;
35131	}
35132	#else
35133	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {
35134	float32x2_t __ret;
35135	__ret = (float32x2_t)(__p0);
35136	return __ret;
35137	}
35138	#endif
35139
35140	#ifdef __LITTLE_ENDIAN__
35141	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {
35142	float32x2_t __ret;
35143	__ret = (float32x2_t)(__p0);
35144	return __ret;
35145	}
35146	#else
35147	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {
35148	float32x2_t __ret;
35149	__ret = (float32x2_t)(__p0);
35150	return __ret;
35151	}
35152	#endif
35153
35154	#ifdef __LITTLE_ENDIAN__
35155	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {
35156	float32x2_t __ret;
35157	__ret = (float32x2_t)(__p0);
35158	return __ret;
35159	}
35160	#else
35161	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {
35162	float32x2_t __ret;
35163	__ret = (float32x2_t)(__p0);
35164	return __ret;
35165	}
35166	#endif
35167
35168	#ifdef __LITTLE_ENDIAN__
35169	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {
35170	float16x4_t __ret;
35171	__ret = (float16x4_t)(__p0);
35172	return __ret;
35173	}
35174	#else
35175	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {
35176	float16x4_t __ret;
35177	__ret = (float16x4_t)(__p0);
35178	return __ret;
35179	}
35180	#endif
35181
35182	#ifdef __LITTLE_ENDIAN__
35183	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {	32175	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {
35184	float16x4_t __ret;	32176	float16x4_t __ret;
35185	__ret = (float16x4_t)(__p0);	32177	__ret = (float16x4_t)(__p0);
35186	return __ret;	32178	return __ret;
35187	}	32179	}
35188	#else
35189	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {
35190	float16x4_t __ret;
35191	__ret = (float16x4_t)(__p0);
35192	return __ret;
35193	}
35194	#endif
35195
35196	#ifdef __LITTLE_ENDIAN__
35197	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {
35198	float16x4_t __ret;
35199	__ret = (float16x4_t)(__p0);
35200	return __ret;
35201	}
35202	#else
35203	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {	32180	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {
35204	float16x4_t __ret;	32181	float16x4_t __ret;
35205	__ret = (float16x4_t)(__p0);	32182	__ret = (float16x4_t)(__p0);
35206	return __ret;	32183	return __ret;
35207	}	32184	}
35208	#endif
35209
35210	#ifdef __LITTLE_ENDIAN__
35211	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {
35212	float16x4_t __ret;
35213	__ret = (float16x4_t)(__p0);
35214	return __ret;
35215	}
35216	#else
35217	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {	32185	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {
35218	float16x4_t __ret;	32186	float16x4_t __ret;
35219	__ret = (float16x4_t)(__p0);	32187	__ret = (float16x4_t)(__p0);
35220	return __ret;	32188	return __ret;
35221	}	32189	}
35222	#endif
35223
35224	#ifdef __LITTLE_ENDIAN__
35225	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {
35226	float16x4_t __ret;
35227	__ret = (float16x4_t)(__p0);
35228	return __ret;
35229	}
35230	#else
35231	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {	32190	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {
35232	float16x4_t __ret;	32191	float16x4_t __ret;
35233	__ret = (float16x4_t)(__p0);	32192	__ret = (float16x4_t)(__p0);
35234	return __ret;	32193	return __ret;
35235	}	32194	}
35236	#endif
35237
35238	#ifdef __LITTLE_ENDIAN__
35239	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {
35240	float16x4_t __ret;
35241	__ret = (float16x4_t)(__p0);
35242	return __ret;
35243	}
35244	#else
35245	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {	32195	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {
35246	float16x4_t __ret;	32196	float16x4_t __ret;
35247	__ret = (float16x4_t)(__p0);	32197	__ret = (float16x4_t)(__p0);
35248	return __ret;	32198	return __ret;
35249	}	32199	}
35250	#endif
35251
35252	#ifdef __LITTLE_ENDIAN__
35253	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
35254	float16x4_t __ret;
35255	__ret = (float16x4_t)(__p0);
35256	return __ret;
35257	}
35258	#else
35259	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {	32200	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
35260	float16x4_t __ret;	32201	float16x4_t __ret;
35261	__ret = (float16x4_t)(__p0);	32202	__ret = (float16x4_t)(__p0);
35262	return __ret;	32203	return __ret;
35263	}	32204	}
35264	#endif
35265
35266	#ifdef __LITTLE_ENDIAN__
35267	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {	32205	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {
35268	float16x4_t __ret;	32206	float16x4_t __ret;
35269	__ret = (float16x4_t)(__p0);	32207	__ret = (float16x4_t)(__p0);
35270	return __ret;	32208	return __ret;
35271	}	32209	}
35272	#else
35273	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {
35274	float16x4_t __ret;
35275	__ret = (float16x4_t)(__p0);
35276	return __ret;
35277	}
35278	#endif
35279
35280	#ifdef __LITTLE_ENDIAN__
35281	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {
35282	float16x4_t __ret;
35283	__ret = (float16x4_t)(__p0);
35284	return __ret;
35285	}
35286	#else
35287	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {	32210	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {
35288	float16x4_t __ret;	32211	float16x4_t __ret;
35289	__ret = (float16x4_t)(__p0);	32212	__ret = (float16x4_t)(__p0);
35290	return __ret;	32213	return __ret;
35291	}	32214	}
35292	#endif
35293
35294	#ifdef __LITTLE_ENDIAN__
35295	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {	32215	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {
35296	float16x4_t __ret;	32216	float16x4_t __ret;
35297	__ret = (float16x4_t)(__p0);	32217	__ret = (float16x4_t)(__p0);
35298	return __ret;	32218	return __ret;
35299	}	32219	}
35300	#else
35301	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {
35302	float16x4_t __ret;
35303	__ret = (float16x4_t)(__p0);
35304	return __ret;
35305	}
35306	#endif
35307
35308	#ifdef __LITTLE_ENDIAN__
35309	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {
35310	float16x4_t __ret;
35311	__ret = (float16x4_t)(__p0);
35312	return __ret;
35313	}
35314	#else
35315	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {	32220	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {
35316	float16x4_t __ret;	32221	float16x4_t __ret;
35317	__ret = (float16x4_t)(__p0);	32222	__ret = (float16x4_t)(__p0);
35318	return __ret;	32223	return __ret;
35319	}	32224	}
35320	#endif
35321
35322	#ifdef __LITTLE_ENDIAN__
35323	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {
35324	int32x2_t __ret;
35325	__ret = (int32x2_t)(__p0);
35326	return __ret;
35327	}
35328	#else
35329	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {	32225	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {
35330	int32x2_t __ret;	32226	int32x2_t __ret;
35331	__ret = (int32x2_t)(__p0);	32227	__ret = (int32x2_t)(__p0);
35332	return __ret;	32228	return __ret;
35333	}	32229	}
35334	#endif
35335
35336	#ifdef __LITTLE_ENDIAN__
35337	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {
35338	int32x2_t __ret;
35339	__ret = (int32x2_t)(__p0);
35340	return __ret;
35341	}
35342	#else
35343	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {	32230	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {
35344	int32x2_t __ret;	32231	int32x2_t __ret;
35345	__ret = (int32x2_t)(__p0);	32232	__ret = (int32x2_t)(__p0);
35346	return __ret;	32233	return __ret;
35347	}	32234	}
35348	#endif
35349
35350	#ifdef __LITTLE_ENDIAN__
35351	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {	32235	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {
35352	int32x2_t __ret;	32236	int32x2_t __ret;
35353	__ret = (int32x2_t)(__p0);	32237	__ret = (int32x2_t)(__p0);
35354	return __ret;	32238	return __ret;
35355	}	32239	}
35356	#else
35357	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {
35358	int32x2_t __ret;
35359	__ret = (int32x2_t)(__p0);
35360	return __ret;
35361	}
35362	#endif
35363
35364	#ifdef __LITTLE_ENDIAN__
35365	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {
35366	int32x2_t __ret;
35367	__ret = (int32x2_t)(__p0);
35368	return __ret;
35369	}
35370	#else
35371	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {	32240	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {
35372	int32x2_t __ret;	32241	int32x2_t __ret;
35373	__ret = (int32x2_t)(__p0);	32242	__ret = (int32x2_t)(__p0);
35374	return __ret;	32243	return __ret;
35375	}	32244	}
35376	#endif
35377
35378	#ifdef __LITTLE_ENDIAN__
35379	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {	32245	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {
35380	int32x2_t __ret;	32246	int32x2_t __ret;
35381	__ret = (int32x2_t)(__p0);	32247	__ret = (int32x2_t)(__p0);
35382	return __ret;	32248	return __ret;
35383	}	32249	}
35384	#else
35385	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {
35386	int32x2_t __ret;
35387	__ret = (int32x2_t)(__p0);
35388	return __ret;
35389	}
35390	#endif
35391
35392	#ifdef __LITTLE_ENDIAN__
35393	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {
35394	int32x2_t __ret;
35395	__ret = (int32x2_t)(__p0);
35396	return __ret;
35397	}
35398	#else
35399	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {	32250	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {
35400	int32x2_t __ret;	32251	int32x2_t __ret;
35401	__ret = (int32x2_t)(__p0);	32252	__ret = (int32x2_t)(__p0);
35402	return __ret;	32253	return __ret;
35403	}	32254	}
35404	#endif
35405
35406	#ifdef __LITTLE_ENDIAN__
35407	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
35408	int32x2_t __ret;
35409	__ret = (int32x2_t)(__p0);
35410	return __ret;
35411	}
35412	#else
35413	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {	32255	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
35414	int32x2_t __ret;	32256	int32x2_t __ret;
35415	__ret = (int32x2_t)(__p0);	32257	__ret = (int32x2_t)(__p0);
35416	return __ret;	32258	return __ret;
35417	}	32259	}
35418	#endif
35419
35420	#ifdef __LITTLE_ENDIAN__
35421	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {
35422	int32x2_t __ret;
35423	__ret = (int32x2_t)(__p0);
35424	return __ret;
35425	}
35426	#else
35427	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {	32260	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {
35428	int32x2_t __ret;	32261	int32x2_t __ret;
35429	__ret = (int32x2_t)(__p0);	32262	__ret = (int32x2_t)(__p0);
35430	return __ret;	32263	return __ret;
35431	}	32264	}
35432	#endif
35433
35434	#ifdef __LITTLE_ENDIAN__
35435	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {	32265	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {
35436	int32x2_t __ret;	32266	int32x2_t __ret;
35437	__ret = (int32x2_t)(__p0);	32267	__ret = (int32x2_t)(__p0);
35438	return __ret;	32268	return __ret;
35439	}	32269	}
35440	#else
35441	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {
35442	int32x2_t __ret;
35443	__ret = (int32x2_t)(__p0);
35444	return __ret;
35445	}
35446	#endif
35447
35448	#ifdef __LITTLE_ENDIAN__
35449	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {	32270	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {
35450	int32x2_t __ret;	32271	int32x2_t __ret;
35451	__ret = (int32x2_t)(__p0);	32272	__ret = (int32x2_t)(__p0);
35452	return __ret;	32273	return __ret;
35453	}	32274	}
35454	#else
35455	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {
35456	int32x2_t __ret;
35457	__ret = (int32x2_t)(__p0);
35458	return __ret;
35459	}
35460	#endif
35461
35462	#ifdef __LITTLE_ENDIAN__
35463	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {
35464	int32x2_t __ret;
35465	__ret = (int32x2_t)(__p0);
35466	return __ret;
35467	}
35468	#else
35469	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {	32275	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {
35470	int32x2_t __ret;	32276	int32x2_t __ret;
35471	__ret = (int32x2_t)(__p0);	32277	__ret = (int32x2_t)(__p0);
35472	return __ret;	32278	return __ret;
35473	}	32279	}
35474	#endif
35475
35476	#ifdef __LITTLE_ENDIAN__
35477	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {	32280	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {
35478	int64x1_t __ret;	32281	int64x1_t __ret;
35479	__ret = (int64x1_t)(__p0);	32282	__ret = (int64x1_t)(__p0);
35480	return __ret;	32283	return __ret;
35481	}	32284	}
35482	#else
35483	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {
35484	int64x1_t __ret;
35485	__ret = (int64x1_t)(__p0);
35486	return __ret;
35487	}
35488	#endif
35489
35490	#ifdef __LITTLE_ENDIAN__
35491	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {	32285	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {
35492	int64x1_t __ret;	32286	int64x1_t __ret;
35493	__ret = (int64x1_t)(__p0);	32287	__ret = (int64x1_t)(__p0);
35494	return __ret;	32288	return __ret;
35495	}	32289	}
35496	#else
35497	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {
35498	int64x1_t __ret;
35499	__ret = (int64x1_t)(__p0);
35500	return __ret;
35501	}
35502	#endif
35503
35504	#ifdef __LITTLE_ENDIAN__
35505	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {
35506	int64x1_t __ret;
35507	__ret = (int64x1_t)(__p0);
35508	return __ret;
35509	}
35510	#else
35511	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {	32290	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {
35512	int64x1_t __ret;	32291	int64x1_t __ret;
35513	__ret = (int64x1_t)(__p0);	32292	__ret = (int64x1_t)(__p0);
35514	return __ret;	32293	return __ret;
35515	}	32294	}
35516	#endif
35517
35518	#ifdef __LITTLE_ENDIAN__
35519	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {
35520	int64x1_t __ret;
35521	__ret = (int64x1_t)(__p0);
35522	return __ret;
35523	}
35524	#else
35525	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {	32295	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {
35526	int64x1_t __ret;	32296	int64x1_t __ret;
35527	__ret = (int64x1_t)(__p0);	32297	__ret = (int64x1_t)(__p0);
35528	return __ret;	32298	return __ret;
35529	}	32299	}
35530	#endif
35531
35532	#ifdef __LITTLE_ENDIAN__
35533	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {	32300	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {
35534	int64x1_t __ret;	32301	int64x1_t __ret;
35535	__ret = (int64x1_t)(__p0);	32302	__ret = (int64x1_t)(__p0);
35536	return __ret;	32303	return __ret;
35537	}	32304	}
35538	#else
35539	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {
35540	int64x1_t __ret;
35541	__ret = (int64x1_t)(__p0);
35542	return __ret;
35543	}
35544	#endif
35545
35546	#ifdef __LITTLE_ENDIAN__
35547	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {
35548	int64x1_t __ret;
35549	__ret = (int64x1_t)(__p0);
35550	return __ret;
35551	}
35552	#else
35553	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {	32305	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {
35554	int64x1_t __ret;	32306	int64x1_t __ret;
35555	__ret = (int64x1_t)(__p0);	32307	__ret = (int64x1_t)(__p0);
35556	return __ret;	32308	return __ret;
35557	}	32309	}
35558	#endif
35559
35560	#ifdef __LITTLE_ENDIAN__
35561	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {	32310	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
35562	int64x1_t __ret;	32311	int64x1_t __ret;
35563	__ret = (int64x1_t)(__p0);	32312	__ret = (int64x1_t)(__p0);
35564	return __ret;	32313	return __ret;
35565	}	32314	}
35566	#else
35567	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
35568	int64x1_t __ret;
35569	__ret = (int64x1_t)(__p0);
35570	return __ret;
35571	}
35572	#endif
35573
35574	#ifdef __LITTLE_ENDIAN__
35575	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {
35576	int64x1_t __ret;
35577	__ret = (int64x1_t)(__p0);
35578	return __ret;
35579	}
35580	#else
35581	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {	32315	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {
35582	int64x1_t __ret;	32316	int64x1_t __ret;
35583	__ret = (int64x1_t)(__p0);	32317	__ret = (int64x1_t)(__p0);
35584	return __ret;	32318	return __ret;
35585	}	32319	}
35586	#endif
35587
35588	#ifdef __LITTLE_ENDIAN__
35589	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {
35590	int64x1_t __ret;
35591	__ret = (int64x1_t)(__p0);
35592	return __ret;
35593	}
35594	#else
35595	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {	32320	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {
35596	int64x1_t __ret;	32321	int64x1_t __ret;
35597	__ret = (int64x1_t)(__p0);	32322	__ret = (int64x1_t)(__p0);
35598	return __ret;	32323	return __ret;
35599	}	32324	}
35600	#endif
35601
35602	#ifdef __LITTLE_ENDIAN__
35603	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {	32325	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {
35604	int64x1_t __ret;	32326	int64x1_t __ret;
35605	__ret = (int64x1_t)(__p0);	32327	__ret = (int64x1_t)(__p0);
35606	return __ret;	32328	return __ret;
35607	}	32329	}
35608	#else
35609	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {
35610	int64x1_t __ret;
35611	__ret = (int64x1_t)(__p0);
35612	return __ret;
35613	}
35614	#endif
35615
35616	#ifdef __LITTLE_ENDIAN__
35617	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {	32330	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {
35618	int64x1_t __ret;	32331	int64x1_t __ret;
35619	__ret = (int64x1_t)(__p0);	32332	__ret = (int64x1_t)(__p0);
35620	return __ret;	32333	return __ret;
35621	}	32334	}
35622	#else
35623	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {
35624	int64x1_t __ret;
35625	__ret = (int64x1_t)(__p0);
35626	return __ret;
35627	}
35628	#endif
35629
35630	#ifdef __LITTLE_ENDIAN__
35631	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {
35632	int16x4_t __ret;
35633	__ret = (int16x4_t)(__p0);
35634	return __ret;
35635	}
35636	#else
35637	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {	32335	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {
35638	int16x4_t __ret;	32336	int16x4_t __ret;
35639	__ret = (int16x4_t)(__p0);	32337	__ret = (int16x4_t)(__p0);
35640	return __ret;	32338	return __ret;
35641	}	32339	}
35642	#endif
35643
35644	#ifdef __LITTLE_ENDIAN__
35645	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {	32340	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {
35646	int16x4_t __ret;	32341	int16x4_t __ret;
35647	__ret = (int16x4_t)(__p0);	32342	__ret = (int16x4_t)(__p0);
35648	return __ret;	32343	return __ret;
35649	}	32344	}
35650	#else
35651	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {
35652	int16x4_t __ret;
35653	__ret = (int16x4_t)(__p0);
35654	return __ret;
35655	}
35656	#endif
35657
35658	#ifdef __LITTLE_ENDIAN__
35659	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {
35660	int16x4_t __ret;
35661	__ret = (int16x4_t)(__p0);
35662	return __ret;
35663	}
35664	#else
35665	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {	32345	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {
35666	int16x4_t __ret;	32346	int16x4_t __ret;
35667	__ret = (int16x4_t)(__p0);	32347	__ret = (int16x4_t)(__p0);
35668	return __ret;	32348	return __ret;
35669	}	32349	}
35670	#endif
35671
35672	#ifdef __LITTLE_ENDIAN__
35673	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {
35674	int16x4_t __ret;
35675	__ret = (int16x4_t)(__p0);
35676	return __ret;
35677	}
35678	#else
35679	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {	32350	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {
35680	int16x4_t __ret;	32351	int16x4_t __ret;
35681	__ret = (int16x4_t)(__p0);	32352	__ret = (int16x4_t)(__p0);
35682	return __ret;	32353	return __ret;
35683	}	32354	}
35684	#endif
35685
35686	#ifdef __LITTLE_ENDIAN__
35687	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {
35688	int16x4_t __ret;
35689	__ret = (int16x4_t)(__p0);
35690	return __ret;
35691	}
35692	#else
35693	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {	32355	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {
35694	int16x4_t __ret;	32356	int16x4_t __ret;
35695	__ret = (int16x4_t)(__p0);	32357	__ret = (int16x4_t)(__p0);
35696	return __ret;	32358	return __ret;
35697	}	32359	}
35698	#endif
35699
35700	#ifdef __LITTLE_ENDIAN__
35701	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {	32360	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {
35702	int16x4_t __ret;	32361	int16x4_t __ret;
35703	__ret = (int16x4_t)(__p0);	32362	__ret = (int16x4_t)(__p0);
35704	return __ret;	32363	return __ret;
35705	}	32364	}
35706	#else
35707	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {
35708	int16x4_t __ret;
35709	__ret = (int16x4_t)(__p0);
35710	return __ret;
35711	}
35712	#endif
35713
35714	#ifdef __LITTLE_ENDIAN__
35715	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {	32365	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
35716	int16x4_t __ret;	32366	int16x4_t __ret;
35717	__ret = (int16x4_t)(__p0);	32367	__ret = (int16x4_t)(__p0);
35718	return __ret;	32368	return __ret;
35719	}	32369	}
35720	#else
35721	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
35722	int16x4_t __ret;
35723	__ret = (int16x4_t)(__p0);
35724	return __ret;
35725	}
35726	#endif
35727
35728	#ifdef __LITTLE_ENDIAN__
35729	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {	32370	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {
35730	int16x4_t __ret;	32371	int16x4_t __ret;
35731	__ret = (int16x4_t)(__p0);	32372	__ret = (int16x4_t)(__p0);
35732	return __ret;	32373	return __ret;
35733	}	32374	}
35734	#else
35735	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {
35736	int16x4_t __ret;
35737	__ret = (int16x4_t)(__p0);
35738	return __ret;
35739	}
35740	#endif
35741
35742	#ifdef __LITTLE_ENDIAN__
35743	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {
35744	int16x4_t __ret;
35745	__ret = (int16x4_t)(__p0);
35746	return __ret;
35747	}
35748	#else
35749	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {	32375	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {
35750	int16x4_t __ret;	32376	int16x4_t __ret;
35751	__ret = (int16x4_t)(__p0);	32377	__ret = (int16x4_t)(__p0);
35752	return __ret;	32378	return __ret;
35753	}	32379	}
35754	#endif
35755
35756	#ifdef __LITTLE_ENDIAN__
35757	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {
35758	int16x4_t __ret;
35759	__ret = (int16x4_t)(__p0);
35760	return __ret;
35761	}
35762	#else
35763	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {	32380	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {
35764	int16x4_t __ret;	32381	int16x4_t __ret;
35765	__ret = (int16x4_t)(__p0);	32382	__ret = (int16x4_t)(__p0);
35766	return __ret;	32383	return __ret;
35767	}	32384	}
35768	#endif
35769
35770	#ifdef __LITTLE_ENDIAN__
35771	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {
35772	int16x4_t __ret;
35773	__ret = (int16x4_t)(__p0);
35774	return __ret;
35775	}
35776	#else
35777	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {	32385	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {
35778	int16x4_t __ret;	32386	int16x4_t __ret;
35779	__ret = (int16x4_t)(__p0);	32387	__ret = (int16x4_t)(__p0);
35780	return __ret;	32388	return __ret;
35781	}	32389	}
35782	#endif
35783
35784	#endif	32390	#endif
35785	#if (__ARM_FP & 2)	32391	#if (__ARM_FP & 2)
35786	#ifdef __LITTLE_ENDIAN__	32392	#ifdef __LITTLE_ENDIAN__
35787	__ai float16x4_t vcvt_f16_f32(float32x4_t __p0) {	32393	__ai float16x4_t vcvt_f16_f32(float32x4_t __p0) {
35788	float16x4_t __ret;	32394	float16x4_t __ret;
35789	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__p0, 8);	32395	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__p0, 41);
35790	return __ret;	32396	return __ret;
35791	}	32397	}
35792	#else	32398	#else
35793	__ai float16x4_t vcvt_f16_f32(float32x4_t __p0) {	32399	__ai float16x4_t vcvt_f16_f32(float32x4_t __p0) {
35794	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	32400	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
35795	float16x4_t __ret;	32401	float16x4_t __ret;
35796	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__rev0, 8);	32402	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__rev0, 41);
35797	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	32403	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
35798	return __ret;	32404	return __ret;
35799	}	32405	}
35800	__ai float16x4_t __noswap_vcvt_f16_f32(float32x4_t __p0) {	32406	__ai float16x4_t __noswap_vcvt_f16_f32(float32x4_t __p0) {
35801	float16x4_t __ret;	32407	float16x4_t __ret;
35802	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__p0, 8);	32408	__ret = (float16x4_t) __builtin_neon_vcvt_f16_f32((int8x16_t)__p0, 41);
35803	return __ret;	32409	return __ret;
35804	}	32410	}
35805	#endif	32411	#endif
...	@@ -35807,20 +32413,20 @@ __ai float16x4_t __noswap_vcvt_f16_f32(float32x4_t __p0) {	...	@@ -35807,20 +32413,20 @@ __ai float16x4_t __noswap_vcvt_f16_f32(float32x4_t __p0) {
35807	#ifdef __LITTLE_ENDIAN__	32413	#ifdef __LITTLE_ENDIAN__
35808	__ai float32x4_t vcvt_f32_f16(float16x4_t __p0) {	32414	__ai float32x4_t vcvt_f32_f16(float16x4_t __p0) {
35809	float32x4_t __ret;	32415	float32x4_t __ret;
35810	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 41);	32416	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 8);
35811	return __ret;	32417	return __ret;
35812	}	32418	}
35813	#else	32419	#else
35814	__ai float32x4_t vcvt_f32_f16(float16x4_t __p0) {	32420	__ai float32x4_t vcvt_f32_f16(float16x4_t __p0) {
35815	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	32421	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
35816	float32x4_t __ret;	32422	float32x4_t __ret;
35817	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__rev0, 41);	32423	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__rev0, 8);
35818	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	32424	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
35819	return __ret;	32425	return __ret;
35820	}	32426	}
35821	__ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	32427	__ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
35822	float32x4_t __ret;	32428	float32x4_t __ret;
35823	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 41);	32429	__ret = (float32x4_t) __builtin_neon_vcvt_f32_f16((int8x8_t)__p0, 8);
35824	return __ret;	32430	return __ret;
35825	}	32431	}
35826	#endif	32432	#endif
...	@@ -36101,7 +32707,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36101,7 +32707,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36101	#define vld2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32707	#define vld2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36102	float16x8x2_t __s1 = __p1; \	32708	float16x8x2_t __s1 = __p1; \
36103	float16x8x2_t __ret; \	32709	float16x8x2_t __ret; \
36104	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 40); \	32710	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 40); \
36105	__ret; \	32711	__ret; \
36106	})	32712	})
36107	#else	32713	#else
...	@@ -36111,7 +32717,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36111,7 +32717,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36111	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	32717	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36112	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	32718	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36113	float16x8x2_t __ret; \	32719	float16x8x2_t __ret; \
36114	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 40); \	32720	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 40); \
36115	\	32721	\
36116	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	32722	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36117	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	32723	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -36123,7 +32729,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36123,7 +32729,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36123	#define vld2_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32729	#define vld2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36124	float16x4x2_t __s1 = __p1; \	32730	float16x4x2_t __s1 = __p1; \
36125	float16x4x2_t __ret; \	32731	float16x4x2_t __ret; \
36126	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 8); \	32732	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 8); \
36127	__ret; \	32733	__ret; \
36128	})	32734	})
36129	#else	32735	#else
...	@@ -36133,7 +32739,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36133,7 +32739,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36133	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	32739	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36134	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	32740	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36135	float16x4x2_t __ret; \	32741	float16x4x2_t __ret; \
36136	__builtin_neon_vld2_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 8); \	32742	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 8); \
36137	\	32743	\
36138	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	32744	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
36139	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	32745	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -36217,7 +32823,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36217,7 +32823,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36217	#define vld3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32823	#define vld3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36218	float16x8x3_t __s1 = __p1; \	32824	float16x8x3_t __s1 = __p1; \
36219	float16x8x3_t __ret; \	32825	float16x8x3_t __ret; \
36220	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 40); \	32826	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 40); \
36221	__ret; \	32827	__ret; \
36222	})	32828	})
36223	#else	32829	#else
...	@@ -36228,7 +32834,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36228,7 +32834,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36228	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	32834	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36229	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	32835	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36230	float16x8x3_t __ret; \	32836	float16x8x3_t __ret; \
36231	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 40); \	32837	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 40); \
36232	\	32838	\
36233	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	32839	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36234	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	32840	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -36241,7 +32847,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36241,7 +32847,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36241	#define vld3_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32847	#define vld3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36242	float16x4x3_t __s1 = __p1; \	32848	float16x4x3_t __s1 = __p1; \
36243	float16x4x3_t __ret; \	32849	float16x4x3_t __ret; \
36244	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 8); \	32850	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 8); \
36245	__ret; \	32851	__ret; \
36246	})	32852	})
36247	#else	32853	#else
...	@@ -36252,7 +32858,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36252,7 +32858,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36252	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	32858	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36253	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	32859	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36254	float16x4x3_t __ret; \	32860	float16x4x3_t __ret; \
36255	__builtin_neon_vld3_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 8); \	32861	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 8); \
36256	\	32862	\
36257	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	32863	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
36258	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	32864	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -36341,7 +32947,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36341,7 +32947,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36341	#define vld4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32947	#define vld4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36342	float16x8x4_t __s1 = __p1; \	32948	float16x8x4_t __s1 = __p1; \
36343	float16x8x4_t __ret; \	32949	float16x8x4_t __ret; \
36344	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 40); \	32950	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 40); \
36345	__ret; \	32951	__ret; \
36346	})	32952	})
36347	#else	32953	#else
...	@@ -36353,7 +32959,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36353,7 +32959,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36353	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	32959	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36354	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	32960	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
36355	float16x8x4_t __ret; \	32961	float16x8x4_t __ret; \
36356	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 40); \	32962	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 40); \
36357	\	32963	\
36358	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	32964	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36359	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	32965	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
...	@@ -36367,7 +32973,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36367,7 +32973,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36367	#define vld4_lane_f16(__p0, __p1, __p2) __extension__ ({ \	32973	#define vld4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36368	float16x4x4_t __s1 = __p1; \	32974	float16x4x4_t __s1 = __p1; \
36369	float16x4x4_t __ret; \	32975	float16x4x4_t __ret; \
36370	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 8); \	32976	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 8); \
36371	__ret; \	32977	__ret; \
36372	})	32978	})
36373	#else	32979	#else
...	@@ -36379,7 +32985,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36379,7 +32985,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36379	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	32985	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36380	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	32986	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
36381	float16x4x4_t __ret; \	32987	float16x4x4_t __ret; \
36382	__builtin_neon_vld4_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 8); \	32988	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 8); \
36383	\	32989	\
36384	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \	32990	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 3, 2, 1, 0); \
36385	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \	32991	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 3, 2, 1, 0); \
...	@@ -36444,7 +33050,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36444,7 +33050,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36444	#ifdef __LITTLE_ENDIAN__	33050	#ifdef __LITTLE_ENDIAN__
36445	#define vst1q_f16_x2(__p0, __p1) __extension__ ({ \	33051	#define vst1q_f16_x2(__p0, __p1) __extension__ ({ \
36446	float16x8x2_t __s1 = __p1; \	33052	float16x8x2_t __s1 = __p1; \
36447	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 40); \	33053	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 40); \
36448	})	33054	})
36449	#else	33055	#else
36450	#define vst1q_f16_x2(__p0, __p1) __extension__ ({ \	33056	#define vst1q_f16_x2(__p0, __p1) __extension__ ({ \
...	@@ -36452,14 +33058,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36452,14 +33058,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36452	float16x8x2_t __rev1; \	33058	float16x8x2_t __rev1; \
36453	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33059	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36454	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33060	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36455	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 40); \	33061	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 40); \
36456	})	33062	})
36457	#endif	33063	#endif
36458		33064
36459	#ifdef __LITTLE_ENDIAN__	33065	#ifdef __LITTLE_ENDIAN__
36460	#define vst1_f16_x2(__p0, __p1) __extension__ ({ \	33066	#define vst1_f16_x2(__p0, __p1) __extension__ ({ \
36461	float16x4x2_t __s1 = __p1; \	33067	float16x4x2_t __s1 = __p1; \
36462	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 8); \	33068	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 8); \
36463	})	33069	})
36464	#else	33070	#else
36465	#define vst1_f16_x2(__p0, __p1) __extension__ ({ \	33071	#define vst1_f16_x2(__p0, __p1) __extension__ ({ \
...	@@ -36467,14 +33073,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36467,14 +33073,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36467	float16x4x2_t __rev1; \	33073	float16x4x2_t __rev1; \
36468	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33074	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36469	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33075	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36470	__builtin_neon_vst1_x2_v(__p0, __rev1.val[0], __rev1.val[1], 8); \	33076	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 8); \
36471	})	33077	})
36472	#endif	33078	#endif
36473		33079
36474	#ifdef __LITTLE_ENDIAN__	33080	#ifdef __LITTLE_ENDIAN__
36475	#define vst1q_f16_x3(__p0, __p1) __extension__ ({ \	33081	#define vst1q_f16_x3(__p0, __p1) __extension__ ({ \
36476	float16x8x3_t __s1 = __p1; \	33082	float16x8x3_t __s1 = __p1; \
36477	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 40); \	33083	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 40); \
36478	})	33084	})
36479	#else	33085	#else
36480	#define vst1q_f16_x3(__p0, __p1) __extension__ ({ \	33086	#define vst1q_f16_x3(__p0, __p1) __extension__ ({ \
...	@@ -36483,14 +33089,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36483,14 +33089,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36483	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33089	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36484	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33090	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36485	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33091	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36486	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 40); \	33092	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 40); \
36487	})	33093	})
36488	#endif	33094	#endif
36489		33095
36490	#ifdef __LITTLE_ENDIAN__	33096	#ifdef __LITTLE_ENDIAN__
36491	#define vst1_f16_x3(__p0, __p1) __extension__ ({ \	33097	#define vst1_f16_x3(__p0, __p1) __extension__ ({ \
36492	float16x4x3_t __s1 = __p1; \	33098	float16x4x3_t __s1 = __p1; \
36493	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 8); \	33099	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 8); \
36494	})	33100	})
36495	#else	33101	#else
36496	#define vst1_f16_x3(__p0, __p1) __extension__ ({ \	33102	#define vst1_f16_x3(__p0, __p1) __extension__ ({ \
...	@@ -36499,14 +33105,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36499,14 +33105,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36499	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33105	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36500	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33106	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36501	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33107	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36502	__builtin_neon_vst1_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 8); \	33108	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 8); \
36503	})	33109	})
36504	#endif	33110	#endif
36505		33111
36506	#ifdef __LITTLE_ENDIAN__	33112	#ifdef __LITTLE_ENDIAN__
36507	#define vst1q_f16_x4(__p0, __p1) __extension__ ({ \	33113	#define vst1q_f16_x4(__p0, __p1) __extension__ ({ \
36508	float16x8x4_t __s1 = __p1; \	33114	float16x8x4_t __s1 = __p1; \
36509	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 40); \	33115	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 40); \
36510	})	33116	})
36511	#else	33117	#else
36512	#define vst1q_f16_x4(__p0, __p1) __extension__ ({ \	33118	#define vst1q_f16_x4(__p0, __p1) __extension__ ({ \
...	@@ -36516,14 +33122,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36516,14 +33122,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36516	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33122	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36517	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33123	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36518	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	33124	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
36519	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 40); \	33125	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 40); \
36520	})	33126	})
36521	#endif	33127	#endif
36522		33128
36523	#ifdef __LITTLE_ENDIAN__	33129	#ifdef __LITTLE_ENDIAN__
36524	#define vst1_f16_x4(__p0, __p1) __extension__ ({ \	33130	#define vst1_f16_x4(__p0, __p1) __extension__ ({ \
36525	float16x4x4_t __s1 = __p1; \	33131	float16x4x4_t __s1 = __p1; \
36526	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 8); \	33132	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 8); \
36527	})	33133	})
36528	#else	33134	#else
36529	#define vst1_f16_x4(__p0, __p1) __extension__ ({ \	33135	#define vst1_f16_x4(__p0, __p1) __extension__ ({ \
...	@@ -36533,14 +33139,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36533,14 +33139,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36533	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33139	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36534	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33140	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36535	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	33141	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
36536	__builtin_neon_vst1_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 8); \	33142	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 8); \
36537	})	33143	})
36538	#endif	33144	#endif
36539		33145
36540	#ifdef __LITTLE_ENDIAN__	33146	#ifdef __LITTLE_ENDIAN__
36541	#define vst2q_f16(__p0, __p1) __extension__ ({ \	33147	#define vst2q_f16(__p0, __p1) __extension__ ({ \
36542	float16x8x2_t __s1 = __p1; \	33148	float16x8x2_t __s1 = __p1; \
36543	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 40); \	33149	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 40); \
36544	})	33150	})
36545	#else	33151	#else
36546	#define vst2q_f16(__p0, __p1) __extension__ ({ \	33152	#define vst2q_f16(__p0, __p1) __extension__ ({ \
...	@@ -36548,14 +33154,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36548,14 +33154,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36548	float16x8x2_t __rev1; \	33154	float16x8x2_t __rev1; \
36549	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33155	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36550	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33156	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36551	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 40); \	33157	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 40); \
36552	})	33158	})
36553	#endif	33159	#endif
36554		33160
36555	#ifdef __LITTLE_ENDIAN__	33161	#ifdef __LITTLE_ENDIAN__
36556	#define vst2_f16(__p0, __p1) __extension__ ({ \	33162	#define vst2_f16(__p0, __p1) __extension__ ({ \
36557	float16x4x2_t __s1 = __p1; \	33163	float16x4x2_t __s1 = __p1; \
36558	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 8); \	33164	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 8); \
36559	})	33165	})
36560	#else	33166	#else
36561	#define vst2_f16(__p0, __p1) __extension__ ({ \	33167	#define vst2_f16(__p0, __p1) __extension__ ({ \
...	@@ -36563,14 +33169,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36563,14 +33169,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36563	float16x4x2_t __rev1; \	33169	float16x4x2_t __rev1; \
36564	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33170	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36565	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33171	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36566	__builtin_neon_vst2_v(__p0, __rev1.val[0], __rev1.val[1], 8); \	33172	__builtin_neon_vst2_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], 8); \
36567	})	33173	})
36568	#endif	33174	#endif
36569		33175
36570	#ifdef __LITTLE_ENDIAN__	33176	#ifdef __LITTLE_ENDIAN__
36571	#define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33177	#define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36572	float16x8x2_t __s1 = __p1; \	33178	float16x8x2_t __s1 = __p1; \
36573	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 40); \	33179	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 40); \
36574	})	33180	})
36575	#else	33181	#else
36576	#define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33182	#define vst2q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36578,14 +33184,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36578,14 +33184,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36578	float16x8x2_t __rev1; \	33184	float16x8x2_t __rev1; \
36579	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33185	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36580	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33186	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36581	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 40); \	33187	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 40); \
36582	})	33188	})
36583	#endif	33189	#endif
36584		33190
36585	#ifdef __LITTLE_ENDIAN__	33191	#ifdef __LITTLE_ENDIAN__
36586	#define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33192	#define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36587	float16x4x2_t __s1 = __p1; \	33193	float16x4x2_t __s1 = __p1; \
36588	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 8); \	33194	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 8); \
36589	})	33195	})
36590	#else	33196	#else
36591	#define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33197	#define vst2_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36593,14 +33199,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36593,14 +33199,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36593	float16x4x2_t __rev1; \	33199	float16x4x2_t __rev1; \
36594	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33200	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36595	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33201	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36596	__builtin_neon_vst2_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 8); \	33202	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], __p2, 8); \
36597	})	33203	})
36598	#endif	33204	#endif
36599		33205
36600	#ifdef __LITTLE_ENDIAN__	33206	#ifdef __LITTLE_ENDIAN__
36601	#define vst3q_f16(__p0, __p1) __extension__ ({ \	33207	#define vst3q_f16(__p0, __p1) __extension__ ({ \
36602	float16x8x3_t __s1 = __p1; \	33208	float16x8x3_t __s1 = __p1; \
36603	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 40); \	33209	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 40); \
36604	})	33210	})
36605	#else	33211	#else
36606	#define vst3q_f16(__p0, __p1) __extension__ ({ \	33212	#define vst3q_f16(__p0, __p1) __extension__ ({ \
...	@@ -36609,14 +33215,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36609,14 +33215,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36609	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33215	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36610	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33216	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36611	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33217	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36612	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 40); \	33218	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 40); \
36613	})	33219	})
36614	#endif	33220	#endif
36615		33221
36616	#ifdef __LITTLE_ENDIAN__	33222	#ifdef __LITTLE_ENDIAN__
36617	#define vst3_f16(__p0, __p1) __extension__ ({ \	33223	#define vst3_f16(__p0, __p1) __extension__ ({ \
36618	float16x4x3_t __s1 = __p1; \	33224	float16x4x3_t __s1 = __p1; \
36619	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 8); \	33225	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 8); \
36620	})	33226	})
36621	#else	33227	#else
36622	#define vst3_f16(__p0, __p1) __extension__ ({ \	33228	#define vst3_f16(__p0, __p1) __extension__ ({ \
...	@@ -36625,14 +33231,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36625,14 +33231,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36625	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33231	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36626	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33232	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36627	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33233	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36628	__builtin_neon_vst3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 8); \	33234	__builtin_neon_vst3_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], 8); \
36629	})	33235	})
36630	#endif	33236	#endif
36631		33237
36632	#ifdef __LITTLE_ENDIAN__	33238	#ifdef __LITTLE_ENDIAN__
36633	#define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33239	#define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36634	float16x8x3_t __s1 = __p1; \	33240	float16x8x3_t __s1 = __p1; \
36635	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 40); \	33241	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 40); \
36636	})	33242	})
36637	#else	33243	#else
36638	#define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33244	#define vst3q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36641,14 +33247,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36641,14 +33247,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36641	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \	33247	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 7, 6, 5, 4, 3, 2, 1, 0); \
36642	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33248	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36643	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33249	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36644	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 40); \	33250	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 40); \
36645	})	33251	})
36646	#endif	33252	#endif
36647		33253
36648	#ifdef __LITTLE_ENDIAN__	33254	#ifdef __LITTLE_ENDIAN__
36649	#define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33255	#define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36650	float16x4x3_t __s1 = __p1; \	33256	float16x4x3_t __s1 = __p1; \
36651	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 8); \	33257	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 8); \
36652	})	33258	})
36653	#else	33259	#else
36654	#define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33260	#define vst3_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36657,14 +33263,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36657,14 +33263,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36657	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \	33263	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 3, 2, 1, 0); \
36658	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33264	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36659	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33265	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36660	__builtin_neon_vst3_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 8); \	33266	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], __p2, 8); \
36661	})	33267	})
36662	#endif	33268	#endif
36663		33269
36664	#ifdef __LITTLE_ENDIAN__	33270	#ifdef __LITTLE_ENDIAN__
36665	#define vst4q_f16(__p0, __p1) __extension__ ({ \	33271	#define vst4q_f16(__p0, __p1) __extension__ ({ \
36666	float16x8x4_t __s1 = __p1; \	33272	float16x8x4_t __s1 = __p1; \
36667	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 40); \	33273	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 40); \
36668	})	33274	})
36669	#else	33275	#else
36670	#define vst4q_f16(__p0, __p1) __extension__ ({ \	33276	#define vst4q_f16(__p0, __p1) __extension__ ({ \
...	@@ -36674,14 +33280,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36674,14 +33280,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36674	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33280	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36675	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33281	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36676	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	33282	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
36677	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 40); \	33283	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 40); \
36678	})	33284	})
36679	#endif	33285	#endif
36680		33286
36681	#ifdef __LITTLE_ENDIAN__	33287	#ifdef __LITTLE_ENDIAN__
36682	#define vst4_f16(__p0, __p1) __extension__ ({ \	33288	#define vst4_f16(__p0, __p1) __extension__ ({ \
36683	float16x4x4_t __s1 = __p1; \	33289	float16x4x4_t __s1 = __p1; \
36684	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 8); \	33290	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 8); \
36685	})	33291	})
36686	#else	33292	#else
36687	#define vst4_f16(__p0, __p1) __extension__ ({ \	33293	#define vst4_f16(__p0, __p1) __extension__ ({ \
...	@@ -36691,14 +33297,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36691,14 +33297,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36691	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33297	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36692	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33298	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36693	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	33299	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
36694	__builtin_neon_vst4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 8); \	33300	__builtin_neon_vst4_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], 8); \
36695	})	33301	})
36696	#endif	33302	#endif
36697		33303
36698	#ifdef __LITTLE_ENDIAN__	33304	#ifdef __LITTLE_ENDIAN__
36699	#define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33305	#define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36700	float16x8x4_t __s1 = __p1; \	33306	float16x8x4_t __s1 = __p1; \
36701	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 40); \	33307	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 40); \
36702	})	33308	})
36703	#else	33309	#else
36704	#define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33310	#define vst4q_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36708,14 +33314,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36708,14 +33314,14 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36708	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \	33314	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 7, 6, 5, 4, 3, 2, 1, 0); \
36709	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \	33315	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 7, 6, 5, 4, 3, 2, 1, 0); \
36710	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \	33316	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 7, 6, 5, 4, 3, 2, 1, 0); \
36711	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 40); \	33317	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 40); \
36712	})	33318	})
36713	#endif	33319	#endif
36714		33320
36715	#ifdef __LITTLE_ENDIAN__	33321	#ifdef __LITTLE_ENDIAN__
36716	#define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33322	#define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
36717	float16x4x4_t __s1 = __p1; \	33323	float16x4x4_t __s1 = __p1; \
36718	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 8); \	33324	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 8); \
36719	})	33325	})
36720	#else	33326	#else
36721	#define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \	33327	#define vst4_lane_f16(__p0, __p1, __p2) __extension__ ({ \
...	@@ -36725,7 +33331,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {	...	@@ -36725,7 +33331,7 @@ __ai float32x4_t __noswap_vcvt_f32_f16(float16x4_t __p0) {
36725	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \	33331	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 3, 2, 1, 0); \
36726	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \	33332	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 3, 2, 1, 0); \
36727	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \	33333	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 3, 2, 1, 0); \
36728	__builtin_neon_vst4_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 8); \	33334	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__rev1.val[0], (int8x8_t)__rev1.val[1], (int8x8_t)__rev1.val[2], (int8x8_t)__rev1.val[3], __p2, 8); \
36729	})	33335	})
36730	#endif	33336	#endif
36731		33337
...	@@ -37058,7 +33664,7 @@ __ai uint8x16_t vaesmcq_u8(uint8x16_t __p0) {	...	@@ -37058,7 +33664,7 @@ __ai uint8x16_t vaesmcq_u8(uint8x16_t __p0) {
37058	#ifdef __LITTLE_ENDIAN__	33664	#ifdef __LITTLE_ENDIAN__
37059	__ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	33665	__ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37060	uint32x4_t __ret;	33666	uint32x4_t __ret;
37061	__ret = (uint32x4_t) __builtin_neon_vsha1cq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);	33667	__ret = (uint32x4_t) __builtin_neon_vsha1cq_u32(__p0, __p1, __p2);
37062	return __ret;	33668	return __ret;
37063	}	33669	}
37064	#else	33670	#else
...	@@ -37066,30 +33672,21 @@ __ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	...	@@ -37066,30 +33672,21 @@ __ai uint32x4_t vsha1cq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37066	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	33672	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
37067	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);	33673	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);
37068	uint32x4_t __ret;	33674	uint32x4_t __ret;
37069	__ret = (uint32x4_t) __builtin_neon_vsha1cq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);	33675	__ret = (uint32x4_t) __builtin_neon_vsha1cq_u32(__rev0, __p1, __rev2);
37070	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	33676	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
37071	return __ret;	33677	return __ret;
37072	}	33678	}
37073	#endif	33679	#endif
37074		33680
37075	#ifdef __LITTLE_ENDIAN__
37076	__ai uint32_t vsha1h_u32(uint32_t __p0) {
37077	uint32_t __ret;
37078	__ret = (uint32_t) __builtin_neon_vsha1h_u32(__p0);
37079	return __ret;
37080	}
37081	#else
37082	__ai uint32_t vsha1h_u32(uint32_t __p0) {	33681	__ai uint32_t vsha1h_u32(uint32_t __p0) {
37083	uint32_t __ret;	33682	uint32_t __ret;
37084	__ret = (uint32_t) __builtin_neon_vsha1h_u32(__p0);	33683	__ret = (uint32_t) __builtin_neon_vsha1h_u32(__p0);
37085	return __ret;	33684	return __ret;
37086	}	33685	}
37087	#endif
37088
37089	#ifdef __LITTLE_ENDIAN__	33686	#ifdef __LITTLE_ENDIAN__
37090	__ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	33687	__ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37091	uint32x4_t __ret;	33688	uint32x4_t __ret;
37092	__ret = (uint32x4_t) __builtin_neon_vsha1mq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);	33689	__ret = (uint32x4_t) __builtin_neon_vsha1mq_u32(__p0, __p1, __p2);
37093	return __ret;	33690	return __ret;
37094	}	33691	}
37095	#else	33692	#else
...	@@ -37097,7 +33694,7 @@ __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	...	@@ -37097,7 +33694,7 @@ __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37097	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	33694	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
37098	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);	33695	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);
37099	uint32x4_t __ret;	33696	uint32x4_t __ret;
37100	__ret = (uint32x4_t) __builtin_neon_vsha1mq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);	33697	__ret = (uint32x4_t) __builtin_neon_vsha1mq_u32(__rev0, __p1, __rev2);
37101	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	33698	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
37102	return __ret;	33699	return __ret;
37103	}	33700	}
...	@@ -37106,7 +33703,7 @@ __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	...	@@ -37106,7 +33703,7 @@ __ai uint32x4_t vsha1mq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37106	#ifdef __LITTLE_ENDIAN__	33703	#ifdef __LITTLE_ENDIAN__
37107	__ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	33704	__ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37108	uint32x4_t __ret;	33705	uint32x4_t __ret;
37109	__ret = (uint32x4_t) __builtin_neon_vsha1pq_u32((int8x16_t)__p0, __p1, (int8x16_t)__p2);	33706	__ret = (uint32x4_t) __builtin_neon_vsha1pq_u32(__p0, __p1, __p2);
37110	return __ret;	33707	return __ret;
37111	}	33708	}
37112	#else	33709	#else
...	@@ -37114,7 +33711,7 @@ __ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {	...	@@ -37114,7 +33711,7 @@ __ai uint32x4_t vsha1pq_u32(uint32x4_t __p0, uint32_t __p1, uint32x4_t __p2) {
37114	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	33711	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
37115	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);	33712	uint32x4_t __rev2; __rev2 = __builtin_shufflevector(__p2, __p2, 3, 2, 1, 0);
37116	uint32x4_t __ret;	33713	uint32x4_t __ret;
37117	__ret = (uint32x4_t) __builtin_neon_vsha1pq_u32((int8x16_t)__rev0, __p1, (int8x16_t)__rev2);	33714	__ret = (uint32x4_t) __builtin_neon_vsha1pq_u32(__rev0, __p1, __rev2);
37118	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);	33715	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
37119	return __ret;	33716	return __ret;
37120	}	33717	}
...	@@ -37388,20 +33985,11 @@ __ai float32x2_t vrndn_f32(float32x2_t __p0) {	...	@@ -37388,20 +33985,11 @@ __ai float32x2_t vrndn_f32(float32x2_t __p0) {
37388	}	33985	}
37389	#endif	33986	#endif
37390		33987
37391	#ifdef __LITTLE_ENDIAN__
37392	__ai float32_t vrndns_f32(float32_t __p0) {
37393	float32_t __ret;
37394	__ret = (float32_t) __builtin_neon_vrndns_f32(__p0);
37395	return __ret;
37396	}
37397	#else
37398	__ai float32_t vrndns_f32(float32_t __p0) {	33988	__ai float32_t vrndns_f32(float32_t __p0) {
37399	float32_t __ret;	33989	float32_t __ret;
37400	__ret = (float32_t) __builtin_neon_vrndns_f32(__p0);	33990	__ret = (float32_t) __builtin_neon_vrndns_f32(__p0);
37401	return __ret;	33991	return __ret;
37402	}	33992	}
37403	#endif
37404
37405	#ifdef __LITTLE_ENDIAN__	33993	#ifdef __LITTLE_ENDIAN__
37406	__ai float32x4_t vrndpq_f32(float32x4_t __p0) {	33994	__ai float32x4_t vrndpq_f32(float32x4_t __p0) {
37407	float32x4_t __ret;	33995	float32x4_t __ret;
...	@@ -37818,20 +34406,11 @@ __ai int64x2_t vcvtaq_s64_f64(float64x2_t __p0) {	...	@@ -37818,20 +34406,11 @@ __ai int64x2_t vcvtaq_s64_f64(float64x2_t __p0) {
37818	}	34406	}
37819	#endif	34407	#endif
37820		34408
37821	#ifdef __LITTLE_ENDIAN__
37822	__ai int64x1_t vcvta_s64_f64(float64x1_t __p0) {
37823	int64x1_t __ret;
37824	__ret = (int64x1_t) __builtin_neon_vcvta_s64_v((int8x8_t)__p0, 3);
37825	return __ret;
37826	}
37827	#else
37828	__ai int64x1_t vcvta_s64_f64(float64x1_t __p0) {	34409	__ai int64x1_t vcvta_s64_f64(float64x1_t __p0) {
37829	int64x1_t __ret;	34410	int64x1_t __ret;
37830	__ret = (int64x1_t) __builtin_neon_vcvta_s64_v((int8x8_t)__p0, 3);	34411	__ret = (int64x1_t) __builtin_neon_vcvta_s64_v((int8x8_t)__p0, 3);
37831	return __ret;	34412	return __ret;
37832	}	34413	}
37833	#endif
37834
37835	#ifdef __LITTLE_ENDIAN__	34414	#ifdef __LITTLE_ENDIAN__
37836	__ai uint64x2_t vcvtaq_u64_f64(float64x2_t __p0) {	34415	__ai uint64x2_t vcvtaq_u64_f64(float64x2_t __p0) {
37837	uint64x2_t __ret;	34416	uint64x2_t __ret;
...	@@ -37848,20 +34427,11 @@ __ai uint64x2_t vcvtaq_u64_f64(float64x2_t __p0) {	...	@@ -37848,20 +34427,11 @@ __ai uint64x2_t vcvtaq_u64_f64(float64x2_t __p0) {
37848	}	34427	}
37849	#endif	34428	#endif
37850		34429
37851	#ifdef __LITTLE_ENDIAN__
37852	__ai uint64x1_t vcvta_u64_f64(float64x1_t __p0) {
37853	uint64x1_t __ret;
37854	__ret = (uint64x1_t) __builtin_neon_vcvta_u64_v((int8x8_t)__p0, 19);
37855	return __ret;
37856	}
37857	#else
37858	__ai uint64x1_t vcvta_u64_f64(float64x1_t __p0) {	34430	__ai uint64x1_t vcvta_u64_f64(float64x1_t __p0) {
37859	uint64x1_t __ret;	34431	uint64x1_t __ret;
37860	__ret = (uint64x1_t) __builtin_neon_vcvta_u64_v((int8x8_t)__p0, 19);	34432	__ret = (uint64x1_t) __builtin_neon_vcvta_u64_v((int8x8_t)__p0, 19);
37861	return __ret;	34433	return __ret;
37862	}	34434	}
37863	#endif
37864
37865	#ifdef __LITTLE_ENDIAN__	34435	#ifdef __LITTLE_ENDIAN__
37866	__ai int64x2_t vcvtmq_s64_f64(float64x2_t __p0) {	34436	__ai int64x2_t vcvtmq_s64_f64(float64x2_t __p0) {
37867	int64x2_t __ret;	34437	int64x2_t __ret;
...	@@ -37878,20 +34448,11 @@ __ai int64x2_t vcvtmq_s64_f64(float64x2_t __p0) {	...	@@ -37878,20 +34448,11 @@ __ai int64x2_t vcvtmq_s64_f64(float64x2_t __p0) {
37878	}	34448	}
37879	#endif	34449	#endif
37880		34450
37881	#ifdef __LITTLE_ENDIAN__
37882	__ai int64x1_t vcvtm_s64_f64(float64x1_t __p0) {
37883	int64x1_t __ret;
37884	__ret = (int64x1_t) __builtin_neon_vcvtm_s64_v((int8x8_t)__p0, 3);
37885	return __ret;
37886	}
37887	#else
37888	__ai int64x1_t vcvtm_s64_f64(float64x1_t __p0) {	34451	__ai int64x1_t vcvtm_s64_f64(float64x1_t __p0) {
37889	int64x1_t __ret;	34452	int64x1_t __ret;
37890	__ret = (int64x1_t) __builtin_neon_vcvtm_s64_v((int8x8_t)__p0, 3);	34453	__ret = (int64x1_t) __builtin_neon_vcvtm_s64_v((int8x8_t)__p0, 3);
37891	return __ret;	34454	return __ret;
37892	}	34455	}
37893	#endif
37894
37895	#ifdef __LITTLE_ENDIAN__	34456	#ifdef __LITTLE_ENDIAN__
37896	__ai uint64x2_t vcvtmq_u64_f64(float64x2_t __p0) {	34457	__ai uint64x2_t vcvtmq_u64_f64(float64x2_t __p0) {
37897	uint64x2_t __ret;	34458	uint64x2_t __ret;
...	@@ -37908,20 +34469,11 @@ __ai uint64x2_t vcvtmq_u64_f64(float64x2_t __p0) {	...	@@ -37908,20 +34469,11 @@ __ai uint64x2_t vcvtmq_u64_f64(float64x2_t __p0) {
37908	}	34469	}
37909	#endif	34470	#endif
37910		34471
37911	#ifdef __LITTLE_ENDIAN__
37912	__ai uint64x1_t vcvtm_u64_f64(float64x1_t __p0) {
37913	uint64x1_t __ret;
37914	__ret = (uint64x1_t) __builtin_neon_vcvtm_u64_v((int8x8_t)__p0, 19);
37915	return __ret;
37916	}
37917	#else
37918	__ai uint64x1_t vcvtm_u64_f64(float64x1_t __p0) {	34472	__ai uint64x1_t vcvtm_u64_f64(float64x1_t __p0) {
37919	uint64x1_t __ret;	34473	uint64x1_t __ret;
37920	__ret = (uint64x1_t) __builtin_neon_vcvtm_u64_v((int8x8_t)__p0, 19);	34474	__ret = (uint64x1_t) __builtin_neon_vcvtm_u64_v((int8x8_t)__p0, 19);
37921	return __ret;	34475	return __ret;
37922	}	34476	}
37923	#endif
37924
37925	#ifdef __LITTLE_ENDIAN__	34477	#ifdef __LITTLE_ENDIAN__
37926	__ai int64x2_t vcvtnq_s64_f64(float64x2_t __p0) {	34478	__ai int64x2_t vcvtnq_s64_f64(float64x2_t __p0) {
37927	int64x2_t __ret;	34479	int64x2_t __ret;
...	@@ -37938,20 +34490,11 @@ __ai int64x2_t vcvtnq_s64_f64(float64x2_t __p0) {	...	@@ -37938,20 +34490,11 @@ __ai int64x2_t vcvtnq_s64_f64(float64x2_t __p0) {
37938	}	34490	}
37939	#endif	34491	#endif
37940		34492
37941	#ifdef __LITTLE_ENDIAN__
37942	__ai int64x1_t vcvtn_s64_f64(float64x1_t __p0) {
37943	int64x1_t __ret;
37944	__ret = (int64x1_t) __builtin_neon_vcvtn_s64_v((int8x8_t)__p0, 3);
37945	return __ret;
37946	}
37947	#else
37948	__ai int64x1_t vcvtn_s64_f64(float64x1_t __p0) {	34493	__ai int64x1_t vcvtn_s64_f64(float64x1_t __p0) {
37949	int64x1_t __ret;	34494	int64x1_t __ret;
37950	__ret = (int64x1_t) __builtin_neon_vcvtn_s64_v((int8x8_t)__p0, 3);	34495	__ret = (int64x1_t) __builtin_neon_vcvtn_s64_v((int8x8_t)__p0, 3);
37951	return __ret;	34496	return __ret;
37952	}	34497	}
37953	#endif
37954
37955	#ifdef __LITTLE_ENDIAN__	34498	#ifdef __LITTLE_ENDIAN__
37956	__ai uint64x2_t vcvtnq_u64_f64(float64x2_t __p0) {	34499	__ai uint64x2_t vcvtnq_u64_f64(float64x2_t __p0) {
37957	uint64x2_t __ret;	34500	uint64x2_t __ret;
...	@@ -37968,20 +34511,11 @@ __ai uint64x2_t vcvtnq_u64_f64(float64x2_t __p0) {	...	@@ -37968,20 +34511,11 @@ __ai uint64x2_t vcvtnq_u64_f64(float64x2_t __p0) {
37968	}	34511	}
37969	#endif	34512	#endif
37970		34513
37971	#ifdef __LITTLE_ENDIAN__
37972	__ai uint64x1_t vcvtn_u64_f64(float64x1_t __p0) {	34514	__ai uint64x1_t vcvtn_u64_f64(float64x1_t __p0) {
37973	uint64x1_t __ret;	34515	uint64x1_t __ret;
37974	__ret = (uint64x1_t) __builtin_neon_vcvtn_u64_v((int8x8_t)__p0, 19);	34516	__ret = (uint64x1_t) __builtin_neon_vcvtn_u64_v((int8x8_t)__p0, 19);
37975	return __ret;	34517	return __ret;
37976	}	34518	}
37977	#else
37978	__ai uint64x1_t vcvtn_u64_f64(float64x1_t __p0) {
37979	uint64x1_t __ret;
37980	__ret = (uint64x1_t) __builtin_neon_vcvtn_u64_v((int8x8_t)__p0, 19);
37981	return __ret;
37982	}
37983	#endif
37984
37985	#ifdef __LITTLE_ENDIAN__	34519	#ifdef __LITTLE_ENDIAN__
37986	__ai int64x2_t vcvtpq_s64_f64(float64x2_t __p0) {	34520	__ai int64x2_t vcvtpq_s64_f64(float64x2_t __p0) {
37987	int64x2_t __ret;	34521	int64x2_t __ret;
...	@@ -37998,20 +34532,11 @@ __ai int64x2_t vcvtpq_s64_f64(float64x2_t __p0) {	...	@@ -37998,20 +34532,11 @@ __ai int64x2_t vcvtpq_s64_f64(float64x2_t __p0) {
37998	}	34532	}
37999	#endif	34533	#endif
38000		34534
38001	#ifdef __LITTLE_ENDIAN__
38002	__ai int64x1_t vcvtp_s64_f64(float64x1_t __p0) {
38003	int64x1_t __ret;
38004	__ret = (int64x1_t) __builtin_neon_vcvtp_s64_v((int8x8_t)__p0, 3);
38005	return __ret;
38006	}
38007	#else
38008	__ai int64x1_t vcvtp_s64_f64(float64x1_t __p0) {	34535	__ai int64x1_t vcvtp_s64_f64(float64x1_t __p0) {
38009	int64x1_t __ret;	34536	int64x1_t __ret;
38010	__ret = (int64x1_t) __builtin_neon_vcvtp_s64_v((int8x8_t)__p0, 3);	34537	__ret = (int64x1_t) __builtin_neon_vcvtp_s64_v((int8x8_t)__p0, 3);
38011	return __ret;	34538	return __ret;
38012	}	34539	}
38013	#endif
38014
38015	#ifdef __LITTLE_ENDIAN__	34540	#ifdef __LITTLE_ENDIAN__
38016	__ai uint64x2_t vcvtpq_u64_f64(float64x2_t __p0) {	34541	__ai uint64x2_t vcvtpq_u64_f64(float64x2_t __p0) {
38017	uint64x2_t __ret;	34542	uint64x2_t __ret;
...	@@ -38028,5508 +34553,1971 @@ __ai uint64x2_t vcvtpq_u64_f64(float64x2_t __p0) {	...	@@ -38028,5508 +34553,1971 @@ __ai uint64x2_t vcvtpq_u64_f64(float64x2_t __p0) {
38028	}	34553	}
38029	#endif	34554	#endif
38030		34555
38031	#ifdef __LITTLE_ENDIAN__
38032	__ai uint64x1_t vcvtp_u64_f64(float64x1_t __p0) {
38033	uint64x1_t __ret;
38034	__ret = (uint64x1_t) __builtin_neon_vcvtp_u64_v((int8x8_t)__p0, 19);
38035	return __ret;
38036	}
38037	#else
38038	__ai uint64x1_t vcvtp_u64_f64(float64x1_t __p0) {	34556	__ai uint64x1_t vcvtp_u64_f64(float64x1_t __p0) {
38039	uint64x1_t __ret;	34557	uint64x1_t __ret;
38040	__ret = (uint64x1_t) __builtin_neon_vcvtp_u64_v((int8x8_t)__p0, 19);	34558	__ret = (uint64x1_t) __builtin_neon_vcvtp_u64_v((int8x8_t)__p0, 19);
38041	return __ret;	34559	return __ret;
38042	}	34560	}
38043	#endif
38044
38045	#ifdef __LITTLE_ENDIAN__
38046	__ai poly8x8_t vreinterpret_p8_p64(poly64x1_t __p0) {
38047	poly8x8_t __ret;
38048	__ret = (poly8x8_t)(__p0);
38049	return __ret;
38050	}
38051	#else
38052	__ai poly8x8_t vreinterpret_p8_p64(poly64x1_t __p0) {	34561	__ai poly8x8_t vreinterpret_p8_p64(poly64x1_t __p0) {
38053	poly8x8_t __ret;	34562	poly8x8_t __ret;
38054	__ret = (poly8x8_t)(__p0);	34563	__ret = (poly8x8_t)(__p0);
38055	return __ret;	34564	return __ret;
38056	}	34565	}
38057	#endif
38058
38059	#ifdef __LITTLE_ENDIAN__
38060	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {
38061	poly8x8_t __ret;
38062	__ret = (poly8x8_t)(__p0);
38063	return __ret;
38064	}
38065	#else
38066	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {	34566	__ai poly8x8_t vreinterpret_p8_p16(poly16x4_t __p0) {
38067	poly8x8_t __ret;	34567	poly8x8_t __ret;
38068	__ret = (poly8x8_t)(__p0);	34568	__ret = (poly8x8_t)(__p0);
38069	return __ret;	34569	return __ret;
38070	}	34570	}
38071	#endif
38072
38073	#ifdef __LITTLE_ENDIAN__
38074	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {
38075	poly8x8_t __ret;
38076	__ret = (poly8x8_t)(__p0);
38077	return __ret;
38078	}
38079	#else
38080	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {	34571	__ai poly8x8_t vreinterpret_p8_u8(uint8x8_t __p0) {
38081	poly8x8_t __ret;	34572	poly8x8_t __ret;
38082	__ret = (poly8x8_t)(__p0);	34573	__ret = (poly8x8_t)(__p0);
38083	return __ret;	34574	return __ret;
38084	}	34575	}
38085	#endif
38086
38087	#ifdef __LITTLE_ENDIAN__
38088	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {
38089	poly8x8_t __ret;
38090	__ret = (poly8x8_t)(__p0);
38091	return __ret;
38092	}
38093	#else
38094	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {	34576	__ai poly8x8_t vreinterpret_p8_u32(uint32x2_t __p0) {
38095	poly8x8_t __ret;	34577	poly8x8_t __ret;
38096	__ret = (poly8x8_t)(__p0);	34578	__ret = (poly8x8_t)(__p0);
38097	return __ret;	34579	return __ret;
38098	}	34580	}
38099	#endif
38100
38101	#ifdef __LITTLE_ENDIAN__
38102	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {
38103	poly8x8_t __ret;
38104	__ret = (poly8x8_t)(__p0);
38105	return __ret;
38106	}
38107	#else
38108	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {	34581	__ai poly8x8_t vreinterpret_p8_u64(uint64x1_t __p0) {
38109	poly8x8_t __ret;	34582	poly8x8_t __ret;
38110	__ret = (poly8x8_t)(__p0);	34583	__ret = (poly8x8_t)(__p0);
38111	return __ret;	34584	return __ret;
38112	}	34585	}
38113	#endif
38114
38115	#ifdef __LITTLE_ENDIAN__
38116	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {
38117	poly8x8_t __ret;
38118	__ret = (poly8x8_t)(__p0);
38119	return __ret;
38120	}
38121	#else
38122	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {	34586	__ai poly8x8_t vreinterpret_p8_u16(uint16x4_t __p0) {
38123	poly8x8_t __ret;	34587	poly8x8_t __ret;
38124	__ret = (poly8x8_t)(__p0);	34588	__ret = (poly8x8_t)(__p0);
38125	return __ret;	34589	return __ret;
38126	}	34590	}
38127	#endif
38128
38129	#ifdef __LITTLE_ENDIAN__
38130	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
38131	poly8x8_t __ret;
38132	__ret = (poly8x8_t)(__p0);
38133	return __ret;
38134	}
38135	#else
38136	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {	34591	__ai poly8x8_t vreinterpret_p8_s8(int8x8_t __p0) {
38137	poly8x8_t __ret;	34592	poly8x8_t __ret;
38138	__ret = (poly8x8_t)(__p0);	34593	__ret = (poly8x8_t)(__p0);
38139	return __ret;	34594	return __ret;
38140	}	34595	}
38141	#endif
38142
38143	#ifdef __LITTLE_ENDIAN__
38144	__ai poly8x8_t vreinterpret_p8_f64(float64x1_t __p0) {
38145	poly8x8_t __ret;
38146	__ret = (poly8x8_t)(__p0);
38147	return __ret;
38148	}
38149	#else
38150	__ai poly8x8_t vreinterpret_p8_f64(float64x1_t __p0) {	34596	__ai poly8x8_t vreinterpret_p8_f64(float64x1_t __p0) {
38151	poly8x8_t __ret;	34597	poly8x8_t __ret;
38152	__ret = (poly8x8_t)(__p0);	34598	__ret = (poly8x8_t)(__p0);
38153	return __ret;	34599	return __ret;
38154	}	34600	}
38155	#endif
38156
38157	#ifdef __LITTLE_ENDIAN__
38158	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {
38159	poly8x8_t __ret;
38160	__ret = (poly8x8_t)(__p0);
38161	return __ret;
38162	}
38163	#else
38164	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {	34601	__ai poly8x8_t vreinterpret_p8_f32(float32x2_t __p0) {
38165	poly8x8_t __ret;	34602	poly8x8_t __ret;
38166	__ret = (poly8x8_t)(__p0);	34603	__ret = (poly8x8_t)(__p0);
38167	return __ret;	34604	return __ret;
38168	}	34605	}
38169	#endif
38170
38171	#ifdef __LITTLE_ENDIAN__
38172	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {
38173	poly8x8_t __ret;
38174	__ret = (poly8x8_t)(__p0);
38175	return __ret;
38176	}
38177	#else
38178	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {	34606	__ai poly8x8_t vreinterpret_p8_f16(float16x4_t __p0) {
38179	poly8x8_t __ret;	34607	poly8x8_t __ret;
38180	__ret = (poly8x8_t)(__p0);	34608	__ret = (poly8x8_t)(__p0);
38181	return __ret;	34609	return __ret;
38182	}	34610	}
38183	#endif
38184
38185	#ifdef __LITTLE_ENDIAN__
38186	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {
38187	poly8x8_t __ret;
38188	__ret = (poly8x8_t)(__p0);
38189	return __ret;
38190	}
38191	#else
38192	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {	34611	__ai poly8x8_t vreinterpret_p8_s32(int32x2_t __p0) {
38193	poly8x8_t __ret;	34612	poly8x8_t __ret;
38194	__ret = (poly8x8_t)(__p0);	34613	__ret = (poly8x8_t)(__p0);
38195	return __ret;	34614	return __ret;
38196	}	34615	}
38197	#endif
38198
38199	#ifdef __LITTLE_ENDIAN__
38200	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {
38201	poly8x8_t __ret;
38202	__ret = (poly8x8_t)(__p0);
38203	return __ret;
38204	}
38205	#else
38206	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {	34616	__ai poly8x8_t vreinterpret_p8_s64(int64x1_t __p0) {
38207	poly8x8_t __ret;	34617	poly8x8_t __ret;
38208	__ret = (poly8x8_t)(__p0);	34618	__ret = (poly8x8_t)(__p0);
38209	return __ret;	34619	return __ret;
38210	}	34620	}
38211	#endif
38212
38213	#ifdef __LITTLE_ENDIAN__
38214	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {
38215	poly8x8_t __ret;
38216	__ret = (poly8x8_t)(__p0);
38217	return __ret;
38218	}
38219	#else
38220	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {	34621	__ai poly8x8_t vreinterpret_p8_s16(int16x4_t __p0) {
38221	poly8x8_t __ret;	34622	poly8x8_t __ret;
38222	__ret = (poly8x8_t)(__p0);	34623	__ret = (poly8x8_t)(__p0);
38223	return __ret;	34624	return __ret;
38224	}	34625	}
38225	#endif
38226
38227	#ifdef __LITTLE_ENDIAN__
38228	__ai poly64x1_t vreinterpret_p64_p8(poly8x8_t __p0) {
38229	poly64x1_t __ret;
38230	__ret = (poly64x1_t)(__p0);
38231	return __ret;
38232	}
38233	#else
38234	__ai poly64x1_t vreinterpret_p64_p8(poly8x8_t __p0) {	34626	__ai poly64x1_t vreinterpret_p64_p8(poly8x8_t __p0) {
38235	poly64x1_t __ret;	34627	poly64x1_t __ret;
38236	__ret = (poly64x1_t)(__p0);	34628	__ret = (poly64x1_t)(__p0);
38237	return __ret;	34629	return __ret;
38238	}	34630	}
38239	#endif
38240
38241	#ifdef __LITTLE_ENDIAN__
38242	__ai poly64x1_t vreinterpret_p64_p16(poly16x4_t __p0) {
38243	poly64x1_t __ret;
38244	__ret = (poly64x1_t)(__p0);
38245	return __ret;
38246	}
38247	#else
38248	__ai poly64x1_t vreinterpret_p64_p16(poly16x4_t __p0) {	34631	__ai poly64x1_t vreinterpret_p64_p16(poly16x4_t __p0) {
38249	poly64x1_t __ret;	34632	poly64x1_t __ret;
38250	__ret = (poly64x1_t)(__p0);	34633	__ret = (poly64x1_t)(__p0);
38251	return __ret;	34634	return __ret;
38252	}	34635	}
38253	#endif
38254
38255	#ifdef __LITTLE_ENDIAN__
38256	__ai poly64x1_t vreinterpret_p64_u8(uint8x8_t __p0) {
38257	poly64x1_t __ret;
38258	__ret = (poly64x1_t)(__p0);
38259	return __ret;
38260	}
38261	#else
38262	__ai poly64x1_t vreinterpret_p64_u8(uint8x8_t __p0) {	34636	__ai poly64x1_t vreinterpret_p64_u8(uint8x8_t __p0) {
38263	poly64x1_t __ret;	34637	poly64x1_t __ret;
38264	__ret = (poly64x1_t)(__p0);	34638	__ret = (poly64x1_t)(__p0);
38265	return __ret;	34639	return __ret;
38266	}	34640	}
38267	#endif
38268
38269	#ifdef __LITTLE_ENDIAN__
38270	__ai poly64x1_t vreinterpret_p64_u32(uint32x2_t __p0) {
38271	poly64x1_t __ret;
38272	__ret = (poly64x1_t)(__p0);
38273	return __ret;
38274	}
38275	#else
38276	__ai poly64x1_t vreinterpret_p64_u32(uint32x2_t __p0) {	34641	__ai poly64x1_t vreinterpret_p64_u32(uint32x2_t __p0) {
38277	poly64x1_t __ret;	34642	poly64x1_t __ret;
38278	__ret = (poly64x1_t)(__p0);	34643	__ret = (poly64x1_t)(__p0);
38279	return __ret;	34644	return __ret;
38280	}	34645	}
38281	#endif
38282
38283	#ifdef __LITTLE_ENDIAN__
38284	__ai poly64x1_t vreinterpret_p64_u64(uint64x1_t __p0) {
38285	poly64x1_t __ret;
38286	__ret = (poly64x1_t)(__p0);
38287	return __ret;
38288	}
38289	#else
38290	__ai poly64x1_t vreinterpret_p64_u64(uint64x1_t __p0) {	34646	__ai poly64x1_t vreinterpret_p64_u64(uint64x1_t __p0) {
38291	poly64x1_t __ret;	34647	poly64x1_t __ret;
38292	__ret = (poly64x1_t)(__p0);	34648	__ret = (poly64x1_t)(__p0);
38293	return __ret;	34649	return __ret;
38294	}	34650	}
38295	#endif
38296
38297	#ifdef __LITTLE_ENDIAN__
38298	__ai poly64x1_t vreinterpret_p64_u16(uint16x4_t __p0) {
38299	poly64x1_t __ret;
38300	__ret = (poly64x1_t)(__p0);
38301	return __ret;
38302	}
38303	#else
38304	__ai poly64x1_t vreinterpret_p64_u16(uint16x4_t __p0) {	34651	__ai poly64x1_t vreinterpret_p64_u16(uint16x4_t __p0) {
38305	poly64x1_t __ret;	34652	poly64x1_t __ret;
38306	__ret = (poly64x1_t)(__p0);	34653	__ret = (poly64x1_t)(__p0);
38307	return __ret;	34654	return __ret;
38308	}	34655	}
38309	#endif
38310
38311	#ifdef __LITTLE_ENDIAN__
38312	__ai poly64x1_t vreinterpret_p64_s8(int8x8_t __p0) {
38313	poly64x1_t __ret;
38314	__ret = (poly64x1_t)(__p0);
38315	return __ret;
38316	}
38317	#else
38318	__ai poly64x1_t vreinterpret_p64_s8(int8x8_t __p0) {	34656	__ai poly64x1_t vreinterpret_p64_s8(int8x8_t __p0) {
38319	poly64x1_t __ret;	34657	poly64x1_t __ret;
38320	__ret = (poly64x1_t)(__p0);	34658	__ret = (poly64x1_t)(__p0);
38321	return __ret;	34659	return __ret;
38322	}	34660	}
38323	#endif
38324
38325	#ifdef __LITTLE_ENDIAN__
38326	__ai poly64x1_t vreinterpret_p64_f64(float64x1_t __p0) {
38327	poly64x1_t __ret;
38328	__ret = (poly64x1_t)(__p0);
38329	return __ret;
38330	}
38331	#else
38332	__ai poly64x1_t vreinterpret_p64_f64(float64x1_t __p0) {	34661	__ai poly64x1_t vreinterpret_p64_f64(float64x1_t __p0) {
38333	poly64x1_t __ret;	34662	poly64x1_t __ret;
38334	__ret = (poly64x1_t)(__p0);	34663	__ret = (poly64x1_t)(__p0);
38335	return __ret;	34664	return __ret;
38336	}	34665	}
38337	#endif
38338
38339	#ifdef __LITTLE_ENDIAN__
38340	__ai poly64x1_t vreinterpret_p64_f32(float32x2_t __p0) {
38341	poly64x1_t __ret;
38342	__ret = (poly64x1_t)(__p0);
38343	return __ret;
38344	}
38345	#else
38346	__ai poly64x1_t vreinterpret_p64_f32(float32x2_t __p0) {	34666	__ai poly64x1_t vreinterpret_p64_f32(float32x2_t __p0) {
38347	poly64x1_t __ret;	34667	poly64x1_t __ret;
38348	__ret = (poly64x1_t)(__p0);	34668	__ret = (poly64x1_t)(__p0);
38349	return __ret;	34669	return __ret;
38350	}	34670	}
38351	#endif
38352
38353	#ifdef __LITTLE_ENDIAN__
38354	__ai poly64x1_t vreinterpret_p64_f16(float16x4_t __p0) {
38355	poly64x1_t __ret;
38356	__ret = (poly64x1_t)(__p0);
38357	return __ret;
38358	}
38359	#else
38360	__ai poly64x1_t vreinterpret_p64_f16(float16x4_t __p0) {	34671	__ai poly64x1_t vreinterpret_p64_f16(float16x4_t __p0) {
38361	poly64x1_t __ret;	34672	poly64x1_t __ret;
38362	__ret = (poly64x1_t)(__p0);	34673	__ret = (poly64x1_t)(__p0);
38363	return __ret;	34674	return __ret;
38364	}	34675	}
38365	#endif
38366
38367	#ifdef __LITTLE_ENDIAN__
38368	__ai poly64x1_t vreinterpret_p64_s32(int32x2_t __p0) {
38369	poly64x1_t __ret;
38370	__ret = (poly64x1_t)(__p0);
38371	return __ret;
38372	}
38373	#else
38374	__ai poly64x1_t vreinterpret_p64_s32(int32x2_t __p0) {	34676	__ai poly64x1_t vreinterpret_p64_s32(int32x2_t __p0) {
38375	poly64x1_t __ret;	34677	poly64x1_t __ret;
38376	__ret = (poly64x1_t)(__p0);	34678	__ret = (poly64x1_t)(__p0);
38377	return __ret;	34679	return __ret;
38378	}	34680	}
38379	#endif
38380
38381	#ifdef __LITTLE_ENDIAN__
38382	__ai poly64x1_t vreinterpret_p64_s64(int64x1_t __p0) {
38383	poly64x1_t __ret;
38384	__ret = (poly64x1_t)(__p0);
38385	return __ret;
38386	}
38387	#else
38388	__ai poly64x1_t vreinterpret_p64_s64(int64x1_t __p0) {	34681	__ai poly64x1_t vreinterpret_p64_s64(int64x1_t __p0) {
38389	poly64x1_t __ret;	34682	poly64x1_t __ret;
38390	__ret = (poly64x1_t)(__p0);	34683	__ret = (poly64x1_t)(__p0);
38391	return __ret;	34684	return __ret;
38392	}	34685	}
38393	#endif
38394
38395	#ifdef __LITTLE_ENDIAN__
38396	__ai poly64x1_t vreinterpret_p64_s16(int16x4_t __p0) {
38397	poly64x1_t __ret;
38398	__ret = (poly64x1_t)(__p0);
38399	return __ret;
38400	}
38401	#else
38402	__ai poly64x1_t vreinterpret_p64_s16(int16x4_t __p0) {	34686	__ai poly64x1_t vreinterpret_p64_s16(int16x4_t __p0) {
38403	poly64x1_t __ret;	34687	poly64x1_t __ret;
38404	__ret = (poly64x1_t)(__p0);	34688	__ret = (poly64x1_t)(__p0);
38405	return __ret;	34689	return __ret;
38406	}	34690	}
38407	#endif
38408
38409	#ifdef __LITTLE_ENDIAN__
38410	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {
38411	poly16x4_t __ret;
38412	__ret = (poly16x4_t)(__p0);
38413	return __ret;
38414	}
38415	#else
38416	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {	34691	__ai poly16x4_t vreinterpret_p16_p8(poly8x8_t __p0) {
38417	poly16x4_t __ret;	34692	poly16x4_t __ret;
38418	__ret = (poly16x4_t)(__p0);	34693	__ret = (poly16x4_t)(__p0);
38419	return __ret;	34694	return __ret;
38420	}	34695	}
38421	#endif
38422
38423	#ifdef __LITTLE_ENDIAN__
38424	__ai poly16x4_t vreinterpret_p16_p64(poly64x1_t __p0) {
38425	poly16x4_t __ret;
38426	__ret = (poly16x4_t)(__p0);
38427	return __ret;
38428	}
38429	#else
38430	__ai poly16x4_t vreinterpret_p16_p64(poly64x1_t __p0) {	34696	__ai poly16x4_t vreinterpret_p16_p64(poly64x1_t __p0) {
38431	poly16x4_t __ret;	34697	poly16x4_t __ret;
38432	__ret = (poly16x4_t)(__p0);	34698	__ret = (poly16x4_t)(__p0);
38433	return __ret;	34699	return __ret;
38434	}	34700	}
38435	#endif
38436
38437	#ifdef __LITTLE_ENDIAN__
38438	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {
38439	poly16x4_t __ret;
38440	__ret = (poly16x4_t)(__p0);
38441	return __ret;
38442	}
38443	#else
38444	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {	34701	__ai poly16x4_t vreinterpret_p16_u8(uint8x8_t __p0) {
38445	poly16x4_t __ret;	34702	poly16x4_t __ret;
38446	__ret = (poly16x4_t)(__p0);	34703	__ret = (poly16x4_t)(__p0);
38447	return __ret;	34704	return __ret;
38448	}	34705	}
38449	#endif
38450
38451	#ifdef __LITTLE_ENDIAN__
38452	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {
38453	poly16x4_t __ret;
38454	__ret = (poly16x4_t)(__p0);
38455	return __ret;
38456	}
38457	#else
38458	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {	34706	__ai poly16x4_t vreinterpret_p16_u32(uint32x2_t __p0) {
38459	poly16x4_t __ret;	34707	poly16x4_t __ret;
38460	__ret = (poly16x4_t)(__p0);	34708	__ret = (poly16x4_t)(__p0);
38461	return __ret;	34709	return __ret;
38462	}	34710	}
38463	#endif
38464
38465	#ifdef __LITTLE_ENDIAN__
38466	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {
38467	poly16x4_t __ret;
38468	__ret = (poly16x4_t)(__p0);
38469	return __ret;
38470	}
38471	#else
38472	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {	34711	__ai poly16x4_t vreinterpret_p16_u64(uint64x1_t __p0) {
38473	poly16x4_t __ret;	34712	poly16x4_t __ret;
38474	__ret = (poly16x4_t)(__p0);	34713	__ret = (poly16x4_t)(__p0);
38475	return __ret;	34714	return __ret;
38476	}	34715	}
38477	#endif
38478
38479	#ifdef __LITTLE_ENDIAN__
38480	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {
38481	poly16x4_t __ret;
38482	__ret = (poly16x4_t)(__p0);
38483	return __ret;
38484	}
38485	#else
38486	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {	34716	__ai poly16x4_t vreinterpret_p16_u16(uint16x4_t __p0) {
38487	poly16x4_t __ret;	34717	poly16x4_t __ret;
38488	__ret = (poly16x4_t)(__p0);	34718	__ret = (poly16x4_t)(__p0);
38489	return __ret;	34719	return __ret;
38490	}	34720	}
38491	#endif
38492
38493	#ifdef __LITTLE_ENDIAN__
38494	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
38495	poly16x4_t __ret;
38496	__ret = (poly16x4_t)(__p0);
38497	return __ret;
38498	}
38499	#else
38500	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {	34721	__ai poly16x4_t vreinterpret_p16_s8(int8x8_t __p0) {
38501	poly16x4_t __ret;	34722	poly16x4_t __ret;
38502	__ret = (poly16x4_t)(__p0);	34723	__ret = (poly16x4_t)(__p0);
38503	return __ret;	34724	return __ret;
38504	}	34725	}
38505	#endif
38506
38507	#ifdef __LITTLE_ENDIAN__
38508	__ai poly16x4_t vreinterpret_p16_f64(float64x1_t __p0) {
38509	poly16x4_t __ret;
38510	__ret = (poly16x4_t)(__p0);
38511	return __ret;
38512	}
38513	#else
38514	__ai poly16x4_t vreinterpret_p16_f64(float64x1_t __p0) {	34726	__ai poly16x4_t vreinterpret_p16_f64(float64x1_t __p0) {
38515	poly16x4_t __ret;	34727	poly16x4_t __ret;
38516	__ret = (poly16x4_t)(__p0);	34728	__ret = (poly16x4_t)(__p0);
38517	return __ret;	34729	return __ret;
38518	}	34730	}
38519	#endif
38520
38521	#ifdef __LITTLE_ENDIAN__
38522	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {
38523	poly16x4_t __ret;
38524	__ret = (poly16x4_t)(__p0);
38525	return __ret;
38526	}
38527	#else
38528	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {	34731	__ai poly16x4_t vreinterpret_p16_f32(float32x2_t __p0) {
38529	poly16x4_t __ret;	34732	poly16x4_t __ret;
38530	__ret = (poly16x4_t)(__p0);	34733	__ret = (poly16x4_t)(__p0);
38531	return __ret;	34734	return __ret;
38532	}	34735	}
38533	#endif
38534
38535	#ifdef __LITTLE_ENDIAN__
38536	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {
38537	poly16x4_t __ret;
38538	__ret = (poly16x4_t)(__p0);
38539	return __ret;
38540	}
38541	#else
38542	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {	34736	__ai poly16x4_t vreinterpret_p16_f16(float16x4_t __p0) {
38543	poly16x4_t __ret;	34737	poly16x4_t __ret;
38544	__ret = (poly16x4_t)(__p0);	34738	__ret = (poly16x4_t)(__p0);
38545	return __ret;	34739	return __ret;
38546	}	34740	}
38547	#endif
38548
38549	#ifdef __LITTLE_ENDIAN__
38550	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {
38551	poly16x4_t __ret;
38552	__ret = (poly16x4_t)(__p0);
38553	return __ret;
38554	}
38555	#else
38556	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {	34741	__ai poly16x4_t vreinterpret_p16_s32(int32x2_t __p0) {
38557	poly16x4_t __ret;	34742	poly16x4_t __ret;
38558	__ret = (poly16x4_t)(__p0);	34743	__ret = (poly16x4_t)(__p0);
38559	return __ret;	34744	return __ret;
38560	}	34745	}
38561	#endif
38562
38563	#ifdef __LITTLE_ENDIAN__
38564	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {
38565	poly16x4_t __ret;
38566	__ret = (poly16x4_t)(__p0);
38567	return __ret;
38568	}
38569	#else
38570	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {	34746	__ai poly16x4_t vreinterpret_p16_s64(int64x1_t __p0) {
38571	poly16x4_t __ret;	34747	poly16x4_t __ret;
38572	__ret = (poly16x4_t)(__p0);	34748	__ret = (poly16x4_t)(__p0);
38573	return __ret;	34749	return __ret;
38574	}	34750	}
38575	#endif
38576
38577	#ifdef __LITTLE_ENDIAN__
38578	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {
38579	poly16x4_t __ret;
38580	__ret = (poly16x4_t)(__p0);
38581	return __ret;
38582	}
38583	#else
38584	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {	34751	__ai poly16x4_t vreinterpret_p16_s16(int16x4_t __p0) {
38585	poly16x4_t __ret;	34752	poly16x4_t __ret;
38586	__ret = (poly16x4_t)(__p0);	34753	__ret = (poly16x4_t)(__p0);
38587	return __ret;	34754	return __ret;
38588	}	34755	}
38589	#endif
38590
38591	#ifdef __LITTLE_ENDIAN__
38592	__ai poly8x16_t vreinterpretq_p8_p128(poly128_t __p0) {
38593	poly8x16_t __ret;
38594	__ret = (poly8x16_t)(__p0);
38595	return __ret;
38596	}
38597	#else
38598	__ai poly8x16_t vreinterpretq_p8_p128(poly128_t __p0) {	34756	__ai poly8x16_t vreinterpretq_p8_p128(poly128_t __p0) {
38599	poly8x16_t __ret;	34757	poly8x16_t __ret;
38600	__ret = (poly8x16_t)(__p0);	34758	__ret = (poly8x16_t)(__p0);
38601	return __ret;	34759	return __ret;
38602	}	34760	}
38603	#endif
38604
38605	#ifdef __LITTLE_ENDIAN__
38606	__ai poly8x16_t vreinterpretq_p8_p64(poly64x2_t __p0) {
38607	poly8x16_t __ret;
38608	__ret = (poly8x16_t)(__p0);
38609	return __ret;
38610	}
38611	#else
38612	__ai poly8x16_t vreinterpretq_p8_p64(poly64x2_t __p0) {	34761	__ai poly8x16_t vreinterpretq_p8_p64(poly64x2_t __p0) {
38613	poly8x16_t __ret;	34762	poly8x16_t __ret;
38614	__ret = (poly8x16_t)(__p0);	34763	__ret = (poly8x16_t)(__p0);
38615	return __ret;	34764	return __ret;
38616	}	34765	}
38617	#endif
38618
38619	#ifdef __LITTLE_ENDIAN__
38620	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {	34766	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {
38621	poly8x16_t __ret;	34767	poly8x16_t __ret;
38622	__ret = (poly8x16_t)(__p0);	34768	__ret = (poly8x16_t)(__p0);
38623	return __ret;	34769	return __ret;
38624	}	34770	}
38625	#else	34771	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {
38626	__ai poly8x16_t vreinterpretq_p8_p16(poly16x8_t __p0) {
38627	poly8x16_t __ret;	34772	poly8x16_t __ret;
38628	__ret = (poly8x16_t)(__p0);	34773	__ret = (poly8x16_t)(__p0);
38629	return __ret;	34774	return __ret;
38630	}	34775	}
38631	#endif	34776	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {
38632
38633	#ifdef __LITTLE_ENDIAN__
38634	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {
38635	poly8x16_t __ret;	34777	poly8x16_t __ret;
38636	__ret = (poly8x16_t)(__p0);	34778	__ret = (poly8x16_t)(__p0);
38637	return __ret;	34779	return __ret;
38638	}	34780	}
38639	#else	34781	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {
38640	__ai poly8x16_t vreinterpretq_p8_u8(uint8x16_t __p0) {
38641	poly8x16_t __ret;	34782	poly8x16_t __ret;
38642	__ret = (poly8x16_t)(__p0);	34783	__ret = (poly8x16_t)(__p0);
38643	return __ret;	34784	return __ret;
38644	}	34785	}
38645	#endif	34786	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {
38646
38647	#ifdef __LITTLE_ENDIAN__
38648	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {
38649	poly8x16_t __ret;	34787	poly8x16_t __ret;
38650	__ret = (poly8x16_t)(__p0);	34788	__ret = (poly8x16_t)(__p0);
38651	return __ret;	34789	return __ret;
38652	}	34790	}
38653	#else	34791	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {
38654	__ai poly8x16_t vreinterpretq_p8_u32(uint32x4_t __p0) {
38655	poly8x16_t __ret;	34792	poly8x16_t __ret;
38656	__ret = (poly8x16_t)(__p0);	34793	__ret = (poly8x16_t)(__p0);
38657	return __ret;	34794	return __ret;
38658	}	34795	}
38659	#endif	34796	__ai poly8x16_t vreinterpretq_p8_f64(float64x2_t __p0) {
38660
38661	#ifdef __LITTLE_ENDIAN__
38662	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {
38663	poly8x16_t __ret;	34797	poly8x16_t __ret;
38664	__ret = (poly8x16_t)(__p0);	34798	__ret = (poly8x16_t)(__p0);
38665	return __ret;	34799	return __ret;
38666	}	34800	}
38667	#else	34801	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {
38668	__ai poly8x16_t vreinterpretq_p8_u64(uint64x2_t __p0) {
38669	poly8x16_t __ret;	34802	poly8x16_t __ret;
38670	__ret = (poly8x16_t)(__p0);	34803	__ret = (poly8x16_t)(__p0);
38671	return __ret;	34804	return __ret;
38672	}	34805	}
38673	#endif	34806	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {
38674
38675	#ifdef __LITTLE_ENDIAN__
38676	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {
38677	poly8x16_t __ret;	34807	poly8x16_t __ret;
38678	__ret = (poly8x16_t)(__p0);	34808	__ret = (poly8x16_t)(__p0);
38679	return __ret;	34809	return __ret;
38680	}	34810	}
38681	#else	34811	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {
38682	__ai poly8x16_t vreinterpretq_p8_u16(uint16x8_t __p0) {
38683	poly8x16_t __ret;	34812	poly8x16_t __ret;
38684	__ret = (poly8x16_t)(__p0);	34813	__ret = (poly8x16_t)(__p0);
38685	return __ret;	34814	return __ret;
38686	}	34815	}
38687	#endif	34816	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {
38688
38689	#ifdef __LITTLE_ENDIAN__
38690	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {
38691	poly8x16_t __ret;	34817	poly8x16_t __ret;
38692	__ret = (poly8x16_t)(__p0);	34818	__ret = (poly8x16_t)(__p0);
38693	return __ret;	34819	return __ret;
38694	}	34820	}
38695	#else	34821	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {
38696	__ai poly8x16_t vreinterpretq_p8_s8(int8x16_t __p0) {
38697	poly8x16_t __ret;	34822	poly8x16_t __ret;
38698	__ret = (poly8x16_t)(__p0);	34823	__ret = (poly8x16_t)(__p0);
38699	return __ret;	34824	return __ret;
38700	}	34825	}
38701	#endif	34826	__ai poly128_t vreinterpretq_p128_p8(poly8x16_t __p0) {
38702		34827	poly128_t __ret;
38703	#ifdef __LITTLE_ENDIAN__	34828	__ret = (poly128_t)(__p0);
38704	__ai poly8x16_t vreinterpretq_p8_f64(float64x2_t __p0) {
38705	poly8x16_t __ret;
38706	__ret = (poly8x16_t)(__p0);
38707	return __ret;	34829	return __ret;
38708	}	34830	}
38709	#else
38710	__ai poly8x16_t vreinterpretq_p8_f64(float64x2_t __p0) {
38711	poly8x16_t __ret;
38712	__ret = (poly8x16_t)(__p0);
38713	return __ret;
38714	}
38715	#endif
38716
38717	#ifdef __LITTLE_ENDIAN__
38718	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {
38719	poly8x16_t __ret;
38720	__ret = (poly8x16_t)(__p0);
38721	return __ret;
38722	}
38723	#else
38724	__ai poly8x16_t vreinterpretq_p8_f32(float32x4_t __p0) {
38725	poly8x16_t __ret;
38726	__ret = (poly8x16_t)(__p0);
38727	return __ret;
38728	}
38729	#endif
38730
38731	#ifdef __LITTLE_ENDIAN__
38732	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {
38733	poly8x16_t __ret;
38734	__ret = (poly8x16_t)(__p0);
38735	return __ret;
38736	}
38737	#else
38738	__ai poly8x16_t vreinterpretq_p8_f16(float16x8_t __p0) {
38739	poly8x16_t __ret;
38740	__ret = (poly8x16_t)(__p0);
38741	return __ret;
38742	}
38743	#endif
38744
38745	#ifdef __LITTLE_ENDIAN__
38746	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {
38747	poly8x16_t __ret;
38748	__ret = (poly8x16_t)(__p0);
38749	return __ret;
38750	}
38751	#else
38752	__ai poly8x16_t vreinterpretq_p8_s32(int32x4_t __p0) {
38753	poly8x16_t __ret;
38754	__ret = (poly8x16_t)(__p0);
38755	return __ret;
38756	}
38757	#endif
38758
38759	#ifdef __LITTLE_ENDIAN__
38760	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {
38761	poly8x16_t __ret;
38762	__ret = (poly8x16_t)(__p0);
38763	return __ret;
38764	}
38765	#else
38766	__ai poly8x16_t vreinterpretq_p8_s64(int64x2_t __p0) {
38767	poly8x16_t __ret;
38768	__ret = (poly8x16_t)(__p0);
38769	return __ret;
38770	}
38771	#endif
38772
38773	#ifdef __LITTLE_ENDIAN__
38774	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {
38775	poly8x16_t __ret;
38776	__ret = (poly8x16_t)(__p0);
38777	return __ret;
38778	}
38779	#else
38780	__ai poly8x16_t vreinterpretq_p8_s16(int16x8_t __p0) {
38781	poly8x16_t __ret;
38782	__ret = (poly8x16_t)(__p0);
38783	return __ret;
38784	}
38785	#endif
38786
38787	#ifdef __LITTLE_ENDIAN__
38788	__ai poly128_t vreinterpretq_p128_p8(poly8x16_t __p0) {
38789	poly128_t __ret;
38790	__ret = (poly128_t)(__p0);
38791	return __ret;
38792	}
38793	#else
38794	__ai poly128_t vreinterpretq_p128_p8(poly8x16_t __p0) {
38795	poly128_t __ret;
38796	__ret = (poly128_t)(__p0);
38797	return __ret;
38798	}
38799	#endif
38800
38801	#ifdef __LITTLE_ENDIAN__
38802	__ai poly128_t vreinterpretq_p128_p64(poly64x2_t __p0) {
38803	poly128_t __ret;
38804	__ret = (poly128_t)(__p0);
38805	return __ret;
38806	}
38807	#else
38808	__ai poly128_t vreinterpretq_p128_p64(poly64x2_t __p0) {	34831	__ai poly128_t vreinterpretq_p128_p64(poly64x2_t __p0) {
38809	poly128_t __ret;	34832	poly128_t __ret;
38810	__ret = (poly128_t)(__p0);	34833	__ret = (poly128_t)(__p0);
38811	return __ret;	34834	return __ret;
38812	}	34835	}
38813	#endif
38814
38815	#ifdef __LITTLE_ENDIAN__
38816	__ai poly128_t vreinterpretq_p128_p16(poly16x8_t __p0) {
38817	poly128_t __ret;
38818	__ret = (poly128_t)(__p0);
38819	return __ret;
38820	}
38821	#else
38822	__ai poly128_t vreinterpretq_p128_p16(poly16x8_t __p0) {	34836	__ai poly128_t vreinterpretq_p128_p16(poly16x8_t __p0) {
38823	poly128_t __ret;	34837	poly128_t __ret;
38824	__ret = (poly128_t)(__p0);	34838	__ret = (poly128_t)(__p0);
38825	return __ret;	34839	return __ret;
38826	}	34840	}
38827	#endif
38828
38829	#ifdef __LITTLE_ENDIAN__
38830	__ai poly128_t vreinterpretq_p128_u8(uint8x16_t __p0) {
38831	poly128_t __ret;
38832	__ret = (poly128_t)(__p0);
38833	return __ret;
38834	}
38835	#else
38836	__ai poly128_t vreinterpretq_p128_u8(uint8x16_t __p0) {	34841	__ai poly128_t vreinterpretq_p128_u8(uint8x16_t __p0) {
38837	poly128_t __ret;	34842	poly128_t __ret;
38838	__ret = (poly128_t)(__p0);	34843	__ret = (poly128_t)(__p0);
38839	return __ret;	34844	return __ret;
38840	}	34845	}
38841	#endif
38842
38843	#ifdef __LITTLE_ENDIAN__
38844	__ai poly128_t vreinterpretq_p128_u32(uint32x4_t __p0) {
38845	poly128_t __ret;
38846	__ret = (poly128_t)(__p0);
38847	return __ret;
38848	}
38849	#else
38850	__ai poly128_t vreinterpretq_p128_u32(uint32x4_t __p0) {	34846	__ai poly128_t vreinterpretq_p128_u32(uint32x4_t __p0) {
38851	poly128_t __ret;	34847	poly128_t __ret;
38852	__ret = (poly128_t)(__p0);	34848	__ret = (poly128_t)(__p0);
38853	return __ret;	34849	return __ret;
38854	}	34850	}
38855	#endif
38856
38857	#ifdef __LITTLE_ENDIAN__
38858	__ai poly128_t vreinterpretq_p128_u64(uint64x2_t __p0) {
38859	poly128_t __ret;
38860	__ret = (poly128_t)(__p0);
38861	return __ret;
38862	}
38863	#else
38864	__ai poly128_t vreinterpretq_p128_u64(uint64x2_t __p0) {	34851	__ai poly128_t vreinterpretq_p128_u64(uint64x2_t __p0) {
38865	poly128_t __ret;	34852	poly128_t __ret;
38866	__ret = (poly128_t)(__p0);	34853	__ret = (poly128_t)(__p0);
38867	return __ret;	34854	return __ret;
38868	}	34855	}
38869	#endif
38870
38871	#ifdef __LITTLE_ENDIAN__
38872	__ai poly128_t vreinterpretq_p128_u16(uint16x8_t __p0) {
38873	poly128_t __ret;
38874	__ret = (poly128_t)(__p0);
38875	return __ret;
38876	}
38877	#else
38878	__ai poly128_t vreinterpretq_p128_u16(uint16x8_t __p0) {	34856	__ai poly128_t vreinterpretq_p128_u16(uint16x8_t __p0) {
38879	poly128_t __ret;	34857	poly128_t __ret;
38880	__ret = (poly128_t)(__p0);	34858	__ret = (poly128_t)(__p0);
38881	return __ret;	34859	return __ret;
38882	}	34860	}
38883	#endif
38884
38885	#ifdef __LITTLE_ENDIAN__
38886	__ai poly128_t vreinterpretq_p128_s8(int8x16_t __p0) {
38887	poly128_t __ret;
38888	__ret = (poly128_t)(__p0);
38889	return __ret;
38890	}
38891	#else
38892	__ai poly128_t vreinterpretq_p128_s8(int8x16_t __p0) {	34861	__ai poly128_t vreinterpretq_p128_s8(int8x16_t __p0) {
38893	poly128_t __ret;	34862	poly128_t __ret;
38894	__ret = (poly128_t)(__p0);	34863	__ret = (poly128_t)(__p0);
38895	return __ret;	34864	return __ret;
38896	}	34865	}
38897	#endif
38898
38899	#ifdef __LITTLE_ENDIAN__
38900	__ai poly128_t vreinterpretq_p128_f64(float64x2_t __p0) {
38901	poly128_t __ret;
38902	__ret = (poly128_t)(__p0);
38903	return __ret;
38904	}
38905	#else
38906	__ai poly128_t vreinterpretq_p128_f64(float64x2_t __p0) {	34866	__ai poly128_t vreinterpretq_p128_f64(float64x2_t __p0) {
38907	poly128_t __ret;	34867	poly128_t __ret;
38908	__ret = (poly128_t)(__p0);	34868	__ret = (poly128_t)(__p0);
38909	return __ret;	34869	return __ret;
38910	}	34870	}
38911	#endif
38912
38913	#ifdef __LITTLE_ENDIAN__
38914	__ai poly128_t vreinterpretq_p128_f32(float32x4_t __p0) {
38915	poly128_t __ret;
38916	__ret = (poly128_t)(__p0);
38917	return __ret;
38918	}
38919	#else
38920	__ai poly128_t vreinterpretq_p128_f32(float32x4_t __p0) {	34871	__ai poly128_t vreinterpretq_p128_f32(float32x4_t __p0) {
38921	poly128_t __ret;	34872	poly128_t __ret;
38922	__ret = (poly128_t)(__p0);	34873	__ret = (poly128_t)(__p0);
38923	return __ret;	34874	return __ret;
38924	}	34875	}
38925	#endif
38926
38927	#ifdef __LITTLE_ENDIAN__
38928	__ai poly128_t vreinterpretq_p128_f16(float16x8_t __p0) {
38929	poly128_t __ret;
38930	__ret = (poly128_t)(__p0);
38931	return __ret;
38932	}
38933	#else
38934	__ai poly128_t vreinterpretq_p128_f16(float16x8_t __p0) {	34876	__ai poly128_t vreinterpretq_p128_f16(float16x8_t __p0) {
38935	poly128_t __ret;	34877	poly128_t __ret;
38936	__ret = (poly128_t)(__p0);	34878	__ret = (poly128_t)(__p0);
38937	return __ret;	34879	return __ret;
38938	}	34880	}
38939	#endif
38940
38941	#ifdef __LITTLE_ENDIAN__
38942	__ai poly128_t vreinterpretq_p128_s32(int32x4_t __p0) {
38943	poly128_t __ret;
38944	__ret = (poly128_t)(__p0);
38945	return __ret;
38946	}
38947	#else
38948	__ai poly128_t vreinterpretq_p128_s32(int32x4_t __p0) {	34881	__ai poly128_t vreinterpretq_p128_s32(int32x4_t __p0) {
38949	poly128_t __ret;	34882	poly128_t __ret;
38950	__ret = (poly128_t)(__p0);	34883	__ret = (poly128_t)(__p0);
38951	return __ret;	34884	return __ret;
38952	}	34885	}
38953	#endif
38954
38955	#ifdef __LITTLE_ENDIAN__
38956	__ai poly128_t vreinterpretq_p128_s64(int64x2_t __p0) {
38957	poly128_t __ret;
38958	__ret = (poly128_t)(__p0);
38959	return __ret;
38960	}
38961	#else
38962	__ai poly128_t vreinterpretq_p128_s64(int64x2_t __p0) {	34886	__ai poly128_t vreinterpretq_p128_s64(int64x2_t __p0) {
38963	poly128_t __ret;	34887	poly128_t __ret;
38964	__ret = (poly128_t)(__p0);	34888	__ret = (poly128_t)(__p0);
38965	return __ret;	34889	return __ret;
38966	}	34890	}
38967	#endif
38968
38969	#ifdef __LITTLE_ENDIAN__
38970	__ai poly128_t vreinterpretq_p128_s16(int16x8_t __p0) {
38971	poly128_t __ret;
38972	__ret = (poly128_t)(__p0);
38973	return __ret;
38974	}
38975	#else
38976	__ai poly128_t vreinterpretq_p128_s16(int16x8_t __p0) {	34891	__ai poly128_t vreinterpretq_p128_s16(int16x8_t __p0) {
38977	poly128_t __ret;	34892	poly128_t __ret;
38978	__ret = (poly128_t)(__p0);	34893	__ret = (poly128_t)(__p0);
38979	return __ret;	34894	return __ret;
38980	}	34895	}
38981	#endif
38982
38983	#ifdef __LITTLE_ENDIAN__
38984	__ai poly64x2_t vreinterpretq_p64_p8(poly8x16_t __p0) {
38985	poly64x2_t __ret;
38986	__ret = (poly64x2_t)(__p0);
38987	return __ret;
38988	}
38989	#else
38990	__ai poly64x2_t vreinterpretq_p64_p8(poly8x16_t __p0) {	34896	__ai poly64x2_t vreinterpretq_p64_p8(poly8x16_t __p0) {
38991	poly64x2_t __ret;	34897	poly64x2_t __ret;
38992	__ret = (poly64x2_t)(__p0);	34898	__ret = (poly64x2_t)(__p0);
38993	return __ret;	34899	return __ret;
38994	}	34900	}
38995	#endif
38996
38997	#ifdef __LITTLE_ENDIAN__
38998	__ai poly64x2_t vreinterpretq_p64_p128(poly128_t __p0) {
38999	poly64x2_t __ret;
39000	__ret = (poly64x2_t)(__p0);
39001	return __ret;
39002	}
39003	#else
39004	__ai poly64x2_t vreinterpretq_p64_p128(poly128_t __p0) {	34901	__ai poly64x2_t vreinterpretq_p64_p128(poly128_t __p0) {
39005	poly64x2_t __ret;	34902	poly64x2_t __ret;
39006	__ret = (poly64x2_t)(__p0);	34903	__ret = (poly64x2_t)(__p0);
39007	return __ret;	34904	return __ret;
39008	}	34905	}
39009	#endif
39010
39011	#ifdef __LITTLE_ENDIAN__
39012	__ai poly64x2_t vreinterpretq_p64_p16(poly16x8_t __p0) {
39013	poly64x2_t __ret;
39014	__ret = (poly64x2_t)(__p0);
39015	return __ret;
39016	}
39017	#else
39018	__ai poly64x2_t vreinterpretq_p64_p16(poly16x8_t __p0) {	34906	__ai poly64x2_t vreinterpretq_p64_p16(poly16x8_t __p0) {
39019	poly64x2_t __ret;	34907	poly64x2_t __ret;
39020	__ret = (poly64x2_t)(__p0);	34908	__ret = (poly64x2_t)(__p0);
39021	return __ret;	34909	return __ret;
39022	}	34910	}
39023	#endif
39024
39025	#ifdef __LITTLE_ENDIAN__
39026	__ai poly64x2_t vreinterpretq_p64_u8(uint8x16_t __p0) {
39027	poly64x2_t __ret;
39028	__ret = (poly64x2_t)(__p0);
39029	return __ret;
39030	}
39031	#else
39032	__ai poly64x2_t vreinterpretq_p64_u8(uint8x16_t __p0) {	34911	__ai poly64x2_t vreinterpretq_p64_u8(uint8x16_t __p0) {
39033	poly64x2_t __ret;	34912	poly64x2_t __ret;
39034	__ret = (poly64x2_t)(__p0);	34913	__ret = (poly64x2_t)(__p0);
39035	return __ret;	34914	return __ret;
39036	}	34915	}
39037	#endif
39038
39039	#ifdef __LITTLE_ENDIAN__
39040	__ai poly64x2_t vreinterpretq_p64_u32(uint32x4_t __p0) {
39041	poly64x2_t __ret;
39042	__ret = (poly64x2_t)(__p0);
39043	return __ret;
39044	}
39045	#else
39046	__ai poly64x2_t vreinterpretq_p64_u32(uint32x4_t __p0) {	34916	__ai poly64x2_t vreinterpretq_p64_u32(uint32x4_t __p0) {
39047	poly64x2_t __ret;	34917	poly64x2_t __ret;
39048	__ret = (poly64x2_t)(__p0);	34918	__ret = (poly64x2_t)(__p0);
39049	return __ret;	34919	return __ret;
39050	}	34920	}
39051	#endif
39052
39053	#ifdef __LITTLE_ENDIAN__
39054	__ai poly64x2_t vreinterpretq_p64_u64(uint64x2_t __p0) {
39055	poly64x2_t __ret;
39056	__ret = (poly64x2_t)(__p0);
39057	return __ret;
39058	}
39059	#else
39060	__ai poly64x2_t vreinterpretq_p64_u64(uint64x2_t __p0) {	34921	__ai poly64x2_t vreinterpretq_p64_u64(uint64x2_t __p0) {
39061	poly64x2_t __ret;	34922	poly64x2_t __ret;
39062	__ret = (poly64x2_t)(__p0);	34923	__ret = (poly64x2_t)(__p0);
39063	return __ret;	34924	return __ret;
39064	}	34925	}
39065	#endif
39066
39067	#ifdef __LITTLE_ENDIAN__
39068	__ai poly64x2_t vreinterpretq_p64_u16(uint16x8_t __p0) {
39069	poly64x2_t __ret;
39070	__ret = (poly64x2_t)(__p0);
39071	return __ret;
39072	}
39073	#else
39074	__ai poly64x2_t vreinterpretq_p64_u16(uint16x8_t __p0) {	34926	__ai poly64x2_t vreinterpretq_p64_u16(uint16x8_t __p0) {
39075	poly64x2_t __ret;	34927	poly64x2_t __ret;
39076	__ret = (poly64x2_t)(__p0);	34928	__ret = (poly64x2_t)(__p0);
39077	return __ret;	34929	return __ret;
39078	}	34930	}
39079	#endif
39080
39081	#ifdef __LITTLE_ENDIAN__
39082	__ai poly64x2_t vreinterpretq_p64_s8(int8x16_t __p0) {
39083	poly64x2_t __ret;
39084	__ret = (poly64x2_t)(__p0);
39085	return __ret;
39086	}
39087	#else
39088	__ai poly64x2_t vreinterpretq_p64_s8(int8x16_t __p0) {	34931	__ai poly64x2_t vreinterpretq_p64_s8(int8x16_t __p0) {
39089	poly64x2_t __ret;	34932	poly64x2_t __ret;
39090	__ret = (poly64x2_t)(__p0);	34933	__ret = (poly64x2_t)(__p0);
39091	return __ret;	34934	return __ret;
39092	}	34935	}
39093	#endif
39094
39095	#ifdef __LITTLE_ENDIAN__
39096	__ai poly64x2_t vreinterpretq_p64_f64(float64x2_t __p0) {
39097	poly64x2_t __ret;
39098	__ret = (poly64x2_t)(__p0);
39099	return __ret;
39100	}
39101	#else
39102	__ai poly64x2_t vreinterpretq_p64_f64(float64x2_t __p0) {	34936	__ai poly64x2_t vreinterpretq_p64_f64(float64x2_t __p0) {
39103	poly64x2_t __ret;	34937	poly64x2_t __ret;
39104	__ret = (poly64x2_t)(__p0);	34938	__ret = (poly64x2_t)(__p0);
39105	return __ret;	34939	return __ret;
39106	}	34940	}
39107	#endif
39108
39109	#ifdef __LITTLE_ENDIAN__
39110	__ai poly64x2_t vreinterpretq_p64_f32(float32x4_t __p0) {
39111	poly64x2_t __ret;
39112	__ret = (poly64x2_t)(__p0);
39113	return __ret;
39114	}
39115	#else
39116	__ai poly64x2_t vreinterpretq_p64_f32(float32x4_t __p0) {	34941	__ai poly64x2_t vreinterpretq_p64_f32(float32x4_t __p0) {
39117	poly64x2_t __ret;	34942	poly64x2_t __ret;
39118	__ret = (poly64x2_t)(__p0);	34943	__ret = (poly64x2_t)(__p0);
39119	return __ret;	34944	return __ret;
39120	}	34945	}
39121	#endif
39122
39123	#ifdef __LITTLE_ENDIAN__
39124	__ai poly64x2_t vreinterpretq_p64_f16(float16x8_t __p0) {
39125	poly64x2_t __ret;
39126	__ret = (poly64x2_t)(__p0);
39127	return __ret;
39128	}
39129	#else
39130	__ai poly64x2_t vreinterpretq_p64_f16(float16x8_t __p0) {	34946	__ai poly64x2_t vreinterpretq_p64_f16(float16x8_t __p0) {
39131	poly64x2_t __ret;	34947	poly64x2_t __ret;
39132	__ret = (poly64x2_t)(__p0);	34948	__ret = (poly64x2_t)(__p0);
39133	return __ret;	34949	return __ret;
39134	}	34950	}
39135	#endif
39136
39137	#ifdef __LITTLE_ENDIAN__
39138	__ai poly64x2_t vreinterpretq_p64_s32(int32x4_t __p0) {
39139	poly64x2_t __ret;
39140	__ret = (poly64x2_t)(__p0);
39141	return __ret;
39142	}
39143	#else
39144	__ai poly64x2_t vreinterpretq_p64_s32(int32x4_t __p0) {	34951	__ai poly64x2_t vreinterpretq_p64_s32(int32x4_t __p0) {
39145	poly64x2_t __ret;	34952	poly64x2_t __ret;
39146	__ret = (poly64x2_t)(__p0);	34953	__ret = (poly64x2_t)(__p0);
39147	return __ret;	34954	return __ret;
39148	}	34955	}
39149	#endif
39150
39151	#ifdef __LITTLE_ENDIAN__
39152	__ai poly64x2_t vreinterpretq_p64_s64(int64x2_t __p0) {
39153	poly64x2_t __ret;
39154	__ret = (poly64x2_t)(__p0);
39155	return __ret;
39156	}
39157	#else
39158	__ai poly64x2_t vreinterpretq_p64_s64(int64x2_t __p0) {	34956	__ai poly64x2_t vreinterpretq_p64_s64(int64x2_t __p0) {
39159	poly64x2_t __ret;	34957	poly64x2_t __ret;
39160	__ret = (poly64x2_t)(__p0);	34958	__ret = (poly64x2_t)(__p0);
39161	return __ret;	34959	return __ret;
39162	}	34960	}
39163	#endif
39164
39165	#ifdef __LITTLE_ENDIAN__
39166	__ai poly64x2_t vreinterpretq_p64_s16(int16x8_t __p0) {
39167	poly64x2_t __ret;
39168	__ret = (poly64x2_t)(__p0);
39169	return __ret;
39170	}
39171	#else
39172	__ai poly64x2_t vreinterpretq_p64_s16(int16x8_t __p0) {	34961	__ai poly64x2_t vreinterpretq_p64_s16(int16x8_t __p0) {
39173	poly64x2_t __ret;	34962	poly64x2_t __ret;
39174	__ret = (poly64x2_t)(__p0);	34963	__ret = (poly64x2_t)(__p0);
39175	return __ret;	34964	return __ret;
39176	}	34965	}
39177	#endif
39178
39179	#ifdef __LITTLE_ENDIAN__
39180	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {
39181	poly16x8_t __ret;
39182	__ret = (poly16x8_t)(__p0);
39183	return __ret;
39184	}
39185	#else
39186	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {	34966	__ai poly16x8_t vreinterpretq_p16_p8(poly8x16_t __p0) {
39187	poly16x8_t __ret;	34967	poly16x8_t __ret;
39188	__ret = (poly16x8_t)(__p0);	34968	__ret = (poly16x8_t)(__p0);
39189	return __ret;	34969	return __ret;
39190	}	34970	}
39191	#endif
39192
39193	#ifdef __LITTLE_ENDIAN__
39194	__ai poly16x8_t vreinterpretq_p16_p128(poly128_t __p0) {
39195	poly16x8_t __ret;
39196	__ret = (poly16x8_t)(__p0);
39197	return __ret;
39198	}
39199	#else
39200	__ai poly16x8_t vreinterpretq_p16_p128(poly128_t __p0) {	34971	__ai poly16x8_t vreinterpretq_p16_p128(poly128_t __p0) {
39201	poly16x8_t __ret;	34972	poly16x8_t __ret;
39202	__ret = (poly16x8_t)(__p0);	34973	__ret = (poly16x8_t)(__p0);
39203	return __ret;	34974	return __ret;
39204	}	34975	}
39205	#endif
39206
39207	#ifdef __LITTLE_ENDIAN__
39208	__ai poly16x8_t vreinterpretq_p16_p64(poly64x2_t __p0) {
39209	poly16x8_t __ret;
39210	__ret = (poly16x8_t)(__p0);
39211	return __ret;
39212	}
39213	#else
39214	__ai poly16x8_t vreinterpretq_p16_p64(poly64x2_t __p0) {	34976	__ai poly16x8_t vreinterpretq_p16_p64(poly64x2_t __p0) {
39215	poly16x8_t __ret;	34977	poly16x8_t __ret;
39216	__ret = (poly16x8_t)(__p0);	34978	__ret = (poly16x8_t)(__p0);
39217	return __ret;	34979	return __ret;
39218	}	34980	}
39219	#endif
39220
39221	#ifdef __LITTLE_ENDIAN__
39222	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {
39223	poly16x8_t __ret;
39224	__ret = (poly16x8_t)(__p0);
39225	return __ret;
39226	}
39227	#else
39228	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {	34981	__ai poly16x8_t vreinterpretq_p16_u8(uint8x16_t __p0) {
39229	poly16x8_t __ret;	34982	poly16x8_t __ret;
39230	__ret = (poly16x8_t)(__p0);	34983	__ret = (poly16x8_t)(__p0);
39231	return __ret;	34984	return __ret;
39232	}	34985	}
39233	#endif
39234
39235	#ifdef __LITTLE_ENDIAN__
39236	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {
39237	poly16x8_t __ret;
39238	__ret = (poly16x8_t)(__p0);
39239	return __ret;
39240	}
39241	#else
39242	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {	34986	__ai poly16x8_t vreinterpretq_p16_u32(uint32x4_t __p0) {
39243	poly16x8_t __ret;	34987	poly16x8_t __ret;
39244	__ret = (poly16x8_t)(__p0);	34988	__ret = (poly16x8_t)(__p0);
39245	return __ret;	34989	return __ret;
39246	}	34990	}
39247	#endif
39248
39249	#ifdef __LITTLE_ENDIAN__
39250	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {
39251	poly16x8_t __ret;
39252	__ret = (poly16x8_t)(__p0);
39253	return __ret;
39254	}
39255	#else
39256	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {	34991	__ai poly16x8_t vreinterpretq_p16_u64(uint64x2_t __p0) {
39257	poly16x8_t __ret;	34992	poly16x8_t __ret;
39258	__ret = (poly16x8_t)(__p0);	34993	__ret = (poly16x8_t)(__p0);
39259	return __ret;	34994	return __ret;
39260	}	34995	}
39261	#endif
39262
39263	#ifdef __LITTLE_ENDIAN__
39264	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {
39265	poly16x8_t __ret;
39266	__ret = (poly16x8_t)(__p0);
39267	return __ret;
39268	}
39269	#else
39270	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {	34996	__ai poly16x8_t vreinterpretq_p16_u16(uint16x8_t __p0) {
39271	poly16x8_t __ret;	34997	poly16x8_t __ret;
39272	__ret = (poly16x8_t)(__p0);	34998	__ret = (poly16x8_t)(__p0);
39273	return __ret;	34999	return __ret;
39274	}	35000	}
39275	#endif
39276
39277	#ifdef __LITTLE_ENDIAN__
39278	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {
39279	poly16x8_t __ret;
39280	__ret = (poly16x8_t)(__p0);
39281	return __ret;
39282	}
39283	#else
39284	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {	35001	__ai poly16x8_t vreinterpretq_p16_s8(int8x16_t __p0) {
39285	poly16x8_t __ret;	35002	poly16x8_t __ret;
39286	__ret = (poly16x8_t)(__p0);	35003	__ret = (poly16x8_t)(__p0);
39287	return __ret;	35004	return __ret;
39288	}	35005	}
39289	#endif
39290
39291	#ifdef __LITTLE_ENDIAN__
39292	__ai poly16x8_t vreinterpretq_p16_f64(float64x2_t __p0) {
39293	poly16x8_t __ret;
39294	__ret = (poly16x8_t)(__p0);
39295	return __ret;
39296	}
39297	#else
39298	__ai poly16x8_t vreinterpretq_p16_f64(float64x2_t __p0) {	35006	__ai poly16x8_t vreinterpretq_p16_f64(float64x2_t __p0) {
39299	poly16x8_t __ret;	35007	poly16x8_t __ret;
39300	__ret = (poly16x8_t)(__p0);	35008	__ret = (poly16x8_t)(__p0);
39301	return __ret;	35009	return __ret;
39302	}	35010	}
39303	#endif
39304
39305	#ifdef __LITTLE_ENDIAN__
39306	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {
39307	poly16x8_t __ret;
39308	__ret = (poly16x8_t)(__p0);
39309	return __ret;
39310	}
39311	#else
39312	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {	35011	__ai poly16x8_t vreinterpretq_p16_f32(float32x4_t __p0) {
39313	poly16x8_t __ret;	35012	poly16x8_t __ret;
39314	__ret = (poly16x8_t)(__p0);	35013	__ret = (poly16x8_t)(__p0);
39315	return __ret;	35014	return __ret;
39316	}	35015	}
39317	#endif
39318
39319	#ifdef __LITTLE_ENDIAN__
39320	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {
39321	poly16x8_t __ret;
39322	__ret = (poly16x8_t)(__p0);
39323	return __ret;
39324	}
39325	#else
39326	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {	35016	__ai poly16x8_t vreinterpretq_p16_f16(float16x8_t __p0) {
39327	poly16x8_t __ret;	35017	poly16x8_t __ret;
39328	__ret = (poly16x8_t)(__p0);	35018	__ret = (poly16x8_t)(__p0);
39329	return __ret;	35019	return __ret;
39330	}	35020	}
39331	#endif
39332
39333	#ifdef __LITTLE_ENDIAN__
39334	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {
39335	poly16x8_t __ret;
39336	__ret = (poly16x8_t)(__p0);
39337	return __ret;
39338	}
39339	#else
39340	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {	35021	__ai poly16x8_t vreinterpretq_p16_s32(int32x4_t __p0) {
39341	poly16x8_t __ret;	35022	poly16x8_t __ret;
39342	__ret = (poly16x8_t)(__p0);	35023	__ret = (poly16x8_t)(__p0);
39343	return __ret;	35024	return __ret;
39344	}	35025	}
39345	#endif
39346
39347	#ifdef __LITTLE_ENDIAN__
39348	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {
39349	poly16x8_t __ret;
39350	__ret = (poly16x8_t)(__p0);
39351	return __ret;
39352	}
39353	#else
39354	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {	35026	__ai poly16x8_t vreinterpretq_p16_s64(int64x2_t __p0) {
39355	poly16x8_t __ret;	35027	poly16x8_t __ret;
39356	__ret = (poly16x8_t)(__p0);	35028	__ret = (poly16x8_t)(__p0);
39357	return __ret;	35029	return __ret;
39358	}	35030	}
39359	#endif
39360
39361	#ifdef __LITTLE_ENDIAN__
39362	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {
39363	poly16x8_t __ret;
39364	__ret = (poly16x8_t)(__p0);
39365	return __ret;
39366	}
39367	#else
39368	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {	35031	__ai poly16x8_t vreinterpretq_p16_s16(int16x8_t __p0) {
39369	poly16x8_t __ret;	35032	poly16x8_t __ret;
39370	__ret = (poly16x8_t)(__p0);	35033	__ret = (poly16x8_t)(__p0);
39371	return __ret;	35034	return __ret;
39372	}	35035	}
39373	#endif
39374
39375	#ifdef __LITTLE_ENDIAN__
39376	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {	35036	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {
39377	uint8x16_t __ret;	35037	uint8x16_t __ret;
39378	__ret = (uint8x16_t)(__p0);	35038	__ret = (uint8x16_t)(__p0);
39379	return __ret;	35039	return __ret;
39380	}	35040	}
39381	#else	35041	__ai uint8x16_t vreinterpretq_u8_p128(poly128_t __p0) {
39382	__ai uint8x16_t vreinterpretq_u8_p8(poly8x16_t __p0) {
39383	uint8x16_t __ret;	35042	uint8x16_t __ret;
39384	__ret = (uint8x16_t)(__p0);	35043	__ret = (uint8x16_t)(__p0);
39385	return __ret;	35044	return __ret;
39386	}	35045	}
39387	#endif	35046	__ai uint8x16_t vreinterpretq_u8_p64(poly64x2_t __p0) {
39388
39389	#ifdef __LITTLE_ENDIAN__
39390	__ai uint8x16_t vreinterpretq_u8_p128(poly128_t __p0) {
39391	uint8x16_t __ret;	35047	uint8x16_t __ret;
39392	__ret = (uint8x16_t)(__p0);	35048	__ret = (uint8x16_t)(__p0);
39393	return __ret;	35049	return __ret;
39394	}	35050	}
39395	#else	35051	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {
39396	__ai uint8x16_t vreinterpretq_u8_p128(poly128_t __p0) {
39397	uint8x16_t __ret;	35052	uint8x16_t __ret;
39398	__ret = (uint8x16_t)(__p0);	35053	__ret = (uint8x16_t)(__p0);
39399	return __ret;	35054	return __ret;
39400	}	35055	}
39401	#endif	35056	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {
39402
39403	#ifdef __LITTLE_ENDIAN__
39404	__ai uint8x16_t vreinterpretq_u8_p64(poly64x2_t __p0) {
39405	uint8x16_t __ret;	35057	uint8x16_t __ret;
39406	__ret = (uint8x16_t)(__p0);	35058	__ret = (uint8x16_t)(__p0);
39407	return __ret;	35059	return __ret;
39408	}	35060	}
39409	#else	35061	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {
39410	__ai uint8x16_t vreinterpretq_u8_p64(poly64x2_t __p0) {
39411	uint8x16_t __ret;	35062	uint8x16_t __ret;
39412	__ret = (uint8x16_t)(__p0);	35063	__ret = (uint8x16_t)(__p0);
39413	return __ret;	35064	return __ret;
39414	}	35065	}
39415	#endif	35066	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {
39416
39417	#ifdef __LITTLE_ENDIAN__
39418	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {
39419	uint8x16_t __ret;	35067	uint8x16_t __ret;
39420	__ret = (uint8x16_t)(__p0);	35068	__ret = (uint8x16_t)(__p0);
39421	return __ret;	35069	return __ret;
39422	}	35070	}
39423	#else	35071	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
39424	__ai uint8x16_t vreinterpretq_u8_p16(poly16x8_t __p0) {
39425	uint8x16_t __ret;	35072	uint8x16_t __ret;
39426	__ret = (uint8x16_t)(__p0);	35073	__ret = (uint8x16_t)(__p0);
39427	return __ret;	35074	return __ret;
39428	}	35075	}
39429	#endif	35076	__ai uint8x16_t vreinterpretq_u8_f64(float64x2_t __p0) {
39430
39431	#ifdef __LITTLE_ENDIAN__
39432	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {
39433	uint8x16_t __ret;	35077	uint8x16_t __ret;
39434	__ret = (uint8x16_t)(__p0);	35078	__ret = (uint8x16_t)(__p0);
39435	return __ret;	35079	return __ret;
39436	}	35080	}
39437	#else	35081	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
39438	__ai uint8x16_t vreinterpretq_u8_u32(uint32x4_t __p0) {
39439	uint8x16_t __ret;	35082	uint8x16_t __ret;
39440	__ret = (uint8x16_t)(__p0);	35083	__ret = (uint8x16_t)(__p0);
39441	return __ret;	35084	return __ret;
39442	}	35085	}
39443	#endif	35086	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {
39444
39445	#ifdef __LITTLE_ENDIAN__
39446	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {
39447	uint8x16_t __ret;	35087	uint8x16_t __ret;
39448	__ret = (uint8x16_t)(__p0);	35088	__ret = (uint8x16_t)(__p0);
39449	return __ret;	35089	return __ret;
39450	}	35090	}
39451	#else	35091	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
39452	__ai uint8x16_t vreinterpretq_u8_u64(uint64x2_t __p0) {
39453	uint8x16_t __ret;	35092	uint8x16_t __ret;
39454	__ret = (uint8x16_t)(__p0);	35093	__ret = (uint8x16_t)(__p0);
39455	return __ret;	35094	return __ret;
39456	}	35095	}
39457	#endif	35096	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
39458
39459	#ifdef __LITTLE_ENDIAN__
39460	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {
39461	uint8x16_t __ret;	35097	uint8x16_t __ret;
39462	__ret = (uint8x16_t)(__p0);	35098	__ret = (uint8x16_t)(__p0);
39463	return __ret;	35099	return __ret;
39464	}	35100	}
39465	#else
39466	__ai uint8x16_t vreinterpretq_u8_u16(uint16x8_t __p0) {
39467	uint8x16_t __ret;
39468	__ret = (uint8x16_t)(__p0);
39469	return __ret;
39470	}
39471	#endif
39472
39473	#ifdef __LITTLE_ENDIAN__
39474	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
39475	uint8x16_t __ret;
39476	__ret = (uint8x16_t)(__p0);
39477	return __ret;
39478	}
39479	#else
39480	__ai uint8x16_t vreinterpretq_u8_s8(int8x16_t __p0) {
39481	uint8x16_t __ret;
39482	__ret = (uint8x16_t)(__p0);
39483	return __ret;
39484	}
39485	#endif
39486
39487	#ifdef __LITTLE_ENDIAN__
39488	__ai uint8x16_t vreinterpretq_u8_f64(float64x2_t __p0) {
39489	uint8x16_t __ret;
39490	__ret = (uint8x16_t)(__p0);
39491	return __ret;
39492	}
39493	#else
39494	__ai uint8x16_t vreinterpretq_u8_f64(float64x2_t __p0) {
39495	uint8x16_t __ret;
39496	__ret = (uint8x16_t)(__p0);
39497	return __ret;
39498	}
39499	#endif
39500
39501	#ifdef __LITTLE_ENDIAN__
39502	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
39503	uint8x16_t __ret;
39504	__ret = (uint8x16_t)(__p0);
39505	return __ret;
39506	}
39507	#else
39508	__ai uint8x16_t vreinterpretq_u8_f32(float32x4_t __p0) {
39509	uint8x16_t __ret;
39510	__ret = (uint8x16_t)(__p0);
39511	return __ret;
39512	}
39513	#endif
39514
39515	#ifdef __LITTLE_ENDIAN__
39516	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {
39517	uint8x16_t __ret;
39518	__ret = (uint8x16_t)(__p0);
39519	return __ret;
39520	}
39521	#else
39522	__ai uint8x16_t vreinterpretq_u8_f16(float16x8_t __p0) {
39523	uint8x16_t __ret;
39524	__ret = (uint8x16_t)(__p0);
39525	return __ret;
39526	}
39527	#endif
39528
39529	#ifdef __LITTLE_ENDIAN__
39530	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
39531	uint8x16_t __ret;
39532	__ret = (uint8x16_t)(__p0);
39533	return __ret;
39534	}
39535	#else
39536	__ai uint8x16_t vreinterpretq_u8_s32(int32x4_t __p0) {
39537	uint8x16_t __ret;
39538	__ret = (uint8x16_t)(__p0);
39539	return __ret;
39540	}
39541	#endif
39542
39543	#ifdef __LITTLE_ENDIAN__
39544	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
39545	uint8x16_t __ret;
39546	__ret = (uint8x16_t)(__p0);
39547	return __ret;
39548	}
39549	#else
39550	__ai uint8x16_t vreinterpretq_u8_s64(int64x2_t __p0) {
39551	uint8x16_t __ret;
39552	__ret = (uint8x16_t)(__p0);
39553	return __ret;
39554	}
39555	#endif
39556
39557	#ifdef __LITTLE_ENDIAN__
39558	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {
39559	uint8x16_t __ret;
39560	__ret = (uint8x16_t)(__p0);
39561	return __ret;
39562	}
39563	#else
39564	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {	35101	__ai uint8x16_t vreinterpretq_u8_s16(int16x8_t __p0) {
39565	uint8x16_t __ret;	35102	uint8x16_t __ret;
39566	__ret = (uint8x16_t)(__p0);	35103	__ret = (uint8x16_t)(__p0);
39567	return __ret;	35104	return __ret;
39568	}	35105	}
39569	#endif
39570
39571	#ifdef __LITTLE_ENDIAN__
39572	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {
39573	uint32x4_t __ret;
39574	__ret = (uint32x4_t)(__p0);
39575	return __ret;
39576	}
39577	#else
39578	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {	35106	__ai uint32x4_t vreinterpretq_u32_p8(poly8x16_t __p0) {
39579	uint32x4_t __ret;	35107	uint32x4_t __ret;
39580	__ret = (uint32x4_t)(__p0);	35108	__ret = (uint32x4_t)(__p0);
39581	return __ret;	35109	return __ret;
39582	}	35110	}
39583	#endif
39584
39585	#ifdef __LITTLE_ENDIAN__
39586	__ai uint32x4_t vreinterpretq_u32_p128(poly128_t __p0) {
39587	uint32x4_t __ret;
39588	__ret = (uint32x4_t)(__p0);
39589	return __ret;
39590	}
39591	#else
39592	__ai uint32x4_t vreinterpretq_u32_p128(poly128_t __p0) {	35111	__ai uint32x4_t vreinterpretq_u32_p128(poly128_t __p0) {
39593	uint32x4_t __ret;	35112	uint32x4_t __ret;
39594	__ret = (uint32x4_t)(__p0);	35113	__ret = (uint32x4_t)(__p0);
39595	return __ret;	35114	return __ret;
39596	}	35115	}
39597	#endif
39598
39599	#ifdef __LITTLE_ENDIAN__
39600	__ai uint32x4_t vreinterpretq_u32_p64(poly64x2_t __p0) {
39601	uint32x4_t __ret;
39602	__ret = (uint32x4_t)(__p0);
39603	return __ret;
39604	}
39605	#else
39606	__ai uint32x4_t vreinterpretq_u32_p64(poly64x2_t __p0) {	35116	__ai uint32x4_t vreinterpretq_u32_p64(poly64x2_t __p0) {
39607	uint32x4_t __ret;	35117	uint32x4_t __ret;
39608	__ret = (uint32x4_t)(__p0);	35118	__ret = (uint32x4_t)(__p0);
39609	return __ret;	35119	return __ret;
39610	}	35120	}
39611	#endif
39612
39613	#ifdef __LITTLE_ENDIAN__
39614	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {
39615	uint32x4_t __ret;
39616	__ret = (uint32x4_t)(__p0);
39617	return __ret;
39618	}
39619	#else
39620	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {	35121	__ai uint32x4_t vreinterpretq_u32_p16(poly16x8_t __p0) {
39621	uint32x4_t __ret;	35122	uint32x4_t __ret;
39622	__ret = (uint32x4_t)(__p0);	35123	__ret = (uint32x4_t)(__p0);
39623	return __ret;	35124	return __ret;
39624	}	35125	}
39625	#endif
39626
39627	#ifdef __LITTLE_ENDIAN__
39628	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
39629	uint32x4_t __ret;
39630	__ret = (uint32x4_t)(__p0);
39631	return __ret;
39632	}
39633	#else
39634	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {	35126	__ai uint32x4_t vreinterpretq_u32_u8(uint8x16_t __p0) {
39635	uint32x4_t __ret;	35127	uint32x4_t __ret;
39636	__ret = (uint32x4_t)(__p0);	35128	__ret = (uint32x4_t)(__p0);
39637	return __ret;	35129	return __ret;
39638	}	35130	}
39639	#endif
39640
39641	#ifdef __LITTLE_ENDIAN__
39642	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {
39643	uint32x4_t __ret;
39644	__ret = (uint32x4_t)(__p0);
39645	return __ret;
39646	}
39647	#else
39648	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {	35131	__ai uint32x4_t vreinterpretq_u32_u64(uint64x2_t __p0) {
39649	uint32x4_t __ret;	35132	uint32x4_t __ret;
39650	__ret = (uint32x4_t)(__p0);	35133	__ret = (uint32x4_t)(__p0);
39651	return __ret;	35134	return __ret;
39652	}	35135	}
39653	#endif
39654
39655	#ifdef __LITTLE_ENDIAN__
39656	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {
39657	uint32x4_t __ret;
39658	__ret = (uint32x4_t)(__p0);
39659	return __ret;
39660	}
39661	#else
39662	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {	35136	__ai uint32x4_t vreinterpretq_u32_u16(uint16x8_t __p0) {
39663	uint32x4_t __ret;	35137	uint32x4_t __ret;
39664	__ret = (uint32x4_t)(__p0);	35138	__ret = (uint32x4_t)(__p0);
39665	return __ret;	35139	return __ret;
39666	}	35140	}
39667	#endif
39668
39669	#ifdef __LITTLE_ENDIAN__
39670	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {
39671	uint32x4_t __ret;
39672	__ret = (uint32x4_t)(__p0);
39673	return __ret;
39674	}
39675	#else
39676	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {	35141	__ai uint32x4_t vreinterpretq_u32_s8(int8x16_t __p0) {
39677	uint32x4_t __ret;	35142	uint32x4_t __ret;
39678	__ret = (uint32x4_t)(__p0);	35143	__ret = (uint32x4_t)(__p0);
39679	return __ret;	35144	return __ret;
39680	}	35145	}
39681	#endif
39682
39683	#ifdef __LITTLE_ENDIAN__
39684	__ai uint32x4_t vreinterpretq_u32_f64(float64x2_t __p0) {
39685	uint32x4_t __ret;
39686	__ret = (uint32x4_t)(__p0);
39687	return __ret;
39688	}
39689	#else
39690	__ai uint32x4_t vreinterpretq_u32_f64(float64x2_t __p0) {	35146	__ai uint32x4_t vreinterpretq_u32_f64(float64x2_t __p0) {
39691	uint32x4_t __ret;	35147	uint32x4_t __ret;
39692	__ret = (uint32x4_t)(__p0);	35148	__ret = (uint32x4_t)(__p0);
39693	return __ret;	35149	return __ret;
39694	}	35150	}
39695	#endif
39696
39697	#ifdef __LITTLE_ENDIAN__
39698	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {
39699	uint32x4_t __ret;
39700	__ret = (uint32x4_t)(__p0);
39701	return __ret;
39702	}
39703	#else
39704	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {	35151	__ai uint32x4_t vreinterpretq_u32_f32(float32x4_t __p0) {
39705	uint32x4_t __ret;	35152	uint32x4_t __ret;
39706	__ret = (uint32x4_t)(__p0);	35153	__ret = (uint32x4_t)(__p0);
39707	return __ret;	35154	return __ret;
39708	}	35155	}
39709	#endif
39710
39711	#ifdef __LITTLE_ENDIAN__
39712	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {
39713	uint32x4_t __ret;
39714	__ret = (uint32x4_t)(__p0);
39715	return __ret;
39716	}
39717	#else
39718	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {	35156	__ai uint32x4_t vreinterpretq_u32_f16(float16x8_t __p0) {
39719	uint32x4_t __ret;	35157	uint32x4_t __ret;
39720	__ret = (uint32x4_t)(__p0);	35158	__ret = (uint32x4_t)(__p0);
39721	return __ret;	35159	return __ret;
39722	}	35160	}
39723	#endif
39724
39725	#ifdef __LITTLE_ENDIAN__
39726	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {
39727	uint32x4_t __ret;
39728	__ret = (uint32x4_t)(__p0);
39729	return __ret;
39730	}
39731	#else
39732	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {	35161	__ai uint32x4_t vreinterpretq_u32_s32(int32x4_t __p0) {
39733	uint32x4_t __ret;	35162	uint32x4_t __ret;
39734	__ret = (uint32x4_t)(__p0);	35163	__ret = (uint32x4_t)(__p0);
39735	return __ret;	35164	return __ret;
39736	}	35165	}
39737	#endif
39738
39739	#ifdef __LITTLE_ENDIAN__
39740	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {
39741	uint32x4_t __ret;
39742	__ret = (uint32x4_t)(__p0);
39743	return __ret;
39744	}
39745	#else
39746	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {	35166	__ai uint32x4_t vreinterpretq_u32_s64(int64x2_t __p0) {
39747	uint32x4_t __ret;	35167	uint32x4_t __ret;
39748	__ret = (uint32x4_t)(__p0);	35168	__ret = (uint32x4_t)(__p0);
39749	return __ret;	35169	return __ret;
39750	}	35170	}
39751	#endif
39752
39753	#ifdef __LITTLE_ENDIAN__
39754	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {
39755	uint32x4_t __ret;
39756	__ret = (uint32x4_t)(__p0);
39757	return __ret;
39758	}
39759	#else
39760	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {	35171	__ai uint32x4_t vreinterpretq_u32_s16(int16x8_t __p0) {
39761	uint32x4_t __ret;	35172	uint32x4_t __ret;
39762	__ret = (uint32x4_t)(__p0);	35173	__ret = (uint32x4_t)(__p0);
39763	return __ret;	35174	return __ret;
39764	}	35175	}
39765	#endif
39766
39767	#ifdef __LITTLE_ENDIAN__
39768	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {
39769	uint64x2_t __ret;
39770	__ret = (uint64x2_t)(__p0);
39771	return __ret;
39772	}
39773	#else
39774	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {	35176	__ai uint64x2_t vreinterpretq_u64_p8(poly8x16_t __p0) {
39775	uint64x2_t __ret;	35177	uint64x2_t __ret;
39776	__ret = (uint64x2_t)(__p0);	35178	__ret = (uint64x2_t)(__p0);
39777	return __ret;	35179	return __ret;
39778	}	35180	}
39779	#endif
39780
39781	#ifdef __LITTLE_ENDIAN__
39782	__ai uint64x2_t vreinterpretq_u64_p128(poly128_t __p0) {
39783	uint64x2_t __ret;
39784	__ret = (uint64x2_t)(__p0);
39785	return __ret;
39786	}
39787	#else
39788	__ai uint64x2_t vreinterpretq_u64_p128(poly128_t __p0) {	35181	__ai uint64x2_t vreinterpretq_u64_p128(poly128_t __p0) {
39789	uint64x2_t __ret;	35182	uint64x2_t __ret;
39790	__ret = (uint64x2_t)(__p0);	35183	__ret = (uint64x2_t)(__p0);
39791	return __ret;	35184	return __ret;
39792	}	35185	}
39793	#endif
39794
39795	#ifdef __LITTLE_ENDIAN__
39796	__ai uint64x2_t vreinterpretq_u64_p64(poly64x2_t __p0) {
39797	uint64x2_t __ret;
39798	__ret = (uint64x2_t)(__p0);
39799	return __ret;
39800	}
39801	#else
39802	__ai uint64x2_t vreinterpretq_u64_p64(poly64x2_t __p0) {	35186	__ai uint64x2_t vreinterpretq_u64_p64(poly64x2_t __p0) {
39803	uint64x2_t __ret;	35187	uint64x2_t __ret;
39804	__ret = (uint64x2_t)(__p0);	35188	__ret = (uint64x2_t)(__p0);
39805	return __ret;	35189	return __ret;
39806	}	35190	}
39807	#endif
39808
39809	#ifdef __LITTLE_ENDIAN__
39810	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {
39811	uint64x2_t __ret;
39812	__ret = (uint64x2_t)(__p0);
39813	return __ret;
39814	}
39815	#else
39816	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {	35191	__ai uint64x2_t vreinterpretq_u64_p16(poly16x8_t __p0) {
39817	uint64x2_t __ret;	35192	uint64x2_t __ret;
39818	__ret = (uint64x2_t)(__p0);	35193	__ret = (uint64x2_t)(__p0);
39819	return __ret;	35194	return __ret;
39820	}	35195	}
39821	#endif
39822
39823	#ifdef __LITTLE_ENDIAN__
39824	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {
39825	uint64x2_t __ret;
39826	__ret = (uint64x2_t)(__p0);
39827	return __ret;
39828	}
39829	#else
39830	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {	35196	__ai uint64x2_t vreinterpretq_u64_u8(uint8x16_t __p0) {
39831	uint64x2_t __ret;	35197	uint64x2_t __ret;
39832	__ret = (uint64x2_t)(__p0);	35198	__ret = (uint64x2_t)(__p0);
39833	return __ret;	35199	return __ret;
39834	}	35200	}
39835	#endif
39836
39837	#ifdef __LITTLE_ENDIAN__
39838	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {
39839	uint64x2_t __ret;
39840	__ret = (uint64x2_t)(__p0);
39841	return __ret;
39842	}
39843	#else
39844	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {	35201	__ai uint64x2_t vreinterpretq_u64_u32(uint32x4_t __p0) {
39845	uint64x2_t __ret;	35202	uint64x2_t __ret;
39846	__ret = (uint64x2_t)(__p0);	35203	__ret = (uint64x2_t)(__p0);
39847	return __ret;	35204	return __ret;
39848	}	35205	}
39849	#endif
39850
39851	#ifdef __LITTLE_ENDIAN__
39852	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {
39853	uint64x2_t __ret;
39854	__ret = (uint64x2_t)(__p0);
39855	return __ret;
39856	}
39857	#else
39858	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {	35206	__ai uint64x2_t vreinterpretq_u64_u16(uint16x8_t __p0) {
39859	uint64x2_t __ret;	35207	uint64x2_t __ret;
39860	__ret = (uint64x2_t)(__p0);	35208	__ret = (uint64x2_t)(__p0);
39861	return __ret;	35209	return __ret;
39862	}	35210	}
39863	#endif
39864
39865	#ifdef __LITTLE_ENDIAN__
39866	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {
39867	uint64x2_t __ret;
39868	__ret = (uint64x2_t)(__p0);
39869	return __ret;
39870	}
39871	#else
39872	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {	35211	__ai uint64x2_t vreinterpretq_u64_s8(int8x16_t __p0) {
39873	uint64x2_t __ret;	35212	uint64x2_t __ret;
39874	__ret = (uint64x2_t)(__p0);	35213	__ret = (uint64x2_t)(__p0);
39875	return __ret;	35214	return __ret;
39876	}	35215	}
39877	#endif
39878
39879	#ifdef __LITTLE_ENDIAN__
39880	__ai uint64x2_t vreinterpretq_u64_f64(float64x2_t __p0) {
39881	uint64x2_t __ret;
39882	__ret = (uint64x2_t)(__p0);
39883	return __ret;
39884	}
39885	#else
39886	__ai uint64x2_t vreinterpretq_u64_f64(float64x2_t __p0) {	35216	__ai uint64x2_t vreinterpretq_u64_f64(float64x2_t __p0) {
39887	uint64x2_t __ret;	35217	uint64x2_t __ret;
39888	__ret = (uint64x2_t)(__p0);	35218	__ret = (uint64x2_t)(__p0);
39889	return __ret;	35219	return __ret;
39890	}	35220	}
39891	#endif
39892
39893	#ifdef __LITTLE_ENDIAN__
39894	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {
39895	uint64x2_t __ret;
39896	__ret = (uint64x2_t)(__p0);
39897	return __ret;
39898	}
39899	#else
39900	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {	35221	__ai uint64x2_t vreinterpretq_u64_f32(float32x4_t __p0) {
39901	uint64x2_t __ret;	35222	uint64x2_t __ret;
39902	__ret = (uint64x2_t)(__p0);	35223	__ret = (uint64x2_t)(__p0);
39903	return __ret;	35224	return __ret;
39904	}	35225	}
39905	#endif
39906
39907	#ifdef __LITTLE_ENDIAN__
39908	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {
39909	uint64x2_t __ret;
39910	__ret = (uint64x2_t)(__p0);
39911	return __ret;
39912	}
39913	#else
39914	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {	35226	__ai uint64x2_t vreinterpretq_u64_f16(float16x8_t __p0) {
39915	uint64x2_t __ret;	35227	uint64x2_t __ret;
39916	__ret = (uint64x2_t)(__p0);	35228	__ret = (uint64x2_t)(__p0);
39917	return __ret;	35229	return __ret;
39918	}	35230	}
39919	#endif
39920
39921	#ifdef __LITTLE_ENDIAN__
39922	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {
39923	uint64x2_t __ret;
39924	__ret = (uint64x2_t)(__p0);
39925	return __ret;
39926	}
39927	#else
39928	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {	35231	__ai uint64x2_t vreinterpretq_u64_s32(int32x4_t __p0) {
39929	uint64x2_t __ret;	35232	uint64x2_t __ret;
39930	__ret = (uint64x2_t)(__p0);	35233	__ret = (uint64x2_t)(__p0);
39931	return __ret;	35234	return __ret;
39932	}	35235	}
39933	#endif
39934
39935	#ifdef __LITTLE_ENDIAN__
39936	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {
39937	uint64x2_t __ret;
39938	__ret = (uint64x2_t)(__p0);
39939	return __ret;
39940	}
39941	#else
39942	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {	35236	__ai uint64x2_t vreinterpretq_u64_s64(int64x2_t __p0) {
39943	uint64x2_t __ret;	35237	uint64x2_t __ret;
39944	__ret = (uint64x2_t)(__p0);	35238	__ret = (uint64x2_t)(__p0);
39945	return __ret;	35239	return __ret;
39946	}	35240	}
39947	#endif
39948
39949	#ifdef __LITTLE_ENDIAN__
39950	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {
39951	uint64x2_t __ret;
39952	__ret = (uint64x2_t)(__p0);
39953	return __ret;
39954	}
39955	#else
39956	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {	35241	__ai uint64x2_t vreinterpretq_u64_s16(int16x8_t __p0) {
39957	uint64x2_t __ret;	35242	uint64x2_t __ret;
39958	__ret = (uint64x2_t)(__p0);	35243	__ret = (uint64x2_t)(__p0);
39959	return __ret;	35244	return __ret;
39960	}	35245	}
39961	#endif
39962
39963	#ifdef __LITTLE_ENDIAN__
39964	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {
39965	uint16x8_t __ret;
39966	__ret = (uint16x8_t)(__p0);
39967	return __ret;
39968	}
39969	#else
39970	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {	35246	__ai uint16x8_t vreinterpretq_u16_p8(poly8x16_t __p0) {
39971	uint16x8_t __ret;	35247	uint16x8_t __ret;
39972	__ret = (uint16x8_t)(__p0);	35248	__ret = (uint16x8_t)(__p0);
39973	return __ret;	35249	return __ret;
39974	}	35250	}
39975	#endif
39976
39977	#ifdef __LITTLE_ENDIAN__
39978	__ai uint16x8_t vreinterpretq_u16_p128(poly128_t __p0) {
39979	uint16x8_t __ret;
39980	__ret = (uint16x8_t)(__p0);
39981	return __ret;
39982	}
39983	#else
39984	__ai uint16x8_t vreinterpretq_u16_p128(poly128_t __p0) {	35251	__ai uint16x8_t vreinterpretq_u16_p128(poly128_t __p0) {
39985	uint16x8_t __ret;	35252	uint16x8_t __ret;
39986	__ret = (uint16x8_t)(__p0);	35253	__ret = (uint16x8_t)(__p0);
39987	return __ret;	35254	return __ret;
39988	}	35255	}
39989	#endif
39990
39991	#ifdef __LITTLE_ENDIAN__
39992	__ai uint16x8_t vreinterpretq_u16_p64(poly64x2_t __p0) {
39993	uint16x8_t __ret;
39994	__ret = (uint16x8_t)(__p0);
39995	return __ret;
39996	}
39997	#else
39998	__ai uint16x8_t vreinterpretq_u16_p64(poly64x2_t __p0) {	35256	__ai uint16x8_t vreinterpretq_u16_p64(poly64x2_t __p0) {
39999	uint16x8_t __ret;	35257	uint16x8_t __ret;
40000	__ret = (uint16x8_t)(__p0);	35258	__ret = (uint16x8_t)(__p0);
40001	return __ret;	35259	return __ret;
40002	}	35260	}
40003	#endif
40004
40005	#ifdef __LITTLE_ENDIAN__
40006	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {
40007	uint16x8_t __ret;
40008	__ret = (uint16x8_t)(__p0);
40009	return __ret;
40010	}
40011	#else
40012	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {	35261	__ai uint16x8_t vreinterpretq_u16_p16(poly16x8_t __p0) {
40013	uint16x8_t __ret;	35262	uint16x8_t __ret;
40014	__ret = (uint16x8_t)(__p0);	35263	__ret = (uint16x8_t)(__p0);
40015	return __ret;	35264	return __ret;
40016	}	35265	}
40017	#endif
40018
40019	#ifdef __LITTLE_ENDIAN__
40020	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {
40021	uint16x8_t __ret;
40022	__ret = (uint16x8_t)(__p0);
40023	return __ret;
40024	}
40025	#else
40026	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {	35266	__ai uint16x8_t vreinterpretq_u16_u8(uint8x16_t __p0) {
40027	uint16x8_t __ret;	35267	uint16x8_t __ret;
40028	__ret = (uint16x8_t)(__p0);	35268	__ret = (uint16x8_t)(__p0);
40029	return __ret;	35269	return __ret;
40030	}	35270	}
40031	#endif
40032
40033	#ifdef __LITTLE_ENDIAN__
40034	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {
40035	uint16x8_t __ret;
40036	__ret = (uint16x8_t)(__p0);
40037	return __ret;
40038	}
40039	#else
40040	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {	35271	__ai uint16x8_t vreinterpretq_u16_u32(uint32x4_t __p0) {
40041	uint16x8_t __ret;	35272	uint16x8_t __ret;
40042	__ret = (uint16x8_t)(__p0);	35273	__ret = (uint16x8_t)(__p0);
40043	return __ret;	35274	return __ret;
40044	}	35275	}
40045	#endif
40046
40047	#ifdef __LITTLE_ENDIAN__
40048	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {
40049	uint16x8_t __ret;
40050	__ret = (uint16x8_t)(__p0);
40051	return __ret;
40052	}
40053	#else
40054	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {	35276	__ai uint16x8_t vreinterpretq_u16_u64(uint64x2_t __p0) {
40055	uint16x8_t __ret;	35277	uint16x8_t __ret;
40056	__ret = (uint16x8_t)(__p0);	35278	__ret = (uint16x8_t)(__p0);
40057	return __ret;	35279	return __ret;
40058	}	35280	}
40059	#endif
40060
40061	#ifdef __LITTLE_ENDIAN__
40062	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {
40063	uint16x8_t __ret;
40064	__ret = (uint16x8_t)(__p0);
40065	return __ret;
40066	}
40067	#else
40068	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {	35281	__ai uint16x8_t vreinterpretq_u16_s8(int8x16_t __p0) {
40069	uint16x8_t __ret;	35282	uint16x8_t __ret;
40070	__ret = (uint16x8_t)(__p0);	35283	__ret = (uint16x8_t)(__p0);
40071	return __ret;	35284	return __ret;
40072	}	35285	}
40073	#endif
40074
40075	#ifdef __LITTLE_ENDIAN__
40076	__ai uint16x8_t vreinterpretq_u16_f64(float64x2_t __p0) {
40077	uint16x8_t __ret;
40078	__ret = (uint16x8_t)(__p0);
40079	return __ret;
40080	}
40081	#else
40082	__ai uint16x8_t vreinterpretq_u16_f64(float64x2_t __p0) {	35286	__ai uint16x8_t vreinterpretq_u16_f64(float64x2_t __p0) {
40083	uint16x8_t __ret;	35287	uint16x8_t __ret;
40084	__ret = (uint16x8_t)(__p0);	35288	__ret = (uint16x8_t)(__p0);
40085	return __ret;	35289	return __ret;
40086	}	35290	}
40087	#endif
40088
40089	#ifdef __LITTLE_ENDIAN__
40090	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {
40091	uint16x8_t __ret;
40092	__ret = (uint16x8_t)(__p0);
40093	return __ret;
40094	}
40095	#else
40096	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {	35291	__ai uint16x8_t vreinterpretq_u16_f32(float32x4_t __p0) {
40097	uint16x8_t __ret;	35292	uint16x8_t __ret;
40098	__ret = (uint16x8_t)(__p0);	35293	__ret = (uint16x8_t)(__p0);
40099	return __ret;	35294	return __ret;
40100	}	35295	}
40101	#endif
40102
40103	#ifdef __LITTLE_ENDIAN__
40104	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {
40105	uint16x8_t __ret;
40106	__ret = (uint16x8_t)(__p0);
40107	return __ret;
40108	}
40109	#else
40110	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {	35296	__ai uint16x8_t vreinterpretq_u16_f16(float16x8_t __p0) {
40111	uint16x8_t __ret;	35297	uint16x8_t __ret;
40112	__ret = (uint16x8_t)(__p0);	35298	__ret = (uint16x8_t)(__p0);
40113	return __ret;	35299	return __ret;
40114	}	35300	}
40115	#endif
40116
40117	#ifdef __LITTLE_ENDIAN__
40118	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {
40119	uint16x8_t __ret;
40120	__ret = (uint16x8_t)(__p0);
40121	return __ret;
40122	}
40123	#else
40124	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {	35301	__ai uint16x8_t vreinterpretq_u16_s32(int32x4_t __p0) {
40125	uint16x8_t __ret;	35302	uint16x8_t __ret;
40126	__ret = (uint16x8_t)(__p0);	35303	__ret = (uint16x8_t)(__p0);
40127	return __ret;	35304	return __ret;
40128	}	35305	}
40129	#endif
40130
40131	#ifdef __LITTLE_ENDIAN__
40132	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {
40133	uint16x8_t __ret;
40134	__ret = (uint16x8_t)(__p0);
40135	return __ret;
40136	}
40137	#else
40138	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {	35306	__ai uint16x8_t vreinterpretq_u16_s64(int64x2_t __p0) {
40139	uint16x8_t __ret;	35307	uint16x8_t __ret;
40140	__ret = (uint16x8_t)(__p0);	35308	__ret = (uint16x8_t)(__p0);
40141	return __ret;	35309	return __ret;
40142	}	35310	}
40143	#endif
40144
40145	#ifdef __LITTLE_ENDIAN__
40146	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {
40147	uint16x8_t __ret;
40148	__ret = (uint16x8_t)(__p0);
40149	return __ret;
40150	}
40151	#else
40152	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {	35311	__ai uint16x8_t vreinterpretq_u16_s16(int16x8_t __p0) {
40153	uint16x8_t __ret;	35312	uint16x8_t __ret;
40154	__ret = (uint16x8_t)(__p0);	35313	__ret = (uint16x8_t)(__p0);
40155	return __ret;	35314	return __ret;
40156	}	35315	}
40157	#endif
40158
40159	#ifdef __LITTLE_ENDIAN__
40160	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {	35316	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {
40161	int8x16_t __ret;	35317	int8x16_t __ret;
40162	__ret = (int8x16_t)(__p0);	35318	__ret = (int8x16_t)(__p0);
40163	return __ret;	35319	return __ret;
40164	}	35320	}
40165	#else	35321	__ai int8x16_t vreinterpretq_s8_p128(poly128_t __p0) {
40166	__ai int8x16_t vreinterpretq_s8_p8(poly8x16_t __p0) {
40167	int8x16_t __ret;	35322	int8x16_t __ret;
40168	__ret = (int8x16_t)(__p0);	35323	__ret = (int8x16_t)(__p0);
40169	return __ret;	35324	return __ret;
40170	}	35325	}
40171	#endif	35326	__ai int8x16_t vreinterpretq_s8_p64(poly64x2_t __p0) {
40172
40173	#ifdef __LITTLE_ENDIAN__
40174	__ai int8x16_t vreinterpretq_s8_p128(poly128_t __p0) {
40175	int8x16_t __ret;	35327	int8x16_t __ret;
40176	__ret = (int8x16_t)(__p0);	35328	__ret = (int8x16_t)(__p0);
40177	return __ret;	35329	return __ret;
40178	}	35330	}
40179	#else	35331	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {
40180	__ai int8x16_t vreinterpretq_s8_p128(poly128_t __p0) {
40181	int8x16_t __ret;	35332	int8x16_t __ret;
40182	__ret = (int8x16_t)(__p0);	35333	__ret = (int8x16_t)(__p0);
40183	return __ret;	35334	return __ret;
40184	}	35335	}
40185	#endif	35336	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {
40186
40187	#ifdef __LITTLE_ENDIAN__
40188	__ai int8x16_t vreinterpretq_s8_p64(poly64x2_t __p0) {
40189	int8x16_t __ret;	35337	int8x16_t __ret;
40190	__ret = (int8x16_t)(__p0);	35338	__ret = (int8x16_t)(__p0);
40191	return __ret;	35339	return __ret;
40192	}	35340	}
40193	#else	35341	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {
40194	__ai int8x16_t vreinterpretq_s8_p64(poly64x2_t __p0) {
40195	int8x16_t __ret;	35342	int8x16_t __ret;
40196	__ret = (int8x16_t)(__p0);	35343	__ret = (int8x16_t)(__p0);
40197	return __ret;	35344	return __ret;
40198	}	35345	}
40199	#endif	35346	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {
40200
40201	#ifdef __LITTLE_ENDIAN__
40202	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {
40203	int8x16_t __ret;	35347	int8x16_t __ret;
40204	__ret = (int8x16_t)(__p0);	35348	__ret = (int8x16_t)(__p0);
40205	return __ret;	35349	return __ret;
40206	}	35350	}
40207	#else	35351	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {
40208	__ai int8x16_t vreinterpretq_s8_p16(poly16x8_t __p0) {
40209	int8x16_t __ret;	35352	int8x16_t __ret;
40210	__ret = (int8x16_t)(__p0);	35353	__ret = (int8x16_t)(__p0);
40211	return __ret;	35354	return __ret;
40212	}	35355	}
40213	#endif	35356	__ai int8x16_t vreinterpretq_s8_f64(float64x2_t __p0) {
40214
40215	#ifdef __LITTLE_ENDIAN__
40216	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {
40217	int8x16_t __ret;	35357	int8x16_t __ret;
40218	__ret = (int8x16_t)(__p0);	35358	__ret = (int8x16_t)(__p0);
40219	return __ret;	35359	return __ret;
40220	}	35360	}
40221	#else
40222	__ai int8x16_t vreinterpretq_s8_u8(uint8x16_t __p0) {
40223	int8x16_t __ret;
40224	__ret = (int8x16_t)(__p0);
40225	return __ret;
40226	}
40227	#endif
40228
40229	#ifdef __LITTLE_ENDIAN__
40230	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {
40231	int8x16_t __ret;
40232	__ret = (int8x16_t)(__p0);
40233	return __ret;
40234	}
40235	#else
40236	__ai int8x16_t vreinterpretq_s8_u32(uint32x4_t __p0) {
40237	int8x16_t __ret;
40238	__ret = (int8x16_t)(__p0);
40239	return __ret;
40240	}
40241	#endif
40242
40243	#ifdef __LITTLE_ENDIAN__
40244	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {
40245	int8x16_t __ret;
40246	__ret = (int8x16_t)(__p0);
40247	return __ret;
40248	}
40249	#else
40250	__ai int8x16_t vreinterpretq_s8_u64(uint64x2_t __p0) {
40251	int8x16_t __ret;
40252	__ret = (int8x16_t)(__p0);
40253	return __ret;
40254	}
40255	#endif
40256
40257	#ifdef __LITTLE_ENDIAN__
40258	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {
40259	int8x16_t __ret;
40260	__ret = (int8x16_t)(__p0);
40261	return __ret;
40262	}
40263	#else
40264	__ai int8x16_t vreinterpretq_s8_u16(uint16x8_t __p0) {
40265	int8x16_t __ret;
40266	__ret = (int8x16_t)(__p0);
40267	return __ret;
40268	}
40269	#endif
40270
40271	#ifdef __LITTLE_ENDIAN__
40272	__ai int8x16_t vreinterpretq_s8_f64(float64x2_t __p0) {
40273	int8x16_t __ret;
40274	__ret = (int8x16_t)(__p0);
40275	return __ret;
40276	}
40277	#else
40278	__ai int8x16_t vreinterpretq_s8_f64(float64x2_t __p0) {
40279	int8x16_t __ret;
40280	__ret = (int8x16_t)(__p0);
40281	return __ret;
40282	}
40283	#endif
40284
40285	#ifdef __LITTLE_ENDIAN__
40286	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {
40287	int8x16_t __ret;
40288	__ret = (int8x16_t)(__p0);
40289	return __ret;
40290	}
40291	#else
40292	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {	35361	__ai int8x16_t vreinterpretq_s8_f32(float32x4_t __p0) {
40293	int8x16_t __ret;	35362	int8x16_t __ret;
40294	__ret = (int8x16_t)(__p0);	35363	__ret = (int8x16_t)(__p0);
40295	return __ret;	35364	return __ret;
40296	}	35365	}
40297	#endif
40298
40299	#ifdef __LITTLE_ENDIAN__
40300	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {
40301	int8x16_t __ret;
40302	__ret = (int8x16_t)(__p0);
40303	return __ret;
40304	}
40305	#else
40306	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {	35366	__ai int8x16_t vreinterpretq_s8_f16(float16x8_t __p0) {
40307	int8x16_t __ret;	35367	int8x16_t __ret;
40308	__ret = (int8x16_t)(__p0);	35368	__ret = (int8x16_t)(__p0);
40309	return __ret;	35369	return __ret;
40310	}	35370	}
40311	#endif
40312
40313	#ifdef __LITTLE_ENDIAN__
40314	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {
40315	int8x16_t __ret;
40316	__ret = (int8x16_t)(__p0);
40317	return __ret;
40318	}
40319	#else
40320	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {	35371	__ai int8x16_t vreinterpretq_s8_s32(int32x4_t __p0) {
40321	int8x16_t __ret;	35372	int8x16_t __ret;
40322	__ret = (int8x16_t)(__p0);	35373	__ret = (int8x16_t)(__p0);
40323	return __ret;	35374	return __ret;
40324	}	35375	}
40325	#endif
40326
40327	#ifdef __LITTLE_ENDIAN__
40328	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {
40329	int8x16_t __ret;
40330	__ret = (int8x16_t)(__p0);
40331	return __ret;
40332	}
40333	#else
40334	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {	35376	__ai int8x16_t vreinterpretq_s8_s64(int64x2_t __p0) {
40335	int8x16_t __ret;	35377	int8x16_t __ret;
40336	__ret = (int8x16_t)(__p0);	35378	__ret = (int8x16_t)(__p0);
40337	return __ret;	35379	return __ret;
40338	}	35380	}
40339	#endif
40340
40341	#ifdef __LITTLE_ENDIAN__
40342	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {
40343	int8x16_t __ret;
40344	__ret = (int8x16_t)(__p0);
40345	return __ret;
40346	}
40347	#else
40348	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {	35381	__ai int8x16_t vreinterpretq_s8_s16(int16x8_t __p0) {
40349	int8x16_t __ret;	35382	int8x16_t __ret;
40350	__ret = (int8x16_t)(__p0);	35383	__ret = (int8x16_t)(__p0);
40351	return __ret;	35384	return __ret;
40352	}	35385	}
40353	#endif
40354
40355	#ifdef __LITTLE_ENDIAN__
40356	__ai float64x2_t vreinterpretq_f64_p8(poly8x16_t __p0) {
40357	float64x2_t __ret;
40358	__ret = (float64x2_t)(__p0);
40359	return __ret;
40360	}
40361	#else
40362	__ai float64x2_t vreinterpretq_f64_p8(poly8x16_t __p0) {	35386	__ai float64x2_t vreinterpretq_f64_p8(poly8x16_t __p0) {
40363	float64x2_t __ret;	35387	float64x2_t __ret;
40364	__ret = (float64x2_t)(__p0);	35388	__ret = (float64x2_t)(__p0);
40365	return __ret;	35389	return __ret;
40366	}	35390	}
40367	#endif
40368
40369	#ifdef __LITTLE_ENDIAN__
40370	__ai float64x2_t vreinterpretq_f64_p128(poly128_t __p0) {
40371	float64x2_t __ret;
40372	__ret = (float64x2_t)(__p0);
40373	return __ret;
40374	}
40375	#else
40376	__ai float64x2_t vreinterpretq_f64_p128(poly128_t __p0) {	35391	__ai float64x2_t vreinterpretq_f64_p128(poly128_t __p0) {
40377	float64x2_t __ret;	35392	float64x2_t __ret;
40378	__ret = (float64x2_t)(__p0);	35393	__ret = (float64x2_t)(__p0);
40379	return __ret;	35394	return __ret;
40380	}	35395	}
40381	#endif
40382
40383	#ifdef __LITTLE_ENDIAN__
40384	__ai float64x2_t vreinterpretq_f64_p64(poly64x2_t __p0) {
40385	float64x2_t __ret;
40386	__ret = (float64x2_t)(__p0);
40387	return __ret;
40388	}
40389	#else
40390	__ai float64x2_t vreinterpretq_f64_p64(poly64x2_t __p0) {	35396	__ai float64x2_t vreinterpretq_f64_p64(poly64x2_t __p0) {
40391	float64x2_t __ret;	35397	float64x2_t __ret;
40392	__ret = (float64x2_t)(__p0);	35398	__ret = (float64x2_t)(__p0);
40393	return __ret;	35399	return __ret;
40394	}	35400	}
40395	#endif
40396
40397	#ifdef __LITTLE_ENDIAN__
40398	__ai float64x2_t vreinterpretq_f64_p16(poly16x8_t __p0) {
40399	float64x2_t __ret;
40400	__ret = (float64x2_t)(__p0);
40401	return __ret;
40402	}
40403	#else
40404	__ai float64x2_t vreinterpretq_f64_p16(poly16x8_t __p0) {	35401	__ai float64x2_t vreinterpretq_f64_p16(poly16x8_t __p0) {
40405	float64x2_t __ret;	35402	float64x2_t __ret;
40406	__ret = (float64x2_t)(__p0);	35403	__ret = (float64x2_t)(__p0);
40407	return __ret;	35404	return __ret;
40408	}	35405	}
40409	#endif
40410
40411	#ifdef __LITTLE_ENDIAN__
40412	__ai float64x2_t vreinterpretq_f64_u8(uint8x16_t __p0) {
40413	float64x2_t __ret;
40414	__ret = (float64x2_t)(__p0);
40415	return __ret;
40416	}
40417	#else
40418	__ai float64x2_t vreinterpretq_f64_u8(uint8x16_t __p0) {	35406	__ai float64x2_t vreinterpretq_f64_u8(uint8x16_t __p0) {
40419	float64x2_t __ret;	35407	float64x2_t __ret;
40420	__ret = (float64x2_t)(__p0);	35408	__ret = (float64x2_t)(__p0);
40421	return __ret;	35409	return __ret;
40422	}	35410	}
40423	#endif
40424
40425	#ifdef __LITTLE_ENDIAN__
40426	__ai float64x2_t vreinterpretq_f64_u32(uint32x4_t __p0) {
40427	float64x2_t __ret;
40428	__ret = (float64x2_t)(__p0);
40429	return __ret;
40430	}
40431	#else
40432	__ai float64x2_t vreinterpretq_f64_u32(uint32x4_t __p0) {	35411	__ai float64x2_t vreinterpretq_f64_u32(uint32x4_t __p0) {
40433	float64x2_t __ret;	35412	float64x2_t __ret;
40434	__ret = (float64x2_t)(__p0);	35413	__ret = (float64x2_t)(__p0);
40435	return __ret;	35414	return __ret;
40436	}	35415	}
40437	#endif
40438
40439	#ifdef __LITTLE_ENDIAN__
40440	__ai float64x2_t vreinterpretq_f64_u64(uint64x2_t __p0) {
40441	float64x2_t __ret;
40442	__ret = (float64x2_t)(__p0);
40443	return __ret;
40444	}
40445	#else
40446	__ai float64x2_t vreinterpretq_f64_u64(uint64x2_t __p0) {	35416	__ai float64x2_t vreinterpretq_f64_u64(uint64x2_t __p0) {
40447	float64x2_t __ret;	35417	float64x2_t __ret;
40448	__ret = (float64x2_t)(__p0);	35418	__ret = (float64x2_t)(__p0);
40449	return __ret;	35419	return __ret;
40450	}	35420	}
40451	#endif
40452
40453	#ifdef __LITTLE_ENDIAN__
40454	__ai float64x2_t vreinterpretq_f64_u16(uint16x8_t __p0) {
40455	float64x2_t __ret;
40456	__ret = (float64x2_t)(__p0);
40457	return __ret;
40458	}
40459	#else
40460	__ai float64x2_t vreinterpretq_f64_u16(uint16x8_t __p0) {	35421	__ai float64x2_t vreinterpretq_f64_u16(uint16x8_t __p0) {
40461	float64x2_t __ret;	35422	float64x2_t __ret;
40462	__ret = (float64x2_t)(__p0);	35423	__ret = (float64x2_t)(__p0);
40463	return __ret;	35424	return __ret;
40464	}	35425	}
40465	#endif
40466
40467	#ifdef __LITTLE_ENDIAN__
40468	__ai float64x2_t vreinterpretq_f64_s8(int8x16_t __p0) {
40469	float64x2_t __ret;
40470	__ret = (float64x2_t)(__p0);
40471	return __ret;
40472	}
40473	#else
40474	__ai float64x2_t vreinterpretq_f64_s8(int8x16_t __p0) {	35426	__ai float64x2_t vreinterpretq_f64_s8(int8x16_t __p0) {
40475	float64x2_t __ret;	35427	float64x2_t __ret;
40476	__ret = (float64x2_t)(__p0);	35428	__ret = (float64x2_t)(__p0);
40477	return __ret;	35429	return __ret;
40478	}	35430	}
40479	#endif
40480
40481	#ifdef __LITTLE_ENDIAN__
40482	__ai float64x2_t vreinterpretq_f64_f32(float32x4_t __p0) {
40483	float64x2_t __ret;
40484	__ret = (float64x2_t)(__p0);
40485	return __ret;
40486	}
40487	#else
40488	__ai float64x2_t vreinterpretq_f64_f32(float32x4_t __p0) {	35431	__ai float64x2_t vreinterpretq_f64_f32(float32x4_t __p0) {
40489	float64x2_t __ret;	35432	float64x2_t __ret;
40490	__ret = (float64x2_t)(__p0);	35433	__ret = (float64x2_t)(__p0);
40491	return __ret;	35434	return __ret;
40492	}	35435	}
40493	#endif
40494
40495	#ifdef __LITTLE_ENDIAN__
40496	__ai float64x2_t vreinterpretq_f64_f16(float16x8_t __p0) {
40497	float64x2_t __ret;
40498	__ret = (float64x2_t)(__p0);
40499	return __ret;
40500	}
40501	#else
40502	__ai float64x2_t vreinterpretq_f64_f16(float16x8_t __p0) {	35436	__ai float64x2_t vreinterpretq_f64_f16(float16x8_t __p0) {
40503	float64x2_t __ret;	35437	float64x2_t __ret;
40504	__ret = (float64x2_t)(__p0);	35438	__ret = (float64x2_t)(__p0);
40505	return __ret;	35439	return __ret;
40506	}	35440	}
40507	#endif
40508
40509	#ifdef __LITTLE_ENDIAN__
40510	__ai float64x2_t vreinterpretq_f64_s32(int32x4_t __p0) {
40511	float64x2_t __ret;
40512	__ret = (float64x2_t)(__p0);
40513	return __ret;
40514	}
40515	#else
40516	__ai float64x2_t vreinterpretq_f64_s32(int32x4_t __p0) {	35441	__ai float64x2_t vreinterpretq_f64_s32(int32x4_t __p0) {
40517	float64x2_t __ret;	35442	float64x2_t __ret;
40518	__ret = (float64x2_t)(__p0);	35443	__ret = (float64x2_t)(__p0);
40519	return __ret;	35444	return __ret;
40520	}	35445	}
40521	#endif
40522
40523	#ifdef __LITTLE_ENDIAN__
40524	__ai float64x2_t vreinterpretq_f64_s64(int64x2_t __p0) {
40525	float64x2_t __ret;
40526	__ret = (float64x2_t)(__p0);
40527	return __ret;
40528	}
40529	#else
40530	__ai float64x2_t vreinterpretq_f64_s64(int64x2_t __p0) {	35446	__ai float64x2_t vreinterpretq_f64_s64(int64x2_t __p0) {
40531	float64x2_t __ret;	35447	float64x2_t __ret;
40532	__ret = (float64x2_t)(__p0);	35448	__ret = (float64x2_t)(__p0);
40533	return __ret;	35449	return __ret;
40534	}	35450	}
40535	#endif
40536
40537	#ifdef __LITTLE_ENDIAN__
40538	__ai float64x2_t vreinterpretq_f64_s16(int16x8_t __p0) {
40539	float64x2_t __ret;
40540	__ret = (float64x2_t)(__p0);
40541	return __ret;
40542	}
40543	#else
40544	__ai float64x2_t vreinterpretq_f64_s16(int16x8_t __p0) {	35451	__ai float64x2_t vreinterpretq_f64_s16(int16x8_t __p0) {
40545	float64x2_t __ret;	35452	float64x2_t __ret;
40546	__ret = (float64x2_t)(__p0);	35453	__ret = (float64x2_t)(__p0);
40547	return __ret;	35454	return __ret;
40548	}	35455	}
40549	#endif
40550
40551	#ifdef __LITTLE_ENDIAN__
40552	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {
40553	float32x4_t __ret;
40554	__ret = (float32x4_t)(__p0);
40555	return __ret;
40556	}
40557	#else
40558	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {	35456	__ai float32x4_t vreinterpretq_f32_p8(poly8x16_t __p0) {
40559	float32x4_t __ret;	35457	float32x4_t __ret;
40560	__ret = (float32x4_t)(__p0);	35458	__ret = (float32x4_t)(__p0);
40561	return __ret;	35459	return __ret;
40562	}	35460	}
40563	#endif
40564
40565	#ifdef __LITTLE_ENDIAN__
40566	__ai float32x4_t vreinterpretq_f32_p128(poly128_t __p0) {
40567	float32x4_t __ret;
40568	__ret = (float32x4_t)(__p0);
40569	return __ret;
40570	}
40571	#else
40572	__ai float32x4_t vreinterpretq_f32_p128(poly128_t __p0) {	35461	__ai float32x4_t vreinterpretq_f32_p128(poly128_t __p0) {
40573	float32x4_t __ret;	35462	float32x4_t __ret;
40574	__ret = (float32x4_t)(__p0);	35463	__ret = (float32x4_t)(__p0);
40575	return __ret;	35464	return __ret;
40576	}	35465	}
40577	#endif
40578
40579	#ifdef __LITTLE_ENDIAN__
40580	__ai float32x4_t vreinterpretq_f32_p64(poly64x2_t __p0) {
40581	float32x4_t __ret;
40582	__ret = (float32x4_t)(__p0);
40583	return __ret;
40584	}
40585	#else
40586	__ai float32x4_t vreinterpretq_f32_p64(poly64x2_t __p0) {	35466	__ai float32x4_t vreinterpretq_f32_p64(poly64x2_t __p0) {
40587	float32x4_t __ret;	35467	float32x4_t __ret;
40588	__ret = (float32x4_t)(__p0);	35468	__ret = (float32x4_t)(__p0);
40589	return __ret;	35469	return __ret;
40590	}	35470	}
40591	#endif
40592
40593	#ifdef __LITTLE_ENDIAN__
40594	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {
40595	float32x4_t __ret;
40596	__ret = (float32x4_t)(__p0);
40597	return __ret;
40598	}
40599	#else
40600	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {	35471	__ai float32x4_t vreinterpretq_f32_p16(poly16x8_t __p0) {
40601	float32x4_t __ret;	35472	float32x4_t __ret;
40602	__ret = (float32x4_t)(__p0);	35473	__ret = (float32x4_t)(__p0);
40603	return __ret;	35474	return __ret;
40604	}	35475	}
40605	#endif
40606
40607	#ifdef __LITTLE_ENDIAN__
40608	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {
40609	float32x4_t __ret;
40610	__ret = (float32x4_t)(__p0);
40611	return __ret;
40612	}
40613	#else
40614	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {	35476	__ai float32x4_t vreinterpretq_f32_u8(uint8x16_t __p0) {
40615	float32x4_t __ret;	35477	float32x4_t __ret;
40616	__ret = (float32x4_t)(__p0);	35478	__ret = (float32x4_t)(__p0);
40617	return __ret;	35479	return __ret;
40618	}	35480	}
40619	#endif
40620
40621	#ifdef __LITTLE_ENDIAN__
40622	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {
40623	float32x4_t __ret;
40624	__ret = (float32x4_t)(__p0);
40625	return __ret;
40626	}
40627	#else
40628	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {	35481	__ai float32x4_t vreinterpretq_f32_u32(uint32x4_t __p0) {
40629	float32x4_t __ret;	35482	float32x4_t __ret;
40630	__ret = (float32x4_t)(__p0);	35483	__ret = (float32x4_t)(__p0);
40631	return __ret;	35484	return __ret;
40632	}	35485	}
40633	#endif
40634
40635	#ifdef __LITTLE_ENDIAN__
40636	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {
40637	float32x4_t __ret;
40638	__ret = (float32x4_t)(__p0);
40639	return __ret;
40640	}
40641	#else
40642	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {	35486	__ai float32x4_t vreinterpretq_f32_u64(uint64x2_t __p0) {
40643	float32x4_t __ret;	35487	float32x4_t __ret;
40644	__ret = (float32x4_t)(__p0);	35488	__ret = (float32x4_t)(__p0);
40645	return __ret;	35489	return __ret;
40646	}	35490	}
40647	#endif
40648
40649	#ifdef __LITTLE_ENDIAN__
40650	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {
40651	float32x4_t __ret;
40652	__ret = (float32x4_t)(__p0);
40653	return __ret;
40654	}
40655	#else
40656	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {	35491	__ai float32x4_t vreinterpretq_f32_u16(uint16x8_t __p0) {
40657	float32x4_t __ret;	35492	float32x4_t __ret;
40658	__ret = (float32x4_t)(__p0);	35493	__ret = (float32x4_t)(__p0);
40659	return __ret;	35494	return __ret;
40660	}	35495	}
40661	#endif
40662
40663	#ifdef __LITTLE_ENDIAN__
40664	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {
40665	float32x4_t __ret;
40666	__ret = (float32x4_t)(__p0);
40667	return __ret;
40668	}
40669	#else
40670	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {	35496	__ai float32x4_t vreinterpretq_f32_s8(int8x16_t __p0) {
40671	float32x4_t __ret;	35497	float32x4_t __ret;
40672	__ret = (float32x4_t)(__p0);	35498	__ret = (float32x4_t)(__p0);
40673	return __ret;	35499	return __ret;
40674	}	35500	}
40675	#endif
40676
40677	#ifdef __LITTLE_ENDIAN__
40678	__ai float32x4_t vreinterpretq_f32_f64(float64x2_t __p0) {
40679	float32x4_t __ret;
40680	__ret = (float32x4_t)(__p0);
40681	return __ret;
40682	}
40683	#else
40684	__ai float32x4_t vreinterpretq_f32_f64(float64x2_t __p0) {	35501	__ai float32x4_t vreinterpretq_f32_f64(float64x2_t __p0) {
40685	float32x4_t __ret;	35502	float32x4_t __ret;
40686	__ret = (float32x4_t)(__p0);	35503	__ret = (float32x4_t)(__p0);
40687	return __ret;	35504	return __ret;
40688	}	35505	}
40689	#endif
40690
40691	#ifdef __LITTLE_ENDIAN__
40692	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {
40693	float32x4_t __ret;
40694	__ret = (float32x4_t)(__p0);
40695	return __ret;
40696	}
40697	#else
40698	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {	35506	__ai float32x4_t vreinterpretq_f32_f16(float16x8_t __p0) {
40699	float32x4_t __ret;	35507	float32x4_t __ret;
40700	__ret = (float32x4_t)(__p0);	35508	__ret = (float32x4_t)(__p0);
40701	return __ret;	35509	return __ret;
40702	}	35510	}
40703	#endif
40704
40705	#ifdef __LITTLE_ENDIAN__
40706	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {
40707	float32x4_t __ret;
40708	__ret = (float32x4_t)(__p0);
40709	return __ret;
40710	}
40711	#else
40712	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {	35511	__ai float32x4_t vreinterpretq_f32_s32(int32x4_t __p0) {
40713	float32x4_t __ret;	35512	float32x4_t __ret;
40714	__ret = (float32x4_t)(__p0);	35513	__ret = (float32x4_t)(__p0);
40715	return __ret;	35514	return __ret;
40716	}	35515	}
40717	#endif
40718
40719	#ifdef __LITTLE_ENDIAN__
40720	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {
40721	float32x4_t __ret;
40722	__ret = (float32x4_t)(__p0);
40723	return __ret;
40724	}
40725	#else
40726	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {	35516	__ai float32x4_t vreinterpretq_f32_s64(int64x2_t __p0) {
40727	float32x4_t __ret;	35517	float32x4_t __ret;
40728	__ret = (float32x4_t)(__p0);	35518	__ret = (float32x4_t)(__p0);
40729	return __ret;	35519	return __ret;
40730	}	35520	}
40731	#endif
40732
40733	#ifdef __LITTLE_ENDIAN__
40734	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {
40735	float32x4_t __ret;
40736	__ret = (float32x4_t)(__p0);
40737	return __ret;
40738	}
40739	#else
40740	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {	35521	__ai float32x4_t vreinterpretq_f32_s16(int16x8_t __p0) {
40741	float32x4_t __ret;	35522	float32x4_t __ret;
40742	__ret = (float32x4_t)(__p0);	35523	__ret = (float32x4_t)(__p0);
40743	return __ret;	35524	return __ret;
40744	}	35525	}
40745	#endif
40746
40747	#ifdef __LITTLE_ENDIAN__
40748	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {
40749	float16x8_t __ret;
40750	__ret = (float16x8_t)(__p0);
40751	return __ret;
40752	}
40753	#else
40754	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {	35526	__ai float16x8_t vreinterpretq_f16_p8(poly8x16_t __p0) {
40755	float16x8_t __ret;	35527	float16x8_t __ret;
40756	__ret = (float16x8_t)(__p0);	35528	__ret = (float16x8_t)(__p0);
40757	return __ret;	35529	return __ret;
40758	}	35530	}
40759	#endif
40760
40761	#ifdef __LITTLE_ENDIAN__
40762	__ai float16x8_t vreinterpretq_f16_p128(poly128_t __p0) {
40763	float16x8_t __ret;
40764	__ret = (float16x8_t)(__p0);
40765	return __ret;
40766	}
40767	#else
40768	__ai float16x8_t vreinterpretq_f16_p128(poly128_t __p0) {	35531	__ai float16x8_t vreinterpretq_f16_p128(poly128_t __p0) {
40769	float16x8_t __ret;	35532	float16x8_t __ret;
40770	__ret = (float16x8_t)(__p0);	35533	__ret = (float16x8_t)(__p0);
40771	return __ret;	35534	return __ret;
40772	}	35535	}
40773	#endif
40774
40775	#ifdef __LITTLE_ENDIAN__
40776	__ai float16x8_t vreinterpretq_f16_p64(poly64x2_t __p0) {
40777	float16x8_t __ret;
40778	__ret = (float16x8_t)(__p0);
40779	return __ret;
40780	}
40781	#else
40782	__ai float16x8_t vreinterpretq_f16_p64(poly64x2_t __p0) {	35536	__ai float16x8_t vreinterpretq_f16_p64(poly64x2_t __p0) {
40783	float16x8_t __ret;	35537	float16x8_t __ret;
40784	__ret = (float16x8_t)(__p0);	35538	__ret = (float16x8_t)(__p0);
40785	return __ret;	35539	return __ret;
40786	}	35540	}
40787	#endif
40788
40789	#ifdef __LITTLE_ENDIAN__
40790	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {
40791	float16x8_t __ret;
40792	__ret = (float16x8_t)(__p0);
40793	return __ret;
40794	}
40795	#else
40796	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {	35541	__ai float16x8_t vreinterpretq_f16_p16(poly16x8_t __p0) {
40797	float16x8_t __ret;	35542	float16x8_t __ret;
40798	__ret = (float16x8_t)(__p0);	35543	__ret = (float16x8_t)(__p0);
40799	return __ret;	35544	return __ret;
40800	}	35545	}
40801	#endif
40802
40803	#ifdef __LITTLE_ENDIAN__
40804	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {
40805	float16x8_t __ret;
40806	__ret = (float16x8_t)(__p0);
40807	return __ret;
40808	}
40809	#else
40810	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {	35546	__ai float16x8_t vreinterpretq_f16_u8(uint8x16_t __p0) {
40811	float16x8_t __ret;	35547	float16x8_t __ret;
40812	__ret = (float16x8_t)(__p0);	35548	__ret = (float16x8_t)(__p0);
40813	return __ret;	35549	return __ret;
40814	}	35550	}
40815	#endif
40816
40817	#ifdef __LITTLE_ENDIAN__
40818	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {
40819	float16x8_t __ret;
40820	__ret = (float16x8_t)(__p0);
40821	return __ret;
40822	}
40823	#else
40824	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {	35551	__ai float16x8_t vreinterpretq_f16_u32(uint32x4_t __p0) {
40825	float16x8_t __ret;	35552	float16x8_t __ret;
40826	__ret = (float16x8_t)(__p0);	35553	__ret = (float16x8_t)(__p0);
40827	return __ret;	35554	return __ret;
40828	}	35555	}
40829	#endif
40830
40831	#ifdef __LITTLE_ENDIAN__
40832	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {
40833	float16x8_t __ret;
40834	__ret = (float16x8_t)(__p0);
40835	return __ret;
40836	}
40837	#else
40838	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {	35556	__ai float16x8_t vreinterpretq_f16_u64(uint64x2_t __p0) {
40839	float16x8_t __ret;	35557	float16x8_t __ret;
40840	__ret = (float16x8_t)(__p0);	35558	__ret = (float16x8_t)(__p0);
40841	return __ret;	35559	return __ret;
40842	}	35560	}
40843	#endif
40844
40845	#ifdef __LITTLE_ENDIAN__
40846	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {
40847	float16x8_t __ret;
40848	__ret = (float16x8_t)(__p0);
40849	return __ret;
40850	}
40851	#else
40852	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {	35561	__ai float16x8_t vreinterpretq_f16_u16(uint16x8_t __p0) {
40853	float16x8_t __ret;	35562	float16x8_t __ret;
40854	__ret = (float16x8_t)(__p0);	35563	__ret = (float16x8_t)(__p0);
40855	return __ret;	35564	return __ret;
40856	}	35565	}
40857	#endif
40858
40859	#ifdef __LITTLE_ENDIAN__
40860	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {
40861	float16x8_t __ret;
40862	__ret = (float16x8_t)(__p0);
40863	return __ret;
40864	}
40865	#else
40866	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {	35566	__ai float16x8_t vreinterpretq_f16_s8(int8x16_t __p0) {
40867	float16x8_t __ret;	35567	float16x8_t __ret;
40868	__ret = (float16x8_t)(__p0);	35568	__ret = (float16x8_t)(__p0);
40869	return __ret;	35569	return __ret;
40870	}	35570	}
40871	#endif
40872
40873	#ifdef __LITTLE_ENDIAN__
40874	__ai float16x8_t vreinterpretq_f16_f64(float64x2_t __p0) {
40875	float16x8_t __ret;
40876	__ret = (float16x8_t)(__p0);
40877	return __ret;
40878	}
40879	#else
40880	__ai float16x8_t vreinterpretq_f16_f64(float64x2_t __p0) {	35571	__ai float16x8_t vreinterpretq_f16_f64(float64x2_t __p0) {
40881	float16x8_t __ret;	35572	float16x8_t __ret;
40882	__ret = (float16x8_t)(__p0);	35573	__ret = (float16x8_t)(__p0);
40883	return __ret;	35574	return __ret;
40884	}	35575	}
40885	#endif
40886
40887	#ifdef __LITTLE_ENDIAN__
40888	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {
40889	float16x8_t __ret;
40890	__ret = (float16x8_t)(__p0);
40891	return __ret;
40892	}
40893	#else
40894	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {	35576	__ai float16x8_t vreinterpretq_f16_f32(float32x4_t __p0) {
40895	float16x8_t __ret;	35577	float16x8_t __ret;
40896	__ret = (float16x8_t)(__p0);	35578	__ret = (float16x8_t)(__p0);
40897	return __ret;	35579	return __ret;
40898	}	35580	}
40899	#endif
40900
40901	#ifdef __LITTLE_ENDIAN__
40902	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {
40903	float16x8_t __ret;
40904	__ret = (float16x8_t)(__p0);
40905	return __ret;
40906	}
40907	#else
40908	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {	35581	__ai float16x8_t vreinterpretq_f16_s32(int32x4_t __p0) {
40909	float16x8_t __ret;	35582	float16x8_t __ret;
40910	__ret = (float16x8_t)(__p0);	35583	__ret = (float16x8_t)(__p0);
40911	return __ret;	35584	return __ret;
40912	}	35585	}
40913	#endif
40914
40915	#ifdef __LITTLE_ENDIAN__
40916	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {
40917	float16x8_t __ret;
40918	__ret = (float16x8_t)(__p0);
40919	return __ret;
40920	}
40921	#else
40922	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {	35586	__ai float16x8_t vreinterpretq_f16_s64(int64x2_t __p0) {
40923	float16x8_t __ret;	35587	float16x8_t __ret;
40924	__ret = (float16x8_t)(__p0);	35588	__ret = (float16x8_t)(__p0);
40925	return __ret;	35589	return __ret;
40926	}	35590	}
40927	#endif
40928
40929	#ifdef __LITTLE_ENDIAN__
40930	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {
40931	float16x8_t __ret;
40932	__ret = (float16x8_t)(__p0);
40933	return __ret;
40934	}
40935	#else
40936	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {	35591	__ai float16x8_t vreinterpretq_f16_s16(int16x8_t __p0) {
40937	float16x8_t __ret;	35592	float16x8_t __ret;
40938	__ret = (float16x8_t)(__p0);	35593	__ret = (float16x8_t)(__p0);
40939	return __ret;	35594	return __ret;
40940	}	35595	}
40941	#endif
40942
40943	#ifdef __LITTLE_ENDIAN__
40944	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {	35596	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {
40945	int32x4_t __ret;	35597	int32x4_t __ret;
40946	__ret = (int32x4_t)(__p0);	35598	__ret = (int32x4_t)(__p0);
40947	return __ret;	35599	return __ret;
40948	}	35600	}
40949	#else	35601	__ai int32x4_t vreinterpretq_s32_p128(poly128_t __p0) {
40950	__ai int32x4_t vreinterpretq_s32_p8(poly8x16_t __p0) {
40951	int32x4_t __ret;	35602	int32x4_t __ret;
40952	__ret = (int32x4_t)(__p0);	35603	__ret = (int32x4_t)(__p0);
40953	return __ret;	35604	return __ret;
40954	}	35605	}
40955	#endif	35606	__ai int32x4_t vreinterpretq_s32_p64(poly64x2_t __p0) {
40956
40957	#ifdef __LITTLE_ENDIAN__
40958	__ai int32x4_t vreinterpretq_s32_p128(poly128_t __p0) {
40959	int32x4_t __ret;	35607	int32x4_t __ret;
40960	__ret = (int32x4_t)(__p0);	35608	__ret = (int32x4_t)(__p0);
40961	return __ret;	35609	return __ret;
40962	}	35610	}
40963	#else	35611	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {
40964	__ai int32x4_t vreinterpretq_s32_p128(poly128_t __p0) {
40965	int32x4_t __ret;	35612	int32x4_t __ret;
40966	__ret = (int32x4_t)(__p0);	35613	__ret = (int32x4_t)(__p0);
40967	return __ret;	35614	return __ret;
40968	}	35615	}
40969	#endif	35616	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {
40970
40971	#ifdef __LITTLE_ENDIAN__
40972	__ai int32x4_t vreinterpretq_s32_p64(poly64x2_t __p0) {
40973	int32x4_t __ret;	35617	int32x4_t __ret;
40974	__ret = (int32x4_t)(__p0);	35618	__ret = (int32x4_t)(__p0);
40975	return __ret;	35619	return __ret;
40976	}	35620	}
40977	#else	35621	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {
40978	__ai int32x4_t vreinterpretq_s32_p64(poly64x2_t __p0) {
40979	int32x4_t __ret;	35622	int32x4_t __ret;
40980	__ret = (int32x4_t)(__p0);	35623	__ret = (int32x4_t)(__p0);
40981	return __ret;	35624	return __ret;
40982	}	35625	}
40983	#endif	35626	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {
40984
40985	#ifdef __LITTLE_ENDIAN__
40986	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {
40987	int32x4_t __ret;	35627	int32x4_t __ret;
40988	__ret = (int32x4_t)(__p0);	35628	__ret = (int32x4_t)(__p0);
40989	return __ret;	35629	return __ret;
40990	}	35630	}
40991	#else
40992	__ai int32x4_t vreinterpretq_s32_p16(poly16x8_t __p0) {
40993	int32x4_t __ret;
40994	__ret = (int32x4_t)(__p0);
40995	return __ret;
40996	}
40997	#endif
40998
40999	#ifdef __LITTLE_ENDIAN__
41000	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {
41001	int32x4_t __ret;
41002	__ret = (int32x4_t)(__p0);
41003	return __ret;
41004	}
41005	#else
41006	__ai int32x4_t vreinterpretq_s32_u8(uint8x16_t __p0) {
41007	int32x4_t __ret;
41008	__ret = (int32x4_t)(__p0);
41009	return __ret;
41010	}
41011	#endif
41012
41013	#ifdef __LITTLE_ENDIAN__
41014	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {
41015	int32x4_t __ret;
41016	__ret = (int32x4_t)(__p0);
41017	return __ret;
41018	}
41019	#else
41020	__ai int32x4_t vreinterpretq_s32_u32(uint32x4_t __p0) {
41021	int32x4_t __ret;
41022	__ret = (int32x4_t)(__p0);
41023	return __ret;
41024	}
41025	#endif
41026
41027	#ifdef __LITTLE_ENDIAN__
41028	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {
41029	int32x4_t __ret;
41030	__ret = (int32x4_t)(__p0);
41031	return __ret;
41032	}
41033	#else
41034	__ai int32x4_t vreinterpretq_s32_u64(uint64x2_t __p0) {
41035	int32x4_t __ret;
41036	__ret = (int32x4_t)(__p0);
41037	return __ret;
41038	}
41039	#endif
41040
41041	#ifdef __LITTLE_ENDIAN__
41042	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {
41043	int32x4_t __ret;
41044	__ret = (int32x4_t)(__p0);
41045	return __ret;
41046	}
41047	#else
41048	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {	35631	__ai int32x4_t vreinterpretq_s32_u16(uint16x8_t __p0) {
41049	int32x4_t __ret;	35632	int32x4_t __ret;
41050	__ret = (int32x4_t)(__p0);	35633	__ret = (int32x4_t)(__p0);
41051	return __ret;	35634	return __ret;
41052	}	35635	}
41053	#endif
41054
41055	#ifdef __LITTLE_ENDIAN__
41056	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {
41057	int32x4_t __ret;
41058	__ret = (int32x4_t)(__p0);
41059	return __ret;
41060	}
41061	#else
41062	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {	35636	__ai int32x4_t vreinterpretq_s32_s8(int8x16_t __p0) {
41063	int32x4_t __ret;	35637	int32x4_t __ret;
41064	__ret = (int32x4_t)(__p0);	35638	__ret = (int32x4_t)(__p0);
41065	return __ret;	35639	return __ret;
41066	}	35640	}
41067	#endif
41068
41069	#ifdef __LITTLE_ENDIAN__
41070	__ai int32x4_t vreinterpretq_s32_f64(float64x2_t __p0) {
41071	int32x4_t __ret;
41072	__ret = (int32x4_t)(__p0);
41073	return __ret;
41074	}
41075	#else
41076	__ai int32x4_t vreinterpretq_s32_f64(float64x2_t __p0) {	35641	__ai int32x4_t vreinterpretq_s32_f64(float64x2_t __p0) {
41077	int32x4_t __ret;	35642	int32x4_t __ret;
41078	__ret = (int32x4_t)(__p0);	35643	__ret = (int32x4_t)(__p0);
41079	return __ret;	35644	return __ret;
41080	}	35645	}
41081	#endif
41082
41083	#ifdef __LITTLE_ENDIAN__
41084	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {
41085	int32x4_t __ret;
41086	__ret = (int32x4_t)(__p0);
41087	return __ret;
41088	}
41089	#else
41090	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {	35646	__ai int32x4_t vreinterpretq_s32_f32(float32x4_t __p0) {
41091	int32x4_t __ret;	35647	int32x4_t __ret;
41092	__ret = (int32x4_t)(__p0);	35648	__ret = (int32x4_t)(__p0);
41093	return __ret;	35649	return __ret;
41094	}	35650	}
41095	#endif
41096
41097	#ifdef __LITTLE_ENDIAN__
41098	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {
41099	int32x4_t __ret;
41100	__ret = (int32x4_t)(__p0);
41101	return __ret;
41102	}
41103	#else
41104	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {	35651	__ai int32x4_t vreinterpretq_s32_f16(float16x8_t __p0) {
41105	int32x4_t __ret;	35652	int32x4_t __ret;
41106	__ret = (int32x4_t)(__p0);	35653	__ret = (int32x4_t)(__p0);
41107	return __ret;	35654	return __ret;
41108	}	35655	}
41109	#endif
41110
41111	#ifdef __LITTLE_ENDIAN__
41112	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {
41113	int32x4_t __ret;
41114	__ret = (int32x4_t)(__p0);
41115	return __ret;
41116	}
41117	#else
41118	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {	35656	__ai int32x4_t vreinterpretq_s32_s64(int64x2_t __p0) {
41119	int32x4_t __ret;	35657	int32x4_t __ret;
41120	__ret = (int32x4_t)(__p0);	35658	__ret = (int32x4_t)(__p0);
41121	return __ret;	35659	return __ret;
41122	}	35660	}
41123	#endif
41124
41125	#ifdef __LITTLE_ENDIAN__
41126	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {
41127	int32x4_t __ret;
41128	__ret = (int32x4_t)(__p0);
41129	return __ret;
41130	}
41131	#else
41132	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {	35661	__ai int32x4_t vreinterpretq_s32_s16(int16x8_t __p0) {
41133	int32x4_t __ret;	35662	int32x4_t __ret;
41134	__ret = (int32x4_t)(__p0);	35663	__ret = (int32x4_t)(__p0);
41135	return __ret;	35664	return __ret;
41136	}	35665	}
41137	#endif
41138
41139	#ifdef __LITTLE_ENDIAN__
41140	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {
41141	int64x2_t __ret;
41142	__ret = (int64x2_t)(__p0);
41143	return __ret;
41144	}
41145	#else
41146	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {	35666	__ai int64x2_t vreinterpretq_s64_p8(poly8x16_t __p0) {
41147	int64x2_t __ret;	35667	int64x2_t __ret;
41148	__ret = (int64x2_t)(__p0);	35668	__ret = (int64x2_t)(__p0);
41149	return __ret;	35669	return __ret;
41150	}	35670	}
41151	#endif
41152
41153	#ifdef __LITTLE_ENDIAN__
41154	__ai int64x2_t vreinterpretq_s64_p128(poly128_t __p0) {
41155	int64x2_t __ret;
41156	__ret = (int64x2_t)(__p0);
41157	return __ret;
41158	}
41159	#else
41160	__ai int64x2_t vreinterpretq_s64_p128(poly128_t __p0) {	35671	__ai int64x2_t vreinterpretq_s64_p128(poly128_t __p0) {
41161	int64x2_t __ret;	35672	int64x2_t __ret;
41162	__ret = (int64x2_t)(__p0);	35673	__ret = (int64x2_t)(__p0);
41163	return __ret;	35674	return __ret;
41164	}	35675	}
41165	#endif
41166
41167	#ifdef __LITTLE_ENDIAN__
41168	__ai int64x2_t vreinterpretq_s64_p64(poly64x2_t __p0) {
41169	int64x2_t __ret;
41170	__ret = (int64x2_t)(__p0);
41171	return __ret;
41172	}
41173	#else
41174	__ai int64x2_t vreinterpretq_s64_p64(poly64x2_t __p0) {	35676	__ai int64x2_t vreinterpretq_s64_p64(poly64x2_t __p0) {
41175	int64x2_t __ret;	35677	int64x2_t __ret;
41176	__ret = (int64x2_t)(__p0);	35678	__ret = (int64x2_t)(__p0);
41177	return __ret;	35679	return __ret;
41178	}	35680	}
41179	#endif
41180
41181	#ifdef __LITTLE_ENDIAN__
41182	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {
41183	int64x2_t __ret;
41184	__ret = (int64x2_t)(__p0);
41185	return __ret;
41186	}
41187	#else
41188	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {	35681	__ai int64x2_t vreinterpretq_s64_p16(poly16x8_t __p0) {
41189	int64x2_t __ret;	35682	int64x2_t __ret;
41190	__ret = (int64x2_t)(__p0);	35683	__ret = (int64x2_t)(__p0);
41191	return __ret;	35684	return __ret;
41192	}	35685	}
41193	#endif
41194
41195	#ifdef __LITTLE_ENDIAN__
41196	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {
41197	int64x2_t __ret;
41198	__ret = (int64x2_t)(__p0);
41199	return __ret;
41200	}
41201	#else
41202	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {	35686	__ai int64x2_t vreinterpretq_s64_u8(uint8x16_t __p0) {
41203	int64x2_t __ret;	35687	int64x2_t __ret;
41204	__ret = (int64x2_t)(__p0);	35688	__ret = (int64x2_t)(__p0);
41205	return __ret;	35689	return __ret;
41206	}	35690	}
41207	#endif
41208
41209	#ifdef __LITTLE_ENDIAN__
41210	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {
41211	int64x2_t __ret;
41212	__ret = (int64x2_t)(__p0);
41213	return __ret;
41214	}
41215	#else
41216	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {	35691	__ai int64x2_t vreinterpretq_s64_u32(uint32x4_t __p0) {
41217	int64x2_t __ret;	35692	int64x2_t __ret;
41218	__ret = (int64x2_t)(__p0);	35693	__ret = (int64x2_t)(__p0);
41219	return __ret;	35694	return __ret;
41220	}	35695	}
41221	#endif
41222
41223	#ifdef __LITTLE_ENDIAN__
41224	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {
41225	int64x2_t __ret;
41226	__ret = (int64x2_t)(__p0);
41227	return __ret;
41228	}
41229	#else
41230	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {	35696	__ai int64x2_t vreinterpretq_s64_u64(uint64x2_t __p0) {
41231	int64x2_t __ret;	35697	int64x2_t __ret;
41232	__ret = (int64x2_t)(__p0);	35698	__ret = (int64x2_t)(__p0);
41233	return __ret;	35699	return __ret;
41234	}	35700	}
41235	#endif
41236
41237	#ifdef __LITTLE_ENDIAN__
41238	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {
41239	int64x2_t __ret;
41240	__ret = (int64x2_t)(__p0);
41241	return __ret;
41242	}
41243	#else
41244	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {	35701	__ai int64x2_t vreinterpretq_s64_u16(uint16x8_t __p0) {
41245	int64x2_t __ret;	35702	int64x2_t __ret;
41246	__ret = (int64x2_t)(__p0);	35703	__ret = (int64x2_t)(__p0);
41247	return __ret;	35704	return __ret;
41248	}	35705	}
41249	#endif
41250
41251	#ifdef __LITTLE_ENDIAN__
41252	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {
41253	int64x2_t __ret;
41254	__ret = (int64x2_t)(__p0);
41255	return __ret;
41256	}
41257	#else
41258	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {	35706	__ai int64x2_t vreinterpretq_s64_s8(int8x16_t __p0) {
41259	int64x2_t __ret;	35707	int64x2_t __ret;
41260	__ret = (int64x2_t)(__p0);	35708	__ret = (int64x2_t)(__p0);
41261	return __ret;	35709	return __ret;
41262	}	35710	}
41263	#endif
41264
41265	#ifdef __LITTLE_ENDIAN__
41266	__ai int64x2_t vreinterpretq_s64_f64(float64x2_t __p0) {
41267	int64x2_t __ret;
41268	__ret = (int64x2_t)(__p0);
41269	return __ret;
41270	}
41271	#else
41272	__ai int64x2_t vreinterpretq_s64_f64(float64x2_t __p0) {	35711	__ai int64x2_t vreinterpretq_s64_f64(float64x2_t __p0) {
41273	int64x2_t __ret;	35712	int64x2_t __ret;
41274	__ret = (int64x2_t)(__p0);	35713	__ret = (int64x2_t)(__p0);
41275	return __ret;	35714	return __ret;
41276	}	35715	}
41277	#endif
41278
41279	#ifdef __LITTLE_ENDIAN__
41280	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {
41281	int64x2_t __ret;
41282	__ret = (int64x2_t)(__p0);
41283	return __ret;
41284	}
41285	#else
41286	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {	35716	__ai int64x2_t vreinterpretq_s64_f32(float32x4_t __p0) {
41287	int64x2_t __ret;	35717	int64x2_t __ret;
41288	__ret = (int64x2_t)(__p0);	35718	__ret = (int64x2_t)(__p0);
41289	return __ret;	35719	return __ret;
41290	}	35720	}
41291	#endif
41292
41293	#ifdef __LITTLE_ENDIAN__
41294	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {
41295	int64x2_t __ret;
41296	__ret = (int64x2_t)(__p0);
41297	return __ret;
41298	}
41299	#else
41300	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {	35721	__ai int64x2_t vreinterpretq_s64_f16(float16x8_t __p0) {
41301	int64x2_t __ret;	35722	int64x2_t __ret;
41302	__ret = (int64x2_t)(__p0);	35723	__ret = (int64x2_t)(__p0);
41303	return __ret;	35724	return __ret;
41304	}	35725	}
41305	#endif
41306
41307	#ifdef __LITTLE_ENDIAN__
41308	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {
41309	int64x2_t __ret;
41310	__ret = (int64x2_t)(__p0);
41311	return __ret;
41312	}
41313	#else
41314	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {	35726	__ai int64x2_t vreinterpretq_s64_s32(int32x4_t __p0) {
41315	int64x2_t __ret;	35727	int64x2_t __ret;
41316	__ret = (int64x2_t)(__p0);	35728	__ret = (int64x2_t)(__p0);
41317	return __ret;	35729	return __ret;
41318	}	35730	}
41319	#endif
41320
41321	#ifdef __LITTLE_ENDIAN__
41322	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {
41323	int64x2_t __ret;
41324	__ret = (int64x2_t)(__p0);
41325	return __ret;
41326	}
41327	#else
41328	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {	35731	__ai int64x2_t vreinterpretq_s64_s16(int16x8_t __p0) {
41329	int64x2_t __ret;	35732	int64x2_t __ret;
41330	__ret = (int64x2_t)(__p0);	35733	__ret = (int64x2_t)(__p0);
41331	return __ret;	35734	return __ret;
41332	}	35735	}
41333	#endif
41334
41335	#ifdef __LITTLE_ENDIAN__
41336	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {
41337	int16x8_t __ret;
41338	__ret = (int16x8_t)(__p0);
41339	return __ret;
41340	}
41341	#else
41342	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {	35736	__ai int16x8_t vreinterpretq_s16_p8(poly8x16_t __p0) {
41343	int16x8_t __ret;	35737	int16x8_t __ret;
41344	__ret = (int16x8_t)(__p0);	35738	__ret = (int16x8_t)(__p0);
41345	return __ret;	35739	return __ret;
41346	}	35740	}
41347	#endif
41348
41349	#ifdef __LITTLE_ENDIAN__
41350	__ai int16x8_t vreinterpretq_s16_p128(poly128_t __p0) {
41351	int16x8_t __ret;
41352	__ret = (int16x8_t)(__p0);
41353	return __ret;
41354	}
41355	#else
41356	__ai int16x8_t vreinterpretq_s16_p128(poly128_t __p0) {	35741	__ai int16x8_t vreinterpretq_s16_p128(poly128_t __p0) {
41357	int16x8_t __ret;	35742	int16x8_t __ret;
41358	__ret = (int16x8_t)(__p0);	35743	__ret = (int16x8_t)(__p0);
41359	return __ret;	35744	return __ret;
41360	}	35745	}
41361	#endif
41362
41363	#ifdef __LITTLE_ENDIAN__
41364	__ai int16x8_t vreinterpretq_s16_p64(poly64x2_t __p0) {
41365	int16x8_t __ret;
41366	__ret = (int16x8_t)(__p0);
41367	return __ret;
41368	}
41369	#else
41370	__ai int16x8_t vreinterpretq_s16_p64(poly64x2_t __p0) {	35746	__ai int16x8_t vreinterpretq_s16_p64(poly64x2_t __p0) {
41371	int16x8_t __ret;	35747	int16x8_t __ret;
41372	__ret = (int16x8_t)(__p0);	35748	__ret = (int16x8_t)(__p0);
41373	return __ret;	35749	return __ret;
41374	}	35750	}
41375	#endif
41376
41377	#ifdef __LITTLE_ENDIAN__
41378	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {
41379	int16x8_t __ret;
41380	__ret = (int16x8_t)(__p0);
41381	return __ret;
41382	}
41383	#else
41384	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {	35751	__ai int16x8_t vreinterpretq_s16_p16(poly16x8_t __p0) {
41385	int16x8_t __ret;	35752	int16x8_t __ret;
41386	__ret = (int16x8_t)(__p0);	35753	__ret = (int16x8_t)(__p0);
41387	return __ret;	35754	return __ret;
41388	}	35755	}
41389	#endif
41390
41391	#ifdef __LITTLE_ENDIAN__
41392	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {
41393	int16x8_t __ret;
41394	__ret = (int16x8_t)(__p0);
41395	return __ret;
41396	}
41397	#else
41398	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {	35756	__ai int16x8_t vreinterpretq_s16_u8(uint8x16_t __p0) {
41399	int16x8_t __ret;	35757	int16x8_t __ret;
41400	__ret = (int16x8_t)(__p0);	35758	__ret = (int16x8_t)(__p0);
41401	return __ret;	35759	return __ret;
41402	}	35760	}
41403	#endif
41404
41405	#ifdef __LITTLE_ENDIAN__
41406	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {
41407	int16x8_t __ret;
41408	__ret = (int16x8_t)(__p0);
41409	return __ret;
41410	}
41411	#else
41412	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {	35761	__ai int16x8_t vreinterpretq_s16_u32(uint32x4_t __p0) {
41413	int16x8_t __ret;	35762	int16x8_t __ret;
41414	__ret = (int16x8_t)(__p0);	35763	__ret = (int16x8_t)(__p0);
41415	return __ret;	35764	return __ret;
41416	}	35765	}
41417	#endif
41418
41419	#ifdef __LITTLE_ENDIAN__
41420	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {
41421	int16x8_t __ret;
41422	__ret = (int16x8_t)(__p0);
41423	return __ret;
41424	}
41425	#else
41426	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {	35766	__ai int16x8_t vreinterpretq_s16_u64(uint64x2_t __p0) {
41427	int16x8_t __ret;	35767	int16x8_t __ret;
41428	__ret = (int16x8_t)(__p0);	35768	__ret = (int16x8_t)(__p0);
41429	return __ret;	35769	return __ret;
41430	}	35770	}
41431	#endif
41432
41433	#ifdef __LITTLE_ENDIAN__
41434	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {
41435	int16x8_t __ret;
41436	__ret = (int16x8_t)(__p0);
41437	return __ret;
41438	}
41439	#else
41440	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {	35771	__ai int16x8_t vreinterpretq_s16_u16(uint16x8_t __p0) {
41441	int16x8_t __ret;	35772	int16x8_t __ret;
41442	__ret = (int16x8_t)(__p0);	35773	__ret = (int16x8_t)(__p0);
41443	return __ret;	35774	return __ret;
41444	}	35775	}
41445	#endif
41446
41447	#ifdef __LITTLE_ENDIAN__
41448	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {
41449	int16x8_t __ret;
41450	__ret = (int16x8_t)(__p0);
41451	return __ret;
41452	}
41453	#else
41454	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {	35776	__ai int16x8_t vreinterpretq_s16_s8(int8x16_t __p0) {
41455	int16x8_t __ret;	35777	int16x8_t __ret;
41456	__ret = (int16x8_t)(__p0);	35778	__ret = (int16x8_t)(__p0);
41457	return __ret;	35779	return __ret;
41458	}	35780	}
41459	#endif
41460
41461	#ifdef __LITTLE_ENDIAN__
41462	__ai int16x8_t vreinterpretq_s16_f64(float64x2_t __p0) {
41463	int16x8_t __ret;
41464	__ret = (int16x8_t)(__p0);
41465	return __ret;
41466	}
41467	#else
41468	__ai int16x8_t vreinterpretq_s16_f64(float64x2_t __p0) {	35781	__ai int16x8_t vreinterpretq_s16_f64(float64x2_t __p0) {
41469	int16x8_t __ret;	35782	int16x8_t __ret;
41470	__ret = (int16x8_t)(__p0);	35783	__ret = (int16x8_t)(__p0);
41471	return __ret;	35784	return __ret;
41472	}	35785	}
41473	#endif
41474
41475	#ifdef __LITTLE_ENDIAN__
41476	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {
41477	int16x8_t __ret;
41478	__ret = (int16x8_t)(__p0);
41479	return __ret;
41480	}
41481	#else
41482	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {	35786	__ai int16x8_t vreinterpretq_s16_f32(float32x4_t __p0) {
41483	int16x8_t __ret;	35787	int16x8_t __ret;
41484	__ret = (int16x8_t)(__p0);	35788	__ret = (int16x8_t)(__p0);
41485	return __ret;	35789	return __ret;
41486	}	35790	}
41487	#endif
41488
41489	#ifdef __LITTLE_ENDIAN__
41490	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {
41491	int16x8_t __ret;
41492	__ret = (int16x8_t)(__p0);
41493	return __ret;
41494	}
41495	#else
41496	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {	35791	__ai int16x8_t vreinterpretq_s16_f16(float16x8_t __p0) {
41497	int16x8_t __ret;	35792	int16x8_t __ret;
41498	__ret = (int16x8_t)(__p0);	35793	__ret = (int16x8_t)(__p0);
41499	return __ret;	35794	return __ret;
41500	}	35795	}
41501	#endif
41502
41503	#ifdef __LITTLE_ENDIAN__
41504	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {
41505	int16x8_t __ret;
41506	__ret = (int16x8_t)(__p0);
41507	return __ret;
41508	}
41509	#else
41510	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {	35796	__ai int16x8_t vreinterpretq_s16_s32(int32x4_t __p0) {
41511	int16x8_t __ret;	35797	int16x8_t __ret;
41512	__ret = (int16x8_t)(__p0);	35798	__ret = (int16x8_t)(__p0);
41513	return __ret;	35799	return __ret;
41514	}	35800	}
41515	#endif
41516
41517	#ifdef __LITTLE_ENDIAN__
41518	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {
41519	int16x8_t __ret;
41520	__ret = (int16x8_t)(__p0);
41521	return __ret;
41522	}
41523	#else
41524	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {	35801	__ai int16x8_t vreinterpretq_s16_s64(int64x2_t __p0) {
41525	int16x8_t __ret;	35802	int16x8_t __ret;
41526	__ret = (int16x8_t)(__p0);	35803	__ret = (int16x8_t)(__p0);
41527	return __ret;	35804	return __ret;
41528	}	35805	}
41529	#endif
41530
41531	#ifdef __LITTLE_ENDIAN__
41532	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {
41533	uint8x8_t __ret;
41534	__ret = (uint8x8_t)(__p0);
41535	return __ret;
41536	}
41537	#else
41538	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {	35806	__ai uint8x8_t vreinterpret_u8_p8(poly8x8_t __p0) {
41539	uint8x8_t __ret;	35807	uint8x8_t __ret;
41540	__ret = (uint8x8_t)(__p0);	35808	__ret = (uint8x8_t)(__p0);
41541	return __ret;	35809	return __ret;
41542	}	35810	}
41543	#endif
41544
41545	#ifdef __LITTLE_ENDIAN__
41546	__ai uint8x8_t vreinterpret_u8_p64(poly64x1_t __p0) {
41547	uint8x8_t __ret;
41548	__ret = (uint8x8_t)(__p0);
41549	return __ret;
41550	}
41551	#else
41552	__ai uint8x8_t vreinterpret_u8_p64(poly64x1_t __p0) {	35811	__ai uint8x8_t vreinterpret_u8_p64(poly64x1_t __p0) {
41553	uint8x8_t __ret;	35812	uint8x8_t __ret;
41554	__ret = (uint8x8_t)(__p0);	35813	__ret = (uint8x8_t)(__p0);
41555	return __ret;	35814	return __ret;
41556	}	35815	}
41557	#endif
41558
41559	#ifdef __LITTLE_ENDIAN__
41560	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {
41561	uint8x8_t __ret;
41562	__ret = (uint8x8_t)(__p0);
41563	return __ret;
41564	}
41565	#else
41566	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {	35816	__ai uint8x8_t vreinterpret_u8_p16(poly16x4_t __p0) {
41567	uint8x8_t __ret;	35817	uint8x8_t __ret;
41568	__ret = (uint8x8_t)(__p0);	35818	__ret = (uint8x8_t)(__p0);
41569	return __ret;	35819	return __ret;
41570	}	35820	}
41571	#endif
41572
41573	#ifdef __LITTLE_ENDIAN__
41574	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {
41575	uint8x8_t __ret;
41576	__ret = (uint8x8_t)(__p0);
41577	return __ret;
41578	}
41579	#else
41580	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {	35821	__ai uint8x8_t vreinterpret_u8_u32(uint32x2_t __p0) {
41581	uint8x8_t __ret;	35822	uint8x8_t __ret;
41582	__ret = (uint8x8_t)(__p0);	35823	__ret = (uint8x8_t)(__p0);
41583	return __ret;	35824	return __ret;
41584	}	35825	}
41585	#endif
41586
41587	#ifdef __LITTLE_ENDIAN__
41588	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {
41589	uint8x8_t __ret;
41590	__ret = (uint8x8_t)(__p0);
41591	return __ret;
41592	}
41593	#else
41594	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {	35826	__ai uint8x8_t vreinterpret_u8_u64(uint64x1_t __p0) {
41595	uint8x8_t __ret;	35827	uint8x8_t __ret;
41596	__ret = (uint8x8_t)(__p0);	35828	__ret = (uint8x8_t)(__p0);
41597	return __ret;	35829	return __ret;
41598	}	35830	}
41599	#endif
41600
41601	#ifdef __LITTLE_ENDIAN__
41602	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {
41603	uint8x8_t __ret;
41604	__ret = (uint8x8_t)(__p0);
41605	return __ret;
41606	}
41607	#else
41608	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {	35831	__ai uint8x8_t vreinterpret_u8_u16(uint16x4_t __p0) {
41609	uint8x8_t __ret;	35832	uint8x8_t __ret;
41610	__ret = (uint8x8_t)(__p0);	35833	__ret = (uint8x8_t)(__p0);
41611	return __ret;	35834	return __ret;
41612	}	35835	}
41613	#endif
41614
41615	#ifdef __LITTLE_ENDIAN__
41616	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
41617	uint8x8_t __ret;
41618	__ret = (uint8x8_t)(__p0);
41619	return __ret;
41620	}
41621	#else
41622	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {	35836	__ai uint8x8_t vreinterpret_u8_s8(int8x8_t __p0) {
41623	uint8x8_t __ret;	35837	uint8x8_t __ret;
41624	__ret = (uint8x8_t)(__p0);	35838	__ret = (uint8x8_t)(__p0);
41625	return __ret;	35839	return __ret;
41626	}	35840	}
41627	#endif
41628
41629	#ifdef __LITTLE_ENDIAN__
41630	__ai uint8x8_t vreinterpret_u8_f64(float64x1_t __p0) {
41631	uint8x8_t __ret;
41632	__ret = (uint8x8_t)(__p0);
41633	return __ret;
41634	}
41635	#else
41636	__ai uint8x8_t vreinterpret_u8_f64(float64x1_t __p0) {	35841	__ai uint8x8_t vreinterpret_u8_f64(float64x1_t __p0) {
41637	uint8x8_t __ret;	35842	uint8x8_t __ret;
41638	__ret = (uint8x8_t)(__p0);	35843	__ret = (uint8x8_t)(__p0);
41639	return __ret;	35844	return __ret;
41640	}	35845	}
41641	#endif
41642
41643	#ifdef __LITTLE_ENDIAN__
41644	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {
41645	uint8x8_t __ret;
41646	__ret = (uint8x8_t)(__p0);
41647	return __ret;
41648	}
41649	#else
41650	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {	35846	__ai uint8x8_t vreinterpret_u8_f32(float32x2_t __p0) {
41651	uint8x8_t __ret;	35847	uint8x8_t __ret;
41652	__ret = (uint8x8_t)(__p0);	35848	__ret = (uint8x8_t)(__p0);
41653	return __ret;	35849	return __ret;
41654	}	35850	}
41655	#endif
41656
41657	#ifdef __LITTLE_ENDIAN__
41658	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {
41659	uint8x8_t __ret;
41660	__ret = (uint8x8_t)(__p0);
41661	return __ret;
41662	}
41663	#else
41664	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {	35851	__ai uint8x8_t vreinterpret_u8_f16(float16x4_t __p0) {
41665	uint8x8_t __ret;	35852	uint8x8_t __ret;
41666	__ret = (uint8x8_t)(__p0);	35853	__ret = (uint8x8_t)(__p0);
41667	return __ret;	35854	return __ret;
41668	}	35855	}
41669	#endif
41670
41671	#ifdef __LITTLE_ENDIAN__
41672	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {
41673	uint8x8_t __ret;
41674	__ret = (uint8x8_t)(__p0);
41675	return __ret;
41676	}
41677	#else
41678	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {	35856	__ai uint8x8_t vreinterpret_u8_s32(int32x2_t __p0) {
41679	uint8x8_t __ret;	35857	uint8x8_t __ret;
41680	__ret = (uint8x8_t)(__p0);	35858	__ret = (uint8x8_t)(__p0);
41681	return __ret;	35859	return __ret;
41682	}	35860	}
41683	#endif
41684
41685	#ifdef __LITTLE_ENDIAN__
41686	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {
41687	uint8x8_t __ret;
41688	__ret = (uint8x8_t)(__p0);
41689	return __ret;
41690	}
41691	#else
41692	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {	35861	__ai uint8x8_t vreinterpret_u8_s64(int64x1_t __p0) {
41693	uint8x8_t __ret;	35862	uint8x8_t __ret;
41694	__ret = (uint8x8_t)(__p0);	35863	__ret = (uint8x8_t)(__p0);
41695	return __ret;	35864	return __ret;
41696	}	35865	}
41697	#endif
41698
41699	#ifdef __LITTLE_ENDIAN__
41700	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {	35866	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {
41701	uint8x8_t __ret;	35867	uint8x8_t __ret;
41702	__ret = (uint8x8_t)(__p0);	35868	__ret = (uint8x8_t)(__p0);
41703	return __ret;	35869	return __ret;
41704	}	35870	}
41705	#else	35871	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {
41706	__ai uint8x8_t vreinterpret_u8_s16(int16x4_t __p0) {	35872	uint32x2_t __ret;
41707	uint8x8_t __ret;	35873	__ret = (uint32x2_t)(__p0);
41708	__ret = (uint8x8_t)(__p0);
41709	return __ret;	35874	return __ret;
41710	}	35875	}
41711	#endif	35876	__ai uint32x2_t vreinterpret_u32_p64(poly64x1_t __p0) {
41712
41713	#ifdef __LITTLE_ENDIAN__
41714	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {
41715	uint32x2_t __ret;	35877	uint32x2_t __ret;
41716	__ret = (uint32x2_t)(__p0);	35878	__ret = (uint32x2_t)(__p0);
41717	return __ret;	35879	return __ret;
41718	}	35880	}
41719	#else	35881	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {
41720	__ai uint32x2_t vreinterpret_u32_p8(poly8x8_t __p0) {
41721	uint32x2_t __ret;	35882	uint32x2_t __ret;
41722	__ret = (uint32x2_t)(__p0);	35883	__ret = (uint32x2_t)(__p0);
41723	return __ret;	35884	return __ret;
41724	}	35885	}
41725	#endif	35886	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {
41726
41727	#ifdef __LITTLE_ENDIAN__
41728	__ai uint32x2_t vreinterpret_u32_p64(poly64x1_t __p0) {
41729	uint32x2_t __ret;	35887	uint32x2_t __ret;
41730	__ret = (uint32x2_t)(__p0);	35888	__ret = (uint32x2_t)(__p0);
41731	return __ret;	35889	return __ret;
41732	}	35890	}
41733	#else	35891	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {
41734	__ai uint32x2_t vreinterpret_u32_p64(poly64x1_t __p0) {
41735	uint32x2_t __ret;	35892	uint32x2_t __ret;
41736	__ret = (uint32x2_t)(__p0);	35893	__ret = (uint32x2_t)(__p0);
41737	return __ret;	35894	return __ret;
41738	}	35895	}
41739	#endif	35896	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {
41740
41741	#ifdef __LITTLE_ENDIAN__
41742	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {
41743	uint32x2_t __ret;	35897	uint32x2_t __ret;
41744	__ret = (uint32x2_t)(__p0);	35898	__ret = (uint32x2_t)(__p0);
41745	return __ret;	35899	return __ret;
41746	}	35900	}
41747	#else	35901	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
41748	__ai uint32x2_t vreinterpret_u32_p16(poly16x4_t __p0) {
41749	uint32x2_t __ret;	35902	uint32x2_t __ret;
41750	__ret = (uint32x2_t)(__p0);	35903	__ret = (uint32x2_t)(__p0);
41751	return __ret;	35904	return __ret;
41752	}	35905	}
41753	#endif	35906	__ai uint32x2_t vreinterpret_u32_f64(float64x1_t __p0) {
41754
41755	#ifdef __LITTLE_ENDIAN__
41756	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {
41757	uint32x2_t __ret;	35907	uint32x2_t __ret;
41758	__ret = (uint32x2_t)(__p0);	35908	__ret = (uint32x2_t)(__p0);
41759	return __ret;	35909	return __ret;
41760	}	35910	}
41761	#else	35911	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {
41762	__ai uint32x2_t vreinterpret_u32_u8(uint8x8_t __p0) {
41763	uint32x2_t __ret;	35912	uint32x2_t __ret;
41764	__ret = (uint32x2_t)(__p0);	35913	__ret = (uint32x2_t)(__p0);
41765	return __ret;	35914	return __ret;
41766	}	35915	}
41767	#endif
41768
41769	#ifdef __LITTLE_ENDIAN__
41770	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {
41771	uint32x2_t __ret;
41772	__ret = (uint32x2_t)(__p0);
41773	return __ret;
41774	}
41775	#else
41776	__ai uint32x2_t vreinterpret_u32_u64(uint64x1_t __p0) {
41777	uint32x2_t __ret;
41778	__ret = (uint32x2_t)(__p0);
41779	return __ret;
41780	}
41781	#endif
41782
41783	#ifdef __LITTLE_ENDIAN__
41784	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {
41785	uint32x2_t __ret;
41786	__ret = (uint32x2_t)(__p0);
41787	return __ret;
41788	}
41789	#else
41790	__ai uint32x2_t vreinterpret_u32_u16(uint16x4_t __p0) {
41791	uint32x2_t __ret;
41792	__ret = (uint32x2_t)(__p0);
41793	return __ret;
41794	}
41795	#endif
41796
41797	#ifdef __LITTLE_ENDIAN__
41798	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
41799	uint32x2_t __ret;
41800	__ret = (uint32x2_t)(__p0);
41801	return __ret;
41802	}
41803	#else
41804	__ai uint32x2_t vreinterpret_u32_s8(int8x8_t __p0) {
41805	uint32x2_t __ret;
41806	__ret = (uint32x2_t)(__p0);
41807	return __ret;
41808	}
41809	#endif
41810
41811	#ifdef __LITTLE_ENDIAN__
41812	__ai uint32x2_t vreinterpret_u32_f64(float64x1_t __p0) {
41813	uint32x2_t __ret;
41814	__ret = (uint32x2_t)(__p0);
41815	return __ret;
41816	}
41817	#else
41818	__ai uint32x2_t vreinterpret_u32_f64(float64x1_t __p0) {
41819	uint32x2_t __ret;
41820	__ret = (uint32x2_t)(__p0);
41821	return __ret;
41822	}
41823	#endif
41824
41825	#ifdef __LITTLE_ENDIAN__
41826	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {
41827	uint32x2_t __ret;
41828	__ret = (uint32x2_t)(__p0);
41829	return __ret;
41830	}
41831	#else
41832	__ai uint32x2_t vreinterpret_u32_f32(float32x2_t __p0) {
41833	uint32x2_t __ret;
41834	__ret = (uint32x2_t)(__p0);
41835	return __ret;
41836	}
41837	#endif
41838
41839	#ifdef __LITTLE_ENDIAN__
41840	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {
41841	uint32x2_t __ret;
41842	__ret = (uint32x2_t)(__p0);
41843	return __ret;
41844	}
41845	#else
41846	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {	35916	__ai uint32x2_t vreinterpret_u32_f16(float16x4_t __p0) {
41847	uint32x2_t __ret;	35917	uint32x2_t __ret;
41848	__ret = (uint32x2_t)(__p0);	35918	__ret = (uint32x2_t)(__p0);
41849	return __ret;	35919	return __ret;
41850	}	35920	}
41851	#endif
41852
41853	#ifdef __LITTLE_ENDIAN__
41854	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {
41855	uint32x2_t __ret;
41856	__ret = (uint32x2_t)(__p0);
41857	return __ret;
41858	}
41859	#else
41860	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {	35921	__ai uint32x2_t vreinterpret_u32_s32(int32x2_t __p0) {
41861	uint32x2_t __ret;	35922	uint32x2_t __ret;
41862	__ret = (uint32x2_t)(__p0);	35923	__ret = (uint32x2_t)(__p0);
41863	return __ret;	35924	return __ret;
41864	}	35925	}
41865	#endif
41866
41867	#ifdef __LITTLE_ENDIAN__
41868	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {	35926	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {
41869	uint32x2_t __ret;	35927	uint32x2_t __ret;
41870	__ret = (uint32x2_t)(__p0);	35928	__ret = (uint32x2_t)(__p0);
41871	return __ret;	35929	return __ret;
41872	}	35930	}
41873	#else
41874	__ai uint32x2_t vreinterpret_u32_s64(int64x1_t __p0) {
41875	uint32x2_t __ret;
41876	__ret = (uint32x2_t)(__p0);
41877	return __ret;
41878	}
41879	#endif
41880
41881	#ifdef __LITTLE_ENDIAN__
41882	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {
41883	uint32x2_t __ret;
41884	__ret = (uint32x2_t)(__p0);
41885	return __ret;
41886	}
41887	#else
41888	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {	35931	__ai uint32x2_t vreinterpret_u32_s16(int16x4_t __p0) {
41889	uint32x2_t __ret;	35932	uint32x2_t __ret;
41890	__ret = (uint32x2_t)(__p0);	35933	__ret = (uint32x2_t)(__p0);
41891	return __ret;	35934	return __ret;
41892	}	35935	}
41893	#endif
41894
41895	#ifdef __LITTLE_ENDIAN__
41896	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {	35936	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {
41897	uint64x1_t __ret;	35937	uint64x1_t __ret;
41898	__ret = (uint64x1_t)(__p0);	35938	__ret = (uint64x1_t)(__p0);
41899	return __ret;	35939	return __ret;
41900	}	35940	}
41901	#else
41902	__ai uint64x1_t vreinterpret_u64_p8(poly8x8_t __p0) {
41903	uint64x1_t __ret;
41904	__ret = (uint64x1_t)(__p0);
41905	return __ret;
41906	}
41907	#endif
41908
41909	#ifdef __LITTLE_ENDIAN__
41910	__ai uint64x1_t vreinterpret_u64_p64(poly64x1_t __p0) {	35941	__ai uint64x1_t vreinterpret_u64_p64(poly64x1_t __p0) {
41911	uint64x1_t __ret;	35942	uint64x1_t __ret;
41912	__ret = (uint64x1_t)(__p0);	35943	__ret = (uint64x1_t)(__p0);
41913	return __ret;	35944	return __ret;
41914	}	35945	}
41915	#else
41916	__ai uint64x1_t vreinterpret_u64_p64(poly64x1_t __p0) {
41917	uint64x1_t __ret;
41918	__ret = (uint64x1_t)(__p0);
41919	return __ret;
41920	}
41921	#endif
41922
41923	#ifdef __LITTLE_ENDIAN__
41924	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {
41925	uint64x1_t __ret;
41926	__ret = (uint64x1_t)(__p0);
41927	return __ret;
41928	}
41929	#else
41930	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {	35946	__ai uint64x1_t vreinterpret_u64_p16(poly16x4_t __p0) {
41931	uint64x1_t __ret;	35947	uint64x1_t __ret;
41932	__ret = (uint64x1_t)(__p0);	35948	__ret = (uint64x1_t)(__p0);
41933	return __ret;	35949	return __ret;
41934	}	35950	}
41935	#endif
41936
41937	#ifdef __LITTLE_ENDIAN__
41938	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {
41939	uint64x1_t __ret;
41940	__ret = (uint64x1_t)(__p0);
41941	return __ret;
41942	}
41943	#else
41944	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {	35951	__ai uint64x1_t vreinterpret_u64_u8(uint8x8_t __p0) {
41945	uint64x1_t __ret;	35952	uint64x1_t __ret;
41946	__ret = (uint64x1_t)(__p0);	35953	__ret = (uint64x1_t)(__p0);
41947	return __ret;	35954	return __ret;
41948	}	35955	}
41949	#endif
41950
41951	#ifdef __LITTLE_ENDIAN__
41952	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {
41953	uint64x1_t __ret;
41954	__ret = (uint64x1_t)(__p0);
41955	return __ret;
41956	}
41957	#else
41958	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {	35956	__ai uint64x1_t vreinterpret_u64_u32(uint32x2_t __p0) {
41959	uint64x1_t __ret;	35957	uint64x1_t __ret;
41960	__ret = (uint64x1_t)(__p0);	35958	__ret = (uint64x1_t)(__p0);
41961	return __ret;	35959	return __ret;
41962	}	35960	}
41963	#endif
41964
41965	#ifdef __LITTLE_ENDIAN__
41966	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {	35961	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {
41967	uint64x1_t __ret;	35962	uint64x1_t __ret;
41968	__ret = (uint64x1_t)(__p0);	35963	__ret = (uint64x1_t)(__p0);
41969	return __ret;	35964	return __ret;
41970	}	35965	}
41971	#else
41972	__ai uint64x1_t vreinterpret_u64_u16(uint16x4_t __p0) {
41973	uint64x1_t __ret;
41974	__ret = (uint64x1_t)(__p0);
41975	return __ret;
41976	}
41977	#endif
41978
41979	#ifdef __LITTLE_ENDIAN__
41980	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
41981	uint64x1_t __ret;
41982	__ret = (uint64x1_t)(__p0);
41983	return __ret;
41984	}
41985	#else
41986	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {	35966	__ai uint64x1_t vreinterpret_u64_s8(int8x8_t __p0) {
41987	uint64x1_t __ret;	35967	uint64x1_t __ret;
41988	__ret = (uint64x1_t)(__p0);	35968	__ret = (uint64x1_t)(__p0);
41989	return __ret;	35969	return __ret;
41990	}	35970	}
41991	#endif
41992
41993	#ifdef __LITTLE_ENDIAN__
41994	__ai uint64x1_t vreinterpret_u64_f64(float64x1_t __p0) {	35971	__ai uint64x1_t vreinterpret_u64_f64(float64x1_t __p0) {
41995	uint64x1_t __ret;	35972	uint64x1_t __ret;
41996	__ret = (uint64x1_t)(__p0);	35973	__ret = (uint64x1_t)(__p0);
41997	return __ret;	35974	return __ret;
41998	}	35975	}
41999	#else
42000	__ai uint64x1_t vreinterpret_u64_f64(float64x1_t __p0) {
42001	uint64x1_t __ret;
42002	__ret = (uint64x1_t)(__p0);
42003	return __ret;
42004	}
42005	#endif
42006
42007	#ifdef __LITTLE_ENDIAN__
42008	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {	35976	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {
42009	uint64x1_t __ret;	35977	uint64x1_t __ret;
42010	__ret = (uint64x1_t)(__p0);	35978	__ret = (uint64x1_t)(__p0);
42011	return __ret;	35979	return __ret;
42012	}	35980	}
42013	#else
42014	__ai uint64x1_t vreinterpret_u64_f32(float32x2_t __p0) {
42015	uint64x1_t __ret;
42016	__ret = (uint64x1_t)(__p0);
42017	return __ret;
42018	}
42019	#endif
42020
42021	#ifdef __LITTLE_ENDIAN__
42022	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {
42023	uint64x1_t __ret;
42024	__ret = (uint64x1_t)(__p0);
42025	return __ret;
42026	}
42027	#else
42028	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {	35981	__ai uint64x1_t vreinterpret_u64_f16(float16x4_t __p0) {
42029	uint64x1_t __ret;	35982	uint64x1_t __ret;
42030	__ret = (uint64x1_t)(__p0);	35983	__ret = (uint64x1_t)(__p0);
42031	return __ret;	35984	return __ret;
42032	}	35985	}
42033	#endif
42034
42035	#ifdef __LITTLE_ENDIAN__
42036	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {
42037	uint64x1_t __ret;
42038	__ret = (uint64x1_t)(__p0);
42039	return __ret;
42040	}
42041	#else
42042	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {	35986	__ai uint64x1_t vreinterpret_u64_s32(int32x2_t __p0) {
42043	uint64x1_t __ret;	35987	uint64x1_t __ret;
42044	__ret = (uint64x1_t)(__p0);	35988	__ret = (uint64x1_t)(__p0);
42045	return __ret;	35989	return __ret;
42046	}	35990	}
42047	#endif
42048
42049	#ifdef __LITTLE_ENDIAN__
42050	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {
42051	uint64x1_t __ret;
42052	__ret = (uint64x1_t)(__p0);
42053	return __ret;
42054	}
42055	#else
42056	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {	35991	__ai uint64x1_t vreinterpret_u64_s64(int64x1_t __p0) {
42057	uint64x1_t __ret;	35992	uint64x1_t __ret;
42058	__ret = (uint64x1_t)(__p0);	35993	__ret = (uint64x1_t)(__p0);
42059	return __ret;	35994	return __ret;
42060	}	35995	}
42061	#endif
42062
42063	#ifdef __LITTLE_ENDIAN__
42064	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {	35996	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {
42065	uint64x1_t __ret;	35997	uint64x1_t __ret;
42066	__ret = (uint64x1_t)(__p0);	35998	__ret = (uint64x1_t)(__p0);
42067	return __ret;	35999	return __ret;
42068	}	36000	}
42069	#else
42070	__ai uint64x1_t vreinterpret_u64_s16(int16x4_t __p0) {
42071	uint64x1_t __ret;
42072	__ret = (uint64x1_t)(__p0);
42073	return __ret;
42074	}
42075	#endif
42076
42077	#ifdef __LITTLE_ENDIAN__
42078	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {
42079	uint16x4_t __ret;
42080	__ret = (uint16x4_t)(__p0);
42081	return __ret;
42082	}
42083	#else
42084	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {	36001	__ai uint16x4_t vreinterpret_u16_p8(poly8x8_t __p0) {
42085	uint16x4_t __ret;	36002	uint16x4_t __ret;
42086	__ret = (uint16x4_t)(__p0);	36003	__ret = (uint16x4_t)(__p0);
42087	return __ret;	36004	return __ret;
42088	}	36005	}
42089	#endif
42090
42091	#ifdef __LITTLE_ENDIAN__
42092	__ai uint16x4_t vreinterpret_u16_p64(poly64x1_t __p0) {	36006	__ai uint16x4_t vreinterpret_u16_p64(poly64x1_t __p0) {
42093	uint16x4_t __ret;	36007	uint16x4_t __ret;
42094	__ret = (uint16x4_t)(__p0);	36008	__ret = (uint16x4_t)(__p0);
42095	return __ret;	36009	return __ret;
42096	}	36010	}
42097	#else
42098	__ai uint16x4_t vreinterpret_u16_p64(poly64x1_t __p0) {
42099	uint16x4_t __ret;
42100	__ret = (uint16x4_t)(__p0);
42101	return __ret;
42102	}
42103	#endif
42104
42105	#ifdef __LITTLE_ENDIAN__
42106	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {	36011	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {
42107	uint16x4_t __ret;	36012	uint16x4_t __ret;
42108	__ret = (uint16x4_t)(__p0);	36013	__ret = (uint16x4_t)(__p0);
42109	return __ret;	36014	return __ret;
42110	}	36015	}
42111	#else
42112	__ai uint16x4_t vreinterpret_u16_p16(poly16x4_t __p0) {
42113	uint16x4_t __ret;
42114	__ret = (uint16x4_t)(__p0);
42115	return __ret;
42116	}
42117	#endif
42118
42119	#ifdef __LITTLE_ENDIAN__
42120	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {	36016	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {
42121	uint16x4_t __ret;	36017	uint16x4_t __ret;
42122	__ret = (uint16x4_t)(__p0);	36018	__ret = (uint16x4_t)(__p0);
42123	return __ret;	36019	return __ret;
42124	}	36020	}
42125	#else
42126	__ai uint16x4_t vreinterpret_u16_u8(uint8x8_t __p0) {
42127	uint16x4_t __ret;
42128	__ret = (uint16x4_t)(__p0);
42129	return __ret;
42130	}
42131	#endif
42132
42133	#ifdef __LITTLE_ENDIAN__
42134	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {
42135	uint16x4_t __ret;
42136	__ret = (uint16x4_t)(__p0);
42137	return __ret;
42138	}
42139	#else
42140	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {	36021	__ai uint16x4_t vreinterpret_u16_u32(uint32x2_t __p0) {
42141	uint16x4_t __ret;	36022	uint16x4_t __ret;
42142	__ret = (uint16x4_t)(__p0);	36023	__ret = (uint16x4_t)(__p0);
42143	return __ret;	36024	return __ret;
42144	}	36025	}
42145	#endif
42146
42147	#ifdef __LITTLE_ENDIAN__
42148	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {
42149	uint16x4_t __ret;
42150	__ret = (uint16x4_t)(__p0);
42151	return __ret;
42152	}
42153	#else
42154	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {	36026	__ai uint16x4_t vreinterpret_u16_u64(uint64x1_t __p0) {
42155	uint16x4_t __ret;	36027	uint16x4_t __ret;
42156	__ret = (uint16x4_t)(__p0);	36028	__ret = (uint16x4_t)(__p0);
42157	return __ret;	36029	return __ret;
42158	}	36030	}
42159	#endif
42160
42161	#ifdef __LITTLE_ENDIAN__
42162	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {	36031	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
42163	uint16x4_t __ret;	36032	uint16x4_t __ret;
42164	__ret = (uint16x4_t)(__p0);	36033	__ret = (uint16x4_t)(__p0);
42165	return __ret;	36034	return __ret;
42166	}	36035	}
42167	#else
42168	__ai uint16x4_t vreinterpret_u16_s8(int8x8_t __p0) {
42169	uint16x4_t __ret;
42170	__ret = (uint16x4_t)(__p0);
42171	return __ret;
42172	}
42173	#endif
42174
42175	#ifdef __LITTLE_ENDIAN__
42176	__ai uint16x4_t vreinterpret_u16_f64(float64x1_t __p0) {
42177	uint16x4_t __ret;
42178	__ret = (uint16x4_t)(__p0);
42179	return __ret;
42180	}
42181	#else
42182	__ai uint16x4_t vreinterpret_u16_f64(float64x1_t __p0) {	36036	__ai uint16x4_t vreinterpret_u16_f64(float64x1_t __p0) {
42183	uint16x4_t __ret;	36037	uint16x4_t __ret;
42184	__ret = (uint16x4_t)(__p0);	36038	__ret = (uint16x4_t)(__p0);
42185	return __ret;	36039	return __ret;
42186	}	36040	}
42187	#endif
42188
42189	#ifdef __LITTLE_ENDIAN__
42190	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {	36041	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {
42191	uint16x4_t __ret;	36042	uint16x4_t __ret;
42192	__ret = (uint16x4_t)(__p0);	36043	__ret = (uint16x4_t)(__p0);
42193	return __ret;	36044	return __ret;
42194	}	36045	}
42195	#else
42196	__ai uint16x4_t vreinterpret_u16_f32(float32x2_t __p0) {
42197	uint16x4_t __ret;
42198	__ret = (uint16x4_t)(__p0);
42199	return __ret;
42200	}
42201	#endif
42202
42203	#ifdef __LITTLE_ENDIAN__
42204	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {	36046	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {
42205	uint16x4_t __ret;	36047	uint16x4_t __ret;
42206	__ret = (uint16x4_t)(__p0);	36048	__ret = (uint16x4_t)(__p0);
42207	return __ret;	36049	return __ret;
42208	}	36050	}
42209	#else
42210	__ai uint16x4_t vreinterpret_u16_f16(float16x4_t __p0) {
42211	uint16x4_t __ret;
42212	__ret = (uint16x4_t)(__p0);
42213	return __ret;
42214	}
42215	#endif
42216
42217	#ifdef __LITTLE_ENDIAN__
42218	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {
42219	uint16x4_t __ret;
42220	__ret = (uint16x4_t)(__p0);
42221	return __ret;
42222	}
42223	#else
42224	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {	36051	__ai uint16x4_t vreinterpret_u16_s32(int32x2_t __p0) {
42225	uint16x4_t __ret;	36052	uint16x4_t __ret;
42226	__ret = (uint16x4_t)(__p0);	36053	__ret = (uint16x4_t)(__p0);
42227	return __ret;	36054	return __ret;
42228	}	36055	}
42229	#endif
42230
42231	#ifdef __LITTLE_ENDIAN__
42232	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {
42233	uint16x4_t __ret;
42234	__ret = (uint16x4_t)(__p0);
42235	return __ret;
42236	}
42237	#else
42238	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {	36056	__ai uint16x4_t vreinterpret_u16_s64(int64x1_t __p0) {
42239	uint16x4_t __ret;	36057	uint16x4_t __ret;
42240	__ret = (uint16x4_t)(__p0);	36058	__ret = (uint16x4_t)(__p0);
42241	return __ret;	36059	return __ret;
42242	}	36060	}
42243	#endif
42244
42245	#ifdef __LITTLE_ENDIAN__
42246	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {
42247	uint16x4_t __ret;
42248	__ret = (uint16x4_t)(__p0);
42249	return __ret;
42250	}
42251	#else
42252	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {	36061	__ai uint16x4_t vreinterpret_u16_s16(int16x4_t __p0) {
42253	uint16x4_t __ret;	36062	uint16x4_t __ret;
42254	__ret = (uint16x4_t)(__p0);	36063	__ret = (uint16x4_t)(__p0);
42255	return __ret;	36064	return __ret;
42256	}	36065	}
42257	#endif
42258
42259	#ifdef __LITTLE_ENDIAN__
42260	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {	36066	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
42261	int8x8_t __ret;	36067	int8x8_t __ret;
42262	__ret = (int8x8_t)(__p0);	36068	__ret = (int8x8_t)(__p0);
42263	return __ret;	36069	return __ret;
42264	}	36070	}
42265	#else
42266	__ai int8x8_t vreinterpret_s8_p8(poly8x8_t __p0) {
42267	int8x8_t __ret;
42268	__ret = (int8x8_t)(__p0);
42269	return __ret;
42270	}
42271	#endif
42272
42273	#ifdef __LITTLE_ENDIAN__
42274	__ai int8x8_t vreinterpret_s8_p64(poly64x1_t __p0) {
42275	int8x8_t __ret;
42276	__ret = (int8x8_t)(__p0);
42277	return __ret;
42278	}
42279	#else
42280	__ai int8x8_t vreinterpret_s8_p64(poly64x1_t __p0) {	36071	__ai int8x8_t vreinterpret_s8_p64(poly64x1_t __p0) {
42281	int8x8_t __ret;	36072	int8x8_t __ret;
42282	__ret = (int8x8_t)(__p0);	36073	__ret = (int8x8_t)(__p0);
42283	return __ret;	36074	return __ret;
42284	}	36075	}
42285	#endif
42286
42287	#ifdef __LITTLE_ENDIAN__
42288	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {	36076	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
42289	int8x8_t __ret;	36077	int8x8_t __ret;
42290	__ret = (int8x8_t)(__p0);	36078	__ret = (int8x8_t)(__p0);
42291	return __ret;	36079	return __ret;
42292	}	36080	}
42293	#else
42294	__ai int8x8_t vreinterpret_s8_p16(poly16x4_t __p0) {
42295	int8x8_t __ret;
42296	__ret = (int8x8_t)(__p0);
42297	return __ret;
42298	}
42299	#endif
42300
42301	#ifdef __LITTLE_ENDIAN__
42302	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {	36081	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
42303	int8x8_t __ret;	36082	int8x8_t __ret;
42304	__ret = (int8x8_t)(__p0);	36083	__ret = (int8x8_t)(__p0);
42305	return __ret;	36084	return __ret;
42306	}	36085	}
42307	#else
42308	__ai int8x8_t vreinterpret_s8_u8(uint8x8_t __p0) {
42309	int8x8_t __ret;
42310	__ret = (int8x8_t)(__p0);
42311	return __ret;
42312	}
42313	#endif
42314
42315	#ifdef __LITTLE_ENDIAN__
42316	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {	36086	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
42317	int8x8_t __ret;	36087	int8x8_t __ret;
42318	__ret = (int8x8_t)(__p0);	36088	__ret = (int8x8_t)(__p0);
42319	return __ret;	36089	return __ret;
42320	}	36090	}
42321	#else
42322	__ai int8x8_t vreinterpret_s8_u32(uint32x2_t __p0) {
42323	int8x8_t __ret;
42324	__ret = (int8x8_t)(__p0);
42325	return __ret;
42326	}
42327	#endif
42328
42329	#ifdef __LITTLE_ENDIAN__
42330	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
42331	int8x8_t __ret;
42332	__ret = (int8x8_t)(__p0);
42333	return __ret;
42334	}
42335	#else
42336	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {	36091	__ai int8x8_t vreinterpret_s8_u64(uint64x1_t __p0) {
42337	int8x8_t __ret;	36092	int8x8_t __ret;
42338	__ret = (int8x8_t)(__p0);	36093	__ret = (int8x8_t)(__p0);
42339	return __ret;	36094	return __ret;
42340	}	36095	}
42341	#endif
42342
42343	#ifdef __LITTLE_ENDIAN__
42344	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
42345	int8x8_t __ret;
42346	__ret = (int8x8_t)(__p0);
42347	return __ret;
42348	}
42349	#else
42350	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {	36096	__ai int8x8_t vreinterpret_s8_u16(uint16x4_t __p0) {
42351	int8x8_t __ret;	36097	int8x8_t __ret;
42352	__ret = (int8x8_t)(__p0);	36098	__ret = (int8x8_t)(__p0);
42353	return __ret;	36099	return __ret;
42354	}	36100	}
42355	#endif
42356
42357	#ifdef __LITTLE_ENDIAN__
42358	__ai int8x8_t vreinterpret_s8_f64(float64x1_t __p0) {	36101	__ai int8x8_t vreinterpret_s8_f64(float64x1_t __p0) {
42359	int8x8_t __ret;	36102	int8x8_t __ret;
42360	__ret = (int8x8_t)(__p0);	36103	__ret = (int8x8_t)(__p0);
42361	return __ret;	36104	return __ret;
42362	}	36105	}
42363	#else
42364	__ai int8x8_t vreinterpret_s8_f64(float64x1_t __p0) {
42365	int8x8_t __ret;
42366	__ret = (int8x8_t)(__p0);
42367	return __ret;
42368	}
42369	#endif
42370
42371	#ifdef __LITTLE_ENDIAN__
42372	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
42373	int8x8_t __ret;
42374	__ret = (int8x8_t)(__p0);
42375	return __ret;
42376	}
42377	#else
42378	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {	36106	__ai int8x8_t vreinterpret_s8_f32(float32x2_t __p0) {
42379	int8x8_t __ret;	36107	int8x8_t __ret;
42380	__ret = (int8x8_t)(__p0);	36108	__ret = (int8x8_t)(__p0);
42381	return __ret;	36109	return __ret;
42382	}	36110	}
42383	#endif
42384
42385	#ifdef __LITTLE_ENDIAN__
42386	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {	36111	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
42387	int8x8_t __ret;	36112	int8x8_t __ret;
42388	__ret = (int8x8_t)(__p0);	36113	__ret = (int8x8_t)(__p0);
42389	return __ret;	36114	return __ret;
42390	}	36115	}
42391	#else
42392	__ai int8x8_t vreinterpret_s8_f16(float16x4_t __p0) {
42393	int8x8_t __ret;
42394	__ret = (int8x8_t)(__p0);
42395	return __ret;
42396	}
42397	#endif
42398
42399	#ifdef __LITTLE_ENDIAN__
42400	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {	36116	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
42401	int8x8_t __ret;	36117	int8x8_t __ret;
42402	__ret = (int8x8_t)(__p0);	36118	__ret = (int8x8_t)(__p0);
42403	return __ret;	36119	return __ret;
42404	}	36120	}
42405	#else
42406	__ai int8x8_t vreinterpret_s8_s32(int32x2_t __p0) {
42407	int8x8_t __ret;
42408	__ret = (int8x8_t)(__p0);
42409	return __ret;
42410	}
42411	#endif
42412
42413	#ifdef __LITTLE_ENDIAN__
42414	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {	36121	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
42415	int8x8_t __ret;	36122	int8x8_t __ret;
42416	__ret = (int8x8_t)(__p0);	36123	__ret = (int8x8_t)(__p0);
42417	return __ret;	36124	return __ret;
42418	}	36125	}
42419	#else
42420	__ai int8x8_t vreinterpret_s8_s64(int64x1_t __p0) {
42421	int8x8_t __ret;
42422	__ret = (int8x8_t)(__p0);
42423	return __ret;
42424	}
42425	#endif
42426
42427	#ifdef __LITTLE_ENDIAN__
42428	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
42429	int8x8_t __ret;
42430	__ret = (int8x8_t)(__p0);
42431	return __ret;
42432	}
42433	#else
42434	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {	36126	__ai int8x8_t vreinterpret_s8_s16(int16x4_t __p0) {
42435	int8x8_t __ret;	36127	int8x8_t __ret;
42436	__ret = (int8x8_t)(__p0);	36128	__ret = (int8x8_t)(__p0);
42437	return __ret;	36129	return __ret;
42438	}	36130	}
42439	#endif
42440
42441	#ifdef __LITTLE_ENDIAN__
42442	__ai float64x1_t vreinterpret_f64_p8(poly8x8_t __p0) {
42443	float64x1_t __ret;
42444	__ret = (float64x1_t)(__p0);
42445	return __ret;
42446	}
42447	#else
42448	__ai float64x1_t vreinterpret_f64_p8(poly8x8_t __p0) {	36131	__ai float64x1_t vreinterpret_f64_p8(poly8x8_t __p0) {
42449	float64x1_t __ret;	36132	float64x1_t __ret;
42450	__ret = (float64x1_t)(__p0);	36133	__ret = (float64x1_t)(__p0);
42451	return __ret;	36134	return __ret;
42452	}	36135	}
42453	#endif
42454
42455	#ifdef __LITTLE_ENDIAN__
42456	__ai float64x1_t vreinterpret_f64_p64(poly64x1_t __p0) {
42457	float64x1_t __ret;
42458	__ret = (float64x1_t)(__p0);
42459	return __ret;
42460	}
42461	#else
42462	__ai float64x1_t vreinterpret_f64_p64(poly64x1_t __p0) {	36136	__ai float64x1_t vreinterpret_f64_p64(poly64x1_t __p0) {
42463	float64x1_t __ret;	36137	float64x1_t __ret;
42464	__ret = (float64x1_t)(__p0);	36138	__ret = (float64x1_t)(__p0);
42465	return __ret;	36139	return __ret;
42466	}	36140	}
42467	#endif
42468
42469	#ifdef __LITTLE_ENDIAN__
42470	__ai float64x1_t vreinterpret_f64_p16(poly16x4_t __p0) {
42471	float64x1_t __ret;
42472	__ret = (float64x1_t)(__p0);
42473	return __ret;
42474	}
42475	#else
42476	__ai float64x1_t vreinterpret_f64_p16(poly16x4_t __p0) {	36141	__ai float64x1_t vreinterpret_f64_p16(poly16x4_t __p0) {
42477	float64x1_t __ret;	36142	float64x1_t __ret;
42478	__ret = (float64x1_t)(__p0);	36143	__ret = (float64x1_t)(__p0);
42479	return __ret;	36144	return __ret;
42480	}	36145	}
42481	#endif
42482
42483	#ifdef __LITTLE_ENDIAN__
42484	__ai float64x1_t vreinterpret_f64_u8(uint8x8_t __p0) {	36146	__ai float64x1_t vreinterpret_f64_u8(uint8x8_t __p0) {
42485	float64x1_t __ret;	36147	float64x1_t __ret;
42486	__ret = (float64x1_t)(__p0);	36148	__ret = (float64x1_t)(__p0);
42487	return __ret;	36149	return __ret;
42488	}	36150	}
42489	#else
42490	__ai float64x1_t vreinterpret_f64_u8(uint8x8_t __p0) {
42491	float64x1_t __ret;
42492	__ret = (float64x1_t)(__p0);
42493	return __ret;
42494	}
42495	#endif
42496
42497	#ifdef __LITTLE_ENDIAN__
42498	__ai float64x1_t vreinterpret_f64_u32(uint32x2_t __p0) {	36151	__ai float64x1_t vreinterpret_f64_u32(uint32x2_t __p0) {
42499	float64x1_t __ret;	36152	float64x1_t __ret;
42500	__ret = (float64x1_t)(__p0);	36153	__ret = (float64x1_t)(__p0);
42501	return __ret;	36154	return __ret;
42502	}	36155	}
42503	#else
42504	__ai float64x1_t vreinterpret_f64_u32(uint32x2_t __p0) {
42505	float64x1_t __ret;
42506	__ret = (float64x1_t)(__p0);
42507	return __ret;
42508	}
42509	#endif
42510
42511	#ifdef __LITTLE_ENDIAN__
42512	__ai float64x1_t vreinterpret_f64_u64(uint64x1_t __p0) {
42513	float64x1_t __ret;
42514	__ret = (float64x1_t)(__p0);
42515	return __ret;
42516	}
42517	#else
42518	__ai float64x1_t vreinterpret_f64_u64(uint64x1_t __p0) {	36156	__ai float64x1_t vreinterpret_f64_u64(uint64x1_t __p0) {
42519	float64x1_t __ret;	36157	float64x1_t __ret;
42520	__ret = (float64x1_t)(__p0);	36158	__ret = (float64x1_t)(__p0);
42521	return __ret;	36159	return __ret;
42522	}	36160	}
42523	#endif
42524
42525	#ifdef __LITTLE_ENDIAN__
42526	__ai float64x1_t vreinterpret_f64_u16(uint16x4_t __p0) {
42527	float64x1_t __ret;
42528	__ret = (float64x1_t)(__p0);
42529	return __ret;
42530	}
42531	#else
42532	__ai float64x1_t vreinterpret_f64_u16(uint16x4_t __p0) {	36161	__ai float64x1_t vreinterpret_f64_u16(uint16x4_t __p0) {
42533	float64x1_t __ret;	36162	float64x1_t __ret;
42534	__ret = (float64x1_t)(__p0);	36163	__ret = (float64x1_t)(__p0);
42535	return __ret;	36164	return __ret;
42536	}	36165	}
42537	#endif
42538
42539	#ifdef __LITTLE_ENDIAN__
42540	__ai float64x1_t vreinterpret_f64_s8(int8x8_t __p0) {
42541	float64x1_t __ret;
42542	__ret = (float64x1_t)(__p0);
42543	return __ret;
42544	}
42545	#else
42546	__ai float64x1_t vreinterpret_f64_s8(int8x8_t __p0) {	36166	__ai float64x1_t vreinterpret_f64_s8(int8x8_t __p0) {
42547	float64x1_t __ret;	36167	float64x1_t __ret;
42548	__ret = (float64x1_t)(__p0);	36168	__ret = (float64x1_t)(__p0);
42549	return __ret;	36169	return __ret;
42550	}	36170	}
42551	#endif
42552
42553	#ifdef __LITTLE_ENDIAN__
42554	__ai float64x1_t vreinterpret_f64_f32(float32x2_t __p0) {	36171	__ai float64x1_t vreinterpret_f64_f32(float32x2_t __p0) {
42555	float64x1_t __ret;	36172	float64x1_t __ret;
42556	__ret = (float64x1_t)(__p0);	36173	__ret = (float64x1_t)(__p0);
42557	return __ret;	36174	return __ret;
42558	}	36175	}
42559	#else
42560	__ai float64x1_t vreinterpret_f64_f32(float32x2_t __p0) {
42561	float64x1_t __ret;
42562	__ret = (float64x1_t)(__p0);
42563	return __ret;
42564	}
42565	#endif
42566
42567	#ifdef __LITTLE_ENDIAN__
42568	__ai float64x1_t vreinterpret_f64_f16(float16x4_t __p0) {
42569	float64x1_t __ret;
42570	__ret = (float64x1_t)(__p0);
42571	return __ret;
42572	}
42573	#else
42574	__ai float64x1_t vreinterpret_f64_f16(float16x4_t __p0) {	36176	__ai float64x1_t vreinterpret_f64_f16(float16x4_t __p0) {
42575	float64x1_t __ret;	36177	float64x1_t __ret;
42576	__ret = (float64x1_t)(__p0);	36178	__ret = (float64x1_t)(__p0);
42577	return __ret;	36179	return __ret;
42578	}	36180	}
42579	#endif
42580
42581	#ifdef __LITTLE_ENDIAN__
42582	__ai float64x1_t vreinterpret_f64_s32(int32x2_t __p0) {	36181	__ai float64x1_t vreinterpret_f64_s32(int32x2_t __p0) {
42583	float64x1_t __ret;	36182	float64x1_t __ret;
42584	__ret = (float64x1_t)(__p0);	36183	__ret = (float64x1_t)(__p0);
42585	return __ret;	36184	return __ret;
42586	}	36185	}
42587	#else
42588	__ai float64x1_t vreinterpret_f64_s32(int32x2_t __p0) {
42589	float64x1_t __ret;
42590	__ret = (float64x1_t)(__p0);
42591	return __ret;
42592	}
42593	#endif
42594
42595	#ifdef __LITTLE_ENDIAN__
42596	__ai float64x1_t vreinterpret_f64_s64(int64x1_t __p0) {	36186	__ai float64x1_t vreinterpret_f64_s64(int64x1_t __p0) {
42597	float64x1_t __ret;	36187	float64x1_t __ret;
42598	__ret = (float64x1_t)(__p0);	36188	__ret = (float64x1_t)(__p0);
42599	return __ret;	36189	return __ret;
42600	}	36190	}
42601	#else
42602	__ai float64x1_t vreinterpret_f64_s64(int64x1_t __p0) {
42603	float64x1_t __ret;
42604	__ret = (float64x1_t)(__p0);
42605	return __ret;
42606	}
42607	#endif
42608
42609	#ifdef __LITTLE_ENDIAN__
42610	__ai float64x1_t vreinterpret_f64_s16(int16x4_t __p0) {
42611	float64x1_t __ret;
42612	__ret = (float64x1_t)(__p0);
42613	return __ret;
42614	}
42615	#else
42616	__ai float64x1_t vreinterpret_f64_s16(int16x4_t __p0) {	36191	__ai float64x1_t vreinterpret_f64_s16(int16x4_t __p0) {
42617	float64x1_t __ret;	36192	float64x1_t __ret;
42618	__ret = (float64x1_t)(__p0);	36193	__ret = (float64x1_t)(__p0);
42619	return __ret;	36194	return __ret;
42620	}	36195	}
42621	#endif
42622
42623	#ifdef __LITTLE_ENDIAN__
42624	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {
42625	float32x2_t __ret;
42626	__ret = (float32x2_t)(__p0);
42627	return __ret;
42628	}
42629	#else
42630	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {	36196	__ai float32x2_t vreinterpret_f32_p8(poly8x8_t __p0) {
42631	float32x2_t __ret;	36197	float32x2_t __ret;
42632	__ret = (float32x2_t)(__p0);	36198	__ret = (float32x2_t)(__p0);
42633	return __ret;	36199	return __ret;
42634	}	36200	}
42635	#endif
42636
42637	#ifdef __LITTLE_ENDIAN__
42638	__ai float32x2_t vreinterpret_f32_p64(poly64x1_t __p0) {
42639	float32x2_t __ret;
42640	__ret = (float32x2_t)(__p0);
42641	return __ret;
42642	}
42643	#else
42644	__ai float32x2_t vreinterpret_f32_p64(poly64x1_t __p0) {	36201	__ai float32x2_t vreinterpret_f32_p64(poly64x1_t __p0) {
42645	float32x2_t __ret;	36202	float32x2_t __ret;
42646	__ret = (float32x2_t)(__p0);	36203	__ret = (float32x2_t)(__p0);
42647	return __ret;	36204	return __ret;
42648	}	36205	}
42649	#endif
42650
42651	#ifdef __LITTLE_ENDIAN__
42652	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {	36206	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {
42653	float32x2_t __ret;	36207	float32x2_t __ret;
42654	__ret = (float32x2_t)(__p0);	36208	__ret = (float32x2_t)(__p0);
42655	return __ret;	36209	return __ret;
42656	}	36210	}
42657	#else
42658	__ai float32x2_t vreinterpret_f32_p16(poly16x4_t __p0) {
42659	float32x2_t __ret;
42660	__ret = (float32x2_t)(__p0);
42661	return __ret;
42662	}
42663	#endif
42664
42665	#ifdef __LITTLE_ENDIAN__
42666	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {
42667	float32x2_t __ret;
42668	__ret = (float32x2_t)(__p0);
42669	return __ret;
42670	}
42671	#else
42672	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {	36211	__ai float32x2_t vreinterpret_f32_u8(uint8x8_t __p0) {
42673	float32x2_t __ret;	36212	float32x2_t __ret;
42674	__ret = (float32x2_t)(__p0);	36213	__ret = (float32x2_t)(__p0);
42675	return __ret;	36214	return __ret;
42676	}	36215	}
42677	#endif
42678
42679	#ifdef __LITTLE_ENDIAN__
42680	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {	36216	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {
42681	float32x2_t __ret;	36217	float32x2_t __ret;
42682	__ret = (float32x2_t)(__p0);	36218	__ret = (float32x2_t)(__p0);
42683	return __ret;	36219	return __ret;
42684	}	36220	}
42685	#else
42686	__ai float32x2_t vreinterpret_f32_u32(uint32x2_t __p0) {
42687	float32x2_t __ret;
42688	__ret = (float32x2_t)(__p0);
42689	return __ret;
42690	}
42691	#endif
42692
42693	#ifdef __LITTLE_ENDIAN__
42694	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {	36221	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {
42695	float32x2_t __ret;	36222	float32x2_t __ret;
42696	__ret = (float32x2_t)(__p0);	36223	__ret = (float32x2_t)(__p0);
42697	return __ret;	36224	return __ret;
42698	}	36225	}
42699	#else
42700	__ai float32x2_t vreinterpret_f32_u64(uint64x1_t __p0) {
42701	float32x2_t __ret;
42702	__ret = (float32x2_t)(__p0);
42703	return __ret;
42704	}
42705	#endif
42706
42707	#ifdef __LITTLE_ENDIAN__
42708	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {
42709	float32x2_t __ret;
42710	__ret = (float32x2_t)(__p0);
42711	return __ret;
42712	}
42713	#else
42714	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {	36226	__ai float32x2_t vreinterpret_f32_u16(uint16x4_t __p0) {
42715	float32x2_t __ret;	36227	float32x2_t __ret;
42716	__ret = (float32x2_t)(__p0);	36228	__ret = (float32x2_t)(__p0);
42717	return __ret;	36229	return __ret;
42718	}	36230	}
42719	#endif
42720
42721	#ifdef __LITTLE_ENDIAN__
42722	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
42723	float32x2_t __ret;
42724	__ret = (float32x2_t)(__p0);
42725	return __ret;
42726	}
42727	#else
42728	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {	36231	__ai float32x2_t vreinterpret_f32_s8(int8x8_t __p0) {
42729	float32x2_t __ret;	36232	float32x2_t __ret;
42730	__ret = (float32x2_t)(__p0);	36233	__ret = (float32x2_t)(__p0);
42731	return __ret;	36234	return __ret;
42732	}	36235	}
42733	#endif
42734
42735	#ifdef __LITTLE_ENDIAN__
42736	__ai float32x2_t vreinterpret_f32_f64(float64x1_t __p0) {
42737	float32x2_t __ret;
42738	__ret = (float32x2_t)(__p0);
42739	return __ret;
42740	}
42741	#else
42742	__ai float32x2_t vreinterpret_f32_f64(float64x1_t __p0) {	36236	__ai float32x2_t vreinterpret_f32_f64(float64x1_t __p0) {
42743	float32x2_t __ret;	36237	float32x2_t __ret;
42744	__ret = (float32x2_t)(__p0);	36238	__ret = (float32x2_t)(__p0);
42745	return __ret;	36239	return __ret;
42746	}	36240	}
42747	#endif
42748
42749	#ifdef __LITTLE_ENDIAN__
42750	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {	36241	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {
42751	float32x2_t __ret;	36242	float32x2_t __ret;
42752	__ret = (float32x2_t)(__p0);	36243	__ret = (float32x2_t)(__p0);
42753	return __ret;	36244	return __ret;
42754	}	36245	}
42755	#else
42756	__ai float32x2_t vreinterpret_f32_f16(float16x4_t __p0) {
42757	float32x2_t __ret;
42758	__ret = (float32x2_t)(__p0);
42759	return __ret;
42760	}
42761	#endif
42762
42763	#ifdef __LITTLE_ENDIAN__
42764	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {
42765	float32x2_t __ret;
42766	__ret = (float32x2_t)(__p0);
42767	return __ret;
42768	}
42769	#else
42770	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {	36246	__ai float32x2_t vreinterpret_f32_s32(int32x2_t __p0) {
42771	float32x2_t __ret;	36247	float32x2_t __ret;
42772	__ret = (float32x2_t)(__p0);	36248	__ret = (float32x2_t)(__p0);
42773	return __ret;	36249	return __ret;
42774	}	36250	}
42775	#endif
42776
42777	#ifdef __LITTLE_ENDIAN__
42778	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {	36251	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {
42779	float32x2_t __ret;	36252	float32x2_t __ret;
42780	__ret = (float32x2_t)(__p0);	36253	__ret = (float32x2_t)(__p0);
42781	return __ret;	36254	return __ret;
42782	}	36255	}
42783	#else
42784	__ai float32x2_t vreinterpret_f32_s64(int64x1_t __p0) {
42785	float32x2_t __ret;
42786	__ret = (float32x2_t)(__p0);
42787	return __ret;
42788	}
42789	#endif
42790
42791	#ifdef __LITTLE_ENDIAN__
42792	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {	36256	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {
42793	float32x2_t __ret;	36257	float32x2_t __ret;
42794	__ret = (float32x2_t)(__p0);	36258	__ret = (float32x2_t)(__p0);
42795	return __ret;	36259	return __ret;
42796	}	36260	}
42797	#else
42798	__ai float32x2_t vreinterpret_f32_s16(int16x4_t __p0) {
42799	float32x2_t __ret;
42800	__ret = (float32x2_t)(__p0);
42801	return __ret;
42802	}
42803	#endif
42804
42805	#ifdef __LITTLE_ENDIAN__
42806	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {
42807	float16x4_t __ret;
42808	__ret = (float16x4_t)(__p0);
42809	return __ret;
42810	}
42811	#else
42812	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {	36261	__ai float16x4_t vreinterpret_f16_p8(poly8x8_t __p0) {
42813	float16x4_t __ret;	36262	float16x4_t __ret;
42814	__ret = (float16x4_t)(__p0);	36263	__ret = (float16x4_t)(__p0);
42815	return __ret;	36264	return __ret;
42816	}	36265	}
42817	#endif
42818
42819	#ifdef __LITTLE_ENDIAN__
42820	__ai float16x4_t vreinterpret_f16_p64(poly64x1_t __p0) {
42821	float16x4_t __ret;
42822	__ret = (float16x4_t)(__p0);
42823	return __ret;
42824	}
42825	#else
42826	__ai float16x4_t vreinterpret_f16_p64(poly64x1_t __p0) {	36266	__ai float16x4_t vreinterpret_f16_p64(poly64x1_t __p0) {
42827	float16x4_t __ret;	36267	float16x4_t __ret;
42828	__ret = (float16x4_t)(__p0);	36268	__ret = (float16x4_t)(__p0);
42829	return __ret;	36269	return __ret;
42830	}	36270	}
42831	#endif
42832
42833	#ifdef __LITTLE_ENDIAN__
42834	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {
42835	float16x4_t __ret;
42836	__ret = (float16x4_t)(__p0);
42837	return __ret;
42838	}
42839	#else
42840	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {	36271	__ai float16x4_t vreinterpret_f16_p16(poly16x4_t __p0) {
42841	float16x4_t __ret;	36272	float16x4_t __ret;
42842	__ret = (float16x4_t)(__p0);	36273	__ret = (float16x4_t)(__p0);
42843	return __ret;	36274	return __ret;
42844	}	36275	}
42845	#endif
42846
42847	#ifdef __LITTLE_ENDIAN__
42848	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {	36276	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {
42849	float16x4_t __ret;	36277	float16x4_t __ret;
42850	__ret = (float16x4_t)(__p0);	36278	__ret = (float16x4_t)(__p0);
42851	return __ret;	36279	return __ret;
42852	}	36280	}
42853	#else
42854	__ai float16x4_t vreinterpret_f16_u8(uint8x8_t __p0) {
42855	float16x4_t __ret;
42856	__ret = (float16x4_t)(__p0);
42857	return __ret;
42858	}
42859	#endif
42860
42861	#ifdef __LITTLE_ENDIAN__
42862	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {
42863	float16x4_t __ret;
42864	__ret = (float16x4_t)(__p0);
42865	return __ret;
42866	}
42867	#else
42868	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {	36281	__ai float16x4_t vreinterpret_f16_u32(uint32x2_t __p0) {
42869	float16x4_t __ret;	36282	float16x4_t __ret;
42870	__ret = (float16x4_t)(__p0);	36283	__ret = (float16x4_t)(__p0);
42871	return __ret;	36284	return __ret;
42872	}	36285	}
42873	#endif
42874
42875	#ifdef __LITTLE_ENDIAN__
42876	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {	36286	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {
42877	float16x4_t __ret;	36287	float16x4_t __ret;
42878	__ret = (float16x4_t)(__p0);	36288	__ret = (float16x4_t)(__p0);
42879	return __ret;	36289	return __ret;
42880	}	36290	}
42881	#else
42882	__ai float16x4_t vreinterpret_f16_u64(uint64x1_t __p0) {
42883	float16x4_t __ret;
42884	__ret = (float16x4_t)(__p0);
42885	return __ret;
42886	}
42887	#endif
42888
42889	#ifdef __LITTLE_ENDIAN__
42890	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {	36291	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {
42891	float16x4_t __ret;	36292	float16x4_t __ret;
42892	__ret = (float16x4_t)(__p0);	36293	__ret = (float16x4_t)(__p0);
42893	return __ret;	36294	return __ret;
42894	}	36295	}
42895	#else
42896	__ai float16x4_t vreinterpret_f16_u16(uint16x4_t __p0) {
42897	float16x4_t __ret;
42898	__ret = (float16x4_t)(__p0);
42899	return __ret;
42900	}
42901	#endif
42902
42903	#ifdef __LITTLE_ENDIAN__
42904	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
42905	float16x4_t __ret;
42906	__ret = (float16x4_t)(__p0);
42907	return __ret;
42908	}
42909	#else
42910	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {	36296	__ai float16x4_t vreinterpret_f16_s8(int8x8_t __p0) {
42911	float16x4_t __ret;	36297	float16x4_t __ret;
42912	__ret = (float16x4_t)(__p0);	36298	__ret = (float16x4_t)(__p0);
42913	return __ret;	36299	return __ret;
42914	}	36300	}
42915	#endif
42916
42917	#ifdef __LITTLE_ENDIAN__
42918	__ai float16x4_t vreinterpret_f16_f64(float64x1_t __p0) {
42919	float16x4_t __ret;
42920	__ret = (float16x4_t)(__p0);
42921	return __ret;
42922	}
42923	#else
42924	__ai float16x4_t vreinterpret_f16_f64(float64x1_t __p0) {	36301	__ai float16x4_t vreinterpret_f16_f64(float64x1_t __p0) {
42925	float16x4_t __ret;	36302	float16x4_t __ret;
42926	__ret = (float16x4_t)(__p0);	36303	__ret = (float16x4_t)(__p0);
42927	return __ret;	36304	return __ret;
42928	}	36305	}
42929	#endif
42930
42931	#ifdef __LITTLE_ENDIAN__
42932	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {
42933	float16x4_t __ret;
42934	__ret = (float16x4_t)(__p0);
42935	return __ret;
42936	}
42937	#else
42938	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {	36306	__ai float16x4_t vreinterpret_f16_f32(float32x2_t __p0) {
42939	float16x4_t __ret;	36307	float16x4_t __ret;
42940	__ret = (float16x4_t)(__p0);	36308	__ret = (float16x4_t)(__p0);
42941	return __ret;	36309	return __ret;
42942	}	36310	}
42943	#endif
42944
42945	#ifdef __LITTLE_ENDIAN__
42946	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {	36311	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {
42947	float16x4_t __ret;	36312	float16x4_t __ret;
42948	__ret = (float16x4_t)(__p0);	36313	__ret = (float16x4_t)(__p0);
42949	return __ret;	36314	return __ret;
42950	}	36315	}
42951	#else
42952	__ai float16x4_t vreinterpret_f16_s32(int32x2_t __p0) {
42953	float16x4_t __ret;
42954	__ret = (float16x4_t)(__p0);
42955	return __ret;
42956	}
42957	#endif
42958
42959	#ifdef __LITTLE_ENDIAN__
42960	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {
42961	float16x4_t __ret;
42962	__ret = (float16x4_t)(__p0);
42963	return __ret;
42964	}
42965	#else
42966	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {	36316	__ai float16x4_t vreinterpret_f16_s64(int64x1_t __p0) {
42967	float16x4_t __ret;	36317	float16x4_t __ret;
42968	__ret = (float16x4_t)(__p0);	36318	__ret = (float16x4_t)(__p0);
42969	return __ret;	36319	return __ret;
42970	}	36320	}
42971	#endif
42972
42973	#ifdef __LITTLE_ENDIAN__
42974	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {	36321	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {
42975	float16x4_t __ret;	36322	float16x4_t __ret;
42976	__ret = (float16x4_t)(__p0);	36323	__ret = (float16x4_t)(__p0);
42977	return __ret;	36324	return __ret;
42978	}	36325	}
42979	#else
42980	__ai float16x4_t vreinterpret_f16_s16(int16x4_t __p0) {
42981	float16x4_t __ret;
42982	__ret = (float16x4_t)(__p0);
42983	return __ret;
42984	}
42985	#endif
42986
42987	#ifdef __LITTLE_ENDIAN__
42988	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {	36326	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {
42989	int32x2_t __ret;	36327	int32x2_t __ret;
42990	__ret = (int32x2_t)(__p0);	36328	__ret = (int32x2_t)(__p0);
42991	return __ret;	36329	return __ret;
42992	}	36330	}
42993	#else
42994	__ai int32x2_t vreinterpret_s32_p8(poly8x8_t __p0) {
42995	int32x2_t __ret;
42996	__ret = (int32x2_t)(__p0);
42997	return __ret;
42998	}
42999	#endif
43000
43001	#ifdef __LITTLE_ENDIAN__
43002	__ai int32x2_t vreinterpret_s32_p64(poly64x1_t __p0) {
43003	int32x2_t __ret;
43004	__ret = (int32x2_t)(__p0);
43005	return __ret;
43006	}
43007	#else
43008	__ai int32x2_t vreinterpret_s32_p64(poly64x1_t __p0) {	36331	__ai int32x2_t vreinterpret_s32_p64(poly64x1_t __p0) {
43009	int32x2_t __ret;	36332	int32x2_t __ret;
43010	__ret = (int32x2_t)(__p0);	36333	__ret = (int32x2_t)(__p0);
43011	return __ret;	36334	return __ret;
43012	}	36335	}
43013	#endif
43014
43015	#ifdef __LITTLE_ENDIAN__
43016	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {
43017	int32x2_t __ret;
43018	__ret = (int32x2_t)(__p0);
43019	return __ret;
43020	}
43021	#else
43022	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {	36336	__ai int32x2_t vreinterpret_s32_p16(poly16x4_t __p0) {
43023	int32x2_t __ret;	36337	int32x2_t __ret;
43024	__ret = (int32x2_t)(__p0);	36338	__ret = (int32x2_t)(__p0);
43025	return __ret;	36339	return __ret;
43026	}	36340	}
43027	#endif
43028
43029	#ifdef __LITTLE_ENDIAN__
43030	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {
43031	int32x2_t __ret;
43032	__ret = (int32x2_t)(__p0);
43033	return __ret;
43034	}
43035	#else
43036	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {	36341	__ai int32x2_t vreinterpret_s32_u8(uint8x8_t __p0) {
43037	int32x2_t __ret;	36342	int32x2_t __ret;
43038	__ret = (int32x2_t)(__p0);	36343	__ret = (int32x2_t)(__p0);
43039	return __ret;	36344	return __ret;
43040	}	36345	}
43041	#endif
43042
43043	#ifdef __LITTLE_ENDIAN__
43044	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {	36346	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {
43045	int32x2_t __ret;	36347	int32x2_t __ret;
43046	__ret = (int32x2_t)(__p0);	36348	__ret = (int32x2_t)(__p0);
43047	return __ret;	36349	return __ret;
43048	}	36350	}
43049	#else
43050	__ai int32x2_t vreinterpret_s32_u32(uint32x2_t __p0) {
43051	int32x2_t __ret;
43052	__ret = (int32x2_t)(__p0);
43053	return __ret;
43054	}
43055	#endif
43056
43057	#ifdef __LITTLE_ENDIAN__
43058	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {
43059	int32x2_t __ret;
43060	__ret = (int32x2_t)(__p0);
43061	return __ret;
43062	}
43063	#else
43064	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {	36351	__ai int32x2_t vreinterpret_s32_u64(uint64x1_t __p0) {
43065	int32x2_t __ret;	36352	int32x2_t __ret;
43066	__ret = (int32x2_t)(__p0);	36353	__ret = (int32x2_t)(__p0);
43067	return __ret;	36354	return __ret;
43068	}	36355	}
43069	#endif
43070
43071	#ifdef __LITTLE_ENDIAN__
43072	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {	36356	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {
43073	int32x2_t __ret;	36357	int32x2_t __ret;
43074	__ret = (int32x2_t)(__p0);	36358	__ret = (int32x2_t)(__p0);
43075	return __ret;
43076	}
43077	#else
43078	__ai int32x2_t vreinterpret_s32_u16(uint16x4_t __p0) {
43079	int32x2_t __ret;
43080	__ret = (int32x2_t)(__p0);
43081	return __ret;
43082	}
43083	#endif
43084
43085	#ifdef __LITTLE_ENDIAN__
43086	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
43087	int32x2_t __ret;
43088	__ret = (int32x2_t)(__p0);
43089	return __ret;
43090	}
43091	#else
43092	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
43093	int32x2_t __ret;
43094	__ret = (int32x2_t)(__p0);
43095	return __ret;
43096	}
43097	#endif
43098
43099	#ifdef __LITTLE_ENDIAN__
43100	__ai int32x2_t vreinterpret_s32_f64(float64x1_t __p0) {
43101	int32x2_t __ret;
43102	__ret = (int32x2_t)(__p0);
43103	return __ret;
43104	}
43105	#else
43106	__ai int32x2_t vreinterpret_s32_f64(float64x1_t __p0) {
43107	int32x2_t __ret;
43108	__ret = (int32x2_t)(__p0);
43109	return __ret;
43110	}
43111	#endif
43112
43113	#ifdef __LITTLE_ENDIAN__
43114	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {
43115	int32x2_t __ret;
43116	__ret = (int32x2_t)(__p0);
43117	return __ret;
43118	}
43119	#else
43120	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {
43121	int32x2_t __ret;
43122	__ret = (int32x2_t)(__p0);
43123	return __ret;
43124	}
43125	#endif
43126
43127	#ifdef __LITTLE_ENDIAN__
43128	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {
43129	int32x2_t __ret;
43130	__ret = (int32x2_t)(__p0);
43131	return __ret;
43132	}
43133	#else
43134	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {
43135	int32x2_t __ret;
43136	__ret = (int32x2_t)(__p0);
43137	return __ret;
43138	}
43139	#endif
43140
43141	#ifdef __LITTLE_ENDIAN__
43142	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {
43143	int32x2_t __ret;
43144	__ret = (int32x2_t)(__p0);
43145	return __ret;
43146	}
43147	#else
43148	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {
43149	int32x2_t __ret;
43150	__ret = (int32x2_t)(__p0);
43151	return __ret;
43152	}
43153	#endif
43154
43155	#ifdef __LITTLE_ENDIAN__
43156	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {
43157	int32x2_t __ret;
43158	__ret = (int32x2_t)(__p0);
43159	return __ret;
43160	}
43161	#else
43162	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {
43163	int32x2_t __ret;
43164	__ret = (int32x2_t)(__p0);
43165	return __ret;
43166	}
43167	#endif
43168
43169	#ifdef __LITTLE_ENDIAN__
43170	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {
43171	int64x1_t __ret;
43172	__ret = (int64x1_t)(__p0);
43173	return __ret;
43174	}
43175	#else
43176	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {
43177	int64x1_t __ret;
43178	__ret = (int64x1_t)(__p0);
43179	return __ret;
43180	}
43181	#endif
43182
43183	#ifdef __LITTLE_ENDIAN__
43184	__ai int64x1_t vreinterpret_s64_p64(poly64x1_t __p0) {
43185	int64x1_t __ret;
43186	__ret = (int64x1_t)(__p0);
43187	return __ret;
43188	}
43189	#else
43190	__ai int64x1_t vreinterpret_s64_p64(poly64x1_t __p0) {
43191	int64x1_t __ret;
43192	__ret = (int64x1_t)(__p0);
43193	return __ret;
43194	}
43195	#endif
43196
43197	#ifdef __LITTLE_ENDIAN__
43198	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {
43199	int64x1_t __ret;
43200	__ret = (int64x1_t)(__p0);
43201	return __ret;
43202	}
43203	#else
43204	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {
43205	int64x1_t __ret;
43206	__ret = (int64x1_t)(__p0);
43207	return __ret;
43208	}
43209	#endif
43210
43211	#ifdef __LITTLE_ENDIAN__
43212	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {
43213	int64x1_t __ret;
43214	__ret = (int64x1_t)(__p0);
43215	return __ret;	36359	return __ret;
43216	}	36360	}
43217	#else	36361	__ai int32x2_t vreinterpret_s32_s8(int8x8_t __p0) {
43218	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {	36362	int32x2_t __ret;
43219	int64x1_t __ret;	36363	__ret = (int32x2_t)(__p0);
43220	__ret = (int64x1_t)(__p0);
43221	return __ret;	36364	return __ret;
43222	}	36365	}
43223	#endif	36366	__ai int32x2_t vreinterpret_s32_f64(float64x1_t __p0) {
43224		36367	int32x2_t __ret;
43225	#ifdef __LITTLE_ENDIAN__	36368	__ret = (int32x2_t)(__p0);
43226	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {
43227	int64x1_t __ret;
43228	__ret = (int64x1_t)(__p0);
43229	return __ret;	36369	return __ret;
43230	}	36370	}
43231	#else	36371	__ai int32x2_t vreinterpret_s32_f32(float32x2_t __p0) {
43232	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {	36372	int32x2_t __ret;
43233	int64x1_t __ret;	36373	__ret = (int32x2_t)(__p0);
43234	__ret = (int64x1_t)(__p0);
43235	return __ret;	36374	return __ret;
43236	}	36375	}
43237	#endif	36376	__ai int32x2_t vreinterpret_s32_f16(float16x4_t __p0) {
43238		36377	int32x2_t __ret;
43239	#ifdef __LITTLE_ENDIAN__	36378	__ret = (int32x2_t)(__p0);
43240	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {
43241	int64x1_t __ret;
43242	__ret = (int64x1_t)(__p0);
43243	return __ret;	36379	return __ret;
43244	}	36380	}
43245	#else	36381	__ai int32x2_t vreinterpret_s32_s64(int64x1_t __p0) {
43246	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {	36382	int32x2_t __ret;
43247	int64x1_t __ret;	36383	__ret = (int32x2_t)(__p0);
43248	__ret = (int64x1_t)(__p0);
43249	return __ret;	36384	return __ret;
43250	}	36385	}
43251	#endif	36386	__ai int32x2_t vreinterpret_s32_s16(int16x4_t __p0) {
43252		36387	int32x2_t __ret;
43253	#ifdef __LITTLE_ENDIAN__	36388	__ret = (int32x2_t)(__p0);
43254	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {
43255	int64x1_t __ret;
43256	__ret = (int64x1_t)(__p0);
43257	return __ret;	36389	return __ret;
43258	}	36390	}
43259	#else	36391	__ai int64x1_t vreinterpret_s64_p8(poly8x8_t __p0) {
43260	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {
43261	int64x1_t __ret;	36392	int64x1_t __ret;
43262	__ret = (int64x1_t)(__p0);	36393	__ret = (int64x1_t)(__p0);
43263	return __ret;	36394	return __ret;
43264	}	36395	}
43265	#endif	36396	__ai int64x1_t vreinterpret_s64_p64(poly64x1_t __p0) {
43266
43267	#ifdef __LITTLE_ENDIAN__
43268	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
43269	int64x1_t __ret;	36397	int64x1_t __ret;
43270	__ret = (int64x1_t)(__p0);	36398	__ret = (int64x1_t)(__p0);
43271	return __ret;	36399	return __ret;
43272	}	36400	}
43273	#else	36401	__ai int64x1_t vreinterpret_s64_p16(poly16x4_t __p0) {
43274	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
43275	int64x1_t __ret;	36402	int64x1_t __ret;
43276	__ret = (int64x1_t)(__p0);	36403	__ret = (int64x1_t)(__p0);
43277	return __ret;	36404	return __ret;
43278	}	36405	}
43279	#endif	36406	__ai int64x1_t vreinterpret_s64_u8(uint8x8_t __p0) {
43280
43281	#ifdef __LITTLE_ENDIAN__
43282	__ai int64x1_t vreinterpret_s64_f64(float64x1_t __p0) {
43283	int64x1_t __ret;	36407	int64x1_t __ret;
43284	__ret = (int64x1_t)(__p0);	36408	__ret = (int64x1_t)(__p0);
43285	return __ret;	36409	return __ret;
43286	}	36410	}
43287	#else	36411	__ai int64x1_t vreinterpret_s64_u32(uint32x2_t __p0) {
43288	__ai int64x1_t vreinterpret_s64_f64(float64x1_t __p0) {
43289	int64x1_t __ret;	36412	int64x1_t __ret;
43290	__ret = (int64x1_t)(__p0);	36413	__ret = (int64x1_t)(__p0);
43291	return __ret;	36414	return __ret;
43292	}	36415	}
43293	#endif	36416	__ai int64x1_t vreinterpret_s64_u64(uint64x1_t __p0) {
43294
43295	#ifdef __LITTLE_ENDIAN__
43296	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {
43297	int64x1_t __ret;	36417	int64x1_t __ret;
43298	__ret = (int64x1_t)(__p0);	36418	__ret = (int64x1_t)(__p0);
43299	return __ret;	36419	return __ret;
43300	}	36420	}
43301	#else	36421	__ai int64x1_t vreinterpret_s64_u16(uint16x4_t __p0) {
43302	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {
43303	int64x1_t __ret;	36422	int64x1_t __ret;
43304	__ret = (int64x1_t)(__p0);	36423	__ret = (int64x1_t)(__p0);
43305	return __ret;	36424	return __ret;
43306	}	36425	}
43307	#endif	36426	__ai int64x1_t vreinterpret_s64_s8(int8x8_t __p0) {
43308
43309	#ifdef __LITTLE_ENDIAN__
43310	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {
43311	int64x1_t __ret;	36427	int64x1_t __ret;
43312	__ret = (int64x1_t)(__p0);	36428	__ret = (int64x1_t)(__p0);
43313	return __ret;	36429	return __ret;
43314	}	36430	}
43315	#else	36431	__ai int64x1_t vreinterpret_s64_f64(float64x1_t __p0) {
43316	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {
43317	int64x1_t __ret;	36432	int64x1_t __ret;
43318	__ret = (int64x1_t)(__p0);	36433	__ret = (int64x1_t)(__p0);
43319	return __ret;	36434	return __ret;
43320	}	36435	}
43321	#endif	36436	__ai int64x1_t vreinterpret_s64_f32(float32x2_t __p0) {
43322
43323	#ifdef __LITTLE_ENDIAN__
43324	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {
43325	int64x1_t __ret;	36437	int64x1_t __ret;
43326	__ret = (int64x1_t)(__p0);	36438	__ret = (int64x1_t)(__p0);
43327	return __ret;	36439	return __ret;
43328	}	36440	}
43329	#else	36441	__ai int64x1_t vreinterpret_s64_f16(float16x4_t __p0) {
43330	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {
43331	int64x1_t __ret;	36442	int64x1_t __ret;
43332	__ret = (int64x1_t)(__p0);	36443	__ret = (int64x1_t)(__p0);
43333	return __ret;	36444	return __ret;
43334	}	36445	}
43335	#endif	36446	__ai int64x1_t vreinterpret_s64_s32(int32x2_t __p0) {
43336
43337	#ifdef __LITTLE_ENDIAN__
43338	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {
43339	int64x1_t __ret;	36447	int64x1_t __ret;
43340	__ret = (int64x1_t)(__p0);	36448	__ret = (int64x1_t)(__p0);
43341	return __ret;	36449	return __ret;
43342	}	36450	}
43343	#else
43344	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {	36451	__ai int64x1_t vreinterpret_s64_s16(int16x4_t __p0) {
43345	int64x1_t __ret;	36452	int64x1_t __ret;
43346	__ret = (int64x1_t)(__p0);	36453	__ret = (int64x1_t)(__p0);
43347	return __ret;	36454	return __ret;
43348	}	36455	}
43349	#endif
43350
43351	#ifdef __LITTLE_ENDIAN__
43352	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {
43353	int16x4_t __ret;
43354	__ret = (int16x4_t)(__p0);
43355	return __ret;
43356	}
43357	#else
43358	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {	36456	__ai int16x4_t vreinterpret_s16_p8(poly8x8_t __p0) {
43359	int16x4_t __ret;	36457	int16x4_t __ret;
43360	__ret = (int16x4_t)(__p0);	36458	__ret = (int16x4_t)(__p0);
43361	return __ret;	36459	return __ret;
43362	}	36460	}
43363	#endif
43364
43365	#ifdef __LITTLE_ENDIAN__
43366	__ai int16x4_t vreinterpret_s16_p64(poly64x1_t __p0) {
43367	int16x4_t __ret;
43368	__ret = (int16x4_t)(__p0);
43369	return __ret;
43370	}
43371	#else
43372	__ai int16x4_t vreinterpret_s16_p64(poly64x1_t __p0) {	36461	__ai int16x4_t vreinterpret_s16_p64(poly64x1_t __p0) {
43373	int16x4_t __ret;	36462	int16x4_t __ret;
43374	__ret = (int16x4_t)(__p0);	36463	__ret = (int16x4_t)(__p0);
43375	return __ret;	36464	return __ret;
43376	}	36465	}
43377	#endif
43378
43379	#ifdef __LITTLE_ENDIAN__
43380	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {
43381	int16x4_t __ret;
43382	__ret = (int16x4_t)(__p0);
43383	return __ret;
43384	}
43385	#else
43386	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {	36466	__ai int16x4_t vreinterpret_s16_p16(poly16x4_t __p0) {
43387	int16x4_t __ret;	36467	int16x4_t __ret;
43388	__ret = (int16x4_t)(__p0);	36468	__ret = (int16x4_t)(__p0);
43389	return __ret;	36469	return __ret;
43390	}	36470	}
43391	#endif
43392
43393	#ifdef __LITTLE_ENDIAN__
43394	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {
43395	int16x4_t __ret;
43396	__ret = (int16x4_t)(__p0);
43397	return __ret;
43398	}
43399	#else
43400	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {	36471	__ai int16x4_t vreinterpret_s16_u8(uint8x8_t __p0) {
43401	int16x4_t __ret;	36472	int16x4_t __ret;
43402	__ret = (int16x4_t)(__p0);	36473	__ret = (int16x4_t)(__p0);
43403	return __ret;	36474	return __ret;
43404	}	36475	}
43405	#endif
43406
43407	#ifdef __LITTLE_ENDIAN__
43408	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {
43409	int16x4_t __ret;
43410	__ret = (int16x4_t)(__p0);
43411	return __ret;
43412	}
43413	#else
43414	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {	36476	__ai int16x4_t vreinterpret_s16_u32(uint32x2_t __p0) {
43415	int16x4_t __ret;	36477	int16x4_t __ret;
43416	__ret = (int16x4_t)(__p0);	36478	__ret = (int16x4_t)(__p0);
43417	return __ret;	36479	return __ret;
43418	}	36480	}
43419	#endif
43420
43421	#ifdef __LITTLE_ENDIAN__
43422	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {
43423	int16x4_t __ret;
43424	__ret = (int16x4_t)(__p0);
43425	return __ret;
43426	}
43427	#else
43428	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {	36481	__ai int16x4_t vreinterpret_s16_u64(uint64x1_t __p0) {
43429	int16x4_t __ret;	36482	int16x4_t __ret;
43430	__ret = (int16x4_t)(__p0);	36483	__ret = (int16x4_t)(__p0);
43431	return __ret;	36484	return __ret;
43432	}	36485	}
43433	#endif
43434
43435	#ifdef __LITTLE_ENDIAN__
43436	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {
43437	int16x4_t __ret;
43438	__ret = (int16x4_t)(__p0);
43439	return __ret;
43440	}
43441	#else
43442	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {	36486	__ai int16x4_t vreinterpret_s16_u16(uint16x4_t __p0) {
43443	int16x4_t __ret;	36487	int16x4_t __ret;
43444	__ret = (int16x4_t)(__p0);	36488	__ret = (int16x4_t)(__p0);
43445	return __ret;	36489	return __ret;
43446	}	36490	}
43447	#endif
43448
43449	#ifdef __LITTLE_ENDIAN__
43450	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
43451	int16x4_t __ret;
43452	__ret = (int16x4_t)(__p0);
43453	return __ret;
43454	}
43455	#else
43456	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {	36491	__ai int16x4_t vreinterpret_s16_s8(int8x8_t __p0) {
43457	int16x4_t __ret;	36492	int16x4_t __ret;
43458	__ret = (int16x4_t)(__p0);	36493	__ret = (int16x4_t)(__p0);
43459	return __ret;	36494	return __ret;
43460	}	36495	}
43461	#endif
43462
43463	#ifdef __LITTLE_ENDIAN__
43464	__ai int16x4_t vreinterpret_s16_f64(float64x1_t __p0) {
43465	int16x4_t __ret;
43466	__ret = (int16x4_t)(__p0);
43467	return __ret;
43468	}
43469	#else
43470	__ai int16x4_t vreinterpret_s16_f64(float64x1_t __p0) {	36496	__ai int16x4_t vreinterpret_s16_f64(float64x1_t __p0) {
43471	int16x4_t __ret;	36497	int16x4_t __ret;
43472	__ret = (int16x4_t)(__p0);	36498	__ret = (int16x4_t)(__p0);
43473	return __ret;	36499	return __ret;
43474	}	36500	}
43475	#endif
43476
43477	#ifdef __LITTLE_ENDIAN__
43478	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {
43479	int16x4_t __ret;
43480	__ret = (int16x4_t)(__p0);
43481	return __ret;
43482	}
43483	#else
43484	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {	36501	__ai int16x4_t vreinterpret_s16_f32(float32x2_t __p0) {
43485	int16x4_t __ret;	36502	int16x4_t __ret;
43486	__ret = (int16x4_t)(__p0);	36503	__ret = (int16x4_t)(__p0);
43487	return __ret;	36504	return __ret;
43488	}	36505	}
43489	#endif
43490
43491	#ifdef __LITTLE_ENDIAN__
43492	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {
43493	int16x4_t __ret;
43494	__ret = (int16x4_t)(__p0);
43495	return __ret;
43496	}
43497	#else
43498	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {	36506	__ai int16x4_t vreinterpret_s16_f16(float16x4_t __p0) {
43499	int16x4_t __ret;	36507	int16x4_t __ret;
43500	__ret = (int16x4_t)(__p0);	36508	__ret = (int16x4_t)(__p0);
43501	return __ret;	36509	return __ret;
43502	}	36510	}
43503	#endif
43504
43505	#ifdef __LITTLE_ENDIAN__
43506	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {
43507	int16x4_t __ret;
43508	__ret = (int16x4_t)(__p0);
43509	return __ret;
43510	}
43511	#else
43512	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {	36511	__ai int16x4_t vreinterpret_s16_s32(int32x2_t __p0) {
43513	int16x4_t __ret;	36512	int16x4_t __ret;
43514	__ret = (int16x4_t)(__p0);	36513	__ret = (int16x4_t)(__p0);
43515	return __ret;	36514	return __ret;
43516	}	36515	}
43517	#endif
43518
43519	#ifdef __LITTLE_ENDIAN__
43520	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {
43521	int16x4_t __ret;
43522	__ret = (int16x4_t)(__p0);
43523	return __ret;
43524	}
43525	#else
43526	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {	36516	__ai int16x4_t vreinterpret_s16_s64(int64x1_t __p0) {
43527	int16x4_t __ret;	36517	int16x4_t __ret;
43528	__ret = (int16x4_t)(__p0);	36518	__ret = (int16x4_t)(__p0);
43529	return __ret;	36519	return __ret;
43530	}	36520	}
43531	#endif
43532
43533	#endif	36521	#endif
43534	#if __ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_DIRECTED_ROUNDING)	36522	#if __ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_DIRECTED_ROUNDING)
43535	#ifdef __LITTLE_ENDIAN__	36523	#ifdef __LITTLE_ENDIAN__
...	@@ -43548,20 +36536,11 @@ __ai float64x2_t vrndq_f64(float64x2_t __p0) {	...	@@ -43548,20 +36536,11 @@ __ai float64x2_t vrndq_f64(float64x2_t __p0) {
43548	}	36536	}
43549	#endif	36537	#endif
43550		36538
43551	#ifdef __LITTLE_ENDIAN__
43552	__ai float64x1_t vrnd_f64(float64x1_t __p0) {
43553	float64x1_t __ret;
43554	__ret = (float64x1_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 10);
43555	return __ret;
43556	}
43557	#else
43558	__ai float64x1_t vrnd_f64(float64x1_t __p0) {	36539	__ai float64x1_t vrnd_f64(float64x1_t __p0) {
43559	float64x1_t __ret;	36540	float64x1_t __ret;
43560	__ret = (float64x1_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 10);	36541	__ret = (float64x1_t) __builtin_neon_vrnd_v((int8x8_t)__p0, 10);
43561	return __ret;	36542	return __ret;
43562	}	36543	}
43563	#endif
43564
43565	#ifdef __LITTLE_ENDIAN__	36544	#ifdef __LITTLE_ENDIAN__
43566	__ai float64x2_t vrndaq_f64(float64x2_t __p0) {	36545	__ai float64x2_t vrndaq_f64(float64x2_t __p0) {
43567	float64x2_t __ret;	36546	float64x2_t __ret;
...	@@ -43578,20 +36557,11 @@ __ai float64x2_t vrndaq_f64(float64x2_t __p0) {	...	@@ -43578,20 +36557,11 @@ __ai float64x2_t vrndaq_f64(float64x2_t __p0) {
43578	}	36557	}
43579	#endif	36558	#endif
43580		36559
43581	#ifdef __LITTLE_ENDIAN__
43582	__ai float64x1_t vrnda_f64(float64x1_t __p0) {
43583	float64x1_t __ret;
43584	__ret = (float64x1_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 10);
43585	return __ret;
43586	}
43587	#else
43588	__ai float64x1_t vrnda_f64(float64x1_t __p0) {	36560	__ai float64x1_t vrnda_f64(float64x1_t __p0) {
43589	float64x1_t __ret;	36561	float64x1_t __ret;
43590	__ret = (float64x1_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 10);	36562	__ret = (float64x1_t) __builtin_neon_vrnda_v((int8x8_t)__p0, 10);
43591	return __ret;	36563	return __ret;
43592	}	36564	}
43593	#endif
43594
43595	#ifdef __LITTLE_ENDIAN__	36565	#ifdef __LITTLE_ENDIAN__
43596	__ai float64x2_t vrndiq_f64(float64x2_t __p0) {	36566	__ai float64x2_t vrndiq_f64(float64x2_t __p0) {
43597	float64x2_t __ret;	36567	float64x2_t __ret;
...	@@ -43608,20 +36578,11 @@ __ai float64x2_t vrndiq_f64(float64x2_t __p0) {	...	@@ -43608,20 +36578,11 @@ __ai float64x2_t vrndiq_f64(float64x2_t __p0) {
43608	}	36578	}
43609	#endif	36579	#endif
43610		36580
43611	#ifdef __LITTLE_ENDIAN__
43612	__ai float64x1_t vrndi_f64(float64x1_t __p0) {
43613	float64x1_t __ret;
43614	__ret = (float64x1_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 10);
43615	return __ret;
43616	}
43617	#else
43618	__ai float64x1_t vrndi_f64(float64x1_t __p0) {	36581	__ai float64x1_t vrndi_f64(float64x1_t __p0) {
43619	float64x1_t __ret;	36582	float64x1_t __ret;
43620	__ret = (float64x1_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 10);	36583	__ret = (float64x1_t) __builtin_neon_vrndi_v((int8x8_t)__p0, 10);
43621	return __ret;	36584	return __ret;
43622	}	36585	}
43623	#endif
43624
43625	#ifdef __LITTLE_ENDIAN__	36586	#ifdef __LITTLE_ENDIAN__
43626	__ai float64x2_t vrndmq_f64(float64x2_t __p0) {	36587	__ai float64x2_t vrndmq_f64(float64x2_t __p0) {
43627	float64x2_t __ret;	36588	float64x2_t __ret;
...	@@ -43638,20 +36599,11 @@ __ai float64x2_t vrndmq_f64(float64x2_t __p0) {	...	@@ -43638,20 +36599,11 @@ __ai float64x2_t vrndmq_f64(float64x2_t __p0) {
43638	}	36599	}
43639	#endif	36600	#endif
43640		36601
43641	#ifdef __LITTLE_ENDIAN__
43642	__ai float64x1_t vrndm_f64(float64x1_t __p0) {
43643	float64x1_t __ret;
43644	__ret = (float64x1_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 10);
43645	return __ret;
43646	}
43647	#else
43648	__ai float64x1_t vrndm_f64(float64x1_t __p0) {	36602	__ai float64x1_t vrndm_f64(float64x1_t __p0) {
43649	float64x1_t __ret;	36603	float64x1_t __ret;
43650	__ret = (float64x1_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 10);	36604	__ret = (float64x1_t) __builtin_neon_vrndm_v((int8x8_t)__p0, 10);
43651	return __ret;	36605	return __ret;
43652	}	36606	}
43653	#endif
43654
43655	#ifdef __LITTLE_ENDIAN__	36607	#ifdef __LITTLE_ENDIAN__
43656	__ai float64x2_t vrndnq_f64(float64x2_t __p0) {	36608	__ai float64x2_t vrndnq_f64(float64x2_t __p0) {
43657	float64x2_t __ret;	36609	float64x2_t __ret;
...	@@ -43668,20 +36620,11 @@ __ai float64x2_t vrndnq_f64(float64x2_t __p0) {	...	@@ -43668,20 +36620,11 @@ __ai float64x2_t vrndnq_f64(float64x2_t __p0) {
43668	}	36620	}
43669	#endif	36621	#endif
43670		36622
43671	#ifdef __LITTLE_ENDIAN__
43672	__ai float64x1_t vrndn_f64(float64x1_t __p0) {
43673	float64x1_t __ret;
43674	__ret = (float64x1_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 10);
43675	return __ret;
43676	}
43677	#else
43678	__ai float64x1_t vrndn_f64(float64x1_t __p0) {	36623	__ai float64x1_t vrndn_f64(float64x1_t __p0) {
43679	float64x1_t __ret;	36624	float64x1_t __ret;
43680	__ret = (float64x1_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 10);	36625	__ret = (float64x1_t) __builtin_neon_vrndn_v((int8x8_t)__p0, 10);
43681	return __ret;	36626	return __ret;
43682	}	36627	}
43683	#endif
43684
43685	#ifdef __LITTLE_ENDIAN__	36628	#ifdef __LITTLE_ENDIAN__
43686	__ai float64x2_t vrndpq_f64(float64x2_t __p0) {	36629	__ai float64x2_t vrndpq_f64(float64x2_t __p0) {
43687	float64x2_t __ret;	36630	float64x2_t __ret;
...	@@ -43698,20 +36641,11 @@ __ai float64x2_t vrndpq_f64(float64x2_t __p0) {	...	@@ -43698,20 +36641,11 @@ __ai float64x2_t vrndpq_f64(float64x2_t __p0) {
43698	}	36641	}
43699	#endif	36642	#endif
43700		36643
43701	#ifdef __LITTLE_ENDIAN__
43702	__ai float64x1_t vrndp_f64(float64x1_t __p0) {	36644	__ai float64x1_t vrndp_f64(float64x1_t __p0) {
43703	float64x1_t __ret;	36645	float64x1_t __ret;
43704	__ret = (float64x1_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 10);	36646	__ret = (float64x1_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 10);
43705	return __ret;	36647	return __ret;
43706	}	36648	}
43707	#else
43708	__ai float64x1_t vrndp_f64(float64x1_t __p0) {
43709	float64x1_t __ret;
43710	__ret = (float64x1_t) __builtin_neon_vrndp_v((int8x8_t)__p0, 10);
43711	return __ret;
43712	}
43713	#endif
43714
43715	#ifdef __LITTLE_ENDIAN__	36649	#ifdef __LITTLE_ENDIAN__
43716	__ai float64x2_t vrndxq_f64(float64x2_t __p0) {	36650	__ai float64x2_t vrndxq_f64(float64x2_t __p0) {
43717	float64x2_t __ret;	36651	float64x2_t __ret;
...	@@ -43728,20 +36662,11 @@ __ai float64x2_t vrndxq_f64(float64x2_t __p0) {	...	@@ -43728,20 +36662,11 @@ __ai float64x2_t vrndxq_f64(float64x2_t __p0) {
43728	}	36662	}
43729	#endif	36663	#endif
43730		36664
43731	#ifdef __LITTLE_ENDIAN__
43732	__ai float64x1_t vrndx_f64(float64x1_t __p0) {
43733	float64x1_t __ret;
43734	__ret = (float64x1_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 10);
43735	return __ret;
43736	}
43737	#else
43738	__ai float64x1_t vrndx_f64(float64x1_t __p0) {	36665	__ai float64x1_t vrndx_f64(float64x1_t __p0) {
43739	float64x1_t __ret;	36666	float64x1_t __ret;
43740	__ret = (float64x1_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 10);	36667	__ret = (float64x1_t) __builtin_neon_vrndx_v((int8x8_t)__p0, 10);
43741	return __ret;	36668	return __ret;
43742	}	36669	}
43743	#endif
43744
43745	#endif	36670	#endif
43746	#if __ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_NUMERIC_MAXMIN)	36671	#if __ARM_ARCH >= 8 && defined(__aarch64__) && defined(__ARM_FEATURE_NUMERIC_MAXMIN)
43747	#ifdef __LITTLE_ENDIAN__	36672	#ifdef __LITTLE_ENDIAN__
...	@@ -43761,20 +36686,11 @@ __ai float64x2_t vmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -43761,20 +36686,11 @@ __ai float64x2_t vmaxnmq_f64(float64x2_t __p0, float64x2_t __p1) {
43761	}	36686	}
43762	#endif	36687	#endif
43763		36688
43764	#ifdef __LITTLE_ENDIAN__
43765	__ai float64x1_t vmaxnm_f64(float64x1_t __p0, float64x1_t __p1) {
43766	float64x1_t __ret;
43767	__ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
43768	return __ret;
43769	}
43770	#else
43771	__ai float64x1_t vmaxnm_f64(float64x1_t __p0, float64x1_t __p1) {	36689	__ai float64x1_t vmaxnm_f64(float64x1_t __p0, float64x1_t __p1) {
43772	float64x1_t __ret;	36690	float64x1_t __ret;
43773	__ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	36691	__ret = (float64x1_t) __builtin_neon_vmaxnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
43774	return __ret;	36692	return __ret;
43775	}	36693	}
43776	#endif
43777
43778	#ifdef __LITTLE_ENDIAN__	36694	#ifdef __LITTLE_ENDIAN__
43779	__ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {	36695	__ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
43780	float64x2_t __ret;	36696	float64x2_t __ret;
...	@@ -43792,16 +36708,183 @@ __ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -43792,16 +36708,183 @@ __ai float64x2_t vminnmq_f64(float64x2_t __p0, float64x2_t __p1) {
43792	}	36708	}
43793	#endif	36709	#endif
43794		36710
43795	#ifdef __LITTLE_ENDIAN__
43796	__ai float64x1_t vminnm_f64(float64x1_t __p0, float64x1_t __p1) {	36711	__ai float64x1_t vminnm_f64(float64x1_t __p0, float64x1_t __p1) {
43797	float64x1_t __ret;	36712	float64x1_t __ret;
43798	__ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	36713	__ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
43799	return __ret;	36714	return __ret;
43800	}	36715	}
		36716	#endif
		36717	#if defined(__ARM_FEATURE_COMPLEX)
		36718	#ifdef __LITTLE_ENDIAN__
		36719	__ai float32x2_t vcadd_rot270_f32(float32x2_t __p0, float32x2_t __p1) {
		36720	float32x2_t __ret;
		36721	__ret = (float32x2_t) __builtin_neon_vcadd_rot270_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
		36722	return __ret;
		36723	}
43801	#else	36724	#else
43802	__ai float64x1_t vminnm_f64(float64x1_t __p0, float64x1_t __p1) {	36725	__ai float32x2_t vcadd_rot270_f32(float32x2_t __p0, float32x2_t __p1) {
43803	float64x1_t __ret;	36726	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
43804	__ret = (float64x1_t) __builtin_neon_vminnm_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	36727	float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
		36728	float32x2_t __ret;
		36729	__ret = (float32x2_t) __builtin_neon_vcadd_rot270_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
		36730	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
		36731	return __ret;
		36732	}
		36733	#endif
		36734
		36735	#ifdef __LITTLE_ENDIAN__
		36736	__ai float32x2_t vcadd_rot90_f32(float32x2_t __p0, float32x2_t __p1) {
		36737	float32x2_t __ret;
		36738	__ret = (float32x2_t) __builtin_neon_vcadd_rot90_v((int8x8_t)__p0, (int8x8_t)__p1, 9);
		36739	return __ret;
		36740	}
		36741	#else
		36742	__ai float32x2_t vcadd_rot90_f32(float32x2_t __p0, float32x2_t __p1) {
		36743	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
		36744	float32x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
		36745	float32x2_t __ret;
		36746	__ret = (float32x2_t) __builtin_neon_vcadd_rot90_v((int8x8_t)__rev0, (int8x8_t)__rev1, 9);
		36747	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
		36748	return __ret;
		36749	}
		36750	#endif
		36751
		36752	#ifdef __LITTLE_ENDIAN__
		36753	__ai float32x4_t vcaddq_rot270_f32(float32x4_t __p0, float32x4_t __p1) {
		36754	float32x4_t __ret;
		36755	__ret = (float32x4_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
		36756	return __ret;
		36757	}
		36758	#else
		36759	__ai float32x4_t vcaddq_rot270_f32(float32x4_t __p0, float32x4_t __p1) {
		36760	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
		36761	float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
		36762	float32x4_t __ret;
		36763	__ret = (float32x4_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__rev0, (int8x16_t)__rev1, 41);
		36764	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
		36765	return __ret;
		36766	}
		36767	#endif
		36768
		36769	#ifdef __LITTLE_ENDIAN__
		36770	__ai float32x4_t vcaddq_rot90_f32(float32x4_t __p0, float32x4_t __p1) {
		36771	float32x4_t __ret;
		36772	__ret = (float32x4_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__p0, (int8x16_t)__p1, 41);
		36773	return __ret;
		36774	}
		36775	#else
		36776	__ai float32x4_t vcaddq_rot90_f32(float32x4_t __p0, float32x4_t __p1) {
		36777	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
		36778	float32x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
		36779	float32x4_t __ret;
		36780	__ret = (float32x4_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__rev0, (int8x16_t)__rev1, 41);
		36781	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
		36782	return __ret;
		36783	}
		36784	#endif
		36785
		36786	#endif
		36787	#if defined(__ARM_FEATURE_COMPLEX) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)
		36788	#ifdef __LITTLE_ENDIAN__
		36789	__ai float16x4_t vcadd_rot270_f16(float16x4_t __p0, float16x4_t __p1) {
		36790	float16x4_t __ret;
		36791	__ret = (float16x4_t) __builtin_neon_vcadd_rot270_v((int8x8_t)__p0, (int8x8_t)__p1, 8);
		36792	return __ret;
		36793	}
		36794	#else
		36795	__ai float16x4_t vcadd_rot270_f16(float16x4_t __p0, float16x4_t __p1) {
		36796	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
		36797	float16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
		36798	float16x4_t __ret;
		36799	__ret = (float16x4_t) __builtin_neon_vcadd_rot270_v((int8x8_t)__rev0, (int8x8_t)__rev1, 8);
		36800	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
		36801	return __ret;
		36802	}
		36803	#endif
		36804
		36805	#ifdef __LITTLE_ENDIAN__
		36806	__ai float16x4_t vcadd_rot90_f16(float16x4_t __p0, float16x4_t __p1) {
		36807	float16x4_t __ret;
		36808	__ret = (float16x4_t) __builtin_neon_vcadd_rot90_v((int8x8_t)__p0, (int8x8_t)__p1, 8);
		36809	return __ret;
		36810	}
		36811	#else
		36812	__ai float16x4_t vcadd_rot90_f16(float16x4_t __p0, float16x4_t __p1) {
		36813	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
		36814	float16x4_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 3, 2, 1, 0);
		36815	float16x4_t __ret;
		36816	__ret = (float16x4_t) __builtin_neon_vcadd_rot90_v((int8x8_t)__rev0, (int8x8_t)__rev1, 8);
		36817	__ret = __builtin_shufflevector(__ret, __ret, 3, 2, 1, 0);
		36818	return __ret;
		36819	}
		36820	#endif
		36821
		36822	#ifdef __LITTLE_ENDIAN__
		36823	__ai float16x8_t vcaddq_rot270_f16(float16x8_t __p0, float16x8_t __p1) {
		36824	float16x8_t __ret;
		36825	__ret = (float16x8_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__p0, (int8x16_t)__p1, 40);
		36826	return __ret;
		36827	}
		36828	#else
		36829	__ai float16x8_t vcaddq_rot270_f16(float16x8_t __p0, float16x8_t __p1) {
		36830	float16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
		36831	float16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
		36832	float16x8_t __ret;
		36833	__ret = (float16x8_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__rev0, (int8x16_t)__rev1, 40);
		36834	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);
		36835	return __ret;
		36836	}
		36837	#endif
		36838
		36839	#ifdef __LITTLE_ENDIAN__
		36840	__ai float16x8_t vcaddq_rot90_f16(float16x8_t __p0, float16x8_t __p1) {
		36841	float16x8_t __ret;
		36842	__ret = (float16x8_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__p0, (int8x16_t)__p1, 40);
		36843	return __ret;
		36844	}
		36845	#else
		36846	__ai float16x8_t vcaddq_rot90_f16(float16x8_t __p0, float16x8_t __p1) {
		36847	float16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
		36848	float16x8_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 7, 6, 5, 4, 3, 2, 1, 0);
		36849	float16x8_t __ret;
		36850	__ret = (float16x8_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__rev0, (int8x16_t)__rev1, 40);
		36851	__ret = __builtin_shufflevector(__ret, __ret, 7, 6, 5, 4, 3, 2, 1, 0);
		36852	return __ret;
		36853	}
		36854	#endif
		36855
		36856	#endif
		36857	#if defined(__ARM_FEATURE_COMPLEX) && defined(__aarch64__)
		36858	#ifdef __LITTLE_ENDIAN__
		36859	__ai float64x2_t vcaddq_rot270_f64(float64x2_t __p0, float64x2_t __p1) {
		36860	float64x2_t __ret;
		36861	__ret = (float64x2_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
		36862	return __ret;
		36863	}
		36864	#else
		36865	__ai float64x2_t vcaddq_rot270_f64(float64x2_t __p0, float64x2_t __p1) {
		36866	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
		36867	float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
		36868	float64x2_t __ret;
		36869	__ret = (float64x2_t) __builtin_neon_vcaddq_rot270_v((int8x16_t)__rev0, (int8x16_t)__rev1, 42);
		36870	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
		36871	return __ret;
		36872	}
		36873	#endif
		36874
		36875	#ifdef __LITTLE_ENDIAN__
		36876	__ai float64x2_t vcaddq_rot90_f64(float64x2_t __p0, float64x2_t __p1) {
		36877	float64x2_t __ret;
		36878	__ret = (float64x2_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__p0, (int8x16_t)__p1, 42);
		36879	return __ret;
		36880	}
		36881	#else
		36882	__ai float64x2_t vcaddq_rot90_f64(float64x2_t __p0, float64x2_t __p1) {
		36883	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
		36884	float64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
		36885	float64x2_t __ret;
		36886	__ret = (float64x2_t) __builtin_neon_vcaddq_rot90_v((int8x16_t)__rev0, (int8x16_t)__rev1, 42);
		36887	__ret = __builtin_shufflevector(__ret, __ret, 1, 0);
43805	return __ret;	36888	return __ret;
43806	}	36889	}
43807	#endif	36890	#endif
...	@@ -46305,7 +39388,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46305,7 +39388,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46305	#define vduph_lane_f16(__p0, __p1) __extension__ ({ \	39388	#define vduph_lane_f16(__p0, __p1) __extension__ ({ \
46306	float16x4_t __s0 = __p0; \	39389	float16x4_t __s0 = __p0; \
46307	float16_t __ret; \	39390	float16_t __ret; \
46308	__ret = (float16_t) __builtin_neon_vduph_lane_f16((int8x8_t)__s0, __p1); \	39391	__ret = (float16_t) __builtin_neon_vduph_lane_f16((float16x4_t)__s0, __p1); \
46309	__ret; \	39392	__ret; \
46310	})	39393	})
46311	#else	39394	#else
...	@@ -46313,7 +39396,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46313,7 +39396,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46313	float16x4_t __s0 = __p0; \	39396	float16x4_t __s0 = __p0; \
46314	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	39397	float16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
46315	float16_t __ret; \	39398	float16_t __ret; \
46316	__ret = (float16_t) __builtin_neon_vduph_lane_f16((int8x8_t)__rev0, __p1); \	39399	__ret = (float16_t) __builtin_neon_vduph_lane_f16((float16x4_t)__rev0, __p1); \
46317	__ret; \	39400	__ret; \
46318	})	39401	})
46319	#endif	39402	#endif
...	@@ -46322,7 +39405,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46322,7 +39405,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46322	#define vduph_laneq_f16(__p0, __p1) __extension__ ({ \	39405	#define vduph_laneq_f16(__p0, __p1) __extension__ ({ \
46323	float16x8_t __s0 = __p0; \	39406	float16x8_t __s0 = __p0; \
46324	float16_t __ret; \	39407	float16_t __ret; \
46325	__ret = (float16_t) __builtin_neon_vduph_laneq_f16((int8x16_t)__s0, __p1); \	39408	__ret = (float16_t) __builtin_neon_vduph_laneq_f16((float16x8_t)__s0, __p1); \
46326	__ret; \	39409	__ret; \
46327	})	39410	})
46328	#else	39411	#else
...	@@ -46330,7 +39413,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46330,7 +39413,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46330	float16x8_t __s0 = __p0; \	39413	float16x8_t __s0 = __p0; \
46331	float16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	39414	float16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
46332	float16_t __ret; \	39415	float16_t __ret; \
46333	__ret = (float16_t) __builtin_neon_vduph_laneq_f16((int8x16_t)__rev0, __p1); \	39416	__ret = (float16_t) __builtin_neon_vduph_laneq_f16((float16x8_t)__rev0, __p1); \
46334	__ret; \	39417	__ret; \
46335	})	39418	})
46336	#endif	39419	#endif
...	@@ -46341,7 +39424,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46341,7 +39424,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46341	float16_t __s1 = __p1; \	39424	float16_t __s1 = __p1; \
46342	float16x4_t __s2 = __p2; \	39425	float16x4_t __s2 = __p2; \
46343	float16_t __ret; \	39426	float16_t __ret; \
46344	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (int8x8_t)__s2, __p3); \	39427	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (float16x4_t)__s2, __p3); \
46345	__ret; \	39428	__ret; \
46346	})	39429	})
46347	#else	39430	#else
...	@@ -46351,7 +39434,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46351,7 +39434,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46351	float16x4_t __s2 = __p2; \	39434	float16x4_t __s2 = __p2; \
46352	float16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	39435	float16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
46353	float16_t __ret; \	39436	float16_t __ret; \
46354	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (int8x8_t)__rev2, __p3); \	39437	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (float16x4_t)__rev2, __p3); \
46355	__ret; \	39438	__ret; \
46356	})	39439	})
46357	#define __noswap_vfmah_lane_f16(__p0, __p1, __p2, __p3) __extension__ ({ \	39440	#define __noswap_vfmah_lane_f16(__p0, __p1, __p2, __p3) __extension__ ({ \
...	@@ -46359,7 +39442,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46359,7 +39442,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46359	float16_t __s1 = __p1; \	39442	float16_t __s1 = __p1; \
46360	float16x4_t __s2 = __p2; \	39443	float16x4_t __s2 = __p2; \
46361	float16_t __ret; \	39444	float16_t __ret; \
46362	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (int8x8_t)__s2, __p3); \	39445	__ret = (float16_t) __builtin_neon_vfmah_lane_f16(__s0, __s1, (float16x4_t)__s2, __p3); \
46363	__ret; \	39446	__ret; \
46364	})	39447	})
46365	#endif	39448	#endif
...	@@ -46434,7 +39517,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46434,7 +39517,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46434	float16_t __s1 = __p1; \	39517	float16_t __s1 = __p1; \
46435	float16x8_t __s2 = __p2; \	39518	float16x8_t __s2 = __p2; \
46436	float16_t __ret; \	39519	float16_t __ret; \
46437	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (int8x16_t)__s2, __p3); \	39520	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (float16x8_t)__s2, __p3); \
46438	__ret; \	39521	__ret; \
46439	})	39522	})
46440	#else	39523	#else
...	@@ -46444,7 +39527,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46444,7 +39527,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46444	float16x8_t __s2 = __p2; \	39527	float16x8_t __s2 = __p2; \
46445	float16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \	39528	float16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \
46446	float16_t __ret; \	39529	float16_t __ret; \
46447	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (int8x16_t)__rev2, __p3); \	39530	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (float16x8_t)__rev2, __p3); \
46448	__ret; \	39531	__ret; \
46449	})	39532	})
46450	#define __noswap_vfmah_laneq_f16(__p0, __p1, __p2, __p3) __extension__ ({ \	39533	#define __noswap_vfmah_laneq_f16(__p0, __p1, __p2, __p3) __extension__ ({ \
...	@@ -46452,7 +39535,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46452,7 +39535,7 @@ __ai float16x4_t vdiv_f16(float16x4_t __p0, float16x4_t __p1) {
46452	float16_t __s1 = __p1; \	39535	float16_t __s1 = __p1; \
46453	float16x8_t __s2 = __p2; \	39536	float16x8_t __s2 = __p2; \
46454	float16_t __ret; \	39537	float16_t __ret; \
46455	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (int8x16_t)__s2, __p3); \	39538	__ret = (float16_t) __builtin_neon_vfmah_laneq_f16(__s0, __s1, (float16x8_t)__s2, __p3); \
46456	__ret; \	39539	__ret; \
46457	})	39540	})
46458	#endif	39541	#endif
...	@@ -46978,7 +40061,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46978,7 +40061,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {
46978	float16_t __s0 = __p0; \	40061	float16_t __s0 = __p0; \
46979	float16x4_t __s1 = __p1; \	40062	float16x4_t __s1 = __p1; \
46980	float16_t __ret; \	40063	float16_t __ret; \
46981	__ret = (float16_t) __builtin_neon_vmulxh_lane_f16(__s0, (int8x8_t)__s1, __p2); \	40064	__ret = (float16_t) __builtin_neon_vmulxh_lane_f16(__s0, (float16x4_t)__s1, __p2); \
46982	__ret; \	40065	__ret; \
46983	})	40066	})
46984	#else	40067	#else
...	@@ -46987,7 +40070,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -46987,7 +40070,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {
46987	float16x4_t __s1 = __p1; \	40070	float16x4_t __s1 = __p1; \
46988	float16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \	40071	float16x4_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 3, 2, 1, 0); \
46989	float16_t __ret; \	40072	float16_t __ret; \
46990	__ret = (float16_t) __builtin_neon_vmulxh_lane_f16(__s0, (int8x8_t)__rev1, __p2); \	40073	__ret = (float16_t) __builtin_neon_vmulxh_lane_f16(__s0, (float16x4_t)__rev1, __p2); \
46991	__ret; \	40074	__ret; \
46992	})	40075	})
46993	#endif	40076	#endif
...	@@ -47039,7 +40122,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -47039,7 +40122,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {
47039	float16_t __s0 = __p0; \	40122	float16_t __s0 = __p0; \
47040	float16x8_t __s1 = __p1; \	40123	float16x8_t __s1 = __p1; \
47041	float16_t __ret; \	40124	float16_t __ret; \
47042	__ret = (float16_t) __builtin_neon_vmulxh_laneq_f16(__s0, (int8x16_t)__s1, __p2); \	40125	__ret = (float16_t) __builtin_neon_vmulxh_laneq_f16(__s0, (float16x8_t)__s1, __p2); \
47043	__ret; \	40126	__ret; \
47044	})	40127	})
47045	#else	40128	#else
...	@@ -47048,7 +40131,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {	...	@@ -47048,7 +40131,7 @@ __ai float16x4_t __noswap_vmulx_f16(float16x4_t __p0, float16x4_t __p1) {
47048	float16x8_t __s1 = __p1; \	40131	float16x8_t __s1 = __p1; \
47049	float16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \	40132	float16x8_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 7, 6, 5, 4, 3, 2, 1, 0); \
47050	float16_t __ret; \	40133	float16_t __ret; \
47051	__ret = (float16_t) __builtin_neon_vmulxh_laneq_f16(__s0, (int8x16_t)__rev1, __p2); \	40134	__ret = (float16_t) __builtin_neon_vmulxh_laneq_f16(__s0, (float16x8_t)__rev1, __p2); \
47052	__ret; \	40135	__ret; \
47053	})	40136	})
47054	#endif	40137	#endif
...	@@ -48073,48 +41156,21 @@ __ai float64x2_t vabdq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -48073,48 +41156,21 @@ __ai float64x2_t vabdq_f64(float64x2_t __p0, float64x2_t __p1) {
48073	}	41156	}
48074	#endif	41157	#endif
48075		41158
48076	#ifdef __LITTLE_ENDIAN__
48077	__ai float64x1_t vabd_f64(float64x1_t __p0, float64x1_t __p1) {
48078	float64x1_t __ret;
48079	__ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
48080	return __ret;
48081	}
48082	#else
48083	__ai float64x1_t vabd_f64(float64x1_t __p0, float64x1_t __p1) {	41159	__ai float64x1_t vabd_f64(float64x1_t __p0, float64x1_t __p1) {
48084	float64x1_t __ret;	41160	float64x1_t __ret;
48085	__ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	41161	__ret = (float64x1_t) __builtin_neon_vabd_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
48086	return __ret;	41162	return __ret;
48087	}	41163	}
48088	#endif
48089
48090	#ifdef __LITTLE_ENDIAN__
48091	__ai float64_t vabdd_f64(float64_t __p0, float64_t __p1) {
48092	float64_t __ret;
48093	__ret = (float64_t) __builtin_neon_vabdd_f64(__p0, __p1);
48094	return __ret;
48095	}
48096	#else
48097	__ai float64_t vabdd_f64(float64_t __p0, float64_t __p1) {	41164	__ai float64_t vabdd_f64(float64_t __p0, float64_t __p1) {
48098	float64_t __ret;	41165	float64_t __ret;
48099	__ret = (float64_t) __builtin_neon_vabdd_f64(__p0, __p1);	41166	__ret = (float64_t) __builtin_neon_vabdd_f64(__p0, __p1);
48100	return __ret;	41167	return __ret;
48101	}	41168	}
48102	#endif
48103
48104	#ifdef __LITTLE_ENDIAN__
48105	__ai float32_t vabds_f32(float32_t __p0, float32_t __p1) {
48106	float32_t __ret;
48107	__ret = (float32_t) __builtin_neon_vabds_f32(__p0, __p1);
48108	return __ret;
48109	}
48110	#else
48111	__ai float32_t vabds_f32(float32_t __p0, float32_t __p1) {	41169	__ai float32_t vabds_f32(float32_t __p0, float32_t __p1) {
48112	float32_t __ret;	41170	float32_t __ret;
48113	__ret = (float32_t) __builtin_neon_vabds_f32(__p0, __p1);	41171	__ret = (float32_t) __builtin_neon_vabds_f32(__p0, __p1);
48114	return __ret;	41172	return __ret;
48115	}	41173	}
48116	#endif
48117
48118	#ifdef __LITTLE_ENDIAN__	41174	#ifdef __LITTLE_ENDIAN__
48119	__ai float64x2_t vabsq_f64(float64x2_t __p0) {	41175	__ai float64x2_t vabsq_f64(float64x2_t __p0) {
48120	float64x2_t __ret;	41176	float64x2_t __ret;
...	@@ -48147,48 +41203,21 @@ __ai int64x2_t vabsq_s64(int64x2_t __p0) {	...	@@ -48147,48 +41203,21 @@ __ai int64x2_t vabsq_s64(int64x2_t __p0) {
48147	}	41203	}
48148	#endif	41204	#endif
48149		41205
48150	#ifdef __LITTLE_ENDIAN__
48151	__ai float64x1_t vabs_f64(float64x1_t __p0) {
48152	float64x1_t __ret;
48153	__ret = (float64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 10);
48154	return __ret;
48155	}
48156	#else
48157	__ai float64x1_t vabs_f64(float64x1_t __p0) {	41206	__ai float64x1_t vabs_f64(float64x1_t __p0) {
48158	float64x1_t __ret;	41207	float64x1_t __ret;
48159	__ret = (float64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 10);	41208	__ret = (float64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 10);
48160	return __ret;	41209	return __ret;
48161	}	41210	}
48162	#endif
48163
48164	#ifdef __LITTLE_ENDIAN__
48165	__ai int64x1_t vabs_s64(int64x1_t __p0) {
48166	int64x1_t __ret;
48167	__ret = (int64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 3);
48168	return __ret;
48169	}
48170	#else
48171	__ai int64x1_t vabs_s64(int64x1_t __p0) {	41211	__ai int64x1_t vabs_s64(int64x1_t __p0) {
48172	int64x1_t __ret;	41212	int64x1_t __ret;
48173	__ret = (int64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 3);	41213	__ret = (int64x1_t) __builtin_neon_vabs_v((int8x8_t)__p0, 3);
48174	return __ret;	41214	return __ret;
48175	}	41215	}
48176	#endif
48177
48178	#ifdef __LITTLE_ENDIAN__
48179	__ai int64_t vabsd_s64(int64_t __p0) {
48180	int64_t __ret;
48181	__ret = (int64_t) __builtin_neon_vabsd_s64(__p0);
48182	return __ret;
48183	}
48184	#else
48185	__ai int64_t vabsd_s64(int64_t __p0) {	41216	__ai int64_t vabsd_s64(int64_t __p0) {
48186	int64_t __ret;	41217	int64_t __ret;
48187	__ret = (int64_t) __builtin_neon_vabsd_s64(__p0);	41218	__ret = (int64_t) __builtin_neon_vabsd_s64(__p0);
48188	return __ret;	41219	return __ret;
48189	}	41220	}
48190	#endif
48191
48192	#ifdef __LITTLE_ENDIAN__	41221	#ifdef __LITTLE_ENDIAN__
48193	__ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {	41222	__ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {
48194	float64x2_t __ret;	41223	float64x2_t __ret;
...	@@ -48206,48 +41235,21 @@ __ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -48206,48 +41235,21 @@ __ai float64x2_t vaddq_f64(float64x2_t __p0, float64x2_t __p1) {
48206	}	41235	}
48207	#endif	41236	#endif
48208		41237
48209	#ifdef __LITTLE_ENDIAN__
48210	__ai float64x1_t vadd_f64(float64x1_t __p0, float64x1_t __p1) {
48211	float64x1_t __ret;
48212	__ret = __p0 + __p1;
48213	return __ret;
48214	}
48215	#else
48216	__ai float64x1_t vadd_f64(float64x1_t __p0, float64x1_t __p1) {	41238	__ai float64x1_t vadd_f64(float64x1_t __p0, float64x1_t __p1) {
48217	float64x1_t __ret;	41239	float64x1_t __ret;
48218	__ret = __p0 + __p1;	41240	__ret = __p0 + __p1;
48219	return __ret;	41241	return __ret;
48220	}	41242	}
48221	#endif
48222
48223	#ifdef __LITTLE_ENDIAN__
48224	__ai uint64_t vaddd_u64(uint64_t __p0, uint64_t __p1) {
48225	uint64_t __ret;
48226	__ret = (uint64_t) __builtin_neon_vaddd_u64(__p0, __p1);
48227	return __ret;
48228	}
48229	#else
48230	__ai uint64_t vaddd_u64(uint64_t __p0, uint64_t __p1) {	41243	__ai uint64_t vaddd_u64(uint64_t __p0, uint64_t __p1) {
48231	uint64_t __ret;	41244	uint64_t __ret;
48232	__ret = (uint64_t) __builtin_neon_vaddd_u64(__p0, __p1);	41245	__ret = (uint64_t) __builtin_neon_vaddd_u64(__p0, __p1);
48233	return __ret;	41246	return __ret;
48234	}	41247	}
48235	#endif
48236
48237	#ifdef __LITTLE_ENDIAN__
48238	__ai int64_t vaddd_s64(int64_t __p0, int64_t __p1) {
48239	int64_t __ret;
48240	__ret = (int64_t) __builtin_neon_vaddd_s64(__p0, __p1);
48241	return __ret;
48242	}
48243	#else
48244	__ai int64_t vaddd_s64(int64_t __p0, int64_t __p1) {	41248	__ai int64_t vaddd_s64(int64_t __p0, int64_t __p1) {
48245	int64_t __ret;	41249	int64_t __ret;
48246	__ret = (int64_t) __builtin_neon_vaddd_s64(__p0, __p1);	41250	__ret = (int64_t) __builtin_neon_vaddd_s64(__p0, __p1);
48247	return __ret;	41251	return __ret;
48248	}	41252	}
48249	#endif
48250
48251	#ifdef __LITTLE_ENDIAN__	41253	#ifdef __LITTLE_ENDIAN__
48252	__ai uint16x8_t vaddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {	41254	__ai uint16x8_t vaddhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
48253	uint16x8_t __ret;	41255	uint16x8_t __ret;
...	@@ -48359,14 +41361,14 @@ __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -48359,14 +41361,14 @@ __ai int8x16_t vaddhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
48359	#ifdef __LITTLE_ENDIAN__	41361	#ifdef __LITTLE_ENDIAN__
48360	__ai uint16_t vaddlvq_u8(uint8x16_t __p0) {	41362	__ai uint16_t vaddlvq_u8(uint8x16_t __p0) {
48361	uint16_t __ret;	41363	uint16_t __ret;
48362	__ret = (uint16_t) __builtin_neon_vaddlvq_u8((int8x16_t)__p0);	41364	__ret = (uint16_t) __builtin_neon_vaddlvq_u8(__p0);
48363	return __ret;	41365	return __ret;
48364	}	41366	}
48365	#else	41367	#else
48366	__ai uint16_t vaddlvq_u8(uint8x16_t __p0) {	41368	__ai uint16_t vaddlvq_u8(uint8x16_t __p0) {
48367	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	41369	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
48368	uint16_t __ret;	41370	uint16_t __ret;
48369	__ret = (uint16_t) __builtin_neon_vaddlvq_u8((int8x16_t)__rev0);	41371	__ret = (uint16_t) __builtin_neon_vaddlvq_u8(__rev0);
48370	return __ret;	41372	return __ret;
48371	}	41373	}
48372	#endif	41374	#endif
...	@@ -48374,14 +41376,14 @@ __ai uint16_t vaddlvq_u8(uint8x16_t __p0) {	...	@@ -48374,14 +41376,14 @@ __ai uint16_t vaddlvq_u8(uint8x16_t __p0) {
48374	#ifdef __LITTLE_ENDIAN__	41376	#ifdef __LITTLE_ENDIAN__
48375	__ai uint64_t vaddlvq_u32(uint32x4_t __p0) {	41377	__ai uint64_t vaddlvq_u32(uint32x4_t __p0) {
48376	uint64_t __ret;	41378	uint64_t __ret;
48377	__ret = (uint64_t) __builtin_neon_vaddlvq_u32((int8x16_t)__p0);	41379	__ret = (uint64_t) __builtin_neon_vaddlvq_u32(__p0);
48378	return __ret;	41380	return __ret;
48379	}	41381	}
48380	#else	41382	#else
48381	__ai uint64_t vaddlvq_u32(uint32x4_t __p0) {	41383	__ai uint64_t vaddlvq_u32(uint32x4_t __p0) {
48382	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41384	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48383	uint64_t __ret;	41385	uint64_t __ret;
48384	__ret = (uint64_t) __builtin_neon_vaddlvq_u32((int8x16_t)__rev0);	41386	__ret = (uint64_t) __builtin_neon_vaddlvq_u32(__rev0);
48385	return __ret;	41387	return __ret;
48386	}	41388	}
48387	#endif	41389	#endif
...	@@ -48389,14 +41391,14 @@ __ai uint64_t vaddlvq_u32(uint32x4_t __p0) {	...	@@ -48389,14 +41391,14 @@ __ai uint64_t vaddlvq_u32(uint32x4_t __p0) {
48389	#ifdef __LITTLE_ENDIAN__	41391	#ifdef __LITTLE_ENDIAN__
48390	__ai uint32_t vaddlvq_u16(uint16x8_t __p0) {	41392	__ai uint32_t vaddlvq_u16(uint16x8_t __p0) {
48391	uint32_t __ret;	41393	uint32_t __ret;
48392	__ret = (uint32_t) __builtin_neon_vaddlvq_u16((int8x16_t)__p0);	41394	__ret = (uint32_t) __builtin_neon_vaddlvq_u16(__p0);
48393	return __ret;	41395	return __ret;
48394	}	41396	}
48395	#else	41397	#else
48396	__ai uint32_t vaddlvq_u16(uint16x8_t __p0) {	41398	__ai uint32_t vaddlvq_u16(uint16x8_t __p0) {
48397	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41399	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48398	uint32_t __ret;	41400	uint32_t __ret;
48399	__ret = (uint32_t) __builtin_neon_vaddlvq_u16((int8x16_t)__rev0);	41401	__ret = (uint32_t) __builtin_neon_vaddlvq_u16(__rev0);
48400	return __ret;	41402	return __ret;
48401	}	41403	}
48402	#endif	41404	#endif
...	@@ -48404,14 +41406,14 @@ __ai uint32_t vaddlvq_u16(uint16x8_t __p0) {	...	@@ -48404,14 +41406,14 @@ __ai uint32_t vaddlvq_u16(uint16x8_t __p0) {
48404	#ifdef __LITTLE_ENDIAN__	41406	#ifdef __LITTLE_ENDIAN__
48405	__ai int16_t vaddlvq_s8(int8x16_t __p0) {	41407	__ai int16_t vaddlvq_s8(int8x16_t __p0) {
48406	int16_t __ret;	41408	int16_t __ret;
48407	__ret = (int16_t) __builtin_neon_vaddlvq_s8((int8x16_t)__p0);	41409	__ret = (int16_t) __builtin_neon_vaddlvq_s8(__p0);
48408	return __ret;	41410	return __ret;
48409	}	41411	}
48410	#else	41412	#else
48411	__ai int16_t vaddlvq_s8(int8x16_t __p0) {	41413	__ai int16_t vaddlvq_s8(int8x16_t __p0) {
48412	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	41414	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
48413	int16_t __ret;	41415	int16_t __ret;
48414	__ret = (int16_t) __builtin_neon_vaddlvq_s8((int8x16_t)__rev0);	41416	__ret = (int16_t) __builtin_neon_vaddlvq_s8(__rev0);
48415	return __ret;	41417	return __ret;
48416	}	41418	}
48417	#endif	41419	#endif
...	@@ -48419,14 +41421,14 @@ __ai int16_t vaddlvq_s8(int8x16_t __p0) {	...	@@ -48419,14 +41421,14 @@ __ai int16_t vaddlvq_s8(int8x16_t __p0) {
48419	#ifdef __LITTLE_ENDIAN__	41421	#ifdef __LITTLE_ENDIAN__
48420	__ai int64_t vaddlvq_s32(int32x4_t __p0) {	41422	__ai int64_t vaddlvq_s32(int32x4_t __p0) {
48421	int64_t __ret;	41423	int64_t __ret;
48422	__ret = (int64_t) __builtin_neon_vaddlvq_s32((int8x16_t)__p0);	41424	__ret = (int64_t) __builtin_neon_vaddlvq_s32(__p0);
48423	return __ret;	41425	return __ret;
48424	}	41426	}
48425	#else	41427	#else
48426	__ai int64_t vaddlvq_s32(int32x4_t __p0) {	41428	__ai int64_t vaddlvq_s32(int32x4_t __p0) {
48427	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41429	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48428	int64_t __ret;	41430	int64_t __ret;
48429	__ret = (int64_t) __builtin_neon_vaddlvq_s32((int8x16_t)__rev0);	41431	__ret = (int64_t) __builtin_neon_vaddlvq_s32(__rev0);
48430	return __ret;	41432	return __ret;
48431	}	41433	}
48432	#endif	41434	#endif
...	@@ -48434,14 +41436,14 @@ __ai int64_t vaddlvq_s32(int32x4_t __p0) {	...	@@ -48434,14 +41436,14 @@ __ai int64_t vaddlvq_s32(int32x4_t __p0) {
48434	#ifdef __LITTLE_ENDIAN__	41436	#ifdef __LITTLE_ENDIAN__
48435	__ai int32_t vaddlvq_s16(int16x8_t __p0) {	41437	__ai int32_t vaddlvq_s16(int16x8_t __p0) {
48436	int32_t __ret;	41438	int32_t __ret;
48437	__ret = (int32_t) __builtin_neon_vaddlvq_s16((int8x16_t)__p0);	41439	__ret = (int32_t) __builtin_neon_vaddlvq_s16(__p0);
48438	return __ret;	41440	return __ret;
48439	}	41441	}
48440	#else	41442	#else
48441	__ai int32_t vaddlvq_s16(int16x8_t __p0) {	41443	__ai int32_t vaddlvq_s16(int16x8_t __p0) {
48442	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41444	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48443	int32_t __ret;	41445	int32_t __ret;
48444	__ret = (int32_t) __builtin_neon_vaddlvq_s16((int8x16_t)__rev0);	41446	__ret = (int32_t) __builtin_neon_vaddlvq_s16(__rev0);
48445	return __ret;	41447	return __ret;
48446	}	41448	}
48447	#endif	41449	#endif
...	@@ -48449,14 +41451,14 @@ __ai int32_t vaddlvq_s16(int16x8_t __p0) {	...	@@ -48449,14 +41451,14 @@ __ai int32_t vaddlvq_s16(int16x8_t __p0) {
48449	#ifdef __LITTLE_ENDIAN__	41451	#ifdef __LITTLE_ENDIAN__
48450	__ai uint16_t vaddlv_u8(uint8x8_t __p0) {	41452	__ai uint16_t vaddlv_u8(uint8x8_t __p0) {
48451	uint16_t __ret;	41453	uint16_t __ret;
48452	__ret = (uint16_t) __builtin_neon_vaddlv_u8((int8x8_t)__p0);	41454	__ret = (uint16_t) __builtin_neon_vaddlv_u8(__p0);
48453	return __ret;	41455	return __ret;
48454	}	41456	}
48455	#else	41457	#else
48456	__ai uint16_t vaddlv_u8(uint8x8_t __p0) {	41458	__ai uint16_t vaddlv_u8(uint8x8_t __p0) {
48457	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41459	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48458	uint16_t __ret;	41460	uint16_t __ret;
48459	__ret = (uint16_t) __builtin_neon_vaddlv_u8((int8x8_t)__rev0);	41461	__ret = (uint16_t) __builtin_neon_vaddlv_u8(__rev0);
48460	return __ret;	41462	return __ret;
48461	}	41463	}
48462	#endif	41464	#endif
...	@@ -48464,14 +41466,14 @@ __ai uint16_t vaddlv_u8(uint8x8_t __p0) {	...	@@ -48464,14 +41466,14 @@ __ai uint16_t vaddlv_u8(uint8x8_t __p0) {
48464	#ifdef __LITTLE_ENDIAN__	41466	#ifdef __LITTLE_ENDIAN__
48465	__ai uint64_t vaddlv_u32(uint32x2_t __p0) {	41467	__ai uint64_t vaddlv_u32(uint32x2_t __p0) {
48466	uint64_t __ret;	41468	uint64_t __ret;
48467	__ret = (uint64_t) __builtin_neon_vaddlv_u32((int8x8_t)__p0);	41469	__ret = (uint64_t) __builtin_neon_vaddlv_u32(__p0);
48468	return __ret;	41470	return __ret;
48469	}	41471	}
48470	#else	41472	#else
48471	__ai uint64_t vaddlv_u32(uint32x2_t __p0) {	41473	__ai uint64_t vaddlv_u32(uint32x2_t __p0) {
48472	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41474	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48473	uint64_t __ret;	41475	uint64_t __ret;
48474	__ret = (uint64_t) __builtin_neon_vaddlv_u32((int8x8_t)__rev0);	41476	__ret = (uint64_t) __builtin_neon_vaddlv_u32(__rev0);
48475	return __ret;	41477	return __ret;
48476	}	41478	}
48477	#endif	41479	#endif
...	@@ -48479,14 +41481,14 @@ __ai uint64_t vaddlv_u32(uint32x2_t __p0) {	...	@@ -48479,14 +41481,14 @@ __ai uint64_t vaddlv_u32(uint32x2_t __p0) {
48479	#ifdef __LITTLE_ENDIAN__	41481	#ifdef __LITTLE_ENDIAN__
48480	__ai uint32_t vaddlv_u16(uint16x4_t __p0) {	41482	__ai uint32_t vaddlv_u16(uint16x4_t __p0) {
48481	uint32_t __ret;	41483	uint32_t __ret;
48482	__ret = (uint32_t) __builtin_neon_vaddlv_u16((int8x8_t)__p0);	41484	__ret = (uint32_t) __builtin_neon_vaddlv_u16(__p0);
48483	return __ret;	41485	return __ret;
48484	}	41486	}
48485	#else	41487	#else
48486	__ai uint32_t vaddlv_u16(uint16x4_t __p0) {	41488	__ai uint32_t vaddlv_u16(uint16x4_t __p0) {
48487	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41489	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48488	uint32_t __ret;	41490	uint32_t __ret;
48489	__ret = (uint32_t) __builtin_neon_vaddlv_u16((int8x8_t)__rev0);	41491	__ret = (uint32_t) __builtin_neon_vaddlv_u16(__rev0);
48490	return __ret;	41492	return __ret;
48491	}	41493	}
48492	#endif	41494	#endif
...	@@ -48494,14 +41496,14 @@ __ai uint32_t vaddlv_u16(uint16x4_t __p0) {	...	@@ -48494,14 +41496,14 @@ __ai uint32_t vaddlv_u16(uint16x4_t __p0) {
48494	#ifdef __LITTLE_ENDIAN__	41496	#ifdef __LITTLE_ENDIAN__
48495	__ai int16_t vaddlv_s8(int8x8_t __p0) {	41497	__ai int16_t vaddlv_s8(int8x8_t __p0) {
48496	int16_t __ret;	41498	int16_t __ret;
48497	__ret = (int16_t) __builtin_neon_vaddlv_s8((int8x8_t)__p0);	41499	__ret = (int16_t) __builtin_neon_vaddlv_s8(__p0);
48498	return __ret;	41500	return __ret;
48499	}	41501	}
48500	#else	41502	#else
48501	__ai int16_t vaddlv_s8(int8x8_t __p0) {	41503	__ai int16_t vaddlv_s8(int8x8_t __p0) {
48502	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41504	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48503	int16_t __ret;	41505	int16_t __ret;
48504	__ret = (int16_t) __builtin_neon_vaddlv_s8((int8x8_t)__rev0);	41506	__ret = (int16_t) __builtin_neon_vaddlv_s8(__rev0);
48505	return __ret;	41507	return __ret;
48506	}	41508	}
48507	#endif	41509	#endif
...	@@ -48509,14 +41511,14 @@ __ai int16_t vaddlv_s8(int8x8_t __p0) {	...	@@ -48509,14 +41511,14 @@ __ai int16_t vaddlv_s8(int8x8_t __p0) {
48509	#ifdef __LITTLE_ENDIAN__	41511	#ifdef __LITTLE_ENDIAN__
48510	__ai int64_t vaddlv_s32(int32x2_t __p0) {	41512	__ai int64_t vaddlv_s32(int32x2_t __p0) {
48511	int64_t __ret;	41513	int64_t __ret;
48512	__ret = (int64_t) __builtin_neon_vaddlv_s32((int8x8_t)__p0);	41514	__ret = (int64_t) __builtin_neon_vaddlv_s32(__p0);
48513	return __ret;	41515	return __ret;
48514	}	41516	}
48515	#else	41517	#else
48516	__ai int64_t vaddlv_s32(int32x2_t __p0) {	41518	__ai int64_t vaddlv_s32(int32x2_t __p0) {
48517	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41519	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48518	int64_t __ret;	41520	int64_t __ret;
48519	__ret = (int64_t) __builtin_neon_vaddlv_s32((int8x8_t)__rev0);	41521	__ret = (int64_t) __builtin_neon_vaddlv_s32(__rev0);
48520	return __ret;	41522	return __ret;
48521	}	41523	}
48522	#endif	41524	#endif
...	@@ -48524,14 +41526,14 @@ __ai int64_t vaddlv_s32(int32x2_t __p0) {	...	@@ -48524,14 +41526,14 @@ __ai int64_t vaddlv_s32(int32x2_t __p0) {
48524	#ifdef __LITTLE_ENDIAN__	41526	#ifdef __LITTLE_ENDIAN__
48525	__ai int32_t vaddlv_s16(int16x4_t __p0) {	41527	__ai int32_t vaddlv_s16(int16x4_t __p0) {
48526	int32_t __ret;	41528	int32_t __ret;
48527	__ret = (int32_t) __builtin_neon_vaddlv_s16((int8x8_t)__p0);	41529	__ret = (int32_t) __builtin_neon_vaddlv_s16(__p0);
48528	return __ret;	41530	return __ret;
48529	}	41531	}
48530	#else	41532	#else
48531	__ai int32_t vaddlv_s16(int16x4_t __p0) {	41533	__ai int32_t vaddlv_s16(int16x4_t __p0) {
48532	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41534	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48533	int32_t __ret;	41535	int32_t __ret;
48534	__ret = (int32_t) __builtin_neon_vaddlv_s16((int8x8_t)__rev0);	41536	__ret = (int32_t) __builtin_neon_vaddlv_s16(__rev0);
48535	return __ret;	41537	return __ret;
48536	}	41538	}
48537	#endif	41539	#endif
...	@@ -48539,14 +41541,14 @@ __ai int32_t vaddlv_s16(int16x4_t __p0) {	...	@@ -48539,14 +41541,14 @@ __ai int32_t vaddlv_s16(int16x4_t __p0) {
48539	#ifdef __LITTLE_ENDIAN__	41541	#ifdef __LITTLE_ENDIAN__
48540	__ai uint8_t vaddvq_u8(uint8x16_t __p0) {	41542	__ai uint8_t vaddvq_u8(uint8x16_t __p0) {
48541	uint8_t __ret;	41543	uint8_t __ret;
48542	__ret = (uint8_t) __builtin_neon_vaddvq_u8((int8x16_t)__p0);	41544	__ret = (uint8_t) __builtin_neon_vaddvq_u8(__p0);
48543	return __ret;	41545	return __ret;
48544	}	41546	}
48545	#else	41547	#else
48546	__ai uint8_t vaddvq_u8(uint8x16_t __p0) {	41548	__ai uint8_t vaddvq_u8(uint8x16_t __p0) {
48547	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	41549	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
48548	uint8_t __ret;	41550	uint8_t __ret;
48549	__ret = (uint8_t) __builtin_neon_vaddvq_u8((int8x16_t)__rev0);	41551	__ret = (uint8_t) __builtin_neon_vaddvq_u8(__rev0);
48550	return __ret;	41552	return __ret;
48551	}	41553	}
48552	#endif	41554	#endif
...	@@ -48554,14 +41556,14 @@ __ai uint8_t vaddvq_u8(uint8x16_t __p0) {	...	@@ -48554,14 +41556,14 @@ __ai uint8_t vaddvq_u8(uint8x16_t __p0) {
48554	#ifdef __LITTLE_ENDIAN__	41556	#ifdef __LITTLE_ENDIAN__
48555	__ai uint32_t vaddvq_u32(uint32x4_t __p0) {	41557	__ai uint32_t vaddvq_u32(uint32x4_t __p0) {
48556	uint32_t __ret;	41558	uint32_t __ret;
48557	__ret = (uint32_t) __builtin_neon_vaddvq_u32((int8x16_t)__p0);	41559	__ret = (uint32_t) __builtin_neon_vaddvq_u32(__p0);
48558	return __ret;	41560	return __ret;
48559	}	41561	}
48560	#else	41562	#else
48561	__ai uint32_t vaddvq_u32(uint32x4_t __p0) {	41563	__ai uint32_t vaddvq_u32(uint32x4_t __p0) {
48562	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41564	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48563	uint32_t __ret;	41565	uint32_t __ret;
48564	__ret = (uint32_t) __builtin_neon_vaddvq_u32((int8x16_t)__rev0);	41566	__ret = (uint32_t) __builtin_neon_vaddvq_u32(__rev0);
48565	return __ret;	41567	return __ret;
48566	}	41568	}
48567	#endif	41569	#endif
...	@@ -48569,14 +41571,14 @@ __ai uint32_t vaddvq_u32(uint32x4_t __p0) {	...	@@ -48569,14 +41571,14 @@ __ai uint32_t vaddvq_u32(uint32x4_t __p0) {
48569	#ifdef __LITTLE_ENDIAN__	41571	#ifdef __LITTLE_ENDIAN__
48570	__ai uint64_t vaddvq_u64(uint64x2_t __p0) {	41572	__ai uint64_t vaddvq_u64(uint64x2_t __p0) {
48571	uint64_t __ret;	41573	uint64_t __ret;
48572	__ret = (uint64_t) __builtin_neon_vaddvq_u64((int8x16_t)__p0);	41574	__ret = (uint64_t) __builtin_neon_vaddvq_u64(__p0);
48573	return __ret;	41575	return __ret;
48574	}	41576	}
48575	#else	41577	#else
48576	__ai uint64_t vaddvq_u64(uint64x2_t __p0) {	41578	__ai uint64_t vaddvq_u64(uint64x2_t __p0) {
48577	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41579	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48578	uint64_t __ret;	41580	uint64_t __ret;
48579	__ret = (uint64_t) __builtin_neon_vaddvq_u64((int8x16_t)__rev0);	41581	__ret = (uint64_t) __builtin_neon_vaddvq_u64(__rev0);
48580	return __ret;	41582	return __ret;
48581	}	41583	}
48582	#endif	41584	#endif
...	@@ -48584,14 +41586,14 @@ __ai uint64_t vaddvq_u64(uint64x2_t __p0) {	...	@@ -48584,14 +41586,14 @@ __ai uint64_t vaddvq_u64(uint64x2_t __p0) {
48584	#ifdef __LITTLE_ENDIAN__	41586	#ifdef __LITTLE_ENDIAN__
48585	__ai uint16_t vaddvq_u16(uint16x8_t __p0) {	41587	__ai uint16_t vaddvq_u16(uint16x8_t __p0) {
48586	uint16_t __ret;	41588	uint16_t __ret;
48587	__ret = (uint16_t) __builtin_neon_vaddvq_u16((int8x16_t)__p0);	41589	__ret = (uint16_t) __builtin_neon_vaddvq_u16(__p0);
48588	return __ret;	41590	return __ret;
48589	}	41591	}
48590	#else	41592	#else
48591	__ai uint16_t vaddvq_u16(uint16x8_t __p0) {	41593	__ai uint16_t vaddvq_u16(uint16x8_t __p0) {
48592	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41594	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48593	uint16_t __ret;	41595	uint16_t __ret;
48594	__ret = (uint16_t) __builtin_neon_vaddvq_u16((int8x16_t)__rev0);	41596	__ret = (uint16_t) __builtin_neon_vaddvq_u16(__rev0);
48595	return __ret;	41597	return __ret;
48596	}	41598	}
48597	#endif	41599	#endif
...	@@ -48599,14 +41601,14 @@ __ai uint16_t vaddvq_u16(uint16x8_t __p0) {	...	@@ -48599,14 +41601,14 @@ __ai uint16_t vaddvq_u16(uint16x8_t __p0) {
48599	#ifdef __LITTLE_ENDIAN__	41601	#ifdef __LITTLE_ENDIAN__
48600	__ai int8_t vaddvq_s8(int8x16_t __p0) {	41602	__ai int8_t vaddvq_s8(int8x16_t __p0) {
48601	int8_t __ret;	41603	int8_t __ret;
48602	__ret = (int8_t) __builtin_neon_vaddvq_s8((int8x16_t)__p0);	41604	__ret = (int8_t) __builtin_neon_vaddvq_s8(__p0);
48603	return __ret;	41605	return __ret;
48604	}	41606	}
48605	#else	41607	#else
48606	__ai int8_t vaddvq_s8(int8x16_t __p0) {	41608	__ai int8_t vaddvq_s8(int8x16_t __p0) {
48607	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	41609	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
48608	int8_t __ret;	41610	int8_t __ret;
48609	__ret = (int8_t) __builtin_neon_vaddvq_s8((int8x16_t)__rev0);	41611	__ret = (int8_t) __builtin_neon_vaddvq_s8(__rev0);
48610	return __ret;	41612	return __ret;
48611	}	41613	}
48612	#endif	41614	#endif
...	@@ -48614,14 +41616,14 @@ __ai int8_t vaddvq_s8(int8x16_t __p0) {	...	@@ -48614,14 +41616,14 @@ __ai int8_t vaddvq_s8(int8x16_t __p0) {
48614	#ifdef __LITTLE_ENDIAN__	41616	#ifdef __LITTLE_ENDIAN__
48615	__ai float64_t vaddvq_f64(float64x2_t __p0) {	41617	__ai float64_t vaddvq_f64(float64x2_t __p0) {
48616	float64_t __ret;	41618	float64_t __ret;
48617	__ret = (float64_t) __builtin_neon_vaddvq_f64((int8x16_t)__p0);	41619	__ret = (float64_t) __builtin_neon_vaddvq_f64(__p0);
48618	return __ret;	41620	return __ret;
48619	}	41621	}
48620	#else	41622	#else
48621	__ai float64_t vaddvq_f64(float64x2_t __p0) {	41623	__ai float64_t vaddvq_f64(float64x2_t __p0) {
48622	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41624	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48623	float64_t __ret;	41625	float64_t __ret;
48624	__ret = (float64_t) __builtin_neon_vaddvq_f64((int8x16_t)__rev0);	41626	__ret = (float64_t) __builtin_neon_vaddvq_f64(__rev0);
48625	return __ret;	41627	return __ret;
48626	}	41628	}
48627	#endif	41629	#endif
...	@@ -48629,14 +41631,14 @@ __ai float64_t vaddvq_f64(float64x2_t __p0) {	...	@@ -48629,14 +41631,14 @@ __ai float64_t vaddvq_f64(float64x2_t __p0) {
48629	#ifdef __LITTLE_ENDIAN__	41631	#ifdef __LITTLE_ENDIAN__
48630	__ai float32_t vaddvq_f32(float32x4_t __p0) {	41632	__ai float32_t vaddvq_f32(float32x4_t __p0) {
48631	float32_t __ret;	41633	float32_t __ret;
48632	__ret = (float32_t) __builtin_neon_vaddvq_f32((int8x16_t)__p0);	41634	__ret = (float32_t) __builtin_neon_vaddvq_f32(__p0);
48633	return __ret;	41635	return __ret;
48634	}	41636	}
48635	#else	41637	#else
48636	__ai float32_t vaddvq_f32(float32x4_t __p0) {	41638	__ai float32_t vaddvq_f32(float32x4_t __p0) {
48637	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41639	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48638	float32_t __ret;	41640	float32_t __ret;
48639	__ret = (float32_t) __builtin_neon_vaddvq_f32((int8x16_t)__rev0);	41641	__ret = (float32_t) __builtin_neon_vaddvq_f32(__rev0);
48640	return __ret;	41642	return __ret;
48641	}	41643	}
48642	#endif	41644	#endif
...	@@ -48644,14 +41646,14 @@ __ai float32_t vaddvq_f32(float32x4_t __p0) {	...	@@ -48644,14 +41646,14 @@ __ai float32_t vaddvq_f32(float32x4_t __p0) {
48644	#ifdef __LITTLE_ENDIAN__	41646	#ifdef __LITTLE_ENDIAN__
48645	__ai int32_t vaddvq_s32(int32x4_t __p0) {	41647	__ai int32_t vaddvq_s32(int32x4_t __p0) {
48646	int32_t __ret;	41648	int32_t __ret;
48647	__ret = (int32_t) __builtin_neon_vaddvq_s32((int8x16_t)__p0);	41649	__ret = (int32_t) __builtin_neon_vaddvq_s32(__p0);
48648	return __ret;	41650	return __ret;
48649	}	41651	}
48650	#else	41652	#else
48651	__ai int32_t vaddvq_s32(int32x4_t __p0) {	41653	__ai int32_t vaddvq_s32(int32x4_t __p0) {
48652	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41654	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48653	int32_t __ret;	41655	int32_t __ret;
48654	__ret = (int32_t) __builtin_neon_vaddvq_s32((int8x16_t)__rev0);	41656	__ret = (int32_t) __builtin_neon_vaddvq_s32(__rev0);
48655	return __ret;	41657	return __ret;
48656	}	41658	}
48657	#endif	41659	#endif
...	@@ -48659,14 +41661,14 @@ __ai int32_t vaddvq_s32(int32x4_t __p0) {	...	@@ -48659,14 +41661,14 @@ __ai int32_t vaddvq_s32(int32x4_t __p0) {
48659	#ifdef __LITTLE_ENDIAN__	41661	#ifdef __LITTLE_ENDIAN__
48660	__ai int64_t vaddvq_s64(int64x2_t __p0) {	41662	__ai int64_t vaddvq_s64(int64x2_t __p0) {
48661	int64_t __ret;	41663	int64_t __ret;
48662	__ret = (int64_t) __builtin_neon_vaddvq_s64((int8x16_t)__p0);	41664	__ret = (int64_t) __builtin_neon_vaddvq_s64(__p0);
48663	return __ret;	41665	return __ret;
48664	}	41666	}
48665	#else	41667	#else
48666	__ai int64_t vaddvq_s64(int64x2_t __p0) {	41668	__ai int64_t vaddvq_s64(int64x2_t __p0) {
48667	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41669	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48668	int64_t __ret;	41670	int64_t __ret;
48669	__ret = (int64_t) __builtin_neon_vaddvq_s64((int8x16_t)__rev0);	41671	__ret = (int64_t) __builtin_neon_vaddvq_s64(__rev0);
48670	return __ret;	41672	return __ret;
48671	}	41673	}
48672	#endif	41674	#endif
...	@@ -48674,14 +41676,14 @@ __ai int64_t vaddvq_s64(int64x2_t __p0) {	...	@@ -48674,14 +41676,14 @@ __ai int64_t vaddvq_s64(int64x2_t __p0) {
48674	#ifdef __LITTLE_ENDIAN__	41676	#ifdef __LITTLE_ENDIAN__
48675	__ai int16_t vaddvq_s16(int16x8_t __p0) {	41677	__ai int16_t vaddvq_s16(int16x8_t __p0) {
48676	int16_t __ret;	41678	int16_t __ret;
48677	__ret = (int16_t) __builtin_neon_vaddvq_s16((int8x16_t)__p0);	41679	__ret = (int16_t) __builtin_neon_vaddvq_s16(__p0);
48678	return __ret;	41680	return __ret;
48679	}	41681	}
48680	#else	41682	#else
48681	__ai int16_t vaddvq_s16(int16x8_t __p0) {	41683	__ai int16_t vaddvq_s16(int16x8_t __p0) {
48682	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41684	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48683	int16_t __ret;	41685	int16_t __ret;
48684	__ret = (int16_t) __builtin_neon_vaddvq_s16((int8x16_t)__rev0);	41686	__ret = (int16_t) __builtin_neon_vaddvq_s16(__rev0);
48685	return __ret;	41687	return __ret;
48686	}	41688	}
48687	#endif	41689	#endif
...	@@ -48689,14 +41691,14 @@ __ai int16_t vaddvq_s16(int16x8_t __p0) {	...	@@ -48689,14 +41691,14 @@ __ai int16_t vaddvq_s16(int16x8_t __p0) {
48689	#ifdef __LITTLE_ENDIAN__	41691	#ifdef __LITTLE_ENDIAN__
48690	__ai uint8_t vaddv_u8(uint8x8_t __p0) {	41692	__ai uint8_t vaddv_u8(uint8x8_t __p0) {
48691	uint8_t __ret;	41693	uint8_t __ret;
48692	__ret = (uint8_t) __builtin_neon_vaddv_u8((int8x8_t)__p0);	41694	__ret = (uint8_t) __builtin_neon_vaddv_u8(__p0);
48693	return __ret;	41695	return __ret;
48694	}	41696	}
48695	#else	41697	#else
48696	__ai uint8_t vaddv_u8(uint8x8_t __p0) {	41698	__ai uint8_t vaddv_u8(uint8x8_t __p0) {
48697	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41699	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48698	uint8_t __ret;	41700	uint8_t __ret;
48699	__ret = (uint8_t) __builtin_neon_vaddv_u8((int8x8_t)__rev0);	41701	__ret = (uint8_t) __builtin_neon_vaddv_u8(__rev0);
48700	return __ret;	41702	return __ret;
48701	}	41703	}
48702	#endif	41704	#endif
...	@@ -48704,14 +41706,14 @@ __ai uint8_t vaddv_u8(uint8x8_t __p0) {	...	@@ -48704,14 +41706,14 @@ __ai uint8_t vaddv_u8(uint8x8_t __p0) {
48704	#ifdef __LITTLE_ENDIAN__	41706	#ifdef __LITTLE_ENDIAN__
48705	__ai uint32_t vaddv_u32(uint32x2_t __p0) {	41707	__ai uint32_t vaddv_u32(uint32x2_t __p0) {
48706	uint32_t __ret;	41708	uint32_t __ret;
48707	__ret = (uint32_t) __builtin_neon_vaddv_u32((int8x8_t)__p0);	41709	__ret = (uint32_t) __builtin_neon_vaddv_u32(__p0);
48708	return __ret;	41710	return __ret;
48709	}	41711	}
48710	#else	41712	#else
48711	__ai uint32_t vaddv_u32(uint32x2_t __p0) {	41713	__ai uint32_t vaddv_u32(uint32x2_t __p0) {
48712	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41714	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48713	uint32_t __ret;	41715	uint32_t __ret;
48714	__ret = (uint32_t) __builtin_neon_vaddv_u32((int8x8_t)__rev0);	41716	__ret = (uint32_t) __builtin_neon_vaddv_u32(__rev0);
48715	return __ret;	41717	return __ret;
48716	}	41718	}
48717	#endif	41719	#endif
...	@@ -48719,14 +41721,14 @@ __ai uint32_t vaddv_u32(uint32x2_t __p0) {	...	@@ -48719,14 +41721,14 @@ __ai uint32_t vaddv_u32(uint32x2_t __p0) {
48719	#ifdef __LITTLE_ENDIAN__	41721	#ifdef __LITTLE_ENDIAN__
48720	__ai uint16_t vaddv_u16(uint16x4_t __p0) {	41722	__ai uint16_t vaddv_u16(uint16x4_t __p0) {
48721	uint16_t __ret;	41723	uint16_t __ret;
48722	__ret = (uint16_t) __builtin_neon_vaddv_u16((int8x8_t)__p0);	41724	__ret = (uint16_t) __builtin_neon_vaddv_u16(__p0);
48723	return __ret;	41725	return __ret;
48724	}	41726	}
48725	#else	41727	#else
48726	__ai uint16_t vaddv_u16(uint16x4_t __p0) {	41728	__ai uint16_t vaddv_u16(uint16x4_t __p0) {
48727	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41729	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48728	uint16_t __ret;	41730	uint16_t __ret;
48729	__ret = (uint16_t) __builtin_neon_vaddv_u16((int8x8_t)__rev0);	41731	__ret = (uint16_t) __builtin_neon_vaddv_u16(__rev0);
48730	return __ret;	41732	return __ret;
48731	}	41733	}
48732	#endif	41734	#endif
...	@@ -48734,14 +41736,14 @@ __ai uint16_t vaddv_u16(uint16x4_t __p0) {	...	@@ -48734,14 +41736,14 @@ __ai uint16_t vaddv_u16(uint16x4_t __p0) {
48734	#ifdef __LITTLE_ENDIAN__	41736	#ifdef __LITTLE_ENDIAN__
48735	__ai int8_t vaddv_s8(int8x8_t __p0) {	41737	__ai int8_t vaddv_s8(int8x8_t __p0) {
48736	int8_t __ret;	41738	int8_t __ret;
48737	__ret = (int8_t) __builtin_neon_vaddv_s8((int8x8_t)__p0);	41739	__ret = (int8_t) __builtin_neon_vaddv_s8(__p0);
48738	return __ret;	41740	return __ret;
48739	}	41741	}
48740	#else	41742	#else
48741	__ai int8_t vaddv_s8(int8x8_t __p0) {	41743	__ai int8_t vaddv_s8(int8x8_t __p0) {
48742	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	41744	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
48743	int8_t __ret;	41745	int8_t __ret;
48744	__ret = (int8_t) __builtin_neon_vaddv_s8((int8x8_t)__rev0);	41746	__ret = (int8_t) __builtin_neon_vaddv_s8(__rev0);
48745	return __ret;	41747	return __ret;
48746	}	41748	}
48747	#endif	41749	#endif
...	@@ -48749,14 +41751,14 @@ __ai int8_t vaddv_s8(int8x8_t __p0) {	...	@@ -48749,14 +41751,14 @@ __ai int8_t vaddv_s8(int8x8_t __p0) {
48749	#ifdef __LITTLE_ENDIAN__	41751	#ifdef __LITTLE_ENDIAN__
48750	__ai float32_t vaddv_f32(float32x2_t __p0) {	41752	__ai float32_t vaddv_f32(float32x2_t __p0) {
48751	float32_t __ret;	41753	float32_t __ret;
48752	__ret = (float32_t) __builtin_neon_vaddv_f32((int8x8_t)__p0);	41754	__ret = (float32_t) __builtin_neon_vaddv_f32(__p0);
48753	return __ret;	41755	return __ret;
48754	}	41756	}
48755	#else	41757	#else
48756	__ai float32_t vaddv_f32(float32x2_t __p0) {	41758	__ai float32_t vaddv_f32(float32x2_t __p0) {
48757	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41759	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48758	float32_t __ret;	41760	float32_t __ret;
48759	__ret = (float32_t) __builtin_neon_vaddv_f32((int8x8_t)__rev0);	41761	__ret = (float32_t) __builtin_neon_vaddv_f32(__rev0);
48760	return __ret;	41762	return __ret;
48761	}	41763	}
48762	#endif	41764	#endif
...	@@ -48764,14 +41766,14 @@ __ai float32_t vaddv_f32(float32x2_t __p0) {	...	@@ -48764,14 +41766,14 @@ __ai float32_t vaddv_f32(float32x2_t __p0) {
48764	#ifdef __LITTLE_ENDIAN__	41766	#ifdef __LITTLE_ENDIAN__
48765	__ai int32_t vaddv_s32(int32x2_t __p0) {	41767	__ai int32_t vaddv_s32(int32x2_t __p0) {
48766	int32_t __ret;	41768	int32_t __ret;
48767	__ret = (int32_t) __builtin_neon_vaddv_s32((int8x8_t)__p0);	41769	__ret = (int32_t) __builtin_neon_vaddv_s32(__p0);
48768	return __ret;	41770	return __ret;
48769	}	41771	}
48770	#else	41772	#else
48771	__ai int32_t vaddv_s32(int32x2_t __p0) {	41773	__ai int32_t vaddv_s32(int32x2_t __p0) {
48772	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	41774	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
48773	int32_t __ret;	41775	int32_t __ret;
48774	__ret = (int32_t) __builtin_neon_vaddv_s32((int8x8_t)__rev0);	41776	__ret = (int32_t) __builtin_neon_vaddv_s32(__rev0);
48775	return __ret;	41777	return __ret;
48776	}	41778	}
48777	#endif	41779	#endif
...	@@ -48779,32 +41781,23 @@ __ai int32_t vaddv_s32(int32x2_t __p0) {	...	@@ -48779,32 +41781,23 @@ __ai int32_t vaddv_s32(int32x2_t __p0) {
48779	#ifdef __LITTLE_ENDIAN__	41781	#ifdef __LITTLE_ENDIAN__
48780	__ai int16_t vaddv_s16(int16x4_t __p0) {	41782	__ai int16_t vaddv_s16(int16x4_t __p0) {
48781	int16_t __ret;	41783	int16_t __ret;
48782	__ret = (int16_t) __builtin_neon_vaddv_s16((int8x8_t)__p0);	41784	__ret = (int16_t) __builtin_neon_vaddv_s16(__p0);
48783	return __ret;	41785	return __ret;
48784	}	41786	}
48785	#else	41787	#else
48786	__ai int16_t vaddv_s16(int16x4_t __p0) {	41788	__ai int16_t vaddv_s16(int16x4_t __p0) {
48787	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	41789	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
48788	int16_t __ret;	41790	int16_t __ret;
48789	__ret = (int16_t) __builtin_neon_vaddv_s16((int8x8_t)__rev0);	41791	__ret = (int16_t) __builtin_neon_vaddv_s16(__rev0);
48790	return __ret;	41792	return __ret;
48791	}	41793	}
48792	#endif	41794	#endif
48793		41795
48794	#ifdef __LITTLE_ENDIAN__
48795	__ai poly64x1_t vbsl_p64(uint64x1_t __p0, poly64x1_t __p1, poly64x1_t __p2) {	41796	__ai poly64x1_t vbsl_p64(uint64x1_t __p0, poly64x1_t __p1, poly64x1_t __p2) {
48796	poly64x1_t __ret;	41797	poly64x1_t __ret;
48797	__ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);	41798	__ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
48798	return __ret;	41799	return __ret;
48799	}	41800	}
48800	#else
48801	__ai poly64x1_t vbsl_p64(uint64x1_t __p0, poly64x1_t __p1, poly64x1_t __p2) {
48802	poly64x1_t __ret;
48803	__ret = (poly64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 6);
48804	return __ret;
48805	}
48806	#endif
48807
48808	#ifdef __LITTLE_ENDIAN__	41801	#ifdef __LITTLE_ENDIAN__
48809	__ai poly64x2_t vbslq_p64(uint64x2_t __p0, poly64x2_t __p1, poly64x2_t __p2) {	41802	__ai poly64x2_t vbslq_p64(uint64x2_t __p0, poly64x2_t __p1, poly64x2_t __p2) {
48810	poly64x2_t __ret;	41803	poly64x2_t __ret;
...	@@ -48841,20 +41834,11 @@ __ai float64x2_t vbslq_f64(uint64x2_t __p0, float64x2_t __p1, float64x2_t __p2)	...	@@ -48841,20 +41834,11 @@ __ai float64x2_t vbslq_f64(uint64x2_t __p0, float64x2_t __p1, float64x2_t __p2)
48841	}	41834	}
48842	#endif	41835	#endif
48843		41836
48844	#ifdef __LITTLE_ENDIAN__
48845	__ai float64x1_t vbsl_f64(uint64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	41837	__ai float64x1_t vbsl_f64(uint64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
48846	float64x1_t __ret;	41838	float64x1_t __ret;
48847	__ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);	41839	__ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
48848	return __ret;	41840	return __ret;
48849	}	41841	}
48850	#else
48851	__ai float64x1_t vbsl_f64(uint64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
48852	float64x1_t __ret;
48853	__ret = (float64x1_t) __builtin_neon_vbsl_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
48854	return __ret;
48855	}
48856	#endif
48857
48858	#ifdef __LITTLE_ENDIAN__	41842	#ifdef __LITTLE_ENDIAN__
48859	__ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {	41843	__ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {
48860	uint64x2_t __ret;	41844	uint64x2_t __ret;
...	@@ -48872,48 +41856,21 @@ __ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -48872,48 +41856,21 @@ __ai uint64x2_t vcageq_f64(float64x2_t __p0, float64x2_t __p1) {
48872	}	41856	}
48873	#endif	41857	#endif
48874		41858
48875	#ifdef __LITTLE_ENDIAN__
48876	__ai uint64x1_t vcage_f64(float64x1_t __p0, float64x1_t __p1) {
48877	uint64x1_t __ret;
48878	__ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
48879	return __ret;
48880	}
48881	#else
48882	__ai uint64x1_t vcage_f64(float64x1_t __p0, float64x1_t __p1) {	41859	__ai uint64x1_t vcage_f64(float64x1_t __p0, float64x1_t __p1) {
48883	uint64x1_t __ret;	41860	uint64x1_t __ret;
48884	__ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	41861	__ret = (uint64x1_t) __builtin_neon_vcage_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
48885	return __ret;	41862	return __ret;
48886	}	41863	}
48887	#endif
48888
48889	#ifdef __LITTLE_ENDIAN__
48890	__ai uint64_t vcaged_f64(float64_t __p0, float64_t __p1) {
48891	uint64_t __ret;
48892	__ret = (uint64_t) __builtin_neon_vcaged_f64(__p0, __p1);
48893	return __ret;
48894	}
48895	#else
48896	__ai uint64_t vcaged_f64(float64_t __p0, float64_t __p1) {	41864	__ai uint64_t vcaged_f64(float64_t __p0, float64_t __p1) {
48897	uint64_t __ret;	41865	uint64_t __ret;
48898	__ret = (uint64_t) __builtin_neon_vcaged_f64(__p0, __p1);	41866	__ret = (uint64_t) __builtin_neon_vcaged_f64(__p0, __p1);
48899	return __ret;	41867	return __ret;
48900	}	41868	}
48901	#endif
48902
48903	#ifdef __LITTLE_ENDIAN__
48904	__ai uint32_t vcages_f32(float32_t __p0, float32_t __p1) {
48905	uint32_t __ret;
48906	__ret = (uint32_t) __builtin_neon_vcages_f32(__p0, __p1);
48907	return __ret;
48908	}
48909	#else
48910	__ai uint32_t vcages_f32(float32_t __p0, float32_t __p1) {	41869	__ai uint32_t vcages_f32(float32_t __p0, float32_t __p1) {
48911	uint32_t __ret;	41870	uint32_t __ret;
48912	__ret = (uint32_t) __builtin_neon_vcages_f32(__p0, __p1);	41871	__ret = (uint32_t) __builtin_neon_vcages_f32(__p0, __p1);
48913	return __ret;	41872	return __ret;
48914	}	41873	}
48915	#endif
48916
48917	#ifdef __LITTLE_ENDIAN__	41874	#ifdef __LITTLE_ENDIAN__
48918	__ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {	41875	__ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {
48919	uint64x2_t __ret;	41876	uint64x2_t __ret;
...	@@ -48931,48 +41888,21 @@ __ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -48931,48 +41888,21 @@ __ai uint64x2_t vcagtq_f64(float64x2_t __p0, float64x2_t __p1) {
48931	}	41888	}
48932	#endif	41889	#endif
48933		41890
48934	#ifdef __LITTLE_ENDIAN__
48935	__ai uint64x1_t vcagt_f64(float64x1_t __p0, float64x1_t __p1) {	41891	__ai uint64x1_t vcagt_f64(float64x1_t __p0, float64x1_t __p1) {
48936	uint64x1_t __ret;	41892	uint64x1_t __ret;
48937	__ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	41893	__ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
48938	return __ret;	41894	return __ret;
48939	}	41895	}
48940	#else
48941	__ai uint64x1_t vcagt_f64(float64x1_t __p0, float64x1_t __p1) {
48942	uint64x1_t __ret;
48943	__ret = (uint64x1_t) __builtin_neon_vcagt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
48944	return __ret;
48945	}
48946	#endif
48947
48948	#ifdef __LITTLE_ENDIAN__
48949	__ai uint64_t vcagtd_f64(float64_t __p0, float64_t __p1) {	41896	__ai uint64_t vcagtd_f64(float64_t __p0, float64_t __p1) {
48950	uint64_t __ret;	41897	uint64_t __ret;
48951	__ret = (uint64_t) __builtin_neon_vcagtd_f64(__p0, __p1);	41898	__ret = (uint64_t) __builtin_neon_vcagtd_f64(__p0, __p1);
48952	return __ret;	41899	return __ret;
48953	}	41900	}
48954	#else
48955	__ai uint64_t vcagtd_f64(float64_t __p0, float64_t __p1) {
48956	uint64_t __ret;
48957	__ret = (uint64_t) __builtin_neon_vcagtd_f64(__p0, __p1);
48958	return __ret;
48959	}
48960	#endif
48961
48962	#ifdef __LITTLE_ENDIAN__
48963	__ai uint32_t vcagts_f32(float32_t __p0, float32_t __p1) {
48964	uint32_t __ret;
48965	__ret = (uint32_t) __builtin_neon_vcagts_f32(__p0, __p1);
48966	return __ret;
48967	}
48968	#else
48969	__ai uint32_t vcagts_f32(float32_t __p0, float32_t __p1) {	41901	__ai uint32_t vcagts_f32(float32_t __p0, float32_t __p1) {
48970	uint32_t __ret;	41902	uint32_t __ret;
48971	__ret = (uint32_t) __builtin_neon_vcagts_f32(__p0, __p1);	41903	__ret = (uint32_t) __builtin_neon_vcagts_f32(__p0, __p1);
48972	return __ret;	41904	return __ret;
48973	}	41905	}
48974	#endif
48975
48976	#ifdef __LITTLE_ENDIAN__	41906	#ifdef __LITTLE_ENDIAN__
48977	__ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {	41907	__ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {
48978	uint64x2_t __ret;	41908	uint64x2_t __ret;
...	@@ -48990,48 +41920,21 @@ __ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -48990,48 +41920,21 @@ __ai uint64x2_t vcaleq_f64(float64x2_t __p0, float64x2_t __p1) {
48990	}	41920	}
48991	#endif	41921	#endif
48992		41922
48993	#ifdef __LITTLE_ENDIAN__
48994	__ai uint64x1_t vcale_f64(float64x1_t __p0, float64x1_t __p1) {	41923	__ai uint64x1_t vcale_f64(float64x1_t __p0, float64x1_t __p1) {
48995	uint64x1_t __ret;	41924	uint64x1_t __ret;
48996	__ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	41925	__ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
48997	return __ret;	41926	return __ret;
48998	}	41927	}
48999	#else
49000	__ai uint64x1_t vcale_f64(float64x1_t __p0, float64x1_t __p1) {
49001	uint64x1_t __ret;
49002	__ret = (uint64x1_t) __builtin_neon_vcale_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
49003	return __ret;
49004	}
49005	#endif
49006
49007	#ifdef __LITTLE_ENDIAN__
49008	__ai uint64_t vcaled_f64(float64_t __p0, float64_t __p1) {	41928	__ai uint64_t vcaled_f64(float64_t __p0, float64_t __p1) {
49009	uint64_t __ret;	41929	uint64_t __ret;
49010	__ret = (uint64_t) __builtin_neon_vcaled_f64(__p0, __p1);	41930	__ret = (uint64_t) __builtin_neon_vcaled_f64(__p0, __p1);
49011	return __ret;	41931	return __ret;
49012	}	41932	}
49013	#else
49014	__ai uint64_t vcaled_f64(float64_t __p0, float64_t __p1) {
49015	uint64_t __ret;
49016	__ret = (uint64_t) __builtin_neon_vcaled_f64(__p0, __p1);
49017	return __ret;
49018	}
49019	#endif
49020
49021	#ifdef __LITTLE_ENDIAN__
49022	__ai uint32_t vcales_f32(float32_t __p0, float32_t __p1) {	41933	__ai uint32_t vcales_f32(float32_t __p0, float32_t __p1) {
49023	uint32_t __ret;	41934	uint32_t __ret;
49024	__ret = (uint32_t) __builtin_neon_vcales_f32(__p0, __p1);	41935	__ret = (uint32_t) __builtin_neon_vcales_f32(__p0, __p1);
49025	return __ret;	41936	return __ret;
49026	}	41937	}
49027	#else
49028	__ai uint32_t vcales_f32(float32_t __p0, float32_t __p1) {
49029	uint32_t __ret;
49030	__ret = (uint32_t) __builtin_neon_vcales_f32(__p0, __p1);
49031	return __ret;
49032	}
49033	#endif
49034
49035	#ifdef __LITTLE_ENDIAN__	41938	#ifdef __LITTLE_ENDIAN__
49036	__ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {	41939	__ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {
49037	uint64x2_t __ret;	41940	uint64x2_t __ret;
...	@@ -49049,62 +41952,26 @@ __ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -49049,62 +41952,26 @@ __ai uint64x2_t vcaltq_f64(float64x2_t __p0, float64x2_t __p1) {
49049	}	41952	}
49050	#endif	41953	#endif
49051		41954
49052	#ifdef __LITTLE_ENDIAN__
49053	__ai uint64x1_t vcalt_f64(float64x1_t __p0, float64x1_t __p1) {	41955	__ai uint64x1_t vcalt_f64(float64x1_t __p0, float64x1_t __p1) {
49054	uint64x1_t __ret;	41956	uint64x1_t __ret;
49055	__ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	41957	__ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
49056	return __ret;	41958	return __ret;
49057	}	41959	}
49058	#else
49059	__ai uint64x1_t vcalt_f64(float64x1_t __p0, float64x1_t __p1) {
49060	uint64x1_t __ret;
49061	__ret = (uint64x1_t) __builtin_neon_vcalt_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
49062	return __ret;
49063	}
49064	#endif
49065
49066	#ifdef __LITTLE_ENDIAN__
49067	__ai uint64_t vcaltd_f64(float64_t __p0, float64_t __p1) {
49068	uint64_t __ret;
49069	__ret = (uint64_t) __builtin_neon_vcaltd_f64(__p0, __p1);
49070	return __ret;
49071	}
49072	#else
49073	__ai uint64_t vcaltd_f64(float64_t __p0, float64_t __p1) {	41960	__ai uint64_t vcaltd_f64(float64_t __p0, float64_t __p1) {
49074	uint64_t __ret;	41961	uint64_t __ret;
49075	__ret = (uint64_t) __builtin_neon_vcaltd_f64(__p0, __p1);	41962	__ret = (uint64_t) __builtin_neon_vcaltd_f64(__p0, __p1);
49076	return __ret;	41963	return __ret;
49077	}	41964	}
49078	#endif
49079
49080	#ifdef __LITTLE_ENDIAN__
49081	__ai uint32_t vcalts_f32(float32_t __p0, float32_t __p1) {
49082	uint32_t __ret;
49083	__ret = (uint32_t) __builtin_neon_vcalts_f32(__p0, __p1);
49084	return __ret;
49085	}
49086	#else
49087	__ai uint32_t vcalts_f32(float32_t __p0, float32_t __p1) {	41965	__ai uint32_t vcalts_f32(float32_t __p0, float32_t __p1) {
49088	uint32_t __ret;	41966	uint32_t __ret;
49089	__ret = (uint32_t) __builtin_neon_vcalts_f32(__p0, __p1);	41967	__ret = (uint32_t) __builtin_neon_vcalts_f32(__p0, __p1);
49090	return __ret;	41968	return __ret;
49091	}	41969	}
49092	#endif
49093
49094	#ifdef __LITTLE_ENDIAN__
49095	__ai uint64x1_t vceq_p64(poly64x1_t __p0, poly64x1_t __p1) {
49096	uint64x1_t __ret;
49097	__ret = (uint64x1_t)(__p0 == __p1);
49098	return __ret;
49099	}
49100	#else
49101	__ai uint64x1_t vceq_p64(poly64x1_t __p0, poly64x1_t __p1) {	41970	__ai uint64x1_t vceq_p64(poly64x1_t __p0, poly64x1_t __p1) {
49102	uint64x1_t __ret;	41971	uint64x1_t __ret;
49103	__ret = (uint64x1_t)(__p0 == __p1);	41972	__ret = (uint64x1_t)(__p0 == __p1);
49104	return __ret;	41973	return __ret;
49105	}	41974	}
49106	#endif
49107
49108	#ifdef __LITTLE_ENDIAN__	41975	#ifdef __LITTLE_ENDIAN__
49109	__ai uint64x2_t vceqq_p64(poly64x2_t __p0, poly64x2_t __p1) {	41976	__ai uint64x2_t vceqq_p64(poly64x2_t __p0, poly64x2_t __p1) {
49110	uint64x2_t __ret;	41977	uint64x2_t __ret;
...	@@ -49173,104 +42040,41 @@ __ai uint64x2_t vceqq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -49173,104 +42040,41 @@ __ai uint64x2_t vceqq_s64(int64x2_t __p0, int64x2_t __p1) {
49173	}	42040	}
49174	#endif	42041	#endif
49175		42042
49176	#ifdef __LITTLE_ENDIAN__
49177	__ai uint64x1_t vceq_u64(uint64x1_t __p0, uint64x1_t __p1) {	42043	__ai uint64x1_t vceq_u64(uint64x1_t __p0, uint64x1_t __p1) {
49178	uint64x1_t __ret;	42044	uint64x1_t __ret;
49179	__ret = (uint64x1_t)(__p0 == __p1);	42045	__ret = (uint64x1_t)(__p0 == __p1);
49180	return __ret;	42046	return __ret;
49181	}	42047	}
49182	#else
49183	__ai uint64x1_t vceq_u64(uint64x1_t __p0, uint64x1_t __p1) {
49184	uint64x1_t __ret;
49185	__ret = (uint64x1_t)(__p0 == __p1);
49186	return __ret;
49187	}
49188	#endif
49189
49190	#ifdef __LITTLE_ENDIAN__
49191	__ai uint64x1_t vceq_f64(float64x1_t __p0, float64x1_t __p1) {	42048	__ai uint64x1_t vceq_f64(float64x1_t __p0, float64x1_t __p1) {
49192	uint64x1_t __ret;	42049	uint64x1_t __ret;
49193	__ret = (uint64x1_t)(__p0 == __p1);	42050	__ret = (uint64x1_t)(__p0 == __p1);
49194	return __ret;	42051	return __ret;
49195	}	42052	}
49196	#else
49197	__ai uint64x1_t vceq_f64(float64x1_t __p0, float64x1_t __p1) {
49198	uint64x1_t __ret;
49199	__ret = (uint64x1_t)(__p0 == __p1);
49200	return __ret;
49201	}
49202	#endif
49203
49204	#ifdef __LITTLE_ENDIAN__
49205	__ai uint64x1_t vceq_s64(int64x1_t __p0, int64x1_t __p1) {	42053	__ai uint64x1_t vceq_s64(int64x1_t __p0, int64x1_t __p1) {
49206	uint64x1_t __ret;	42054	uint64x1_t __ret;
49207	__ret = (uint64x1_t)(__p0 == __p1);	42055	__ret = (uint64x1_t)(__p0 == __p1);
49208	return __ret;	42056	return __ret;
49209	}	42057	}
49210	#else
49211	__ai uint64x1_t vceq_s64(int64x1_t __p0, int64x1_t __p1) {
49212	uint64x1_t __ret;
49213	__ret = (uint64x1_t)(__p0 == __p1);
49214	return __ret;
49215	}
49216	#endif
49217
49218	#ifdef __LITTLE_ENDIAN__
49219	__ai uint64_t vceqd_u64(uint64_t __p0, uint64_t __p1) {
49220	uint64_t __ret;
49221	__ret = (uint64_t) __builtin_neon_vceqd_u64(__p0, __p1);
49222	return __ret;
49223	}
49224	#else
49225	__ai uint64_t vceqd_u64(uint64_t __p0, uint64_t __p1) {	42058	__ai uint64_t vceqd_u64(uint64_t __p0, uint64_t __p1) {
49226	uint64_t __ret;	42059	uint64_t __ret;
49227	__ret = (uint64_t) __builtin_neon_vceqd_u64(__p0, __p1);	42060	__ret = (uint64_t) __builtin_neon_vceqd_u64(__p0, __p1);
49228	return __ret;	42061	return __ret;
49229	}	42062	}
49230	#endif
49231
49232	#ifdef __LITTLE_ENDIAN__
49233	__ai int64_t vceqd_s64(int64_t __p0, int64_t __p1) {	42063	__ai int64_t vceqd_s64(int64_t __p0, int64_t __p1) {
49234	int64_t __ret;	42064	int64_t __ret;
49235	__ret = (int64_t) __builtin_neon_vceqd_s64(__p0, __p1);	42065	__ret = (int64_t) __builtin_neon_vceqd_s64(__p0, __p1);
49236	return __ret;	42066	return __ret;
49237	}	42067	}
49238	#else
49239	__ai int64_t vceqd_s64(int64_t __p0, int64_t __p1) {
49240	int64_t __ret;
49241	__ret = (int64_t) __builtin_neon_vceqd_s64(__p0, __p1);
49242	return __ret;
49243	}
49244	#endif
49245
49246	#ifdef __LITTLE_ENDIAN__
49247	__ai uint64_t vceqd_f64(float64_t __p0, float64_t __p1) {	42068	__ai uint64_t vceqd_f64(float64_t __p0, float64_t __p1) {
49248	uint64_t __ret;	42069	uint64_t __ret;
49249	__ret = (uint64_t) __builtin_neon_vceqd_f64(__p0, __p1);	42070	__ret = (uint64_t) __builtin_neon_vceqd_f64(__p0, __p1);
49250	return __ret;	42071	return __ret;
49251	}	42072	}
49252	#else
49253	__ai uint64_t vceqd_f64(float64_t __p0, float64_t __p1) {
49254	uint64_t __ret;
49255	__ret = (uint64_t) __builtin_neon_vceqd_f64(__p0, __p1);
49256	return __ret;
49257	}
49258	#endif
49259
49260	#ifdef __LITTLE_ENDIAN__
49261	__ai uint32_t vceqs_f32(float32_t __p0, float32_t __p1) {
49262	uint32_t __ret;
49263	__ret = (uint32_t) __builtin_neon_vceqs_f32(__p0, __p1);
49264	return __ret;
49265	}
49266	#else
49267	__ai uint32_t vceqs_f32(float32_t __p0, float32_t __p1) {	42073	__ai uint32_t vceqs_f32(float32_t __p0, float32_t __p1) {
49268	uint32_t __ret;	42074	uint32_t __ret;
49269	__ret = (uint32_t) __builtin_neon_vceqs_f32(__p0, __p1);	42075	__ret = (uint32_t) __builtin_neon_vceqs_f32(__p0, __p1);
49270	return __ret;	42076	return __ret;
49271	}	42077	}
49272	#endif
49273
49274	#ifdef __LITTLE_ENDIAN__	42078	#ifdef __LITTLE_ENDIAN__
49275	__ai uint8x8_t vceqz_p8(poly8x8_t __p0) {	42079	__ai uint8x8_t vceqz_p8(poly8x8_t __p0) {
49276	uint8x8_t __ret;	42080	uint8x8_t __ret;
...	@@ -49287,20 +42091,11 @@ __ai uint8x8_t vceqz_p8(poly8x8_t __p0) {	...	@@ -49287,20 +42091,11 @@ __ai uint8x8_t vceqz_p8(poly8x8_t __p0) {
49287	}	42091	}
49288	#endif	42092	#endif
49289		42093
49290	#ifdef __LITTLE_ENDIAN__
49291	__ai uint64x1_t vceqz_p64(poly64x1_t __p0) {
49292	uint64x1_t __ret;
49293	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49294	return __ret;
49295	}
49296	#else
49297	__ai uint64x1_t vceqz_p64(poly64x1_t __p0) {	42094	__ai uint64x1_t vceqz_p64(poly64x1_t __p0) {
49298	uint64x1_t __ret;	42095	uint64x1_t __ret;
49299	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);	42096	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49300	return __ret;	42097	return __ret;
49301	}	42098	}
49302	#endif
49303
49304	#ifdef __LITTLE_ENDIAN__	42099	#ifdef __LITTLE_ENDIAN__
49305	__ai uint16x4_t vceqz_p16(poly16x4_t __p0) {	42100	__ai uint16x4_t vceqz_p16(poly16x4_t __p0) {
49306	uint16x4_t __ret;	42101	uint16x4_t __ret;
...	@@ -49557,20 +42352,11 @@ __ai uint32x2_t vceqz_u32(uint32x2_t __p0) {	...	@@ -49557,20 +42352,11 @@ __ai uint32x2_t vceqz_u32(uint32x2_t __p0) {
49557	}	42352	}
49558	#endif	42353	#endif
49559		42354
49560	#ifdef __LITTLE_ENDIAN__
49561	__ai uint64x1_t vceqz_u64(uint64x1_t __p0) {
49562	uint64x1_t __ret;
49563	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49564	return __ret;
49565	}
49566	#else
49567	__ai uint64x1_t vceqz_u64(uint64x1_t __p0) {	42355	__ai uint64x1_t vceqz_u64(uint64x1_t __p0) {
49568	uint64x1_t __ret;	42356	uint64x1_t __ret;
49569	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);	42357	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49570	return __ret;	42358	return __ret;
49571	}	42359	}
49572	#endif
49573
49574	#ifdef __LITTLE_ENDIAN__	42360	#ifdef __LITTLE_ENDIAN__
49575	__ai uint16x4_t vceqz_u16(uint16x4_t __p0) {	42361	__ai uint16x4_t vceqz_u16(uint16x4_t __p0) {
49576	uint16x4_t __ret;	42362	uint16x4_t __ret;
...	@@ -49603,20 +42389,11 @@ __ai uint8x8_t vceqz_s8(int8x8_t __p0) {	...	@@ -49603,20 +42389,11 @@ __ai uint8x8_t vceqz_s8(int8x8_t __p0) {
49603	}	42389	}
49604	#endif	42390	#endif
49605		42391
49606	#ifdef __LITTLE_ENDIAN__
49607	__ai uint64x1_t vceqz_f64(float64x1_t __p0) {	42392	__ai uint64x1_t vceqz_f64(float64x1_t __p0) {
49608	uint64x1_t __ret;	42393	uint64x1_t __ret;
49609	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);	42394	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49610	return __ret;	42395	return __ret;
49611	}	42396	}
49612	#else
49613	__ai uint64x1_t vceqz_f64(float64x1_t __p0) {
49614	uint64x1_t __ret;
49615	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49616	return __ret;
49617	}
49618	#endif
49619
49620	#ifdef __LITTLE_ENDIAN__	42397	#ifdef __LITTLE_ENDIAN__
49621	__ai uint32x2_t vceqz_f32(float32x2_t __p0) {	42398	__ai uint32x2_t vceqz_f32(float32x2_t __p0) {
49622	uint32x2_t __ret;	42399	uint32x2_t __ret;
...	@@ -49649,20 +42426,11 @@ __ai uint32x2_t vceqz_s32(int32x2_t __p0) {	...	@@ -49649,20 +42426,11 @@ __ai uint32x2_t vceqz_s32(int32x2_t __p0) {
49649	}	42426	}
49650	#endif	42427	#endif
49651		42428
49652	#ifdef __LITTLE_ENDIAN__
49653	__ai uint64x1_t vceqz_s64(int64x1_t __p0) {
49654	uint64x1_t __ret;
49655	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49656	return __ret;
49657	}
49658	#else
49659	__ai uint64x1_t vceqz_s64(int64x1_t __p0) {	42429	__ai uint64x1_t vceqz_s64(int64x1_t __p0) {
49660	uint64x1_t __ret;	42430	uint64x1_t __ret;
49661	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);	42431	__ret = (uint64x1_t) __builtin_neon_vceqz_v((int8x8_t)__p0, 19);
49662	return __ret;	42432	return __ret;
49663	}	42433	}
49664	#endif
49665
49666	#ifdef __LITTLE_ENDIAN__	42434	#ifdef __LITTLE_ENDIAN__
49667	__ai uint16x4_t vceqz_s16(int16x4_t __p0) {	42435	__ai uint16x4_t vceqz_s16(int16x4_t __p0) {
49668	uint16x4_t __ret;	42436	uint16x4_t __ret;
...	@@ -49679,62 +42447,26 @@ __ai uint16x4_t vceqz_s16(int16x4_t __p0) {	...	@@ -49679,62 +42447,26 @@ __ai uint16x4_t vceqz_s16(int16x4_t __p0) {
49679	}	42447	}
49680	#endif	42448	#endif
49681		42449
49682	#ifdef __LITTLE_ENDIAN__
49683	__ai uint64_t vceqzd_u64(uint64_t __p0) {	42450	__ai uint64_t vceqzd_u64(uint64_t __p0) {
49684	uint64_t __ret;	42451	uint64_t __ret;
49685	__ret = (uint64_t) __builtin_neon_vceqzd_u64(__p0);	42452	__ret = (uint64_t) __builtin_neon_vceqzd_u64(__p0);
49686	return __ret;	42453	return __ret;
49687	}	42454	}
49688	#else
49689	__ai uint64_t vceqzd_u64(uint64_t __p0) {
49690	uint64_t __ret;
49691	__ret = (uint64_t) __builtin_neon_vceqzd_u64(__p0);
49692	return __ret;
49693	}
49694	#endif
49695
49696	#ifdef __LITTLE_ENDIAN__
49697	__ai int64_t vceqzd_s64(int64_t __p0) {
49698	int64_t __ret;
49699	__ret = (int64_t) __builtin_neon_vceqzd_s64(__p0);
49700	return __ret;
49701	}
49702	#else
49703	__ai int64_t vceqzd_s64(int64_t __p0) {	42455	__ai int64_t vceqzd_s64(int64_t __p0) {
49704	int64_t __ret;	42456	int64_t __ret;
49705	__ret = (int64_t) __builtin_neon_vceqzd_s64(__p0);	42457	__ret = (int64_t) __builtin_neon_vceqzd_s64(__p0);
49706	return __ret;	42458	return __ret;
49707	}	42459	}
49708	#endif
49709
49710	#ifdef __LITTLE_ENDIAN__
49711	__ai uint64_t vceqzd_f64(float64_t __p0) {
49712	uint64_t __ret;
49713	__ret = (uint64_t) __builtin_neon_vceqzd_f64(__p0);
49714	return __ret;
49715	}
49716	#else
49717	__ai uint64_t vceqzd_f64(float64_t __p0) {	42460	__ai uint64_t vceqzd_f64(float64_t __p0) {
49718	uint64_t __ret;	42461	uint64_t __ret;
49719	__ret = (uint64_t) __builtin_neon_vceqzd_f64(__p0);	42462	__ret = (uint64_t) __builtin_neon_vceqzd_f64(__p0);
49720	return __ret;	42463	return __ret;
49721	}	42464	}
49722	#endif
49723
49724	#ifdef __LITTLE_ENDIAN__
49725	__ai uint32_t vceqzs_f32(float32_t __p0) {
49726	uint32_t __ret;
49727	__ret = (uint32_t) __builtin_neon_vceqzs_f32(__p0);
49728	return __ret;
49729	}
49730	#else
49731	__ai uint32_t vceqzs_f32(float32_t __p0) {	42465	__ai uint32_t vceqzs_f32(float32_t __p0) {
49732	uint32_t __ret;	42466	uint32_t __ret;
49733	__ret = (uint32_t) __builtin_neon_vceqzs_f32(__p0);	42467	__ret = (uint32_t) __builtin_neon_vceqzs_f32(__p0);
49734	return __ret;	42468	return __ret;
49735	}	42469	}
49736	#endif
49737
49738	#ifdef __LITTLE_ENDIAN__	42470	#ifdef __LITTLE_ENDIAN__
49739	__ai uint64x2_t vcgeq_u64(uint64x2_t __p0, uint64x2_t __p1) {	42471	__ai uint64x2_t vcgeq_u64(uint64x2_t __p0, uint64x2_t __p1) {
49740	uint64x2_t __ret;	42472	uint64x2_t __ret;
...	@@ -49786,104 +42518,41 @@ __ai uint64x2_t vcgeq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -49786,104 +42518,41 @@ __ai uint64x2_t vcgeq_s64(int64x2_t __p0, int64x2_t __p1) {
49786	}	42518	}
49787	#endif	42519	#endif
49788		42520
49789	#ifdef __LITTLE_ENDIAN__
49790	__ai uint64x1_t vcge_u64(uint64x1_t __p0, uint64x1_t __p1) {	42521	__ai uint64x1_t vcge_u64(uint64x1_t __p0, uint64x1_t __p1) {
49791	uint64x1_t __ret;	42522	uint64x1_t __ret;
49792	__ret = (uint64x1_t)(__p0 >= __p1);	42523	__ret = (uint64x1_t)(__p0 >= __p1);
49793	return __ret;	42524	return __ret;
49794	}	42525	}
49795	#else
49796	__ai uint64x1_t vcge_u64(uint64x1_t __p0, uint64x1_t __p1) {
49797	uint64x1_t __ret;
49798	__ret = (uint64x1_t)(__p0 >= __p1);
49799	return __ret;
49800	}
49801	#endif
49802
49803	#ifdef __LITTLE_ENDIAN__
49804	__ai uint64x1_t vcge_f64(float64x1_t __p0, float64x1_t __p1) {
49805	uint64x1_t __ret;
49806	__ret = (uint64x1_t)(__p0 >= __p1);
49807	return __ret;
49808	}
49809	#else
49810	__ai uint64x1_t vcge_f64(float64x1_t __p0, float64x1_t __p1) {	42526	__ai uint64x1_t vcge_f64(float64x1_t __p0, float64x1_t __p1) {
49811	uint64x1_t __ret;	42527	uint64x1_t __ret;
49812	__ret = (uint64x1_t)(__p0 >= __p1);	42528	__ret = (uint64x1_t)(__p0 >= __p1);
49813	return __ret;	42529	return __ret;
49814	}	42530	}
49815	#endif
49816
49817	#ifdef __LITTLE_ENDIAN__
49818	__ai uint64x1_t vcge_s64(int64x1_t __p0, int64x1_t __p1) {
49819	uint64x1_t __ret;
49820	__ret = (uint64x1_t)(__p0 >= __p1);
49821	return __ret;
49822	}
49823	#else
49824	__ai uint64x1_t vcge_s64(int64x1_t __p0, int64x1_t __p1) {	42531	__ai uint64x1_t vcge_s64(int64x1_t __p0, int64x1_t __p1) {
49825	uint64x1_t __ret;	42532	uint64x1_t __ret;
49826	__ret = (uint64x1_t)(__p0 >= __p1);	42533	__ret = (uint64x1_t)(__p0 >= __p1);
49827	return __ret;	42534	return __ret;
49828	}	42535	}
49829	#endif
49830
49831	#ifdef __LITTLE_ENDIAN__
49832	__ai int64_t vcged_s64(int64_t __p0, int64_t __p1) {
49833	int64_t __ret;
49834	__ret = (int64_t) __builtin_neon_vcged_s64(__p0, __p1);
49835	return __ret;
49836	}
49837	#else
49838	__ai int64_t vcged_s64(int64_t __p0, int64_t __p1) {	42536	__ai int64_t vcged_s64(int64_t __p0, int64_t __p1) {
49839	int64_t __ret;	42537	int64_t __ret;
49840	__ret = (int64_t) __builtin_neon_vcged_s64(__p0, __p1);	42538	__ret = (int64_t) __builtin_neon_vcged_s64(__p0, __p1);
49841	return __ret;	42539	return __ret;
49842	}	42540	}
49843	#endif
49844
49845	#ifdef __LITTLE_ENDIAN__
49846	__ai uint64_t vcged_u64(uint64_t __p0, uint64_t __p1) {
49847	uint64_t __ret;
49848	__ret = (uint64_t) __builtin_neon_vcged_u64(__p0, __p1);
49849	return __ret;
49850	}
49851	#else
49852	__ai uint64_t vcged_u64(uint64_t __p0, uint64_t __p1) {	42541	__ai uint64_t vcged_u64(uint64_t __p0, uint64_t __p1) {
49853	uint64_t __ret;	42542	uint64_t __ret;
49854	__ret = (uint64_t) __builtin_neon_vcged_u64(__p0, __p1);	42543	__ret = (uint64_t) __builtin_neon_vcged_u64(__p0, __p1);
49855	return __ret;	42544	return __ret;
49856	}	42545	}
49857	#endif
49858
49859	#ifdef __LITTLE_ENDIAN__
49860	__ai uint64_t vcged_f64(float64_t __p0, float64_t __p1) {
49861	uint64_t __ret;
49862	__ret = (uint64_t) __builtin_neon_vcged_f64(__p0, __p1);
49863	return __ret;
49864	}
49865	#else
49866	__ai uint64_t vcged_f64(float64_t __p0, float64_t __p1) {	42546	__ai uint64_t vcged_f64(float64_t __p0, float64_t __p1) {
49867	uint64_t __ret;	42547	uint64_t __ret;
49868	__ret = (uint64_t) __builtin_neon_vcged_f64(__p0, __p1);	42548	__ret = (uint64_t) __builtin_neon_vcged_f64(__p0, __p1);
49869	return __ret;	42549	return __ret;
49870	}	42550	}
49871	#endif
49872
49873	#ifdef __LITTLE_ENDIAN__
49874	__ai uint32_t vcges_f32(float32_t __p0, float32_t __p1) {
49875	uint32_t __ret;
49876	__ret = (uint32_t) __builtin_neon_vcges_f32(__p0, __p1);
49877	return __ret;
49878	}
49879	#else
49880	__ai uint32_t vcges_f32(float32_t __p0, float32_t __p1) {	42551	__ai uint32_t vcges_f32(float32_t __p0, float32_t __p1) {
49881	uint32_t __ret;	42552	uint32_t __ret;
49882	__ret = (uint32_t) __builtin_neon_vcges_f32(__p0, __p1);	42553	__ret = (uint32_t) __builtin_neon_vcges_f32(__p0, __p1);
49883	return __ret;	42554	return __ret;
49884	}	42555	}
49885	#endif
49886
49887	#ifdef __LITTLE_ENDIAN__	42556	#ifdef __LITTLE_ENDIAN__
49888	__ai uint8x16_t vcgezq_s8(int8x16_t __p0) {	42557	__ai uint8x16_t vcgezq_s8(int8x16_t __p0) {
49889	uint8x16_t __ret;	42558	uint8x16_t __ret;
...	@@ -49996,20 +42665,11 @@ __ai uint8x8_t vcgez_s8(int8x8_t __p0) {	...	@@ -49996,20 +42665,11 @@ __ai uint8x8_t vcgez_s8(int8x8_t __p0) {
49996	}	42665	}
49997	#endif	42666	#endif
49998		42667
49999	#ifdef __LITTLE_ENDIAN__
50000	__ai uint64x1_t vcgez_f64(float64x1_t __p0) {	42668	__ai uint64x1_t vcgez_f64(float64x1_t __p0) {
50001	uint64x1_t __ret;	42669	uint64x1_t __ret;
50002	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);	42670	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
50003	return __ret;	42671	return __ret;
50004	}	42672	}
50005	#else
50006	__ai uint64x1_t vcgez_f64(float64x1_t __p0) {
50007	uint64x1_t __ret;
50008	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
50009	return __ret;
50010	}
50011	#endif
50012
50013	#ifdef __LITTLE_ENDIAN__	42673	#ifdef __LITTLE_ENDIAN__
50014	__ai uint32x2_t vcgez_f32(float32x2_t __p0) {	42674	__ai uint32x2_t vcgez_f32(float32x2_t __p0) {
50015	uint32x2_t __ret;	42675	uint32x2_t __ret;
...	@@ -50042,20 +42702,11 @@ __ai uint32x2_t vcgez_s32(int32x2_t __p0) {	...	@@ -50042,20 +42702,11 @@ __ai uint32x2_t vcgez_s32(int32x2_t __p0) {
50042	}	42702	}
50043	#endif	42703	#endif
50044		42704
50045	#ifdef __LITTLE_ENDIAN__
50046	__ai uint64x1_t vcgez_s64(int64x1_t __p0) {	42705	__ai uint64x1_t vcgez_s64(int64x1_t __p0) {
50047	uint64x1_t __ret;	42706	uint64x1_t __ret;
50048	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);	42707	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
50049	return __ret;	42708	return __ret;
50050	}	42709	}
50051	#else
50052	__ai uint64x1_t vcgez_s64(int64x1_t __p0) {
50053	uint64x1_t __ret;
50054	__ret = (uint64x1_t) __builtin_neon_vcgez_v((int8x8_t)__p0, 19);
50055	return __ret;
50056	}
50057	#endif
50058
50059	#ifdef __LITTLE_ENDIAN__	42710	#ifdef __LITTLE_ENDIAN__
50060	__ai uint16x4_t vcgez_s16(int16x4_t __p0) {	42711	__ai uint16x4_t vcgez_s16(int16x4_t __p0) {
50061	uint16x4_t __ret;	42712	uint16x4_t __ret;
...	@@ -50072,48 +42723,21 @@ __ai uint16x4_t vcgez_s16(int16x4_t __p0) {	...	@@ -50072,48 +42723,21 @@ __ai uint16x4_t vcgez_s16(int16x4_t __p0) {
50072	}	42723	}
50073	#endif	42724	#endif
50074		42725
50075	#ifdef __LITTLE_ENDIAN__
50076	__ai int64_t vcgezd_s64(int64_t __p0) {	42726	__ai int64_t vcgezd_s64(int64_t __p0) {
50077	int64_t __ret;	42727	int64_t __ret;
50078	__ret = (int64_t) __builtin_neon_vcgezd_s64(__p0);	42728	__ret = (int64_t) __builtin_neon_vcgezd_s64(__p0);
50079	return __ret;	42729	return __ret;
50080	}	42730	}
50081	#else
50082	__ai int64_t vcgezd_s64(int64_t __p0) {
50083	int64_t __ret;
50084	__ret = (int64_t) __builtin_neon_vcgezd_s64(__p0);
50085	return __ret;
50086	}
50087	#endif
50088
50089	#ifdef __LITTLE_ENDIAN__
50090	__ai uint64_t vcgezd_f64(float64_t __p0) {
50091	uint64_t __ret;
50092	__ret = (uint64_t) __builtin_neon_vcgezd_f64(__p0);
50093	return __ret;
50094	}
50095	#else
50096	__ai uint64_t vcgezd_f64(float64_t __p0) {	42731	__ai uint64_t vcgezd_f64(float64_t __p0) {
50097	uint64_t __ret;	42732	uint64_t __ret;
50098	__ret = (uint64_t) __builtin_neon_vcgezd_f64(__p0);	42733	__ret = (uint64_t) __builtin_neon_vcgezd_f64(__p0);
50099	return __ret;	42734	return __ret;
50100	}	42735	}
50101	#endif
50102
50103	#ifdef __LITTLE_ENDIAN__
50104	__ai uint32_t vcgezs_f32(float32_t __p0) {
50105	uint32_t __ret;
50106	__ret = (uint32_t) __builtin_neon_vcgezs_f32(__p0);
50107	return __ret;
50108	}
50109	#else
50110	__ai uint32_t vcgezs_f32(float32_t __p0) {	42736	__ai uint32_t vcgezs_f32(float32_t __p0) {
50111	uint32_t __ret;	42737	uint32_t __ret;
50112	__ret = (uint32_t) __builtin_neon_vcgezs_f32(__p0);	42738	__ret = (uint32_t) __builtin_neon_vcgezs_f32(__p0);
50113	return __ret;	42739	return __ret;
50114	}	42740	}
50115	#endif
50116
50117	#ifdef __LITTLE_ENDIAN__	42741	#ifdef __LITTLE_ENDIAN__
50118	__ai uint64x2_t vcgtq_u64(uint64x2_t __p0, uint64x2_t __p1) {	42742	__ai uint64x2_t vcgtq_u64(uint64x2_t __p0, uint64x2_t __p1) {
50119	uint64x2_t __ret;	42743	uint64x2_t __ret;
...	@@ -50165,104 +42789,41 @@ __ai uint64x2_t vcgtq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -50165,104 +42789,41 @@ __ai uint64x2_t vcgtq_s64(int64x2_t __p0, int64x2_t __p1) {
50165	}	42789	}
50166	#endif	42790	#endif
50167		42791
50168	#ifdef __LITTLE_ENDIAN__
50169	__ai uint64x1_t vcgt_u64(uint64x1_t __p0, uint64x1_t __p1) {	42792	__ai uint64x1_t vcgt_u64(uint64x1_t __p0, uint64x1_t __p1) {
50170	uint64x1_t __ret;	42793	uint64x1_t __ret;
50171	__ret = (uint64x1_t)(__p0 > __p1);	42794	__ret = (uint64x1_t)(__p0 > __p1);
50172	return __ret;	42795	return __ret;
50173	}	42796	}
50174	#else
50175	__ai uint64x1_t vcgt_u64(uint64x1_t __p0, uint64x1_t __p1) {
50176	uint64x1_t __ret;
50177	__ret = (uint64x1_t)(__p0 > __p1);
50178	return __ret;
50179	}
50180	#endif
50181
50182	#ifdef __LITTLE_ENDIAN__
50183	__ai uint64x1_t vcgt_f64(float64x1_t __p0, float64x1_t __p1) {
50184	uint64x1_t __ret;
50185	__ret = (uint64x1_t)(__p0 > __p1);
50186	return __ret;
50187	}
50188	#else
50189	__ai uint64x1_t vcgt_f64(float64x1_t __p0, float64x1_t __p1) {	42797	__ai uint64x1_t vcgt_f64(float64x1_t __p0, float64x1_t __p1) {
50190	uint64x1_t __ret;	42798	uint64x1_t __ret;
50191	__ret = (uint64x1_t)(__p0 > __p1);	42799	__ret = (uint64x1_t)(__p0 > __p1);
50192	return __ret;	42800	return __ret;
50193	}	42801	}
50194	#endif
50195
50196	#ifdef __LITTLE_ENDIAN__
50197	__ai uint64x1_t vcgt_s64(int64x1_t __p0, int64x1_t __p1) {
50198	uint64x1_t __ret;
50199	__ret = (uint64x1_t)(__p0 > __p1);
50200	return __ret;
50201	}
50202	#else
50203	__ai uint64x1_t vcgt_s64(int64x1_t __p0, int64x1_t __p1) {	42802	__ai uint64x1_t vcgt_s64(int64x1_t __p0, int64x1_t __p1) {
50204	uint64x1_t __ret;	42803	uint64x1_t __ret;
50205	__ret = (uint64x1_t)(__p0 > __p1);	42804	__ret = (uint64x1_t)(__p0 > __p1);
50206	return __ret;	42805	return __ret;
50207	}	42806	}
50208	#endif
50209
50210	#ifdef __LITTLE_ENDIAN__
50211	__ai int64_t vcgtd_s64(int64_t __p0, int64_t __p1) {
50212	int64_t __ret;
50213	__ret = (int64_t) __builtin_neon_vcgtd_s64(__p0, __p1);
50214	return __ret;
50215	}
50216	#else
50217	__ai int64_t vcgtd_s64(int64_t __p0, int64_t __p1) {	42807	__ai int64_t vcgtd_s64(int64_t __p0, int64_t __p1) {
50218	int64_t __ret;	42808	int64_t __ret;
50219	__ret = (int64_t) __builtin_neon_vcgtd_s64(__p0, __p1);	42809	__ret = (int64_t) __builtin_neon_vcgtd_s64(__p0, __p1);
50220	return __ret;	42810	return __ret;
50221	}	42811	}
50222	#endif
50223
50224	#ifdef __LITTLE_ENDIAN__
50225	__ai uint64_t vcgtd_u64(uint64_t __p0, uint64_t __p1) {
50226	uint64_t __ret;
50227	__ret = (uint64_t) __builtin_neon_vcgtd_u64(__p0, __p1);
50228	return __ret;
50229	}
50230	#else
50231	__ai uint64_t vcgtd_u64(uint64_t __p0, uint64_t __p1) {	42812	__ai uint64_t vcgtd_u64(uint64_t __p0, uint64_t __p1) {
50232	uint64_t __ret;	42813	uint64_t __ret;
50233	__ret = (uint64_t) __builtin_neon_vcgtd_u64(__p0, __p1);	42814	__ret = (uint64_t) __builtin_neon_vcgtd_u64(__p0, __p1);
50234	return __ret;	42815	return __ret;
50235	}	42816	}
50236	#endif
50237
50238	#ifdef __LITTLE_ENDIAN__
50239	__ai uint64_t vcgtd_f64(float64_t __p0, float64_t __p1) {
50240	uint64_t __ret;
50241	__ret = (uint64_t) __builtin_neon_vcgtd_f64(__p0, __p1);
50242	return __ret;
50243	}
50244	#else
50245	__ai uint64_t vcgtd_f64(float64_t __p0, float64_t __p1) {	42817	__ai uint64_t vcgtd_f64(float64_t __p0, float64_t __p1) {
50246	uint64_t __ret;	42818	uint64_t __ret;
50247	__ret = (uint64_t) __builtin_neon_vcgtd_f64(__p0, __p1);	42819	__ret = (uint64_t) __builtin_neon_vcgtd_f64(__p0, __p1);
50248	return __ret;	42820	return __ret;
50249	}	42821	}
50250	#endif
50251
50252	#ifdef __LITTLE_ENDIAN__
50253	__ai uint32_t vcgts_f32(float32_t __p0, float32_t __p1) {
50254	uint32_t __ret;
50255	__ret = (uint32_t) __builtin_neon_vcgts_f32(__p0, __p1);
50256	return __ret;
50257	}
50258	#else
50259	__ai uint32_t vcgts_f32(float32_t __p0, float32_t __p1) {	42822	__ai uint32_t vcgts_f32(float32_t __p0, float32_t __p1) {
50260	uint32_t __ret;	42823	uint32_t __ret;
50261	__ret = (uint32_t) __builtin_neon_vcgts_f32(__p0, __p1);	42824	__ret = (uint32_t) __builtin_neon_vcgts_f32(__p0, __p1);
50262	return __ret;	42825	return __ret;
50263	}	42826	}
50264	#endif
50265
50266	#ifdef __LITTLE_ENDIAN__	42827	#ifdef __LITTLE_ENDIAN__
50267	__ai uint8x16_t vcgtzq_s8(int8x16_t __p0) {	42828	__ai uint8x16_t vcgtzq_s8(int8x16_t __p0) {
50268	uint8x16_t __ret;	42829	uint8x16_t __ret;
...	@@ -50375,20 +42936,11 @@ __ai uint8x8_t vcgtz_s8(int8x8_t __p0) {	...	@@ -50375,20 +42936,11 @@ __ai uint8x8_t vcgtz_s8(int8x8_t __p0) {
50375	}	42936	}
50376	#endif	42937	#endif
50377		42938
50378	#ifdef __LITTLE_ENDIAN__
50379	__ai uint64x1_t vcgtz_f64(float64x1_t __p0) {	42939	__ai uint64x1_t vcgtz_f64(float64x1_t __p0) {
50380	uint64x1_t __ret;	42940	uint64x1_t __ret;
50381	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);	42941	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
50382	return __ret;	42942	return __ret;
50383	}	42943	}
50384	#else
50385	__ai uint64x1_t vcgtz_f64(float64x1_t __p0) {
50386	uint64x1_t __ret;
50387	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
50388	return __ret;
50389	}
50390	#endif
50391
50392	#ifdef __LITTLE_ENDIAN__	42944	#ifdef __LITTLE_ENDIAN__
50393	__ai uint32x2_t vcgtz_f32(float32x2_t __p0) {	42945	__ai uint32x2_t vcgtz_f32(float32x2_t __p0) {
50394	uint32x2_t __ret;	42946	uint32x2_t __ret;
...	@@ -50421,20 +42973,11 @@ __ai uint32x2_t vcgtz_s32(int32x2_t __p0) {	...	@@ -50421,20 +42973,11 @@ __ai uint32x2_t vcgtz_s32(int32x2_t __p0) {
50421	}	42973	}
50422	#endif	42974	#endif
50423		42975
50424	#ifdef __LITTLE_ENDIAN__
50425	__ai uint64x1_t vcgtz_s64(int64x1_t __p0) {	42976	__ai uint64x1_t vcgtz_s64(int64x1_t __p0) {
50426	uint64x1_t __ret;	42977	uint64x1_t __ret;
50427	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);	42978	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
50428	return __ret;	42979	return __ret;
50429	}	42980	}
50430	#else
50431	__ai uint64x1_t vcgtz_s64(int64x1_t __p0) {
50432	uint64x1_t __ret;
50433	__ret = (uint64x1_t) __builtin_neon_vcgtz_v((int8x8_t)__p0, 19);
50434	return __ret;
50435	}
50436	#endif
50437
50438	#ifdef __LITTLE_ENDIAN__	42981	#ifdef __LITTLE_ENDIAN__
50439	__ai uint16x4_t vcgtz_s16(int16x4_t __p0) {	42982	__ai uint16x4_t vcgtz_s16(int16x4_t __p0) {
50440	uint16x4_t __ret;	42983	uint16x4_t __ret;
...	@@ -50451,48 +42994,21 @@ __ai uint16x4_t vcgtz_s16(int16x4_t __p0) {	...	@@ -50451,48 +42994,21 @@ __ai uint16x4_t vcgtz_s16(int16x4_t __p0) {
50451	}	42994	}
50452	#endif	42995	#endif
50453		42996
50454	#ifdef __LITTLE_ENDIAN__
50455	__ai int64_t vcgtzd_s64(int64_t __p0) {	42997	__ai int64_t vcgtzd_s64(int64_t __p0) {
50456	int64_t __ret;	42998	int64_t __ret;
50457	__ret = (int64_t) __builtin_neon_vcgtzd_s64(__p0);	42999	__ret = (int64_t) __builtin_neon_vcgtzd_s64(__p0);
50458	return __ret;	43000	return __ret;
50459	}	43001	}
50460	#else
50461	__ai int64_t vcgtzd_s64(int64_t __p0) {
50462	int64_t __ret;
50463	__ret = (int64_t) __builtin_neon_vcgtzd_s64(__p0);
50464	return __ret;
50465	}
50466	#endif
50467
50468	#ifdef __LITTLE_ENDIAN__
50469	__ai uint64_t vcgtzd_f64(float64_t __p0) {
50470	uint64_t __ret;
50471	__ret = (uint64_t) __builtin_neon_vcgtzd_f64(__p0);
50472	return __ret;
50473	}
50474	#else
50475	__ai uint64_t vcgtzd_f64(float64_t __p0) {	43002	__ai uint64_t vcgtzd_f64(float64_t __p0) {
50476	uint64_t __ret;	43003	uint64_t __ret;
50477	__ret = (uint64_t) __builtin_neon_vcgtzd_f64(__p0);	43004	__ret = (uint64_t) __builtin_neon_vcgtzd_f64(__p0);
50478	return __ret;	43005	return __ret;
50479	}	43006	}
50480	#endif
50481
50482	#ifdef __LITTLE_ENDIAN__
50483	__ai uint32_t vcgtzs_f32(float32_t __p0) {
50484	uint32_t __ret;
50485	__ret = (uint32_t) __builtin_neon_vcgtzs_f32(__p0);
50486	return __ret;
50487	}
50488	#else
50489	__ai uint32_t vcgtzs_f32(float32_t __p0) {	43007	__ai uint32_t vcgtzs_f32(float32_t __p0) {
50490	uint32_t __ret;	43008	uint32_t __ret;
50491	__ret = (uint32_t) __builtin_neon_vcgtzs_f32(__p0);	43009	__ret = (uint32_t) __builtin_neon_vcgtzs_f32(__p0);
50492	return __ret;	43010	return __ret;
50493	}	43011	}
50494	#endif
50495
50496	#ifdef __LITTLE_ENDIAN__	43012	#ifdef __LITTLE_ENDIAN__
50497	__ai uint64x2_t vcleq_u64(uint64x2_t __p0, uint64x2_t __p1) {	43013	__ai uint64x2_t vcleq_u64(uint64x2_t __p0, uint64x2_t __p1) {
50498	uint64x2_t __ret;	43014	uint64x2_t __ret;
...	@@ -50544,104 +43060,41 @@ __ai uint64x2_t vcleq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -50544,104 +43060,41 @@ __ai uint64x2_t vcleq_s64(int64x2_t __p0, int64x2_t __p1) {
50544	}	43060	}
50545	#endif	43061	#endif
50546		43062
50547	#ifdef __LITTLE_ENDIAN__
50548	__ai uint64x1_t vcle_u64(uint64x1_t __p0, uint64x1_t __p1) {	43063	__ai uint64x1_t vcle_u64(uint64x1_t __p0, uint64x1_t __p1) {
50549	uint64x1_t __ret;	43064	uint64x1_t __ret;
50550	__ret = (uint64x1_t)(__p0 <= __p1);	43065	__ret = (uint64x1_t)(__p0 <= __p1);
50551	return __ret;	43066	return __ret;
50552	}	43067	}
50553	#else
50554	__ai uint64x1_t vcle_u64(uint64x1_t __p0, uint64x1_t __p1) {
50555	uint64x1_t __ret;
50556	__ret = (uint64x1_t)(__p0 <= __p1);
50557	return __ret;
50558	}
50559	#endif
50560
50561	#ifdef __LITTLE_ENDIAN__
50562	__ai uint64x1_t vcle_f64(float64x1_t __p0, float64x1_t __p1) {
50563	uint64x1_t __ret;
50564	__ret = (uint64x1_t)(__p0 <= __p1);
50565	return __ret;
50566	}
50567	#else
50568	__ai uint64x1_t vcle_f64(float64x1_t __p0, float64x1_t __p1) {	43068	__ai uint64x1_t vcle_f64(float64x1_t __p0, float64x1_t __p1) {
50569	uint64x1_t __ret;	43069	uint64x1_t __ret;
50570	__ret = (uint64x1_t)(__p0 <= __p1);	43070	__ret = (uint64x1_t)(__p0 <= __p1);
50571	return __ret;	43071	return __ret;
50572	}	43072	}
50573	#endif
50574
50575	#ifdef __LITTLE_ENDIAN__
50576	__ai uint64x1_t vcle_s64(int64x1_t __p0, int64x1_t __p1) {
50577	uint64x1_t __ret;
50578	__ret = (uint64x1_t)(__p0 <= __p1);
50579	return __ret;
50580	}
50581	#else
50582	__ai uint64x1_t vcle_s64(int64x1_t __p0, int64x1_t __p1) {	43073	__ai uint64x1_t vcle_s64(int64x1_t __p0, int64x1_t __p1) {
50583	uint64x1_t __ret;	43074	uint64x1_t __ret;
50584	__ret = (uint64x1_t)(__p0 <= __p1);	43075	__ret = (uint64x1_t)(__p0 <= __p1);
50585	return __ret;	43076	return __ret;
50586	}	43077	}
50587	#endif
50588
50589	#ifdef __LITTLE_ENDIAN__
50590	__ai uint64_t vcled_u64(uint64_t __p0, uint64_t __p1) {
50591	uint64_t __ret;
50592	__ret = (uint64_t) __builtin_neon_vcled_u64(__p0, __p1);
50593	return __ret;
50594	}
50595	#else
50596	__ai uint64_t vcled_u64(uint64_t __p0, uint64_t __p1) {	43078	__ai uint64_t vcled_u64(uint64_t __p0, uint64_t __p1) {
50597	uint64_t __ret;	43079	uint64_t __ret;
50598	__ret = (uint64_t) __builtin_neon_vcled_u64(__p0, __p1);	43080	__ret = (uint64_t) __builtin_neon_vcled_u64(__p0, __p1);
50599	return __ret;	43081	return __ret;
50600	}	43082	}
50601	#endif
50602
50603	#ifdef __LITTLE_ENDIAN__
50604	__ai int64_t vcled_s64(int64_t __p0, int64_t __p1) {
50605	int64_t __ret;
50606	__ret = (int64_t) __builtin_neon_vcled_s64(__p0, __p1);
50607	return __ret;
50608	}
50609	#else
50610	__ai int64_t vcled_s64(int64_t __p0, int64_t __p1) {	43083	__ai int64_t vcled_s64(int64_t __p0, int64_t __p1) {
50611	int64_t __ret;	43084	int64_t __ret;
50612	__ret = (int64_t) __builtin_neon_vcled_s64(__p0, __p1);	43085	__ret = (int64_t) __builtin_neon_vcled_s64(__p0, __p1);
50613	return __ret;	43086	return __ret;
50614	}	43087	}
50615	#endif
50616
50617	#ifdef __LITTLE_ENDIAN__
50618	__ai uint64_t vcled_f64(float64_t __p0, float64_t __p1) {
50619	uint64_t __ret;
50620	__ret = (uint64_t) __builtin_neon_vcled_f64(__p0, __p1);
50621	return __ret;
50622	}
50623	#else
50624	__ai uint64_t vcled_f64(float64_t __p0, float64_t __p1) {	43088	__ai uint64_t vcled_f64(float64_t __p0, float64_t __p1) {
50625	uint64_t __ret;	43089	uint64_t __ret;
50626	__ret = (uint64_t) __builtin_neon_vcled_f64(__p0, __p1);	43090	__ret = (uint64_t) __builtin_neon_vcled_f64(__p0, __p1);
50627	return __ret;	43091	return __ret;
50628	}	43092	}
50629	#endif
50630
50631	#ifdef __LITTLE_ENDIAN__
50632	__ai uint32_t vcles_f32(float32_t __p0, float32_t __p1) {
50633	uint32_t __ret;
50634	__ret = (uint32_t) __builtin_neon_vcles_f32(__p0, __p1);
50635	return __ret;
50636	}
50637	#else
50638	__ai uint32_t vcles_f32(float32_t __p0, float32_t __p1) {	43093	__ai uint32_t vcles_f32(float32_t __p0, float32_t __p1) {
50639	uint32_t __ret;	43094	uint32_t __ret;
50640	__ret = (uint32_t) __builtin_neon_vcles_f32(__p0, __p1);	43095	__ret = (uint32_t) __builtin_neon_vcles_f32(__p0, __p1);
50641	return __ret;	43096	return __ret;
50642	}	43097	}
50643	#endif
50644
50645	#ifdef __LITTLE_ENDIAN__	43098	#ifdef __LITTLE_ENDIAN__
50646	__ai uint8x16_t vclezq_s8(int8x16_t __p0) {	43099	__ai uint8x16_t vclezq_s8(int8x16_t __p0) {
50647	uint8x16_t __ret;	43100	uint8x16_t __ret;
...	@@ -50754,20 +43207,11 @@ __ai uint8x8_t vclez_s8(int8x8_t __p0) {	...	@@ -50754,20 +43207,11 @@ __ai uint8x8_t vclez_s8(int8x8_t __p0) {
50754	}	43207	}
50755	#endif	43208	#endif
50756		43209
50757	#ifdef __LITTLE_ENDIAN__
50758	__ai uint64x1_t vclez_f64(float64x1_t __p0) {	43210	__ai uint64x1_t vclez_f64(float64x1_t __p0) {
50759	uint64x1_t __ret;	43211	uint64x1_t __ret;
50760	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);	43212	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
50761	return __ret;	43213	return __ret;
50762	}	43214	}
50763	#else
50764	__ai uint64x1_t vclez_f64(float64x1_t __p0) {
50765	uint64x1_t __ret;
50766	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
50767	return __ret;
50768	}
50769	#endif
50770
50771	#ifdef __LITTLE_ENDIAN__	43215	#ifdef __LITTLE_ENDIAN__
50772	__ai uint32x2_t vclez_f32(float32x2_t __p0) {	43216	__ai uint32x2_t vclez_f32(float32x2_t __p0) {
50773	uint32x2_t __ret;	43217	uint32x2_t __ret;
...	@@ -50800,20 +43244,11 @@ __ai uint32x2_t vclez_s32(int32x2_t __p0) {	...	@@ -50800,20 +43244,11 @@ __ai uint32x2_t vclez_s32(int32x2_t __p0) {
50800	}	43244	}
50801	#endif	43245	#endif
50802		43246
50803	#ifdef __LITTLE_ENDIAN__
50804	__ai uint64x1_t vclez_s64(int64x1_t __p0) {	43247	__ai uint64x1_t vclez_s64(int64x1_t __p0) {
50805	uint64x1_t __ret;	43248	uint64x1_t __ret;
50806	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);	43249	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
50807	return __ret;	43250	return __ret;
50808	}	43251	}
50809	#else
50810	__ai uint64x1_t vclez_s64(int64x1_t __p0) {
50811	uint64x1_t __ret;
50812	__ret = (uint64x1_t) __builtin_neon_vclez_v((int8x8_t)__p0, 19);
50813	return __ret;
50814	}
50815	#endif
50816
50817	#ifdef __LITTLE_ENDIAN__	43252	#ifdef __LITTLE_ENDIAN__
50818	__ai uint16x4_t vclez_s16(int16x4_t __p0) {	43253	__ai uint16x4_t vclez_s16(int16x4_t __p0) {
50819	uint16x4_t __ret;	43254	uint16x4_t __ret;
...	@@ -50830,48 +43265,21 @@ __ai uint16x4_t vclez_s16(int16x4_t __p0) {	...	@@ -50830,48 +43265,21 @@ __ai uint16x4_t vclez_s16(int16x4_t __p0) {
50830	}	43265	}
50831	#endif	43266	#endif
50832		43267
50833	#ifdef __LITTLE_ENDIAN__
50834	__ai int64_t vclezd_s64(int64_t __p0) {	43268	__ai int64_t vclezd_s64(int64_t __p0) {
50835	int64_t __ret;	43269	int64_t __ret;
50836	__ret = (int64_t) __builtin_neon_vclezd_s64(__p0);	43270	__ret = (int64_t) __builtin_neon_vclezd_s64(__p0);
50837	return __ret;	43271	return __ret;
50838	}	43272	}
50839	#else
50840	__ai int64_t vclezd_s64(int64_t __p0) {
50841	int64_t __ret;
50842	__ret = (int64_t) __builtin_neon_vclezd_s64(__p0);
50843	return __ret;
50844	}
50845	#endif
50846
50847	#ifdef __LITTLE_ENDIAN__
50848	__ai uint64_t vclezd_f64(float64_t __p0) {
50849	uint64_t __ret;
50850	__ret = (uint64_t) __builtin_neon_vclezd_f64(__p0);
50851	return __ret;
50852	}
50853	#else
50854	__ai uint64_t vclezd_f64(float64_t __p0) {	43273	__ai uint64_t vclezd_f64(float64_t __p0) {
50855	uint64_t __ret;	43274	uint64_t __ret;
50856	__ret = (uint64_t) __builtin_neon_vclezd_f64(__p0);	43275	__ret = (uint64_t) __builtin_neon_vclezd_f64(__p0);
50857	return __ret;	43276	return __ret;
50858	}	43277	}
50859	#endif
50860
50861	#ifdef __LITTLE_ENDIAN__
50862	__ai uint32_t vclezs_f32(float32_t __p0) {
50863	uint32_t __ret;
50864	__ret = (uint32_t) __builtin_neon_vclezs_f32(__p0);
50865	return __ret;
50866	}
50867	#else
50868	__ai uint32_t vclezs_f32(float32_t __p0) {	43278	__ai uint32_t vclezs_f32(float32_t __p0) {
50869	uint32_t __ret;	43279	uint32_t __ret;
50870	__ret = (uint32_t) __builtin_neon_vclezs_f32(__p0);	43280	__ret = (uint32_t) __builtin_neon_vclezs_f32(__p0);
50871	return __ret;	43281	return __ret;
50872	}	43282	}
50873	#endif
50874
50875	#ifdef __LITTLE_ENDIAN__	43283	#ifdef __LITTLE_ENDIAN__
50876	__ai uint64x2_t vcltq_u64(uint64x2_t __p0, uint64x2_t __p1) {	43284	__ai uint64x2_t vcltq_u64(uint64x2_t __p0, uint64x2_t __p1) {
50877	uint64x2_t __ret;	43285	uint64x2_t __ret;
...	@@ -50923,104 +43331,41 @@ __ai uint64x2_t vcltq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -50923,104 +43331,41 @@ __ai uint64x2_t vcltq_s64(int64x2_t __p0, int64x2_t __p1) {
50923	}	43331	}
50924	#endif	43332	#endif
50925		43333
50926	#ifdef __LITTLE_ENDIAN__
50927	__ai uint64x1_t vclt_u64(uint64x1_t __p0, uint64x1_t __p1) {	43334	__ai uint64x1_t vclt_u64(uint64x1_t __p0, uint64x1_t __p1) {
50928	uint64x1_t __ret;	43335	uint64x1_t __ret;
50929	__ret = (uint64x1_t)(__p0 < __p1);	43336	__ret = (uint64x1_t)(__p0 < __p1);
50930	return __ret;	43337	return __ret;
50931	}	43338	}
50932	#else
50933	__ai uint64x1_t vclt_u64(uint64x1_t __p0, uint64x1_t __p1) {
50934	uint64x1_t __ret;
50935	__ret = (uint64x1_t)(__p0 < __p1);
50936	return __ret;
50937	}
50938	#endif
50939
50940	#ifdef __LITTLE_ENDIAN__
50941	__ai uint64x1_t vclt_f64(float64x1_t __p0, float64x1_t __p1) {
50942	uint64x1_t __ret;
50943	__ret = (uint64x1_t)(__p0 < __p1);
50944	return __ret;
50945	}
50946	#else
50947	__ai uint64x1_t vclt_f64(float64x1_t __p0, float64x1_t __p1) {	43339	__ai uint64x1_t vclt_f64(float64x1_t __p0, float64x1_t __p1) {
50948	uint64x1_t __ret;	43340	uint64x1_t __ret;
50949	__ret = (uint64x1_t)(__p0 < __p1);	43341	__ret = (uint64x1_t)(__p0 < __p1);
50950	return __ret;	43342	return __ret;
50951	}	43343	}
50952	#endif
50953
50954	#ifdef __LITTLE_ENDIAN__
50955	__ai uint64x1_t vclt_s64(int64x1_t __p0, int64x1_t __p1) {	43344	__ai uint64x1_t vclt_s64(int64x1_t __p0, int64x1_t __p1) {
50956	uint64x1_t __ret;	43345	uint64x1_t __ret;
50957	__ret = (uint64x1_t)(__p0 < __p1);	43346	__ret = (uint64x1_t)(__p0 < __p1);
50958	return __ret;	43347	return __ret;
50959	}	43348	}
50960	#else
50961	__ai uint64x1_t vclt_s64(int64x1_t __p0, int64x1_t __p1) {
50962	uint64x1_t __ret;
50963	__ret = (uint64x1_t)(__p0 < __p1);
50964	return __ret;
50965	}
50966	#endif
50967
50968	#ifdef __LITTLE_ENDIAN__
50969	__ai uint64_t vcltd_u64(uint64_t __p0, uint64_t __p1) {
50970	uint64_t __ret;
50971	__ret = (uint64_t) __builtin_neon_vcltd_u64(__p0, __p1);
50972	return __ret;
50973	}
50974	#else
50975	__ai uint64_t vcltd_u64(uint64_t __p0, uint64_t __p1) {	43349	__ai uint64_t vcltd_u64(uint64_t __p0, uint64_t __p1) {
50976	uint64_t __ret;	43350	uint64_t __ret;
50977	__ret = (uint64_t) __builtin_neon_vcltd_u64(__p0, __p1);	43351	__ret = (uint64_t) __builtin_neon_vcltd_u64(__p0, __p1);
50978	return __ret;	43352	return __ret;
50979	}	43353	}
50980	#endif
50981
50982	#ifdef __LITTLE_ENDIAN__
50983	__ai int64_t vcltd_s64(int64_t __p0, int64_t __p1) {	43354	__ai int64_t vcltd_s64(int64_t __p0, int64_t __p1) {
50984	int64_t __ret;	43355	int64_t __ret;
50985	__ret = (int64_t) __builtin_neon_vcltd_s64(__p0, __p1);	43356	__ret = (int64_t) __builtin_neon_vcltd_s64(__p0, __p1);
50986	return __ret;	43357	return __ret;
50987	}	43358	}
50988	#else
50989	__ai int64_t vcltd_s64(int64_t __p0, int64_t __p1) {
50990	int64_t __ret;
50991	__ret = (int64_t) __builtin_neon_vcltd_s64(__p0, __p1);
50992	return __ret;
50993	}
50994	#endif
50995
50996	#ifdef __LITTLE_ENDIAN__
50997	__ai uint64_t vcltd_f64(float64_t __p0, float64_t __p1) {
50998	uint64_t __ret;
50999	__ret = (uint64_t) __builtin_neon_vcltd_f64(__p0, __p1);
51000	return __ret;
51001	}
51002	#else
51003	__ai uint64_t vcltd_f64(float64_t __p0, float64_t __p1) {	43359	__ai uint64_t vcltd_f64(float64_t __p0, float64_t __p1) {
51004	uint64_t __ret;	43360	uint64_t __ret;
51005	__ret = (uint64_t) __builtin_neon_vcltd_f64(__p0, __p1);	43361	__ret = (uint64_t) __builtin_neon_vcltd_f64(__p0, __p1);
51006	return __ret;	43362	return __ret;
51007	}	43363	}
51008	#endif
51009
51010	#ifdef __LITTLE_ENDIAN__
51011	__ai uint32_t vclts_f32(float32_t __p0, float32_t __p1) {	43364	__ai uint32_t vclts_f32(float32_t __p0, float32_t __p1) {
51012	uint32_t __ret;	43365	uint32_t __ret;
51013	__ret = (uint32_t) __builtin_neon_vclts_f32(__p0, __p1);	43366	__ret = (uint32_t) __builtin_neon_vclts_f32(__p0, __p1);
51014	return __ret;	43367	return __ret;
51015	}	43368	}
51016	#else
51017	__ai uint32_t vclts_f32(float32_t __p0, float32_t __p1) {
51018	uint32_t __ret;
51019	__ret = (uint32_t) __builtin_neon_vclts_f32(__p0, __p1);
51020	return __ret;
51021	}
51022	#endif
51023
51024	#ifdef __LITTLE_ENDIAN__	43369	#ifdef __LITTLE_ENDIAN__
51025	__ai uint8x16_t vcltzq_s8(int8x16_t __p0) {	43370	__ai uint8x16_t vcltzq_s8(int8x16_t __p0) {
51026	uint8x16_t __ret;	43371	uint8x16_t __ret;
...	@@ -51133,20 +43478,11 @@ __ai uint8x8_t vcltz_s8(int8x8_t __p0) {	...	@@ -51133,20 +43478,11 @@ __ai uint8x8_t vcltz_s8(int8x8_t __p0) {
51133	}	43478	}
51134	#endif	43479	#endif
51135		43480
51136	#ifdef __LITTLE_ENDIAN__
51137	__ai uint64x1_t vcltz_f64(float64x1_t __p0) {
51138	uint64x1_t __ret;
51139	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
51140	return __ret;
51141	}
51142	#else
51143	__ai uint64x1_t vcltz_f64(float64x1_t __p0) {	43481	__ai uint64x1_t vcltz_f64(float64x1_t __p0) {
51144	uint64x1_t __ret;	43482	uint64x1_t __ret;
51145	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);	43483	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
51146	return __ret;	43484	return __ret;
51147	}	43485	}
51148	#endif
51149
51150	#ifdef __LITTLE_ENDIAN__	43486	#ifdef __LITTLE_ENDIAN__
51151	__ai uint32x2_t vcltz_f32(float32x2_t __p0) {	43487	__ai uint32x2_t vcltz_f32(float32x2_t __p0) {
51152	uint32x2_t __ret;	43488	uint32x2_t __ret;
...	@@ -51179,20 +43515,11 @@ __ai uint32x2_t vcltz_s32(int32x2_t __p0) {	...	@@ -51179,20 +43515,11 @@ __ai uint32x2_t vcltz_s32(int32x2_t __p0) {
51179	}	43515	}
51180	#endif	43516	#endif
51181		43517
51182	#ifdef __LITTLE_ENDIAN__
51183	__ai uint64x1_t vcltz_s64(int64x1_t __p0) {
51184	uint64x1_t __ret;
51185	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
51186	return __ret;
51187	}
51188	#else
51189	__ai uint64x1_t vcltz_s64(int64x1_t __p0) {	43518	__ai uint64x1_t vcltz_s64(int64x1_t __p0) {
51190	uint64x1_t __ret;	43519	uint64x1_t __ret;
51191	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);	43520	__ret = (uint64x1_t) __builtin_neon_vcltz_v((int8x8_t)__p0, 19);
51192	return __ret;	43521	return __ret;
51193	}	43522	}
51194	#endif
51195
51196	#ifdef __LITTLE_ENDIAN__	43523	#ifdef __LITTLE_ENDIAN__
51197	__ai uint16x4_t vcltz_s16(int16x4_t __p0) {	43524	__ai uint16x4_t vcltz_s16(int16x4_t __p0) {
51198	uint16x4_t __ret;	43525	uint16x4_t __ret;
...	@@ -51209,48 +43536,21 @@ __ai uint16x4_t vcltz_s16(int16x4_t __p0) {	...	@@ -51209,48 +43536,21 @@ __ai uint16x4_t vcltz_s16(int16x4_t __p0) {
51209	}	43536	}
51210	#endif	43537	#endif
51211		43538
51212	#ifdef __LITTLE_ENDIAN__
51213	__ai int64_t vcltzd_s64(int64_t __p0) {
51214	int64_t __ret;
51215	__ret = (int64_t) __builtin_neon_vcltzd_s64(__p0);
51216	return __ret;
51217	}
51218	#else
51219	__ai int64_t vcltzd_s64(int64_t __p0) {	43539	__ai int64_t vcltzd_s64(int64_t __p0) {
51220	int64_t __ret;	43540	int64_t __ret;
51221	__ret = (int64_t) __builtin_neon_vcltzd_s64(__p0);	43541	__ret = (int64_t) __builtin_neon_vcltzd_s64(__p0);
51222	return __ret;	43542	return __ret;
51223	}	43543	}
51224	#endif
51225
51226	#ifdef __LITTLE_ENDIAN__
51227	__ai uint64_t vcltzd_f64(float64_t __p0) {
51228	uint64_t __ret;
51229	__ret = (uint64_t) __builtin_neon_vcltzd_f64(__p0);
51230	return __ret;
51231	}
51232	#else
51233	__ai uint64_t vcltzd_f64(float64_t __p0) {	43544	__ai uint64_t vcltzd_f64(float64_t __p0) {
51234	uint64_t __ret;	43545	uint64_t __ret;
51235	__ret = (uint64_t) __builtin_neon_vcltzd_f64(__p0);	43546	__ret = (uint64_t) __builtin_neon_vcltzd_f64(__p0);
51236	return __ret;	43547	return __ret;
51237	}	43548	}
51238	#endif
51239
51240	#ifdef __LITTLE_ENDIAN__
51241	__ai uint32_t vcltzs_f32(float32_t __p0) {
51242	uint32_t __ret;
51243	__ret = (uint32_t) __builtin_neon_vcltzs_f32(__p0);
51244	return __ret;
51245	}
51246	#else
51247	__ai uint32_t vcltzs_f32(float32_t __p0) {	43549	__ai uint32_t vcltzs_f32(float32_t __p0) {
51248	uint32_t __ret;	43550	uint32_t __ret;
51249	__ret = (uint32_t) __builtin_neon_vcltzs_f32(__p0);	43551	__ret = (uint32_t) __builtin_neon_vcltzs_f32(__p0);
51250	return __ret;	43552	return __ret;
51251	}	43553	}
51252	#endif
51253
51254	#ifdef __LITTLE_ENDIAN__	43554	#ifdef __LITTLE_ENDIAN__
51255	__ai poly64x2_t vcombine_p64(poly64x1_t __p0, poly64x1_t __p1) {	43555	__ai poly64x2_t vcombine_p64(poly64x1_t __p0, poly64x1_t __p1) {
51256	poly64x2_t __ret;	43556	poly64x2_t __ret;
...	@@ -51379,7 +43679,7 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -51379,7 +43679,7 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
51379	uint64x1_t __s2_21 = __p2_21; \	43679	uint64x1_t __s2_21 = __p2_21; \
51380	uint64x2_t __rev0_21; __rev0_21 = __builtin_shufflevector(__s0_21, __s0_21, 1, 0); \	43680	uint64x2_t __rev0_21; __rev0_21 = __builtin_shufflevector(__s0_21, __s0_21, 1, 0); \
51381	uint64x2_t __ret_21; \	43681	uint64x2_t __ret_21; \
51382	__ret_21 = __noswap_vsetq_lane_u64(__noswap_vget_lane_u64(__s2_21, __p3_21), __rev0_21, __p1_21); \	43682	__ret_21 = __noswap_vsetq_lane_u64(vget_lane_u64(__s2_21, __p3_21), __rev0_21, __p1_21); \
51383	__ret_21 = __builtin_shufflevector(__ret_21, __ret_21, 1, 0); \	43683	__ret_21 = __builtin_shufflevector(__ret_21, __ret_21, 1, 0); \
51384	__ret_21; \	43684	__ret_21; \
51385	})	43685	})
...	@@ -51483,7 +43783,7 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -51483,7 +43783,7 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
51483	int64x1_t __s2_31 = __p2_31; \	43783	int64x1_t __s2_31 = __p2_31; \
51484	int64x2_t __rev0_31; __rev0_31 = __builtin_shufflevector(__s0_31, __s0_31, 1, 0); \	43784	int64x2_t __rev0_31; __rev0_31 = __builtin_shufflevector(__s0_31, __s0_31, 1, 0); \
51485	int64x2_t __ret_31; \	43785	int64x2_t __ret_31; \
51486	__ret_31 = __noswap_vsetq_lane_s64(__noswap_vget_lane_s64(__s2_31, __p3_31), __rev0_31, __p1_31); \	43786	__ret_31 = __noswap_vsetq_lane_s64(vget_lane_s64(__s2_31, __p3_31), __rev0_31, __p1_31); \
51487	__ret_31 = __builtin_shufflevector(__ret_31, __ret_31, 1, 0); \	43787	__ret_31 = __builtin_shufflevector(__ret_31, __ret_31, 1, 0); \
51488	__ret_31; \	43788	__ret_31; \
51489	})	43789	})
...	@@ -51594,7 +43894,6 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -51594,7 +43894,6 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
51594	})	43894	})
51595	#endif	43895	#endif
51596		43896
51597	#ifdef __LITTLE_ENDIAN__
51598	#define vcopy_lane_u64(__p0_42, __p1_42, __p2_42, __p3_42) __extension__ ({ \	43897	#define vcopy_lane_u64(__p0_42, __p1_42, __p2_42, __p3_42) __extension__ ({ \
51599	uint64x1_t __s0_42 = __p0_42; \	43898	uint64x1_t __s0_42 = __p0_42; \
51600	uint64x1_t __s2_42 = __p2_42; \	43899	uint64x1_t __s2_42 = __p2_42; \
...	@@ -51602,653 +43901,598 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -51602,653 +43901,598 @@ __ai float64x2_t vcombine_f64(float64x1_t __p0, float64x1_t __p1) {
51602	__ret_42 = vset_lane_u64(vget_lane_u64(__s2_42, __p3_42), __s0_42, __p1_42); \	43901	__ret_42 = vset_lane_u64(vget_lane_u64(__s2_42, __p3_42), __s0_42, __p1_42); \
51603	__ret_42; \	43902	__ret_42; \
51604	})	43903	})
51605	#else	43904	#ifdef __LITTLE_ENDIAN__
51606	#define vcopy_lane_u64(__p0_43, __p1_43, __p2_43, __p3_43) __extension__ ({ \	43905	#define vcopy_lane_u16(__p0_43, __p1_43, __p2_43, __p3_43) __extension__ ({ \
51607	uint64x1_t __s0_43 = __p0_43; \	43906	uint16x4_t __s0_43 = __p0_43; \
51608	uint64x1_t __s2_43 = __p2_43; \	43907	uint16x4_t __s2_43 = __p2_43; \
51609	uint64x1_t __ret_43; \	43908	uint16x4_t __ret_43; \
51610	__ret_43 = __noswap_vset_lane_u64(__noswap_vget_lane_u64(__s2_43, __p3_43), __s0_43, __p1_43); \	43909	__ret_43 = vset_lane_u16(vget_lane_u16(__s2_43, __p3_43), __s0_43, __p1_43); \
51611	__ret_43; \	43910	__ret_43; \
51612	})	43911	})
51613	#endif	43912	#else
51614
51615	#ifdef __LITTLE_ENDIAN__
51616	#define vcopy_lane_u16(__p0_44, __p1_44, __p2_44, __p3_44) __extension__ ({ \	43913	#define vcopy_lane_u16(__p0_44, __p1_44, __p2_44, __p3_44) __extension__ ({ \
51617	uint16x4_t __s0_44 = __p0_44; \	43914	uint16x4_t __s0_44 = __p0_44; \
51618	uint16x4_t __s2_44 = __p2_44; \	43915	uint16x4_t __s2_44 = __p2_44; \
		43916	uint16x4_t __rev0_44; __rev0_44 = __builtin_shufflevector(__s0_44, __s0_44, 3, 2, 1, 0); \
		43917	uint16x4_t __rev2_44; __rev2_44 = __builtin_shufflevector(__s2_44, __s2_44, 3, 2, 1, 0); \
51619	uint16x4_t __ret_44; \	43918	uint16x4_t __ret_44; \
51620	__ret_44 = vset_lane_u16(vget_lane_u16(__s2_44, __p3_44), __s0_44, __p1_44); \	43919	__ret_44 = __noswap_vset_lane_u16(__noswap_vget_lane_u16(__rev2_44, __p3_44), __rev0_44, __p1_44); \
		43920	__ret_44 = __builtin_shufflevector(__ret_44, __ret_44, 3, 2, 1, 0); \
51621	__ret_44; \	43921	__ret_44; \
51622	})	43922	})
51623	#else
51624	#define vcopy_lane_u16(__p0_45, __p1_45, __p2_45, __p3_45) __extension__ ({ \
51625	uint16x4_t __s0_45 = __p0_45; \
51626	uint16x4_t __s2_45 = __p2_45; \
51627	uint16x4_t __rev0_45; __rev0_45 = __builtin_shufflevector(__s0_45, __s0_45, 3, 2, 1, 0); \
51628	uint16x4_t __rev2_45; __rev2_45 = __builtin_shufflevector(__s2_45, __s2_45, 3, 2, 1, 0); \
51629	uint16x4_t __ret_45; \
51630	__ret_45 = __noswap_vset_lane_u16(__noswap_vget_lane_u16(__rev2_45, __p3_45), __rev0_45, __p1_45); \
51631	__ret_45 = __builtin_shufflevector(__ret_45, __ret_45, 3, 2, 1, 0); \
51632	__ret_45; \
51633	})
51634	#endif	43923	#endif
51635		43924
51636	#ifdef __LITTLE_ENDIAN__	43925	#ifdef __LITTLE_ENDIAN__
		43926	#define vcopy_lane_s8(__p0_45, __p1_45, __p2_45, __p3_45) __extension__ ({ \
		43927	int8x8_t __s0_45 = __p0_45; \
		43928	int8x8_t __s2_45 = __p2_45; \
		43929	int8x8_t __ret_45; \
		43930	__ret_45 = vset_lane_s8(vget_lane_s8(__s2_45, __p3_45), __s0_45, __p1_45); \
		43931	__ret_45; \
		43932	})
		43933	#else
51637	#define vcopy_lane_s8(__p0_46, __p1_46, __p2_46, __p3_46) __extension__ ({ \	43934	#define vcopy_lane_s8(__p0_46, __p1_46, __p2_46, __p3_46) __extension__ ({ \
51638	int8x8_t __s0_46 = __p0_46; \	43935	int8x8_t __s0_46 = __p0_46; \
51639	int8x8_t __s2_46 = __p2_46; \	43936	int8x8_t __s2_46 = __p2_46; \
		43937	int8x8_t __rev0_46; __rev0_46 = __builtin_shufflevector(__s0_46, __s0_46, 7, 6, 5, 4, 3, 2, 1, 0); \
		43938	int8x8_t __rev2_46; __rev2_46 = __builtin_shufflevector(__s2_46, __s2_46, 7, 6, 5, 4, 3, 2, 1, 0); \
51640	int8x8_t __ret_46; \	43939	int8x8_t __ret_46; \
51641	__ret_46 = vset_lane_s8(vget_lane_s8(__s2_46, __p3_46), __s0_46, __p1_46); \	43940	__ret_46 = __noswap_vset_lane_s8(__noswap_vget_lane_s8(__rev2_46, __p3_46), __rev0_46, __p1_46); \
		43941	__ret_46 = __builtin_shufflevector(__ret_46, __ret_46, 7, 6, 5, 4, 3, 2, 1, 0); \
51642	__ret_46; \	43942	__ret_46; \
51643	})	43943	})
51644	#else
51645	#define vcopy_lane_s8(__p0_47, __p1_47, __p2_47, __p3_47) __extension__ ({ \
51646	int8x8_t __s0_47 = __p0_47; \
51647	int8x8_t __s2_47 = __p2_47; \
51648	int8x8_t __rev0_47; __rev0_47 = __builtin_shufflevector(__s0_47, __s0_47, 7, 6, 5, 4, 3, 2, 1, 0); \
51649	int8x8_t __rev2_47; __rev2_47 = __builtin_shufflevector(__s2_47, __s2_47, 7, 6, 5, 4, 3, 2, 1, 0); \
51650	int8x8_t __ret_47; \
51651	__ret_47 = __noswap_vset_lane_s8(__noswap_vget_lane_s8(__rev2_47, __p3_47), __rev0_47, __p1_47); \
51652	__ret_47 = __builtin_shufflevector(__ret_47, __ret_47, 7, 6, 5, 4, 3, 2, 1, 0); \
51653	__ret_47; \
51654	})
51655	#endif	43944	#endif
51656		43945
51657	#ifdef __LITTLE_ENDIAN__	43946	#ifdef __LITTLE_ENDIAN__
		43947	#define vcopy_lane_f32(__p0_47, __p1_47, __p2_47, __p3_47) __extension__ ({ \
		43948	float32x2_t __s0_47 = __p0_47; \
		43949	float32x2_t __s2_47 = __p2_47; \
		43950	float32x2_t __ret_47; \
		43951	__ret_47 = vset_lane_f32(vget_lane_f32(__s2_47, __p3_47), __s0_47, __p1_47); \
		43952	__ret_47; \
		43953	})
		43954	#else
51658	#define vcopy_lane_f32(__p0_48, __p1_48, __p2_48, __p3_48) __extension__ ({ \	43955	#define vcopy_lane_f32(__p0_48, __p1_48, __p2_48, __p3_48) __extension__ ({ \
51659	float32x2_t __s0_48 = __p0_48; \	43956	float32x2_t __s0_48 = __p0_48; \
51660	float32x2_t __s2_48 = __p2_48; \	43957	float32x2_t __s2_48 = __p2_48; \
		43958	float32x2_t __rev0_48; __rev0_48 = __builtin_shufflevector(__s0_48, __s0_48, 1, 0); \
		43959	float32x2_t __rev2_48; __rev2_48 = __builtin_shufflevector(__s2_48, __s2_48, 1, 0); \
51661	float32x2_t __ret_48; \	43960	float32x2_t __ret_48; \
51662	__ret_48 = vset_lane_f32(vget_lane_f32(__s2_48, __p3_48), __s0_48, __p1_48); \	43961	__ret_48 = __noswap_vset_lane_f32(__noswap_vget_lane_f32(__rev2_48, __p3_48), __rev0_48, __p1_48); \
		43962	__ret_48 = __builtin_shufflevector(__ret_48, __ret_48, 1, 0); \
51663	__ret_48; \	43963	__ret_48; \
51664	})	43964	})
51665	#else
51666	#define vcopy_lane_f32(__p0_49, __p1_49, __p2_49, __p3_49) __extension__ ({ \
51667	float32x2_t __s0_49 = __p0_49; \
51668	float32x2_t __s2_49 = __p2_49; \
51669	float32x2_t __rev0_49; __rev0_49 = __builtin_shufflevector(__s0_49, __s0_49, 1, 0); \
51670	float32x2_t __rev2_49; __rev2_49 = __builtin_shufflevector(__s2_49, __s2_49, 1, 0); \
51671	float32x2_t __ret_49; \
51672	__ret_49 = __noswap_vset_lane_f32(__noswap_vget_lane_f32(__rev2_49, __p3_49), __rev0_49, __p1_49); \
51673	__ret_49 = __builtin_shufflevector(__ret_49, __ret_49, 1, 0); \
51674	__ret_49; \
51675	})
51676	#endif	43965	#endif
51677		43966
51678	#ifdef __LITTLE_ENDIAN__	43967	#ifdef __LITTLE_ENDIAN__
		43968	#define vcopy_lane_s32(__p0_49, __p1_49, __p2_49, __p3_49) __extension__ ({ \
		43969	int32x2_t __s0_49 = __p0_49; \
		43970	int32x2_t __s2_49 = __p2_49; \
		43971	int32x2_t __ret_49; \
		43972	__ret_49 = vset_lane_s32(vget_lane_s32(__s2_49, __p3_49), __s0_49, __p1_49); \
		43973	__ret_49; \
		43974	})
		43975	#else
51679	#define vcopy_lane_s32(__p0_50, __p1_50, __p2_50, __p3_50) __extension__ ({ \	43976	#define vcopy_lane_s32(__p0_50, __p1_50, __p2_50, __p3_50) __extension__ ({ \
51680	int32x2_t __s0_50 = __p0_50; \	43977	int32x2_t __s0_50 = __p0_50; \
51681	int32x2_t __s2_50 = __p2_50; \	43978	int32x2_t __s2_50 = __p2_50; \
		43979	int32x2_t __rev0_50; __rev0_50 = __builtin_shufflevector(__s0_50, __s0_50, 1, 0); \
		43980	int32x2_t __rev2_50; __rev2_50 = __builtin_shufflevector(__s2_50, __s2_50, 1, 0); \
51682	int32x2_t __ret_50; \	43981	int32x2_t __ret_50; \
51683	__ret_50 = vset_lane_s32(vget_lane_s32(__s2_50, __p3_50), __s0_50, __p1_50); \	43982	__ret_50 = __noswap_vset_lane_s32(__noswap_vget_lane_s32(__rev2_50, __p3_50), __rev0_50, __p1_50); \
		43983	__ret_50 = __builtin_shufflevector(__ret_50, __ret_50, 1, 0); \
51684	__ret_50; \	43984	__ret_50; \
51685	})	43985	})
51686	#else
51687	#define vcopy_lane_s32(__p0_51, __p1_51, __p2_51, __p3_51) __extension__ ({ \
51688	int32x2_t __s0_51 = __p0_51; \
51689	int32x2_t __s2_51 = __p2_51; \
51690	int32x2_t __rev0_51; __rev0_51 = __builtin_shufflevector(__s0_51, __s0_51, 1, 0); \
51691	int32x2_t __rev2_51; __rev2_51 = __builtin_shufflevector(__s2_51, __s2_51, 1, 0); \
51692	int32x2_t __ret_51; \
51693	__ret_51 = __noswap_vset_lane_s32(__noswap_vget_lane_s32(__rev2_51, __p3_51), __rev0_51, __p1_51); \
51694	__ret_51 = __builtin_shufflevector(__ret_51, __ret_51, 1, 0); \
51695	__ret_51; \
51696	})
51697	#endif	43986	#endif
51698		43987
		43988	#define vcopy_lane_s64(__p0_51, __p1_51, __p2_51, __p3_51) __extension__ ({ \
		43989	int64x1_t __s0_51 = __p0_51; \
		43990	int64x1_t __s2_51 = __p2_51; \
		43991	int64x1_t __ret_51; \
		43992	__ret_51 = vset_lane_s64(vget_lane_s64(__s2_51, __p3_51), __s0_51, __p1_51); \
		43993	__ret_51; \
		43994	})
51699	#ifdef __LITTLE_ENDIAN__	43995	#ifdef __LITTLE_ENDIAN__
51700	#define vcopy_lane_s64(__p0_52, __p1_52, __p2_52, __p3_52) __extension__ ({ \	43996	#define vcopy_lane_s16(__p0_52, __p1_52, __p2_52, __p3_52) __extension__ ({ \
51701	int64x1_t __s0_52 = __p0_52; \	43997	int16x4_t __s0_52 = __p0_52; \
51702	int64x1_t __s2_52 = __p2_52; \	43998	int16x4_t __s2_52 = __p2_52; \
51703	int64x1_t __ret_52; \	43999	int16x4_t __ret_52; \
51704	__ret_52 = vset_lane_s64(vget_lane_s64(__s2_52, __p3_52), __s0_52, __p1_52); \	44000	__ret_52 = vset_lane_s16(vget_lane_s16(__s2_52, __p3_52), __s0_52, __p1_52); \
51705	__ret_52; \	44001	__ret_52; \
51706	})	44002	})
51707	#else	44003	#else
51708	#define vcopy_lane_s64(__p0_53, __p1_53, __p2_53, __p3_53) __extension__ ({ \	44004	#define vcopy_lane_s16(__p0_53, __p1_53, __p2_53, __p3_53) __extension__ ({ \
51709	int64x1_t __s0_53 = __p0_53; \	44005	int16x4_t __s0_53 = __p0_53; \
51710	int64x1_t __s2_53 = __p2_53; \	44006	int16x4_t __s2_53 = __p2_53; \
51711	int64x1_t __ret_53; \	44007	int16x4_t __rev0_53; __rev0_53 = __builtin_shufflevector(__s0_53, __s0_53, 3, 2, 1, 0); \
51712	__ret_53 = __noswap_vset_lane_s64(__noswap_vget_lane_s64(__s2_53, __p3_53), __s0_53, __p1_53); \	44008	int16x4_t __rev2_53; __rev2_53 = __builtin_shufflevector(__s2_53, __s2_53, 3, 2, 1, 0); \
		44009	int16x4_t __ret_53; \
		44010	__ret_53 = __noswap_vset_lane_s16(__noswap_vget_lane_s16(__rev2_53, __p3_53), __rev0_53, __p1_53); \
		44011	__ret_53 = __builtin_shufflevector(__ret_53, __ret_53, 3, 2, 1, 0); \
51713	__ret_53; \	44012	__ret_53; \
51714	})	44013	})
51715	#endif	44014	#endif
51716		44015
51717	#ifdef __LITTLE_ENDIAN__	44016	#ifdef __LITTLE_ENDIAN__
51718	#define vcopy_lane_s16(__p0_54, __p1_54, __p2_54, __p3_54) __extension__ ({ \	44017	#define vcopyq_laneq_p8(__p0_54, __p1_54, __p2_54, __p3_54) __extension__ ({ \
51719	int16x4_t __s0_54 = __p0_54; \	44018	poly8x16_t __s0_54 = __p0_54; \
51720	int16x4_t __s2_54 = __p2_54; \	44019	poly8x16_t __s2_54 = __p2_54; \
51721	int16x4_t __ret_54; \	44020	poly8x16_t __ret_54; \
51722	__ret_54 = vset_lane_s16(vget_lane_s16(__s2_54, __p3_54), __s0_54, __p1_54); \	44021	__ret_54 = vsetq_lane_p8(vgetq_lane_p8(__s2_54, __p3_54), __s0_54, __p1_54); \
51723	__ret_54; \	44022	__ret_54; \
51724	})	44023	})
51725	#else	44024	#else
51726	#define vcopy_lane_s16(__p0_55, __p1_55, __p2_55, __p3_55) __extension__ ({ \	44025	#define vcopyq_laneq_p8(__p0_55, __p1_55, __p2_55, __p3_55) __extension__ ({ \
51727	int16x4_t __s0_55 = __p0_55; \	44026	poly8x16_t __s0_55 = __p0_55; \
51728	int16x4_t __s2_55 = __p2_55; \	44027	poly8x16_t __s2_55 = __p2_55; \
51729	int16x4_t __rev0_55; __rev0_55 = __builtin_shufflevector(__s0_55, __s0_55, 3, 2, 1, 0); \	44028	poly8x16_t __rev0_55; __rev0_55 = __builtin_shufflevector(__s0_55, __s0_55, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51730	int16x4_t __rev2_55; __rev2_55 = __builtin_shufflevector(__s2_55, __s2_55, 3, 2, 1, 0); \	44029	poly8x16_t __rev2_55; __rev2_55 = __builtin_shufflevector(__s2_55, __s2_55, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51731	int16x4_t __ret_55; \	44030	poly8x16_t __ret_55; \
51732	__ret_55 = __noswap_vset_lane_s16(__noswap_vget_lane_s16(__rev2_55, __p3_55), __rev0_55, __p1_55); \	44031	__ret_55 = __noswap_vsetq_lane_p8(__noswap_vgetq_lane_p8(__rev2_55, __p3_55), __rev0_55, __p1_55); \
51733	__ret_55 = __builtin_shufflevector(__ret_55, __ret_55, 3, 2, 1, 0); \	44032	__ret_55 = __builtin_shufflevector(__ret_55, __ret_55, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51734	__ret_55; \	44033	__ret_55; \
51735	})	44034	})
51736	#endif	44035	#endif
51737		44036
51738	#ifdef __LITTLE_ENDIAN__	44037	#ifdef __LITTLE_ENDIAN__
51739	#define vcopyq_laneq_p8(__p0_56, __p1_56, __p2_56, __p3_56) __extension__ ({ \	44038	#define vcopyq_laneq_p16(__p0_56, __p1_56, __p2_56, __p3_56) __extension__ ({ \
51740	poly8x16_t __s0_56 = __p0_56; \	44039	poly16x8_t __s0_56 = __p0_56; \
51741	poly8x16_t __s2_56 = __p2_56; \	44040	poly16x8_t __s2_56 = __p2_56; \
51742	poly8x16_t __ret_56; \	44041	poly16x8_t __ret_56; \
51743	__ret_56 = vsetq_lane_p8(vgetq_lane_p8(__s2_56, __p3_56), __s0_56, __p1_56); \	44042	__ret_56 = vsetq_lane_p16(vgetq_lane_p16(__s2_56, __p3_56), __s0_56, __p1_56); \
51744	__ret_56; \	44043	__ret_56; \
51745	})	44044	})
51746	#else	44045	#else
51747	#define vcopyq_laneq_p8(__p0_57, __p1_57, __p2_57, __p3_57) __extension__ ({ \	44046	#define vcopyq_laneq_p16(__p0_57, __p1_57, __p2_57, __p3_57) __extension__ ({ \
51748	poly8x16_t __s0_57 = __p0_57; \	44047	poly16x8_t __s0_57 = __p0_57; \
51749	poly8x16_t __s2_57 = __p2_57; \	44048	poly16x8_t __s2_57 = __p2_57; \
51750	poly8x16_t __rev0_57; __rev0_57 = __builtin_shufflevector(__s0_57, __s0_57, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44049	poly16x8_t __rev0_57; __rev0_57 = __builtin_shufflevector(__s0_57, __s0_57, 7, 6, 5, 4, 3, 2, 1, 0); \
51751	poly8x16_t __rev2_57; __rev2_57 = __builtin_shufflevector(__s2_57, __s2_57, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44050	poly16x8_t __rev2_57; __rev2_57 = __builtin_shufflevector(__s2_57, __s2_57, 7, 6, 5, 4, 3, 2, 1, 0); \
51752	poly8x16_t __ret_57; \	44051	poly16x8_t __ret_57; \
51753	__ret_57 = __noswap_vsetq_lane_p8(__noswap_vgetq_lane_p8(__rev2_57, __p3_57), __rev0_57, __p1_57); \	44052	__ret_57 = __noswap_vsetq_lane_p16(__noswap_vgetq_lane_p16(__rev2_57, __p3_57), __rev0_57, __p1_57); \
51754	__ret_57 = __builtin_shufflevector(__ret_57, __ret_57, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44053	__ret_57 = __builtin_shufflevector(__ret_57, __ret_57, 7, 6, 5, 4, 3, 2, 1, 0); \
51755	__ret_57; \	44054	__ret_57; \
51756	})	44055	})
51757	#endif	44056	#endif
51758		44057
51759	#ifdef __LITTLE_ENDIAN__	44058	#ifdef __LITTLE_ENDIAN__
51760	#define vcopyq_laneq_p16(__p0_58, __p1_58, __p2_58, __p3_58) __extension__ ({ \	44059	#define vcopyq_laneq_u8(__p0_58, __p1_58, __p2_58, __p3_58) __extension__ ({ \
51761	poly16x8_t __s0_58 = __p0_58; \	44060	uint8x16_t __s0_58 = __p0_58; \
51762	poly16x8_t __s2_58 = __p2_58; \	44061	uint8x16_t __s2_58 = __p2_58; \
51763	poly16x8_t __ret_58; \	44062	uint8x16_t __ret_58; \
51764	__ret_58 = vsetq_lane_p16(vgetq_lane_p16(__s2_58, __p3_58), __s0_58, __p1_58); \	44063	__ret_58 = vsetq_lane_u8(vgetq_lane_u8(__s2_58, __p3_58), __s0_58, __p1_58); \
51765	__ret_58; \	44064	__ret_58; \
51766	})	44065	})
51767	#else	44066	#else
51768	#define vcopyq_laneq_p16(__p0_59, __p1_59, __p2_59, __p3_59) __extension__ ({ \	44067	#define vcopyq_laneq_u8(__p0_59, __p1_59, __p2_59, __p3_59) __extension__ ({ \
51769	poly16x8_t __s0_59 = __p0_59; \	44068	uint8x16_t __s0_59 = __p0_59; \
51770	poly16x8_t __s2_59 = __p2_59; \	44069	uint8x16_t __s2_59 = __p2_59; \
51771	poly16x8_t __rev0_59; __rev0_59 = __builtin_shufflevector(__s0_59, __s0_59, 7, 6, 5, 4, 3, 2, 1, 0); \	44070	uint8x16_t __rev0_59; __rev0_59 = __builtin_shufflevector(__s0_59, __s0_59, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51772	poly16x8_t __rev2_59; __rev2_59 = __builtin_shufflevector(__s2_59, __s2_59, 7, 6, 5, 4, 3, 2, 1, 0); \	44071	uint8x16_t __rev2_59; __rev2_59 = __builtin_shufflevector(__s2_59, __s2_59, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51773	poly16x8_t __ret_59; \	44072	uint8x16_t __ret_59; \
51774	__ret_59 = __noswap_vsetq_lane_p16(__noswap_vgetq_lane_p16(__rev2_59, __p3_59), __rev0_59, __p1_59); \	44073	__ret_59 = __noswap_vsetq_lane_u8(__noswap_vgetq_lane_u8(__rev2_59, __p3_59), __rev0_59, __p1_59); \
51775	__ret_59 = __builtin_shufflevector(__ret_59, __ret_59, 7, 6, 5, 4, 3, 2, 1, 0); \	44074	__ret_59 = __builtin_shufflevector(__ret_59, __ret_59, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51776	__ret_59; \	44075	__ret_59; \
51777	})	44076	})
51778	#endif	44077	#endif
51779		44078
51780	#ifdef __LITTLE_ENDIAN__	44079	#ifdef __LITTLE_ENDIAN__
51781	#define vcopyq_laneq_u8(__p0_60, __p1_60, __p2_60, __p3_60) __extension__ ({ \	44080	#define vcopyq_laneq_u32(__p0_60, __p1_60, __p2_60, __p3_60) __extension__ ({ \
51782	uint8x16_t __s0_60 = __p0_60; \	44081	uint32x4_t __s0_60 = __p0_60; \
51783	uint8x16_t __s2_60 = __p2_60; \	44082	uint32x4_t __s2_60 = __p2_60; \
51784	uint8x16_t __ret_60; \	44083	uint32x4_t __ret_60; \
51785	__ret_60 = vsetq_lane_u8(vgetq_lane_u8(__s2_60, __p3_60), __s0_60, __p1_60); \	44084	__ret_60 = vsetq_lane_u32(vgetq_lane_u32(__s2_60, __p3_60), __s0_60, __p1_60); \
51786	__ret_60; \	44085	__ret_60; \
51787	})	44086	})
51788	#else	44087	#else
51789	#define vcopyq_laneq_u8(__p0_61, __p1_61, __p2_61, __p3_61) __extension__ ({ \	44088	#define vcopyq_laneq_u32(__p0_61, __p1_61, __p2_61, __p3_61) __extension__ ({ \
51790	uint8x16_t __s0_61 = __p0_61; \	44089	uint32x4_t __s0_61 = __p0_61; \
51791	uint8x16_t __s2_61 = __p2_61; \	44090	uint32x4_t __s2_61 = __p2_61; \
51792	uint8x16_t __rev0_61; __rev0_61 = __builtin_shufflevector(__s0_61, __s0_61, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44091	uint32x4_t __rev0_61; __rev0_61 = __builtin_shufflevector(__s0_61, __s0_61, 3, 2, 1, 0); \
51793	uint8x16_t __rev2_61; __rev2_61 = __builtin_shufflevector(__s2_61, __s2_61, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44092	uint32x4_t __rev2_61; __rev2_61 = __builtin_shufflevector(__s2_61, __s2_61, 3, 2, 1, 0); \
51794	uint8x16_t __ret_61; \	44093	uint32x4_t __ret_61; \
51795	__ret_61 = __noswap_vsetq_lane_u8(__noswap_vgetq_lane_u8(__rev2_61, __p3_61), __rev0_61, __p1_61); \	44094	__ret_61 = __noswap_vsetq_lane_u32(__noswap_vgetq_lane_u32(__rev2_61, __p3_61), __rev0_61, __p1_61); \
51796	__ret_61 = __builtin_shufflevector(__ret_61, __ret_61, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44095	__ret_61 = __builtin_shufflevector(__ret_61, __ret_61, 3, 2, 1, 0); \
51797	__ret_61; \	44096	__ret_61; \
51798	})	44097	})
51799	#endif	44098	#endif
51800		44099
51801	#ifdef __LITTLE_ENDIAN__	44100	#ifdef __LITTLE_ENDIAN__
51802	#define vcopyq_laneq_u32(__p0_62, __p1_62, __p2_62, __p3_62) __extension__ ({ \	44101	#define vcopyq_laneq_u64(__p0_62, __p1_62, __p2_62, __p3_62) __extension__ ({ \
51803	uint32x4_t __s0_62 = __p0_62; \	44102	uint64x2_t __s0_62 = __p0_62; \
51804	uint32x4_t __s2_62 = __p2_62; \	44103	uint64x2_t __s2_62 = __p2_62; \
51805	uint32x4_t __ret_62; \	44104	uint64x2_t __ret_62; \
51806	__ret_62 = vsetq_lane_u32(vgetq_lane_u32(__s2_62, __p3_62), __s0_62, __p1_62); \	44105	__ret_62 = vsetq_lane_u64(vgetq_lane_u64(__s2_62, __p3_62), __s0_62, __p1_62); \
51807	__ret_62; \	44106	__ret_62; \
51808	})	44107	})
51809	#else	44108	#else
51810	#define vcopyq_laneq_u32(__p0_63, __p1_63, __p2_63, __p3_63) __extension__ ({ \	44109	#define vcopyq_laneq_u64(__p0_63, __p1_63, __p2_63, __p3_63) __extension__ ({ \
51811	uint32x4_t __s0_63 = __p0_63; \	44110	uint64x2_t __s0_63 = __p0_63; \
51812	uint32x4_t __s2_63 = __p2_63; \	44111	uint64x2_t __s2_63 = __p2_63; \
51813	uint32x4_t __rev0_63; __rev0_63 = __builtin_shufflevector(__s0_63, __s0_63, 3, 2, 1, 0); \	44112	uint64x2_t __rev0_63; __rev0_63 = __builtin_shufflevector(__s0_63, __s0_63, 1, 0); \
51814	uint32x4_t __rev2_63; __rev2_63 = __builtin_shufflevector(__s2_63, __s2_63, 3, 2, 1, 0); \	44113	uint64x2_t __rev2_63; __rev2_63 = __builtin_shufflevector(__s2_63, __s2_63, 1, 0); \
51815	uint32x4_t __ret_63; \	44114	uint64x2_t __ret_63; \
51816	__ret_63 = __noswap_vsetq_lane_u32(__noswap_vgetq_lane_u32(__rev2_63, __p3_63), __rev0_63, __p1_63); \	44115	__ret_63 = __noswap_vsetq_lane_u64(__noswap_vgetq_lane_u64(__rev2_63, __p3_63), __rev0_63, __p1_63); \
51817	__ret_63 = __builtin_shufflevector(__ret_63, __ret_63, 3, 2, 1, 0); \	44116	__ret_63 = __builtin_shufflevector(__ret_63, __ret_63, 1, 0); \
51818	__ret_63; \	44117	__ret_63; \
51819	})	44118	})
51820	#endif	44119	#endif
51821		44120
51822	#ifdef __LITTLE_ENDIAN__	44121	#ifdef __LITTLE_ENDIAN__
51823	#define vcopyq_laneq_u64(__p0_64, __p1_64, __p2_64, __p3_64) __extension__ ({ \	44122	#define vcopyq_laneq_u16(__p0_64, __p1_64, __p2_64, __p3_64) __extension__ ({ \
51824	uint64x2_t __s0_64 = __p0_64; \	44123	uint16x8_t __s0_64 = __p0_64; \
51825	uint64x2_t __s2_64 = __p2_64; \	44124	uint16x8_t __s2_64 = __p2_64; \
51826	uint64x2_t __ret_64; \	44125	uint16x8_t __ret_64; \
51827	__ret_64 = vsetq_lane_u64(vgetq_lane_u64(__s2_64, __p3_64), __s0_64, __p1_64); \	44126	__ret_64 = vsetq_lane_u16(vgetq_lane_u16(__s2_64, __p3_64), __s0_64, __p1_64); \
51828	__ret_64; \	44127	__ret_64; \
51829	})	44128	})
51830	#else	44129	#else
51831	#define vcopyq_laneq_u64(__p0_65, __p1_65, __p2_65, __p3_65) __extension__ ({ \	44130	#define vcopyq_laneq_u16(__p0_65, __p1_65, __p2_65, __p3_65) __extension__ ({ \
51832	uint64x2_t __s0_65 = __p0_65; \	44131	uint16x8_t __s0_65 = __p0_65; \
51833	uint64x2_t __s2_65 = __p2_65; \	44132	uint16x8_t __s2_65 = __p2_65; \
51834	uint64x2_t __rev0_65; __rev0_65 = __builtin_shufflevector(__s0_65, __s0_65, 1, 0); \	44133	uint16x8_t __rev0_65; __rev0_65 = __builtin_shufflevector(__s0_65, __s0_65, 7, 6, 5, 4, 3, 2, 1, 0); \
51835	uint64x2_t __rev2_65; __rev2_65 = __builtin_shufflevector(__s2_65, __s2_65, 1, 0); \	44134	uint16x8_t __rev2_65; __rev2_65 = __builtin_shufflevector(__s2_65, __s2_65, 7, 6, 5, 4, 3, 2, 1, 0); \
51836	uint64x2_t __ret_65; \	44135	uint16x8_t __ret_65; \
51837	__ret_65 = __noswap_vsetq_lane_u64(__noswap_vgetq_lane_u64(__rev2_65, __p3_65), __rev0_65, __p1_65); \	44136	__ret_65 = __noswap_vsetq_lane_u16(__noswap_vgetq_lane_u16(__rev2_65, __p3_65), __rev0_65, __p1_65); \
51838	__ret_65 = __builtin_shufflevector(__ret_65, __ret_65, 1, 0); \	44137	__ret_65 = __builtin_shufflevector(__ret_65, __ret_65, 7, 6, 5, 4, 3, 2, 1, 0); \
51839	__ret_65; \	44138	__ret_65; \
51840	})	44139	})
51841	#endif	44140	#endif
51842		44141
51843	#ifdef __LITTLE_ENDIAN__	44142	#ifdef __LITTLE_ENDIAN__
51844	#define vcopyq_laneq_u16(__p0_66, __p1_66, __p2_66, __p3_66) __extension__ ({ \	44143	#define vcopyq_laneq_s8(__p0_66, __p1_66, __p2_66, __p3_66) __extension__ ({ \
51845	uint16x8_t __s0_66 = __p0_66; \	44144	int8x16_t __s0_66 = __p0_66; \
51846	uint16x8_t __s2_66 = __p2_66; \	44145	int8x16_t __s2_66 = __p2_66; \
51847	uint16x8_t __ret_66; \	44146	int8x16_t __ret_66; \
51848	__ret_66 = vsetq_lane_u16(vgetq_lane_u16(__s2_66, __p3_66), __s0_66, __p1_66); \	44147	__ret_66 = vsetq_lane_s8(vgetq_lane_s8(__s2_66, __p3_66), __s0_66, __p1_66); \
51849	__ret_66; \	44148	__ret_66; \
51850	})	44149	})
51851	#else	44150	#else
51852	#define vcopyq_laneq_u16(__p0_67, __p1_67, __p2_67, __p3_67) __extension__ ({ \	44151	#define vcopyq_laneq_s8(__p0_67, __p1_67, __p2_67, __p3_67) __extension__ ({ \
51853	uint16x8_t __s0_67 = __p0_67; \	44152	int8x16_t __s0_67 = __p0_67; \
51854	uint16x8_t __s2_67 = __p2_67; \	44153	int8x16_t __s2_67 = __p2_67; \
51855	uint16x8_t __rev0_67; __rev0_67 = __builtin_shufflevector(__s0_67, __s0_67, 7, 6, 5, 4, 3, 2, 1, 0); \	44154	int8x16_t __rev0_67; __rev0_67 = __builtin_shufflevector(__s0_67, __s0_67, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51856	uint16x8_t __rev2_67; __rev2_67 = __builtin_shufflevector(__s2_67, __s2_67, 7, 6, 5, 4, 3, 2, 1, 0); \	44155	int8x16_t __rev2_67; __rev2_67 = __builtin_shufflevector(__s2_67, __s2_67, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51857	uint16x8_t __ret_67; \	44156	int8x16_t __ret_67; \
51858	__ret_67 = __noswap_vsetq_lane_u16(__noswap_vgetq_lane_u16(__rev2_67, __p3_67), __rev0_67, __p1_67); \	44157	__ret_67 = __noswap_vsetq_lane_s8(__noswap_vgetq_lane_s8(__rev2_67, __p3_67), __rev0_67, __p1_67); \
51859	__ret_67 = __builtin_shufflevector(__ret_67, __ret_67, 7, 6, 5, 4, 3, 2, 1, 0); \	44158	__ret_67 = __builtin_shufflevector(__ret_67, __ret_67, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51860	__ret_67; \	44159	__ret_67; \
51861	})	44160	})
51862	#endif	44161	#endif
51863		44162
51864	#ifdef __LITTLE_ENDIAN__	44163	#ifdef __LITTLE_ENDIAN__
51865	#define vcopyq_laneq_s8(__p0_68, __p1_68, __p2_68, __p3_68) __extension__ ({ \	44164	#define vcopyq_laneq_f32(__p0_68, __p1_68, __p2_68, __p3_68) __extension__ ({ \
51866	int8x16_t __s0_68 = __p0_68; \	44165	float32x4_t __s0_68 = __p0_68; \
51867	int8x16_t __s2_68 = __p2_68; \	44166	float32x4_t __s2_68 = __p2_68; \
51868	int8x16_t __ret_68; \	44167	float32x4_t __ret_68; \
51869	__ret_68 = vsetq_lane_s8(vgetq_lane_s8(__s2_68, __p3_68), __s0_68, __p1_68); \	44168	__ret_68 = vsetq_lane_f32(vgetq_lane_f32(__s2_68, __p3_68), __s0_68, __p1_68); \
51870	__ret_68; \	44169	__ret_68; \
51871	})	44170	})
51872	#else	44171	#else
51873	#define vcopyq_laneq_s8(__p0_69, __p1_69, __p2_69, __p3_69) __extension__ ({ \	44172	#define vcopyq_laneq_f32(__p0_69, __p1_69, __p2_69, __p3_69) __extension__ ({ \
51874	int8x16_t __s0_69 = __p0_69; \	44173	float32x4_t __s0_69 = __p0_69; \
51875	int8x16_t __s2_69 = __p2_69; \	44174	float32x4_t __s2_69 = __p2_69; \
51876	int8x16_t __rev0_69; __rev0_69 = __builtin_shufflevector(__s0_69, __s0_69, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44175	float32x4_t __rev0_69; __rev0_69 = __builtin_shufflevector(__s0_69, __s0_69, 3, 2, 1, 0); \
51877	int8x16_t __rev2_69; __rev2_69 = __builtin_shufflevector(__s2_69, __s2_69, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44176	float32x4_t __rev2_69; __rev2_69 = __builtin_shufflevector(__s2_69, __s2_69, 3, 2, 1, 0); \
51878	int8x16_t __ret_69; \	44177	float32x4_t __ret_69; \
51879	__ret_69 = __noswap_vsetq_lane_s8(__noswap_vgetq_lane_s8(__rev2_69, __p3_69), __rev0_69, __p1_69); \	44178	__ret_69 = __noswap_vsetq_lane_f32(__noswap_vgetq_lane_f32(__rev2_69, __p3_69), __rev0_69, __p1_69); \
51880	__ret_69 = __builtin_shufflevector(__ret_69, __ret_69, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44179	__ret_69 = __builtin_shufflevector(__ret_69, __ret_69, 3, 2, 1, 0); \
51881	__ret_69; \	44180	__ret_69; \
51882	})	44181	})
51883	#endif	44182	#endif
51884		44183
51885	#ifdef __LITTLE_ENDIAN__	44184	#ifdef __LITTLE_ENDIAN__
51886	#define vcopyq_laneq_f32(__p0_70, __p1_70, __p2_70, __p3_70) __extension__ ({ \	44185	#define vcopyq_laneq_s32(__p0_70, __p1_70, __p2_70, __p3_70) __extension__ ({ \
51887	float32x4_t __s0_70 = __p0_70; \	44186	int32x4_t __s0_70 = __p0_70; \
51888	float32x4_t __s2_70 = __p2_70; \	44187	int32x4_t __s2_70 = __p2_70; \
51889	float32x4_t __ret_70; \	44188	int32x4_t __ret_70; \
51890	__ret_70 = vsetq_lane_f32(vgetq_lane_f32(__s2_70, __p3_70), __s0_70, __p1_70); \	44189	__ret_70 = vsetq_lane_s32(vgetq_lane_s32(__s2_70, __p3_70), __s0_70, __p1_70); \
51891	__ret_70; \	44190	__ret_70; \
51892	})	44191	})
51893	#else	44192	#else
51894	#define vcopyq_laneq_f32(__p0_71, __p1_71, __p2_71, __p3_71) __extension__ ({ \	44193	#define vcopyq_laneq_s32(__p0_71, __p1_71, __p2_71, __p3_71) __extension__ ({ \
51895	float32x4_t __s0_71 = __p0_71; \	44194	int32x4_t __s0_71 = __p0_71; \
51896	float32x4_t __s2_71 = __p2_71; \	44195	int32x4_t __s2_71 = __p2_71; \
51897	float32x4_t __rev0_71; __rev0_71 = __builtin_shufflevector(__s0_71, __s0_71, 3, 2, 1, 0); \	44196	int32x4_t __rev0_71; __rev0_71 = __builtin_shufflevector(__s0_71, __s0_71, 3, 2, 1, 0); \
51898	float32x4_t __rev2_71; __rev2_71 = __builtin_shufflevector(__s2_71, __s2_71, 3, 2, 1, 0); \	44197	int32x4_t __rev2_71; __rev2_71 = __builtin_shufflevector(__s2_71, __s2_71, 3, 2, 1, 0); \
51899	float32x4_t __ret_71; \	44198	int32x4_t __ret_71; \
51900	__ret_71 = __noswap_vsetq_lane_f32(__noswap_vgetq_lane_f32(__rev2_71, __p3_71), __rev0_71, __p1_71); \	44199	__ret_71 = __noswap_vsetq_lane_s32(__noswap_vgetq_lane_s32(__rev2_71, __p3_71), __rev0_71, __p1_71); \
51901	__ret_71 = __builtin_shufflevector(__ret_71, __ret_71, 3, 2, 1, 0); \	44200	__ret_71 = __builtin_shufflevector(__ret_71, __ret_71, 3, 2, 1, 0); \
51902	__ret_71; \	44201	__ret_71; \
51903	})	44202	})
51904	#endif	44203	#endif
51905		44204
51906	#ifdef __LITTLE_ENDIAN__	44205	#ifdef __LITTLE_ENDIAN__
51907	#define vcopyq_laneq_s32(__p0_72, __p1_72, __p2_72, __p3_72) __extension__ ({ \	44206	#define vcopyq_laneq_s64(__p0_72, __p1_72, __p2_72, __p3_72) __extension__ ({ \
51908	int32x4_t __s0_72 = __p0_72; \	44207	int64x2_t __s0_72 = __p0_72; \
51909	int32x4_t __s2_72 = __p2_72; \	44208	int64x2_t __s2_72 = __p2_72; \
51910	int32x4_t __ret_72; \	44209	int64x2_t __ret_72; \
51911	__ret_72 = vsetq_lane_s32(vgetq_lane_s32(__s2_72, __p3_72), __s0_72, __p1_72); \	44210	__ret_72 = vsetq_lane_s64(vgetq_lane_s64(__s2_72, __p3_72), __s0_72, __p1_72); \
51912	__ret_72; \	44211	__ret_72; \
51913	})	44212	})
51914	#else	44213	#else
51915	#define vcopyq_laneq_s32(__p0_73, __p1_73, __p2_73, __p3_73) __extension__ ({ \	44214	#define vcopyq_laneq_s64(__p0_73, __p1_73, __p2_73, __p3_73) __extension__ ({ \
51916	int32x4_t __s0_73 = __p0_73; \	44215	int64x2_t __s0_73 = __p0_73; \
51917	int32x4_t __s2_73 = __p2_73; \	44216	int64x2_t __s2_73 = __p2_73; \
51918	int32x4_t __rev0_73; __rev0_73 = __builtin_shufflevector(__s0_73, __s0_73, 3, 2, 1, 0); \	44217	int64x2_t __rev0_73; __rev0_73 = __builtin_shufflevector(__s0_73, __s0_73, 1, 0); \
51919	int32x4_t __rev2_73; __rev2_73 = __builtin_shufflevector(__s2_73, __s2_73, 3, 2, 1, 0); \	44218	int64x2_t __rev2_73; __rev2_73 = __builtin_shufflevector(__s2_73, __s2_73, 1, 0); \
51920	int32x4_t __ret_73; \	44219	int64x2_t __ret_73; \
51921	__ret_73 = __noswap_vsetq_lane_s32(__noswap_vgetq_lane_s32(__rev2_73, __p3_73), __rev0_73, __p1_73); \	44220	__ret_73 = __noswap_vsetq_lane_s64(__noswap_vgetq_lane_s64(__rev2_73, __p3_73), __rev0_73, __p1_73); \
51922	__ret_73 = __builtin_shufflevector(__ret_73, __ret_73, 3, 2, 1, 0); \	44221	__ret_73 = __builtin_shufflevector(__ret_73, __ret_73, 1, 0); \
51923	__ret_73; \	44222	__ret_73; \
51924	})	44223	})
51925	#endif	44224	#endif
51926		44225
51927	#ifdef __LITTLE_ENDIAN__	44226	#ifdef __LITTLE_ENDIAN__
51928	#define vcopyq_laneq_s64(__p0_74, __p1_74, __p2_74, __p3_74) __extension__ ({ \	44227	#define vcopyq_laneq_s16(__p0_74, __p1_74, __p2_74, __p3_74) __extension__ ({ \
51929	int64x2_t __s0_74 = __p0_74; \	44228	int16x8_t __s0_74 = __p0_74; \
51930	int64x2_t __s2_74 = __p2_74; \	44229	int16x8_t __s2_74 = __p2_74; \
51931	int64x2_t __ret_74; \	44230	int16x8_t __ret_74; \
51932	__ret_74 = vsetq_lane_s64(vgetq_lane_s64(__s2_74, __p3_74), __s0_74, __p1_74); \	44231	__ret_74 = vsetq_lane_s16(vgetq_lane_s16(__s2_74, __p3_74), __s0_74, __p1_74); \
51933	__ret_74; \	44232	__ret_74; \
51934	})	44233	})
51935	#else	44234	#else
51936	#define vcopyq_laneq_s64(__p0_75, __p1_75, __p2_75, __p3_75) __extension__ ({ \	44235	#define vcopyq_laneq_s16(__p0_75, __p1_75, __p2_75, __p3_75) __extension__ ({ \
51937	int64x2_t __s0_75 = __p0_75; \	44236	int16x8_t __s0_75 = __p0_75; \
51938	int64x2_t __s2_75 = __p2_75; \	44237	int16x8_t __s2_75 = __p2_75; \
51939	int64x2_t __rev0_75; __rev0_75 = __builtin_shufflevector(__s0_75, __s0_75, 1, 0); \	44238	int16x8_t __rev0_75; __rev0_75 = __builtin_shufflevector(__s0_75, __s0_75, 7, 6, 5, 4, 3, 2, 1, 0); \
51940	int64x2_t __rev2_75; __rev2_75 = __builtin_shufflevector(__s2_75, __s2_75, 1, 0); \	44239	int16x8_t __rev2_75; __rev2_75 = __builtin_shufflevector(__s2_75, __s2_75, 7, 6, 5, 4, 3, 2, 1, 0); \
51941	int64x2_t __ret_75; \	44240	int16x8_t __ret_75; \
51942	__ret_75 = __noswap_vsetq_lane_s64(__noswap_vgetq_lane_s64(__rev2_75, __p3_75), __rev0_75, __p1_75); \	44241	__ret_75 = __noswap_vsetq_lane_s16(__noswap_vgetq_lane_s16(__rev2_75, __p3_75), __rev0_75, __p1_75); \
51943	__ret_75 = __builtin_shufflevector(__ret_75, __ret_75, 1, 0); \	44242	__ret_75 = __builtin_shufflevector(__ret_75, __ret_75, 7, 6, 5, 4, 3, 2, 1, 0); \
51944	__ret_75; \	44243	__ret_75; \
51945	})	44244	})
51946	#endif	44245	#endif
51947		44246
51948	#ifdef __LITTLE_ENDIAN__	44247	#ifdef __LITTLE_ENDIAN__
51949	#define vcopyq_laneq_s16(__p0_76, __p1_76, __p2_76, __p3_76) __extension__ ({ \	44248	#define vcopy_laneq_p8(__p0_76, __p1_76, __p2_76, __p3_76) __extension__ ({ \
51950	int16x8_t __s0_76 = __p0_76; \	44249	poly8x8_t __s0_76 = __p0_76; \
51951	int16x8_t __s2_76 = __p2_76; \	44250	poly8x16_t __s2_76 = __p2_76; \
51952	int16x8_t __ret_76; \	44251	poly8x8_t __ret_76; \
51953	__ret_76 = vsetq_lane_s16(vgetq_lane_s16(__s2_76, __p3_76), __s0_76, __p1_76); \	44252	__ret_76 = vset_lane_p8(vgetq_lane_p8(__s2_76, __p3_76), __s0_76, __p1_76); \
51954	__ret_76; \	44253	__ret_76; \
51955	})	44254	})
51956	#else	44255	#else
51957	#define vcopyq_laneq_s16(__p0_77, __p1_77, __p2_77, __p3_77) __extension__ ({ \	44256	#define vcopy_laneq_p8(__p0_77, __p1_77, __p2_77, __p3_77) __extension__ ({ \
51958	int16x8_t __s0_77 = __p0_77; \	44257	poly8x8_t __s0_77 = __p0_77; \
51959	int16x8_t __s2_77 = __p2_77; \	44258	poly8x16_t __s2_77 = __p2_77; \
51960	int16x8_t __rev0_77; __rev0_77 = __builtin_shufflevector(__s0_77, __s0_77, 7, 6, 5, 4, 3, 2, 1, 0); \	44259	poly8x8_t __rev0_77; __rev0_77 = __builtin_shufflevector(__s0_77, __s0_77, 7, 6, 5, 4, 3, 2, 1, 0); \
51961	int16x8_t __rev2_77; __rev2_77 = __builtin_shufflevector(__s2_77, __s2_77, 7, 6, 5, 4, 3, 2, 1, 0); \	44260	poly8x16_t __rev2_77; __rev2_77 = __builtin_shufflevector(__s2_77, __s2_77, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
51962	int16x8_t __ret_77; \	44261	poly8x8_t __ret_77; \
51963	__ret_77 = __noswap_vsetq_lane_s16(__noswap_vgetq_lane_s16(__rev2_77, __p3_77), __rev0_77, __p1_77); \	44262	__ret_77 = __noswap_vset_lane_p8(__noswap_vgetq_lane_p8(__rev2_77, __p3_77), __rev0_77, __p1_77); \
51964	__ret_77 = __builtin_shufflevector(__ret_77, __ret_77, 7, 6, 5, 4, 3, 2, 1, 0); \	44263	__ret_77 = __builtin_shufflevector(__ret_77, __ret_77, 7, 6, 5, 4, 3, 2, 1, 0); \
51965	__ret_77; \	44264	__ret_77; \
51966	})	44265	})
51967	#endif	44266	#endif
51968		44267
51969	#ifdef __LITTLE_ENDIAN__	44268	#ifdef __LITTLE_ENDIAN__
51970	#define vcopy_laneq_p8(__p0_78, __p1_78, __p2_78, __p3_78) __extension__ ({ \	44269	#define vcopy_laneq_p16(__p0_78, __p1_78, __p2_78, __p3_78) __extension__ ({ \
51971	poly8x8_t __s0_78 = __p0_78; \	44270	poly16x4_t __s0_78 = __p0_78; \
51972	poly8x16_t __s2_78 = __p2_78; \	44271	poly16x8_t __s2_78 = __p2_78; \
51973	poly8x8_t __ret_78; \	44272	poly16x4_t __ret_78; \
51974	__ret_78 = vset_lane_p8(vgetq_lane_p8(__s2_78, __p3_78), __s0_78, __p1_78); \	44273	__ret_78 = vset_lane_p16(vgetq_lane_p16(__s2_78, __p3_78), __s0_78, __p1_78); \
51975	__ret_78; \	44274	__ret_78; \
51976	})	44275	})
51977	#else	44276	#else
51978	#define vcopy_laneq_p8(__p0_79, __p1_79, __p2_79, __p3_79) __extension__ ({ \	44277	#define vcopy_laneq_p16(__p0_79, __p1_79, __p2_79, __p3_79) __extension__ ({ \
51979	poly8x8_t __s0_79 = __p0_79; \	44278	poly16x4_t __s0_79 = __p0_79; \
51980	poly8x16_t __s2_79 = __p2_79; \	44279	poly16x8_t __s2_79 = __p2_79; \
51981	poly8x8_t __rev0_79; __rev0_79 = __builtin_shufflevector(__s0_79, __s0_79, 7, 6, 5, 4, 3, 2, 1, 0); \	44280	poly16x4_t __rev0_79; __rev0_79 = __builtin_shufflevector(__s0_79, __s0_79, 3, 2, 1, 0); \
51982	poly8x16_t __rev2_79; __rev2_79 = __builtin_shufflevector(__s2_79, __s2_79, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44281	poly16x8_t __rev2_79; __rev2_79 = __builtin_shufflevector(__s2_79, __s2_79, 7, 6, 5, 4, 3, 2, 1, 0); \
51983	poly8x8_t __ret_79; \	44282	poly16x4_t __ret_79; \
51984	__ret_79 = __noswap_vset_lane_p8(__noswap_vgetq_lane_p8(__rev2_79, __p3_79), __rev0_79, __p1_79); \	44283	__ret_79 = __noswap_vset_lane_p16(__noswap_vgetq_lane_p16(__rev2_79, __p3_79), __rev0_79, __p1_79); \
51985	__ret_79 = __builtin_shufflevector(__ret_79, __ret_79, 7, 6, 5, 4, 3, 2, 1, 0); \	44284	__ret_79 = __builtin_shufflevector(__ret_79, __ret_79, 3, 2, 1, 0); \
51986	__ret_79; \	44285	__ret_79; \
51987	})	44286	})
51988	#endif	44287	#endif
51989		44288
51990	#ifdef __LITTLE_ENDIAN__	44289	#ifdef __LITTLE_ENDIAN__
51991	#define vcopy_laneq_p16(__p0_80, __p1_80, __p2_80, __p3_80) __extension__ ({ \	44290	#define vcopy_laneq_u8(__p0_80, __p1_80, __p2_80, __p3_80) __extension__ ({ \
51992	poly16x4_t __s0_80 = __p0_80; \	44291	uint8x8_t __s0_80 = __p0_80; \
51993	poly16x8_t __s2_80 = __p2_80; \	44292	uint8x16_t __s2_80 = __p2_80; \
51994	poly16x4_t __ret_80; \	44293	uint8x8_t __ret_80; \
51995	__ret_80 = vset_lane_p16(vgetq_lane_p16(__s2_80, __p3_80), __s0_80, __p1_80); \	44294	__ret_80 = vset_lane_u8(vgetq_lane_u8(__s2_80, __p3_80), __s0_80, __p1_80); \
51996	__ret_80; \	44295	__ret_80; \
51997	})	44296	})
51998	#else	44297	#else
51999	#define vcopy_laneq_p16(__p0_81, __p1_81, __p2_81, __p3_81) __extension__ ({ \	44298	#define vcopy_laneq_u8(__p0_81, __p1_81, __p2_81, __p3_81) __extension__ ({ \
52000	poly16x4_t __s0_81 = __p0_81; \	44299	uint8x8_t __s0_81 = __p0_81; \
52001	poly16x8_t __s2_81 = __p2_81; \	44300	uint8x16_t __s2_81 = __p2_81; \
52002	poly16x4_t __rev0_81; __rev0_81 = __builtin_shufflevector(__s0_81, __s0_81, 3, 2, 1, 0); \	44301	uint8x8_t __rev0_81; __rev0_81 = __builtin_shufflevector(__s0_81, __s0_81, 7, 6, 5, 4, 3, 2, 1, 0); \
52003	poly16x8_t __rev2_81; __rev2_81 = __builtin_shufflevector(__s2_81, __s2_81, 7, 6, 5, 4, 3, 2, 1, 0); \	44302	uint8x16_t __rev2_81; __rev2_81 = __builtin_shufflevector(__s2_81, __s2_81, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
52004	poly16x4_t __ret_81; \	44303	uint8x8_t __ret_81; \
52005	__ret_81 = __noswap_vset_lane_p16(__noswap_vgetq_lane_p16(__rev2_81, __p3_81), __rev0_81, __p1_81); \	44304	__ret_81 = __noswap_vset_lane_u8(__noswap_vgetq_lane_u8(__rev2_81, __p3_81), __rev0_81, __p1_81); \
52006	__ret_81 = __builtin_shufflevector(__ret_81, __ret_81, 3, 2, 1, 0); \	44305	__ret_81 = __builtin_shufflevector(__ret_81, __ret_81, 7, 6, 5, 4, 3, 2, 1, 0); \
52007	__ret_81; \	44306	__ret_81; \
52008	})	44307	})
52009	#endif	44308	#endif
52010		44309
52011	#ifdef __LITTLE_ENDIAN__	44310	#ifdef __LITTLE_ENDIAN__
52012	#define vcopy_laneq_u8(__p0_82, __p1_82, __p2_82, __p3_82) __extension__ ({ \	44311	#define vcopy_laneq_u32(__p0_82, __p1_82, __p2_82, __p3_82) __extension__ ({ \
52013	uint8x8_t __s0_82 = __p0_82; \	44312	uint32x2_t __s0_82 = __p0_82; \
52014	uint8x16_t __s2_82 = __p2_82; \	44313	uint32x4_t __s2_82 = __p2_82; \
52015	uint8x8_t __ret_82; \	44314	uint32x2_t __ret_82; \
52016	__ret_82 = vset_lane_u8(vgetq_lane_u8(__s2_82, __p3_82), __s0_82, __p1_82); \	44315	__ret_82 = vset_lane_u32(vgetq_lane_u32(__s2_82, __p3_82), __s0_82, __p1_82); \
52017	__ret_82; \	44316	__ret_82; \
52018	})	44317	})
52019	#else	44318	#else
52020	#define vcopy_laneq_u8(__p0_83, __p1_83, __p2_83, __p3_83) __extension__ ({ \	44319	#define vcopy_laneq_u32(__p0_83, __p1_83, __p2_83, __p3_83) __extension__ ({ \
52021	uint8x8_t __s0_83 = __p0_83; \	44320	uint32x2_t __s0_83 = __p0_83; \
52022	uint8x16_t __s2_83 = __p2_83; \	44321	uint32x4_t __s2_83 = __p2_83; \
52023	uint8x8_t __rev0_83; __rev0_83 = __builtin_shufflevector(__s0_83, __s0_83, 7, 6, 5, 4, 3, 2, 1, 0); \	44322	uint32x2_t __rev0_83; __rev0_83 = __builtin_shufflevector(__s0_83, __s0_83, 1, 0); \
52024	uint8x16_t __rev2_83; __rev2_83 = __builtin_shufflevector(__s2_83, __s2_83, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44323	uint32x4_t __rev2_83; __rev2_83 = __builtin_shufflevector(__s2_83, __s2_83, 3, 2, 1, 0); \
52025	uint8x8_t __ret_83; \	44324	uint32x2_t __ret_83; \
52026	__ret_83 = __noswap_vset_lane_u8(__noswap_vgetq_lane_u8(__rev2_83, __p3_83), __rev0_83, __p1_83); \	44325	__ret_83 = __noswap_vset_lane_u32(__noswap_vgetq_lane_u32(__rev2_83, __p3_83), __rev0_83, __p1_83); \
52027	__ret_83 = __builtin_shufflevector(__ret_83, __ret_83, 7, 6, 5, 4, 3, 2, 1, 0); \	44326	__ret_83 = __builtin_shufflevector(__ret_83, __ret_83, 1, 0); \
52028	__ret_83; \	44327	__ret_83; \
52029	})	44328	})
52030	#endif	44329	#endif
52031		44330
52032	#ifdef __LITTLE_ENDIAN__	44331	#ifdef __LITTLE_ENDIAN__
52033	#define vcopy_laneq_u32(__p0_84, __p1_84, __p2_84, __p3_84) __extension__ ({ \	44332	#define vcopy_laneq_u64(__p0_84, __p1_84, __p2_84, __p3_84) __extension__ ({ \
52034	uint32x2_t __s0_84 = __p0_84; \	44333	uint64x1_t __s0_84 = __p0_84; \
52035	uint32x4_t __s2_84 = __p2_84; \	44334	uint64x2_t __s2_84 = __p2_84; \
52036	uint32x2_t __ret_84; \	44335	uint64x1_t __ret_84; \
52037	__ret_84 = vset_lane_u32(vgetq_lane_u32(__s2_84, __p3_84), __s0_84, __p1_84); \	44336	__ret_84 = vset_lane_u64(vgetq_lane_u64(__s2_84, __p3_84), __s0_84, __p1_84); \
52038	__ret_84; \	44337	__ret_84; \
52039	})	44338	})
52040	#else	44339	#else
52041	#define vcopy_laneq_u32(__p0_85, __p1_85, __p2_85, __p3_85) __extension__ ({ \	44340	#define vcopy_laneq_u64(__p0_85, __p1_85, __p2_85, __p3_85) __extension__ ({ \
52042	uint32x2_t __s0_85 = __p0_85; \	44341	uint64x1_t __s0_85 = __p0_85; \
52043	uint32x4_t __s2_85 = __p2_85; \	44342	uint64x2_t __s2_85 = __p2_85; \
52044	uint32x2_t __rev0_85; __rev0_85 = __builtin_shufflevector(__s0_85, __s0_85, 1, 0); \	44343	uint64x2_t __rev2_85; __rev2_85 = __builtin_shufflevector(__s2_85, __s2_85, 1, 0); \
52045	uint32x4_t __rev2_85; __rev2_85 = __builtin_shufflevector(__s2_85, __s2_85, 3, 2, 1, 0); \	44344	uint64x1_t __ret_85; \
52046	uint32x2_t __ret_85; \	44345	__ret_85 = vset_lane_u64(__noswap_vgetq_lane_u64(__rev2_85, __p3_85), __s0_85, __p1_85); \
52047	__ret_85 = __noswap_vset_lane_u32(__noswap_vgetq_lane_u32(__rev2_85, __p3_85), __rev0_85, __p1_85); \
52048	__ret_85 = __builtin_shufflevector(__ret_85, __ret_85, 1, 0); \
52049	__ret_85; \	44346	__ret_85; \
52050	})	44347	})
52051	#endif	44348	#endif
52052		44349
52053	#ifdef __LITTLE_ENDIAN__	44350	#ifdef __LITTLE_ENDIAN__
52054	#define vcopy_laneq_u64(__p0_86, __p1_86, __p2_86, __p3_86) __extension__ ({ \	44351	#define vcopy_laneq_u16(__p0_86, __p1_86, __p2_86, __p3_86) __extension__ ({ \
52055	uint64x1_t __s0_86 = __p0_86; \	44352	uint16x4_t __s0_86 = __p0_86; \
52056	uint64x2_t __s2_86 = __p2_86; \	44353	uint16x8_t __s2_86 = __p2_86; \
52057	uint64x1_t __ret_86; \	44354	uint16x4_t __ret_86; \
52058	__ret_86 = vset_lane_u64(vgetq_lane_u64(__s2_86, __p3_86), __s0_86, __p1_86); \	44355	__ret_86 = vset_lane_u16(vgetq_lane_u16(__s2_86, __p3_86), __s0_86, __p1_86); \
52059	__ret_86; \	44356	__ret_86; \
52060	})	44357	})
52061	#else	44358	#else
52062	#define vcopy_laneq_u64(__p0_87, __p1_87, __p2_87, __p3_87) __extension__ ({ \	44359	#define vcopy_laneq_u16(__p0_87, __p1_87, __p2_87, __p3_87) __extension__ ({ \
52063	uint64x1_t __s0_87 = __p0_87; \	44360	uint16x4_t __s0_87 = __p0_87; \
52064	uint64x2_t __s2_87 = __p2_87; \	44361	uint16x8_t __s2_87 = __p2_87; \
52065	uint64x2_t __rev2_87; __rev2_87 = __builtin_shufflevector(__s2_87, __s2_87, 1, 0); \	44362	uint16x4_t __rev0_87; __rev0_87 = __builtin_shufflevector(__s0_87, __s0_87, 3, 2, 1, 0); \
52066	uint64x1_t __ret_87; \	44363	uint16x8_t __rev2_87; __rev2_87 = __builtin_shufflevector(__s2_87, __s2_87, 7, 6, 5, 4, 3, 2, 1, 0); \
52067	__ret_87 = __noswap_vset_lane_u64(__noswap_vgetq_lane_u64(__rev2_87, __p3_87), __s0_87, __p1_87); \	44364	uint16x4_t __ret_87; \
		44365	__ret_87 = __noswap_vset_lane_u16(__noswap_vgetq_lane_u16(__rev2_87, __p3_87), __rev0_87, __p1_87); \
		44366	__ret_87 = __builtin_shufflevector(__ret_87, __ret_87, 3, 2, 1, 0); \
52068	__ret_87; \	44367	__ret_87; \
52069	})	44368	})
52070	#endif	44369	#endif
52071		44370
52072	#ifdef __LITTLE_ENDIAN__	44371	#ifdef __LITTLE_ENDIAN__
52073	#define vcopy_laneq_u16(__p0_88, __p1_88, __p2_88, __p3_88) __extension__ ({ \	44372	#define vcopy_laneq_s8(__p0_88, __p1_88, __p2_88, __p3_88) __extension__ ({ \
52074	uint16x4_t __s0_88 = __p0_88; \	44373	int8x8_t __s0_88 = __p0_88; \
52075	uint16x8_t __s2_88 = __p2_88; \	44374	int8x16_t __s2_88 = __p2_88; \
52076	uint16x4_t __ret_88; \	44375	int8x8_t __ret_88; \
52077	__ret_88 = vset_lane_u16(vgetq_lane_u16(__s2_88, __p3_88), __s0_88, __p1_88); \	44376	__ret_88 = vset_lane_s8(vgetq_lane_s8(__s2_88, __p3_88), __s0_88, __p1_88); \
52078	__ret_88; \	44377	__ret_88; \
52079	})	44378	})
52080	#else	44379	#else
52081	#define vcopy_laneq_u16(__p0_89, __p1_89, __p2_89, __p3_89) __extension__ ({ \	44380	#define vcopy_laneq_s8(__p0_89, __p1_89, __p2_89, __p3_89) __extension__ ({ \
52082	uint16x4_t __s0_89 = __p0_89; \	44381	int8x8_t __s0_89 = __p0_89; \
52083	uint16x8_t __s2_89 = __p2_89; \	44382	int8x16_t __s2_89 = __p2_89; \
52084	uint16x4_t __rev0_89; __rev0_89 = __builtin_shufflevector(__s0_89, __s0_89, 3, 2, 1, 0); \	44383	int8x8_t __rev0_89; __rev0_89 = __builtin_shufflevector(__s0_89, __s0_89, 7, 6, 5, 4, 3, 2, 1, 0); \
52085	uint16x8_t __rev2_89; __rev2_89 = __builtin_shufflevector(__s2_89, __s2_89, 7, 6, 5, 4, 3, 2, 1, 0); \	44384	int8x16_t __rev2_89; __rev2_89 = __builtin_shufflevector(__s2_89, __s2_89, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
52086	uint16x4_t __ret_89; \	44385	int8x8_t __ret_89; \
52087	__ret_89 = __noswap_vset_lane_u16(__noswap_vgetq_lane_u16(__rev2_89, __p3_89), __rev0_89, __p1_89); \	44386	__ret_89 = __noswap_vset_lane_s8(__noswap_vgetq_lane_s8(__rev2_89, __p3_89), __rev0_89, __p1_89); \
52088	__ret_89 = __builtin_shufflevector(__ret_89, __ret_89, 3, 2, 1, 0); \	44387	__ret_89 = __builtin_shufflevector(__ret_89, __ret_89, 7, 6, 5, 4, 3, 2, 1, 0); \
52089	__ret_89; \	44388	__ret_89; \
52090	})	44389	})
52091	#endif	44390	#endif
52092		44391
52093	#ifdef __LITTLE_ENDIAN__	44392	#ifdef __LITTLE_ENDIAN__
52094	#define vcopy_laneq_s8(__p0_90, __p1_90, __p2_90, __p3_90) __extension__ ({ \	44393	#define vcopy_laneq_f32(__p0_90, __p1_90, __p2_90, __p3_90) __extension__ ({ \
52095	int8x8_t __s0_90 = __p0_90; \	44394	float32x2_t __s0_90 = __p0_90; \
52096	int8x16_t __s2_90 = __p2_90; \	44395	float32x4_t __s2_90 = __p2_90; \
52097	int8x8_t __ret_90; \	44396	float32x2_t __ret_90; \
52098	__ret_90 = vset_lane_s8(vgetq_lane_s8(__s2_90, __p3_90), __s0_90, __p1_90); \	44397	__ret_90 = vset_lane_f32(vgetq_lane_f32(__s2_90, __p3_90), __s0_90, __p1_90); \
52099	__ret_90; \	44398	__ret_90; \
52100	})	44399	})
52101	#else	44400	#else
52102	#define vcopy_laneq_s8(__p0_91, __p1_91, __p2_91, __p3_91) __extension__ ({ \	44401	#define vcopy_laneq_f32(__p0_91, __p1_91, __p2_91, __p3_91) __extension__ ({ \
52103	int8x8_t __s0_91 = __p0_91; \	44402	float32x2_t __s0_91 = __p0_91; \
52104	int8x16_t __s2_91 = __p2_91; \	44403	float32x4_t __s2_91 = __p2_91; \
52105	int8x8_t __rev0_91; __rev0_91 = __builtin_shufflevector(__s0_91, __s0_91, 7, 6, 5, 4, 3, 2, 1, 0); \	44404	float32x2_t __rev0_91; __rev0_91 = __builtin_shufflevector(__s0_91, __s0_91, 1, 0); \
52106	int8x16_t __rev2_91; __rev2_91 = __builtin_shufflevector(__s2_91, __s2_91, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	44405	float32x4_t __rev2_91; __rev2_91 = __builtin_shufflevector(__s2_91, __s2_91, 3, 2, 1, 0); \
52107	int8x8_t __ret_91; \	44406	float32x2_t __ret_91; \
52108	__ret_91 = __noswap_vset_lane_s8(__noswap_vgetq_lane_s8(__rev2_91, __p3_91), __rev0_91, __p1_91); \	44407	__ret_91 = __noswap_vset_lane_f32(__noswap_vgetq_lane_f32(__rev2_91, __p3_91), __rev0_91, __p1_91); \
52109	__ret_91 = __builtin_shufflevector(__ret_91, __ret_91, 7, 6, 5, 4, 3, 2, 1, 0); \	44408	__ret_91 = __builtin_shufflevector(__ret_91, __ret_91, 1, 0); \
52110	__ret_91; \	44409	__ret_91; \
52111	})	44410	})
52112	#endif	44411	#endif
52113		44412
52114	#ifdef __LITTLE_ENDIAN__	44413	#ifdef __LITTLE_ENDIAN__
52115	#define vcopy_laneq_f32(__p0_92, __p1_92, __p2_92, __p3_92) __extension__ ({ \	44414	#define vcopy_laneq_s32(__p0_92, __p1_92, __p2_92, __p3_92) __extension__ ({ \
52116	float32x2_t __s0_92 = __p0_92; \	44415	int32x2_t __s0_92 = __p0_92; \
52117	float32x4_t __s2_92 = __p2_92; \	44416	int32x4_t __s2_92 = __p2_92; \
52118	float32x2_t __ret_92; \	44417	int32x2_t __ret_92; \
52119	__ret_92 = vset_lane_f32(vgetq_lane_f32(__s2_92, __p3_92), __s0_92, __p1_92); \	44418	__ret_92 = vset_lane_s32(vgetq_lane_s32(__s2_92, __p3_92), __s0_92, __p1_92); \
52120	__ret_92; \	44419	__ret_92; \
52121	})	44420	})
52122	#else	44421	#else
52123	#define vcopy_laneq_f32(__p0_93, __p1_93, __p2_93, __p3_93) __extension__ ({ \	44422	#define vcopy_laneq_s32(__p0_93, __p1_93, __p2_93, __p3_93) __extension__ ({ \
52124	float32x2_t __s0_93 = __p0_93; \	44423	int32x2_t __s0_93 = __p0_93; \
52125	float32x4_t __s2_93 = __p2_93; \	44424	int32x4_t __s2_93 = __p2_93; \
52126	float32x2_t __rev0_93; __rev0_93 = __builtin_shufflevector(__s0_93, __s0_93, 1, 0); \	44425	int32x2_t __rev0_93; __rev0_93 = __builtin_shufflevector(__s0_93, __s0_93, 1, 0); \
52127	float32x4_t __rev2_93; __rev2_93 = __builtin_shufflevector(__s2_93, __s2_93, 3, 2, 1, 0); \	44426	int32x4_t __rev2_93; __rev2_93 = __builtin_shufflevector(__s2_93, __s2_93, 3, 2, 1, 0); \
52128	float32x2_t __ret_93; \	44427	int32x2_t __ret_93; \
52129	__ret_93 = __noswap_vset_lane_f32(__noswap_vgetq_lane_f32(__rev2_93, __p3_93), __rev0_93, __p1_93); \	44428	__ret_93 = __noswap_vset_lane_s32(__noswap_vgetq_lane_s32(__rev2_93, __p3_93), __rev0_93, __p1_93); \
52130	__ret_93 = __builtin_shufflevector(__ret_93, __ret_93, 1, 0); \	44429	__ret_93 = __builtin_shufflevector(__ret_93, __ret_93, 1, 0); \
52131	__ret_93; \	44430	__ret_93; \
52132	})	44431	})
52133	#endif	44432	#endif
52134		44433
52135	#ifdef __LITTLE_ENDIAN__	44434	#ifdef __LITTLE_ENDIAN__
52136	#define vcopy_laneq_s32(__p0_94, __p1_94, __p2_94, __p3_94) __extension__ ({ \	44435	#define vcopy_laneq_s64(__p0_94, __p1_94, __p2_94, __p3_94) __extension__ ({ \
52137	int32x2_t __s0_94 = __p0_94; \	44436	int64x1_t __s0_94 = __p0_94; \
52138	int32x4_t __s2_94 = __p2_94; \	44437	int64x2_t __s2_94 = __p2_94; \
52139	int32x2_t __ret_94; \	44438	int64x1_t __ret_94; \
52140	__ret_94 = vset_lane_s32(vgetq_lane_s32(__s2_94, __p3_94), __s0_94, __p1_94); \	44439	__ret_94 = vset_lane_s64(vgetq_lane_s64(__s2_94, __p3_94), __s0_94, __p1_94); \
52141	__ret_94; \	44440	__ret_94; \
52142	})	44441	})
52143	#else	44442	#else
52144	#define vcopy_laneq_s32(__p0_95, __p1_95, __p2_95, __p3_95) __extension__ ({ \	44443	#define vcopy_laneq_s64(__p0_95, __p1_95, __p2_95, __p3_95) __extension__ ({ \
52145	int32x2_t __s0_95 = __p0_95; \	44444	int64x1_t __s0_95 = __p0_95; \
52146	int32x4_t __s2_95 = __p2_95; \	44445	int64x2_t __s2_95 = __p2_95; \
52147	int32x2_t __rev0_95; __rev0_95 = __builtin_shufflevector(__s0_95, __s0_95, 1, 0); \	44446	int64x2_t __rev2_95; __rev2_95 = __builtin_shufflevector(__s2_95, __s2_95, 1, 0); \
52148	int32x4_t __rev2_95; __rev2_95 = __builtin_shufflevector(__s2_95, __s2_95, 3, 2, 1, 0); \	44447	int64x1_t __ret_95; \
52149	int32x2_t __ret_95; \	44448	__ret_95 = vset_lane_s64(__noswap_vgetq_lane_s64(__rev2_95, __p3_95), __s0_95, __p1_95); \
52150	__ret_95 = __noswap_vset_lane_s32(__noswap_vgetq_lane_s32(__rev2_95, __p3_95), __rev0_95, __p1_95); \
52151	__ret_95 = __builtin_shufflevector(__ret_95, __ret_95, 1, 0); \
52152	__ret_95; \	44449	__ret_95; \
52153	})	44450	})
52154	#endif	44451	#endif
52155		44452
52156	#ifdef __LITTLE_ENDIAN__	44453	#ifdef __LITTLE_ENDIAN__
52157	#define vcopy_laneq_s64(__p0_96, __p1_96, __p2_96, __p3_96) __extension__ ({ \	44454	#define vcopy_laneq_s16(__p0_96, __p1_96, __p2_96, __p3_96) __extension__ ({ \
52158	int64x1_t __s0_96 = __p0_96; \	44455	int16x4_t __s0_96 = __p0_96; \
52159	int64x2_t __s2_96 = __p2_96; \	44456	int16x8_t __s2_96 = __p2_96; \
52160	int64x1_t __ret_96; \	44457	int16x4_t __ret_96; \
52161	__ret_96 = vset_lane_s64(vgetq_lane_s64(__s2_96, __p3_96), __s0_96, __p1_96); \	44458	__ret_96 = vset_lane_s16(vgetq_lane_s16(__s2_96, __p3_96), __s0_96, __p1_96); \
52162	__ret_96; \	44459	__ret_96; \
52163	})	44460	})
52164	#else	44461	#else
52165	#define vcopy_laneq_s64(__p0_97, __p1_97, __p2_97, __p3_97) __extension__ ({ \	44462	#define vcopy_laneq_s16(__p0_97, __p1_97, __p2_97, __p3_97) __extension__ ({ \
52166	int64x1_t __s0_97 = __p0_97; \	44463	int16x4_t __s0_97 = __p0_97; \
52167	int64x2_t __s2_97 = __p2_97; \	44464	int16x8_t __s2_97 = __p2_97; \
52168	int64x2_t __rev2_97; __rev2_97 = __builtin_shufflevector(__s2_97, __s2_97, 1, 0); \	44465	int16x4_t __rev0_97; __rev0_97 = __builtin_shufflevector(__s0_97, __s0_97, 3, 2, 1, 0); \
52169	int64x1_t __ret_97; \	44466	int16x8_t __rev2_97; __rev2_97 = __builtin_shufflevector(__s2_97, __s2_97, 7, 6, 5, 4, 3, 2, 1, 0); \
52170	__ret_97 = __noswap_vset_lane_s64(__noswap_vgetq_lane_s64(__rev2_97, __p3_97), __s0_97, __p1_97); \	44467	int16x4_t __ret_97; \
		44468	__ret_97 = __noswap_vset_lane_s16(__noswap_vgetq_lane_s16(__rev2_97, __p3_97), __rev0_97, __p1_97); \
		44469	__ret_97 = __builtin_shufflevector(__ret_97, __ret_97, 3, 2, 1, 0); \
52171	__ret_97; \	44470	__ret_97; \
52172	})	44471	})
52173	#endif	44472	#endif
52174		44473
52175	#ifdef __LITTLE_ENDIAN__	44474	#define vcreate_p64(__p0) __extension__ ({ \
52176	#define vcopy_laneq_s16(__p0_98, __p1_98, __p2_98, __p3_98) __extension__ ({ \	44475	poly64x1_t __ret; \
52177	int16x4_t __s0_98 = __p0_98; \	44476	uint64_t __promote = __p0; \
52178	int16x8_t __s2_98 = __p2_98; \	44477	__ret = (poly64x1_t)(__promote); \
52179	int16x4_t __ret_98; \	44478	__ret; \
52180	__ret_98 = vset_lane_s16(vgetq_lane_s16(__s2_98, __p3_98), __s0_98, __p1_98); \
52181	__ret_98; \
52182	})	44479	})
52183	#else	44480	#define vcreate_f64(__p0) __extension__ ({ \
52184	#define vcopy_laneq_s16(__p0_99, __p1_99, __p2_99, __p3_99) __extension__ ({ \	44481	float64x1_t __ret; \
52185	int16x4_t __s0_99 = __p0_99; \	44482	uint64_t __promote = __p0; \
52186	int16x8_t __s2_99 = __p2_99; \	44483	__ret = (float64x1_t)(__promote); \
52187	int16x4_t __rev0_99; __rev0_99 = __builtin_shufflevector(__s0_99, __s0_99, 3, 2, 1, 0); \	44484	__ret; \
52188	int16x8_t __rev2_99; __rev2_99 = __builtin_shufflevector(__s2_99, __s2_99, 7, 6, 5, 4, 3, 2, 1, 0); \
52189	int16x4_t __ret_99; \
52190	__ret_99 = __noswap_vset_lane_s16(__noswap_vgetq_lane_s16(__rev2_99, __p3_99), __rev0_99, __p1_99); \
52191	__ret_99 = __builtin_shufflevector(__ret_99, __ret_99, 3, 2, 1, 0); \
52192	__ret_99; \
52193	})	44485	})
52194	#endif
52195
52196	#ifdef __LITTLE_ENDIAN__
52197	__ai poly64x1_t vcreate_p64(uint64_t __p0) {
52198	poly64x1_t __ret;
52199	__ret = (poly64x1_t)(__p0);
52200	return __ret;
52201	}
52202	#else
52203	__ai poly64x1_t vcreate_p64(uint64_t __p0) {
52204	poly64x1_t __ret;
52205	__ret = (poly64x1_t)(__p0);
52206	return __ret;
52207	}
52208	#endif
52209
52210	#ifdef __LITTLE_ENDIAN__
52211	__ai float64x1_t vcreate_f64(uint64_t __p0) {
52212	float64x1_t __ret;
52213	__ret = (float64x1_t)(__p0);
52214	return __ret;
52215	}
52216	#else
52217	__ai float64x1_t vcreate_f64(uint64_t __p0) {
52218	float64x1_t __ret;
52219	__ret = (float64x1_t)(__p0);
52220	return __ret;
52221	}
52222	#endif
52223
52224	#ifdef __LITTLE_ENDIAN__
52225	__ai float32_t vcvts_f32_s32(int32_t __p0) {	44486	__ai float32_t vcvts_f32_s32(int32_t __p0) {
52226	float32_t __ret;	44487	float32_t __ret;
52227	__ret = (float32_t) __builtin_neon_vcvts_f32_s32(__p0);	44488	__ret = (float32_t) __builtin_neon_vcvts_f32_s32(__p0);
52228	return __ret;	44489	return __ret;
52229	}	44490	}
52230	#else
52231	__ai float32_t vcvts_f32_s32(int32_t __p0) {
52232	float32_t __ret;
52233	__ret = (float32_t) __builtin_neon_vcvts_f32_s32(__p0);
52234	return __ret;
52235	}
52236	#endif
52237
52238	#ifdef __LITTLE_ENDIAN__
52239	__ai float32_t vcvts_f32_u32(uint32_t __p0) {
52240	float32_t __ret;
52241	__ret = (float32_t) __builtin_neon_vcvts_f32_u32(__p0);
52242	return __ret;
52243	}
52244	#else
52245	__ai float32_t vcvts_f32_u32(uint32_t __p0) {	44491	__ai float32_t vcvts_f32_u32(uint32_t __p0) {
52246	float32_t __ret;	44492	float32_t __ret;
52247	__ret = (float32_t) __builtin_neon_vcvts_f32_u32(__p0);	44493	__ret = (float32_t) __builtin_neon_vcvts_f32_u32(__p0);
52248	return __ret;	44494	return __ret;
52249	}	44495	}
52250	#endif
52251
52252	#ifdef __LITTLE_ENDIAN__	44496	#ifdef __LITTLE_ENDIAN__
52253	__ai float32x2_t vcvt_f32_f64(float64x2_t __p0) {	44497	__ai float32x2_t vcvt_f32_f64(float64x2_t __p0) {
52254	float32x2_t __ret;	44498	float32x2_t __ret;
...	@@ -52270,34 +44514,16 @@ __ai float32x2_t __noswap_vcvt_f32_f64(float64x2_t __p0) {	...	@@ -52270,34 +44514,16 @@ __ai float32x2_t __noswap_vcvt_f32_f64(float64x2_t __p0) {
52270	}	44514	}
52271	#endif	44515	#endif
52272		44516
52273	#ifdef __LITTLE_ENDIAN__
52274	__ai float64_t vcvtd_f64_s64(int64_t __p0) {	44517	__ai float64_t vcvtd_f64_s64(int64_t __p0) {
52275	float64_t __ret;	44518	float64_t __ret;
52276	__ret = (float64_t) __builtin_neon_vcvtd_f64_s64(__p0);	44519	__ret = (float64_t) __builtin_neon_vcvtd_f64_s64(__p0);
52277	return __ret;	44520	return __ret;
52278	}	44521	}
52279	#else
52280	__ai float64_t vcvtd_f64_s64(int64_t __p0) {
52281	float64_t __ret;
52282	__ret = (float64_t) __builtin_neon_vcvtd_f64_s64(__p0);
52283	return __ret;
52284	}
52285	#endif
52286
52287	#ifdef __LITTLE_ENDIAN__
52288	__ai float64_t vcvtd_f64_u64(uint64_t __p0) {	44522	__ai float64_t vcvtd_f64_u64(uint64_t __p0) {
52289	float64_t __ret;	44523	float64_t __ret;
52290	__ret = (float64_t) __builtin_neon_vcvtd_f64_u64(__p0);	44524	__ret = (float64_t) __builtin_neon_vcvtd_f64_u64(__p0);
52291	return __ret;	44525	return __ret;
52292	}	44526	}
52293	#else
52294	__ai float64_t vcvtd_f64_u64(uint64_t __p0) {
52295	float64_t __ret;
52296	__ret = (float64_t) __builtin_neon_vcvtd_f64_u64(__p0);
52297	return __ret;
52298	}
52299	#endif
52300
52301	#ifdef __LITTLE_ENDIAN__	44527	#ifdef __LITTLE_ENDIAN__
52302	__ai float64x2_t vcvtq_f64_u64(uint64x2_t __p0) {	44528	__ai float64x2_t vcvtq_f64_u64(uint64x2_t __p0) {
52303	float64x2_t __ret;	44529	float64x2_t __ret;
...	@@ -52330,34 +44556,16 @@ __ai float64x2_t vcvtq_f64_s64(int64x2_t __p0) {	...	@@ -52330,34 +44556,16 @@ __ai float64x2_t vcvtq_f64_s64(int64x2_t __p0) {
52330	}	44556	}
52331	#endif	44557	#endif
52332		44558
52333	#ifdef __LITTLE_ENDIAN__
52334	__ai float64x1_t vcvt_f64_u64(uint64x1_t __p0) {
52335	float64x1_t __ret;
52336	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 19);
52337	return __ret;
52338	}
52339	#else
52340	__ai float64x1_t vcvt_f64_u64(uint64x1_t __p0) {	44559	__ai float64x1_t vcvt_f64_u64(uint64x1_t __p0) {
52341	float64x1_t __ret;	44560	float64x1_t __ret;
52342	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 19);	44561	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 19);
52343	return __ret;	44562	return __ret;
52344	}	44563	}
52345	#endif
52346
52347	#ifdef __LITTLE_ENDIAN__
52348	__ai float64x1_t vcvt_f64_s64(int64x1_t __p0) {
52349	float64x1_t __ret;
52350	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 3);
52351	return __ret;
52352	}
52353	#else
52354	__ai float64x1_t vcvt_f64_s64(int64x1_t __p0) {	44564	__ai float64x1_t vcvt_f64_s64(int64x1_t __p0) {
52355	float64x1_t __ret;	44565	float64x1_t __ret;
52356	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 3);	44566	__ret = (float64x1_t) __builtin_neon_vcvt_f64_v((int8x8_t)__p0, 3);
52357	return __ret;	44567	return __ret;
52358	}	44568	}
52359	#endif
52360
52361	#ifdef __LITTLE_ENDIAN__	44569	#ifdef __LITTLE_ENDIAN__
52362	__ai float64x2_t vcvt_f64_f32(float32x2_t __p0) {	44570	__ai float64x2_t vcvt_f64_f32(float32x2_t __p0) {
52363	float64x2_t __ret;	44571	float64x2_t __ret;
...	@@ -52445,38 +44653,18 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {	...	@@ -52445,38 +44653,18 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {
52445	}	44653	}
52446	#endif	44654	#endif
52447		44655
52448	#ifdef __LITTLE_ENDIAN__
52449	#define vcvts_n_f32_u32(__p0, __p1) __extension__ ({ \	44656	#define vcvts_n_f32_u32(__p0, __p1) __extension__ ({ \
52450	uint32_t __s0 = __p0; \	44657	uint32_t __s0 = __p0; \
52451	float32_t __ret; \	44658	float32_t __ret; \
52452	__ret = (float32_t) __builtin_neon_vcvts_n_f32_u32(__s0, __p1); \	44659	__ret = (float32_t) __builtin_neon_vcvts_n_f32_u32(__s0, __p1); \
52453	__ret; \	44660	__ret; \
52454	})	44661	})
52455	#else
52456	#define vcvts_n_f32_u32(__p0, __p1) __extension__ ({ \
52457	uint32_t __s0 = __p0; \
52458	float32_t __ret; \
52459	__ret = (float32_t) __builtin_neon_vcvts_n_f32_u32(__s0, __p1); \
52460	__ret; \
52461	})
52462	#endif
52463
52464	#ifdef __LITTLE_ENDIAN__
52465	#define vcvts_n_f32_s32(__p0, __p1) __extension__ ({ \	44662	#define vcvts_n_f32_s32(__p0, __p1) __extension__ ({ \
52466	int32_t __s0 = __p0; \	44663	int32_t __s0 = __p0; \
52467	float32_t __ret; \	44664	float32_t __ret; \
52468	__ret = (float32_t) __builtin_neon_vcvts_n_f32_s32(__s0, __p1); \	44665	__ret = (float32_t) __builtin_neon_vcvts_n_f32_s32(__s0, __p1); \
52469	__ret; \	44666	__ret; \
52470	})	44667	})
52471	#else
52472	#define vcvts_n_f32_s32(__p0, __p1) __extension__ ({ \
52473	int32_t __s0 = __p0; \
52474	float32_t __ret; \
52475	__ret = (float32_t) __builtin_neon_vcvts_n_f32_s32(__s0, __p1); \
52476	__ret; \
52477	})
52478	#endif
52479
52480	#ifdef __LITTLE_ENDIAN__	44668	#ifdef __LITTLE_ENDIAN__
52481	#define vcvtq_n_f64_u64(__p0, __p1) __extension__ ({ \	44669	#define vcvtq_n_f64_u64(__p0, __p1) __extension__ ({ \
52482	uint64x2_t __s0 = __p0; \	44670	uint64x2_t __s0 = __p0; \
...	@@ -52513,86 +44701,36 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {	...	@@ -52513,86 +44701,36 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {
52513	})	44701	})
52514	#endif	44702	#endif
52515		44703
52516	#ifdef __LITTLE_ENDIAN__
52517	#define vcvt_n_f64_u64(__p0, __p1) __extension__ ({ \
52518	uint64x1_t __s0 = __p0; \
52519	float64x1_t __ret; \
52520	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
52521	__ret; \
52522	})
52523	#else
52524	#define vcvt_n_f64_u64(__p0, __p1) __extension__ ({ \	44704	#define vcvt_n_f64_u64(__p0, __p1) __extension__ ({ \
52525	uint64x1_t __s0 = __p0; \	44705	uint64x1_t __s0 = __p0; \
52526	float64x1_t __ret; \	44706	float64x1_t __ret; \
52527	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \	44707	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 19); \
52528	__ret; \	44708	__ret; \
52529	})	44709	})
52530	#endif
52531
52532	#ifdef __LITTLE_ENDIAN__
52533	#define vcvt_n_f64_s64(__p0, __p1) __extension__ ({ \	44710	#define vcvt_n_f64_s64(__p0, __p1) __extension__ ({ \
52534	int64x1_t __s0 = __p0; \	44711	int64x1_t __s0 = __p0; \
52535	float64x1_t __ret; \	44712	float64x1_t __ret; \
52536	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \	44713	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
52537	__ret; \	44714	__ret; \
52538	})	44715	})
52539	#else
52540	#define vcvt_n_f64_s64(__p0, __p1) __extension__ ({ \
52541	int64x1_t __s0 = __p0; \
52542	float64x1_t __ret; \
52543	__ret = (float64x1_t) __builtin_neon_vcvt_n_f64_v((int8x8_t)__s0, __p1, 3); \
52544	__ret; \
52545	})
52546	#endif
52547
52548	#ifdef __LITTLE_ENDIAN__
52549	#define vcvtd_n_f64_u64(__p0, __p1) __extension__ ({ \
52550	uint64_t __s0 = __p0; \
52551	float64_t __ret; \
52552	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_u64(__s0, __p1); \
52553	__ret; \
52554	})
52555	#else
52556	#define vcvtd_n_f64_u64(__p0, __p1) __extension__ ({ \	44716	#define vcvtd_n_f64_u64(__p0, __p1) __extension__ ({ \
52557	uint64_t __s0 = __p0; \	44717	uint64_t __s0 = __p0; \
52558	float64_t __ret; \	44718	float64_t __ret; \
52559	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_u64(__s0, __p1); \	44719	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_u64(__s0, __p1); \
52560	__ret; \	44720	__ret; \
52561	})	44721	})
52562	#endif
52563
52564	#ifdef __LITTLE_ENDIAN__
52565	#define vcvtd_n_f64_s64(__p0, __p1) __extension__ ({ \
52566	int64_t __s0 = __p0; \
52567	float64_t __ret; \
52568	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_s64(__s0, __p1); \
52569	__ret; \
52570	})
52571	#else
52572	#define vcvtd_n_f64_s64(__p0, __p1) __extension__ ({ \	44722	#define vcvtd_n_f64_s64(__p0, __p1) __extension__ ({ \
52573	int64_t __s0 = __p0; \	44723	int64_t __s0 = __p0; \
52574	float64_t __ret; \	44724	float64_t __ret; \
52575	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_s64(__s0, __p1); \	44725	__ret = (float64_t) __builtin_neon_vcvtd_n_f64_s64(__s0, __p1); \
52576	__ret; \	44726	__ret; \
52577	})	44727	})
52578	#endif
52579
52580	#ifdef __LITTLE_ENDIAN__
52581	#define vcvts_n_s32_f32(__p0, __p1) __extension__ ({ \
52582	float32_t __s0 = __p0; \
52583	int32_t __ret; \
52584	__ret = (int32_t) __builtin_neon_vcvts_n_s32_f32(__s0, __p1); \
52585	__ret; \
52586	})
52587	#else
52588	#define vcvts_n_s32_f32(__p0, __p1) __extension__ ({ \	44728	#define vcvts_n_s32_f32(__p0, __p1) __extension__ ({ \
52589	float32_t __s0 = __p0; \	44729	float32_t __s0 = __p0; \
52590	int32_t __ret; \	44730	int32_t __ret; \
52591	__ret = (int32_t) __builtin_neon_vcvts_n_s32_f32(__s0, __p1); \	44731	__ret = (int32_t) __builtin_neon_vcvts_n_s32_f32(__s0, __p1); \
52592	__ret; \	44732	__ret; \
52593	})	44733	})
52594	#endif
52595
52596	#ifdef __LITTLE_ENDIAN__	44734	#ifdef __LITTLE_ENDIAN__
52597	#define vcvtq_n_s64_f64(__p0, __p1) __extension__ ({ \	44735	#define vcvtq_n_s64_f64(__p0, __p1) __extension__ ({ \
52598	float64x2_t __s0 = __p0; \	44736	float64x2_t __s0 = __p0; \
...	@@ -52611,54 +44749,24 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {	...	@@ -52611,54 +44749,24 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {
52611	})	44749	})
52612	#endif	44750	#endif
52613		44751
52614	#ifdef __LITTLE_ENDIAN__
52615	#define vcvt_n_s64_f64(__p0, __p1) __extension__ ({ \	44752	#define vcvt_n_s64_f64(__p0, __p1) __extension__ ({ \
52616	float64x1_t __s0 = __p0; \	44753	float64x1_t __s0 = __p0; \
52617	int64x1_t __ret; \	44754	int64x1_t __ret; \
52618	__ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \	44755	__ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
52619	__ret; \	44756	__ret; \
52620	})	44757	})
52621	#else
52622	#define vcvt_n_s64_f64(__p0, __p1) __extension__ ({ \
52623	float64x1_t __s0 = __p0; \
52624	int64x1_t __ret; \
52625	__ret = (int64x1_t) __builtin_neon_vcvt_n_s64_v((int8x8_t)__s0, __p1, 3); \
52626	__ret; \
52627	})
52628	#endif
52629
52630	#ifdef __LITTLE_ENDIAN__
52631	#define vcvtd_n_s64_f64(__p0, __p1) __extension__ ({ \
52632	float64_t __s0 = __p0; \
52633	int64_t __ret; \
52634	__ret = (int64_t) __builtin_neon_vcvtd_n_s64_f64(__s0, __p1); \
52635	__ret; \
52636	})
52637	#else
52638	#define vcvtd_n_s64_f64(__p0, __p1) __extension__ ({ \	44758	#define vcvtd_n_s64_f64(__p0, __p1) __extension__ ({ \
52639	float64_t __s0 = __p0; \	44759	float64_t __s0 = __p0; \
52640	int64_t __ret; \	44760	int64_t __ret; \
52641	__ret = (int64_t) __builtin_neon_vcvtd_n_s64_f64(__s0, __p1); \	44761	__ret = (int64_t) __builtin_neon_vcvtd_n_s64_f64(__s0, __p1); \
52642	__ret; \	44762	__ret; \
52643	})	44763	})
52644	#endif
52645
52646	#ifdef __LITTLE_ENDIAN__
52647	#define vcvts_n_u32_f32(__p0, __p1) __extension__ ({ \
52648	float32_t __s0 = __p0; \
52649	uint32_t __ret; \
52650	__ret = (uint32_t) __builtin_neon_vcvts_n_u32_f32(__s0, __p1); \
52651	__ret; \
52652	})
52653	#else
52654	#define vcvts_n_u32_f32(__p0, __p1) __extension__ ({ \	44764	#define vcvts_n_u32_f32(__p0, __p1) __extension__ ({ \
52655	float32_t __s0 = __p0; \	44765	float32_t __s0 = __p0; \
52656	uint32_t __ret; \	44766	uint32_t __ret; \
52657	__ret = (uint32_t) __builtin_neon_vcvts_n_u32_f32(__s0, __p1); \	44767	__ret = (uint32_t) __builtin_neon_vcvts_n_u32_f32(__s0, __p1); \
52658	__ret; \	44768	__ret; \
52659	})	44769	})
52660	#endif
52661
52662	#ifdef __LITTLE_ENDIAN__	44770	#ifdef __LITTLE_ENDIAN__
52663	#define vcvtq_n_u64_f64(__p0, __p1) __extension__ ({ \	44771	#define vcvtq_n_u64_f64(__p0, __p1) __extension__ ({ \
52664	float64x2_t __s0 = __p0; \	44772	float64x2_t __s0 = __p0; \
...	@@ -52677,66 +44785,28 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {	...	@@ -52677,66 +44785,28 @@ __ai float64x2_t vcvt_high_f64_f32(float32x4_t __p0) {
52677	})	44785	})
52678	#endif	44786	#endif
52679		44787
52680	#ifdef __LITTLE_ENDIAN__
52681	#define vcvt_n_u64_f64(__p0, __p1) __extension__ ({ \
52682	float64x1_t __s0 = __p0; \
52683	uint64x1_t __ret; \
52684	__ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
52685	__ret; \
52686	})
52687	#else
52688	#define vcvt_n_u64_f64(__p0, __p1) __extension__ ({ \	44788	#define vcvt_n_u64_f64(__p0, __p1) __extension__ ({ \
52689	float64x1_t __s0 = __p0; \	44789	float64x1_t __s0 = __p0; \
52690	uint64x1_t __ret; \	44790	uint64x1_t __ret; \
52691	__ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \	44791	__ret = (uint64x1_t) __builtin_neon_vcvt_n_u64_v((int8x8_t)__s0, __p1, 19); \
52692	__ret; \	44792	__ret; \
52693	})	44793	})
52694	#endif
52695
52696	#ifdef __LITTLE_ENDIAN__
52697	#define vcvtd_n_u64_f64(__p0, __p1) __extension__ ({ \
52698	float64_t __s0 = __p0; \
52699	uint64_t __ret; \
52700	__ret = (uint64_t) __builtin_neon_vcvtd_n_u64_f64(__s0, __p1); \
52701	__ret; \
52702	})
52703	#else
52704	#define vcvtd_n_u64_f64(__p0, __p1) __extension__ ({ \	44794	#define vcvtd_n_u64_f64(__p0, __p1) __extension__ ({ \
52705	float64_t __s0 = __p0; \	44795	float64_t __s0 = __p0; \
52706	uint64_t __ret; \	44796	uint64_t __ret; \
52707	__ret = (uint64_t) __builtin_neon_vcvtd_n_u64_f64(__s0, __p1); \	44797	__ret = (uint64_t) __builtin_neon_vcvtd_n_u64_f64(__s0, __p1); \
52708	__ret; \	44798	__ret; \
52709	})	44799	})
52710	#endif
52711
52712	#ifdef __LITTLE_ENDIAN__
52713	__ai int32_t vcvts_s32_f32(float32_t __p0) {
52714	int32_t __ret;
52715	__ret = (int32_t) __builtin_neon_vcvts_s32_f32(__p0);
52716	return __ret;
52717	}
52718	#else
52719	__ai int32_t vcvts_s32_f32(float32_t __p0) {	44800	__ai int32_t vcvts_s32_f32(float32_t __p0) {
52720	int32_t __ret;	44801	int32_t __ret;
52721	__ret = (int32_t) __builtin_neon_vcvts_s32_f32(__p0);	44802	__ret = (int32_t) __builtin_neon_vcvts_s32_f32(__p0);
52722	return __ret;	44803	return __ret;
52723	}	44804	}
52724	#endif
52725
52726	#ifdef __LITTLE_ENDIAN__
52727	__ai int64_t vcvtd_s64_f64(float64_t __p0) {
52728	int64_t __ret;
52729	__ret = (int64_t) __builtin_neon_vcvtd_s64_f64(__p0);
52730	return __ret;
52731	}
52732	#else
52733	__ai int64_t vcvtd_s64_f64(float64_t __p0) {	44805	__ai int64_t vcvtd_s64_f64(float64_t __p0) {
52734	int64_t __ret;	44806	int64_t __ret;
52735	__ret = (int64_t) __builtin_neon_vcvtd_s64_f64(__p0);	44807	__ret = (int64_t) __builtin_neon_vcvtd_s64_f64(__p0);
52736	return __ret;	44808	return __ret;
52737	}	44809	}
52738	#endif
52739
52740	#ifdef __LITTLE_ENDIAN__	44810	#ifdef __LITTLE_ENDIAN__
52741	__ai int64x2_t vcvtq_s64_f64(float64x2_t __p0) {	44811	__ai int64x2_t vcvtq_s64_f64(float64x2_t __p0) {
52742	int64x2_t __ret;	44812	int64x2_t __ret;
...	@@ -52753,48 +44823,21 @@ __ai int64x2_t vcvtq_s64_f64(float64x2_t __p0) {	...	@@ -52753,48 +44823,21 @@ __ai int64x2_t vcvtq_s64_f64(float64x2_t __p0) {
52753	}	44823	}
52754	#endif	44824	#endif
52755		44825
52756	#ifdef __LITTLE_ENDIAN__
52757	__ai int64x1_t vcvt_s64_f64(float64x1_t __p0) {	44826	__ai int64x1_t vcvt_s64_f64(float64x1_t __p0) {
52758	int64x1_t __ret;	44827	int64x1_t __ret;
52759	__ret = (int64x1_t) __builtin_neon_vcvt_s64_v((int8x8_t)__p0, 3);	44828	__ret = (int64x1_t) __builtin_neon_vcvt_s64_v((int8x8_t)__p0, 3);
52760	return __ret;	44829	return __ret;
52761	}	44830	}
52762	#else
52763	__ai int64x1_t vcvt_s64_f64(float64x1_t __p0) {
52764	int64x1_t __ret;
52765	__ret = (int64x1_t) __builtin_neon_vcvt_s64_v((int8x8_t)__p0, 3);
52766	return __ret;
52767	}
52768	#endif
52769
52770	#ifdef __LITTLE_ENDIAN__
52771	__ai uint32_t vcvts_u32_f32(float32_t __p0) {	44831	__ai uint32_t vcvts_u32_f32(float32_t __p0) {
52772	uint32_t __ret;	44832	uint32_t __ret;
52773	__ret = (uint32_t) __builtin_neon_vcvts_u32_f32(__p0);	44833	__ret = (uint32_t) __builtin_neon_vcvts_u32_f32(__p0);
52774	return __ret;	44834	return __ret;
52775	}	44835	}
52776	#else
52777	__ai uint32_t vcvts_u32_f32(float32_t __p0) {
52778	uint32_t __ret;
52779	__ret = (uint32_t) __builtin_neon_vcvts_u32_f32(__p0);
52780	return __ret;
52781	}
52782	#endif
52783
52784	#ifdef __LITTLE_ENDIAN__
52785	__ai uint64_t vcvtd_u64_f64(float64_t __p0) {	44836	__ai uint64_t vcvtd_u64_f64(float64_t __p0) {
52786	uint64_t __ret;	44837	uint64_t __ret;
52787	__ret = (uint64_t) __builtin_neon_vcvtd_u64_f64(__p0);	44838	__ret = (uint64_t) __builtin_neon_vcvtd_u64_f64(__p0);
52788	return __ret;	44839	return __ret;
52789	}	44840	}
52790	#else
52791	__ai uint64_t vcvtd_u64_f64(float64_t __p0) {
52792	uint64_t __ret;
52793	__ret = (uint64_t) __builtin_neon_vcvtd_u64_f64(__p0);
52794	return __ret;
52795	}
52796	#endif
52797
52798	#ifdef __LITTLE_ENDIAN__	44841	#ifdef __LITTLE_ENDIAN__
52799	__ai uint64x2_t vcvtq_u64_f64(float64x2_t __p0) {	44842	__ai uint64x2_t vcvtq_u64_f64(float64x2_t __p0) {
52800	uint64x2_t __ret;	44843	uint64x2_t __ret;
...	@@ -52811,258 +44854,96 @@ __ai uint64x2_t vcvtq_u64_f64(float64x2_t __p0) {	...	@@ -52811,258 +44854,96 @@ __ai uint64x2_t vcvtq_u64_f64(float64x2_t __p0) {
52811	}	44854	}
52812	#endif	44855	#endif
52813		44856
52814	#ifdef __LITTLE_ENDIAN__
52815	__ai uint64x1_t vcvt_u64_f64(float64x1_t __p0) {
52816	uint64x1_t __ret;
52817	__ret = (uint64x1_t) __builtin_neon_vcvt_u64_v((int8x8_t)__p0, 19);
52818	return __ret;
52819	}
52820	#else
52821	__ai uint64x1_t vcvt_u64_f64(float64x1_t __p0) {	44857	__ai uint64x1_t vcvt_u64_f64(float64x1_t __p0) {
52822	uint64x1_t __ret;	44858	uint64x1_t __ret;
52823	__ret = (uint64x1_t) __builtin_neon_vcvt_u64_v((int8x8_t)__p0, 19);	44859	__ret = (uint64x1_t) __builtin_neon_vcvt_u64_v((int8x8_t)__p0, 19);
52824	return __ret;	44860	return __ret;
52825	}	44861	}
52826	#endif
52827
52828	#ifdef __LITTLE_ENDIAN__
52829	__ai int32_t vcvtas_s32_f32(float32_t __p0) {
52830	int32_t __ret;
52831	__ret = (int32_t) __builtin_neon_vcvtas_s32_f32(__p0);
52832	return __ret;
52833	}
52834	#else
52835	__ai int32_t vcvtas_s32_f32(float32_t __p0) {	44862	__ai int32_t vcvtas_s32_f32(float32_t __p0) {
52836	int32_t __ret;	44863	int32_t __ret;
52837	__ret = (int32_t) __builtin_neon_vcvtas_s32_f32(__p0);	44864	__ret = (int32_t) __builtin_neon_vcvtas_s32_f32(__p0);
52838	return __ret;	44865	return __ret;
52839	}	44866	}
52840	#endif
52841
52842	#ifdef __LITTLE_ENDIAN__
52843	__ai int64_t vcvtad_s64_f64(float64_t __p0) {
52844	int64_t __ret;
52845	__ret = (int64_t) __builtin_neon_vcvtad_s64_f64(__p0);
52846	return __ret;
52847	}
52848	#else
52849	__ai int64_t vcvtad_s64_f64(float64_t __p0) {	44867	__ai int64_t vcvtad_s64_f64(float64_t __p0) {
52850	int64_t __ret;	44868	int64_t __ret;
52851	__ret = (int64_t) __builtin_neon_vcvtad_s64_f64(__p0);	44869	__ret = (int64_t) __builtin_neon_vcvtad_s64_f64(__p0);
52852	return __ret;	44870	return __ret;
52853	}	44871	}
52854	#endif
52855
52856	#ifdef __LITTLE_ENDIAN__
52857	__ai uint32_t vcvtas_u32_f32(float32_t __p0) {
52858	uint32_t __ret;
52859	__ret = (uint32_t) __builtin_neon_vcvtas_u32_f32(__p0);
52860	return __ret;
52861	}
52862	#else
52863	__ai uint32_t vcvtas_u32_f32(float32_t __p0) {	44872	__ai uint32_t vcvtas_u32_f32(float32_t __p0) {
52864	uint32_t __ret;	44873	uint32_t __ret;
52865	__ret = (uint32_t) __builtin_neon_vcvtas_u32_f32(__p0);	44874	__ret = (uint32_t) __builtin_neon_vcvtas_u32_f32(__p0);
52866	return __ret;	44875	return __ret;
52867	}	44876	}
52868	#endif
52869
52870	#ifdef __LITTLE_ENDIAN__
52871	__ai uint64_t vcvtad_u64_f64(float64_t __p0) {
52872	uint64_t __ret;
52873	__ret = (uint64_t) __builtin_neon_vcvtad_u64_f64(__p0);
52874	return __ret;
52875	}
52876	#else
52877	__ai uint64_t vcvtad_u64_f64(float64_t __p0) {	44877	__ai uint64_t vcvtad_u64_f64(float64_t __p0) {
52878	uint64_t __ret;	44878	uint64_t __ret;
52879	__ret = (uint64_t) __builtin_neon_vcvtad_u64_f64(__p0);	44879	__ret = (uint64_t) __builtin_neon_vcvtad_u64_f64(__p0);
52880	return __ret;	44880	return __ret;
52881	}	44881	}
52882	#endif
52883
52884	#ifdef __LITTLE_ENDIAN__
52885	__ai int32_t vcvtms_s32_f32(float32_t __p0) {
52886	int32_t __ret;
52887	__ret = (int32_t) __builtin_neon_vcvtms_s32_f32(__p0);
52888	return __ret;
52889	}
52890	#else
52891	__ai int32_t vcvtms_s32_f32(float32_t __p0) {	44882	__ai int32_t vcvtms_s32_f32(float32_t __p0) {
52892	int32_t __ret;	44883	int32_t __ret;
52893	__ret = (int32_t) __builtin_neon_vcvtms_s32_f32(__p0);	44884	__ret = (int32_t) __builtin_neon_vcvtms_s32_f32(__p0);
52894	return __ret;	44885	return __ret;
52895	}	44886	}
52896	#endif
52897
52898	#ifdef __LITTLE_ENDIAN__
52899	__ai int64_t vcvtmd_s64_f64(float64_t __p0) {
52900	int64_t __ret;
52901	__ret = (int64_t) __builtin_neon_vcvtmd_s64_f64(__p0);
52902	return __ret;
52903	}
52904	#else
52905	__ai int64_t vcvtmd_s64_f64(float64_t __p0) {	44887	__ai int64_t vcvtmd_s64_f64(float64_t __p0) {
52906	int64_t __ret;	44888	int64_t __ret;
52907	__ret = (int64_t) __builtin_neon_vcvtmd_s64_f64(__p0);	44889	__ret = (int64_t) __builtin_neon_vcvtmd_s64_f64(__p0);
52908	return __ret;	44890	return __ret;
52909	}	44891	}
52910	#endif
52911
52912	#ifdef __LITTLE_ENDIAN__
52913	__ai uint32_t vcvtms_u32_f32(float32_t __p0) {
52914	uint32_t __ret;
52915	__ret = (uint32_t) __builtin_neon_vcvtms_u32_f32(__p0);
52916	return __ret;
52917	}
52918	#else
52919	__ai uint32_t vcvtms_u32_f32(float32_t __p0) {	44892	__ai uint32_t vcvtms_u32_f32(float32_t __p0) {
52920	uint32_t __ret;	44893	uint32_t __ret;
52921	__ret = (uint32_t) __builtin_neon_vcvtms_u32_f32(__p0);	44894	__ret = (uint32_t) __builtin_neon_vcvtms_u32_f32(__p0);
52922	return __ret;	44895	return __ret;
52923	}	44896	}
52924	#endif
52925
52926	#ifdef __LITTLE_ENDIAN__
52927	__ai uint64_t vcvtmd_u64_f64(float64_t __p0) {
52928	uint64_t __ret;
52929	__ret = (uint64_t) __builtin_neon_vcvtmd_u64_f64(__p0);
52930	return __ret;
52931	}
52932	#else
52933	__ai uint64_t vcvtmd_u64_f64(float64_t __p0) {	44897	__ai uint64_t vcvtmd_u64_f64(float64_t __p0) {
52934	uint64_t __ret;	44898	uint64_t __ret;
52935	__ret = (uint64_t) __builtin_neon_vcvtmd_u64_f64(__p0);	44899	__ret = (uint64_t) __builtin_neon_vcvtmd_u64_f64(__p0);
52936	return __ret;	44900	return __ret;
52937	}	44901	}
52938	#endif
52939
52940	#ifdef __LITTLE_ENDIAN__
52941	__ai int32_t vcvtns_s32_f32(float32_t __p0) {
52942	int32_t __ret;
52943	__ret = (int32_t) __builtin_neon_vcvtns_s32_f32(__p0);
52944	return __ret;
52945	}
52946	#else
52947	__ai int32_t vcvtns_s32_f32(float32_t __p0) {	44902	__ai int32_t vcvtns_s32_f32(float32_t __p0) {
52948	int32_t __ret;	44903	int32_t __ret;
52949	__ret = (int32_t) __builtin_neon_vcvtns_s32_f32(__p0);	44904	__ret = (int32_t) __builtin_neon_vcvtns_s32_f32(__p0);
52950	return __ret;	44905	return __ret;
52951	}	44906	}
52952	#endif
52953
52954	#ifdef __LITTLE_ENDIAN__
52955	__ai int64_t vcvtnd_s64_f64(float64_t __p0) {	44907	__ai int64_t vcvtnd_s64_f64(float64_t __p0) {
52956	int64_t __ret;	44908	int64_t __ret;
52957	__ret = (int64_t) __builtin_neon_vcvtnd_s64_f64(__p0);	44909	__ret = (int64_t) __builtin_neon_vcvtnd_s64_f64(__p0);
52958	return __ret;	44910	return __ret;
52959	}	44911	}
52960	#else
52961	__ai int64_t vcvtnd_s64_f64(float64_t __p0) {
52962	int64_t __ret;
52963	__ret = (int64_t) __builtin_neon_vcvtnd_s64_f64(__p0);
52964	return __ret;
52965	}
52966	#endif
52967
52968	#ifdef __LITTLE_ENDIAN__
52969	__ai uint32_t vcvtns_u32_f32(float32_t __p0) {
52970	uint32_t __ret;
52971	__ret = (uint32_t) __builtin_neon_vcvtns_u32_f32(__p0);
52972	return __ret;
52973	}
52974	#else
52975	__ai uint32_t vcvtns_u32_f32(float32_t __p0) {	44912	__ai uint32_t vcvtns_u32_f32(float32_t __p0) {
52976	uint32_t __ret;	44913	uint32_t __ret;
52977	__ret = (uint32_t) __builtin_neon_vcvtns_u32_f32(__p0);	44914	__ret = (uint32_t) __builtin_neon_vcvtns_u32_f32(__p0);
52978	return __ret;	44915	return __ret;
52979	}	44916	}
52980	#endif
52981
52982	#ifdef __LITTLE_ENDIAN__
52983	__ai uint64_t vcvtnd_u64_f64(float64_t __p0) {	44917	__ai uint64_t vcvtnd_u64_f64(float64_t __p0) {
52984	uint64_t __ret;	44918	uint64_t __ret;
52985	__ret = (uint64_t) __builtin_neon_vcvtnd_u64_f64(__p0);	44919	__ret = (uint64_t) __builtin_neon_vcvtnd_u64_f64(__p0);
52986	return __ret;	44920	return __ret;
52987	}	44921	}
52988	#else
52989	__ai uint64_t vcvtnd_u64_f64(float64_t __p0) {
52990	uint64_t __ret;
52991	__ret = (uint64_t) __builtin_neon_vcvtnd_u64_f64(__p0);
52992	return __ret;
52993	}
52994	#endif
52995
52996	#ifdef __LITTLE_ENDIAN__
52997	__ai int32_t vcvtps_s32_f32(float32_t __p0) {
52998	int32_t __ret;
52999	__ret = (int32_t) __builtin_neon_vcvtps_s32_f32(__p0);
53000	return __ret;
53001	}
53002	#else
53003	__ai int32_t vcvtps_s32_f32(float32_t __p0) {	44922	__ai int32_t vcvtps_s32_f32(float32_t __p0) {
53004	int32_t __ret;	44923	int32_t __ret;
53005	__ret = (int32_t) __builtin_neon_vcvtps_s32_f32(__p0);	44924	__ret = (int32_t) __builtin_neon_vcvtps_s32_f32(__p0);
53006	return __ret;	44925	return __ret;
53007	}	44926	}
53008	#endif
53009
53010	#ifdef __LITTLE_ENDIAN__
53011	__ai int64_t vcvtpd_s64_f64(float64_t __p0) {
53012	int64_t __ret;
53013	__ret = (int64_t) __builtin_neon_vcvtpd_s64_f64(__p0);
53014	return __ret;
53015	}
53016	#else
53017	__ai int64_t vcvtpd_s64_f64(float64_t __p0) {	44927	__ai int64_t vcvtpd_s64_f64(float64_t __p0) {
53018	int64_t __ret;	44928	int64_t __ret;
53019	__ret = (int64_t) __builtin_neon_vcvtpd_s64_f64(__p0);	44929	__ret = (int64_t) __builtin_neon_vcvtpd_s64_f64(__p0);
53020	return __ret;	44930	return __ret;
53021	}	44931	}
53022	#endif
53023
53024	#ifdef __LITTLE_ENDIAN__
53025	__ai uint32_t vcvtps_u32_f32(float32_t __p0) {	44932	__ai uint32_t vcvtps_u32_f32(float32_t __p0) {
53026	uint32_t __ret;	44933	uint32_t __ret;
53027	__ret = (uint32_t) __builtin_neon_vcvtps_u32_f32(__p0);	44934	__ret = (uint32_t) __builtin_neon_vcvtps_u32_f32(__p0);
53028	return __ret;	44935	return __ret;
53029	}	44936	}
53030	#else
53031	__ai uint32_t vcvtps_u32_f32(float32_t __p0) {
53032	uint32_t __ret;
53033	__ret = (uint32_t) __builtin_neon_vcvtps_u32_f32(__p0);
53034	return __ret;
53035	}
53036	#endif
53037
53038	#ifdef __LITTLE_ENDIAN__
53039	__ai uint64_t vcvtpd_u64_f64(float64_t __p0) {	44937	__ai uint64_t vcvtpd_u64_f64(float64_t __p0) {
53040	uint64_t __ret;	44938	uint64_t __ret;
53041	__ret = (uint64_t) __builtin_neon_vcvtpd_u64_f64(__p0);	44939	__ret = (uint64_t) __builtin_neon_vcvtpd_u64_f64(__p0);
53042	return __ret;	44940	return __ret;
53043	}	44941	}
53044	#else
53045	__ai uint64_t vcvtpd_u64_f64(float64_t __p0) {
53046	uint64_t __ret;
53047	__ret = (uint64_t) __builtin_neon_vcvtpd_u64_f64(__p0);
53048	return __ret;
53049	}
53050	#endif
53051
53052	#ifdef __LITTLE_ENDIAN__
53053	__ai float32_t vcvtxd_f32_f64(float64_t __p0) {
53054	float32_t __ret;
53055	__ret = (float32_t) __builtin_neon_vcvtxd_f32_f64(__p0);
53056	return __ret;
53057	}
53058	#else
53059	__ai float32_t vcvtxd_f32_f64(float64_t __p0) {	44942	__ai float32_t vcvtxd_f32_f64(float64_t __p0) {
53060	float32_t __ret;	44943	float32_t __ret;
53061	__ret = (float32_t) __builtin_neon_vcvtxd_f32_f64(__p0);	44944	__ret = (float32_t) __builtin_neon_vcvtxd_f32_f64(__p0);
53062	return __ret;	44945	return __ret;
53063	}	44946	}
53064	#endif
53065
53066	#ifdef __LITTLE_ENDIAN__	44947	#ifdef __LITTLE_ENDIAN__
53067	__ai float32x2_t vcvtx_f32_f64(float64x2_t __p0) {	44948	__ai float32x2_t vcvtx_f32_f64(float64x2_t __p0) {
53068	float32x2_t __ret;	44949	float32x2_t __ret;
...	@@ -53135,20 +45016,11 @@ __ai float32x4_t vdivq_f32(float32x4_t __p0, float32x4_t __p1) {	...	@@ -53135,20 +45016,11 @@ __ai float32x4_t vdivq_f32(float32x4_t __p0, float32x4_t __p1) {
53135	}	45016	}
53136	#endif	45017	#endif
53137		45018
53138	#ifdef __LITTLE_ENDIAN__
53139	__ai float64x1_t vdiv_f64(float64x1_t __p0, float64x1_t __p1) {
53140	float64x1_t __ret;
53141	__ret = __p0 / __p1;
53142	return __ret;
53143	}
53144	#else
53145	__ai float64x1_t vdiv_f64(float64x1_t __p0, float64x1_t __p1) {	45019	__ai float64x1_t vdiv_f64(float64x1_t __p0, float64x1_t __p1) {
53146	float64x1_t __ret;	45020	float64x1_t __ret;
53147	__ret = __p0 / __p1;	45021	__ret = __p0 / __p1;
53148	return __ret;	45022	return __ret;
53149	}	45023	}
53150	#endif
53151
53152	#ifdef __LITTLE_ENDIAN__	45024	#ifdef __LITTLE_ENDIAN__
53153	__ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	45025	__ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53154	float32x2_t __ret;	45026	float32x2_t __ret;
...	@@ -53170,7 +45042,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53170,7 +45042,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53170	#define vdupb_lane_p8(__p0, __p1) __extension__ ({ \	45042	#define vdupb_lane_p8(__p0, __p1) __extension__ ({ \
53171	poly8x8_t __s0 = __p0; \	45043	poly8x8_t __s0 = __p0; \
53172	poly8_t __ret; \	45044	poly8_t __ret; \
53173	__ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__s0, __p1); \	45045	__ret = (poly8_t) __builtin_neon_vdupb_lane_i8((poly8x8_t)__s0, __p1); \
53174	__ret; \	45046	__ret; \
53175	})	45047	})
53176	#else	45048	#else
...	@@ -53178,7 +45050,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53178,7 +45050,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53178	poly8x8_t __s0 = __p0; \	45050	poly8x8_t __s0 = __p0; \
53179	poly8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	45051	poly8x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
53180	poly8_t __ret; \	45052	poly8_t __ret; \
53181	__ret = (poly8_t) __builtin_neon_vdupb_lane_i8((int8x8_t)__rev0, __p1); \	45053	__ret = (poly8_t) __builtin_neon_vdupb_lane_i8((poly8x8_t)__rev0, __p1); \
53182	__ret; \	45054	__ret; \
53183	})	45055	})
53184	#endif	45056	#endif
...	@@ -53187,7 +45059,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53187,7 +45059,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53187	#define vduph_lane_p16(__p0, __p1) __extension__ ({ \	45059	#define vduph_lane_p16(__p0, __p1) __extension__ ({ \
53188	poly16x4_t __s0 = __p0; \	45060	poly16x4_t __s0 = __p0; \
53189	poly16_t __ret; \	45061	poly16_t __ret; \
53190	__ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \	45062	__ret = (poly16_t) __builtin_neon_vduph_lane_i16((poly16x4_t)__s0, __p1); \
53191	__ret; \	45063	__ret; \
53192	})	45064	})
53193	#else	45065	#else
...	@@ -53195,7 +45067,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53195,7 +45067,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53195	poly16x4_t __s0 = __p0; \	45067	poly16x4_t __s0 = __p0; \
53196	poly16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45068	poly16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53197	poly16_t __ret; \	45069	poly16_t __ret; \
53198	__ret = (poly16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \	45070	__ret = (poly16_t) __builtin_neon_vduph_lane_i16((poly16x4_t)__rev0, __p1); \
53199	__ret; \	45071	__ret; \
53200	})	45072	})
53201	#endif	45073	#endif
...	@@ -53221,7 +45093,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53221,7 +45093,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53221	#define vdups_lane_u32(__p0, __p1) __extension__ ({ \	45093	#define vdups_lane_u32(__p0, __p1) __extension__ ({ \
53222	uint32x2_t __s0 = __p0; \	45094	uint32x2_t __s0 = __p0; \
53223	uint32_t __ret; \	45095	uint32_t __ret; \
53224	__ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \	45096	__ret = (uint32_t) __builtin_neon_vdups_lane_i32((int32x2_t)__s0, __p1); \
53225	__ret; \	45097	__ret; \
53226	})	45098	})
53227	#else	45099	#else
...	@@ -53229,32 +45101,22 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53229,32 +45101,22 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53229	uint32x2_t __s0 = __p0; \	45101	uint32x2_t __s0 = __p0; \
53230	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45102	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53231	uint32_t __ret; \	45103	uint32_t __ret; \
53232	__ret = (uint32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \	45104	__ret = (uint32_t) __builtin_neon_vdups_lane_i32((int32x2_t)__rev0, __p1); \
53233	__ret; \	45105	__ret; \
53234	})	45106	})
53235	#endif	45107	#endif
53236		45108
53237	#ifdef __LITTLE_ENDIAN__
53238	#define vdupd_lane_u64(__p0, __p1) __extension__ ({ \
53239	uint64x1_t __s0 = __p0; \
53240	uint64_t __ret; \
53241	__ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
53242	__ret; \
53243	})
53244	#else
53245	#define vdupd_lane_u64(__p0, __p1) __extension__ ({ \	45109	#define vdupd_lane_u64(__p0, __p1) __extension__ ({ \
53246	uint64x1_t __s0 = __p0; \	45110	uint64x1_t __s0 = __p0; \
53247	uint64_t __ret; \	45111	uint64_t __ret; \
53248	__ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \	45112	__ret = (uint64_t) __builtin_neon_vdupd_lane_i64((int64x1_t)__s0, __p1); \
53249	__ret; \	45113	__ret; \
53250	})	45114	})
53251	#endif
53252
53253	#ifdef __LITTLE_ENDIAN__	45115	#ifdef __LITTLE_ENDIAN__
53254	#define vduph_lane_u16(__p0, __p1) __extension__ ({ \	45116	#define vduph_lane_u16(__p0, __p1) __extension__ ({ \
53255	uint16x4_t __s0 = __p0; \	45117	uint16x4_t __s0 = __p0; \
53256	uint16_t __ret; \	45118	uint16_t __ret; \
53257	__ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \	45119	__ret = (uint16_t) __builtin_neon_vduph_lane_i16((int16x4_t)__s0, __p1); \
53258	__ret; \	45120	__ret; \
53259	})	45121	})
53260	#else	45122	#else
...	@@ -53262,7 +45124,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53262,7 +45124,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53262	uint16x4_t __s0 = __p0; \	45124	uint16x4_t __s0 = __p0; \
53263	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45125	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53264	uint16_t __ret; \	45126	uint16_t __ret; \
53265	__ret = (uint16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \	45127	__ret = (uint16_t) __builtin_neon_vduph_lane_i16((int16x4_t)__rev0, __p1); \
53266	__ret; \	45128	__ret; \
53267	})	45129	})
53268	#endif	45130	#endif
...	@@ -53284,27 +45146,17 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53284,27 +45146,17 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53284	})	45146	})
53285	#endif	45147	#endif
53286		45148
53287	#ifdef __LITTLE_ENDIAN__
53288	#define vdupd_lane_f64(__p0, __p1) __extension__ ({ \
53289	float64x1_t __s0 = __p0; \
53290	float64_t __ret; \
53291	__ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \
53292	__ret; \
53293	})
53294	#else
53295	#define vdupd_lane_f64(__p0, __p1) __extension__ ({ \	45149	#define vdupd_lane_f64(__p0, __p1) __extension__ ({ \
53296	float64x1_t __s0 = __p0; \	45150	float64x1_t __s0 = __p0; \
53297	float64_t __ret; \	45151	float64_t __ret; \
53298	__ret = (float64_t) __builtin_neon_vdupd_lane_f64((int8x8_t)__s0, __p1); \	45152	__ret = (float64_t) __builtin_neon_vdupd_lane_f64((float64x1_t)__s0, __p1); \
53299	__ret; \	45153	__ret; \
53300	})	45154	})
53301	#endif
53302
53303	#ifdef __LITTLE_ENDIAN__	45155	#ifdef __LITTLE_ENDIAN__
53304	#define vdups_lane_f32(__p0, __p1) __extension__ ({ \	45156	#define vdups_lane_f32(__p0, __p1) __extension__ ({ \
53305	float32x2_t __s0 = __p0; \	45157	float32x2_t __s0 = __p0; \
53306	float32_t __ret; \	45158	float32_t __ret; \
53307	__ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__s0, __p1); \	45159	__ret = (float32_t) __builtin_neon_vdups_lane_f32((float32x2_t)__s0, __p1); \
53308	__ret; \	45160	__ret; \
53309	})	45161	})
53310	#else	45162	#else
...	@@ -53312,7 +45164,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53312,7 +45164,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53312	float32x2_t __s0 = __p0; \	45164	float32x2_t __s0 = __p0; \
53313	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45165	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53314	float32_t __ret; \	45166	float32_t __ret; \
53315	__ret = (float32_t) __builtin_neon_vdups_lane_f32((int8x8_t)__rev0, __p1); \	45167	__ret = (float32_t) __builtin_neon_vdups_lane_f32((float32x2_t)__rev0, __p1); \
53316	__ret; \	45168	__ret; \
53317	})	45169	})
53318	#endif	45170	#endif
...	@@ -53321,7 +45173,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53321,7 +45173,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53321	#define vdups_lane_s32(__p0, __p1) __extension__ ({ \	45173	#define vdups_lane_s32(__p0, __p1) __extension__ ({ \
53322	int32x2_t __s0 = __p0; \	45174	int32x2_t __s0 = __p0; \
53323	int32_t __ret; \	45175	int32_t __ret; \
53324	__ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__s0, __p1); \	45176	__ret = (int32_t) __builtin_neon_vdups_lane_i32((int32x2_t)__s0, __p1); \
53325	__ret; \	45177	__ret; \
53326	})	45178	})
53327	#else	45179	#else
...	@@ -53329,32 +45181,22 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53329,32 +45181,22 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53329	int32x2_t __s0 = __p0; \	45181	int32x2_t __s0 = __p0; \
53330	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45182	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53331	int32_t __ret; \	45183	int32_t __ret; \
53332	__ret = (int32_t) __builtin_neon_vdups_lane_i32((int8x8_t)__rev0, __p1); \	45184	__ret = (int32_t) __builtin_neon_vdups_lane_i32((int32x2_t)__rev0, __p1); \
53333	__ret; \	45185	__ret; \
53334	})	45186	})
53335	#endif	45187	#endif
53336		45188
53337	#ifdef __LITTLE_ENDIAN__
53338	#define vdupd_lane_s64(__p0, __p1) __extension__ ({ \
53339	int64x1_t __s0 = __p0; \
53340	int64_t __ret; \
53341	__ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \
53342	__ret; \
53343	})
53344	#else
53345	#define vdupd_lane_s64(__p0, __p1) __extension__ ({ \	45189	#define vdupd_lane_s64(__p0, __p1) __extension__ ({ \
53346	int64x1_t __s0 = __p0; \	45190	int64x1_t __s0 = __p0; \
53347	int64_t __ret; \	45191	int64_t __ret; \
53348	__ret = (int64_t) __builtin_neon_vdupd_lane_i64((int8x8_t)__s0, __p1); \	45192	__ret = (int64_t) __builtin_neon_vdupd_lane_i64((int64x1_t)__s0, __p1); \
53349	__ret; \	45193	__ret; \
53350	})	45194	})
53351	#endif
53352
53353	#ifdef __LITTLE_ENDIAN__	45195	#ifdef __LITTLE_ENDIAN__
53354	#define vduph_lane_s16(__p0, __p1) __extension__ ({ \	45196	#define vduph_lane_s16(__p0, __p1) __extension__ ({ \
53355	int16x4_t __s0 = __p0; \	45197	int16x4_t __s0 = __p0; \
53356	int16_t __ret; \	45198	int16_t __ret; \
53357	__ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__s0, __p1); \	45199	__ret = (int16_t) __builtin_neon_vduph_lane_i16((int16x4_t)__s0, __p1); \
53358	__ret; \	45200	__ret; \
53359	})	45201	})
53360	#else	45202	#else
...	@@ -53362,27 +45204,17 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53362,27 +45204,17 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53362	int16x4_t __s0 = __p0; \	45204	int16x4_t __s0 = __p0; \
53363	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45205	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53364	int16_t __ret; \	45206	int16_t __ret; \
53365	__ret = (int16_t) __builtin_neon_vduph_lane_i16((int8x8_t)__rev0, __p1); \	45207	__ret = (int16_t) __builtin_neon_vduph_lane_i16((int16x4_t)__rev0, __p1); \
53366	__ret; \	45208	__ret; \
53367	})	45209	})
53368	#endif	45210	#endif
53369		45211
53370	#ifdef __LITTLE_ENDIAN__
53371	#define vdup_lane_p64(__p0, __p1) __extension__ ({ \	45212	#define vdup_lane_p64(__p0, __p1) __extension__ ({ \
53372	poly64x1_t __s0 = __p0; \	45213	poly64x1_t __s0 = __p0; \
53373	poly64x1_t __ret; \	45214	poly64x1_t __ret; \
53374	__ret = __builtin_shufflevector(__s0, __s0, __p1); \	45215	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
53375	__ret; \	45216	__ret; \
53376	})	45217	})
53377	#else
53378	#define vdup_lane_p64(__p0, __p1) __extension__ ({ \
53379	poly64x1_t __s0 = __p0; \
53380	poly64x1_t __ret; \
53381	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
53382	__ret; \
53383	})
53384	#endif
53385
53386	#ifdef __LITTLE_ENDIAN__	45218	#ifdef __LITTLE_ENDIAN__
53387	#define vdupq_lane_p64(__p0, __p1) __extension__ ({ \	45219	#define vdupq_lane_p64(__p0, __p1) __extension__ ({ \
53388	poly64x1_t __s0 = __p0; \	45220	poly64x1_t __s0 = __p0; \
...	@@ -53435,22 +45267,12 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53435,22 +45267,12 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53435	})	45267	})
53436	#endif	45268	#endif
53437		45269
53438	#ifdef __LITTLE_ENDIAN__
53439	#define vdup_lane_f64(__p0, __p1) __extension__ ({ \	45270	#define vdup_lane_f64(__p0, __p1) __extension__ ({ \
53440	float64x1_t __s0 = __p0; \	45271	float64x1_t __s0 = __p0; \
53441	float64x1_t __ret; \	45272	float64x1_t __ret; \
53442	__ret = __builtin_shufflevector(__s0, __s0, __p1); \	45273	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
53443	__ret; \	45274	__ret; \
53444	})	45275	})
53445	#else
53446	#define vdup_lane_f64(__p0, __p1) __extension__ ({ \
53447	float64x1_t __s0 = __p0; \
53448	float64x1_t __ret; \
53449	__ret = __builtin_shufflevector(__s0, __s0, __p1); \
53450	__ret; \
53451	})
53452	#endif
53453
53454	#ifdef __LITTLE_ENDIAN__	45276	#ifdef __LITTLE_ENDIAN__
53455	#define vdup_lane_f16(__p0, __p1) __extension__ ({ \	45277	#define vdup_lane_f16(__p0, __p1) __extension__ ({ \
53456	float16x4_t __s0 = __p0; \	45278	float16x4_t __s0 = __p0; \
...	@@ -53473,7 +45295,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53473,7 +45295,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53473	#define vdupb_laneq_p8(__p0, __p1) __extension__ ({ \	45295	#define vdupb_laneq_p8(__p0, __p1) __extension__ ({ \
53474	poly8x16_t __s0 = __p0; \	45296	poly8x16_t __s0 = __p0; \
53475	poly8_t __ret; \	45297	poly8_t __ret; \
53476	__ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__s0, __p1); \	45298	__ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((poly8x16_t)__s0, __p1); \
53477	__ret; \	45299	__ret; \
53478	})	45300	})
53479	#else	45301	#else
...	@@ -53481,7 +45303,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53481,7 +45303,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53481	poly8x16_t __s0 = __p0; \	45303	poly8x16_t __s0 = __p0; \
53482	poly8x16_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	45304	poly8x16_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
53483	poly8_t __ret; \	45305	poly8_t __ret; \
53484	__ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((int8x16_t)__rev0, __p1); \	45306	__ret = (poly8_t) __builtin_neon_vdupb_laneq_i8((poly8x16_t)__rev0, __p1); \
53485	__ret; \	45307	__ret; \
53486	})	45308	})
53487	#endif	45309	#endif
...	@@ -53490,7 +45312,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53490,7 +45312,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53490	#define vduph_laneq_p16(__p0, __p1) __extension__ ({ \	45312	#define vduph_laneq_p16(__p0, __p1) __extension__ ({ \
53491	poly16x8_t __s0 = __p0; \	45313	poly16x8_t __s0 = __p0; \
53492	poly16_t __ret; \	45314	poly16_t __ret; \
53493	__ret = (poly16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \	45315	__ret = (poly16_t) __builtin_neon_vduph_laneq_i16((poly16x8_t)__s0, __p1); \
53494	__ret; \	45316	__ret; \
53495	})	45317	})
53496	#else	45318	#else
...	@@ -53498,7 +45320,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53498,7 +45320,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53498	poly16x8_t __s0 = __p0; \	45320	poly16x8_t __s0 = __p0; \
53499	poly16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	45321	poly16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
53500	poly16_t __ret; \	45322	poly16_t __ret; \
53501	__ret = (poly16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \	45323	__ret = (poly16_t) __builtin_neon_vduph_laneq_i16((poly16x8_t)__rev0, __p1); \
53502	__ret; \	45324	__ret; \
53503	})	45325	})
53504	#endif	45326	#endif
...	@@ -53524,7 +45346,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53524,7 +45346,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53524	#define vdups_laneq_u32(__p0, __p1) __extension__ ({ \	45346	#define vdups_laneq_u32(__p0, __p1) __extension__ ({ \
53525	uint32x4_t __s0 = __p0; \	45347	uint32x4_t __s0 = __p0; \
53526	uint32_t __ret; \	45348	uint32_t __ret; \
53527	__ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__s0, __p1); \	45349	__ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int32x4_t)__s0, __p1); \
53528	__ret; \	45350	__ret; \
53529	})	45351	})
53530	#else	45352	#else
...	@@ -53532,7 +45354,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53532,7 +45354,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53532	uint32x4_t __s0 = __p0; \	45354	uint32x4_t __s0 = __p0; \
53533	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45355	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53534	uint32_t __ret; \	45356	uint32_t __ret; \
53535	__ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__rev0, __p1); \	45357	__ret = (uint32_t) __builtin_neon_vdups_laneq_i32((int32x4_t)__rev0, __p1); \
53536	__ret; \	45358	__ret; \
53537	})	45359	})
53538	#endif	45360	#endif
...	@@ -53541,7 +45363,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53541,7 +45363,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53541	#define vdupd_laneq_u64(__p0, __p1) __extension__ ({ \	45363	#define vdupd_laneq_u64(__p0, __p1) __extension__ ({ \
53542	uint64x2_t __s0 = __p0; \	45364	uint64x2_t __s0 = __p0; \
53543	uint64_t __ret; \	45365	uint64_t __ret; \
53544	__ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__s0, __p1); \	45366	__ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int64x2_t)__s0, __p1); \
53545	__ret; \	45367	__ret; \
53546	})	45368	})
53547	#else	45369	#else
...	@@ -53549,7 +45371,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53549,7 +45371,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53549	uint64x2_t __s0 = __p0; \	45371	uint64x2_t __s0 = __p0; \
53550	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45372	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53551	uint64_t __ret; \	45373	uint64_t __ret; \
53552	__ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__rev0, __p1); \	45374	__ret = (uint64_t) __builtin_neon_vdupd_laneq_i64((int64x2_t)__rev0, __p1); \
53553	__ret; \	45375	__ret; \
53554	})	45376	})
53555	#endif	45377	#endif
...	@@ -53558,7 +45380,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53558,7 +45380,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53558	#define vduph_laneq_u16(__p0, __p1) __extension__ ({ \	45380	#define vduph_laneq_u16(__p0, __p1) __extension__ ({ \
53559	uint16x8_t __s0 = __p0; \	45381	uint16x8_t __s0 = __p0; \
53560	uint16_t __ret; \	45382	uint16_t __ret; \
53561	__ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \	45383	__ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int16x8_t)__s0, __p1); \
53562	__ret; \	45384	__ret; \
53563	})	45385	})
53564	#else	45386	#else
...	@@ -53566,7 +45388,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53566,7 +45388,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53566	uint16x8_t __s0 = __p0; \	45388	uint16x8_t __s0 = __p0; \
53567	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	45389	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
53568	uint16_t __ret; \	45390	uint16_t __ret; \
53569	__ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \	45391	__ret = (uint16_t) __builtin_neon_vduph_laneq_i16((int16x8_t)__rev0, __p1); \
53570	__ret; \	45392	__ret; \
53571	})	45393	})
53572	#endif	45394	#endif
...	@@ -53592,7 +45414,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53592,7 +45414,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53592	#define vdupd_laneq_f64(__p0, __p1) __extension__ ({ \	45414	#define vdupd_laneq_f64(__p0, __p1) __extension__ ({ \
53593	float64x2_t __s0 = __p0; \	45415	float64x2_t __s0 = __p0; \
53594	float64_t __ret; \	45416	float64_t __ret; \
53595	__ret = (float64_t) __builtin_neon_vdupd_laneq_f64((int8x16_t)__s0, __p1); \	45417	__ret = (float64_t) __builtin_neon_vdupd_laneq_f64((float64x2_t)__s0, __p1); \
53596	__ret; \	45418	__ret; \
53597	})	45419	})
53598	#else	45420	#else
...	@@ -53600,7 +45422,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53600,7 +45422,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53600	float64x2_t __s0 = __p0; \	45422	float64x2_t __s0 = __p0; \
53601	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45423	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53602	float64_t __ret; \	45424	float64_t __ret; \
53603	__ret = (float64_t) __builtin_neon_vdupd_laneq_f64((int8x16_t)__rev0, __p1); \	45425	__ret = (float64_t) __builtin_neon_vdupd_laneq_f64((float64x2_t)__rev0, __p1); \
53604	__ret; \	45426	__ret; \
53605	})	45427	})
53606	#endif	45428	#endif
...	@@ -53609,7 +45431,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53609,7 +45431,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53609	#define vdups_laneq_f32(__p0, __p1) __extension__ ({ \	45431	#define vdups_laneq_f32(__p0, __p1) __extension__ ({ \
53610	float32x4_t __s0 = __p0; \	45432	float32x4_t __s0 = __p0; \
53611	float32_t __ret; \	45433	float32_t __ret; \
53612	__ret = (float32_t) __builtin_neon_vdups_laneq_f32((int8x16_t)__s0, __p1); \	45434	__ret = (float32_t) __builtin_neon_vdups_laneq_f32((float32x4_t)__s0, __p1); \
53613	__ret; \	45435	__ret; \
53614	})	45436	})
53615	#else	45437	#else
...	@@ -53617,7 +45439,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53617,7 +45439,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53617	float32x4_t __s0 = __p0; \	45439	float32x4_t __s0 = __p0; \
53618	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45440	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53619	float32_t __ret; \	45441	float32_t __ret; \
53620	__ret = (float32_t) __builtin_neon_vdups_laneq_f32((int8x16_t)__rev0, __p1); \	45442	__ret = (float32_t) __builtin_neon_vdups_laneq_f32((float32x4_t)__rev0, __p1); \
53621	__ret; \	45443	__ret; \
53622	})	45444	})
53623	#endif	45445	#endif
...	@@ -53626,7 +45448,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53626,7 +45448,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53626	#define vdups_laneq_s32(__p0, __p1) __extension__ ({ \	45448	#define vdups_laneq_s32(__p0, __p1) __extension__ ({ \
53627	int32x4_t __s0 = __p0; \	45449	int32x4_t __s0 = __p0; \
53628	int32_t __ret; \	45450	int32_t __ret; \
53629	__ret = (int32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__s0, __p1); \	45451	__ret = (int32_t) __builtin_neon_vdups_laneq_i32((int32x4_t)__s0, __p1); \
53630	__ret; \	45452	__ret; \
53631	})	45453	})
53632	#else	45454	#else
...	@@ -53634,7 +45456,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53634,7 +45456,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53634	int32x4_t __s0 = __p0; \	45456	int32x4_t __s0 = __p0; \
53635	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \	45457	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 3, 2, 1, 0); \
53636	int32_t __ret; \	45458	int32_t __ret; \
53637	__ret = (int32_t) __builtin_neon_vdups_laneq_i32((int8x16_t)__rev0, __p1); \	45459	__ret = (int32_t) __builtin_neon_vdups_laneq_i32((int32x4_t)__rev0, __p1); \
53638	__ret; \	45460	__ret; \
53639	})	45461	})
53640	#endif	45462	#endif
...	@@ -53643,7 +45465,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53643,7 +45465,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53643	#define vdupd_laneq_s64(__p0, __p1) __extension__ ({ \	45465	#define vdupd_laneq_s64(__p0, __p1) __extension__ ({ \
53644	int64x2_t __s0 = __p0; \	45466	int64x2_t __s0 = __p0; \
53645	int64_t __ret; \	45467	int64_t __ret; \
53646	__ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__s0, __p1); \	45468	__ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int64x2_t)__s0, __p1); \
53647	__ret; \	45469	__ret; \
53648	})	45470	})
53649	#else	45471	#else
...	@@ -53651,7 +45473,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53651,7 +45473,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53651	int64x2_t __s0 = __p0; \	45473	int64x2_t __s0 = __p0; \
53652	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	45474	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
53653	int64_t __ret; \	45475	int64_t __ret; \
53654	__ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int8x16_t)__rev0, __p1); \	45476	__ret = (int64_t) __builtin_neon_vdupd_laneq_i64((int64x2_t)__rev0, __p1); \
53655	__ret; \	45477	__ret; \
53656	})	45478	})
53657	#endif	45479	#endif
...	@@ -53660,7 +45482,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53660,7 +45482,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53660	#define vduph_laneq_s16(__p0, __p1) __extension__ ({ \	45482	#define vduph_laneq_s16(__p0, __p1) __extension__ ({ \
53661	int16x8_t __s0 = __p0; \	45483	int16x8_t __s0 = __p0; \
53662	int16_t __ret; \	45484	int16_t __ret; \
53663	__ret = (int16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__s0, __p1); \	45485	__ret = (int16_t) __builtin_neon_vduph_laneq_i16((int16x8_t)__s0, __p1); \
53664	__ret; \	45486	__ret; \
53665	})	45487	})
53666	#else	45488	#else
...	@@ -53668,7 +45490,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -53668,7 +45490,7 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
53668	int16x8_t __s0 = __p0; \	45490	int16x8_t __s0 = __p0; \
53669	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \	45491	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 7, 6, 5, 4, 3, 2, 1, 0); \
53670	int16_t __ret; \	45492	int16_t __ret; \
53671	__ret = (int16_t) __builtin_neon_vduph_laneq_i16((int8x16_t)__rev0, __p1); \	45493	__ret = (int16_t) __builtin_neon_vduph_laneq_i16((int16x8_t)__rev0, __p1); \
53672	__ret; \	45494	__ret; \
53673	})	45495	})
53674	#endif	45496	#endif
...	@@ -54173,20 +45995,11 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -54173,20 +45995,11 @@ __ai float32x2_t vdiv_f32(float32x2_t __p0, float32x2_t __p1) {
54173	})	45995	})
54174	#endif	45996	#endif
54175		45997
54176	#ifdef __LITTLE_ENDIAN__
54177	__ai poly64x1_t vdup_n_p64(poly64_t __p0) {	45998	__ai poly64x1_t vdup_n_p64(poly64_t __p0) {
54178	poly64x1_t __ret;	45999	poly64x1_t __ret;
54179	__ret = (poly64x1_t) {__p0};	46000	__ret = (poly64x1_t) {__p0};
54180	return __ret;	46001	return __ret;
54181	}	46002	}
54182	#else
54183	__ai poly64x1_t vdup_n_p64(poly64_t __p0) {
54184	poly64x1_t __ret;
54185	__ret = (poly64x1_t) {__p0};
54186	return __ret;
54187	}
54188	#endif
54189
54190	#ifdef __LITTLE_ENDIAN__	46003	#ifdef __LITTLE_ENDIAN__
54191	__ai poly64x2_t vdupq_n_p64(poly64_t __p0) {	46004	__ai poly64x2_t vdupq_n_p64(poly64_t __p0) {
54192	poly64x2_t __ret;	46005	poly64x2_t __ret;
...	@@ -54217,21 +46030,11 @@ __ai float64x2_t vdupq_n_f64(float64_t __p0) {	...	@@ -54217,21 +46030,11 @@ __ai float64x2_t vdupq_n_f64(float64_t __p0) {
54217	}	46030	}
54218	#endif	46031	#endif
54219		46032
54220	#ifdef __LITTLE_ENDIAN__
54221	__ai float64x1_t vdup_n_f64(float64_t __p0) {
54222	float64x1_t __ret;
54223	__ret = (float64x1_t) {__p0};
54224	return __ret;
54225	}
54226	#else
54227	__ai float64x1_t vdup_n_f64(float64_t __p0) {	46033	__ai float64x1_t vdup_n_f64(float64_t __p0) {
54228	float64x1_t __ret;	46034	float64x1_t __ret;
54229	__ret = (float64x1_t) {__p0};	46035	__ret = (float64x1_t) {__p0};
54230	return __ret;	46036	return __ret;
54231	}	46037	}
54232	#endif
54233
54234	#ifdef __LITTLE_ENDIAN__
54235	#define vext_p64(__p0, __p1, __p2) __extension__ ({ \	46038	#define vext_p64(__p0, __p1, __p2) __extension__ ({ \
54236	poly64x1_t __s0 = __p0; \	46039	poly64x1_t __s0 = __p0; \
54237	poly64x1_t __s1 = __p1; \	46040	poly64x1_t __s1 = __p1; \
...	@@ -54239,16 +46042,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {	...	@@ -54239,16 +46042,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {
54239	__ret = (poly64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \	46042	__ret = (poly64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
54240	__ret; \	46043	__ret; \
54241	})	46044	})
54242	#else
54243	#define vext_p64(__p0, __p1, __p2) __extension__ ({ \
54244	poly64x1_t __s0 = __p0; \
54245	poly64x1_t __s1 = __p1; \
54246	poly64x1_t __ret; \
54247	__ret = (poly64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
54248	__ret; \
54249	})
54250	#endif
54251
54252	#ifdef __LITTLE_ENDIAN__	46045	#ifdef __LITTLE_ENDIAN__
54253	#define vextq_p64(__p0, __p1, __p2) __extension__ ({ \	46046	#define vextq_p64(__p0, __p1, __p2) __extension__ ({ \
54254	poly64x2_t __s0 = __p0; \	46047	poly64x2_t __s0 = __p0; \
...	@@ -54291,7 +46084,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {	...	@@ -54291,7 +46084,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {
54291	})	46084	})
54292	#endif	46085	#endif
54293		46086
54294	#ifdef __LITTLE_ENDIAN__
54295	#define vext_f64(__p0, __p1, __p2) __extension__ ({ \	46087	#define vext_f64(__p0, __p1, __p2) __extension__ ({ \
54296	float64x1_t __s0 = __p0; \	46088	float64x1_t __s0 = __p0; \
54297	float64x1_t __s1 = __p1; \	46089	float64x1_t __s1 = __p1; \
...	@@ -54299,16 +46091,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {	...	@@ -54299,16 +46091,6 @@ __ai float64x1_t vdup_n_f64(float64_t __p0) {
54299	__ret = (float64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \	46091	__ret = (float64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
54300	__ret; \	46092	__ret; \
54301	})	46093	})
54302	#else
54303	#define vext_f64(__p0, __p1, __p2) __extension__ ({ \
54304	float64x1_t __s0 = __p0; \
54305	float64x1_t __s1 = __p1; \
54306	float64x1_t __ret; \
54307	__ret = (float64x1_t) __builtin_neon_vext_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
54308	__ret; \
54309	})
54310	#endif
54311
54312	#ifdef __LITTLE_ENDIAN__	46094	#ifdef __LITTLE_ENDIAN__
54313	__ai float64x2_t vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {	46095	__ai float64x2_t vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
54314	float64x2_t __ret;	46096	float64x2_t __ret;
...	@@ -54332,60 +46114,26 @@ __ai float64x2_t __noswap_vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x	...	@@ -54332,60 +46114,26 @@ __ai float64x2_t __noswap_vfmaq_f64(float64x2_t __p0, float64x2_t __p1, float64x
54332	}	46114	}
54333	#endif	46115	#endif
54334		46116
54335	#ifdef __LITTLE_ENDIAN__
54336	__ai float64x1_t vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
54337	float64x1_t __ret;
54338	__ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
54339	return __ret;
54340	}
54341	#else
54342	__ai float64x1_t vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	46117	__ai float64x1_t vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
54343	float64x1_t __ret;	46118	float64x1_t __ret;
54344	__ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);	46119	__ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
54345	return __ret;	46120	return __ret;
54346	}	46121	}
54347	__ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
54348	float64x1_t __ret;
54349	__ret = (float64x1_t) __builtin_neon_vfma_v((int8x8_t)__p0, (int8x8_t)__p1, (int8x8_t)__p2, 10);
54350	return __ret;
54351	}
54352	#endif
54353
54354	#ifdef __LITTLE_ENDIAN__
54355	#define vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54356	float64_t __s0 = __p0; \
54357	float64_t __s1 = __p1; \
54358	float64x1_t __s2 = __p2; \
54359	float64_t __ret; \
54360	__ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \
54361	__ret; \
54362	})
54363	#else
54364	#define vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \	46122	#define vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54365	float64_t __s0 = __p0; \	46123	float64_t __s0 = __p0; \
54366	float64_t __s1 = __p1; \	46124	float64_t __s1 = __p1; \
54367	float64x1_t __s2 = __p2; \	46125	float64x1_t __s2 = __p2; \
54368	float64_t __ret; \	46126	float64_t __ret; \
54369	__ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \	46127	__ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (float64x1_t)__s2, __p3); \
54370	__ret; \
54371	})
54372	#define __noswap_vfmad_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54373	float64_t __s0 = __p0; \
54374	float64_t __s1 = __p1; \
54375	float64x1_t __s2 = __p2; \
54376	float64_t __ret; \
54377	__ret = (float64_t) __builtin_neon_vfmad_lane_f64(__s0, __s1, (int8x8_t)__s2, __p3); \
54378	__ret; \	46128	__ret; \
54379	})	46129	})
54380	#endif
54381
54382	#ifdef __LITTLE_ENDIAN__	46130	#ifdef __LITTLE_ENDIAN__
54383	#define vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \	46131	#define vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
54384	float32_t __s0 = __p0; \	46132	float32_t __s0 = __p0; \
54385	float32_t __s1 = __p1; \	46133	float32_t __s1 = __p1; \
54386	float32x2_t __s2 = __p2; \	46134	float32x2_t __s2 = __p2; \
54387	float32_t __ret; \	46135	float32_t __ret; \
54388	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__s2, __p3); \	46136	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (float32x2_t)__s2, __p3); \
54389	__ret; \	46137	__ret; \
54390	})	46138	})
54391	#else	46139	#else
...	@@ -54395,7 +46143,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54395,7 +46143,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54395	float32x2_t __s2 = __p2; \	46143	float32x2_t __s2 = __p2; \
54396	float32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \	46144	float32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \
54397	float32_t __ret; \	46145	float32_t __ret; \
54398	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__rev2, __p3); \	46146	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (float32x2_t)__rev2, __p3); \
54399	__ret; \	46147	__ret; \
54400	})	46148	})
54401	#define __noswap_vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \	46149	#define __noswap_vfmas_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
...	@@ -54403,7 +46151,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54403,7 +46151,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54403	float32_t __s1 = __p1; \	46151	float32_t __s1 = __p1; \
54404	float32x2_t __s2 = __p2; \	46152	float32x2_t __s2 = __p2; \
54405	float32_t __ret; \	46153	float32_t __ret; \
54406	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (int8x8_t)__s2, __p3); \	46154	__ret = (float32_t) __builtin_neon_vfmas_lane_f32(__s0, __s1, (float32x2_t)__s2, __p3); \
54407	__ret; \	46155	__ret; \
54408	})	46156	})
54409	#endif	46157	#endif
...	@@ -54471,16 +46219,6 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54471,16 +46219,6 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54471	})	46219	})
54472	#endif	46220	#endif
54473		46221
54474	#ifdef __LITTLE_ENDIAN__
54475	#define vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54476	float64x1_t __s0 = __p0; \
54477	float64x1_t __s1 = __p1; \
54478	float64x1_t __s2 = __p2; \
54479	float64x1_t __ret; \
54480	__ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
54481	__ret; \
54482	})
54483	#else
54484	#define vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \	46222	#define vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54485	float64x1_t __s0 = __p0; \	46223	float64x1_t __s0 = __p0; \
54486	float64x1_t __s1 = __p1; \	46224	float64x1_t __s1 = __p1; \
...	@@ -54489,16 +46227,6 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54489,16 +46227,6 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54489	__ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \	46227	__ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
54490	__ret; \	46228	__ret; \
54491	})	46229	})
54492	#define __noswap_vfma_lane_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
54493	float64x1_t __s0 = __p0; \
54494	float64x1_t __s1 = __p1; \
54495	float64x1_t __s2 = __p2; \
54496	float64x1_t __ret; \
54497	__ret = (float64x1_t) __builtin_neon_vfma_lane_v((int8x8_t)__s0, (int8x8_t)__s1, (int8x8_t)__s2, __p3, 10); \
54498	__ret; \
54499	})
54500	#endif
54501
54502	#ifdef __LITTLE_ENDIAN__	46230	#ifdef __LITTLE_ENDIAN__
54503	#define vfma_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \	46231	#define vfma_lane_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
54504	float32x2_t __s0 = __p0; \	46232	float32x2_t __s0 = __p0; \
...	@@ -54537,7 +46265,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54537,7 +46265,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54537	float64_t __s1 = __p1; \	46265	float64_t __s1 = __p1; \
54538	float64x2_t __s2 = __p2; \	46266	float64x2_t __s2 = __p2; \
54539	float64_t __ret; \	46267	float64_t __ret; \
54540	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (int8x16_t)__s2, __p3); \	46268	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (float64x2_t)__s2, __p3); \
54541	__ret; \	46269	__ret; \
54542	})	46270	})
54543	#else	46271	#else
...	@@ -54547,7 +46275,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54547,7 +46275,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54547	float64x2_t __s2 = __p2; \	46275	float64x2_t __s2 = __p2; \
54548	float64x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \	46276	float64x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \
54549	float64_t __ret; \	46277	float64_t __ret; \
54550	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (int8x16_t)__rev2, __p3); \	46278	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (float64x2_t)__rev2, __p3); \
54551	__ret; \	46279	__ret; \
54552	})	46280	})
54553	#define __noswap_vfmad_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \	46281	#define __noswap_vfmad_laneq_f64(__p0, __p1, __p2, __p3) __extension__ ({ \
...	@@ -54555,7 +46283,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54555,7 +46283,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54555	float64_t __s1 = __p1; \	46283	float64_t __s1 = __p1; \
54556	float64x2_t __s2 = __p2; \	46284	float64x2_t __s2 = __p2; \
54557	float64_t __ret; \	46285	float64_t __ret; \
54558	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (int8x16_t)__s2, __p3); \	46286	__ret = (float64_t) __builtin_neon_vfmad_laneq_f64(__s0, __s1, (float64x2_t)__s2, __p3); \
54559	__ret; \	46287	__ret; \
54560	})	46288	})
54561	#endif	46289	#endif
...	@@ -54566,7 +46294,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54566,7 +46294,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54566	float32_t __s1 = __p1; \	46294	float32_t __s1 = __p1; \
54567	float32x4_t __s2 = __p2; \	46295	float32x4_t __s2 = __p2; \
54568	float32_t __ret; \	46296	float32_t __ret; \
54569	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (int8x16_t)__s2, __p3); \	46297	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (float32x4_t)__s2, __p3); \
54570	__ret; \	46298	__ret; \
54571	})	46299	})
54572	#else	46300	#else
...	@@ -54576,7 +46304,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54576,7 +46304,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54576	float32x4_t __s2 = __p2; \	46304	float32x4_t __s2 = __p2; \
54577	float32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	46305	float32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
54578	float32_t __ret; \	46306	float32_t __ret; \
54579	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (int8x16_t)__rev2, __p3); \	46307	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (float32x4_t)__rev2, __p3); \
54580	__ret; \	46308	__ret; \
54581	})	46309	})
54582	#define __noswap_vfmas_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \	46310	#define __noswap_vfmas_laneq_f32(__p0, __p1, __p2, __p3) __extension__ ({ \
...	@@ -54584,7 +46312,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1	...	@@ -54584,7 +46312,7 @@ __ai float64x1_t __noswap_vfma_f64(float64x1_t __p0, float64x1_t __p1, float64x1
54584	float32_t __s1 = __p1; \	46312	float32_t __s1 = __p1; \
54585	float32x4_t __s2 = __p2; \	46313	float32x4_t __s2 = __p2; \
54586	float32_t __ret; \	46314	float32_t __ret; \
54587	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (int8x16_t)__s2, __p3); \	46315	__ret = (float32_t) __builtin_neon_vfmas_laneq_f32(__s0, __s1, (float32x4_t)__s2, __p3); \
54588	__ret; \	46316	__ret; \
54589	})	46317	})
54590	#endif	46318	#endif
...	@@ -54731,20 +46459,11 @@ __ai float64x2_t vfmaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2)	...	@@ -54731,20 +46459,11 @@ __ai float64x2_t vfmaq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2)
54731	}	46459	}
54732	#endif	46460	#endif
54733		46461
54734	#ifdef __LITTLE_ENDIAN__
54735	__ai float64x1_t vfma_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {	46462	__ai float64x1_t vfma_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {
54736	float64x1_t __ret;	46463	float64x1_t __ret;
54737	__ret = vfma_f64(__p0, __p1, (float64x1_t) {__p2});	46464	__ret = vfma_f64(__p0, __p1, (float64x1_t) {__p2});
54738	return __ret;	46465	return __ret;
54739	}	46466	}
54740	#else
54741	__ai float64x1_t vfma_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {
54742	float64x1_t __ret;
54743	__ret = __noswap_vfma_f64(__p0, __p1, (float64x1_t) {__p2});
54744	return __ret;
54745	}
54746	#endif
54747
54748	#ifdef __LITTLE_ENDIAN__	46467	#ifdef __LITTLE_ENDIAN__
54749	__ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {	46468	__ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2) {
54750	float64x2_t __ret;	46469	float64x2_t __ret;
...	@@ -54763,287 +46482,254 @@ __ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)	...	@@ -54763,287 +46482,254 @@ __ai float64x2_t vfmsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)
54763	}	46482	}
54764	#endif	46483	#endif
54765		46484
54766	#ifdef __LITTLE_ENDIAN__
54767	__ai float64x1_t vfms_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	46485	__ai float64x1_t vfms_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
54768	float64x1_t __ret;	46486	float64x1_t __ret;
54769	__ret = vfma_f64(__p0, -__p1, __p2);	46487	__ret = vfma_f64(__p0, -__p1, __p2);
54770	return __ret;	46488	return __ret;
54771	}	46489	}
54772	#else	46490	#define vfmsd_lane_f64(__p0_98, __p1_98, __p2_98, __p3_98) __extension__ ({ \
54773	__ai float64x1_t vfms_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	46491	float64_t __s0_98 = __p0_98; \
54774	float64x1_t __ret;	46492	float64_t __s1_98 = __p1_98; \
54775	__ret = __noswap_vfma_f64(__p0, -__p1, __p2);	46493	float64x1_t __s2_98 = __p2_98; \
54776	return __ret;	46494	float64_t __ret_98; \
54777	}	46495	__ret_98 = vfmad_lane_f64(__s0_98, -__s1_98, __s2_98, __p3_98); \
54778	#endif	46496	__ret_98; \
54779		46497	})
54780	#ifdef __LITTLE_ENDIAN__	46498	#ifdef __LITTLE_ENDIAN__
54781	#define vfmsd_lane_f64(__p0_100, __p1_100, __p2_100, __p3_100) __extension__ ({ \	46499	#define vfmss_lane_f32(__p0_99, __p1_99, __p2_99, __p3_99) __extension__ ({ \
54782	float64_t __s0_100 = __p0_100; \	46500	float32_t __s0_99 = __p0_99; \
54783	float64_t __s1_100 = __p1_100; \	46501	float32_t __s1_99 = __p1_99; \
54784	float64x1_t __s2_100 = __p2_100; \	46502	float32x2_t __s2_99 = __p2_99; \
54785	float64_t __ret_100; \	46503	float32_t __ret_99; \
54786	__ret_100 = vfmad_lane_f64(__s0_100, -__s1_100, __s2_100, __p3_100); \	46504	__ret_99 = vfmas_lane_f32(__s0_99, -__s1_99, __s2_99, __p3_99); \
54787	__ret_100; \	46505	__ret_99; \
54788	})	46506	})
54789	#else	46507	#else
54790	#define vfmsd_lane_f64(__p0_101, __p1_101, __p2_101, __p3_101) __extension__ ({ \	46508	#define vfmss_lane_f32(__p0_100, __p1_100, __p2_100, __p3_100) __extension__ ({ \
54791	float64_t __s0_101 = __p0_101; \	46509	float32_t __s0_100 = __p0_100; \
54792	float64_t __s1_101 = __p1_101; \	46510	float32_t __s1_100 = __p1_100; \
54793	float64x1_t __s2_101 = __p2_101; \	46511	float32x2_t __s2_100 = __p2_100; \
54794	float64_t __ret_101; \	46512	float32x2_t __rev2_100; __rev2_100 = __builtin_shufflevector(__s2_100, __s2_100, 1, 0); \
54795	__ret_101 = __noswap_vfmad_lane_f64(__s0_101, -__s1_101, __s2_101, __p3_101); \	46513	float32_t __ret_100; \
54796	__ret_101; \	46514	__ret_100 = __noswap_vfmas_lane_f32(__s0_100, -__s1_100, __rev2_100, __p3_100); \
		46515	__ret_100; \
54797	})	46516	})
54798	#endif	46517	#endif
54799		46518
54800	#ifdef __LITTLE_ENDIAN__	46519	#ifdef __LITTLE_ENDIAN__
54801	#define vfmss_lane_f32(__p0_102, __p1_102, __p2_102, __p3_102) __extension__ ({ \	46520	#define vfmsq_lane_f64(__p0_101, __p1_101, __p2_101, __p3_101) __extension__ ({ \
54802	float32_t __s0_102 = __p0_102; \	46521	float64x2_t __s0_101 = __p0_101; \
54803	float32_t __s1_102 = __p1_102; \	46522	float64x2_t __s1_101 = __p1_101; \
54804	float32x2_t __s2_102 = __p2_102; \	46523	float64x1_t __s2_101 = __p2_101; \
54805	float32_t __ret_102; \	46524	float64x2_t __ret_101; \
54806	__ret_102 = vfmas_lane_f32(__s0_102, -__s1_102, __s2_102, __p3_102); \	46525	__ret_101 = vfmaq_lane_f64(__s0_101, -__s1_101, __s2_101, __p3_101); \
54807	__ret_102; \	46526	__ret_101; \
54808	})	46527	})
54809	#else	46528	#else
54810	#define vfmss_lane_f32(__p0_103, __p1_103, __p2_103, __p3_103) __extension__ ({ \	46529	#define vfmsq_lane_f64(__p0_102, __p1_102, __p2_102, __p3_102) __extension__ ({ \
54811	float32_t __s0_103 = __p0_103; \	46530	float64x2_t __s0_102 = __p0_102; \
54812	float32_t __s1_103 = __p1_103; \	46531	float64x2_t __s1_102 = __p1_102; \
54813	float32x2_t __s2_103 = __p2_103; \	46532	float64x1_t __s2_102 = __p2_102; \
54814	float32x2_t __rev2_103; __rev2_103 = __builtin_shufflevector(__s2_103, __s2_103, 1, 0); \	46533	float64x2_t __rev0_102; __rev0_102 = __builtin_shufflevector(__s0_102, __s0_102, 1, 0); \
54815	float32_t __ret_103; \	46534	float64x2_t __rev1_102; __rev1_102 = __builtin_shufflevector(__s1_102, __s1_102, 1, 0); \
54816	__ret_103 = __noswap_vfmas_lane_f32(__s0_103, -__s1_103, __rev2_103, __p3_103); \	46535	float64x2_t __ret_102; \
54817	__ret_103; \	46536	__ret_102 = __noswap_vfmaq_lane_f64(__rev0_102, -__rev1_102, __s2_102, __p3_102); \
		46537	__ret_102 = __builtin_shufflevector(__ret_102, __ret_102, 1, 0); \
		46538	__ret_102; \
54818	})	46539	})
54819	#endif	46540	#endif
54820		46541
54821	#ifdef __LITTLE_ENDIAN__	46542	#ifdef __LITTLE_ENDIAN__
54822	#define vfmsq_lane_f64(__p0_104, __p1_104, __p2_104, __p3_104) __extension__ ({ \	46543	#define vfmsq_lane_f32(__p0_103, __p1_103, __p2_103, __p3_103) __extension__ ({ \
54823	float64x2_t __s0_104 = __p0_104; \	46544	float32x4_t __s0_103 = __p0_103; \
54824	float64x2_t __s1_104 = __p1_104; \	46545	float32x4_t __s1_103 = __p1_103; \
54825	float64x1_t __s2_104 = __p2_104; \	46546	float32x2_t __s2_103 = __p2_103; \
54826	float64x2_t __ret_104; \	46547	float32x4_t __ret_103; \
54827	__ret_104 = vfmaq_lane_f64(__s0_104, -__s1_104, __s2_104, __p3_104); \	46548	__ret_103 = vfmaq_lane_f32(__s0_103, -__s1_103, __s2_103, __p3_103); \
54828	__ret_104; \	46549	__ret_103; \
54829	})	46550	})
54830	#else	46551	#else
54831	#define vfmsq_lane_f64(__p0_105, __p1_105, __p2_105, __p3_105) __extension__ ({ \	46552	#define vfmsq_lane_f32(__p0_104, __p1_104, __p2_104, __p3_104) __extension__ ({ \
54832	float64x2_t __s0_105 = __p0_105; \	46553	float32x4_t __s0_104 = __p0_104; \
54833	float64x2_t __s1_105 = __p1_105; \	46554	float32x4_t __s1_104 = __p1_104; \
54834	float64x1_t __s2_105 = __p2_105; \	46555	float32x2_t __s2_104 = __p2_104; \
54835	float64x2_t __rev0_105; __rev0_105 = __builtin_shufflevector(__s0_105, __s0_105, 1, 0); \	46556	float32x4_t __rev0_104; __rev0_104 = __builtin_shufflevector(__s0_104, __s0_104, 3, 2, 1, 0); \
54836	float64x2_t __rev1_105; __rev1_105 = __builtin_shufflevector(__s1_105, __s1_105, 1, 0); \	46557	float32x4_t __rev1_104; __rev1_104 = __builtin_shufflevector(__s1_104, __s1_104, 3, 2, 1, 0); \
54837	float64x2_t __ret_105; \	46558	float32x2_t __rev2_104; __rev2_104 = __builtin_shufflevector(__s2_104, __s2_104, 1, 0); \
54838	__ret_105 = __noswap_vfmaq_lane_f64(__rev0_105, -__rev1_105, __s2_105, __p3_105); \	46559	float32x4_t __ret_104; \
54839	__ret_105 = __builtin_shufflevector(__ret_105, __ret_105, 1, 0); \	46560	__ret_104 = __noswap_vfmaq_lane_f32(__rev0_104, -__rev1_104, __rev2_104, __p3_104); \
54840	__ret_105; \	46561	__ret_104 = __builtin_shufflevector(__ret_104, __ret_104, 3, 2, 1, 0); \
		46562	__ret_104; \
54841	})	46563	})
54842	#endif	46564	#endif
54843		46565
		46566	#define vfms_lane_f64(__p0_105, __p1_105, __p2_105, __p3_105) __extension__ ({ \
		46567	float64x1_t __s0_105 = __p0_105; \
		46568	float64x1_t __s1_105 = __p1_105; \
		46569	float64x1_t __s2_105 = __p2_105; \
		46570	float64x1_t __ret_105; \
		46571	__ret_105 = vfma_lane_f64(__s0_105, -__s1_105, __s2_105, __p3_105); \
		46572	__ret_105; \
		46573	})
54844	#ifdef __LITTLE_ENDIAN__	46574	#ifdef __LITTLE_ENDIAN__
54845	#define vfmsq_lane_f32(__p0_106, __p1_106, __p2_106, __p3_106) __extension__ ({ \	46575	#define vfms_lane_f32(__p0_106, __p1_106, __p2_106, __p3_106) __extension__ ({ \
54846	float32x4_t __s0_106 = __p0_106; \	46576	float32x2_t __s0_106 = __p0_106; \
54847	float32x4_t __s1_106 = __p1_106; \	46577	float32x2_t __s1_106 = __p1_106; \
54848	float32x2_t __s2_106 = __p2_106; \	46578	float32x2_t __s2_106 = __p2_106; \
54849	float32x4_t __ret_106; \	46579	float32x2_t __ret_106; \
54850	__ret_106 = vfmaq_lane_f32(__s0_106, -__s1_106, __s2_106, __p3_106); \	46580	__ret_106 = vfma_lane_f32(__s0_106, -__s1_106, __s2_106, __p3_106); \
54851	__ret_106; \	46581	__ret_106; \
54852	})	46582	})
54853	#else	46583	#else
54854	#define vfmsq_lane_f32(__p0_107, __p1_107, __p2_107, __p3_107) __extension__ ({ \	46584	#define vfms_lane_f32(__p0_107, __p1_107, __p2_107, __p3_107) __extension__ ({ \
54855	float32x4_t __s0_107 = __p0_107; \	46585	float32x2_t __s0_107 = __p0_107; \
54856	float32x4_t __s1_107 = __p1_107; \	46586	float32x2_t __s1_107 = __p1_107; \
54857	float32x2_t __s2_107 = __p2_107; \	46587	float32x2_t __s2_107 = __p2_107; \
54858	float32x4_t __rev0_107; __rev0_107 = __builtin_shufflevector(__s0_107, __s0_107, 3, 2, 1, 0); \	46588	float32x2_t __rev0_107; __rev0_107 = __builtin_shufflevector(__s0_107, __s0_107, 1, 0); \
54859	float32x4_t __rev1_107; __rev1_107 = __builtin_shufflevector(__s1_107, __s1_107, 3, 2, 1, 0); \	46589	float32x2_t __rev1_107; __rev1_107 = __builtin_shufflevector(__s1_107, __s1_107, 1, 0); \
54860	float32x2_t __rev2_107; __rev2_107 = __builtin_shufflevector(__s2_107, __s2_107, 1, 0); \	46590	float32x2_t __rev2_107; __rev2_107 = __builtin_shufflevector(__s2_107, __s2_107, 1, 0); \
54861	float32x4_t __ret_107; \	46591	float32x2_t __ret_107; \
54862	__ret_107 = __noswap_vfmaq_lane_f32(__rev0_107, -__rev1_107, __rev2_107, __p3_107); \	46592	__ret_107 = __noswap_vfma_lane_f32(__rev0_107, -__rev1_107, __rev2_107, __p3_107); \
54863	__ret_107 = __builtin_shufflevector(__ret_107, __ret_107, 3, 2, 1, 0); \	46593	__ret_107 = __builtin_shufflevector(__ret_107, __ret_107, 1, 0); \
54864	__ret_107; \	46594	__ret_107; \
54865	})	46595	})
54866	#endif	46596	#endif
54867		46597
54868	#ifdef __LITTLE_ENDIAN__	46598	#ifdef __LITTLE_ENDIAN__
54869	#define vfms_lane_f64(__p0_108, __p1_108, __p2_108, __p3_108) __extension__ ({ \	46599	#define vfmsd_laneq_f64(__p0_108, __p1_108, __p2_108, __p3_108) __extension__ ({ \
54870	float64x1_t __s0_108 = __p0_108; \	46600	float64_t __s0_108 = __p0_108; \
54871	float64x1_t __s1_108 = __p1_108; \	46601	float64_t __s1_108 = __p1_108; \
54872	float64x1_t __s2_108 = __p2_108; \	46602	float64x2_t __s2_108 = __p2_108; \
54873	float64x1_t __ret_108; \	46603	float64_t __ret_108; \
54874	__ret_108 = vfma_lane_f64(__s0_108, -__s1_108, __s2_108, __p3_108); \	46604	__ret_108 = vfmad_laneq_f64(__s0_108, -__s1_108, __s2_108, __p3_108); \
54875	__ret_108; \	46605	__ret_108; \
54876	})	46606	})
54877	#else	46607	#else
54878	#define vfms_lane_f64(__p0_109, __p1_109, __p2_109, __p3_109) __extension__ ({ \	46608	#define vfmsd_laneq_f64(__p0_109, __p1_109, __p2_109, __p3_109) __extension__ ({ \
54879	float64x1_t __s0_109 = __p0_109; \	46609	float64_t __s0_109 = __p0_109; \
54880	float64x1_t __s1_109 = __p1_109; \	46610	float64_t __s1_109 = __p1_109; \
54881	float64x1_t __s2_109 = __p2_109; \	46611	float64x2_t __s2_109 = __p2_109; \
54882	float64x1_t __ret_109; \	46612	float64x2_t __rev2_109; __rev2_109 = __builtin_shufflevector(__s2_109, __s2_109, 1, 0); \
54883	__ret_109 = __noswap_vfma_lane_f64(__s0_109, -__s1_109, __s2_109, __p3_109); \	46613	float64_t __ret_109; \
		46614	__ret_109 = __noswap_vfmad_laneq_f64(__s0_109, -__s1_109, __rev2_109, __p3_109); \
54884	__ret_109; \	46615	__ret_109; \
54885	})	46616	})
54886	#endif	46617	#endif
54887		46618
54888	#ifdef __LITTLE_ENDIAN__	46619	#ifdef __LITTLE_ENDIAN__
54889	#define vfms_lane_f32(__p0_110, __p1_110, __p2_110, __p3_110) __extension__ ({ \	46620	#define vfmss_laneq_f32(__p0_110, __p1_110, __p2_110, __p3_110) __extension__ ({ \
54890	float32x2_t __s0_110 = __p0_110; \	46621	float32_t __s0_110 = __p0_110; \
54891	float32x2_t __s1_110 = __p1_110; \	46622	float32_t __s1_110 = __p1_110; \
54892	float32x2_t __s2_110 = __p2_110; \	46623	float32x4_t __s2_110 = __p2_110; \
54893	float32x2_t __ret_110; \	46624	float32_t __ret_110; \
54894	__ret_110 = vfma_lane_f32(__s0_110, -__s1_110, __s2_110, __p3_110); \	46625	__ret_110 = vfmas_laneq_f32(__s0_110, -__s1_110, __s2_110, __p3_110); \
54895	__ret_110; \	46626	__ret_110; \
54896	})	46627	})
54897	#else	46628	#else
54898	#define vfms_lane_f32(__p0_111, __p1_111, __p2_111, __p3_111) __extension__ ({ \	46629	#define vfmss_laneq_f32(__p0_111, __p1_111, __p2_111, __p3_111) __extension__ ({ \
54899	float32x2_t __s0_111 = __p0_111; \	46630	float32_t __s0_111 = __p0_111; \
54900	float32x2_t __s1_111 = __p1_111; \	46631	float32_t __s1_111 = __p1_111; \
54901	float32x2_t __s2_111 = __p2_111; \	46632	float32x4_t __s2_111 = __p2_111; \
54902	float32x2_t __rev0_111; __rev0_111 = __builtin_shufflevector(__s0_111, __s0_111, 1, 0); \	46633	float32x4_t __rev2_111; __rev2_111 = __builtin_shufflevector(__s2_111, __s2_111, 3, 2, 1, 0); \
54903	float32x2_t __rev1_111; __rev1_111 = __builtin_shufflevector(__s1_111, __s1_111, 1, 0); \	46634	float32_t __ret_111; \
54904	float32x2_t __rev2_111; __rev2_111 = __builtin_shufflevector(__s2_111, __s2_111, 1, 0); \	46635	__ret_111 = __noswap_vfmas_laneq_f32(__s0_111, -__s1_111, __rev2_111, __p3_111); \
54905	float32x2_t __ret_111; \
54906	__ret_111 = __noswap_vfma_lane_f32(__rev0_111, -__rev1_111, __rev2_111, __p3_111); \
54907	__ret_111 = __builtin_shufflevector(__ret_111, __ret_111, 1, 0); \
54908	__ret_111; \	46636	__ret_111; \
54909	})	46637	})
54910	#endif	46638	#endif
54911		46639
54912	#ifdef __LITTLE_ENDIAN__	46640	#ifdef __LITTLE_ENDIAN__
54913	#define vfmsd_laneq_f64(__p0_112, __p1_112, __p2_112, __p3_112) __extension__ ({ \	46641	#define vfmsq_laneq_f64(__p0_112, __p1_112, __p2_112, __p3_112) __extension__ ({ \
54914	float64_t __s0_112 = __p0_112; \	46642	float64x2_t __s0_112 = __p0_112; \
54915	float64_t __s1_112 = __p1_112; \	46643	float64x2_t __s1_112 = __p1_112; \
54916	float64x2_t __s2_112 = __p2_112; \	46644	float64x2_t __s2_112 = __p2_112; \
54917	float64_t __ret_112; \	46645	float64x2_t __ret_112; \
54918	__ret_112 = vfmad_laneq_f64(__s0_112, -__s1_112, __s2_112, __p3_112); \	46646	__ret_112 = vfmaq_laneq_f64(__s0_112, -__s1_112, __s2_112, __p3_112); \
54919	__ret_112; \	46647	__ret_112; \
54920	})	46648	})
54921	#else	46649	#else
54922	#define vfmsd_laneq_f64(__p0_113, __p1_113, __p2_113, __p3_113) __extension__ ({ \	46650	#define vfmsq_laneq_f64(__p0_113, __p1_113, __p2_113, __p3_113) __extension__ ({ \
54923	float64_t __s0_113 = __p0_113; \	46651	float64x2_t __s0_113 = __p0_113; \
54924	float64_t __s1_113 = __p1_113; \	46652	float64x2_t __s1_113 = __p1_113; \
54925	float64x2_t __s2_113 = __p2_113; \	46653	float64x2_t __s2_113 = __p2_113; \
		46654	float64x2_t __rev0_113; __rev0_113 = __builtin_shufflevector(__s0_113, __s0_113, 1, 0); \
		46655	float64x2_t __rev1_113; __rev1_113 = __builtin_shufflevector(__s1_113, __s1_113, 1, 0); \
54926	float64x2_t __rev2_113; __rev2_113 = __builtin_shufflevector(__s2_113, __s2_113, 1, 0); \	46656	float64x2_t __rev2_113; __rev2_113 = __builtin_shufflevector(__s2_113, __s2_113, 1, 0); \
54927	float64_t __ret_113; \	46657	float64x2_t __ret_113; \
54928	__ret_113 = __noswap_vfmad_laneq_f64(__s0_113, -__s1_113, __rev2_113, __p3_113); \	46658	__ret_113 = __noswap_vfmaq_laneq_f64(__rev0_113, -__rev1_113, __rev2_113, __p3_113); \
		46659	__ret_113 = __builtin_shufflevector(__ret_113, __ret_113, 1, 0); \
54929	__ret_113; \	46660	__ret_113; \
54930	})	46661	})
54931	#endif	46662	#endif
54932		46663
54933	#ifdef __LITTLE_ENDIAN__	46664	#ifdef __LITTLE_ENDIAN__
54934	#define vfmss_laneq_f32(__p0_114, __p1_114, __p2_114, __p3_114) __extension__ ({ \	46665	#define vfmsq_laneq_f32(__p0_114, __p1_114, __p2_114, __p3_114) __extension__ ({ \
54935	float32_t __s0_114 = __p0_114; \	46666	float32x4_t __s0_114 = __p0_114; \
54936	float32_t __s1_114 = __p1_114; \	46667	float32x4_t __s1_114 = __p1_114; \
54937	float32x4_t __s2_114 = __p2_114; \	46668	float32x4_t __s2_114 = __p2_114; \
54938	float32_t __ret_114; \	46669	float32x4_t __ret_114; \
54939	__ret_114 = vfmas_laneq_f32(__s0_114, -__s1_114, __s2_114, __p3_114); \	46670	__ret_114 = vfmaq_laneq_f32(__s0_114, -__s1_114, __s2_114, __p3_114); \
54940	__ret_114; \	46671	__ret_114; \
54941	})	46672	})
54942	#else	46673	#else
54943	#define vfmss_laneq_f32(__p0_115, __p1_115, __p2_115, __p3_115) __extension__ ({ \	46674	#define vfmsq_laneq_f32(__p0_115, __p1_115, __p2_115, __p3_115) __extension__ ({ \
54944	float32_t __s0_115 = __p0_115; \	46675	float32x4_t __s0_115 = __p0_115; \
54945	float32_t __s1_115 = __p1_115; \	46676	float32x4_t __s1_115 = __p1_115; \
54946	float32x4_t __s2_115 = __p2_115; \	46677	float32x4_t __s2_115 = __p2_115; \
		46678	float32x4_t __rev0_115; __rev0_115 = __builtin_shufflevector(__s0_115, __s0_115, 3, 2, 1, 0); \
		46679	float32x4_t __rev1_115; __rev1_115 = __builtin_shufflevector(__s1_115, __s1_115, 3, 2, 1, 0); \
54947	float32x4_t __rev2_115; __rev2_115 = __builtin_shufflevector(__s2_115, __s2_115, 3, 2, 1, 0); \	46680	float32x4_t __rev2_115; __rev2_115 = __builtin_shufflevector(__s2_115, __s2_115, 3, 2, 1, 0); \
54948	float32_t __ret_115; \	46681	float32x4_t __ret_115; \
54949	__ret_115 = __noswap_vfmas_laneq_f32(__s0_115, -__s1_115, __rev2_115, __p3_115); \	46682	__ret_115 = __noswap_vfmaq_laneq_f32(__rev0_115, -__rev1_115, __rev2_115, __p3_115); \
		46683	__ret_115 = __builtin_shufflevector(__ret_115, __ret_115, 3, 2, 1, 0); \
54950	__ret_115; \	46684	__ret_115; \
54951	})	46685	})
54952	#endif	46686	#endif
54953		46687
54954	#ifdef __LITTLE_ENDIAN__	46688	#ifdef __LITTLE_ENDIAN__
54955	#define vfmsq_laneq_f64(__p0_116, __p1_116, __p2_116, __p3_116) __extension__ ({ \	46689	#define vfms_laneq_f64(__p0_116, __p1_116, __p2_116, __p3_116) __extension__ ({ \
54956	float64x2_t __s0_116 = __p0_116; \	46690	float64x1_t __s0_116 = __p0_116; \
54957	float64x2_t __s1_116 = __p1_116; \	46691	float64x1_t __s1_116 = __p1_116; \
54958	float64x2_t __s2_116 = __p2_116; \	46692	float64x2_t __s2_116 = __p2_116; \
54959	float64x2_t __ret_116; \	46693	float64x1_t __ret_116; \
54960	__ret_116 = vfmaq_laneq_f64(__s0_116, -__s1_116, __s2_116, __p3_116); \	46694	__ret_116 = vfma_laneq_f64(__s0_116, -__s1_116, __s2_116, __p3_116); \
54961	__ret_116; \	46695	__ret_116; \
54962	})	46696	})
54963	#else	46697	#else
54964	#define vfmsq_laneq_f64(__p0_117, __p1_117, __p2_117, __p3_117) __extension__ ({ \	46698	#define vfms_laneq_f64(__p0_117, __p1_117, __p2_117, __p3_117) __extension__ ({ \
54965	float64x2_t __s0_117 = __p0_117; \	46699	float64x1_t __s0_117 = __p0_117; \
54966	float64x2_t __s1_117 = __p1_117; \	46700	float64x1_t __s1_117 = __p1_117; \
54967	float64x2_t __s2_117 = __p2_117; \	46701	float64x2_t __s2_117 = __p2_117; \
54968	float64x2_t __rev0_117; __rev0_117 = __builtin_shufflevector(__s0_117, __s0_117, 1, 0); \
54969	float64x2_t __rev1_117; __rev1_117 = __builtin_shufflevector(__s1_117, __s1_117, 1, 0); \
54970	float64x2_t __rev2_117; __rev2_117 = __builtin_shufflevector(__s2_117, __s2_117, 1, 0); \	46702	float64x2_t __rev2_117; __rev2_117 = __builtin_shufflevector(__s2_117, __s2_117, 1, 0); \
54971	float64x2_t __ret_117; \	46703	float64x1_t __ret_117; \
54972	__ret_117 = __noswap_vfmaq_laneq_f64(__rev0_117, -__rev1_117, __rev2_117, __p3_117); \	46704	__ret_117 = __noswap_vfma_laneq_f64(__s0_117, -__s1_117, __rev2_117, __p3_117); \
54973	__ret_117 = __builtin_shufflevector(__ret_117, __ret_117, 1, 0); \
54974	__ret_117; \	46705	__ret_117; \
54975	})	46706	})
54976	#endif	46707	#endif
54977		46708
54978	#ifdef __LITTLE_ENDIAN__	46709	#ifdef __LITTLE_ENDIAN__
54979	#define vfmsq_laneq_f32(__p0_118, __p1_118, __p2_118, __p3_118) __extension__ ({ \	46710	#define vfms_laneq_f32(__p0_118, __p1_118, __p2_118, __p3_118) __extension__ ({ \
54980	float32x4_t __s0_118 = __p0_118; \	46711	float32x2_t __s0_118 = __p0_118; \
54981	float32x4_t __s1_118 = __p1_118; \	46712	float32x2_t __s1_118 = __p1_118; \
54982	float32x4_t __s2_118 = __p2_118; \	46713	float32x4_t __s2_118 = __p2_118; \
54983	float32x4_t __ret_118; \	46714	float32x2_t __ret_118; \
54984	__ret_118 = vfmaq_laneq_f32(__s0_118, -__s1_118, __s2_118, __p3_118); \	46715	__ret_118 = vfma_laneq_f32(__s0_118, -__s1_118, __s2_118, __p3_118); \
54985	__ret_118; \	46716	__ret_118; \
54986	})	46717	})
54987	#else	46718	#else
54988	#define vfmsq_laneq_f32(__p0_119, __p1_119, __p2_119, __p3_119) __extension__ ({ \	46719	#define vfms_laneq_f32(__p0_119, __p1_119, __p2_119, __p3_119) __extension__ ({ \
54989	float32x4_t __s0_119 = __p0_119; \	46720	float32x2_t __s0_119 = __p0_119; \
54990	float32x4_t __s1_119 = __p1_119; \	46721	float32x2_t __s1_119 = __p1_119; \
54991	float32x4_t __s2_119 = __p2_119; \	46722	float32x4_t __s2_119 = __p2_119; \
54992	float32x4_t __rev0_119; __rev0_119 = __builtin_shufflevector(__s0_119, __s0_119, 3, 2, 1, 0); \	46723	float32x2_t __rev0_119; __rev0_119 = __builtin_shufflevector(__s0_119, __s0_119, 1, 0); \
54993	float32x4_t __rev1_119; __rev1_119 = __builtin_shufflevector(__s1_119, __s1_119, 3, 2, 1, 0); \	46724	float32x2_t __rev1_119; __rev1_119 = __builtin_shufflevector(__s1_119, __s1_119, 1, 0); \
54994	float32x4_t __rev2_119; __rev2_119 = __builtin_shufflevector(__s2_119, __s2_119, 3, 2, 1, 0); \	46725	float32x4_t __rev2_119; __rev2_119 = __builtin_shufflevector(__s2_119, __s2_119, 3, 2, 1, 0); \
54995	float32x4_t __ret_119; \	46726	float32x2_t __ret_119; \
54996	__ret_119 = __noswap_vfmaq_laneq_f32(__rev0_119, -__rev1_119, __rev2_119, __p3_119); \	46727	__ret_119 = __noswap_vfma_laneq_f32(__rev0_119, -__rev1_119, __rev2_119, __p3_119); \
54997	__ret_119 = __builtin_shufflevector(__ret_119, __ret_119, 3, 2, 1, 0); \	46728	__ret_119 = __builtin_shufflevector(__ret_119, __ret_119, 1, 0); \
54998	__ret_119; \	46729	__ret_119; \
54999	})	46730	})
55000	#endif	46731	#endif
55001		46732
55002	#ifdef __LITTLE_ENDIAN__
55003	#define vfms_laneq_f64(__p0_120, __p1_120, __p2_120, __p3_120) __extension__ ({ \
55004	float64x1_t __s0_120 = __p0_120; \
55005	float64x1_t __s1_120 = __p1_120; \
55006	float64x2_t __s2_120 = __p2_120; \
55007	float64x1_t __ret_120; \
55008	__ret_120 = vfma_laneq_f64(__s0_120, -__s1_120, __s2_120, __p3_120); \
55009	__ret_120; \
55010	})
55011	#else
55012	#define vfms_laneq_f64(__p0_121, __p1_121, __p2_121, __p3_121) __extension__ ({ \
55013	float64x1_t __s0_121 = __p0_121; \
55014	float64x1_t __s1_121 = __p1_121; \
55015	float64x2_t __s2_121 = __p2_121; \
55016	float64x2_t __rev2_121; __rev2_121 = __builtin_shufflevector(__s2_121, __s2_121, 1, 0); \
55017	float64x1_t __ret_121; \
55018	__ret_121 = __noswap_vfma_laneq_f64(__s0_121, -__s1_121, __rev2_121, __p3_121); \
55019	__ret_121; \
55020	})
55021	#endif
55022
55023	#ifdef __LITTLE_ENDIAN__
55024	#define vfms_laneq_f32(__p0_122, __p1_122, __p2_122, __p3_122) __extension__ ({ \
55025	float32x2_t __s0_122 = __p0_122; \
55026	float32x2_t __s1_122 = __p1_122; \
55027	float32x4_t __s2_122 = __p2_122; \
55028	float32x2_t __ret_122; \
55029	__ret_122 = vfma_laneq_f32(__s0_122, -__s1_122, __s2_122, __p3_122); \
55030	__ret_122; \
55031	})
55032	#else
55033	#define vfms_laneq_f32(__p0_123, __p1_123, __p2_123, __p3_123) __extension__ ({ \
55034	float32x2_t __s0_123 = __p0_123; \
55035	float32x2_t __s1_123 = __p1_123; \
55036	float32x4_t __s2_123 = __p2_123; \
55037	float32x2_t __rev0_123; __rev0_123 = __builtin_shufflevector(__s0_123, __s0_123, 1, 0); \
55038	float32x2_t __rev1_123; __rev1_123 = __builtin_shufflevector(__s1_123, __s1_123, 1, 0); \
55039	float32x4_t __rev2_123; __rev2_123 = __builtin_shufflevector(__s2_123, __s2_123, 3, 2, 1, 0); \
55040	float32x2_t __ret_123; \
55041	__ret_123 = __noswap_vfma_laneq_f32(__rev0_123, -__rev1_123, __rev2_123, __p3_123); \
55042	__ret_123 = __builtin_shufflevector(__ret_123, __ret_123, 1, 0); \
55043	__ret_123; \
55044	})
55045	#endif
55046
55047	#ifdef __LITTLE_ENDIAN__	46733	#ifdef __LITTLE_ENDIAN__
55048	__ai float64x2_t vfmsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {	46734	__ai float64x2_t vfmsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2) {
55049	float64x2_t __ret;	46735	float64x2_t __ret;
...	@@ -55078,20 +46764,11 @@ __ai float32x4_t vfmsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2)	...	@@ -55078,20 +46764,11 @@ __ai float32x4_t vfmsq_n_f32(float32x4_t __p0, float32x4_t __p1, float32_t __p2)
55078	}	46764	}
55079	#endif	46765	#endif
55080		46766
55081	#ifdef __LITTLE_ENDIAN__
55082	__ai float64x1_t vfms_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {	46767	__ai float64x1_t vfms_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {
55083	float64x1_t __ret;	46768	float64x1_t __ret;
55084	__ret = vfma_f64(__p0, -__p1, (float64x1_t) {__p2});	46769	__ret = vfma_f64(__p0, -__p1, (float64x1_t) {__p2});
55085	return __ret;	46770	return __ret;
55086	}	46771	}
55087	#else
55088	__ai float64x1_t vfms_n_f64(float64x1_t __p0, float64x1_t __p1, float64_t __p2) {
55089	float64x1_t __ret;
55090	__ret = __noswap_vfma_f64(__p0, -__p1, (float64x1_t) {__p2});
55091	return __ret;
55092	}
55093	#endif
55094
55095	#ifdef __LITTLE_ENDIAN__	46772	#ifdef __LITTLE_ENDIAN__
55096	__ai float32x2_t vfms_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {	46773	__ai float32x2_t vfms_n_f32(float32x2_t __p0, float32x2_t __p1, float32_t __p2) {
55097	float32x2_t __ret;	46774	float32x2_t __ret;
...	@@ -55144,33 +46821,17 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {	...	@@ -55144,33 +46821,17 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {
55144	}	46821	}
55145	#endif	46822	#endif
55146		46823
55147	#ifdef __LITTLE_ENDIAN__
55148	#define vget_lane_p64(__p0, __p1) __extension__ ({ \	46824	#define vget_lane_p64(__p0, __p1) __extension__ ({ \
55149	poly64x1_t __s0 = __p0; \	46825	poly64x1_t __s0 = __p0; \
55150	poly64_t __ret; \	46826	poly64_t __ret; \
55151	__ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \	46827	__ret = (poly64_t) __builtin_neon_vget_lane_i64((poly64x1_t)__s0, __p1); \
55152	__ret; \	46828	__ret; \
55153	})	46829	})
55154	#else
55155	#define vget_lane_p64(__p0, __p1) __extension__ ({ \
55156	poly64x1_t __s0 = __p0; \
55157	poly64_t __ret; \
55158	__ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
55159	__ret; \
55160	})
55161	#define __noswap_vget_lane_p64(__p0, __p1) __extension__ ({ \
55162	poly64x1_t __s0 = __p0; \
55163	poly64_t __ret; \
55164	__ret = (poly64_t) __builtin_neon_vget_lane_i64((int8x8_t)__s0, __p1); \
55165	__ret; \
55166	})
55167	#endif
55168
55169	#ifdef __LITTLE_ENDIAN__	46830	#ifdef __LITTLE_ENDIAN__
55170	#define vgetq_lane_p64(__p0, __p1) __extension__ ({ \	46831	#define vgetq_lane_p64(__p0, __p1) __extension__ ({ \
55171	poly64x2_t __s0 = __p0; \	46832	poly64x2_t __s0 = __p0; \
55172	poly64_t __ret; \	46833	poly64_t __ret; \
55173	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	46834	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((poly64x2_t)__s0, __p1); \
55174	__ret; \	46835	__ret; \
55175	})	46836	})
55176	#else	46837	#else
...	@@ -55178,13 +46839,13 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {	...	@@ -55178,13 +46839,13 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {
55178	poly64x2_t __s0 = __p0; \	46839	poly64x2_t __s0 = __p0; \
55179	poly64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	46840	poly64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
55180	poly64_t __ret; \	46841	poly64_t __ret; \
55181	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__rev0, __p1); \	46842	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((poly64x2_t)__rev0, __p1); \
55182	__ret; \	46843	__ret; \
55183	})	46844	})
55184	#define __noswap_vgetq_lane_p64(__p0, __p1) __extension__ ({ \	46845	#define __noswap_vgetq_lane_p64(__p0, __p1) __extension__ ({ \
55185	poly64x2_t __s0 = __p0; \	46846	poly64x2_t __s0 = __p0; \
55186	poly64_t __ret; \	46847	poly64_t __ret; \
55187	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((int8x16_t)__s0, __p1); \	46848	__ret = (poly64_t) __builtin_neon_vgetq_lane_i64((poly64x2_t)__s0, __p1); \
55188	__ret; \	46849	__ret; \
55189	})	46850	})
55190	#endif	46851	#endif
...	@@ -55193,7 +46854,7 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {	...	@@ -55193,7 +46854,7 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {
55193	#define vgetq_lane_f64(__p0, __p1) __extension__ ({ \	46854	#define vgetq_lane_f64(__p0, __p1) __extension__ ({ \
55194	float64x2_t __s0 = __p0; \	46855	float64x2_t __s0 = __p0; \
55195	float64_t __ret; \	46856	float64_t __ret; \
55196	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__s0, __p1); \	46857	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((float64x2_t)__s0, __p1); \
55197	__ret; \	46858	__ret; \
55198	})	46859	})
55199	#else	46860	#else
...	@@ -55201,39 +46862,23 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {	...	@@ -55201,39 +46862,23 @@ __ai float64x1_t vget_high_f64(float64x2_t __p0) {
55201	float64x2_t __s0 = __p0; \	46862	float64x2_t __s0 = __p0; \
55202	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \	46863	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__s0, __s0, 1, 0); \
55203	float64_t __ret; \	46864	float64_t __ret; \
55204	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__rev0, __p1); \	46865	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((float64x2_t)__rev0, __p1); \
55205	__ret; \	46866	__ret; \
55206	})	46867	})
55207	#define __noswap_vgetq_lane_f64(__p0, __p1) __extension__ ({ \	46868	#define __noswap_vgetq_lane_f64(__p0, __p1) __extension__ ({ \
55208	float64x2_t __s0 = __p0; \	46869	float64x2_t __s0 = __p0; \
55209	float64_t __ret; \	46870	float64_t __ret; \
55210	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((int8x16_t)__s0, __p1); \	46871	__ret = (float64_t) __builtin_neon_vgetq_lane_f64((float64x2_t)__s0, __p1); \
55211	__ret; \	46872	__ret; \
55212	})	46873	})
55213	#endif	46874	#endif
55214		46875
55215	#ifdef __LITTLE_ENDIAN__
55216	#define vget_lane_f64(__p0, __p1) __extension__ ({ \	46876	#define vget_lane_f64(__p0, __p1) __extension__ ({ \
55217	float64x1_t __s0 = __p0; \	46877	float64x1_t __s0 = __p0; \
55218	float64_t __ret; \	46878	float64_t __ret; \
55219	__ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \	46879	__ret = (float64_t) __builtin_neon_vget_lane_f64((float64x1_t)__s0, __p1); \
55220	__ret; \
55221	})
55222	#else
55223	#define vget_lane_f64(__p0, __p1) __extension__ ({ \
55224	float64x1_t __s0 = __p0; \
55225	float64_t __ret; \
55226	__ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
55227	__ret; \
55228	})
55229	#define __noswap_vget_lane_f64(__p0, __p1) __extension__ ({ \
55230	float64x1_t __s0 = __p0; \
55231	float64_t __ret; \
55232	__ret = (float64_t) __builtin_neon_vget_lane_f64((int8x8_t)__s0, __p1); \
55233	__ret; \	46880	__ret; \
55234	})	46881	})
55235	#endif
55236
55237	#ifdef __LITTLE_ENDIAN__	46882	#ifdef __LITTLE_ENDIAN__
55238	__ai poly64x1_t vget_low_p64(poly64x2_t __p0) {	46883	__ai poly64x1_t vget_low_p64(poly64x2_t __p0) {
55239	poly64x1_t __ret;	46884	poly64x1_t __ret;
...	@@ -55264,20 +46909,11 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55264,20 +46909,11 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55264	}	46909	}
55265	#endif	46910	#endif
55266		46911
55267	#ifdef __LITTLE_ENDIAN__
55268	#define vld1_p64(__p0) __extension__ ({ \	46912	#define vld1_p64(__p0) __extension__ ({ \
55269	poly64x1_t __ret; \	46913	poly64x1_t __ret; \
55270	__ret = (poly64x1_t) __builtin_neon_vld1_v(__p0, 6); \	46914	__ret = (poly64x1_t) __builtin_neon_vld1_v(__p0, 6); \
55271	__ret; \	46915	__ret; \
55272	})	46916	})
55273	#else
55274	#define vld1_p64(__p0) __extension__ ({ \
55275	poly64x1_t __ret; \
55276	__ret = (poly64x1_t) __builtin_neon_vld1_v(__p0, 6); \
55277	__ret; \
55278	})
55279	#endif
55280
55281	#ifdef __LITTLE_ENDIAN__	46917	#ifdef __LITTLE_ENDIAN__
55282	#define vld1q_p64(__p0) __extension__ ({ \	46918	#define vld1q_p64(__p0) __extension__ ({ \
55283	poly64x2_t __ret; \	46919	poly64x2_t __ret; \
...	@@ -55308,34 +46944,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55308,34 +46944,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55308	})	46944	})
55309	#endif	46945	#endif
55310		46946
55311	#ifdef __LITTLE_ENDIAN__
55312	#define vld1_f64(__p0) __extension__ ({ \	46947	#define vld1_f64(__p0) __extension__ ({ \
55313	float64x1_t __ret; \	46948	float64x1_t __ret; \
55314	__ret = (float64x1_t) __builtin_neon_vld1_v(__p0, 10); \	46949	__ret = (float64x1_t) __builtin_neon_vld1_v(__p0, 10); \
55315	__ret; \	46950	__ret; \
55316	})	46951	})
55317	#else
55318	#define vld1_f64(__p0) __extension__ ({ \
55319	float64x1_t __ret; \
55320	__ret = (float64x1_t) __builtin_neon_vld1_v(__p0, 10); \
55321	__ret; \
55322	})
55323	#endif
55324
55325	#ifdef __LITTLE_ENDIAN__
55326	#define vld1_dup_p64(__p0) __extension__ ({ \	46952	#define vld1_dup_p64(__p0) __extension__ ({ \
55327	poly64x1_t __ret; \	46953	poly64x1_t __ret; \
55328	__ret = (poly64x1_t) __builtin_neon_vld1_dup_v(__p0, 6); \	46954	__ret = (poly64x1_t) __builtin_neon_vld1_dup_v(__p0, 6); \
55329	__ret; \	46955	__ret; \
55330	})	46956	})
55331	#else
55332	#define vld1_dup_p64(__p0) __extension__ ({ \
55333	poly64x1_t __ret; \
55334	__ret = (poly64x1_t) __builtin_neon_vld1_dup_v(__p0, 6); \
55335	__ret; \
55336	})
55337	#endif
55338
55339	#ifdef __LITTLE_ENDIAN__	46957	#ifdef __LITTLE_ENDIAN__
55340	#define vld1q_dup_p64(__p0) __extension__ ({ \	46958	#define vld1q_dup_p64(__p0) __extension__ ({ \
55341	poly64x2_t __ret; \	46959	poly64x2_t __ret; \
...	@@ -55366,36 +46984,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55366,36 +46984,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55366	})	46984	})
55367	#endif	46985	#endif
55368		46986
55369	#ifdef __LITTLE_ENDIAN__
55370	#define vld1_dup_f64(__p0) __extension__ ({ \	46987	#define vld1_dup_f64(__p0) __extension__ ({ \
55371	float64x1_t __ret; \	46988	float64x1_t __ret; \
55372	__ret = (float64x1_t) __builtin_neon_vld1_dup_v(__p0, 10); \	46989	__ret = (float64x1_t) __builtin_neon_vld1_dup_v(__p0, 10); \
55373	__ret; \	46990	__ret; \
55374	})	46991	})
55375	#else
55376	#define vld1_dup_f64(__p0) __extension__ ({ \
55377	float64x1_t __ret; \
55378	__ret = (float64x1_t) __builtin_neon_vld1_dup_v(__p0, 10); \
55379	__ret; \
55380	})
55381	#endif
55382
55383	#ifdef __LITTLE_ENDIAN__
55384	#define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
55385	poly64x1_t __s1 = __p1; \
55386	poly64x1_t __ret; \
55387	__ret = (poly64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
55388	__ret; \
55389	})
55390	#else
55391	#define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({ \	46992	#define vld1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
55392	poly64x1_t __s1 = __p1; \	46993	poly64x1_t __s1 = __p1; \
55393	poly64x1_t __ret; \	46994	poly64x1_t __ret; \
55394	__ret = (poly64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \	46995	__ret = (poly64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
55395	__ret; \	46996	__ret; \
55396	})	46997	})
55397	#endif
55398
55399	#ifdef __LITTLE_ENDIAN__	46998	#ifdef __LITTLE_ENDIAN__
55400	#define vld1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \	46999	#define vld1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
55401	poly64x2_t __s1 = __p1; \	47000	poly64x2_t __s1 = __p1; \
...	@@ -55432,36 +47031,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55432,36 +47031,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55432	})	47031	})
55433	#endif	47032	#endif
55434		47033
55435	#ifdef __LITTLE_ENDIAN__
55436	#define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({ \	47034	#define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
55437	float64x1_t __s1 = __p1; \	47035	float64x1_t __s1 = __p1; \
55438	float64x1_t __ret; \	47036	float64x1_t __ret; \
55439	__ret = (float64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \	47037	__ret = (float64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
55440	__ret; \	47038	__ret; \
55441	})	47039	})
55442	#else
55443	#define vld1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
55444	float64x1_t __s1 = __p1; \
55445	float64x1_t __ret; \
55446	__ret = (float64x1_t) __builtin_neon_vld1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
55447	__ret; \
55448	})
55449	#endif
55450
55451	#ifdef __LITTLE_ENDIAN__
55452	#define vld1_p64_x2(__p0) __extension__ ({ \	47040	#define vld1_p64_x2(__p0) __extension__ ({ \
55453	poly64x1x2_t __ret; \	47041	poly64x1x2_t __ret; \
55454	__builtin_neon_vld1_x2_v(&__ret, __p0, 6); \	47042	__builtin_neon_vld1_x2_v(&__ret, __p0, 6); \
55455	__ret; \	47043	__ret; \
55456	})	47044	})
55457	#else
55458	#define vld1_p64_x2(__p0) __extension__ ({ \
55459	poly64x1x2_t __ret; \
55460	__builtin_neon_vld1_x2_v(&__ret, __p0, 6); \
55461	__ret; \
55462	})
55463	#endif
55464
55465	#ifdef __LITTLE_ENDIAN__	47045	#ifdef __LITTLE_ENDIAN__
55466	#define vld1q_p64_x2(__p0) __extension__ ({ \	47046	#define vld1q_p64_x2(__p0) __extension__ ({ \
55467	poly64x2x2_t __ret; \	47047	poly64x2x2_t __ret; \
...	@@ -55496,34 +47076,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55496,34 +47076,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55496	})	47076	})
55497	#endif	47077	#endif
55498		47078
55499	#ifdef __LITTLE_ENDIAN__
55500	#define vld1_f64_x2(__p0) __extension__ ({ \	47079	#define vld1_f64_x2(__p0) __extension__ ({ \
55501	float64x1x2_t __ret; \	47080	float64x1x2_t __ret; \
55502	__builtin_neon_vld1_x2_v(&__ret, __p0, 10); \	47081	__builtin_neon_vld1_x2_v(&__ret, __p0, 10); \
55503	__ret; \	47082	__ret; \
55504	})	47083	})
55505	#else
55506	#define vld1_f64_x2(__p0) __extension__ ({ \
55507	float64x1x2_t __ret; \
55508	__builtin_neon_vld1_x2_v(&__ret, __p0, 10); \
55509	__ret; \
55510	})
55511	#endif
55512
55513	#ifdef __LITTLE_ENDIAN__
55514	#define vld1_p64_x3(__p0) __extension__ ({ \	47084	#define vld1_p64_x3(__p0) __extension__ ({ \
55515	poly64x1x3_t __ret; \	47085	poly64x1x3_t __ret; \
55516	__builtin_neon_vld1_x3_v(&__ret, __p0, 6); \	47086	__builtin_neon_vld1_x3_v(&__ret, __p0, 6); \
55517	__ret; \	47087	__ret; \
55518	})	47088	})
55519	#else
55520	#define vld1_p64_x3(__p0) __extension__ ({ \
55521	poly64x1x3_t __ret; \
55522	__builtin_neon_vld1_x3_v(&__ret, __p0, 6); \
55523	__ret; \
55524	})
55525	#endif
55526
55527	#ifdef __LITTLE_ENDIAN__	47089	#ifdef __LITTLE_ENDIAN__
55528	#define vld1q_p64_x3(__p0) __extension__ ({ \	47090	#define vld1q_p64_x3(__p0) __extension__ ({ \
55529	poly64x2x3_t __ret; \	47091	poly64x2x3_t __ret; \
...	@@ -55560,34 +47122,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55560,34 +47122,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55560	})	47122	})
55561	#endif	47123	#endif
55562		47124
55563	#ifdef __LITTLE_ENDIAN__
55564	#define vld1_f64_x3(__p0) __extension__ ({ \
55565	float64x1x3_t __ret; \
55566	__builtin_neon_vld1_x3_v(&__ret, __p0, 10); \
55567	__ret; \
55568	})
55569	#else
55570	#define vld1_f64_x3(__p0) __extension__ ({ \	47125	#define vld1_f64_x3(__p0) __extension__ ({ \
55571	float64x1x3_t __ret; \	47126	float64x1x3_t __ret; \
55572	__builtin_neon_vld1_x3_v(&__ret, __p0, 10); \	47127	__builtin_neon_vld1_x3_v(&__ret, __p0, 10); \
55573	__ret; \	47128	__ret; \
55574	})	47129	})
55575	#endif
55576
55577	#ifdef __LITTLE_ENDIAN__
55578	#define vld1_p64_x4(__p0) __extension__ ({ \
55579	poly64x1x4_t __ret; \
55580	__builtin_neon_vld1_x4_v(&__ret, __p0, 6); \
55581	__ret; \
55582	})
55583	#else
55584	#define vld1_p64_x4(__p0) __extension__ ({ \	47130	#define vld1_p64_x4(__p0) __extension__ ({ \
55585	poly64x1x4_t __ret; \	47131	poly64x1x4_t __ret; \
55586	__builtin_neon_vld1_x4_v(&__ret, __p0, 6); \	47132	__builtin_neon_vld1_x4_v(&__ret, __p0, 6); \
55587	__ret; \	47133	__ret; \
55588	})	47134	})
55589	#endif
55590
55591	#ifdef __LITTLE_ENDIAN__	47135	#ifdef __LITTLE_ENDIAN__
55592	#define vld1q_p64_x4(__p0) __extension__ ({ \	47136	#define vld1q_p64_x4(__p0) __extension__ ({ \
55593	poly64x2x4_t __ret; \	47137	poly64x2x4_t __ret; \
...	@@ -55626,34 +47170,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55626,34 +47170,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55626	})	47170	})
55627	#endif	47171	#endif
55628		47172
55629	#ifdef __LITTLE_ENDIAN__
55630	#define vld1_f64_x4(__p0) __extension__ ({ \
55631	float64x1x4_t __ret; \
55632	__builtin_neon_vld1_x4_v(&__ret, __p0, 10); \
55633	__ret; \
55634	})
55635	#else
55636	#define vld1_f64_x4(__p0) __extension__ ({ \	47173	#define vld1_f64_x4(__p0) __extension__ ({ \
55637	float64x1x4_t __ret; \	47174	float64x1x4_t __ret; \
55638	__builtin_neon_vld1_x4_v(&__ret, __p0, 10); \	47175	__builtin_neon_vld1_x4_v(&__ret, __p0, 10); \
55639	__ret; \	47176	__ret; \
55640	})	47177	})
55641	#endif
55642
55643	#ifdef __LITTLE_ENDIAN__
55644	#define vld2_p64(__p0) __extension__ ({ \	47178	#define vld2_p64(__p0) __extension__ ({ \
55645	poly64x1x2_t __ret; \	47179	poly64x1x2_t __ret; \
55646	__builtin_neon_vld2_v(&__ret, __p0, 6); \	47180	__builtin_neon_vld2_v(&__ret, __p0, 6); \
55647	__ret; \	47181	__ret; \
55648	})	47182	})
55649	#else
55650	#define vld2_p64(__p0) __extension__ ({ \
55651	poly64x1x2_t __ret; \
55652	__builtin_neon_vld2_v(&__ret, __p0, 6); \
55653	__ret; \
55654	})
55655	#endif
55656
55657	#ifdef __LITTLE_ENDIAN__	47183	#ifdef __LITTLE_ENDIAN__
55658	#define vld2q_p64(__p0) __extension__ ({ \	47184	#define vld2q_p64(__p0) __extension__ ({ \
55659	poly64x2x2_t __ret; \	47185	poly64x2x2_t __ret; \
...	@@ -55722,34 +47248,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55722,34 +47248,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55722	})	47248	})
55723	#endif	47249	#endif
55724		47250
55725	#ifdef __LITTLE_ENDIAN__
55726	#define vld2_f64(__p0) __extension__ ({ \
55727	float64x1x2_t __ret; \
55728	__builtin_neon_vld2_v(&__ret, __p0, 10); \
55729	__ret; \
55730	})
55731	#else
55732	#define vld2_f64(__p0) __extension__ ({ \	47251	#define vld2_f64(__p0) __extension__ ({ \
55733	float64x1x2_t __ret; \	47252	float64x1x2_t __ret; \
55734	__builtin_neon_vld2_v(&__ret, __p0, 10); \	47253	__builtin_neon_vld2_v(&__ret, __p0, 10); \
55735	__ret; \	47254	__ret; \
55736	})	47255	})
55737	#endif
55738
55739	#ifdef __LITTLE_ENDIAN__
55740	#define vld2_dup_p64(__p0) __extension__ ({ \
55741	poly64x1x2_t __ret; \
55742	__builtin_neon_vld2_dup_v(&__ret, __p0, 6); \
55743	__ret; \
55744	})
55745	#else
55746	#define vld2_dup_p64(__p0) __extension__ ({ \	47256	#define vld2_dup_p64(__p0) __extension__ ({ \
55747	poly64x1x2_t __ret; \	47257	poly64x1x2_t __ret; \
55748	__builtin_neon_vld2_dup_v(&__ret, __p0, 6); \	47258	__builtin_neon_vld2_dup_v(&__ret, __p0, 6); \
55749	__ret; \	47259	__ret; \
55750	})	47260	})
55751	#endif
55752
55753	#ifdef __LITTLE_ENDIAN__	47261	#ifdef __LITTLE_ENDIAN__
55754	#define vld2q_dup_p64(__p0) __extension__ ({ \	47262	#define vld2q_dup_p64(__p0) __extension__ ({ \
55755	poly64x2x2_t __ret; \	47263	poly64x2x2_t __ret; \
...	@@ -55784,36 +47292,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55784,36 +47292,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55784	})	47292	})
55785	#endif	47293	#endif
55786		47294
55787	#ifdef __LITTLE_ENDIAN__
55788	#define vld2_dup_f64(__p0) __extension__ ({ \	47295	#define vld2_dup_f64(__p0) __extension__ ({ \
55789	float64x1x2_t __ret; \	47296	float64x1x2_t __ret; \
55790	__builtin_neon_vld2_dup_v(&__ret, __p0, 10); \	47297	__builtin_neon_vld2_dup_v(&__ret, __p0, 10); \
55791	__ret; \	47298	__ret; \
55792	})	47299	})
55793	#else
55794	#define vld2_dup_f64(__p0) __extension__ ({ \
55795	float64x1x2_t __ret; \
55796	__builtin_neon_vld2_dup_v(&__ret, __p0, 10); \
55797	__ret; \
55798	})
55799	#endif
55800
55801	#ifdef __LITTLE_ENDIAN__
55802	#define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({ \	47300	#define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
55803	poly64x1x2_t __s1 = __p1; \	47301	poly64x1x2_t __s1 = __p1; \
55804	poly64x1x2_t __ret; \	47302	poly64x1x2_t __ret; \
55805	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \	47303	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
55806	__ret; \	47304	__ret; \
55807	})	47305	})
55808	#else
55809	#define vld2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
55810	poly64x1x2_t __s1 = __p1; \
55811	poly64x1x2_t __ret; \
55812	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
55813	__ret; \
55814	})
55815	#endif
55816
55817	#ifdef __LITTLE_ENDIAN__	47306	#ifdef __LITTLE_ENDIAN__
55818	#define vld2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	47307	#define vld2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
55819	poly8x16x2_t __s1 = __p1; \	47308	poly8x16x2_t __s1 = __p1; \
...	@@ -55928,7 +47417,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55928,7 +47417,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55928	#define vld2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	47417	#define vld2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
55929	float64x2x2_t __s1 = __p1; \	47418	float64x2x2_t __s1 = __p1; \
55930	float64x2x2_t __ret; \	47419	float64x2x2_t __ret; \
55931	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 42); \	47420	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 42); \
55932	__ret; \	47421	__ret; \
55933	})	47422	})
55934	#else	47423	#else
...	@@ -55938,7 +47427,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55938,7 +47427,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55938	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	47427	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
55939	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	47428	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
55940	float64x2x2_t __ret; \	47429	float64x2x2_t __ret; \
55941	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 42); \	47430	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 42); \
55942	\	47431	\
55943	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	47432	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
55944	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	47433	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -55950,7 +47439,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55950,7 +47439,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55950	#define vld2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	47439	#define vld2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
55951	int64x2x2_t __s1 = __p1; \	47440	int64x2x2_t __s1 = __p1; \
55952	int64x2x2_t __ret; \	47441	int64x2x2_t __ret; \
55953	__builtin_neon_vld2q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 35); \	47442	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 35); \
55954	__ret; \	47443	__ret; \
55955	})	47444	})
55956	#else	47445	#else
...	@@ -55960,7 +47449,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55960,7 +47449,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55960	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	47449	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
55961	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	47450	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
55962	int64x2x2_t __ret; \	47451	int64x2x2_t __ret; \
55963	__builtin_neon_vld2q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __p2, 35); \	47452	__builtin_neon_vld2q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 35); \
55964	\	47453	\
55965	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	47454	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
55966	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	47455	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -55968,68 +47457,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -55968,68 +47457,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
55968	})	47457	})
55969	#endif	47458	#endif
55970		47459
55971	#ifdef __LITTLE_ENDIAN__
55972	#define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({ \	47460	#define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
55973	uint64x1x2_t __s1 = __p1; \	47461	uint64x1x2_t __s1 = __p1; \
55974	uint64x1x2_t __ret; \	47462	uint64x1x2_t __ret; \
55975	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \	47463	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
55976	__ret; \	47464	__ret; \
55977	})	47465	})
55978	#else
55979	#define vld2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
55980	uint64x1x2_t __s1 = __p1; \
55981	uint64x1x2_t __ret; \
55982	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
55983	__ret; \
55984	})
55985	#endif
55986
55987	#ifdef __LITTLE_ENDIAN__
55988	#define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({ \	47466	#define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
55989	float64x1x2_t __s1 = __p1; \	47467	float64x1x2_t __s1 = __p1; \
55990	float64x1x2_t __ret; \	47468	float64x1x2_t __ret; \
55991	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 10); \	47469	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 10); \
55992	__ret; \
55993	})
55994	#else
55995	#define vld2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
55996	float64x1x2_t __s1 = __p1; \
55997	float64x1x2_t __ret; \
55998	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 10); \
55999	__ret; \
56000	})
56001	#endif
56002
56003	#ifdef __LITTLE_ENDIAN__
56004	#define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56005	int64x1x2_t __s1 = __p1; \
56006	int64x1x2_t __ret; \
56007	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 3); \
56008	__ret; \	47470	__ret; \
56009	})	47471	})
56010	#else
56011	#define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({ \	47472	#define vld2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56012	int64x1x2_t __s1 = __p1; \	47473	int64x1x2_t __s1 = __p1; \
56013	int64x1x2_t __ret; \	47474	int64x1x2_t __ret; \
56014	__builtin_neon_vld2_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __p2, 3); \	47475	__builtin_neon_vld2_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 3); \
56015	__ret; \	47476	__ret; \
56016	})	47477	})
56017	#endif
56018
56019	#ifdef __LITTLE_ENDIAN__
56020	#define vld3_p64(__p0) __extension__ ({ \	47478	#define vld3_p64(__p0) __extension__ ({ \
56021	poly64x1x3_t __ret; \	47479	poly64x1x3_t __ret; \
56022	__builtin_neon_vld3_v(&__ret, __p0, 6); \	47480	__builtin_neon_vld3_v(&__ret, __p0, 6); \
56023	__ret; \	47481	__ret; \
56024	})	47482	})
56025	#else
56026	#define vld3_p64(__p0) __extension__ ({ \
56027	poly64x1x3_t __ret; \
56028	__builtin_neon_vld3_v(&__ret, __p0, 6); \
56029	__ret; \
56030	})
56031	#endif
56032
56033	#ifdef __LITTLE_ENDIAN__	47483	#ifdef __LITTLE_ENDIAN__
56034	#define vld3q_p64(__p0) __extension__ ({ \	47484	#define vld3q_p64(__p0) __extension__ ({ \
56035	poly64x2x3_t __ret; \	47485	poly64x2x3_t __ret; \
...	@@ -56102,34 +47552,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56102,34 +47552,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56102	})	47552	})
56103	#endif	47553	#endif
56104		47554
56105	#ifdef __LITTLE_ENDIAN__
56106	#define vld3_f64(__p0) __extension__ ({ \	47555	#define vld3_f64(__p0) __extension__ ({ \
56107	float64x1x3_t __ret; \	47556	float64x1x3_t __ret; \
56108	__builtin_neon_vld3_v(&__ret, __p0, 10); \	47557	__builtin_neon_vld3_v(&__ret, __p0, 10); \
56109	__ret; \	47558	__ret; \
56110	})	47559	})
56111	#else
56112	#define vld3_f64(__p0) __extension__ ({ \
56113	float64x1x3_t __ret; \
56114	__builtin_neon_vld3_v(&__ret, __p0, 10); \
56115	__ret; \
56116	})
56117	#endif
56118
56119	#ifdef __LITTLE_ENDIAN__
56120	#define vld3_dup_p64(__p0) __extension__ ({ \
56121	poly64x1x3_t __ret; \
56122	__builtin_neon_vld3_dup_v(&__ret, __p0, 6); \
56123	__ret; \
56124	})
56125	#else
56126	#define vld3_dup_p64(__p0) __extension__ ({ \	47560	#define vld3_dup_p64(__p0) __extension__ ({ \
56127	poly64x1x3_t __ret; \	47561	poly64x1x3_t __ret; \
56128	__builtin_neon_vld3_dup_v(&__ret, __p0, 6); \	47562	__builtin_neon_vld3_dup_v(&__ret, __p0, 6); \
56129	__ret; \	47563	__ret; \
56130	})	47564	})
56131	#endif
56132
56133	#ifdef __LITTLE_ENDIAN__	47565	#ifdef __LITTLE_ENDIAN__
56134	#define vld3q_dup_p64(__p0) __extension__ ({ \	47566	#define vld3q_dup_p64(__p0) __extension__ ({ \
56135	poly64x2x3_t __ret; \	47567	poly64x2x3_t __ret; \
...	@@ -56166,36 +47598,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56166,36 +47598,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56166	})	47598	})
56167	#endif	47599	#endif
56168		47600
56169	#ifdef __LITTLE_ENDIAN__
56170	#define vld3_dup_f64(__p0) __extension__ ({ \	47601	#define vld3_dup_f64(__p0) __extension__ ({ \
56171	float64x1x3_t __ret; \	47602	float64x1x3_t __ret; \
56172	__builtin_neon_vld3_dup_v(&__ret, __p0, 10); \	47603	__builtin_neon_vld3_dup_v(&__ret, __p0, 10); \
56173	__ret; \	47604	__ret; \
56174	})	47605	})
56175	#else
56176	#define vld3_dup_f64(__p0) __extension__ ({ \
56177	float64x1x3_t __ret; \
56178	__builtin_neon_vld3_dup_v(&__ret, __p0, 10); \
56179	__ret; \
56180	})
56181	#endif
56182
56183	#ifdef __LITTLE_ENDIAN__
56184	#define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
56185	poly64x1x3_t __s1 = __p1; \
56186	poly64x1x3_t __ret; \
56187	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
56188	__ret; \
56189	})
56190	#else
56191	#define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({ \	47606	#define vld3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
56192	poly64x1x3_t __s1 = __p1; \	47607	poly64x1x3_t __s1 = __p1; \
56193	poly64x1x3_t __ret; \	47608	poly64x1x3_t __ret; \
56194	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \	47609	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
56195	__ret; \	47610	__ret; \
56196	})	47611	})
56197	#endif
56198
56199	#ifdef __LITTLE_ENDIAN__	47612	#ifdef __LITTLE_ENDIAN__
56200	#define vld3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	47613	#define vld3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
56201	poly8x16x3_t __s1 = __p1; \	47614	poly8x16x3_t __s1 = __p1; \
...	@@ -56320,7 +47733,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56320,7 +47733,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56320	#define vld3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	47733	#define vld3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56321	float64x2x3_t __s1 = __p1; \	47734	float64x2x3_t __s1 = __p1; \
56322	float64x2x3_t __ret; \	47735	float64x2x3_t __ret; \
56323	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 42); \	47736	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 42); \
56324	__ret; \	47737	__ret; \
56325	})	47738	})
56326	#else	47739	#else
...	@@ -56331,7 +47744,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56331,7 +47744,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56331	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	47744	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
56332	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	47745	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
56333	float64x2x3_t __ret; \	47746	float64x2x3_t __ret; \
56334	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 42); \	47747	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 42); \
56335	\	47748	\
56336	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	47749	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
56337	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	47750	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -56344,7 +47757,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56344,7 +47757,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56344	#define vld3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	47757	#define vld3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56345	int64x2x3_t __s1 = __p1; \	47758	int64x2x3_t __s1 = __p1; \
56346	int64x2x3_t __ret; \	47759	int64x2x3_t __ret; \
56347	__builtin_neon_vld3q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 35); \	47760	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 35); \
56348	__ret; \	47761	__ret; \
56349	})	47762	})
56350	#else	47763	#else
...	@@ -56355,7 +47768,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56355,7 +47768,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56355	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	47768	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
56356	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	47769	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
56357	int64x2x3_t __ret; \	47770	int64x2x3_t __ret; \
56358	__builtin_neon_vld3q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 35); \	47771	__builtin_neon_vld3q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 35); \
56359	\	47772	\
56360	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	47773	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
56361	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	47774	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -56364,68 +47777,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56364,68 +47777,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56364	})	47777	})
56365	#endif	47778	#endif
56366		47779
56367	#ifdef __LITTLE_ENDIAN__
56368	#define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({ \	47780	#define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
56369	uint64x1x3_t __s1 = __p1; \	47781	uint64x1x3_t __s1 = __p1; \
56370	uint64x1x3_t __ret; \	47782	uint64x1x3_t __ret; \
56371	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \	47783	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
56372	__ret; \	47784	__ret; \
56373	})	47785	})
56374	#else
56375	#define vld3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
56376	uint64x1x3_t __s1 = __p1; \
56377	uint64x1x3_t __ret; \
56378	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
56379	__ret; \
56380	})
56381	#endif
56382
56383	#ifdef __LITTLE_ENDIAN__
56384	#define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56385	float64x1x3_t __s1 = __p1; \
56386	float64x1x3_t __ret; \
56387	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 10); \
56388	__ret; \
56389	})
56390	#else
56391	#define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({ \	47786	#define vld3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56392	float64x1x3_t __s1 = __p1; \	47787	float64x1x3_t __s1 = __p1; \
56393	float64x1x3_t __ret; \	47788	float64x1x3_t __ret; \
56394	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 10); \	47789	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 10); \
56395	__ret; \	47790	__ret; \
56396	})	47791	})
56397	#endif
56398
56399	#ifdef __LITTLE_ENDIAN__
56400	#define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({ \	47792	#define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56401	int64x1x3_t __s1 = __p1; \	47793	int64x1x3_t __s1 = __p1; \
56402	int64x1x3_t __ret; \	47794	int64x1x3_t __ret; \
56403	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 3); \	47795	__builtin_neon_vld3_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 3); \
56404	__ret; \	47796	__ret; \
56405	})	47797	})
56406	#else
56407	#define vld3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56408	int64x1x3_t __s1 = __p1; \
56409	int64x1x3_t __ret; \
56410	__builtin_neon_vld3_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 3); \
56411	__ret; \
56412	})
56413	#endif
56414
56415	#ifdef __LITTLE_ENDIAN__
56416	#define vld4_p64(__p0) __extension__ ({ \	47798	#define vld4_p64(__p0) __extension__ ({ \
56417	poly64x1x4_t __ret; \	47799	poly64x1x4_t __ret; \
56418	__builtin_neon_vld4_v(&__ret, __p0, 6); \	47800	__builtin_neon_vld4_v(&__ret, __p0, 6); \
56419	__ret; \	47801	__ret; \
56420	})	47802	})
56421	#else
56422	#define vld4_p64(__p0) __extension__ ({ \
56423	poly64x1x4_t __ret; \
56424	__builtin_neon_vld4_v(&__ret, __p0, 6); \
56425	__ret; \
56426	})
56427	#endif
56428
56429	#ifdef __LITTLE_ENDIAN__	47803	#ifdef __LITTLE_ENDIAN__
56430	#define vld4q_p64(__p0) __extension__ ({ \	47804	#define vld4q_p64(__p0) __extension__ ({ \
56431	poly64x2x4_t __ret; \	47805	poly64x2x4_t __ret; \
...	@@ -56502,34 +47876,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56502,34 +47876,16 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56502	})	47876	})
56503	#endif	47877	#endif
56504		47878
56505	#ifdef __LITTLE_ENDIAN__
56506	#define vld4_f64(__p0) __extension__ ({ \	47879	#define vld4_f64(__p0) __extension__ ({ \
56507	float64x1x4_t __ret; \	47880	float64x1x4_t __ret; \
56508	__builtin_neon_vld4_v(&__ret, __p0, 10); \	47881	__builtin_neon_vld4_v(&__ret, __p0, 10); \
56509	__ret; \	47882	__ret; \
56510	})	47883	})
56511	#else
56512	#define vld4_f64(__p0) __extension__ ({ \
56513	float64x1x4_t __ret; \
56514	__builtin_neon_vld4_v(&__ret, __p0, 10); \
56515	__ret; \
56516	})
56517	#endif
56518
56519	#ifdef __LITTLE_ENDIAN__
56520	#define vld4_dup_p64(__p0) __extension__ ({ \
56521	poly64x1x4_t __ret; \
56522	__builtin_neon_vld4_dup_v(&__ret, __p0, 6); \
56523	__ret; \
56524	})
56525	#else
56526	#define vld4_dup_p64(__p0) __extension__ ({ \	47884	#define vld4_dup_p64(__p0) __extension__ ({ \
56527	poly64x1x4_t __ret; \	47885	poly64x1x4_t __ret; \
56528	__builtin_neon_vld4_dup_v(&__ret, __p0, 6); \	47886	__builtin_neon_vld4_dup_v(&__ret, __p0, 6); \
56529	__ret; \	47887	__ret; \
56530	})	47888	})
56531	#endif
56532
56533	#ifdef __LITTLE_ENDIAN__	47889	#ifdef __LITTLE_ENDIAN__
56534	#define vld4q_dup_p64(__p0) __extension__ ({ \	47890	#define vld4q_dup_p64(__p0) __extension__ ({ \
56535	poly64x2x4_t __ret; \	47891	poly64x2x4_t __ret; \
...	@@ -56568,36 +47924,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56568,36 +47924,17 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56568	})	47924	})
56569	#endif	47925	#endif
56570		47926
56571	#ifdef __LITTLE_ENDIAN__
56572	#define vld4_dup_f64(__p0) __extension__ ({ \	47927	#define vld4_dup_f64(__p0) __extension__ ({ \
56573	float64x1x4_t __ret; \	47928	float64x1x4_t __ret; \
56574	__builtin_neon_vld4_dup_v(&__ret, __p0, 10); \	47929	__builtin_neon_vld4_dup_v(&__ret, __p0, 10); \
56575	__ret; \	47930	__ret; \
56576	})	47931	})
56577	#else
56578	#define vld4_dup_f64(__p0) __extension__ ({ \
56579	float64x1x4_t __ret; \
56580	__builtin_neon_vld4_dup_v(&__ret, __p0, 10); \
56581	__ret; \
56582	})
56583	#endif
56584
56585	#ifdef __LITTLE_ENDIAN__
56586	#define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
56587	poly64x1x4_t __s1 = __p1; \
56588	poly64x1x4_t __ret; \
56589	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
56590	__ret; \
56591	})
56592	#else
56593	#define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({ \	47932	#define vld4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
56594	poly64x1x4_t __s1 = __p1; \	47933	poly64x1x4_t __s1 = __p1; \
56595	poly64x1x4_t __ret; \	47934	poly64x1x4_t __ret; \
56596	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \	47935	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
56597	__ret; \	47936	__ret; \
56598	})	47937	})
56599	#endif
56600
56601	#ifdef __LITTLE_ENDIAN__	47938	#ifdef __LITTLE_ENDIAN__
56602	#define vld4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	47939	#define vld4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
56603	poly8x16x4_t __s1 = __p1; \	47940	poly8x16x4_t __s1 = __p1; \
...	@@ -56732,7 +48069,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56732,7 +48069,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56732	#define vld4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	48069	#define vld4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56733	float64x2x4_t __s1 = __p1; \	48070	float64x2x4_t __s1 = __p1; \
56734	float64x2x4_t __ret; \	48071	float64x2x4_t __ret; \
56735	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 42); \	48072	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 42); \
56736	__ret; \	48073	__ret; \
56737	})	48074	})
56738	#else	48075	#else
...	@@ -56744,7 +48081,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56744,7 +48081,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56744	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	48081	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
56745	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	48082	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
56746	float64x2x4_t __ret; \	48083	float64x2x4_t __ret; \
56747	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 42); \	48084	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 42); \
56748	\	48085	\
56749	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	48086	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
56750	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	48087	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -56758,7 +48095,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56758,7 +48095,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56758	#define vld4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	48095	#define vld4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56759	int64x2x4_t __s1 = __p1; \	48096	int64x2x4_t __s1 = __p1; \
56760	int64x2x4_t __ret; \	48097	int64x2x4_t __ret; \
56761	__builtin_neon_vld4q_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 35); \	48098	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 35); \
56762	__ret; \	48099	__ret; \
56763	})	48100	})
56764	#else	48101	#else
...	@@ -56770,7 +48107,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56770,7 +48107,7 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56770	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	48107	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
56771	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	48108	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
56772	int64x2x4_t __ret; \	48109	int64x2x4_t __ret; \
56773	__builtin_neon_vld4q_lane_v(&__ret, __p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 35); \	48110	__builtin_neon_vld4q_lane_v(&__ret, __p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 35); \
56774	\	48111	\
56775	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \	48112	__ret.val[0] = __builtin_shufflevector(__ret.val[0], __ret.val[0], 1, 0); \
56776	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \	48113	__ret.val[1] = __builtin_shufflevector(__ret.val[1], __ret.val[1], 1, 0); \
...	@@ -56780,68 +48117,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {	...	@@ -56780,68 +48117,29 @@ __ai float64x1_t vget_low_f64(float64x2_t __p0) {
56780	})	48117	})
56781	#endif	48118	#endif
56782		48119
56783	#ifdef __LITTLE_ENDIAN__
56784	#define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({ \	48120	#define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
56785	uint64x1x4_t __s1 = __p1; \	48121	uint64x1x4_t __s1 = __p1; \
56786	uint64x1x4_t __ret; \	48122	uint64x1x4_t __ret; \
56787	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \	48123	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
56788	__ret; \	48124	__ret; \
56789	})	48125	})
56790	#else
56791	#define vld4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
56792	uint64x1x4_t __s1 = __p1; \
56793	uint64x1x4_t __ret; \
56794	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
56795	__ret; \
56796	})
56797	#endif
56798
56799	#ifdef __LITTLE_ENDIAN__
56800	#define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56801	float64x1x4_t __s1 = __p1; \
56802	float64x1x4_t __ret; \
56803	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 10); \
56804	__ret; \
56805	})
56806	#else
56807	#define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({ \	48126	#define vld4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
56808	float64x1x4_t __s1 = __p1; \	48127	float64x1x4_t __s1 = __p1; \
56809	float64x1x4_t __ret; \	48128	float64x1x4_t __ret; \
56810	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 10); \	48129	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 10); \
56811	__ret; \	48130	__ret; \
56812	})	48131	})
56813	#endif
56814
56815	#ifdef __LITTLE_ENDIAN__
56816	#define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56817	int64x1x4_t __s1 = __p1; \
56818	int64x1x4_t __ret; \
56819	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 3); \
56820	__ret; \
56821	})
56822	#else
56823	#define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({ \	48132	#define vld4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
56824	int64x1x4_t __s1 = __p1; \	48133	int64x1x4_t __s1 = __p1; \
56825	int64x1x4_t __ret; \	48134	int64x1x4_t __ret; \
56826	__builtin_neon_vld4_lane_v(&__ret, __p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 3); \	48135	__builtin_neon_vld4_lane_v(&__ret, __p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 3); \
56827	__ret; \	48136	__ret; \
56828	})	48137	})
56829	#endif
56830
56831	#ifdef __LITTLE_ENDIAN__
56832	#define vldrq_p128(__p0) __extension__ ({ \
56833	poly128_t __ret; \
56834	__ret = (poly128_t) __builtin_neon_vldrq_p128(__p0); \
56835	__ret; \
56836	})
56837	#else
56838	#define vldrq_p128(__p0) __extension__ ({ \	48138	#define vldrq_p128(__p0) __extension__ ({ \
56839	poly128_t __ret; \	48139	poly128_t __ret; \
56840	__ret = (poly128_t) __builtin_neon_vldrq_p128(__p0); \	48140	__ret = (poly128_t) __builtin_neon_vldrq_p128(__p0); \
56841	__ret; \	48141	__ret; \
56842	})	48142	})
56843	#endif
56844
56845	#ifdef __LITTLE_ENDIAN__	48143	#ifdef __LITTLE_ENDIAN__
56846	__ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {	48144	__ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
56847	float64x2_t __ret;	48145	float64x2_t __ret;
...	@@ -56859,31 +48157,22 @@ __ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -56859,31 +48157,22 @@ __ai float64x2_t vmaxq_f64(float64x2_t __p0, float64x2_t __p1) {
56859	}	48157	}
56860	#endif	48158	#endif
56861		48159
56862	#ifdef __LITTLE_ENDIAN__
56863	__ai float64x1_t vmax_f64(float64x1_t __p0, float64x1_t __p1) {
56864	float64x1_t __ret;
56865	__ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
56866	return __ret;
56867	}
56868	#else
56869	__ai float64x1_t vmax_f64(float64x1_t __p0, float64x1_t __p1) {	48160	__ai float64x1_t vmax_f64(float64x1_t __p0, float64x1_t __p1) {
56870	float64x1_t __ret;	48161	float64x1_t __ret;
56871	__ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	48162	__ret = (float64x1_t) __builtin_neon_vmax_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
56872	return __ret;	48163	return __ret;
56873	}	48164	}
56874	#endif
56875
56876	#ifdef __LITTLE_ENDIAN__	48165	#ifdef __LITTLE_ENDIAN__
56877	__ai float64_t vmaxnmvq_f64(float64x2_t __p0) {	48166	__ai float64_t vmaxnmvq_f64(float64x2_t __p0) {
56878	float64_t __ret;	48167	float64_t __ret;
56879	__ret = (float64_t) __builtin_neon_vmaxnmvq_f64((int8x16_t)__p0);	48168	__ret = (float64_t) __builtin_neon_vmaxnmvq_f64(__p0);
56880	return __ret;	48169	return __ret;
56881	}	48170	}
56882	#else	48171	#else
56883	__ai float64_t vmaxnmvq_f64(float64x2_t __p0) {	48172	__ai float64_t vmaxnmvq_f64(float64x2_t __p0) {
56884	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48173	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
56885	float64_t __ret;	48174	float64_t __ret;
56886	__ret = (float64_t) __builtin_neon_vmaxnmvq_f64((int8x16_t)__rev0);	48175	__ret = (float64_t) __builtin_neon_vmaxnmvq_f64(__rev0);
56887	return __ret;	48176	return __ret;
56888	}	48177	}
56889	#endif	48178	#endif
...	@@ -56891,14 +48180,14 @@ __ai float64_t vmaxnmvq_f64(float64x2_t __p0) {	...	@@ -56891,14 +48180,14 @@ __ai float64_t vmaxnmvq_f64(float64x2_t __p0) {
56891	#ifdef __LITTLE_ENDIAN__	48180	#ifdef __LITTLE_ENDIAN__
56892	__ai float32_t vmaxnmvq_f32(float32x4_t __p0) {	48181	__ai float32_t vmaxnmvq_f32(float32x4_t __p0) {
56893	float32_t __ret;	48182	float32_t __ret;
56894	__ret = (float32_t) __builtin_neon_vmaxnmvq_f32((int8x16_t)__p0);	48183	__ret = (float32_t) __builtin_neon_vmaxnmvq_f32(__p0);
56895	return __ret;	48184	return __ret;
56896	}	48185	}
56897	#else	48186	#else
56898	__ai float32_t vmaxnmvq_f32(float32x4_t __p0) {	48187	__ai float32_t vmaxnmvq_f32(float32x4_t __p0) {
56899	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48188	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
56900	float32_t __ret;	48189	float32_t __ret;
56901	__ret = (float32_t) __builtin_neon_vmaxnmvq_f32((int8x16_t)__rev0);	48190	__ret = (float32_t) __builtin_neon_vmaxnmvq_f32(__rev0);
56902	return __ret;	48191	return __ret;
56903	}	48192	}
56904	#endif	48193	#endif
...	@@ -56906,14 +48195,14 @@ __ai float32_t vmaxnmvq_f32(float32x4_t __p0) {	...	@@ -56906,14 +48195,14 @@ __ai float32_t vmaxnmvq_f32(float32x4_t __p0) {
56906	#ifdef __LITTLE_ENDIAN__	48195	#ifdef __LITTLE_ENDIAN__
56907	__ai float32_t vmaxnmv_f32(float32x2_t __p0) {	48196	__ai float32_t vmaxnmv_f32(float32x2_t __p0) {
56908	float32_t __ret;	48197	float32_t __ret;
56909	__ret = (float32_t) __builtin_neon_vmaxnmv_f32((int8x8_t)__p0);	48198	__ret = (float32_t) __builtin_neon_vmaxnmv_f32(__p0);
56910	return __ret;	48199	return __ret;
56911	}	48200	}
56912	#else	48201	#else
56913	__ai float32_t vmaxnmv_f32(float32x2_t __p0) {	48202	__ai float32_t vmaxnmv_f32(float32x2_t __p0) {
56914	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48203	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
56915	float32_t __ret;	48204	float32_t __ret;
56916	__ret = (float32_t) __builtin_neon_vmaxnmv_f32((int8x8_t)__rev0);	48205	__ret = (float32_t) __builtin_neon_vmaxnmv_f32(__rev0);
56917	return __ret;	48206	return __ret;
56918	}	48207	}
56919	#endif	48208	#endif
...	@@ -56921,14 +48210,14 @@ __ai float32_t vmaxnmv_f32(float32x2_t __p0) {	...	@@ -56921,14 +48210,14 @@ __ai float32_t vmaxnmv_f32(float32x2_t __p0) {
56921	#ifdef __LITTLE_ENDIAN__	48210	#ifdef __LITTLE_ENDIAN__
56922	__ai uint8_t vmaxvq_u8(uint8x16_t __p0) {	48211	__ai uint8_t vmaxvq_u8(uint8x16_t __p0) {
56923	uint8_t __ret;	48212	uint8_t __ret;
56924	__ret = (uint8_t) __builtin_neon_vmaxvq_u8((int8x16_t)__p0);	48213	__ret = (uint8_t) __builtin_neon_vmaxvq_u8(__p0);
56925	return __ret;	48214	return __ret;
56926	}	48215	}
56927	#else	48216	#else
56928	__ai uint8_t vmaxvq_u8(uint8x16_t __p0) {	48217	__ai uint8_t vmaxvq_u8(uint8x16_t __p0) {
56929	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	48218	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
56930	uint8_t __ret;	48219	uint8_t __ret;
56931	__ret = (uint8_t) __builtin_neon_vmaxvq_u8((int8x16_t)__rev0);	48220	__ret = (uint8_t) __builtin_neon_vmaxvq_u8(__rev0);
56932	return __ret;	48221	return __ret;
56933	}	48222	}
56934	#endif	48223	#endif
...	@@ -56936,14 +48225,14 @@ __ai uint8_t vmaxvq_u8(uint8x16_t __p0) {	...	@@ -56936,14 +48225,14 @@ __ai uint8_t vmaxvq_u8(uint8x16_t __p0) {
56936	#ifdef __LITTLE_ENDIAN__	48225	#ifdef __LITTLE_ENDIAN__
56937	__ai uint32_t vmaxvq_u32(uint32x4_t __p0) {	48226	__ai uint32_t vmaxvq_u32(uint32x4_t __p0) {
56938	uint32_t __ret;	48227	uint32_t __ret;
56939	__ret = (uint32_t) __builtin_neon_vmaxvq_u32((int8x16_t)__p0);	48228	__ret = (uint32_t) __builtin_neon_vmaxvq_u32(__p0);
56940	return __ret;	48229	return __ret;
56941	}	48230	}
56942	#else	48231	#else
56943	__ai uint32_t vmaxvq_u32(uint32x4_t __p0) {	48232	__ai uint32_t vmaxvq_u32(uint32x4_t __p0) {
56944	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48233	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
56945	uint32_t __ret;	48234	uint32_t __ret;
56946	__ret = (uint32_t) __builtin_neon_vmaxvq_u32((int8x16_t)__rev0);	48235	__ret = (uint32_t) __builtin_neon_vmaxvq_u32(__rev0);
56947	return __ret;	48236	return __ret;
56948	}	48237	}
56949	#endif	48238	#endif
...	@@ -56951,14 +48240,14 @@ __ai uint32_t vmaxvq_u32(uint32x4_t __p0) {	...	@@ -56951,14 +48240,14 @@ __ai uint32_t vmaxvq_u32(uint32x4_t __p0) {
56951	#ifdef __LITTLE_ENDIAN__	48240	#ifdef __LITTLE_ENDIAN__
56952	__ai uint16_t vmaxvq_u16(uint16x8_t __p0) {	48241	__ai uint16_t vmaxvq_u16(uint16x8_t __p0) {
56953	uint16_t __ret;	48242	uint16_t __ret;
56954	__ret = (uint16_t) __builtin_neon_vmaxvq_u16((int8x16_t)__p0);	48243	__ret = (uint16_t) __builtin_neon_vmaxvq_u16(__p0);
56955	return __ret;	48244	return __ret;
56956	}	48245	}
56957	#else	48246	#else
56958	__ai uint16_t vmaxvq_u16(uint16x8_t __p0) {	48247	__ai uint16_t vmaxvq_u16(uint16x8_t __p0) {
56959	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48248	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
56960	uint16_t __ret;	48249	uint16_t __ret;
56961	__ret = (uint16_t) __builtin_neon_vmaxvq_u16((int8x16_t)__rev0);	48250	__ret = (uint16_t) __builtin_neon_vmaxvq_u16(__rev0);
56962	return __ret;	48251	return __ret;
56963	}	48252	}
56964	#endif	48253	#endif
...	@@ -56966,14 +48255,14 @@ __ai uint16_t vmaxvq_u16(uint16x8_t __p0) {	...	@@ -56966,14 +48255,14 @@ __ai uint16_t vmaxvq_u16(uint16x8_t __p0) {
56966	#ifdef __LITTLE_ENDIAN__	48255	#ifdef __LITTLE_ENDIAN__
56967	__ai int8_t vmaxvq_s8(int8x16_t __p0) {	48256	__ai int8_t vmaxvq_s8(int8x16_t __p0) {
56968	int8_t __ret;	48257	int8_t __ret;
56969	__ret = (int8_t) __builtin_neon_vmaxvq_s8((int8x16_t)__p0);	48258	__ret = (int8_t) __builtin_neon_vmaxvq_s8(__p0);
56970	return __ret;	48259	return __ret;
56971	}	48260	}
56972	#else	48261	#else
56973	__ai int8_t vmaxvq_s8(int8x16_t __p0) {	48262	__ai int8_t vmaxvq_s8(int8x16_t __p0) {
56974	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	48263	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
56975	int8_t __ret;	48264	int8_t __ret;
56976	__ret = (int8_t) __builtin_neon_vmaxvq_s8((int8x16_t)__rev0);	48265	__ret = (int8_t) __builtin_neon_vmaxvq_s8(__rev0);
56977	return __ret;	48266	return __ret;
56978	}	48267	}
56979	#endif	48268	#endif
...	@@ -56981,14 +48270,14 @@ __ai int8_t vmaxvq_s8(int8x16_t __p0) {	...	@@ -56981,14 +48270,14 @@ __ai int8_t vmaxvq_s8(int8x16_t __p0) {
56981	#ifdef __LITTLE_ENDIAN__	48270	#ifdef __LITTLE_ENDIAN__
56982	__ai float64_t vmaxvq_f64(float64x2_t __p0) {	48271	__ai float64_t vmaxvq_f64(float64x2_t __p0) {
56983	float64_t __ret;	48272	float64_t __ret;
56984	__ret = (float64_t) __builtin_neon_vmaxvq_f64((int8x16_t)__p0);	48273	__ret = (float64_t) __builtin_neon_vmaxvq_f64(__p0);
56985	return __ret;	48274	return __ret;
56986	}	48275	}
56987	#else	48276	#else
56988	__ai float64_t vmaxvq_f64(float64x2_t __p0) {	48277	__ai float64_t vmaxvq_f64(float64x2_t __p0) {
56989	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48278	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
56990	float64_t __ret;	48279	float64_t __ret;
56991	__ret = (float64_t) __builtin_neon_vmaxvq_f64((int8x16_t)__rev0);	48280	__ret = (float64_t) __builtin_neon_vmaxvq_f64(__rev0);
56992	return __ret;	48281	return __ret;
56993	}	48282	}
56994	#endif	48283	#endif
...	@@ -56996,14 +48285,14 @@ __ai float64_t vmaxvq_f64(float64x2_t __p0) {	...	@@ -56996,14 +48285,14 @@ __ai float64_t vmaxvq_f64(float64x2_t __p0) {
56996	#ifdef __LITTLE_ENDIAN__	48285	#ifdef __LITTLE_ENDIAN__
56997	__ai float32_t vmaxvq_f32(float32x4_t __p0) {	48286	__ai float32_t vmaxvq_f32(float32x4_t __p0) {
56998	float32_t __ret;	48287	float32_t __ret;
56999	__ret = (float32_t) __builtin_neon_vmaxvq_f32((int8x16_t)__p0);	48288	__ret = (float32_t) __builtin_neon_vmaxvq_f32(__p0);
57000	return __ret;	48289	return __ret;
57001	}	48290	}
57002	#else	48291	#else
57003	__ai float32_t vmaxvq_f32(float32x4_t __p0) {	48292	__ai float32_t vmaxvq_f32(float32x4_t __p0) {
57004	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48293	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57005	float32_t __ret;	48294	float32_t __ret;
57006	__ret = (float32_t) __builtin_neon_vmaxvq_f32((int8x16_t)__rev0);	48295	__ret = (float32_t) __builtin_neon_vmaxvq_f32(__rev0);
57007	return __ret;	48296	return __ret;
57008	}	48297	}
57009	#endif	48298	#endif
...	@@ -57011,14 +48300,14 @@ __ai float32_t vmaxvq_f32(float32x4_t __p0) {	...	@@ -57011,14 +48300,14 @@ __ai float32_t vmaxvq_f32(float32x4_t __p0) {
57011	#ifdef __LITTLE_ENDIAN__	48300	#ifdef __LITTLE_ENDIAN__
57012	__ai int32_t vmaxvq_s32(int32x4_t __p0) {	48301	__ai int32_t vmaxvq_s32(int32x4_t __p0) {
57013	int32_t __ret;	48302	int32_t __ret;
57014	__ret = (int32_t) __builtin_neon_vmaxvq_s32((int8x16_t)__p0);	48303	__ret = (int32_t) __builtin_neon_vmaxvq_s32(__p0);
57015	return __ret;	48304	return __ret;
57016	}	48305	}
57017	#else	48306	#else
57018	__ai int32_t vmaxvq_s32(int32x4_t __p0) {	48307	__ai int32_t vmaxvq_s32(int32x4_t __p0) {
57019	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48308	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57020	int32_t __ret;	48309	int32_t __ret;
57021	__ret = (int32_t) __builtin_neon_vmaxvq_s32((int8x16_t)__rev0);	48310	__ret = (int32_t) __builtin_neon_vmaxvq_s32(__rev0);
57022	return __ret;	48311	return __ret;
57023	}	48312	}
57024	#endif	48313	#endif
...	@@ -57026,14 +48315,14 @@ __ai int32_t vmaxvq_s32(int32x4_t __p0) {	...	@@ -57026,14 +48315,14 @@ __ai int32_t vmaxvq_s32(int32x4_t __p0) {
57026	#ifdef __LITTLE_ENDIAN__	48315	#ifdef __LITTLE_ENDIAN__
57027	__ai int16_t vmaxvq_s16(int16x8_t __p0) {	48316	__ai int16_t vmaxvq_s16(int16x8_t __p0) {
57028	int16_t __ret;	48317	int16_t __ret;
57029	__ret = (int16_t) __builtin_neon_vmaxvq_s16((int8x16_t)__p0);	48318	__ret = (int16_t) __builtin_neon_vmaxvq_s16(__p0);
57030	return __ret;	48319	return __ret;
57031	}	48320	}
57032	#else	48321	#else
57033	__ai int16_t vmaxvq_s16(int16x8_t __p0) {	48322	__ai int16_t vmaxvq_s16(int16x8_t __p0) {
57034	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48323	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57035	int16_t __ret;	48324	int16_t __ret;
57036	__ret = (int16_t) __builtin_neon_vmaxvq_s16((int8x16_t)__rev0);	48325	__ret = (int16_t) __builtin_neon_vmaxvq_s16(__rev0);
57037	return __ret;	48326	return __ret;
57038	}	48327	}
57039	#endif	48328	#endif
...	@@ -57041,14 +48330,14 @@ __ai int16_t vmaxvq_s16(int16x8_t __p0) {	...	@@ -57041,14 +48330,14 @@ __ai int16_t vmaxvq_s16(int16x8_t __p0) {
57041	#ifdef __LITTLE_ENDIAN__	48330	#ifdef __LITTLE_ENDIAN__
57042	__ai uint8_t vmaxv_u8(uint8x8_t __p0) {	48331	__ai uint8_t vmaxv_u8(uint8x8_t __p0) {
57043	uint8_t __ret;	48332	uint8_t __ret;
57044	__ret = (uint8_t) __builtin_neon_vmaxv_u8((int8x8_t)__p0);	48333	__ret = (uint8_t) __builtin_neon_vmaxv_u8(__p0);
57045	return __ret;	48334	return __ret;
57046	}	48335	}
57047	#else	48336	#else
57048	__ai uint8_t vmaxv_u8(uint8x8_t __p0) {	48337	__ai uint8_t vmaxv_u8(uint8x8_t __p0) {
57049	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48338	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57050	uint8_t __ret;	48339	uint8_t __ret;
57051	__ret = (uint8_t) __builtin_neon_vmaxv_u8((int8x8_t)__rev0);	48340	__ret = (uint8_t) __builtin_neon_vmaxv_u8(__rev0);
57052	return __ret;	48341	return __ret;
57053	}	48342	}
57054	#endif	48343	#endif
...	@@ -57056,14 +48345,14 @@ __ai uint8_t vmaxv_u8(uint8x8_t __p0) {	...	@@ -57056,14 +48345,14 @@ __ai uint8_t vmaxv_u8(uint8x8_t __p0) {
57056	#ifdef __LITTLE_ENDIAN__	48345	#ifdef __LITTLE_ENDIAN__
57057	__ai uint32_t vmaxv_u32(uint32x2_t __p0) {	48346	__ai uint32_t vmaxv_u32(uint32x2_t __p0) {
57058	uint32_t __ret;	48347	uint32_t __ret;
57059	__ret = (uint32_t) __builtin_neon_vmaxv_u32((int8x8_t)__p0);	48348	__ret = (uint32_t) __builtin_neon_vmaxv_u32(__p0);
57060	return __ret;	48349	return __ret;
57061	}	48350	}
57062	#else	48351	#else
57063	__ai uint32_t vmaxv_u32(uint32x2_t __p0) {	48352	__ai uint32_t vmaxv_u32(uint32x2_t __p0) {
57064	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48353	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57065	uint32_t __ret;	48354	uint32_t __ret;
57066	__ret = (uint32_t) __builtin_neon_vmaxv_u32((int8x8_t)__rev0);	48355	__ret = (uint32_t) __builtin_neon_vmaxv_u32(__rev0);
57067	return __ret;	48356	return __ret;
57068	}	48357	}
57069	#endif	48358	#endif
...	@@ -57071,14 +48360,14 @@ __ai uint32_t vmaxv_u32(uint32x2_t __p0) {	...	@@ -57071,14 +48360,14 @@ __ai uint32_t vmaxv_u32(uint32x2_t __p0) {
57071	#ifdef __LITTLE_ENDIAN__	48360	#ifdef __LITTLE_ENDIAN__
57072	__ai uint16_t vmaxv_u16(uint16x4_t __p0) {	48361	__ai uint16_t vmaxv_u16(uint16x4_t __p0) {
57073	uint16_t __ret;	48362	uint16_t __ret;
57074	__ret = (uint16_t) __builtin_neon_vmaxv_u16((int8x8_t)__p0);	48363	__ret = (uint16_t) __builtin_neon_vmaxv_u16(__p0);
57075	return __ret;	48364	return __ret;
57076	}	48365	}
57077	#else	48366	#else
57078	__ai uint16_t vmaxv_u16(uint16x4_t __p0) {	48367	__ai uint16_t vmaxv_u16(uint16x4_t __p0) {
57079	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48368	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57080	uint16_t __ret;	48369	uint16_t __ret;
57081	__ret = (uint16_t) __builtin_neon_vmaxv_u16((int8x8_t)__rev0);	48370	__ret = (uint16_t) __builtin_neon_vmaxv_u16(__rev0);
57082	return __ret;	48371	return __ret;
57083	}	48372	}
57084	#endif	48373	#endif
...	@@ -57086,14 +48375,14 @@ __ai uint16_t vmaxv_u16(uint16x4_t __p0) {	...	@@ -57086,14 +48375,14 @@ __ai uint16_t vmaxv_u16(uint16x4_t __p0) {
57086	#ifdef __LITTLE_ENDIAN__	48375	#ifdef __LITTLE_ENDIAN__
57087	__ai int8_t vmaxv_s8(int8x8_t __p0) {	48376	__ai int8_t vmaxv_s8(int8x8_t __p0) {
57088	int8_t __ret;	48377	int8_t __ret;
57089	__ret = (int8_t) __builtin_neon_vmaxv_s8((int8x8_t)__p0);	48378	__ret = (int8_t) __builtin_neon_vmaxv_s8(__p0);
57090	return __ret;	48379	return __ret;
57091	}	48380	}
57092	#else	48381	#else
57093	__ai int8_t vmaxv_s8(int8x8_t __p0) {	48382	__ai int8_t vmaxv_s8(int8x8_t __p0) {
57094	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48383	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57095	int8_t __ret;	48384	int8_t __ret;
57096	__ret = (int8_t) __builtin_neon_vmaxv_s8((int8x8_t)__rev0);	48385	__ret = (int8_t) __builtin_neon_vmaxv_s8(__rev0);
57097	return __ret;	48386	return __ret;
57098	}	48387	}
57099	#endif	48388	#endif
...	@@ -57101,14 +48390,14 @@ __ai int8_t vmaxv_s8(int8x8_t __p0) {	...	@@ -57101,14 +48390,14 @@ __ai int8_t vmaxv_s8(int8x8_t __p0) {
57101	#ifdef __LITTLE_ENDIAN__	48390	#ifdef __LITTLE_ENDIAN__
57102	__ai float32_t vmaxv_f32(float32x2_t __p0) {	48391	__ai float32_t vmaxv_f32(float32x2_t __p0) {
57103	float32_t __ret;	48392	float32_t __ret;
57104	__ret = (float32_t) __builtin_neon_vmaxv_f32((int8x8_t)__p0);	48393	__ret = (float32_t) __builtin_neon_vmaxv_f32(__p0);
57105	return __ret;	48394	return __ret;
57106	}	48395	}
57107	#else	48396	#else
57108	__ai float32_t vmaxv_f32(float32x2_t __p0) {	48397	__ai float32_t vmaxv_f32(float32x2_t __p0) {
57109	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48398	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57110	float32_t __ret;	48399	float32_t __ret;
57111	__ret = (float32_t) __builtin_neon_vmaxv_f32((int8x8_t)__rev0);	48400	__ret = (float32_t) __builtin_neon_vmaxv_f32(__rev0);
57112	return __ret;	48401	return __ret;
57113	}	48402	}
57114	#endif	48403	#endif
...	@@ -57116,14 +48405,14 @@ __ai float32_t vmaxv_f32(float32x2_t __p0) {	...	@@ -57116,14 +48405,14 @@ __ai float32_t vmaxv_f32(float32x2_t __p0) {
57116	#ifdef __LITTLE_ENDIAN__	48405	#ifdef __LITTLE_ENDIAN__
57117	__ai int32_t vmaxv_s32(int32x2_t __p0) {	48406	__ai int32_t vmaxv_s32(int32x2_t __p0) {
57118	int32_t __ret;	48407	int32_t __ret;
57119	__ret = (int32_t) __builtin_neon_vmaxv_s32((int8x8_t)__p0);	48408	__ret = (int32_t) __builtin_neon_vmaxv_s32(__p0);
57120	return __ret;	48409	return __ret;
57121	}	48410	}
57122	#else	48411	#else
57123	__ai int32_t vmaxv_s32(int32x2_t __p0) {	48412	__ai int32_t vmaxv_s32(int32x2_t __p0) {
57124	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48413	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57125	int32_t __ret;	48414	int32_t __ret;
57126	__ret = (int32_t) __builtin_neon_vmaxv_s32((int8x8_t)__rev0);	48415	__ret = (int32_t) __builtin_neon_vmaxv_s32(__rev0);
57127	return __ret;	48416	return __ret;
57128	}	48417	}
57129	#endif	48418	#endif
...	@@ -57131,14 +48420,14 @@ __ai int32_t vmaxv_s32(int32x2_t __p0) {	...	@@ -57131,14 +48420,14 @@ __ai int32_t vmaxv_s32(int32x2_t __p0) {
57131	#ifdef __LITTLE_ENDIAN__	48420	#ifdef __LITTLE_ENDIAN__
57132	__ai int16_t vmaxv_s16(int16x4_t __p0) {	48421	__ai int16_t vmaxv_s16(int16x4_t __p0) {
57133	int16_t __ret;	48422	int16_t __ret;
57134	__ret = (int16_t) __builtin_neon_vmaxv_s16((int8x8_t)__p0);	48423	__ret = (int16_t) __builtin_neon_vmaxv_s16(__p0);
57135	return __ret;	48424	return __ret;
57136	}	48425	}
57137	#else	48426	#else
57138	__ai int16_t vmaxv_s16(int16x4_t __p0) {	48427	__ai int16_t vmaxv_s16(int16x4_t __p0) {
57139	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48428	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57140	int16_t __ret;	48429	int16_t __ret;
57141	__ret = (int16_t) __builtin_neon_vmaxv_s16((int8x8_t)__rev0);	48430	__ret = (int16_t) __builtin_neon_vmaxv_s16(__rev0);
57142	return __ret;	48431	return __ret;
57143	}	48432	}
57144	#endif	48433	#endif
...	@@ -57160,31 +48449,22 @@ __ai float64x2_t vminq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -57160,31 +48449,22 @@ __ai float64x2_t vminq_f64(float64x2_t __p0, float64x2_t __p1) {
57160	}	48449	}
57161	#endif	48450	#endif
57162		48451
57163	#ifdef __LITTLE_ENDIAN__
57164	__ai float64x1_t vmin_f64(float64x1_t __p0, float64x1_t __p1) {
57165	float64x1_t __ret;
57166	__ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
57167	return __ret;
57168	}
57169	#else
57170	__ai float64x1_t vmin_f64(float64x1_t __p0, float64x1_t __p1) {	48452	__ai float64x1_t vmin_f64(float64x1_t __p0, float64x1_t __p1) {
57171	float64x1_t __ret;	48453	float64x1_t __ret;
57172	__ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	48454	__ret = (float64x1_t) __builtin_neon_vmin_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
57173	return __ret;	48455	return __ret;
57174	}	48456	}
57175	#endif
57176
57177	#ifdef __LITTLE_ENDIAN__	48457	#ifdef __LITTLE_ENDIAN__
57178	__ai float64_t vminnmvq_f64(float64x2_t __p0) {	48458	__ai float64_t vminnmvq_f64(float64x2_t __p0) {
57179	float64_t __ret;	48459	float64_t __ret;
57180	__ret = (float64_t) __builtin_neon_vminnmvq_f64((int8x16_t)__p0);	48460	__ret = (float64_t) __builtin_neon_vminnmvq_f64(__p0);
57181	return __ret;	48461	return __ret;
57182	}	48462	}
57183	#else	48463	#else
57184	__ai float64_t vminnmvq_f64(float64x2_t __p0) {	48464	__ai float64_t vminnmvq_f64(float64x2_t __p0) {
57185	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48465	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57186	float64_t __ret;	48466	float64_t __ret;
57187	__ret = (float64_t) __builtin_neon_vminnmvq_f64((int8x16_t)__rev0);	48467	__ret = (float64_t) __builtin_neon_vminnmvq_f64(__rev0);
57188	return __ret;	48468	return __ret;
57189	}	48469	}
57190	#endif	48470	#endif
...	@@ -57192,14 +48472,14 @@ __ai float64_t vminnmvq_f64(float64x2_t __p0) {	...	@@ -57192,14 +48472,14 @@ __ai float64_t vminnmvq_f64(float64x2_t __p0) {
57192	#ifdef __LITTLE_ENDIAN__	48472	#ifdef __LITTLE_ENDIAN__
57193	__ai float32_t vminnmvq_f32(float32x4_t __p0) {	48473	__ai float32_t vminnmvq_f32(float32x4_t __p0) {
57194	float32_t __ret;	48474	float32_t __ret;
57195	__ret = (float32_t) __builtin_neon_vminnmvq_f32((int8x16_t)__p0);	48475	__ret = (float32_t) __builtin_neon_vminnmvq_f32(__p0);
57196	return __ret;	48476	return __ret;
57197	}	48477	}
57198	#else	48478	#else
57199	__ai float32_t vminnmvq_f32(float32x4_t __p0) {	48479	__ai float32_t vminnmvq_f32(float32x4_t __p0) {
57200	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48480	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57201	float32_t __ret;	48481	float32_t __ret;
57202	__ret = (float32_t) __builtin_neon_vminnmvq_f32((int8x16_t)__rev0);	48482	__ret = (float32_t) __builtin_neon_vminnmvq_f32(__rev0);
57203	return __ret;	48483	return __ret;
57204	}	48484	}
57205	#endif	48485	#endif
...	@@ -57207,14 +48487,14 @@ __ai float32_t vminnmvq_f32(float32x4_t __p0) {	...	@@ -57207,14 +48487,14 @@ __ai float32_t vminnmvq_f32(float32x4_t __p0) {
57207	#ifdef __LITTLE_ENDIAN__	48487	#ifdef __LITTLE_ENDIAN__
57208	__ai float32_t vminnmv_f32(float32x2_t __p0) {	48488	__ai float32_t vminnmv_f32(float32x2_t __p0) {
57209	float32_t __ret;	48489	float32_t __ret;
57210	__ret = (float32_t) __builtin_neon_vminnmv_f32((int8x8_t)__p0);	48490	__ret = (float32_t) __builtin_neon_vminnmv_f32(__p0);
57211	return __ret;	48491	return __ret;
57212	}	48492	}
57213	#else	48493	#else
57214	__ai float32_t vminnmv_f32(float32x2_t __p0) {	48494	__ai float32_t vminnmv_f32(float32x2_t __p0) {
57215	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48495	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57216	float32_t __ret;	48496	float32_t __ret;
57217	__ret = (float32_t) __builtin_neon_vminnmv_f32((int8x8_t)__rev0);	48497	__ret = (float32_t) __builtin_neon_vminnmv_f32(__rev0);
57218	return __ret;	48498	return __ret;
57219	}	48499	}
57220	#endif	48500	#endif
...	@@ -57222,14 +48502,14 @@ __ai float32_t vminnmv_f32(float32x2_t __p0) {	...	@@ -57222,14 +48502,14 @@ __ai float32_t vminnmv_f32(float32x2_t __p0) {
57222	#ifdef __LITTLE_ENDIAN__	48502	#ifdef __LITTLE_ENDIAN__
57223	__ai uint8_t vminvq_u8(uint8x16_t __p0) {	48503	__ai uint8_t vminvq_u8(uint8x16_t __p0) {
57224	uint8_t __ret;	48504	uint8_t __ret;
57225	__ret = (uint8_t) __builtin_neon_vminvq_u8((int8x16_t)__p0);	48505	__ret = (uint8_t) __builtin_neon_vminvq_u8(__p0);
57226	return __ret;	48506	return __ret;
57227	}	48507	}
57228	#else	48508	#else
57229	__ai uint8_t vminvq_u8(uint8x16_t __p0) {	48509	__ai uint8_t vminvq_u8(uint8x16_t __p0) {
57230	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	48510	uint8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
57231	uint8_t __ret;	48511	uint8_t __ret;
57232	__ret = (uint8_t) __builtin_neon_vminvq_u8((int8x16_t)__rev0);	48512	__ret = (uint8_t) __builtin_neon_vminvq_u8(__rev0);
57233	return __ret;	48513	return __ret;
57234	}	48514	}
57235	#endif	48515	#endif
...	@@ -57237,14 +48517,14 @@ __ai uint8_t vminvq_u8(uint8x16_t __p0) {	...	@@ -57237,14 +48517,14 @@ __ai uint8_t vminvq_u8(uint8x16_t __p0) {
57237	#ifdef __LITTLE_ENDIAN__	48517	#ifdef __LITTLE_ENDIAN__
57238	__ai uint32_t vminvq_u32(uint32x4_t __p0) {	48518	__ai uint32_t vminvq_u32(uint32x4_t __p0) {
57239	uint32_t __ret;	48519	uint32_t __ret;
57240	__ret = (uint32_t) __builtin_neon_vminvq_u32((int8x16_t)__p0);	48520	__ret = (uint32_t) __builtin_neon_vminvq_u32(__p0);
57241	return __ret;	48521	return __ret;
57242	}	48522	}
57243	#else	48523	#else
57244	__ai uint32_t vminvq_u32(uint32x4_t __p0) {	48524	__ai uint32_t vminvq_u32(uint32x4_t __p0) {
57245	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48525	uint32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57246	uint32_t __ret;	48526	uint32_t __ret;
57247	__ret = (uint32_t) __builtin_neon_vminvq_u32((int8x16_t)__rev0);	48527	__ret = (uint32_t) __builtin_neon_vminvq_u32(__rev0);
57248	return __ret;	48528	return __ret;
57249	}	48529	}
57250	#endif	48530	#endif
...	@@ -57252,14 +48532,14 @@ __ai uint32_t vminvq_u32(uint32x4_t __p0) {	...	@@ -57252,14 +48532,14 @@ __ai uint32_t vminvq_u32(uint32x4_t __p0) {
57252	#ifdef __LITTLE_ENDIAN__	48532	#ifdef __LITTLE_ENDIAN__
57253	__ai uint16_t vminvq_u16(uint16x8_t __p0) {	48533	__ai uint16_t vminvq_u16(uint16x8_t __p0) {
57254	uint16_t __ret;	48534	uint16_t __ret;
57255	__ret = (uint16_t) __builtin_neon_vminvq_u16((int8x16_t)__p0);	48535	__ret = (uint16_t) __builtin_neon_vminvq_u16(__p0);
57256	return __ret;	48536	return __ret;
57257	}	48537	}
57258	#else	48538	#else
57259	__ai uint16_t vminvq_u16(uint16x8_t __p0) {	48539	__ai uint16_t vminvq_u16(uint16x8_t __p0) {
57260	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48540	uint16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57261	uint16_t __ret;	48541	uint16_t __ret;
57262	__ret = (uint16_t) __builtin_neon_vminvq_u16((int8x16_t)__rev0);	48542	__ret = (uint16_t) __builtin_neon_vminvq_u16(__rev0);
57263	return __ret;	48543	return __ret;
57264	}	48544	}
57265	#endif	48545	#endif
...	@@ -57267,14 +48547,14 @@ __ai uint16_t vminvq_u16(uint16x8_t __p0) {	...	@@ -57267,14 +48547,14 @@ __ai uint16_t vminvq_u16(uint16x8_t __p0) {
57267	#ifdef __LITTLE_ENDIAN__	48547	#ifdef __LITTLE_ENDIAN__
57268	__ai int8_t vminvq_s8(int8x16_t __p0) {	48548	__ai int8_t vminvq_s8(int8x16_t __p0) {
57269	int8_t __ret;	48549	int8_t __ret;
57270	__ret = (int8_t) __builtin_neon_vminvq_s8((int8x16_t)__p0);	48550	__ret = (int8_t) __builtin_neon_vminvq_s8(__p0);
57271	return __ret;	48551	return __ret;
57272	}	48552	}
57273	#else	48553	#else
57274	__ai int8_t vminvq_s8(int8x16_t __p0) {	48554	__ai int8_t vminvq_s8(int8x16_t __p0) {
57275	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	48555	int8x16_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
57276	int8_t __ret;	48556	int8_t __ret;
57277	__ret = (int8_t) __builtin_neon_vminvq_s8((int8x16_t)__rev0);	48557	__ret = (int8_t) __builtin_neon_vminvq_s8(__rev0);
57278	return __ret;	48558	return __ret;
57279	}	48559	}
57280	#endif	48560	#endif
...	@@ -57282,14 +48562,14 @@ __ai int8_t vminvq_s8(int8x16_t __p0) {	...	@@ -57282,14 +48562,14 @@ __ai int8_t vminvq_s8(int8x16_t __p0) {
57282	#ifdef __LITTLE_ENDIAN__	48562	#ifdef __LITTLE_ENDIAN__
57283	__ai float64_t vminvq_f64(float64x2_t __p0) {	48563	__ai float64_t vminvq_f64(float64x2_t __p0) {
57284	float64_t __ret;	48564	float64_t __ret;
57285	__ret = (float64_t) __builtin_neon_vminvq_f64((int8x16_t)__p0);	48565	__ret = (float64_t) __builtin_neon_vminvq_f64(__p0);
57286	return __ret;	48566	return __ret;
57287	}	48567	}
57288	#else	48568	#else
57289	__ai float64_t vminvq_f64(float64x2_t __p0) {	48569	__ai float64_t vminvq_f64(float64x2_t __p0) {
57290	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48570	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57291	float64_t __ret;	48571	float64_t __ret;
57292	__ret = (float64_t) __builtin_neon_vminvq_f64((int8x16_t)__rev0);	48572	__ret = (float64_t) __builtin_neon_vminvq_f64(__rev0);
57293	return __ret;	48573	return __ret;
57294	}	48574	}
57295	#endif	48575	#endif
...	@@ -57297,14 +48577,14 @@ __ai float64_t vminvq_f64(float64x2_t __p0) {	...	@@ -57297,14 +48577,14 @@ __ai float64_t vminvq_f64(float64x2_t __p0) {
57297	#ifdef __LITTLE_ENDIAN__	48577	#ifdef __LITTLE_ENDIAN__
57298	__ai float32_t vminvq_f32(float32x4_t __p0) {	48578	__ai float32_t vminvq_f32(float32x4_t __p0) {
57299	float32_t __ret;	48579	float32_t __ret;
57300	__ret = (float32_t) __builtin_neon_vminvq_f32((int8x16_t)__p0);	48580	__ret = (float32_t) __builtin_neon_vminvq_f32(__p0);
57301	return __ret;	48581	return __ret;
57302	}	48582	}
57303	#else	48583	#else
57304	__ai float32_t vminvq_f32(float32x4_t __p0) {	48584	__ai float32_t vminvq_f32(float32x4_t __p0) {
57305	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48585	float32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57306	float32_t __ret;	48586	float32_t __ret;
57307	__ret = (float32_t) __builtin_neon_vminvq_f32((int8x16_t)__rev0);	48587	__ret = (float32_t) __builtin_neon_vminvq_f32(__rev0);
57308	return __ret;	48588	return __ret;
57309	}	48589	}
57310	#endif	48590	#endif
...	@@ -57312,14 +48592,14 @@ __ai float32_t vminvq_f32(float32x4_t __p0) {	...	@@ -57312,14 +48592,14 @@ __ai float32_t vminvq_f32(float32x4_t __p0) {
57312	#ifdef __LITTLE_ENDIAN__	48592	#ifdef __LITTLE_ENDIAN__
57313	__ai int32_t vminvq_s32(int32x4_t __p0) {	48593	__ai int32_t vminvq_s32(int32x4_t __p0) {
57314	int32_t __ret;	48594	int32_t __ret;
57315	__ret = (int32_t) __builtin_neon_vminvq_s32((int8x16_t)__p0);	48595	__ret = (int32_t) __builtin_neon_vminvq_s32(__p0);
57316	return __ret;	48596	return __ret;
57317	}	48597	}
57318	#else	48598	#else
57319	__ai int32_t vminvq_s32(int32x4_t __p0) {	48599	__ai int32_t vminvq_s32(int32x4_t __p0) {
57320	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48600	int32x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57321	int32_t __ret;	48601	int32_t __ret;
57322	__ret = (int32_t) __builtin_neon_vminvq_s32((int8x16_t)__rev0);	48602	__ret = (int32_t) __builtin_neon_vminvq_s32(__rev0);
57323	return __ret;	48603	return __ret;
57324	}	48604	}
57325	#endif	48605	#endif
...	@@ -57327,14 +48607,14 @@ __ai int32_t vminvq_s32(int32x4_t __p0) {	...	@@ -57327,14 +48607,14 @@ __ai int32_t vminvq_s32(int32x4_t __p0) {
57327	#ifdef __LITTLE_ENDIAN__	48607	#ifdef __LITTLE_ENDIAN__
57328	__ai int16_t vminvq_s16(int16x8_t __p0) {	48608	__ai int16_t vminvq_s16(int16x8_t __p0) {
57329	int16_t __ret;	48609	int16_t __ret;
57330	__ret = (int16_t) __builtin_neon_vminvq_s16((int8x16_t)__p0);	48610	__ret = (int16_t) __builtin_neon_vminvq_s16(__p0);
57331	return __ret;	48611	return __ret;
57332	}	48612	}
57333	#else	48613	#else
57334	__ai int16_t vminvq_s16(int16x8_t __p0) {	48614	__ai int16_t vminvq_s16(int16x8_t __p0) {
57335	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48615	int16x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57336	int16_t __ret;	48616	int16_t __ret;
57337	__ret = (int16_t) __builtin_neon_vminvq_s16((int8x16_t)__rev0);	48617	__ret = (int16_t) __builtin_neon_vminvq_s16(__rev0);
57338	return __ret;	48618	return __ret;
57339	}	48619	}
57340	#endif	48620	#endif
...	@@ -57342,14 +48622,14 @@ __ai int16_t vminvq_s16(int16x8_t __p0) {	...	@@ -57342,14 +48622,14 @@ __ai int16_t vminvq_s16(int16x8_t __p0) {
57342	#ifdef __LITTLE_ENDIAN__	48622	#ifdef __LITTLE_ENDIAN__
57343	__ai uint8_t vminv_u8(uint8x8_t __p0) {	48623	__ai uint8_t vminv_u8(uint8x8_t __p0) {
57344	uint8_t __ret;	48624	uint8_t __ret;
57345	__ret = (uint8_t) __builtin_neon_vminv_u8((int8x8_t)__p0);	48625	__ret = (uint8_t) __builtin_neon_vminv_u8(__p0);
57346	return __ret;	48626	return __ret;
57347	}	48627	}
57348	#else	48628	#else
57349	__ai uint8_t vminv_u8(uint8x8_t __p0) {	48629	__ai uint8_t vminv_u8(uint8x8_t __p0) {
57350	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48630	uint8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57351	uint8_t __ret;	48631	uint8_t __ret;
57352	__ret = (uint8_t) __builtin_neon_vminv_u8((int8x8_t)__rev0);	48632	__ret = (uint8_t) __builtin_neon_vminv_u8(__rev0);
57353	return __ret;	48633	return __ret;
57354	}	48634	}
57355	#endif	48635	#endif
...	@@ -57357,14 +48637,14 @@ __ai uint8_t vminv_u8(uint8x8_t __p0) {	...	@@ -57357,14 +48637,14 @@ __ai uint8_t vminv_u8(uint8x8_t __p0) {
57357	#ifdef __LITTLE_ENDIAN__	48637	#ifdef __LITTLE_ENDIAN__
57358	__ai uint32_t vminv_u32(uint32x2_t __p0) {	48638	__ai uint32_t vminv_u32(uint32x2_t __p0) {
57359	uint32_t __ret;	48639	uint32_t __ret;
57360	__ret = (uint32_t) __builtin_neon_vminv_u32((int8x8_t)__p0);	48640	__ret = (uint32_t) __builtin_neon_vminv_u32(__p0);
57361	return __ret;	48641	return __ret;
57362	}	48642	}
57363	#else	48643	#else
57364	__ai uint32_t vminv_u32(uint32x2_t __p0) {	48644	__ai uint32_t vminv_u32(uint32x2_t __p0) {
57365	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48645	uint32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57366	uint32_t __ret;	48646	uint32_t __ret;
57367	__ret = (uint32_t) __builtin_neon_vminv_u32((int8x8_t)__rev0);	48647	__ret = (uint32_t) __builtin_neon_vminv_u32(__rev0);
57368	return __ret;	48648	return __ret;
57369	}	48649	}
57370	#endif	48650	#endif
...	@@ -57372,14 +48652,14 @@ __ai uint32_t vminv_u32(uint32x2_t __p0) {	...	@@ -57372,14 +48652,14 @@ __ai uint32_t vminv_u32(uint32x2_t __p0) {
57372	#ifdef __LITTLE_ENDIAN__	48652	#ifdef __LITTLE_ENDIAN__
57373	__ai uint16_t vminv_u16(uint16x4_t __p0) {	48653	__ai uint16_t vminv_u16(uint16x4_t __p0) {
57374	uint16_t __ret;	48654	uint16_t __ret;
57375	__ret = (uint16_t) __builtin_neon_vminv_u16((int8x8_t)__p0);	48655	__ret = (uint16_t) __builtin_neon_vminv_u16(__p0);
57376	return __ret;	48656	return __ret;
57377	}	48657	}
57378	#else	48658	#else
57379	__ai uint16_t vminv_u16(uint16x4_t __p0) {	48659	__ai uint16_t vminv_u16(uint16x4_t __p0) {
57380	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48660	uint16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57381	uint16_t __ret;	48661	uint16_t __ret;
57382	__ret = (uint16_t) __builtin_neon_vminv_u16((int8x8_t)__rev0);	48662	__ret = (uint16_t) __builtin_neon_vminv_u16(__rev0);
57383	return __ret;	48663	return __ret;
57384	}	48664	}
57385	#endif	48665	#endif
...	@@ -57387,14 +48667,14 @@ __ai uint16_t vminv_u16(uint16x4_t __p0) {	...	@@ -57387,14 +48667,14 @@ __ai uint16_t vminv_u16(uint16x4_t __p0) {
57387	#ifdef __LITTLE_ENDIAN__	48667	#ifdef __LITTLE_ENDIAN__
57388	__ai int8_t vminv_s8(int8x8_t __p0) {	48668	__ai int8_t vminv_s8(int8x8_t __p0) {
57389	int8_t __ret;	48669	int8_t __ret;
57390	__ret = (int8_t) __builtin_neon_vminv_s8((int8x8_t)__p0);	48670	__ret = (int8_t) __builtin_neon_vminv_s8(__p0);
57391	return __ret;	48671	return __ret;
57392	}	48672	}
57393	#else	48673	#else
57394	__ai int8_t vminv_s8(int8x8_t __p0) {	48674	__ai int8_t vminv_s8(int8x8_t __p0) {
57395	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);	48675	int8x8_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 7, 6, 5, 4, 3, 2, 1, 0);
57396	int8_t __ret;	48676	int8_t __ret;
57397	__ret = (int8_t) __builtin_neon_vminv_s8((int8x8_t)__rev0);	48677	__ret = (int8_t) __builtin_neon_vminv_s8(__rev0);
57398	return __ret;	48678	return __ret;
57399	}	48679	}
57400	#endif	48680	#endif
...	@@ -57402,14 +48682,14 @@ __ai int8_t vminv_s8(int8x8_t __p0) {	...	@@ -57402,14 +48682,14 @@ __ai int8_t vminv_s8(int8x8_t __p0) {
57402	#ifdef __LITTLE_ENDIAN__	48682	#ifdef __LITTLE_ENDIAN__
57403	__ai float32_t vminv_f32(float32x2_t __p0) {	48683	__ai float32_t vminv_f32(float32x2_t __p0) {
57404	float32_t __ret;	48684	float32_t __ret;
57405	__ret = (float32_t) __builtin_neon_vminv_f32((int8x8_t)__p0);	48685	__ret = (float32_t) __builtin_neon_vminv_f32(__p0);
57406	return __ret;	48686	return __ret;
57407	}	48687	}
57408	#else	48688	#else
57409	__ai float32_t vminv_f32(float32x2_t __p0) {	48689	__ai float32_t vminv_f32(float32x2_t __p0) {
57410	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48690	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57411	float32_t __ret;	48691	float32_t __ret;
57412	__ret = (float32_t) __builtin_neon_vminv_f32((int8x8_t)__rev0);	48692	__ret = (float32_t) __builtin_neon_vminv_f32(__rev0);
57413	return __ret;	48693	return __ret;
57414	}	48694	}
57415	#endif	48695	#endif
...	@@ -57417,14 +48697,14 @@ __ai float32_t vminv_f32(float32x2_t __p0) {	...	@@ -57417,14 +48697,14 @@ __ai float32_t vminv_f32(float32x2_t __p0) {
57417	#ifdef __LITTLE_ENDIAN__	48697	#ifdef __LITTLE_ENDIAN__
57418	__ai int32_t vminv_s32(int32x2_t __p0) {	48698	__ai int32_t vminv_s32(int32x2_t __p0) {
57419	int32_t __ret;	48699	int32_t __ret;
57420	__ret = (int32_t) __builtin_neon_vminv_s32((int8x8_t)__p0);	48700	__ret = (int32_t) __builtin_neon_vminv_s32(__p0);
57421	return __ret;	48701	return __ret;
57422	}	48702	}
57423	#else	48703	#else
57424	__ai int32_t vminv_s32(int32x2_t __p0) {	48704	__ai int32_t vminv_s32(int32x2_t __p0) {
57425	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	48705	int32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
57426	int32_t __ret;	48706	int32_t __ret;
57427	__ret = (int32_t) __builtin_neon_vminv_s32((int8x8_t)__rev0);	48707	__ret = (int32_t) __builtin_neon_vminv_s32(__rev0);
57428	return __ret;	48708	return __ret;
57429	}	48709	}
57430	#endif	48710	#endif
...	@@ -57432,14 +48712,14 @@ __ai int32_t vminv_s32(int32x2_t __p0) {	...	@@ -57432,14 +48712,14 @@ __ai int32_t vminv_s32(int32x2_t __p0) {
57432	#ifdef __LITTLE_ENDIAN__	48712	#ifdef __LITTLE_ENDIAN__
57433	__ai int16_t vminv_s16(int16x4_t __p0) {	48713	__ai int16_t vminv_s16(int16x4_t __p0) {
57434	int16_t __ret;	48714	int16_t __ret;
57435	__ret = (int16_t) __builtin_neon_vminv_s16((int8x8_t)__p0);	48715	__ret = (int16_t) __builtin_neon_vminv_s16(__p0);
57436	return __ret;	48716	return __ret;
57437	}	48717	}
57438	#else	48718	#else
57439	__ai int16_t vminv_s16(int16x4_t __p0) {	48719	__ai int16_t vminv_s16(int16x4_t __p0) {
57440	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);	48720	int16x4_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 3, 2, 1, 0);
57441	int16_t __ret;	48721	int16_t __ret;
57442	__ret = (int16_t) __builtin_neon_vminv_s16((int8x8_t)__rev0);	48722	__ret = (int16_t) __builtin_neon_vminv_s16(__rev0);
57443	return __ret;	48723	return __ret;
57444	}	48724	}
57445	#endif	48725	#endif
...	@@ -57462,20 +48742,11 @@ __ai float64x2_t vmlaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)	...	@@ -57462,20 +48742,11 @@ __ai float64x2_t vmlaq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)
57462	}	48742	}
57463	#endif	48743	#endif
57464		48744
57465	#ifdef __LITTLE_ENDIAN__
57466	__ai float64x1_t vmla_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	48745	__ai float64x1_t vmla_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
57467	float64x1_t __ret;	48746	float64x1_t __ret;
57468	__ret = __p0 + __p1 * __p2;	48747	__ret = __p0 + __p1 * __p2;
57469	return __ret;	48748	return __ret;
57470	}	48749	}
57471	#else
57472	__ai float64x1_t vmla_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
57473	float64x1_t __ret;
57474	__ret = __p0 + __p1 * __p2;
57475	return __ret;
57476	}
57477	#endif
57478
57479	#ifdef __LITTLE_ENDIAN__	48750	#ifdef __LITTLE_ENDIAN__
57480	#define vmlaq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \	48751	#define vmlaq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
57481	uint32x4_t __s0 = __p0; \	48752	uint32x4_t __s0 = __p0; \
...	@@ -58039,20 +49310,11 @@ __ai float64x2_t vmlsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)	...	@@ -58039,20 +49310,11 @@ __ai float64x2_t vmlsq_f64(float64x2_t __p0, float64x2_t __p1, float64x2_t __p2)
58039	}	49310	}
58040	#endif	49311	#endif
58041		49312
58042	#ifdef __LITTLE_ENDIAN__
58043	__ai float64x1_t vmls_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {	49313	__ai float64x1_t vmls_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
58044	float64x1_t __ret;	49314	float64x1_t __ret;
58045	__ret = __p0 - __p1 * __p2;	49315	__ret = __p0 - __p1 * __p2;
58046	return __ret;	49316	return __ret;
58047	}	49317	}
58048	#else
58049	__ai float64x1_t vmls_f64(float64x1_t __p0, float64x1_t __p1, float64x1_t __p2) {
58050	float64x1_t __ret;
58051	__ret = __p0 - __p1 * __p2;
58052	return __ret;
58053	}
58054	#endif
58055
58056	#ifdef __LITTLE_ENDIAN__	49318	#ifdef __LITTLE_ENDIAN__
58057	#define vmlsq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \	49319	#define vmlsq_laneq_u32(__p0, __p1, __p2, __p3) __extension__ ({ \
58058	uint32x4_t __s0 = __p0; \	49320	uint32x4_t __s0 = __p0; \
...	@@ -58598,20 +49860,11 @@ __ai float64x2_t vmlsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2)	...	@@ -58598,20 +49860,11 @@ __ai float64x2_t vmlsq_n_f64(float64x2_t __p0, float64x2_t __p1, float64_t __p2)
58598	})	49860	})
58599	#endif	49861	#endif
58600		49862
58601	#ifdef __LITTLE_ENDIAN__
58602	__ai poly64x1_t vmov_n_p64(poly64_t __p0) {
58603	poly64x1_t __ret;
58604	__ret = (poly64x1_t) {__p0};
58605	return __ret;
58606	}
58607	#else
58608	__ai poly64x1_t vmov_n_p64(poly64_t __p0) {	49863	__ai poly64x1_t vmov_n_p64(poly64_t __p0) {
58609	poly64x1_t __ret;	49864	poly64x1_t __ret;
58610	__ret = (poly64x1_t) {__p0};	49865	__ret = (poly64x1_t) {__p0};
58611	return __ret;	49866	return __ret;
58612	}	49867	}
58613	#endif
58614
58615	#ifdef __LITTLE_ENDIAN__	49868	#ifdef __LITTLE_ENDIAN__
58616	__ai poly64x2_t vmovq_n_p64(poly64_t __p0) {	49869	__ai poly64x2_t vmovq_n_p64(poly64_t __p0) {
58617	poly64x2_t __ret;	49870	poly64x2_t __ret;
...	@@ -58642,161 +49895,152 @@ __ai float64x2_t vmovq_n_f64(float64_t __p0) {	...	@@ -58642,161 +49895,152 @@ __ai float64x2_t vmovq_n_f64(float64_t __p0) {
58642	}	49895	}
58643	#endif	49896	#endif
58644		49897
58645	#ifdef __LITTLE_ENDIAN__
58646	__ai float64x1_t vmov_n_f64(float64_t __p0) {	49898	__ai float64x1_t vmov_n_f64(float64_t __p0) {
58647	float64x1_t __ret;	49899	float64x1_t __ret;
58648	__ret = (float64x1_t) {__p0};	49900	__ret = (float64x1_t) {__p0};
58649	return __ret;	49901	return __ret;
58650	}	49902	}
58651	#else
58652	__ai float64x1_t vmov_n_f64(float64_t __p0) {
58653	float64x1_t __ret;
58654	__ret = (float64x1_t) {__p0};
58655	return __ret;
58656	}
58657	#endif
58658
58659	#ifdef __LITTLE_ENDIAN__	49903	#ifdef __LITTLE_ENDIAN__
58660	__ai uint16x8_t vmovl_high_u8(uint8x16_t __p0_124) {	49904	__ai uint16x8_t vmovl_high_u8(uint8x16_t __p0_120) {
58661	uint16x8_t __ret_124;	49905	uint16x8_t __ret_120;
58662	uint8x8_t __a1_124 = vget_high_u8(__p0_124);	49906	uint8x8_t __a1_120 = vget_high_u8(__p0_120);
58663	__ret_124 = (uint16x8_t)(vshll_n_u8(__a1_124, 0));	49907	__ret_120 = (uint16x8_t)(vshll_n_u8(__a1_120, 0));
58664	return __ret_124;	49908	return __ret_120;
58665	}	49909	}
58666	#else	49910	#else
58667	__ai uint16x8_t vmovl_high_u8(uint8x16_t __p0_125) {	49911	__ai uint16x8_t vmovl_high_u8(uint8x16_t __p0_121) {
58668	uint8x16_t __rev0_125; __rev0_125 = __builtin_shufflevector(__p0_125, __p0_125, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	49912	uint8x16_t __rev0_121; __rev0_121 = __builtin_shufflevector(__p0_121, __p0_121, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
58669	uint16x8_t __ret_125;	49913	uint16x8_t __ret_121;
58670	uint8x8_t __a1_125 = __noswap_vget_high_u8(__rev0_125);	49914	uint8x8_t __a1_121 = __noswap_vget_high_u8(__rev0_121);
58671	__ret_125 = (uint16x8_t)(__noswap_vshll_n_u8(__a1_125, 0));	49915	__ret_121 = (uint16x8_t)(__noswap_vshll_n_u8(__a1_121, 0));
58672	__ret_125 = __builtin_shufflevector(__ret_125, __ret_125, 7, 6, 5, 4, 3, 2, 1, 0);	49916	__ret_121 = __builtin_shufflevector(__ret_121, __ret_121, 7, 6, 5, 4, 3, 2, 1, 0);
58673	return __ret_125;	49917	return __ret_121;
58674	}	49918	}
58675	__ai uint16x8_t __noswap_vmovl_high_u8(uint8x16_t __p0_126) {	49919	__ai uint16x8_t __noswap_vmovl_high_u8(uint8x16_t __p0_122) {
58676	uint16x8_t __ret_126;	49920	uint16x8_t __ret_122;
58677	uint8x8_t __a1_126 = __noswap_vget_high_u8(__p0_126);	49921	uint8x8_t __a1_122 = __noswap_vget_high_u8(__p0_122);
58678	__ret_126 = (uint16x8_t)(__noswap_vshll_n_u8(__a1_126, 0));	49922	__ret_122 = (uint16x8_t)(__noswap_vshll_n_u8(__a1_122, 0));
58679	return __ret_126;	49923	return __ret_122;
58680	}	49924	}
58681	#endif	49925	#endif
58682		49926
58683	#ifdef __LITTLE_ENDIAN__	49927	#ifdef __LITTLE_ENDIAN__
58684	__ai uint64x2_t vmovl_high_u32(uint32x4_t __p0_127) {	49928	__ai uint64x2_t vmovl_high_u32(uint32x4_t __p0_123) {
58685	uint64x2_t __ret_127;	49929	uint64x2_t __ret_123;
58686	uint32x2_t __a1_127 = vget_high_u32(__p0_127);	49930	uint32x2_t __a1_123 = vget_high_u32(__p0_123);
58687	__ret_127 = (uint64x2_t)(vshll_n_u32(__a1_127, 0));	49931	__ret_123 = (uint64x2_t)(vshll_n_u32(__a1_123, 0));
58688	return __ret_127;	49932	return __ret_123;
58689	}	49933	}
58690	#else	49934	#else
58691	__ai uint64x2_t vmovl_high_u32(uint32x4_t __p0_128) {	49935	__ai uint64x2_t vmovl_high_u32(uint32x4_t __p0_124) {
58692	uint32x4_t __rev0_128; __rev0_128 = __builtin_shufflevector(__p0_128, __p0_128, 3, 2, 1, 0);	49936	uint32x4_t __rev0_124; __rev0_124 = __builtin_shufflevector(__p0_124, __p0_124, 3, 2, 1, 0);
58693	uint64x2_t __ret_128;	49937	uint64x2_t __ret_124;
58694	uint32x2_t __a1_128 = __noswap_vget_high_u32(__rev0_128);	49938	uint32x2_t __a1_124 = __noswap_vget_high_u32(__rev0_124);
58695	__ret_128 = (uint64x2_t)(__noswap_vshll_n_u32(__a1_128, 0));	49939	__ret_124 = (uint64x2_t)(__noswap_vshll_n_u32(__a1_124, 0));
58696	__ret_128 = __builtin_shufflevector(__ret_128, __ret_128, 1, 0);	49940	__ret_124 = __builtin_shufflevector(__ret_124, __ret_124, 1, 0);
58697	return __ret_128;	49941	return __ret_124;
58698	}	49942	}
58699	__ai uint64x2_t __noswap_vmovl_high_u32(uint32x4_t __p0_129) {	49943	__ai uint64x2_t __noswap_vmovl_high_u32(uint32x4_t __p0_125) {
58700	uint64x2_t __ret_129;	49944	uint64x2_t __ret_125;
58701	uint32x2_t __a1_129 = __noswap_vget_high_u32(__p0_129);	49945	uint32x2_t __a1_125 = __noswap_vget_high_u32(__p0_125);
58702	__ret_129 = (uint64x2_t)(__noswap_vshll_n_u32(__a1_129, 0));	49946	__ret_125 = (uint64x2_t)(__noswap_vshll_n_u32(__a1_125, 0));
58703	return __ret_129;	49947	return __ret_125;
58704	}	49948	}
58705	#endif	49949	#endif
58706		49950
58707	#ifdef __LITTLE_ENDIAN__	49951	#ifdef __LITTLE_ENDIAN__
58708	__ai uint32x4_t vmovl_high_u16(uint16x8_t __p0_130) {	49952	__ai uint32x4_t vmovl_high_u16(uint16x8_t __p0_126) {
58709	uint32x4_t __ret_130;	49953	uint32x4_t __ret_126;
58710	uint16x4_t __a1_130 = vget_high_u16(__p0_130);	49954	uint16x4_t __a1_126 = vget_high_u16(__p0_126);
58711	__ret_130 = (uint32x4_t)(vshll_n_u16(__a1_130, 0));	49955	__ret_126 = (uint32x4_t)(vshll_n_u16(__a1_126, 0));
58712	return __ret_130;	49956	return __ret_126;
58713	}	49957	}
58714	#else	49958	#else
58715	__ai uint32x4_t vmovl_high_u16(uint16x8_t __p0_131) {	49959	__ai uint32x4_t vmovl_high_u16(uint16x8_t __p0_127) {
58716	uint16x8_t __rev0_131; __rev0_131 = __builtin_shufflevector(__p0_131, __p0_131, 7, 6, 5, 4, 3, 2, 1, 0);	49960	uint16x8_t __rev0_127; __rev0_127 = __builtin_shufflevector(__p0_127, __p0_127, 7, 6, 5, 4, 3, 2, 1, 0);
58717	uint32x4_t __ret_131;	49961	uint32x4_t __ret_127;
58718	uint16x4_t __a1_131 = __noswap_vget_high_u16(__rev0_131);	49962	uint16x4_t __a1_127 = __noswap_vget_high_u16(__rev0_127);
58719	__ret_131 = (uint32x4_t)(__noswap_vshll_n_u16(__a1_131, 0));	49963	__ret_127 = (uint32x4_t)(__noswap_vshll_n_u16(__a1_127, 0));
58720	__ret_131 = __builtin_shufflevector(__ret_131, __ret_131, 3, 2, 1, 0);	49964	__ret_127 = __builtin_shufflevector(__ret_127, __ret_127, 3, 2, 1, 0);
58721	return __ret_131;	49965	return __ret_127;
58722	}	49966	}
58723	__ai uint32x4_t __noswap_vmovl_high_u16(uint16x8_t __p0_132) {	49967	__ai uint32x4_t __noswap_vmovl_high_u16(uint16x8_t __p0_128) {
58724	uint32x4_t __ret_132;	49968	uint32x4_t __ret_128;
58725	uint16x4_t __a1_132 = __noswap_vget_high_u16(__p0_132);	49969	uint16x4_t __a1_128 = __noswap_vget_high_u16(__p0_128);
58726	__ret_132 = (uint32x4_t)(__noswap_vshll_n_u16(__a1_132, 0));	49970	__ret_128 = (uint32x4_t)(__noswap_vshll_n_u16(__a1_128, 0));
58727	return __ret_132;	49971	return __ret_128;
58728	}	49972	}
58729	#endif	49973	#endif
58730		49974
58731	#ifdef __LITTLE_ENDIAN__	49975	#ifdef __LITTLE_ENDIAN__
58732	__ai int16x8_t vmovl_high_s8(int8x16_t __p0_133) {	49976	__ai int16x8_t vmovl_high_s8(int8x16_t __p0_129) {
58733	int16x8_t __ret_133;	49977	int16x8_t __ret_129;
58734	int8x8_t __a1_133 = vget_high_s8(__p0_133);	49978	int8x8_t __a1_129 = vget_high_s8(__p0_129);
58735	__ret_133 = (int16x8_t)(vshll_n_s8(__a1_133, 0));	49979	__ret_129 = (int16x8_t)(vshll_n_s8(__a1_129, 0));
58736	return __ret_133;	49980	return __ret_129;
58737	}	49981	}
58738	#else	49982	#else
58739	__ai int16x8_t vmovl_high_s8(int8x16_t __p0_134) {	49983	__ai int16x8_t vmovl_high_s8(int8x16_t __p0_130) {
58740	int8x16_t __rev0_134; __rev0_134 = __builtin_shufflevector(__p0_134, __p0_134, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);	49984	int8x16_t __rev0_130; __rev0_130 = __builtin_shufflevector(__p0_130, __p0_130, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0);
58741	int16x8_t __ret_134;	49985	int16x8_t __ret_130;
58742	int8x8_t __a1_134 = __noswap_vget_high_s8(__rev0_134);	49986	int8x8_t __a1_130 = __noswap_vget_high_s8(__rev0_130);
58743	__ret_134 = (int16x8_t)(__noswap_vshll_n_s8(__a1_134, 0));	49987	__ret_130 = (int16x8_t)(__noswap_vshll_n_s8(__a1_130, 0));
58744	__ret_134 = __builtin_shufflevector(__ret_134, __ret_134, 7, 6, 5, 4, 3, 2, 1, 0);	49988	__ret_130 = __builtin_shufflevector(__ret_130, __ret_130, 7, 6, 5, 4, 3, 2, 1, 0);
58745	return __ret_134;	49989	return __ret_130;
58746	}	49990	}
58747	__ai int16x8_t __noswap_vmovl_high_s8(int8x16_t __p0_135) {	49991	__ai int16x8_t __noswap_vmovl_high_s8(int8x16_t __p0_131) {
58748	int16x8_t __ret_135;	49992	int16x8_t __ret_131;
58749	int8x8_t __a1_135 = __noswap_vget_high_s8(__p0_135);	49993	int8x8_t __a1_131 = __noswap_vget_high_s8(__p0_131);
58750	__ret_135 = (int16x8_t)(__noswap_vshll_n_s8(__a1_135, 0));	49994	__ret_131 = (int16x8_t)(__noswap_vshll_n_s8(__a1_131, 0));
58751	return __ret_135;	49995	return __ret_131;
58752	}	49996	}
58753	#endif	49997	#endif
58754		49998
58755	#ifdef __LITTLE_ENDIAN__	49999	#ifdef __LITTLE_ENDIAN__
58756	__ai int64x2_t vmovl_high_s32(int32x4_t __p0_136) {	50000	__ai int64x2_t vmovl_high_s32(int32x4_t __p0_132) {
58757	int64x2_t __ret_136;	50001	int64x2_t __ret_132;
58758	int32x2_t __a1_136 = vget_high_s32(__p0_136);	50002	int32x2_t __a1_132 = vget_high_s32(__p0_132);
58759	__ret_136 = (int64x2_t)(vshll_n_s32(__a1_136, 0));	50003	__ret_132 = (int64x2_t)(vshll_n_s32(__a1_132, 0));
58760	return __ret_136;	50004	return __ret_132;
58761	}	50005	}
58762	#else	50006	#else
58763	__ai int64x2_t vmovl_high_s32(int32x4_t __p0_137) {	50007	__ai int64x2_t vmovl_high_s32(int32x4_t __p0_133) {
58764	int32x4_t __rev0_137; __rev0_137 = __builtin_shufflevector(__p0_137, __p0_137, 3, 2, 1, 0);	50008	int32x4_t __rev0_133; __rev0_133 = __builtin_shufflevector(__p0_133, __p0_133, 3, 2, 1, 0);
58765	int64x2_t __ret_137;	50009	int64x2_t __ret_133;
58766	int32x2_t __a1_137 = __noswap_vget_high_s32(__rev0_137);	50010	int32x2_t __a1_133 = __noswap_vget_high_s32(__rev0_133);
58767	__ret_137 = (int64x2_t)(__noswap_vshll_n_s32(__a1_137, 0));	50011	__ret_133 = (int64x2_t)(__noswap_vshll_n_s32(__a1_133, 0));
58768	__ret_137 = __builtin_shufflevector(__ret_137, __ret_137, 1, 0);	50012	__ret_133 = __builtin_shufflevector(__ret_133, __ret_133, 1, 0);
58769	return __ret_137;	50013	return __ret_133;
58770	}	50014	}
58771	__ai int64x2_t __noswap_vmovl_high_s32(int32x4_t __p0_138) {	50015	__ai int64x2_t __noswap_vmovl_high_s32(int32x4_t __p0_134) {
58772	int64x2_t __ret_138;	50016	int64x2_t __ret_134;
58773	int32x2_t __a1_138 = __noswap_vget_high_s32(__p0_138);	50017	int32x2_t __a1_134 = __noswap_vget_high_s32(__p0_134);
58774	__ret_138 = (int64x2_t)(__noswap_vshll_n_s32(__a1_138, 0));	50018	__ret_134 = (int64x2_t)(__noswap_vshll_n_s32(__a1_134, 0));
58775	return __ret_138;	50019	return __ret_134;
58776	}	50020	}
58777	#endif	50021	#endif
58778		50022
58779	#ifdef __LITTLE_ENDIAN__	50023	#ifdef __LITTLE_ENDIAN__
58780	__ai int32x4_t vmovl_high_s16(int16x8_t __p0_139) {	50024	__ai int32x4_t vmovl_high_s16(int16x8_t __p0_135) {
58781	int32x4_t __ret_139;	50025	int32x4_t __ret_135;
58782	int16x4_t __a1_139 = vget_high_s16(__p0_139);	50026	int16x4_t __a1_135 = vget_high_s16(__p0_135);
58783	__ret_139 = (int32x4_t)(vshll_n_s16(__a1_139, 0));	50027	__ret_135 = (int32x4_t)(vshll_n_s16(__a1_135, 0));
58784	return __ret_139;	50028	return __ret_135;
58785	}	50029	}
58786	#else	50030	#else
58787	__ai int32x4_t vmovl_high_s16(int16x8_t __p0_140) {	50031	__ai int32x4_t vmovl_high_s16(int16x8_t __p0_136) {
58788	int16x8_t __rev0_140; __rev0_140 = __builtin_shufflevector(__p0_140, __p0_140, 7, 6, 5, 4, 3, 2, 1, 0);	50032	int16x8_t __rev0_136; __rev0_136 = __builtin_shufflevector(__p0_136, __p0_136, 7, 6, 5, 4, 3, 2, 1, 0);
58789	int32x4_t __ret_140;	50033	int32x4_t __ret_136;
58790	int16x4_t __a1_140 = __noswap_vget_high_s16(__rev0_140);	50034	int16x4_t __a1_136 = __noswap_vget_high_s16(__rev0_136);
58791	__ret_140 = (int32x4_t)(__noswap_vshll_n_s16(__a1_140, 0));	50035	__ret_136 = (int32x4_t)(__noswap_vshll_n_s16(__a1_136, 0));
58792	__ret_140 = __builtin_shufflevector(__ret_140, __ret_140, 3, 2, 1, 0);	50036	__ret_136 = __builtin_shufflevector(__ret_136, __ret_136, 3, 2, 1, 0);
58793	return __ret_140;	50037	return __ret_136;
58794	}	50038	}
58795	__ai int32x4_t __noswap_vmovl_high_s16(int16x8_t __p0_141) {	50039	__ai int32x4_t __noswap_vmovl_high_s16(int16x8_t __p0_137) {
58796	int32x4_t __ret_141;	50040	int32x4_t __ret_137;
58797	int16x4_t __a1_141 = __noswap_vget_high_s16(__p0_141);	50041	int16x4_t __a1_137 = __noswap_vget_high_s16(__p0_137);
58798	__ret_141 = (int32x4_t)(__noswap_vshll_n_s16(__a1_141, 0));	50042	__ret_137 = (int32x4_t)(__noswap_vshll_n_s16(__a1_137, 0));
58799	return __ret_141;	50043	return __ret_137;
58800	}	50044	}
58801	#endif	50045	#endif
58802		50046
...	@@ -58919,66 +50163,37 @@ __ai float64x2_t vmulq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -58919,66 +50163,37 @@ __ai float64x2_t vmulq_f64(float64x2_t __p0, float64x2_t __p1) {
58919	}	50163	}
58920	#endif	50164	#endif
58921		50165
58922	#ifdef __LITTLE_ENDIAN__
58923	__ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {	50166	__ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
58924	float64x1_t __ret;	50167	float64x1_t __ret;
58925	__ret = __p0 * __p1;	50168	__ret = __p0 * __p1;
58926	return __ret;	50169	return __ret;
58927	}	50170	}
58928	#else	50171	#define vmuld_lane_f64(__p0_138, __p1_138, __p2_138) __extension__ ({ \
58929	__ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {	50172	float64_t __s0_138 = __p0_138; \
58930	float64x1_t __ret;	50173	float64x1_t __s1_138 = __p1_138; \
58931	__ret = __p0 * __p1;	50174	float64_t __ret_138; \
58932	return __ret;	50175	__ret_138 = __s0_138 * vget_lane_f64(__s1_138, __p2_138); \
58933	}	50176	__ret_138; \
58934	#endif
58935
58936	#ifdef __LITTLE_ENDIAN__
58937	#define vmuld_lane_f64(__p0_142, __p1_142, __p2_142) __extension__ ({ \
58938	float64_t __s0_142 = __p0_142; \
58939	float64x1_t __s1_142 = __p1_142; \
58940	float64_t __ret_142; \
58941	__ret_142 = __s0_142 * vget_lane_f64(__s1_142, __p2_142); \
58942	__ret_142; \
58943	})	50177	})
58944	#else
58945	#define vmuld_lane_f64(__p0_143, __p1_143, __p2_143) __extension__ ({ \
58946	float64_t __s0_143 = __p0_143; \
58947	float64x1_t __s1_143 = __p1_143; \
58948	float64_t __ret_143; \
58949	__ret_143 = __s0_143 * __noswap_vget_lane_f64(__s1_143, __p2_143); \
58950	__ret_143; \
58951	})
58952	#endif
58953
58954	#ifdef __LITTLE_ENDIAN__	50178	#ifdef __LITTLE_ENDIAN__
58955	#define vmuls_lane_f32(__p0_144, __p1_144, __p2_144) __extension__ ({ \	50179	#define vmuls_lane_f32(__p0_139, __p1_139, __p2_139) __extension__ ({ \
58956	float32_t __s0_144 = __p0_144; \	50180	float32_t __s0_139 = __p0_139; \
58957	float32x2_t __s1_144 = __p1_144; \	50181	float32x2_t __s1_139 = __p1_139; \
58958	float32_t __ret_144; \	50182	float32_t __ret_139; \
58959	__ret_144 = __s0_144 * vget_lane_f32(__s1_144, __p2_144); \	50183	__ret_139 = __s0_139 * vget_lane_f32(__s1_139, __p2_139); \
58960	__ret_144; \	50184	__ret_139; \
58961	})	50185	})
58962	#else	50186	#else
58963	#define vmuls_lane_f32(__p0_145, __p1_145, __p2_145) __extension__ ({ \	50187	#define vmuls_lane_f32(__p0_140, __p1_140, __p2_140) __extension__ ({ \
58964	float32_t __s0_145 = __p0_145; \	50188	float32_t __s0_140 = __p0_140; \
58965	float32x2_t __s1_145 = __p1_145; \	50189	float32x2_t __s1_140 = __p1_140; \
58966	float32x2_t __rev1_145; __rev1_145 = __builtin_shufflevector(__s1_145, __s1_145, 1, 0); \	50190	float32x2_t __rev1_140; __rev1_140 = __builtin_shufflevector(__s1_140, __s1_140, 1, 0); \
58967	float32_t __ret_145; \	50191	float32_t __ret_140; \
58968	__ret_145 = __s0_145 * __noswap_vget_lane_f32(__rev1_145, __p2_145); \	50192	__ret_140 = __s0_140 * __noswap_vget_lane_f32(__rev1_140, __p2_140); \
58969	__ret_145; \	50193	__ret_140; \
58970	})	50194	})
58971	#endif	50195	#endif
58972		50196
58973	#ifdef __LITTLE_ENDIAN__
58974	#define vmul_lane_f64(__p0, __p1, __p2) __extension__ ({ \
58975	float64x1_t __s0 = __p0; \
58976	float64x1_t __s1 = __p1; \
58977	float64x1_t __ret; \
58978	__ret = (float64x1_t) __builtin_neon_vmul_lane_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
58979	__ret; \
58980	})
58981	#else
58982	#define vmul_lane_f64(__p0, __p1, __p2) __extension__ ({ \	50197	#define vmul_lane_f64(__p0, __p1, __p2) __extension__ ({ \
58983	float64x1_t __s0 = __p0; \	50198	float64x1_t __s0 = __p0; \
58984	float64x1_t __s1 = __p1; \	50199	float64x1_t __s1 = __p1; \
...	@@ -58986,8 +50201,6 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -58986,8 +50201,6 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
58986	__ret = (float64x1_t) __builtin_neon_vmul_lane_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \	50201	__ret = (float64x1_t) __builtin_neon_vmul_lane_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 10); \
58987	__ret; \	50202	__ret; \
58988	})	50203	})
58989	#endif
58990
58991	#ifdef __LITTLE_ENDIAN__	50204	#ifdef __LITTLE_ENDIAN__
58992	#define vmulq_lane_f64(__p0, __p1, __p2) __extension__ ({ \	50205	#define vmulq_lane_f64(__p0, __p1, __p2) __extension__ ({ \
58993	float64x2_t __s0 = __p0; \	50206	float64x2_t __s0 = __p0; \
...	@@ -59009,40 +50222,40 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -59009,40 +50222,40 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
59009	#endif	50222	#endif
59010		50223
59011	#ifdef __LITTLE_ENDIAN__	50224	#ifdef __LITTLE_ENDIAN__
59012	#define vmuld_laneq_f64(__p0_146, __p1_146, __p2_146) __extension__ ({ \	50225	#define vmuld_laneq_f64(__p0_141, __p1_141, __p2_141) __extension__ ({ \
59013	float64_t __s0_146 = __p0_146; \	50226	float64_t __s0_141 = __p0_141; \
59014	float64x2_t __s1_146 = __p1_146; \	50227	float64x2_t __s1_141 = __p1_141; \
59015	float64_t __ret_146; \	50228	float64_t __ret_141; \
59016	__ret_146 = __s0_146 * vgetq_lane_f64(__s1_146, __p2_146); \	50229	__ret_141 = __s0_141 * vgetq_lane_f64(__s1_141, __p2_141); \
59017	__ret_146; \	50230	__ret_141; \
59018	})	50231	})
59019	#else	50232	#else
59020	#define vmuld_laneq_f64(__p0_147, __p1_147, __p2_147) __extension__ ({ \	50233	#define vmuld_laneq_f64(__p0_142, __p1_142, __p2_142) __extension__ ({ \
59021	float64_t __s0_147 = __p0_147; \	50234	float64_t __s0_142 = __p0_142; \
59022	float64x2_t __s1_147 = __p1_147; \	50235	float64x2_t __s1_142 = __p1_142; \
59023	float64x2_t __rev1_147; __rev1_147 = __builtin_shufflevector(__s1_147, __s1_147, 1, 0); \	50236	float64x2_t __rev1_142; __rev1_142 = __builtin_shufflevector(__s1_142, __s1_142, 1, 0); \
59024	float64_t __ret_147; \	50237	float64_t __ret_142; \
59025	__ret_147 = __s0_147 * __noswap_vgetq_lane_f64(__rev1_147, __p2_147); \	50238	__ret_142 = __s0_142 * __noswap_vgetq_lane_f64(__rev1_142, __p2_142); \
59026	__ret_147; \	50239	__ret_142; \
59027	})	50240	})
59028	#endif	50241	#endif
59029		50242
59030	#ifdef __LITTLE_ENDIAN__	50243	#ifdef __LITTLE_ENDIAN__
59031	#define vmuls_laneq_f32(__p0_148, __p1_148, __p2_148) __extension__ ({ \	50244	#define vmuls_laneq_f32(__p0_143, __p1_143, __p2_143) __extension__ ({ \
59032	float32_t __s0_148 = __p0_148; \	50245	float32_t __s0_143 = __p0_143; \
59033	float32x4_t __s1_148 = __p1_148; \	50246	float32x4_t __s1_143 = __p1_143; \
59034	float32_t __ret_148; \	50247	float32_t __ret_143; \
59035	__ret_148 = __s0_148 * vgetq_lane_f32(__s1_148, __p2_148); \	50248	__ret_143 = __s0_143 * vgetq_lane_f32(__s1_143, __p2_143); \
59036	__ret_148; \	50249	__ret_143; \
59037	})	50250	})
59038	#else	50251	#else
59039	#define vmuls_laneq_f32(__p0_149, __p1_149, __p2_149) __extension__ ({ \	50252	#define vmuls_laneq_f32(__p0_144, __p1_144, __p2_144) __extension__ ({ \
59040	float32_t __s0_149 = __p0_149; \	50253	float32_t __s0_144 = __p0_144; \
59041	float32x4_t __s1_149 = __p1_149; \	50254	float32x4_t __s1_144 = __p1_144; \
59042	float32x4_t __rev1_149; __rev1_149 = __builtin_shufflevector(__s1_149, __s1_149, 3, 2, 1, 0); \	50255	float32x4_t __rev1_144; __rev1_144 = __builtin_shufflevector(__s1_144, __s1_144, 3, 2, 1, 0); \
59043	float32_t __ret_149; \	50256	float32_t __ret_144; \
59044	__ret_149 = __s0_149 * __noswap_vgetq_lane_f32(__rev1_149, __p2_149); \	50257	__ret_144 = __s0_144 * __noswap_vgetq_lane_f32(__rev1_144, __p2_144); \
59045	__ret_149; \	50258	__ret_144; \
59046	})	50259	})
59047	#endif	50260	#endif
59048		50261
...	@@ -59296,20 +50509,11 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {	...	@@ -59296,20 +50509,11 @@ __ai float64x1_t vmul_f64(float64x1_t __p0, float64x1_t __p1) {
59296	})	50509	})
59297	#endif	50510	#endif
59298		50511
59299	#ifdef __LITTLE_ENDIAN__
59300	__ai float64x1_t vmul_n_f64(float64x1_t __p0, float64_t __p1) {	50512	__ai float64x1_t vmul_n_f64(float64x1_t __p0, float64_t __p1) {
59301	float64x1_t __ret;	50513	float64x1_t __ret;
59302	__ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);	50514	__ret = (float64x1_t) __builtin_neon_vmul_n_f64((float64x1_t)__p0, __p1);
59303	return __ret;	50515	return __ret;
59304	}	50516	}
59305	#else
59306	__ai float64x1_t vmul_n_f64(float64x1_t __p0, float64_t __p1) {
59307	float64x1_t __ret;
59308	__ret = (float64x1_t) __builtin_neon_vmul_n_f64((int8x8_t)__p0, __p1);
59309	return __ret;
59310	}
59311	#endif
59312
59313	#ifdef __LITTLE_ENDIAN__	50517	#ifdef __LITTLE_ENDIAN__
59314	__ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {	50518	__ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {
59315	float64x2_t __ret;	50519	float64x2_t __ret;
...	@@ -59326,25 +50530,11 @@ __ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {	...	@@ -59326,25 +50530,11 @@ __ai float64x2_t vmulq_n_f64(float64x2_t __p0, float64_t __p1) {
59326	}	50530	}
59327	#endif	50531	#endif
59328		50532
59329	#ifdef __LITTLE_ENDIAN__
59330	__ai poly128_t vmull_p64(poly64_t __p0, poly64_t __p1) {	50533	__ai poly128_t vmull_p64(poly64_t __p0, poly64_t __p1) {
59331	poly128_t __ret;	50534	poly128_t __ret;
59332	__ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);	50535	__ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
59333	return __ret;	50536	return __ret;
59334	}	50537	}
59335	#else
59336	__ai poly128_t vmull_p64(poly64_t __p0, poly64_t __p1) {
59337	poly128_t __ret;
59338	__ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
59339	return __ret;
59340	}
59341	__ai poly128_t __noswap_vmull_p64(poly64_t __p0, poly64_t __p1) {
59342	poly128_t __ret;
59343	__ret = (poly128_t) __builtin_neon_vmull_p64(__p0, __p1);
59344	return __ret;
59345	}
59346	#endif
59347
59348	#ifdef __LITTLE_ENDIAN__	50538	#ifdef __LITTLE_ENDIAN__
59349	__ai poly16x8_t vmull_high_p8(poly8x16_t __p0, poly8x16_t __p1) {	50539	__ai poly16x8_t vmull_high_p8(poly8x16_t __p0, poly8x16_t __p1) {
59350	poly16x8_t __ret;	50540	poly16x8_t __ret;
...	@@ -59475,7 +50665,7 @@ __ai poly128_t vmull_high_p64(poly64x2_t __p0, poly64x2_t __p1) {	...	@@ -59475,7 +50665,7 @@ __ai poly128_t vmull_high_p64(poly64x2_t __p0, poly64x2_t __p1) {
59475	poly64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	50665	poly64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
59476	poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);	50666	poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__p1, __p1, 1, 0);
59477	poly128_t __ret;	50667	poly128_t __ret;
59478	__ret = __noswap_vmull_p64((poly64_t)(__noswap_vget_high_p64(__rev0)), (poly64_t)(__noswap_vget_high_p64(__rev1)));	50668	__ret = vmull_p64((poly64_t)(__noswap_vget_high_p64(__rev0)), (poly64_t)(__noswap_vget_high_p64(__rev1)));
59479	return __ret;	50669	return __ret;
59480	}	50670	}
59481	#endif	50671	#endif
...	@@ -59840,20 +51030,11 @@ __ai float32x4_t __noswap_vmulxq_f32(float32x4_t __p0, float32x4_t __p1) {	...	@@ -59840,20 +51030,11 @@ __ai float32x4_t __noswap_vmulxq_f32(float32x4_t __p0, float32x4_t __p1) {
59840	}	51030	}
59841	#endif	51031	#endif
59842		51032
59843	#ifdef __LITTLE_ENDIAN__
59844	__ai float64x1_t vmulx_f64(float64x1_t __p0, float64x1_t __p1) {
59845	float64x1_t __ret;
59846	__ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
59847	return __ret;
59848	}
59849	#else
59850	__ai float64x1_t vmulx_f64(float64x1_t __p0, float64x1_t __p1) {	51033	__ai float64x1_t vmulx_f64(float64x1_t __p0, float64x1_t __p1) {
59851	float64x1_t __ret;	51034	float64x1_t __ret;
59852	__ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	51035	__ret = (float64x1_t) __builtin_neon_vmulx_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
59853	return __ret;	51036	return __ret;
59854	}	51037	}
59855	#endif
59856
59857	#ifdef __LITTLE_ENDIAN__	51038	#ifdef __LITTLE_ENDIAN__
59858	__ai float32x2_t vmulx_f32(float32x2_t __p0, float32x2_t __p1) {	51039	__ai float32x2_t vmulx_f32(float32x2_t __p0, float32x2_t __p1) {
59859	float32x2_t __ret;	51040	float32x2_t __ret;
...	@@ -59876,78 +51057,39 @@ __ai float32x2_t __noswap_vmulx_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -59876,78 +51057,39 @@ __ai float32x2_t __noswap_vmulx_f32(float32x2_t __p0, float32x2_t __p1) {
59876	}	51057	}
59877	#endif	51058	#endif
59878		51059
59879	#ifdef __LITTLE_ENDIAN__
59880	__ai float64_t vmulxd_f64(float64_t __p0, float64_t __p1) {
59881	float64_t __ret;
59882	__ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
59883	return __ret;
59884	}
59885	#else
59886	__ai float64_t vmulxd_f64(float64_t __p0, float64_t __p1) {	51060	__ai float64_t vmulxd_f64(float64_t __p0, float64_t __p1) {
59887	float64_t __ret;	51061	float64_t __ret;
59888	__ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);	51062	__ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
59889	return __ret;	51063	return __ret;
59890	}	51064	}
59891	__ai float64_t __noswap_vmulxd_f64(float64_t __p0, float64_t __p1) {
59892	float64_t __ret;
59893	__ret = (float64_t) __builtin_neon_vmulxd_f64(__p0, __p1);
59894	return __ret;
59895	}
59896	#endif
59897
59898	#ifdef __LITTLE_ENDIAN__
59899	__ai float32_t vmulxs_f32(float32_t __p0, float32_t __p1) {
59900	float32_t __ret;
59901	__ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);
59902	return __ret;
59903	}
59904	#else
59905	__ai float32_t vmulxs_f32(float32_t __p0, float32_t __p1) {	51065	__ai float32_t vmulxs_f32(float32_t __p0, float32_t __p1) {
59906	float32_t __ret;	51066	float32_t __ret;
59907	__ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);	51067	__ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);
59908	return __ret;	51068	return __ret;
59909	}	51069	}
59910	__ai float32_t __noswap_vmulxs_f32(float32_t __p0, float32_t __p1) {	51070	#define vmulxd_lane_f64(__p0_145, __p1_145, __p2_145) __extension__ ({ \
59911	float32_t __ret;	51071	float64_t __s0_145 = __p0_145; \
59912	__ret = (float32_t) __builtin_neon_vmulxs_f32(__p0, __p1);	51072	float64x1_t __s1_145 = __p1_145; \
59913	return __ret;	51073	float64_t __ret_145; \
59914	}	51074	__ret_145 = vmulxd_f64(__s0_145, vget_lane_f64(__s1_145, __p2_145)); \
59915	#endif	51075	__ret_145; \
59916
59917	#ifdef __LITTLE_ENDIAN__
59918	#define vmulxd_lane_f64(__p0_150, __p1_150, __p2_150) __extension__ ({ \
59919	float64_t __s0_150 = __p0_150; \
59920	float64x1_t __s1_150 = __p1_150; \
59921	float64_t __ret_150; \
59922	__ret_150 = vmulxd_f64(__s0_150, vget_lane_f64(__s1_150, __p2_150)); \
59923	__ret_150; \
59924	})
59925	#else
59926	#define vmulxd_lane_f64(__p0_151, __p1_151, __p2_151) __extension__ ({ \
59927	float64_t __s0_151 = __p0_151; \
59928	float64x1_t __s1_151 = __p1_151; \
59929	float64_t __ret_151; \
59930	__ret_151 = __noswap_vmulxd_f64(__s0_151, __noswap_vget_lane_f64(__s1_151, __p2_151)); \
59931	__ret_151; \
59932	})	51076	})
59933	#endif
59934
59935	#ifdef __LITTLE_ENDIAN__	51077	#ifdef __LITTLE_ENDIAN__
59936	#define vmulxs_lane_f32(__p0_152, __p1_152, __p2_152) __extension__ ({ \	51078	#define vmulxs_lane_f32(__p0_146, __p1_146, __p2_146) __extension__ ({ \
59937	float32_t __s0_152 = __p0_152; \	51079	float32_t __s0_146 = __p0_146; \
59938	float32x2_t __s1_152 = __p1_152; \	51080	float32x2_t __s1_146 = __p1_146; \
59939	float32_t __ret_152; \	51081	float32_t __ret_146; \
59940	__ret_152 = vmulxs_f32(__s0_152, vget_lane_f32(__s1_152, __p2_152)); \	51082	__ret_146 = vmulxs_f32(__s0_146, vget_lane_f32(__s1_146, __p2_146)); \
59941	__ret_152; \	51083	__ret_146; \
59942	})	51084	})
59943	#else	51085	#else
59944	#define vmulxs_lane_f32(__p0_153, __p1_153, __p2_153) __extension__ ({ \	51086	#define vmulxs_lane_f32(__p0_147, __p1_147, __p2_147) __extension__ ({ \
59945	float32_t __s0_153 = __p0_153; \	51087	float32_t __s0_147 = __p0_147; \
59946	float32x2_t __s1_153 = __p1_153; \	51088	float32x2_t __s1_147 = __p1_147; \
59947	float32x2_t __rev1_153; __rev1_153 = __builtin_shufflevector(__s1_153, __s1_153, 1, 0); \	51089	float32x2_t __rev1_147; __rev1_147 = __builtin_shufflevector(__s1_147, __s1_147, 1, 0); \
59948	float32_t __ret_153; \	51090	float32_t __ret_147; \
59949	__ret_153 = __noswap_vmulxs_f32(__s0_153, __noswap_vget_lane_f32(__rev1_153, __p2_153)); \	51091	__ret_147 = vmulxs_f32(__s0_147, __noswap_vget_lane_f32(__rev1_147, __p2_147)); \
59950	__ret_153; \	51092	__ret_147; \
59951	})	51093	})
59952	#endif	51094	#endif
59953		51095
...	@@ -60014,40 +51156,40 @@ __ai float32_t __noswap_vmulxs_f32(float32_t __p0, float32_t __p1) {	...	@@ -60014,40 +51156,40 @@ __ai float32_t __noswap_vmulxs_f32(float32_t __p0, float32_t __p1) {
60014	#endif	51156	#endif
60015		51157
60016	#ifdef __LITTLE_ENDIAN__	51158	#ifdef __LITTLE_ENDIAN__
60017	#define vmulxd_laneq_f64(__p0_154, __p1_154, __p2_154) __extension__ ({ \	51159	#define vmulxd_laneq_f64(__p0_148, __p1_148, __p2_148) __extension__ ({ \
60018	float64_t __s0_154 = __p0_154; \	51160	float64_t __s0_148 = __p0_148; \
60019	float64x2_t __s1_154 = __p1_154; \	51161	float64x2_t __s1_148 = __p1_148; \
60020	float64_t __ret_154; \	51162	float64_t __ret_148; \
60021	__ret_154 = vmulxd_f64(__s0_154, vgetq_lane_f64(__s1_154, __p2_154)); \	51163	__ret_148 = vmulxd_f64(__s0_148, vgetq_lane_f64(__s1_148, __p2_148)); \
60022	__ret_154; \	51164	__ret_148; \
60023	})	51165	})
60024	#else	51166	#else
60025	#define vmulxd_laneq_f64(__p0_155, __p1_155, __p2_155) __extension__ ({ \	51167	#define vmulxd_laneq_f64(__p0_149, __p1_149, __p2_149) __extension__ ({ \
60026	float64_t __s0_155 = __p0_155; \	51168	float64_t __s0_149 = __p0_149; \
60027	float64x2_t __s1_155 = __p1_155; \	51169	float64x2_t __s1_149 = __p1_149; \
60028	float64x2_t __rev1_155; __rev1_155 = __builtin_shufflevector(__s1_155, __s1_155, 1, 0); \	51170	float64x2_t __rev1_149; __rev1_149 = __builtin_shufflevector(__s1_149, __s1_149, 1, 0); \
60029	float64_t __ret_155; \	51171	float64_t __ret_149; \
60030	__ret_155 = __noswap_vmulxd_f64(__s0_155, __noswap_vgetq_lane_f64(__rev1_155, __p2_155)); \	51172	__ret_149 = vmulxd_f64(__s0_149, __noswap_vgetq_lane_f64(__rev1_149, __p2_149)); \
60031	__ret_155; \	51173	__ret_149; \
60032	})	51174	})
60033	#endif	51175	#endif
60034		51176
60035	#ifdef __LITTLE_ENDIAN__	51177	#ifdef __LITTLE_ENDIAN__
60036	#define vmulxs_laneq_f32(__p0_156, __p1_156, __p2_156) __extension__ ({ \	51178	#define vmulxs_laneq_f32(__p0_150, __p1_150, __p2_150) __extension__ ({ \
60037	float32_t __s0_156 = __p0_156; \	51179	float32_t __s0_150 = __p0_150; \
60038	float32x4_t __s1_156 = __p1_156; \	51180	float32x4_t __s1_150 = __p1_150; \
60039	float32_t __ret_156; \	51181	float32_t __ret_150; \
60040	__ret_156 = vmulxs_f32(__s0_156, vgetq_lane_f32(__s1_156, __p2_156)); \	51182	__ret_150 = vmulxs_f32(__s0_150, vgetq_lane_f32(__s1_150, __p2_150)); \
60041	__ret_156; \	51183	__ret_150; \
60042	})	51184	})
60043	#else	51185	#else
60044	#define vmulxs_laneq_f32(__p0_157, __p1_157, __p2_157) __extension__ ({ \	51186	#define vmulxs_laneq_f32(__p0_151, __p1_151, __p2_151) __extension__ ({ \
60045	float32_t __s0_157 = __p0_157; \	51187	float32_t __s0_151 = __p0_151; \
60046	float32x4_t __s1_157 = __p1_157; \	51188	float32x4_t __s1_151 = __p1_151; \
60047	float32x4_t __rev1_157; __rev1_157 = __builtin_shufflevector(__s1_157, __s1_157, 3, 2, 1, 0); \	51189	float32x4_t __rev1_151; __rev1_151 = __builtin_shufflevector(__s1_151, __s1_151, 3, 2, 1, 0); \
60048	float32_t __ret_157; \	51190	float32_t __ret_151; \
60049	__ret_157 = __noswap_vmulxs_f32(__s0_157, __noswap_vgetq_lane_f32(__rev1_157, __p2_157)); \	51191	__ret_151 = vmulxs_f32(__s0_151, __noswap_vgetq_lane_f32(__rev1_151, __p2_151)); \
60050	__ret_157; \	51192	__ret_151; \
60051	})	51193	})
60052	#endif	51194	#endif
60053		51195
...	@@ -60146,48 +51288,21 @@ __ai int64x2_t vnegq_s64(int64x2_t __p0) {	...	@@ -60146,48 +51288,21 @@ __ai int64x2_t vnegq_s64(int64x2_t __p0) {
60146	}	51288	}
60147	#endif	51289	#endif
60148		51290
60149	#ifdef __LITTLE_ENDIAN__
60150	__ai float64x1_t vneg_f64(float64x1_t __p0) {
60151	float64x1_t __ret;
60152	__ret = -__p0;
60153	return __ret;
60154	}
60155	#else
60156	__ai float64x1_t vneg_f64(float64x1_t __p0) {	51291	__ai float64x1_t vneg_f64(float64x1_t __p0) {
60157	float64x1_t __ret;	51292	float64x1_t __ret;
60158	__ret = -__p0;	51293	__ret = -__p0;
60159	return __ret;	51294	return __ret;
60160	}	51295	}
60161	#endif
60162
60163	#ifdef __LITTLE_ENDIAN__
60164	__ai int64x1_t vneg_s64(int64x1_t __p0) {
60165	int64x1_t __ret;
60166	__ret = -__p0;
60167	return __ret;
60168	}
60169	#else
60170	__ai int64x1_t vneg_s64(int64x1_t __p0) {	51296	__ai int64x1_t vneg_s64(int64x1_t __p0) {
60171	int64x1_t __ret;	51297	int64x1_t __ret;
60172	__ret = -__p0;	51298	__ret = -__p0;
60173	return __ret;	51299	return __ret;
60174	}	51300	}
60175	#endif
60176
60177	#ifdef __LITTLE_ENDIAN__
60178	__ai int64_t vnegd_s64(int64_t __p0) {
60179	int64_t __ret;
60180	__ret = (int64_t) __builtin_neon_vnegd_s64(__p0);
60181	return __ret;
60182	}
60183	#else
60184	__ai int64_t vnegd_s64(int64_t __p0) {	51301	__ai int64_t vnegd_s64(int64_t __p0) {
60185	int64_t __ret;	51302	int64_t __ret;
60186	__ret = (int64_t) __builtin_neon_vnegd_s64(__p0);	51303	__ret = (int64_t) __builtin_neon_vnegd_s64(__p0);
60187	return __ret;	51304	return __ret;
60188	}	51305	}
60189	#endif
60190
60191	#ifdef __LITTLE_ENDIAN__	51306	#ifdef __LITTLE_ENDIAN__
60192	__ai uint8x16_t vpaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {	51307	__ai uint8x16_t vpaddq_u8(uint8x16_t __p0, uint8x16_t __p1) {
60193	uint8x16_t __ret;	51308	uint8x16_t __ret;
...	@@ -60361,14 +51476,14 @@ __ai int16x8_t vpaddq_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -60361,14 +51476,14 @@ __ai int16x8_t vpaddq_s16(int16x8_t __p0, int16x8_t __p1) {
60361	#ifdef __LITTLE_ENDIAN__	51476	#ifdef __LITTLE_ENDIAN__
60362	__ai uint64_t vpaddd_u64(uint64x2_t __p0) {	51477	__ai uint64_t vpaddd_u64(uint64x2_t __p0) {
60363	uint64_t __ret;	51478	uint64_t __ret;
60364	__ret = (uint64_t) __builtin_neon_vpaddd_u64((int8x16_t)__p0);	51479	__ret = (uint64_t) __builtin_neon_vpaddd_u64(__p0);
60365	return __ret;	51480	return __ret;
60366	}	51481	}
60367	#else	51482	#else
60368	__ai uint64_t vpaddd_u64(uint64x2_t __p0) {	51483	__ai uint64_t vpaddd_u64(uint64x2_t __p0) {
60369	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51484	uint64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60370	uint64_t __ret;	51485	uint64_t __ret;
60371	__ret = (uint64_t) __builtin_neon_vpaddd_u64((int8x16_t)__rev0);	51486	__ret = (uint64_t) __builtin_neon_vpaddd_u64(__rev0);
60372	return __ret;	51487	return __ret;
60373	}	51488	}
60374	#endif	51489	#endif
...	@@ -60376,14 +51491,14 @@ __ai uint64_t vpaddd_u64(uint64x2_t __p0) {	...	@@ -60376,14 +51491,14 @@ __ai uint64_t vpaddd_u64(uint64x2_t __p0) {
60376	#ifdef __LITTLE_ENDIAN__	51491	#ifdef __LITTLE_ENDIAN__
60377	__ai float64_t vpaddd_f64(float64x2_t __p0) {	51492	__ai float64_t vpaddd_f64(float64x2_t __p0) {
60378	float64_t __ret;	51493	float64_t __ret;
60379	__ret = (float64_t) __builtin_neon_vpaddd_f64((int8x16_t)__p0);	51494	__ret = (float64_t) __builtin_neon_vpaddd_f64(__p0);
60380	return __ret;	51495	return __ret;
60381	}	51496	}
60382	#else	51497	#else
60383	__ai float64_t vpaddd_f64(float64x2_t __p0) {	51498	__ai float64_t vpaddd_f64(float64x2_t __p0) {
60384	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51499	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60385	float64_t __ret;	51500	float64_t __ret;
60386	__ret = (float64_t) __builtin_neon_vpaddd_f64((int8x16_t)__rev0);	51501	__ret = (float64_t) __builtin_neon_vpaddd_f64(__rev0);
60387	return __ret;	51502	return __ret;
60388	}	51503	}
60389	#endif	51504	#endif
...	@@ -60391,14 +51506,14 @@ __ai float64_t vpaddd_f64(float64x2_t __p0) {	...	@@ -60391,14 +51506,14 @@ __ai float64_t vpaddd_f64(float64x2_t __p0) {
60391	#ifdef __LITTLE_ENDIAN__	51506	#ifdef __LITTLE_ENDIAN__
60392	__ai int64_t vpaddd_s64(int64x2_t __p0) {	51507	__ai int64_t vpaddd_s64(int64x2_t __p0) {
60393	int64_t __ret;	51508	int64_t __ret;
60394	__ret = (int64_t) __builtin_neon_vpaddd_s64((int8x16_t)__p0);	51509	__ret = (int64_t) __builtin_neon_vpaddd_s64(__p0);
60395	return __ret;	51510	return __ret;
60396	}	51511	}
60397	#else	51512	#else
60398	__ai int64_t vpaddd_s64(int64x2_t __p0) {	51513	__ai int64_t vpaddd_s64(int64x2_t __p0) {
60399	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51514	int64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60400	int64_t __ret;	51515	int64_t __ret;
60401	__ret = (int64_t) __builtin_neon_vpaddd_s64((int8x16_t)__rev0);	51516	__ret = (int64_t) __builtin_neon_vpaddd_s64(__rev0);
60402	return __ret;	51517	return __ret;
60403	}	51518	}
60404	#endif	51519	#endif
...	@@ -60406,14 +51521,14 @@ __ai int64_t vpaddd_s64(int64x2_t __p0) {	...	@@ -60406,14 +51521,14 @@ __ai int64_t vpaddd_s64(int64x2_t __p0) {
60406	#ifdef __LITTLE_ENDIAN__	51521	#ifdef __LITTLE_ENDIAN__
60407	__ai float32_t vpadds_f32(float32x2_t __p0) {	51522	__ai float32_t vpadds_f32(float32x2_t __p0) {
60408	float32_t __ret;	51523	float32_t __ret;
60409	__ret = (float32_t) __builtin_neon_vpadds_f32((int8x8_t)__p0);	51524	__ret = (float32_t) __builtin_neon_vpadds_f32(__p0);
60410	return __ret;	51525	return __ret;
60411	}	51526	}
60412	#else	51527	#else
60413	__ai float32_t vpadds_f32(float32x2_t __p0) {	51528	__ai float32_t vpadds_f32(float32x2_t __p0) {
60414	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51529	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60415	float32_t __ret;	51530	float32_t __ret;
60416	__ret = (float32_t) __builtin_neon_vpadds_f32((int8x8_t)__rev0);	51531	__ret = (float32_t) __builtin_neon_vpadds_f32(__rev0);
60417	return __ret;	51532	return __ret;
60418	}	51533	}
60419	#endif	51534	#endif
...	@@ -60557,14 +51672,14 @@ __ai int16x8_t vpmaxq_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -60557,14 +51672,14 @@ __ai int16x8_t vpmaxq_s16(int16x8_t __p0, int16x8_t __p1) {
60557	#ifdef __LITTLE_ENDIAN__	51672	#ifdef __LITTLE_ENDIAN__
60558	__ai float64_t vpmaxqd_f64(float64x2_t __p0) {	51673	__ai float64_t vpmaxqd_f64(float64x2_t __p0) {
60559	float64_t __ret;	51674	float64_t __ret;
60560	__ret = (float64_t) __builtin_neon_vpmaxqd_f64((int8x16_t)__p0);	51675	__ret = (float64_t) __builtin_neon_vpmaxqd_f64(__p0);
60561	return __ret;	51676	return __ret;
60562	}	51677	}
60563	#else	51678	#else
60564	__ai float64_t vpmaxqd_f64(float64x2_t __p0) {	51679	__ai float64_t vpmaxqd_f64(float64x2_t __p0) {
60565	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51680	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60566	float64_t __ret;	51681	float64_t __ret;
60567	__ret = (float64_t) __builtin_neon_vpmaxqd_f64((int8x16_t)__rev0);	51682	__ret = (float64_t) __builtin_neon_vpmaxqd_f64(__rev0);
60568	return __ret;	51683	return __ret;
60569	}	51684	}
60570	#endif	51685	#endif
...	@@ -60572,14 +51687,14 @@ __ai float64_t vpmaxqd_f64(float64x2_t __p0) {	...	@@ -60572,14 +51687,14 @@ __ai float64_t vpmaxqd_f64(float64x2_t __p0) {
60572	#ifdef __LITTLE_ENDIAN__	51687	#ifdef __LITTLE_ENDIAN__
60573	__ai float32_t vpmaxs_f32(float32x2_t __p0) {	51688	__ai float32_t vpmaxs_f32(float32x2_t __p0) {
60574	float32_t __ret;	51689	float32_t __ret;
60575	__ret = (float32_t) __builtin_neon_vpmaxs_f32((int8x8_t)__p0);	51690	__ret = (float32_t) __builtin_neon_vpmaxs_f32(__p0);
60576	return __ret;	51691	return __ret;
60577	}	51692	}
60578	#else	51693	#else
60579	__ai float32_t vpmaxs_f32(float32x2_t __p0) {	51694	__ai float32_t vpmaxs_f32(float32x2_t __p0) {
60580	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51695	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60581	float32_t __ret;	51696	float32_t __ret;
60582	__ret = (float32_t) __builtin_neon_vpmaxs_f32((int8x8_t)__rev0);	51697	__ret = (float32_t) __builtin_neon_vpmaxs_f32(__rev0);
60583	return __ret;	51698	return __ret;
60584	}	51699	}
60585	#endif	51700	#endif
...	@@ -60638,14 +51753,14 @@ __ai float32x2_t vpmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -60638,14 +51753,14 @@ __ai float32x2_t vpmaxnm_f32(float32x2_t __p0, float32x2_t __p1) {
60638	#ifdef __LITTLE_ENDIAN__	51753	#ifdef __LITTLE_ENDIAN__
60639	__ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {	51754	__ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {
60640	float64_t __ret;	51755	float64_t __ret;
60641	__ret = (float64_t) __builtin_neon_vpmaxnmqd_f64((int8x16_t)__p0);	51756	__ret = (float64_t) __builtin_neon_vpmaxnmqd_f64(__p0);
60642	return __ret;	51757	return __ret;
60643	}	51758	}
60644	#else	51759	#else
60645	__ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {	51760	__ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {
60646	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51761	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60647	float64_t __ret;	51762	float64_t __ret;
60648	__ret = (float64_t) __builtin_neon_vpmaxnmqd_f64((int8x16_t)__rev0);	51763	__ret = (float64_t) __builtin_neon_vpmaxnmqd_f64(__rev0);
60649	return __ret;	51764	return __ret;
60650	}	51765	}
60651	#endif	51766	#endif
...	@@ -60653,14 +51768,14 @@ __ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {	...	@@ -60653,14 +51768,14 @@ __ai float64_t vpmaxnmqd_f64(float64x2_t __p0) {
60653	#ifdef __LITTLE_ENDIAN__	51768	#ifdef __LITTLE_ENDIAN__
60654	__ai float32_t vpmaxnms_f32(float32x2_t __p0) {	51769	__ai float32_t vpmaxnms_f32(float32x2_t __p0) {
60655	float32_t __ret;	51770	float32_t __ret;
60656	__ret = (float32_t) __builtin_neon_vpmaxnms_f32((int8x8_t)__p0);	51771	__ret = (float32_t) __builtin_neon_vpmaxnms_f32(__p0);
60657	return __ret;	51772	return __ret;
60658	}	51773	}
60659	#else	51774	#else
60660	__ai float32_t vpmaxnms_f32(float32x2_t __p0) {	51775	__ai float32_t vpmaxnms_f32(float32x2_t __p0) {
60661	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51776	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60662	float32_t __ret;	51777	float32_t __ret;
60663	__ret = (float32_t) __builtin_neon_vpmaxnms_f32((int8x8_t)__rev0);	51778	__ret = (float32_t) __builtin_neon_vpmaxnms_f32(__rev0);
60664	return __ret;	51779	return __ret;
60665	}	51780	}
60666	#endif	51781	#endif
...	@@ -60804,14 +51919,14 @@ __ai int16x8_t vpminq_s16(int16x8_t __p0, int16x8_t __p1) {	...	@@ -60804,14 +51919,14 @@ __ai int16x8_t vpminq_s16(int16x8_t __p0, int16x8_t __p1) {
60804	#ifdef __LITTLE_ENDIAN__	51919	#ifdef __LITTLE_ENDIAN__
60805	__ai float64_t vpminqd_f64(float64x2_t __p0) {	51920	__ai float64_t vpminqd_f64(float64x2_t __p0) {
60806	float64_t __ret;	51921	float64_t __ret;
60807	__ret = (float64_t) __builtin_neon_vpminqd_f64((int8x16_t)__p0);	51922	__ret = (float64_t) __builtin_neon_vpminqd_f64(__p0);
60808	return __ret;	51923	return __ret;
60809	}	51924	}
60810	#else	51925	#else
60811	__ai float64_t vpminqd_f64(float64x2_t __p0) {	51926	__ai float64_t vpminqd_f64(float64x2_t __p0) {
60812	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51927	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60813	float64_t __ret;	51928	float64_t __ret;
60814	__ret = (float64_t) __builtin_neon_vpminqd_f64((int8x16_t)__rev0);	51929	__ret = (float64_t) __builtin_neon_vpminqd_f64(__rev0);
60815	return __ret;	51930	return __ret;
60816	}	51931	}
60817	#endif	51932	#endif
...	@@ -60819,14 +51934,14 @@ __ai float64_t vpminqd_f64(float64x2_t __p0) {	...	@@ -60819,14 +51934,14 @@ __ai float64_t vpminqd_f64(float64x2_t __p0) {
60819	#ifdef __LITTLE_ENDIAN__	51934	#ifdef __LITTLE_ENDIAN__
60820	__ai float32_t vpmins_f32(float32x2_t __p0) {	51935	__ai float32_t vpmins_f32(float32x2_t __p0) {
60821	float32_t __ret;	51936	float32_t __ret;
60822	__ret = (float32_t) __builtin_neon_vpmins_f32((int8x8_t)__p0);	51937	__ret = (float32_t) __builtin_neon_vpmins_f32(__p0);
60823	return __ret;	51938	return __ret;
60824	}	51939	}
60825	#else	51940	#else
60826	__ai float32_t vpmins_f32(float32x2_t __p0) {	51941	__ai float32_t vpmins_f32(float32x2_t __p0) {
60827	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	51942	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60828	float32_t __ret;	51943	float32_t __ret;
60829	__ret = (float32_t) __builtin_neon_vpmins_f32((int8x8_t)__rev0);	51944	__ret = (float32_t) __builtin_neon_vpmins_f32(__rev0);
60830	return __ret;	51945	return __ret;
60831	}	51946	}
60832	#endif	51947	#endif
...	@@ -60885,14 +52000,14 @@ __ai float32x2_t vpminnm_f32(float32x2_t __p0, float32x2_t __p1) {	...	@@ -60885,14 +52000,14 @@ __ai float32x2_t vpminnm_f32(float32x2_t __p0, float32x2_t __p1) {
60885	#ifdef __LITTLE_ENDIAN__	52000	#ifdef __LITTLE_ENDIAN__
60886	__ai float64_t vpminnmqd_f64(float64x2_t __p0) {	52001	__ai float64_t vpminnmqd_f64(float64x2_t __p0) {
60887	float64_t __ret;	52002	float64_t __ret;
60888	__ret = (float64_t) __builtin_neon_vpminnmqd_f64((int8x16_t)__p0);	52003	__ret = (float64_t) __builtin_neon_vpminnmqd_f64(__p0);
60889	return __ret;	52004	return __ret;
60890	}	52005	}
60891	#else	52006	#else
60892	__ai float64_t vpminnmqd_f64(float64x2_t __p0) {	52007	__ai float64_t vpminnmqd_f64(float64x2_t __p0) {
60893	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	52008	float64x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60894	float64_t __ret;	52009	float64_t __ret;
60895	__ret = (float64_t) __builtin_neon_vpminnmqd_f64((int8x16_t)__rev0);	52010	__ret = (float64_t) __builtin_neon_vpminnmqd_f64(__rev0);
60896	return __ret;	52011	return __ret;
60897	}	52012	}
60898	#endif	52013	#endif
...	@@ -60900,14 +52015,14 @@ __ai float64_t vpminnmqd_f64(float64x2_t __p0) {	...	@@ -60900,14 +52015,14 @@ __ai float64_t vpminnmqd_f64(float64x2_t __p0) {
60900	#ifdef __LITTLE_ENDIAN__	52015	#ifdef __LITTLE_ENDIAN__
60901	__ai float32_t vpminnms_f32(float32x2_t __p0) {	52016	__ai float32_t vpminnms_f32(float32x2_t __p0) {
60902	float32_t __ret;	52017	float32_t __ret;
60903	__ret = (float32_t) __builtin_neon_vpminnms_f32((int8x8_t)__p0);	52018	__ret = (float32_t) __builtin_neon_vpminnms_f32(__p0);
60904	return __ret;	52019	return __ret;
60905	}	52020	}
60906	#else	52021	#else
60907	__ai float32_t vpminnms_f32(float32x2_t __p0) {	52022	__ai float32_t vpminnms_f32(float32x2_t __p0) {
60908	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);	52023	float32x2_t __rev0; __rev0 = __builtin_shufflevector(__p0, __p0, 1, 0);
60909	float32_t __ret;	52024	float32_t __ret;
60910	__ret = (float32_t) __builtin_neon_vpminnms_f32((int8x8_t)__rev0);	52025	__ret = (float32_t) __builtin_neon_vpminnms_f32(__rev0);
60911	return __ret;	52026	return __ret;
60912	}	52027	}
60913	#endif	52028	#endif
...	@@ -60928,226 +52043,81 @@ __ai int64x2_t vqabsq_s64(int64x2_t __p0) {	...	@@ -60928,226 +52043,81 @@ __ai int64x2_t vqabsq_s64(int64x2_t __p0) {
60928	}	52043	}
60929	#endif	52044	#endif
60930		52045
60931	#ifdef __LITTLE_ENDIAN__
60932	__ai int64x1_t vqabs_s64(int64x1_t __p0) {	52046	__ai int64x1_t vqabs_s64(int64x1_t __p0) {
60933	int64x1_t __ret;	52047	int64x1_t __ret;
60934	__ret = (int64x1_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 3);	52048	__ret = (int64x1_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 3);
60935	return __ret;	52049	return __ret;
60936	}	52050	}
60937	#else
60938	__ai int64x1_t vqabs_s64(int64x1_t __p0) {
60939	int64x1_t __ret;
60940	__ret = (int64x1_t) __builtin_neon_vqabs_v((int8x8_t)__p0, 3);
60941	return __ret;
60942	}
60943	#endif
60944
60945	#ifdef __LITTLE_ENDIAN__
60946	__ai int8_t vqabsb_s8(int8_t __p0) {	52051	__ai int8_t vqabsb_s8(int8_t __p0) {
60947	int8_t __ret;	52052	int8_t __ret;
60948	__ret = (int8_t) __builtin_neon_vqabsb_s8(__p0);	52053	__ret = (int8_t) __builtin_neon_vqabsb_s8(__p0);
60949	return __ret;	52054	return __ret;
60950	}	52055	}
60951	#else
60952	__ai int8_t vqabsb_s8(int8_t __p0) {
60953	int8_t __ret;
60954	__ret = (int8_t) __builtin_neon_vqabsb_s8(__p0);
60955	return __ret;
60956	}
60957	#endif
60958
60959	#ifdef __LITTLE_ENDIAN__
60960	__ai int32_t vqabss_s32(int32_t __p0) {
60961	int32_t __ret;
60962	__ret = (int32_t) __builtin_neon_vqabss_s32(__p0);
60963	return __ret;
60964	}
60965	#else
60966	__ai int32_t vqabss_s32(int32_t __p0) {	52056	__ai int32_t vqabss_s32(int32_t __p0) {
60967	int32_t __ret;	52057	int32_t __ret;
60968	__ret = (int32_t) __builtin_neon_vqabss_s32(__p0);	52058	__ret = (int32_t) __builtin_neon_vqabss_s32(__p0);
60969	return __ret;	52059	return __ret;
60970	}	52060	}
60971	#endif
60972
60973	#ifdef __LITTLE_ENDIAN__
60974	__ai int64_t vqabsd_s64(int64_t __p0) {
60975	int64_t __ret;
60976	__ret = (int64_t) __builtin_neon_vqabsd_s64(__p0);
60977	return __ret;
60978	}
60979	#else
60980	__ai int64_t vqabsd_s64(int64_t __p0) {	52061	__ai int64_t vqabsd_s64(int64_t __p0) {
60981	int64_t __ret;	52062	int64_t __ret;
60982	__ret = (int64_t) __builtin_neon_vqabsd_s64(__p0);	52063	__ret = (int64_t) __builtin_neon_vqabsd_s64(__p0);
60983	return __ret;	52064	return __ret;
60984	}	52065	}
60985	#endif
60986
60987	#ifdef __LITTLE_ENDIAN__
60988	__ai int16_t vqabsh_s16(int16_t __p0) {	52066	__ai int16_t vqabsh_s16(int16_t __p0) {
60989	int16_t __ret;	52067	int16_t __ret;
60990	__ret = (int16_t) __builtin_neon_vqabsh_s16(__p0);	52068	__ret = (int16_t) __builtin_neon_vqabsh_s16(__p0);
60991	return __ret;	52069	return __ret;
60992	}	52070	}
60993	#else
60994	__ai int16_t vqabsh_s16(int16_t __p0) {
60995	int16_t __ret;
60996	__ret = (int16_t) __builtin_neon_vqabsh_s16(__p0);
60997	return __ret;
60998	}
60999	#endif
61000
61001	#ifdef __LITTLE_ENDIAN__
61002	__ai uint8_t vqaddb_u8(uint8_t __p0, uint8_t __p1) {	52071	__ai uint8_t vqaddb_u8(uint8_t __p0, uint8_t __p1) {
61003	uint8_t __ret;	52072	uint8_t __ret;
61004	__ret = (uint8_t) __builtin_neon_vqaddb_u8(__p0, __p1);	52073	__ret = (uint8_t) __builtin_neon_vqaddb_u8(__p0, __p1);
61005	return __ret;	52074	return __ret;
61006	}	52075	}
61007	#else
61008	__ai uint8_t vqaddb_u8(uint8_t __p0, uint8_t __p1) {
61009	uint8_t __ret;
61010	__ret = (uint8_t) __builtin_neon_vqaddb_u8(__p0, __p1);
61011	return __ret;
61012	}
61013	#endif
61014
61015	#ifdef __LITTLE_ENDIAN__
61016	__ai uint32_t vqadds_u32(uint32_t __p0, uint32_t __p1) {
61017	uint32_t __ret;
61018	__ret = (uint32_t) __builtin_neon_vqadds_u32(__p0, __p1);
61019	return __ret;
61020	}
61021	#else
61022	__ai uint32_t vqadds_u32(uint32_t __p0, uint32_t __p1) {	52076	__ai uint32_t vqadds_u32(uint32_t __p0, uint32_t __p1) {
61023	uint32_t __ret;	52077	uint32_t __ret;
61024	__ret = (uint32_t) __builtin_neon_vqadds_u32(__p0, __p1);	52078	__ret = (uint32_t) __builtin_neon_vqadds_u32(__p0, __p1);
61025	return __ret;	52079	return __ret;
61026	}	52080	}
61027	#endif
61028
61029	#ifdef __LITTLE_ENDIAN__
61030	__ai uint64_t vqaddd_u64(uint64_t __p0, uint64_t __p1) {
61031	uint64_t __ret;
61032	__ret = (uint64_t) __builtin_neon_vqaddd_u64(__p0, __p1);
61033	return __ret;
61034	}
61035	#else
61036	__ai uint64_t vqaddd_u64(uint64_t __p0, uint64_t __p1) {	52081	__ai uint64_t vqaddd_u64(uint64_t __p0, uint64_t __p1) {
61037	uint64_t __ret;	52082	uint64_t __ret;
61038	__ret = (uint64_t) __builtin_neon_vqaddd_u64(__p0, __p1);	52083	__ret = (uint64_t) __builtin_neon_vqaddd_u64(__p0, __p1);
61039	return __ret;	52084	return __ret;
61040	}	52085	}
61041	#endif
61042
61043	#ifdef __LITTLE_ENDIAN__
61044	__ai uint16_t vqaddh_u16(uint16_t __p0, uint16_t __p1) {
61045	uint16_t __ret;
61046	__ret = (uint16_t) __builtin_neon_vqaddh_u16(__p0, __p1);
61047	return __ret;
61048	}
61049	#else
61050	__ai uint16_t vqaddh_u16(uint16_t __p0, uint16_t __p1) {	52086	__ai uint16_t vqaddh_u16(uint16_t __p0, uint16_t __p1) {
61051	uint16_t __ret;	52087	uint16_t __ret;
61052	__ret = (uint16_t) __builtin_neon_vqaddh_u16(__p0, __p1);	52088	__ret = (uint16_t) __builtin_neon_vqaddh_u16(__p0, __p1);
61053	return __ret;	52089	return __ret;
61054	}	52090	}
61055	#endif
61056
61057	#ifdef __LITTLE_ENDIAN__
61058	__ai int8_t vqaddb_s8(int8_t __p0, int8_t __p1) {
61059	int8_t __ret;
61060	__ret = (int8_t) __builtin_neon_vqaddb_s8(__p0, __p1);
61061	return __ret;
61062	}
61063	#else
61064	__ai int8_t vqaddb_s8(int8_t __p0, int8_t __p1) {	52091	__ai int8_t vqaddb_s8(int8_t __p0, int8_t __p1) {
61065	int8_t __ret;	52092	int8_t __ret;
61066	__ret = (int8_t) __builtin_neon_vqaddb_s8(__p0, __p1);	52093	__ret = (int8_t) __builtin_neon_vqaddb_s8(__p0, __p1);
61067	return __ret;	52094	return __ret;
61068	}	52095	}
61069	#endif
61070
61071	#ifdef __LITTLE_ENDIAN__
61072	__ai int32_t vqadds_s32(int32_t __p0, int32_t __p1) {
61073	int32_t __ret;
61074	__ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
61075	return __ret;
61076	}
61077	#else
61078	__ai int32_t vqadds_s32(int32_t __p0, int32_t __p1) {	52096	__ai int32_t vqadds_s32(int32_t __p0, int32_t __p1) {
61079	int32_t __ret;	52097	int32_t __ret;
61080	__ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);	52098	__ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
61081	return __ret;	52099	return __ret;
61082	}	52100	}
61083	__ai int32_t __noswap_vqadds_s32(int32_t __p0, int32_t __p1) {
61084	int32_t __ret;
61085	__ret = (int32_t) __builtin_neon_vqadds_s32(__p0, __p1);
61086	return __ret;
61087	}
61088	#endif
61089
61090	#ifdef __LITTLE_ENDIAN__
61091	__ai int64_t vqaddd_s64(int64_t __p0, int64_t __p1) {	52101	__ai int64_t vqaddd_s64(int64_t __p0, int64_t __p1) {
61092	int64_t __ret;	52102	int64_t __ret;
61093	__ret = (int64_t) __builtin_neon_vqaddd_s64(__p0, __p1);	52103	__ret = (int64_t) __builtin_neon_vqaddd_s64(__p0, __p1);
61094	return __ret;	52104	return __ret;
61095	}	52105	}
61096	#else
61097	__ai int64_t vqaddd_s64(int64_t __p0, int64_t __p1) {
61098	int64_t __ret;
61099	__ret = (int64_t) __builtin_neon_vqaddd_s64(__p0, __p1);
61100	return __ret;
61101	}
61102	#endif
61103
61104	#ifdef __LITTLE_ENDIAN__
61105	__ai int16_t vqaddh_s16(int16_t __p0, int16_t __p1) {
61106	int16_t __ret;
61107	__ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
61108	return __ret;
61109	}
61110	#else
61111	__ai int16_t vqaddh_s16(int16_t __p0, int16_t __p1) {	52106	__ai int16_t vqaddh_s16(int16_t __p0, int16_t __p1) {
61112	int16_t __ret;	52107	int16_t __ret;
61113	__ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);	52108	__ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
61114	return __ret;	52109	return __ret;
61115	}	52110	}
61116	__ai int16_t __noswap_vqaddh_s16(int16_t __p0, int16_t __p1) {
61117	int16_t __ret;
61118	__ret = (int16_t) __builtin_neon_vqaddh_s16(__p0, __p1);
61119	return __ret;
61120	}
61121	#endif
61122
61123	#ifdef __LITTLE_ENDIAN__
61124	__ai int64_t vqdmlals_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
61125	int64_t __ret;
61126	__ret = (int64_t) __builtin_neon_vqdmlals_s32(__p0, __p1, __p2);
61127	return __ret;
61128	}
61129	#else
61130	__ai int64_t vqdmlals_s32(int64_t __p0, int32_t __p1, int32_t __p2) {	52111	__ai int64_t vqdmlals_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
61131	int64_t __ret;	52112	int64_t __ret;
61132	__ret = (int64_t) __builtin_neon_vqdmlals_s32(__p0, __p1, __p2);	52113	__ret = (int64_t) __builtin_neon_vqdmlals_s32(__p0, __p1, __p2);
61133	return __ret;	52114	return __ret;
61134	}	52115	}
61135	#endif
61136
61137	#ifdef __LITTLE_ENDIAN__
61138	__ai int32_t vqdmlalh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {	52116	__ai int32_t vqdmlalh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
61139	int32_t __ret;	52117	int32_t __ret;
61140	__ret = (int32_t) __builtin_neon_vqdmlalh_s16(__p0, __p1, __p2);	52118	__ret = (int32_t) __builtin_neon_vqdmlalh_s16(__p0, __p1, __p2);
61141	return __ret;	52119	return __ret;
61142	}	52120	}
61143	#else
61144	__ai int32_t vqdmlalh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
61145	int32_t __ret;
61146	__ret = (int32_t) __builtin_neon_vqdmlalh_s16(__p0, __p1, __p2);
61147	return __ret;
61148	}
61149	#endif
61150
61151	#ifdef __LITTLE_ENDIAN__	52121	#ifdef __LITTLE_ENDIAN__
61152	__ai int64x2_t vqdmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {	52122	__ai int64x2_t vqdmlal_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
61153	int64x2_t __ret;	52123	int64x2_t __ret;
...	@@ -61320,7 +52290,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61320,7 +52290,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61320	int32_t __s1 = __p1; \	52290	int32_t __s1 = __p1; \
61321	int32x2_t __s2 = __p2; \	52291	int32x2_t __s2 = __p2; \
61322	int64_t __ret; \	52292	int64_t __ret; \
61323	__ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, (int8x8_t)__s2, __p3); \	52293	__ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, __s2, __p3); \
61324	__ret; \	52294	__ret; \
61325	})	52295	})
61326	#else	52296	#else
...	@@ -61330,7 +52300,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61330,7 +52300,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61330	int32x2_t __s2 = __p2; \	52300	int32x2_t __s2 = __p2; \
61331	int32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \	52301	int32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \
61332	int64_t __ret; \	52302	int64_t __ret; \
61333	__ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, (int8x8_t)__rev2, __p3); \	52303	__ret = (int64_t) __builtin_neon_vqdmlals_lane_s32(__s0, __s1, __rev2, __p3); \
61334	__ret; \	52304	__ret; \
61335	})	52305	})
61336	#endif	52306	#endif
...	@@ -61341,7 +52311,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61341,7 +52311,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61341	int16_t __s1 = __p1; \	52311	int16_t __s1 = __p1; \
61342	int16x4_t __s2 = __p2; \	52312	int16x4_t __s2 = __p2; \
61343	int32_t __ret; \	52313	int32_t __ret; \
61344	__ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, (int8x8_t)__s2, __p3); \	52314	__ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, __s2, __p3); \
61345	__ret; \	52315	__ret; \
61346	})	52316	})
61347	#else	52317	#else
...	@@ -61351,7 +52321,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61351,7 +52321,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61351	int16x4_t __s2 = __p2; \	52321	int16x4_t __s2 = __p2; \
61352	int16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	52322	int16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
61353	int32_t __ret; \	52323	int32_t __ret; \
61354	__ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, (int8x8_t)__rev2, __p3); \	52324	__ret = (int32_t) __builtin_neon_vqdmlalh_lane_s16(__s0, __s1, __rev2, __p3); \
61355	__ret; \	52325	__ret; \
61356	})	52326	})
61357	#endif	52327	#endif
...	@@ -61362,7 +52332,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61362,7 +52332,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61362	int32_t __s1 = __p1; \	52332	int32_t __s1 = __p1; \
61363	int32x4_t __s2 = __p2; \	52333	int32x4_t __s2 = __p2; \
61364	int64_t __ret; \	52334	int64_t __ret; \
61365	__ret = (int64_t) __builtin_neon_vqdmlals_laneq_s32(__s0, __s1, (int8x16_t)__s2, __p3); \	52335	__ret = (int64_t) __builtin_neon_vqdmlals_laneq_s32(__s0, __s1, __s2, __p3); \
61366	__ret; \	52336	__ret; \
61367	})	52337	})
61368	#else	52338	#else
...	@@ -61372,7 +52342,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61372,7 +52342,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61372	int32x4_t __s2 = __p2; \	52342	int32x4_t __s2 = __p2; \
61373	int32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	52343	int32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
61374	int64_t __ret; \	52344	int64_t __ret; \
61375	__ret = (int64_t) __builtin_neon_vqdmlals_laneq_s32(__s0, __s1, (int8x16_t)__rev2, __p3); \	52345	__ret = (int64_t) __builtin_neon_vqdmlals_laneq_s32(__s0, __s1, __rev2, __p3); \
61376	__ret; \	52346	__ret; \
61377	})	52347	})
61378	#endif	52348	#endif
...	@@ -61383,7 +52353,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61383,7 +52353,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61383	int16_t __s1 = __p1; \	52353	int16_t __s1 = __p1; \
61384	int16x8_t __s2 = __p2; \	52354	int16x8_t __s2 = __p2; \
61385	int32_t __ret; \	52355	int32_t __ret; \
61386	__ret = (int32_t) __builtin_neon_vqdmlalh_laneq_s16(__s0, __s1, (int8x16_t)__s2, __p3); \	52356	__ret = (int32_t) __builtin_neon_vqdmlalh_laneq_s16(__s0, __s1, __s2, __p3); \
61387	__ret; \	52357	__ret; \
61388	})	52358	})
61389	#else	52359	#else
...	@@ -61393,7 +52363,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61393,7 +52363,7 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61393	int16x8_t __s2 = __p2; \	52363	int16x8_t __s2 = __p2; \
61394	int16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \	52364	int16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \
61395	int32_t __ret; \	52365	int32_t __ret; \
61396	__ret = (int32_t) __builtin_neon_vqdmlalh_laneq_s16(__s0, __s1, (int8x16_t)__rev2, __p3); \	52366	__ret = (int32_t) __builtin_neon_vqdmlalh_laneq_s16(__s0, __s1, __rev2, __p3); \
61397	__ret; \	52367	__ret; \
61398	})	52368	})
61399	#endif	52369	#endif
...	@@ -61446,34 +52416,16 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61446,34 +52416,16 @@ __ai int32x4_t vqdmlal_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61446	})	52416	})
61447	#endif	52417	#endif
61448		52418
61449	#ifdef __LITTLE_ENDIAN__
61450	__ai int64_t vqdmlsls_s32(int64_t __p0, int32_t __p1, int32_t __p2) {	52419	__ai int64_t vqdmlsls_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
61451	int64_t __ret;	52420	int64_t __ret;
61452	__ret = (int64_t) __builtin_neon_vqdmlsls_s32(__p0, __p1, __p2);	52421	__ret = (int64_t) __builtin_neon_vqdmlsls_s32(__p0, __p1, __p2);
61453	return __ret;	52422	return __ret;
61454	}	52423	}
61455	#else
61456	__ai int64_t vqdmlsls_s32(int64_t __p0, int32_t __p1, int32_t __p2) {
61457	int64_t __ret;
61458	__ret = (int64_t) __builtin_neon_vqdmlsls_s32(__p0, __p1, __p2);
61459	return __ret;
61460	}
61461	#endif
61462
61463	#ifdef __LITTLE_ENDIAN__
61464	__ai int32_t vqdmlslh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {	52424	__ai int32_t vqdmlslh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
61465	int32_t __ret;	52425	int32_t __ret;
61466	__ret = (int32_t) __builtin_neon_vqdmlslh_s16(__p0, __p1, __p2);	52426	__ret = (int32_t) __builtin_neon_vqdmlslh_s16(__p0, __p1, __p2);
61467	return __ret;	52427	return __ret;
61468	}	52428	}
61469	#else
61470	__ai int32_t vqdmlslh_s16(int32_t __p0, int16_t __p1, int16_t __p2) {
61471	int32_t __ret;
61472	__ret = (int32_t) __builtin_neon_vqdmlslh_s16(__p0, __p1, __p2);
61473	return __ret;
61474	}
61475	#endif
61476
61477	#ifdef __LITTLE_ENDIAN__	52429	#ifdef __LITTLE_ENDIAN__
61478	__ai int64x2_t vqdmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {	52430	__ai int64x2_t vqdmlsl_high_s32(int64x2_t __p0, int32x4_t __p1, int32x4_t __p2) {
61479	int64x2_t __ret;	52431	int64x2_t __ret;
...	@@ -61646,7 +52598,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61646,7 +52598,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61646	int32_t __s1 = __p1; \	52598	int32_t __s1 = __p1; \
61647	int32x2_t __s2 = __p2; \	52599	int32x2_t __s2 = __p2; \
61648	int64_t __ret; \	52600	int64_t __ret; \
61649	__ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, (int8x8_t)__s2, __p3); \	52601	__ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, __s2, __p3); \
61650	__ret; \	52602	__ret; \
61651	})	52603	})
61652	#else	52604	#else
...	@@ -61656,7 +52608,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61656,7 +52608,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61656	int32x2_t __s2 = __p2; \	52608	int32x2_t __s2 = __p2; \
61657	int32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \	52609	int32x2_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 1, 0); \
61658	int64_t __ret; \	52610	int64_t __ret; \
61659	__ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, (int8x8_t)__rev2, __p3); \	52611	__ret = (int64_t) __builtin_neon_vqdmlsls_lane_s32(__s0, __s1, __rev2, __p3); \
61660	__ret; \	52612	__ret; \
61661	})	52613	})
61662	#endif	52614	#endif
...	@@ -61667,7 +52619,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61667,7 +52619,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61667	int16_t __s1 = __p1; \	52619	int16_t __s1 = __p1; \
61668	int16x4_t __s2 = __p2; \	52620	int16x4_t __s2 = __p2; \
61669	int32_t __ret; \	52621	int32_t __ret; \
61670	__ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, (int8x8_t)__s2, __p3); \	52622	__ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, __s2, __p3); \
61671	__ret; \	52623	__ret; \
61672	})	52624	})
61673	#else	52625	#else
...	@@ -61677,7 +52629,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61677,7 +52629,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61677	int16x4_t __s2 = __p2; \	52629	int16x4_t __s2 = __p2; \
61678	int16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	52630	int16x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
61679	int32_t __ret; \	52631	int32_t __ret; \
61680	__ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, (int8x8_t)__rev2, __p3); \	52632	__ret = (int32_t) __builtin_neon_vqdmlslh_lane_s16(__s0, __s1, __rev2, __p3); \
61681	__ret; \	52633	__ret; \
61682	})	52634	})
61683	#endif	52635	#endif
...	@@ -61688,7 +52640,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61688,7 +52640,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61688	int32_t __s1 = __p1; \	52640	int32_t __s1 = __p1; \
61689	int32x4_t __s2 = __p2; \	52641	int32x4_t __s2 = __p2; \
61690	int64_t __ret; \	52642	int64_t __ret; \
61691	__ret = (int64_t) __builtin_neon_vqdmlsls_laneq_s32(__s0, __s1, (int8x16_t)__s2, __p3); \	52643	__ret = (int64_t) __builtin_neon_vqdmlsls_laneq_s32(__s0, __s1, __s2, __p3); \
61692	__ret; \	52644	__ret; \
61693	})	52645	})
61694	#else	52646	#else
...	@@ -61698,7 +52650,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61698,7 +52650,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61698	int32x4_t __s2 = __p2; \	52650	int32x4_t __s2 = __p2; \
61699	int32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \	52651	int32x4_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 3, 2, 1, 0); \
61700	int64_t __ret; \	52652	int64_t __ret; \
61701	__ret = (int64_t) __builtin_neon_vqdmlsls_laneq_s32(__s0, __s1, (int8x16_t)__rev2, __p3); \	52653	__ret = (int64_t) __builtin_neon_vqdmlsls_laneq_s32(__s0, __s1, __rev2, __p3); \
61702	__ret; \	52654	__ret; \
61703	})	52655	})
61704	#endif	52656	#endif
...	@@ -61709,7 +52661,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61709,7 +52661,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61709	int16_t __s1 = __p1; \	52661	int16_t __s1 = __p1; \
61710	int16x8_t __s2 = __p2; \	52662	int16x8_t __s2 = __p2; \
61711	int32_t __ret; \	52663	int32_t __ret; \
61712	__ret = (int32_t) __builtin_neon_vqdmlslh_laneq_s16(__s0, __s1, (int8x16_t)__s2, __p3); \	52664	__ret = (int32_t) __builtin_neon_vqdmlslh_laneq_s16(__s0, __s1, __s2, __p3); \
61713	__ret; \	52665	__ret; \
61714	})	52666	})
61715	#else	52667	#else
...	@@ -61719,7 +52671,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61719,7 +52671,7 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61719	int16x8_t __s2 = __p2; \	52671	int16x8_t __s2 = __p2; \
61720	int16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \	52672	int16x8_t __rev2; __rev2 = __builtin_shufflevector(__s2, __s2, 7, 6, 5, 4, 3, 2, 1, 0); \
61721	int32_t __ret; \	52673	int32_t __ret; \
61722	__ret = (int32_t) __builtin_neon_vqdmlslh_laneq_s16(__s0, __s1, (int8x16_t)__rev2, __p3); \	52674	__ret = (int32_t) __builtin_neon_vqdmlslh_laneq_s16(__s0, __s1, __rev2, __p3); \
61723	__ret; \	52675	__ret; \
61724	})	52676	})
61725	#endif	52677	#endif
...	@@ -61772,117 +52724,89 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)	...	@@ -61772,117 +52724,89 @@ __ai int32x4_t vqdmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2)
61772	})	52724	})
61773	#endif	52725	#endif
61774		52726
61775	#ifdef __LITTLE_ENDIAN__
61776	__ai int32_t vqdmulhs_s32(int32_t __p0, int32_t __p1) {
61777	int32_t __ret;
61778	__ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
61779	return __ret;
61780	}
61781	#else
61782	__ai int32_t vqdmulhs_s32(int32_t __p0, int32_t __p1) {	52727	__ai int32_t vqdmulhs_s32(int32_t __p0, int32_t __p1) {
61783	int32_t __ret;	52728	int32_t __ret;
61784	__ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);	52729	__ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
61785	return __ret;	52730	return __ret;
61786	}	52731	}
61787	__ai int32_t __noswap_vqdmulhs_s32(int32_t __p0, int32_t __p1) {
61788	int32_t __ret;
61789	__ret = (int32_t) __builtin_neon_vqdmulhs_s32(__p0, __p1);
61790	return __ret;
61791	}
61792	#endif
61793
61794	#ifdef __LITTLE_ENDIAN__
61795	__ai int16_t vqdmulhh_s16(int16_t __p0, int16_t __p1) {
61796	int16_t __ret;
61797	__ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
61798	return __ret;
61799	}
61800	#else
61801	__ai int16_t vqdmulhh_s16(int16_t __p0, int16_t __p1) {	52732	__ai int16_t vqdmulhh_s16(int16_t __p0, int16_t __p1) {
61802	int16_t __ret;	52733	int16_t __ret;
61803	__ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);	52734	__ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
61804	return __ret;	52735	return __ret;
61805	}	52736	}
61806	__ai int16_t __noswap_vqdmulhh_s16(int16_t __p0, int16_t __p1) {
61807	int16_t __ret;
61808	__ret = (int16_t) __builtin_neon_vqdmulhh_s16(__p0, __p1);
61809	return __ret;
61810	}
61811	#endif
61812
61813	#ifdef __LITTLE_ENDIAN__	52737	#ifdef __LITTLE_ENDIAN__
61814	#define vqdmulhs_lane_s32(__p0_158, __p1_158, __p2_158) __extension__ ({ \	52738	#define vqdmulhs_lane_s32(__p0_152, __p1_152, __p2_152) __extension__ ({ \
61815	int32_t __s0_158 = __p0_158; \	52739	int32_t __s0_152 = __p0_152; \
61816	int32x2_t __s1_158 = __p1_158; \	52740	int32x2_t __s1_152 = __p1_152; \
61817	int32_t __ret_158; \	52741	int32_t __ret_152; \
61818	__ret_158 = vqdmulhs_s32(__s0_158, vget_lane_s32(__s1_158, __p2_158)); \	52742	__ret_152 = vqdmulhs_s32(__s0_152, vget_lane_s32(__s1_152, __p2_152)); \
61819	__ret_158; \	52743	__ret_152; \
61820	})	52744	})
61821	#else	52745	#else
61822	#define vqdmulhs_lane_s32(__p0_159, __p1_159, __p2_159) __extension__ ({ \	52746	#define vqdmulhs_lane_s32(__p0_153, __p1_153, __p2_153) __extension__ ({ \
61823	int32_t __s0_159 = __p0_159; \	52747	int32_t __s0_153 = __p0_153; \
61824	int32x2_t __s1_159 = __p1_159; \	52748	int32x2_t __s1_153 = __p1_153; \
61825	int32x2_t __rev1_159; __rev1_159 = __builtin_shufflevector(__s1_159, __s1_159, 1, 0); \	52749	int32x2_t __rev1_153; __rev1_153 = __builtin_shufflevector(__s1_153, __s1_153, 1, 0); \
61826	int32_t __ret_159; \	52750	int32_t __ret_153; \
61827	__ret_159 = __noswap_vqdmulhs_s32(__s0_159, __noswap_vget_lane_s32(__rev1_159, __p2_159)); \	52751	__ret_153 = vqdmulhs_s32(__s0_153, __noswap_vget_lane_s32(__rev1_153, __p2_153)); \
61828	__ret_159; \	52752	__ret_153; \
61829	})	52753	})
61830	#endif	52754	#endif
61831		52755
61832	#ifdef __LITTLE_ENDIAN__	52756	#ifdef __LITTLE_ENDIAN__
61833	#define vqdmulhh_lane_s16(__p0_160, __p1_160, __p2_160) __extension__ ({ \	52757	#define vqdmulhh_lane_s16(__p0_154, __p1_154, __p2_154) __extension__ ({ \
61834	int16_t __s0_160 = __p0_160; \	52758	int16_t __s0_154 = __p0_154; \
61835	int16x4_t __s1_160 = __p1_160; \	52759	int16x4_t __s1_154 = __p1_154; \
61836	int16_t __ret_160; \	52760	int16_t __ret_154; \
61837	__ret_160 = vqdmulhh_s16(__s0_160, vget_lane_s16(__s1_160, __p2_160)); \	52761	__ret_154 = vqdmulhh_s16(__s0_154, vget_lane_s16(__s1_154, __p2_154)); \
61838	__ret_160; \	52762	__ret_154; \
61839	})	52763	})
61840	#else	52764	#else
61841	#define vqdmulhh_lane_s16(__p0_161, __p1_161, __p2_161) __extension__ ({ \	52765	#define vqdmulhh_lane_s16(__p0_155, __p1_155, __p2_155) __extension__ ({ \
61842	int16_t __s0_161 = __p0_161; \	52766	int16_t __s0_155 = __p0_155; \
61843	int16x4_t __s1_161 = __p1_161; \	52767	int16x4_t __s1_155 = __p1_155; \
61844	int16x4_t __rev1_161; __rev1_161 = __builtin_shufflevector(__s1_161, __s1_161, 3, 2, 1, 0); \	52768	int16x4_t __rev1_155; __rev1_155 = __builtin_shufflevector(__s1_155, __s1_155, 3, 2, 1, 0); \
61845	int16_t __ret_161; \	52769	int16_t __ret_155; \
61846	__ret_161 = __noswap_vqdmulhh_s16(__s0_161, __noswap_vget_lane_s16(__rev1_161, __p2_161)); \	52770	__ret_155 = vqdmulhh_s16(__s0_155, __noswap_vget_lane_s16(__rev1_155, __p2_155)); \
61847	__ret_161; \	52771	__ret_155; \
61848	})	52772	})
61849	#endif	52773	#endif
61850		52774
61851	#ifdef __LITTLE_ENDIAN__	52775	#ifdef __LITTLE_ENDIAN__
61852	#define vqdmulhs_laneq_s32(__p0_162, __p1_162, __p2_162) __extension__ ({ \	52776	#define vqdmulhs_laneq_s32(__p0_156, __p1_156, __p2_156) __extension__ ({ \
61853	int32_t __s0_162 = __p0_162; \	52777	int32_t __s0_156 = __p0_156; \
61854	int32x4_t __s1_162 = __p1_162; \	52778	int32x4_t __s1_156 = __p1_156; \
61855	int32_t __ret_162; \	52779	int32_t __ret_156; \
61856	__ret_162 = vqdmulhs_s32(__s0_162, vgetq_lane_s32(__s1_162, __p2_162)); \	52780	__ret_156 = vqdmulhs_s32(__s0_156, vgetq_lane_s32(__s1_156, __p2_156)); \
61857	__ret_162; \	52781	__ret_156; \
61858	})	52782	})
61859	#else	52783	#else
61860	#define vqdmulhs_laneq_s32(__p0_163, __p1_163, __p2_163) __extension__ ({ \	52784	#define vqdmulhs_laneq_s32(__p0_157, __p1_157, __p2_157) __extension__ ({ \
61861	int32_t __s0_163 = __p0_163; \	52785	int32_t __s0_157 = __p0_157; \
61862	int32x4_t __s1_163 = __p1_163; \	52786	int32x4_t __s1_157 = __p1_157; \
61863	int32x4_t __rev1_163; __rev1_163 = __builtin_shufflevector(__s1_163, __s1_163, 3, 2, 1, 0); \	52787	int32x4_t __rev1_157; __rev1_157 = __builtin_shufflevector(__s1_157, __s1_157, 3, 2, 1, 0); \
61864	int32_t __ret_163; \	52788	int32_t __ret_157; \
61865	__ret_163 = __noswap_vqdmulhs_s32(__s0_163, __noswap_vgetq_lane_s32(__rev1_163, __p2_163)); \	52789	__ret_157 = vqdmulhs_s32(__s0_157, __noswap_vgetq_lane_s32(__rev1_157, __p2_157)); \
61866	__ret_163; \	52790	__ret_157; \
61867	})	52791	})
61868	#endif	52792	#endif
61869		52793
61870	#ifdef __LITTLE_ENDIAN__	52794	#ifdef __LITTLE_ENDIAN__
61871	#define vqdmulhh_laneq_s16(__p0_164, __p1_164, __p2_164) __extension__ ({ \	52795	#define vqdmulhh_laneq_s16(__p0_158, __p1_158, __p2_158) __extension__ ({ \
61872	int16_t __s0_164 = __p0_164; \	52796	int16_t __s0_158 = __p0_158; \
61873	int16x8_t __s1_164 = __p1_164; \	52797	int16x8_t __s1_158 = __p1_158; \
61874	int16_t __ret_164; \	52798	int16_t __ret_158; \
61875	__ret_164 = vqdmulhh_s16(__s0_164, vgetq_lane_s16(__s1_164, __p2_164)); \	52799	__ret_158 = vqdmulhh_s16(__s0_158, vgetq_lane_s16(__s1_158, __p2_158)); \
61876	__ret_164; \	52800	__ret_158; \
61877	})	52801	})
61878	#else	52802	#else
61879	#define vqdmulhh_laneq_s16(__p0_165, __p1_165, __p2_165) __extension__ ({ \	52803	#define vqdmulhh_laneq_s16(__p0_159, __p1_159, __p2_159) __extension__ ({ \
61880	int16_t __s0_165 = __p0_165; \	52804	int16_t __s0_159 = __p0_159; \
61881	int16x8_t __s1_165 = __p1_165; \	52805	int16x8_t __s1_159 = __p1_159; \
61882	int16x8_t __rev1_165; __rev1_165 = __builtin_shufflevector(__s1_165, __s1_165, 7, 6, 5, 4, 3, 2, 1, 0); \	52806	int16x8_t __rev1_159; __rev1_159 = __builtin_shufflevector(__s1_159, __s1_159, 7, 6, 5, 4, 3, 2, 1, 0); \
61883	int16_t __ret_165; \	52807	int16_t __ret_159; \
61884	__ret_165 = __noswap_vqdmulhh_s16(__s0_165, __noswap_vgetq_lane_s16(__rev1_165, __p2_165)); \	52808	__ret_159 = vqdmulhh_s16(__s0_159, __noswap_vgetq_lane_s16(__rev1_159, __p2_159)); \
61885	__ret_165; \	52809	__ret_159; \
61886	})	52810	})
61887	#endif	52811	#endif
61888		52812
...	@@ -61970,44 +52894,16 @@ __ai int16_t __noswap_vqdmulhh_s16(int16_t __p0, int16_t __p1) {	...	@@ -61970,44 +52894,16 @@ __ai int16_t __noswap_vqdmulhh_s16(int16_t __p0, int16_t __p1) {
61970	})	52894	})
61971	#endif	52895	#endif
61972		52896
61973	#ifdef __LITTLE_ENDIAN__
61974	__ai int64_t vqdmulls_s32(int32_t __p0, int32_t __p1) {	52897	__ai int64_t vqdmulls_s32(int32_t __p0, int32_t __p1) {
61975	int64_t __ret;	52898	int64_t __ret;
61976	__ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);	52899	__ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
61977	return __ret;	52900	return __ret;
61978	}	52901	}
61979	#else
61980	__ai int64_t vqdmulls_s32(int32_t __p0, int32_t __p1) {
61981	int64_t __ret;
61982	__ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
61983	return __ret;
61984	}
61985	__ai int64_t __noswap_vqdmulls_s32(int32_t __p0, int32_t __p1) {
61986	int64_t __ret;
61987	__ret = (int64_t) __builtin_neon_vqdmulls_s32(__p0, __p1);
61988	return __ret;
61989	}
61990	#endif
61991
61992	#ifdef __LITTLE_ENDIAN__
61993	__ai int32_t vqdmullh_s16(int16_t __p0, int16_t __p1) {
61994	int32_t __ret;
61995	__ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
61996	return __ret;
61997	}
61998	#else
61999	__ai int32_t vqdmullh_s16(int16_t __p0, int16_t __p1) {	52902	__ai int32_t vqdmullh_s16(int16_t __p0, int16_t __p1) {
62000	int32_t __ret;	52903	int32_t __ret;
62001	__ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);	52904	__ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
62002	return __ret;	52905	return __ret;
62003	}	52906	}
62004	__ai int32_t __noswap_vqdmullh_s16(int16_t __p0, int16_t __p1) {
62005	int32_t __ret;
62006	__ret = (int32_t) __builtin_neon_vqdmullh_s16(__p0, __p1);
62007	return __ret;
62008	}
62009	#endif
62010
62011	#ifdef __LITTLE_ENDIAN__	52907	#ifdef __LITTLE_ENDIAN__
62012	__ai int64x2_t vqdmull_high_s32(int32x4_t __p0, int32x4_t __p1) {	52908	__ai int64x2_t vqdmull_high_s32(int32x4_t __p0, int32x4_t __p1) {
62013	int64x2_t __ret;	52909	int64x2_t __ret;
...	@@ -62159,78 +53055,78 @@ __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {	...	@@ -62159,78 +53055,78 @@ __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
62159	#endif	53055	#endif
62160		53056
62161	#ifdef __LITTLE_ENDIAN__	53057	#ifdef __LITTLE_ENDIAN__
62162	#define vqdmulls_lane_s32(__p0_166, __p1_166, __p2_166) __extension__ ({ \	53058	#define vqdmulls_lane_s32(__p0_160, __p1_160, __p2_160) __extension__ ({ \
62163	int32_t __s0_166 = __p0_166; \	53059	int32_t __s0_160 = __p0_160; \
62164	int32x2_t __s1_166 = __p1_166; \	53060	int32x2_t __s1_160 = __p1_160; \
62165	int64_t __ret_166; \	53061	int64_t __ret_160; \
62166	__ret_166 = vqdmulls_s32(__s0_166, vget_lane_s32(__s1_166, __p2_166)); \	53062	__ret_160 = vqdmulls_s32(__s0_160, vget_lane_s32(__s1_160, __p2_160)); \
62167	__ret_166; \	53063	__ret_160; \
62168	})	53064	})
62169	#else	53065	#else
62170	#define vqdmulls_lane_s32(__p0_167, __p1_167, __p2_167) __extension__ ({ \	53066	#define vqdmulls_lane_s32(__p0_161, __p1_161, __p2_161) __extension__ ({ \
62171	int32_t __s0_167 = __p0_167; \	53067	int32_t __s0_161 = __p0_161; \
62172	int32x2_t __s1_167 = __p1_167; \	53068	int32x2_t __s1_161 = __p1_161; \
62173	int32x2_t __rev1_167; __rev1_167 = __builtin_shufflevector(__s1_167, __s1_167, 1, 0); \	53069	int32x2_t __rev1_161; __rev1_161 = __builtin_shufflevector(__s1_161, __s1_161, 1, 0); \
62174	int64_t __ret_167; \	53070	int64_t __ret_161; \
62175	__ret_167 = __noswap_vqdmulls_s32(__s0_167, __noswap_vget_lane_s32(__rev1_167, __p2_167)); \	53071	__ret_161 = vqdmulls_s32(__s0_161, __noswap_vget_lane_s32(__rev1_161, __p2_161)); \
62176	__ret_167; \	53072	__ret_161; \
62177	})	53073	})
62178	#endif	53074	#endif
62179		53075
62180	#ifdef __LITTLE_ENDIAN__	53076	#ifdef __LITTLE_ENDIAN__
62181	#define vqdmullh_lane_s16(__p0_168, __p1_168, __p2_168) __extension__ ({ \	53077	#define vqdmullh_lane_s16(__p0_162, __p1_162, __p2_162) __extension__ ({ \
62182	int16_t __s0_168 = __p0_168; \	53078	int16_t __s0_162 = __p0_162; \
62183	int16x4_t __s1_168 = __p1_168; \	53079	int16x4_t __s1_162 = __p1_162; \
62184	int32_t __ret_168; \	53080	int32_t __ret_162; \
62185	__ret_168 = vqdmullh_s16(__s0_168, vget_lane_s16(__s1_168, __p2_168)); \	53081	__ret_162 = vqdmullh_s16(__s0_162, vget_lane_s16(__s1_162, __p2_162)); \
62186	__ret_168; \	53082	__ret_162; \
62187	})	53083	})
62188	#else	53084	#else
62189	#define vqdmullh_lane_s16(__p0_169, __p1_169, __p2_169) __extension__ ({ \	53085	#define vqdmullh_lane_s16(__p0_163, __p1_163, __p2_163) __extension__ ({ \
62190	int16_t __s0_169 = __p0_169; \	53086	int16_t __s0_163 = __p0_163; \
62191	int16x4_t __s1_169 = __p1_169; \	53087	int16x4_t __s1_163 = __p1_163; \
62192	int16x4_t __rev1_169; __rev1_169 = __builtin_shufflevector(__s1_169, __s1_169, 3, 2, 1, 0); \	53088	int16x4_t __rev1_163; __rev1_163 = __builtin_shufflevector(__s1_163, __s1_163, 3, 2, 1, 0); \
62193	int32_t __ret_169; \	53089	int32_t __ret_163; \
62194	__ret_169 = __noswap_vqdmullh_s16(__s0_169, __noswap_vget_lane_s16(__rev1_169, __p2_169)); \	53090	__ret_163 = vqdmullh_s16(__s0_163, __noswap_vget_lane_s16(__rev1_163, __p2_163)); \
62195	__ret_169; \	53091	__ret_163; \
62196	})	53092	})
62197	#endif	53093	#endif
62198		53094
62199	#ifdef __LITTLE_ENDIAN__	53095	#ifdef __LITTLE_ENDIAN__
62200	#define vqdmulls_laneq_s32(__p0_170, __p1_170, __p2_170) __extension__ ({ \	53096	#define vqdmulls_laneq_s32(__p0_164, __p1_164, __p2_164) __extension__ ({ \
62201	int32_t __s0_170 = __p0_170; \	53097	int32_t __s0_164 = __p0_164; \
62202	int32x4_t __s1_170 = __p1_170; \	53098	int32x4_t __s1_164 = __p1_164; \
62203	int64_t __ret_170; \	53099	int64_t __ret_164; \
62204	__ret_170 = vqdmulls_s32(__s0_170, vgetq_lane_s32(__s1_170, __p2_170)); \	53100	__ret_164 = vqdmulls_s32(__s0_164, vgetq_lane_s32(__s1_164, __p2_164)); \
62205	__ret_170; \	53101	__ret_164; \
62206	})	53102	})
62207	#else	53103	#else
62208	#define vqdmulls_laneq_s32(__p0_171, __p1_171, __p2_171) __extension__ ({ \	53104	#define vqdmulls_laneq_s32(__p0_165, __p1_165, __p2_165) __extension__ ({ \
62209	int32_t __s0_171 = __p0_171; \	53105	int32_t __s0_165 = __p0_165; \
62210	int32x4_t __s1_171 = __p1_171; \	53106	int32x4_t __s1_165 = __p1_165; \
62211	int32x4_t __rev1_171; __rev1_171 = __builtin_shufflevector(__s1_171, __s1_171, 3, 2, 1, 0); \	53107	int32x4_t __rev1_165; __rev1_165 = __builtin_shufflevector(__s1_165, __s1_165, 3, 2, 1, 0); \
62212	int64_t __ret_171; \	53108	int64_t __ret_165; \
62213	__ret_171 = __noswap_vqdmulls_s32(__s0_171, __noswap_vgetq_lane_s32(__rev1_171, __p2_171)); \	53109	__ret_165 = vqdmulls_s32(__s0_165, __noswap_vgetq_lane_s32(__rev1_165, __p2_165)); \
62214	__ret_171; \	53110	__ret_165; \
62215	})	53111	})
62216	#endif	53112	#endif
62217		53113
62218	#ifdef __LITTLE_ENDIAN__	53114	#ifdef __LITTLE_ENDIAN__
62219	#define vqdmullh_laneq_s16(__p0_172, __p1_172, __p2_172) __extension__ ({ \	53115	#define vqdmullh_laneq_s16(__p0_166, __p1_166, __p2_166) __extension__ ({ \
62220	int16_t __s0_172 = __p0_172; \	53116	int16_t __s0_166 = __p0_166; \
62221	int16x8_t __s1_172 = __p1_172; \	53117	int16x8_t __s1_166 = __p1_166; \
62222	int32_t __ret_172; \	53118	int32_t __ret_166; \
62223	__ret_172 = vqdmullh_s16(__s0_172, vgetq_lane_s16(__s1_172, __p2_172)); \	53119	__ret_166 = vqdmullh_s16(__s0_166, vgetq_lane_s16(__s1_166, __p2_166)); \
62224	__ret_172; \	53120	__ret_166; \
62225	})	53121	})
62226	#else	53122	#else
62227	#define vqdmullh_laneq_s16(__p0_173, __p1_173, __p2_173) __extension__ ({ \	53123	#define vqdmullh_laneq_s16(__p0_167, __p1_167, __p2_167) __extension__ ({ \
62228	int16_t __s0_173 = __p0_173; \	53124	int16_t __s0_167 = __p0_167; \
62229	int16x8_t __s1_173 = __p1_173; \	53125	int16x8_t __s1_167 = __p1_167; \
62230	int16x8_t __rev1_173; __rev1_173 = __builtin_shufflevector(__s1_173, __s1_173, 7, 6, 5, 4, 3, 2, 1, 0); \	53126	int16x8_t __rev1_167; __rev1_167 = __builtin_shufflevector(__s1_167, __s1_167, 7, 6, 5, 4, 3, 2, 1, 0); \
62231	int32_t __ret_173; \	53127	int32_t __ret_167; \
62232	__ret_173 = __noswap_vqdmullh_s16(__s0_173, __noswap_vgetq_lane_s16(__rev1_173, __p2_173)); \	53128	__ret_167 = vqdmullh_s16(__s0_167, __noswap_vgetq_lane_s16(__rev1_167, __p2_167)); \
62233	__ret_173; \	53129	__ret_167; \
62234	})	53130	})
62235	#endif	53131	#endif
62236		53132
...	@@ -62276,90 +53172,36 @@ __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {	...	@@ -62276,90 +53172,36 @@ __ai int32x4_t vqdmull_high_n_s16(int16x8_t __p0, int16_t __p1) {
62276	})	53172	})
62277	#endif	53173	#endif
62278		53174
62279	#ifdef __LITTLE_ENDIAN__
62280	__ai int16_t vqmovns_s32(int32_t __p0) {	53175	__ai int16_t vqmovns_s32(int32_t __p0) {
62281	int16_t __ret;	53176	int16_t __ret;
62282	__ret = (int16_t) __builtin_neon_vqmovns_s32(__p0);	53177	__ret = (int16_t) __builtin_neon_vqmovns_s32(__p0);
62283	return __ret;	53178	return __ret;
62284	}	53179	}
62285	#else
62286	__ai int16_t vqmovns_s32(int32_t __p0) {
62287	int16_t __ret;
62288	__ret = (int16_t) __builtin_neon_vqmovns_s32(__p0);
62289	return __ret;
62290	}
62291	#endif
62292
62293	#ifdef __LITTLE_ENDIAN__
62294	__ai int32_t vqmovnd_s64(int64_t __p0) {
62295	int32_t __ret;
62296	__ret = (int32_t) __builtin_neon_vqmovnd_s64(__p0);
62297	return __ret;
62298	}
62299	#else
62300	__ai int32_t vqmovnd_s64(int64_t __p0) {	53180	__ai int32_t vqmovnd_s64(int64_t __p0) {
62301	int32_t __ret;	53181	int32_t __ret;
62302	__ret = (int32_t) __builtin_neon_vqmovnd_s64(__p0);	53182	__ret = (int32_t) __builtin_neon_vqmovnd_s64(__p0);
62303	return __ret;	53183	return __ret;
62304	}	53184	}
62305	#endif
62306
62307	#ifdef __LITTLE_ENDIAN__
62308	__ai int8_t vqmovnh_s16(int16_t __p0) {	53185	__ai int8_t vqmovnh_s16(int16_t __p0) {
62309	int8_t __ret;	53186	int8_t __ret;
62310	__ret = (int8_t) __builtin_neon_vqmovnh_s16(__p0);	53187	__ret = (int8_t) __builtin_neon_vqmovnh_s16(__p0);
62311	return __ret;	53188	return __ret;
62312	}	53189	}
62313	#else
62314	__ai int8_t vqmovnh_s16(int16_t __p0) {
62315	int8_t __ret;
62316	__ret = (int8_t) __builtin_neon_vqmovnh_s16(__p0);
62317	return __ret;
62318	}
62319	#endif
62320
62321	#ifdef __LITTLE_ENDIAN__
62322	__ai uint16_t vqmovns_u32(uint32_t __p0) {	53190	__ai uint16_t vqmovns_u32(uint32_t __p0) {
62323	uint16_t __ret;	53191	uint16_t __ret;
62324	__ret = (uint16_t) __builtin_neon_vqmovns_u32(__p0);	53192	__ret = (uint16_t) __builtin_neon_vqmovns_u32(__p0);
62325	return __ret;	53193	return __ret;
62326	}	53194	}
62327	#else
62328	__ai uint16_t vqmovns_u32(uint32_t __p0) {
62329	uint16_t __ret;
62330	__ret = (uint16_t) __builtin_neon_vqmovns_u32(__p0);
62331	return __ret;
62332	}
62333	#endif
62334
62335	#ifdef __LITTLE_ENDIAN__
62336	__ai uint32_t vqmovnd_u64(uint64_t __p0) {
62337	uint32_t __ret;
62338	__ret = (uint32_t) __builtin_neon_vqmovnd_u64(__p0);
62339	return __ret;
62340	}
62341	#else
62342	__ai uint32_t vqmovnd_u64(uint64_t __p0) {	53195	__ai uint32_t vqmovnd_u64(uint64_t __p0) {
62343	uint32_t __ret;	53196	uint32_t __ret;
62344	__ret = (uint32_t) __builtin_neon_vqmovnd_u64(__p0);	53197	__ret = (uint32_t) __builtin_neon_vqmovnd_u64(__p0);
62345	return __ret;	53198	return __ret;
62346	}	53199	}
62347	#endif
62348
62349	#ifdef __LITTLE_ENDIAN__
62350	__ai uint8_t vqmovnh_u16(uint16_t __p0) {	53200	__ai uint8_t vqmovnh_u16(uint16_t __p0) {
62351	uint8_t __ret;	53201	uint8_t __ret;
62352	__ret = (uint8_t) __builtin_neon_vqmovnh_u16(__p0);	53202	__ret = (uint8_t) __builtin_neon_vqmovnh_u16(__p0);
62353	return __ret;	53203	return __ret;
62354	}	53204	}
62355	#else
62356	__ai uint8_t vqmovnh_u16(uint16_t __p0) {
62357	uint8_t __ret;
62358	__ret = (uint8_t) __builtin_neon_vqmovnh_u16(__p0);
62359	return __ret;
62360	}
62361	#endif
62362
62363	#ifdef __LITTLE_ENDIAN__	53205	#ifdef __LITTLE_ENDIAN__
62364	__ai uint16x8_t vqmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {	53206	__ai uint16x8_t vqmovn_high_u32(uint16x4_t __p0, uint32x4_t __p1) {
62365	uint16x8_t __ret;	53207	uint16x8_t __ret;
...	@@ -62462,48 +53304,21 @@ __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {	...	@@ -62462,48 +53304,21 @@ __ai int8x16_t vqmovn_high_s16(int8x8_t __p0, int16x8_t __p1) {
62462	}	53304	}
62463	#endif	53305	#endif
62464		53306
62465	#ifdef __LITTLE_ENDIAN__
62466	__ai int16_t vqmovuns_s32(int32_t __p0) {
62467	int16_t __ret;
62468	__ret = (int16_t) __builtin_neon_vqmovuns_s32(__p0);
62469	return __ret;
62470	}
62471	#else
62472	__ai int16_t vqmovuns_s32(int32_t __p0) {	53307	__ai int16_t vqmovuns_s32(int32_t __p0) {
62473	int16_t __ret;	53308	int16_t __ret;
62474	__ret = (int16_t) __builtin_neon_vqmovuns_s32(__p0);	53309	__ret = (int16_t) __builtin_neon_vqmovuns_s32(__p0);
62475	return __ret;	53310	return __ret;
62476	}	53311	}
62477	#endif
62478
62479	#ifdef __LITTLE_ENDIAN__
62480	__ai int32_t vqmovund_s64(int64_t __p0) {	53312	__ai int32_t vqmovund_s64(int64_t __p0) {
62481	int32_t __ret;	53313	int32_t __ret;
62482	__ret = (int32_t) __builtin_neon_vqmovund_s64(__p0);	53314	__ret = (int32_t) __builtin_neon_vqmovund_s64(__p0);
62483	return __ret;	53315	return __ret;
62484	}	53316	}
62485	#else
62486	__ai int32_t vqmovund_s64(int64_t __p0) {
62487	int32_t __ret;
62488	__ret = (int32_t) __builtin_neon_vqmovund_s64(__p0);
62489	return __ret;
62490	}
62491	#endif
62492
62493	#ifdef __LITTLE_ENDIAN__
62494	__ai int8_t vqmovunh_s16(int16_t __p0) {
62495	int8_t __ret;
62496	__ret = (int8_t) __builtin_neon_vqmovunh_s16(__p0);
62497	return __ret;
62498	}
62499	#else
62500	__ai int8_t vqmovunh_s16(int16_t __p0) {	53317	__ai int8_t vqmovunh_s16(int16_t __p0) {
62501	int8_t __ret;	53318	int8_t __ret;
62502	__ret = (int8_t) __builtin_neon_vqmovunh_s16(__p0);	53319	__ret = (int8_t) __builtin_neon_vqmovunh_s16(__p0);
62503	return __ret;	53320	return __ret;
62504	}	53321	}
62505	#endif
62506
62507	#ifdef __LITTLE_ENDIAN__	53322	#ifdef __LITTLE_ENDIAN__
62508	__ai uint16x8_t vqmovun_high_s32(int16x4_t __p0, int32x4_t __p1) {	53323	__ai uint16x8_t vqmovun_high_s32(int16x4_t __p0, int32x4_t __p1) {
62509	uint16x8_t __ret;	53324	uint16x8_t __ret;
...	@@ -62571,187 +53386,114 @@ __ai int64x2_t vqnegq_s64(int64x2_t __p0) {	...	@@ -62571,187 +53386,114 @@ __ai int64x2_t vqnegq_s64(int64x2_t __p0) {
62571	}	53386	}
62572	#endif	53387	#endif
62573		53388
62574	#ifdef __LITTLE_ENDIAN__
62575	__ai int64x1_t vqneg_s64(int64x1_t __p0) {
62576	int64x1_t __ret;
62577	__ret = (int64x1_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 3);
62578	return __ret;
62579	}
62580	#else
62581	__ai int64x1_t vqneg_s64(int64x1_t __p0) {	53389	__ai int64x1_t vqneg_s64(int64x1_t __p0) {
62582	int64x1_t __ret;	53390	int64x1_t __ret;
62583	__ret = (int64x1_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 3);	53391	__ret = (int64x1_t) __builtin_neon_vqneg_v((int8x8_t)__p0, 3);
62584	return __ret;	53392	return __ret;
62585	}	53393	}
62586	#endif
62587
62588	#ifdef __LITTLE_ENDIAN__
62589	__ai int8_t vqnegb_s8(int8_t __p0) {	53394	__ai int8_t vqnegb_s8(int8_t __p0) {
62590	int8_t __ret;	53395	int8_t __ret;
62591	__ret = (int8_t) __builtin_neon_vqnegb_s8(__p0);	53396	__ret = (int8_t) __builtin_neon_vqnegb_s8(__p0);
62592	return __ret;	53397	return __ret;
62593	}	53398	}
62594	#else
62595	__ai int8_t vqnegb_s8(int8_t __p0) {
62596	int8_t __ret;
62597	__ret = (int8_t) __builtin_neon_vqnegb_s8(__p0);
62598	return __ret;
62599	}
62600	#endif
62601
62602	#ifdef __LITTLE_ENDIAN__
62603	__ai int32_t vqnegs_s32(int32_t __p0) {
62604	int32_t __ret;
62605	__ret = (int32_t) __builtin_neon_vqnegs_s32(__p0);
62606	return __ret;
62607	}
62608	#else
62609	__ai int32_t vqnegs_s32(int32_t __p0) {	53399	__ai int32_t vqnegs_s32(int32_t __p0) {
62610	int32_t __ret;	53400	int32_t __ret;
62611	__ret = (int32_t) __builtin_neon_vqnegs_s32(__p0);	53401	__ret = (int32_t) __builtin_neon_vqnegs_s32(__p0);
62612	return __ret;	53402	return __ret;
62613	}	53403	}
62614	#endif
62615
62616	#ifdef __LITTLE_ENDIAN__
62617	__ai int64_t vqnegd_s64(int64_t __p0) {	53404	__ai int64_t vqnegd_s64(int64_t __p0) {
62618	int64_t __ret;	53405	int64_t __ret;
62619	__ret = (int64_t) __builtin_neon_vqnegd_s64(__p0);	53406	__ret = (int64_t) __builtin_neon_vqnegd_s64(__p0);
62620	return __ret;	53407	return __ret;
62621	}	53408	}
62622	#else
62623	__ai int64_t vqnegd_s64(int64_t __p0) {
62624	int64_t __ret;
62625	__ret = (int64_t) __builtin_neon_vqnegd_s64(__p0);
62626	return __ret;
62627	}
62628	#endif
62629
62630	#ifdef __LITTLE_ENDIAN__
62631	__ai int16_t vqnegh_s16(int16_t __p0) {	53409	__ai int16_t vqnegh_s16(int16_t __p0) {
62632	int16_t __ret;	53410	int16_t __ret;
62633	__ret = (int16_t) __builtin_neon_vqnegh_s16(__p0);	53411	__ret = (int16_t) __builtin_neon_vqnegh_s16(__p0);
62634	return __ret;	53412	return __ret;
62635	}	53413	}
62636	#else
62637	__ai int16_t vqnegh_s16(int16_t __p0) {
62638	int16_t __ret;
62639	__ret = (int16_t) __builtin_neon_vqnegh_s16(__p0);
62640	return __ret;
62641	}
62642	#endif
62643
62644	#ifdef __LITTLE_ENDIAN__
62645	__ai int32_t vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
62646	int32_t __ret;
62647	__ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
62648	return __ret;
62649	}
62650	#else
62651	__ai int32_t vqrdmulhs_s32(int32_t __p0, int32_t __p1) {	53414	__ai int32_t vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
62652	int32_t __ret;	53415	int32_t __ret;
62653	__ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);	53416	__ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
62654	return __ret;	53417	return __ret;
62655	}	53418	}
62656	__ai int32_t __noswap_vqrdmulhs_s32(int32_t __p0, int32_t __p1) {
62657	int32_t __ret;
62658	__ret = (int32_t) __builtin_neon_vqrdmulhs_s32(__p0, __p1);
62659	return __ret;
62660	}
62661	#endif
62662
62663	#ifdef __LITTLE_ENDIAN__
62664	__ai int16_t vqrdmulhh_s16(int16_t __p0, int16_t __p1) {	53419	__ai int16_t vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
62665	int16_t __ret;	53420	int16_t __ret;
62666	__ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);	53421	__ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
62667	return __ret;	53422	return __ret;
62668	}	53423	}
62669	#else
62670	__ai int16_t vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
62671	int16_t __ret;
62672	__ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
62673	return __ret;
62674	}
62675	__ai int16_t __noswap_vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
62676	int16_t __ret;
62677	__ret = (int16_t) __builtin_neon_vqrdmulhh_s16(__p0, __p1);
62678	return __ret;
62679	}
62680	#endif
62681
62682	#ifdef __LITTLE_ENDIAN__	53424	#ifdef __LITTLE_ENDIAN__
62683	#define vqrdmulhs_lane_s32(__p0_174, __p1_174, __p2_174) __extension__ ({ \	53425	#define vqrdmulhs_lane_s32(__p0_168, __p1_168, __p2_168) __extension__ ({ \
62684	int32_t __s0_174 = __p0_174; \	53426	int32_t __s0_168 = __p0_168; \
62685	int32x2_t __s1_174 = __p1_174; \	53427	int32x2_t __s1_168 = __p1_168; \
62686	int32_t __ret_174; \	53428	int32_t __ret_168; \
62687	__ret_174 = vqrdmulhs_s32(__s0_174, vget_lane_s32(__s1_174, __p2_174)); \	53429	__ret_168 = vqrdmulhs_s32(__s0_168, vget_lane_s32(__s1_168, __p2_168)); \
62688	__ret_174; \	53430	__ret_168; \
62689	})	53431	})
62690	#else	53432	#else
62691	#define vqrdmulhs_lane_s32(__p0_175, __p1_175, __p2_175) __extension__ ({ \	53433	#define vqrdmulhs_lane_s32(__p0_169, __p1_169, __p2_169) __extension__ ({ \
62692	int32_t __s0_175 = __p0_175; \	53434	int32_t __s0_169 = __p0_169; \
62693	int32x2_t __s1_175 = __p1_175; \	53435	int32x2_t __s1_169 = __p1_169; \
62694	int32x2_t __rev1_175; __rev1_175 = __builtin_shufflevector(__s1_175, __s1_175, 1, 0); \	53436	int32x2_t __rev1_169; __rev1_169 = __builtin_shufflevector(__s1_169, __s1_169, 1, 0); \
62695	int32_t __ret_175; \	53437	int32_t __ret_169; \
62696	__ret_175 = __noswap_vqrdmulhs_s32(__s0_175, __noswap_vget_lane_s32(__rev1_175, __p2_175)); \	53438	__ret_169 = vqrdmulhs_s32(__s0_169, __noswap_vget_lane_s32(__rev1_169, __p2_169)); \
62697	__ret_175; \	53439	__ret_169; \
62698	})	53440	})
62699	#endif	53441	#endif
62700		53442
62701	#ifdef __LITTLE_ENDIAN__	53443	#ifdef __LITTLE_ENDIAN__
62702	#define vqrdmulhh_lane_s16(__p0_176, __p1_176, __p2_176) __extension__ ({ \	53444	#define vqrdmulhh_lane_s16(__p0_170, __p1_170, __p2_170) __extension__ ({ \
62703	int16_t __s0_176 = __p0_176; \	53445	int16_t __s0_170 = __p0_170; \
62704	int16x4_t __s1_176 = __p1_176; \	53446	int16x4_t __s1_170 = __p1_170; \
62705	int16_t __ret_176; \	53447	int16_t __ret_170; \
62706	__ret_176 = vqrdmulhh_s16(__s0_176, vget_lane_s16(__s1_176, __p2_176)); \	53448	__ret_170 = vqrdmulhh_s16(__s0_170, vget_lane_s16(__s1_170, __p2_170)); \
62707	__ret_176; \	53449	__ret_170; \
62708	})	53450	})
62709	#else	53451	#else
62710	#define vqrdmulhh_lane_s16(__p0_177, __p1_177, __p2_177) __extension__ ({ \	53452	#define vqrdmulhh_lane_s16(__p0_171, __p1_171, __p2_171) __extension__ ({ \
62711	int16_t __s0_177 = __p0_177; \	53453	int16_t __s0_171 = __p0_171; \
62712	int16x4_t __s1_177 = __p1_177; \	53454	int16x4_t __s1_171 = __p1_171; \
62713	int16x4_t __rev1_177; __rev1_177 = __builtin_shufflevector(__s1_177, __s1_177, 3, 2, 1, 0); \	53455	int16x4_t __rev1_171; __rev1_171 = __builtin_shufflevector(__s1_171, __s1_171, 3, 2, 1, 0); \
62714	int16_t __ret_177; \	53456	int16_t __ret_171; \
62715	__ret_177 = __noswap_vqrdmulhh_s16(__s0_177, __noswap_vget_lane_s16(__rev1_177, __p2_177)); \	53457	__ret_171 = vqrdmulhh_s16(__s0_171, __noswap_vget_lane_s16(__rev1_171, __p2_171)); \
62716	__ret_177; \	53458	__ret_171; \
62717	})	53459	})
62718	#endif	53460	#endif
62719		53461
62720	#ifdef __LITTLE_ENDIAN__	53462	#ifdef __LITTLE_ENDIAN__
62721	#define vqrdmulhs_laneq_s32(__p0_178, __p1_178, __p2_178) __extension__ ({ \	53463	#define vqrdmulhs_laneq_s32(__p0_172, __p1_172, __p2_172) __extension__ ({ \
62722	int32_t __s0_178 = __p0_178; \	53464	int32_t __s0_172 = __p0_172; \
62723	int32x4_t __s1_178 = __p1_178; \	53465	int32x4_t __s1_172 = __p1_172; \
62724	int32_t __ret_178; \	53466	int32_t __ret_172; \
62725	__ret_178 = vqrdmulhs_s32(__s0_178, vgetq_lane_s32(__s1_178, __p2_178)); \	53467	__ret_172 = vqrdmulhs_s32(__s0_172, vgetq_lane_s32(__s1_172, __p2_172)); \
62726	__ret_178; \	53468	__ret_172; \
62727	})	53469	})
62728	#else	53470	#else
62729	#define vqrdmulhs_laneq_s32(__p0_179, __p1_179, __p2_179) __extension__ ({ \	53471	#define vqrdmulhs_laneq_s32(__p0_173, __p1_173, __p2_173) __extension__ ({ \
62730	int32_t __s0_179 = __p0_179; \	53472	int32_t __s0_173 = __p0_173; \
62731	int32x4_t __s1_179 = __p1_179; \	53473	int32x4_t __s1_173 = __p1_173; \
62732	int32x4_t __rev1_179; __rev1_179 = __builtin_shufflevector(__s1_179, __s1_179, 3, 2, 1, 0); \	53474	int32x4_t __rev1_173; __rev1_173 = __builtin_shufflevector(__s1_173, __s1_173, 3, 2, 1, 0); \
62733	int32_t __ret_179; \	53475	int32_t __ret_173; \
62734	__ret_179 = __noswap_vqrdmulhs_s32(__s0_179, __noswap_vgetq_lane_s32(__rev1_179, __p2_179)); \	53476	__ret_173 = vqrdmulhs_s32(__s0_173, __noswap_vgetq_lane_s32(__rev1_173, __p2_173)); \
62735	__ret_179; \	53477	__ret_173; \
62736	})	53478	})
62737	#endif	53479	#endif
62738		53480
62739	#ifdef __LITTLE_ENDIAN__	53481	#ifdef __LITTLE_ENDIAN__
62740	#define vqrdmulhh_laneq_s16(__p0_180, __p1_180, __p2_180) __extension__ ({ \	53482	#define vqrdmulhh_laneq_s16(__p0_174, __p1_174, __p2_174) __extension__ ({ \
62741	int16_t __s0_180 = __p0_180; \	53483	int16_t __s0_174 = __p0_174; \
62742	int16x8_t __s1_180 = __p1_180; \	53484	int16x8_t __s1_174 = __p1_174; \
62743	int16_t __ret_180; \	53485	int16_t __ret_174; \
62744	__ret_180 = vqrdmulhh_s16(__s0_180, vgetq_lane_s16(__s1_180, __p2_180)); \	53486	__ret_174 = vqrdmulhh_s16(__s0_174, vgetq_lane_s16(__s1_174, __p2_174)); \
62745	__ret_180; \	53487	__ret_174; \
62746	})	53488	})
62747	#else	53489	#else
62748	#define vqrdmulhh_laneq_s16(__p0_181, __p1_181, __p2_181) __extension__ ({ \	53490	#define vqrdmulhh_laneq_s16(__p0_175, __p1_175, __p2_175) __extension__ ({ \
62749	int16_t __s0_181 = __p0_181; \	53491	int16_t __s0_175 = __p0_175; \
62750	int16x8_t __s1_181 = __p1_181; \	53492	int16x8_t __s1_175 = __p1_175; \
62751	int16x8_t __rev1_181; __rev1_181 = __builtin_shufflevector(__s1_181, __s1_181, 7, 6, 5, 4, 3, 2, 1, 0); \	53493	int16x8_t __rev1_175; __rev1_175 = __builtin_shufflevector(__s1_175, __s1_175, 7, 6, 5, 4, 3, 2, 1, 0); \
62752	int16_t __ret_181; \	53494	int16_t __ret_175; \
62753	__ret_181 = __noswap_vqrdmulhh_s16(__s0_181, __noswap_vgetq_lane_s16(__rev1_181, __p2_181)); \	53495	__ret_175 = vqrdmulhh_s16(__s0_175, __noswap_vgetq_lane_s16(__rev1_175, __p2_175)); \
62754	__ret_181; \	53496	__ret_175; \
62755	})	53497	})
62756	#endif	53498	#endif
62757		53499
...	@@ -62839,1210 +53581,684 @@ __ai int16_t __noswap_vqrdmulhh_s16(int16_t __p0, int16_t __p1) {	...	@@ -62839,1210 +53581,684 @@ __ai int16_t __noswap_vqrdmulhh_s16(int16_t __p0, int16_t __p1) {
62839	})	53581	})
62840	#endif	53582	#endif
62841		53583
62842	#ifdef __LITTLE_ENDIAN__
62843	__ai uint8_t vqrshlb_u8(uint8_t __p0, uint8_t __p1) {
62844	uint8_t __ret;
62845	__ret = (uint8_t) __builtin_neon_vqrshlb_u8(__p0, __p1);
62846	return __ret;
62847	}
62848	#else
62849	__ai uint8_t vqrshlb_u8(uint8_t __p0, uint8_t __p1) {	53584	__ai uint8_t vqrshlb_u8(uint8_t __p0, uint8_t __p1) {
62850	uint8_t __ret;	53585	uint8_t __ret;
62851	__ret = (uint8_t) __builtin_neon_vqrshlb_u8(__p0, __p1);	53586	__ret = (uint8_t) __builtin_neon_vqrshlb_u8(__p0, __p1);
62852	return __ret;	53587	return __ret;
62853	}	53588	}
62854	#endif
62855
62856	#ifdef __LITTLE_ENDIAN__
62857	__ai uint32_t vqrshls_u32(uint32_t __p0, uint32_t __p1) {	53589	__ai uint32_t vqrshls_u32(uint32_t __p0, uint32_t __p1) {
62858	uint32_t __ret;	53590	uint32_t __ret;
62859	__ret = (uint32_t) __builtin_neon_vqrshls_u32(__p0, __p1);	53591	__ret = (uint32_t) __builtin_neon_vqrshls_u32(__p0, __p1);
62860	return __ret;	53592	return __ret;
62861	}	53593	}
62862	#else
62863	__ai uint32_t vqrshls_u32(uint32_t __p0, uint32_t __p1) {
62864	uint32_t __ret;
62865	__ret = (uint32_t) __builtin_neon_vqrshls_u32(__p0, __p1);
62866	return __ret;
62867	}
62868	#endif
62869
62870	#ifdef __LITTLE_ENDIAN__
62871	__ai uint64_t vqrshld_u64(uint64_t __p0, uint64_t __p1) {
62872	uint64_t __ret;
62873	__ret = (uint64_t) __builtin_neon_vqrshld_u64(__p0, __p1);
62874	return __ret;
62875	}
62876	#else
62877	__ai uint64_t vqrshld_u64(uint64_t __p0, uint64_t __p1) {	53594	__ai uint64_t vqrshld_u64(uint64_t __p0, uint64_t __p1) {
62878	uint64_t __ret;	53595	uint64_t __ret;
62879	__ret = (uint64_t) __builtin_neon_vqrshld_u64(__p0, __p1);	53596	__ret = (uint64_t) __builtin_neon_vqrshld_u64(__p0, __p1);
62880	return __ret;	53597	return __ret;
62881	}	53598	}
62882	#endif
62883
62884	#ifdef __LITTLE_ENDIAN__
62885	__ai uint16_t vqrshlh_u16(uint16_t __p0, uint16_t __p1) {	53599	__ai uint16_t vqrshlh_u16(uint16_t __p0, uint16_t __p1) {
62886	uint16_t __ret;	53600	uint16_t __ret;
62887	__ret = (uint16_t) __builtin_neon_vqrshlh_u16(__p0, __p1);	53601	__ret = (uint16_t) __builtin_neon_vqrshlh_u16(__p0, __p1);
62888	return __ret;	53602	return __ret;
62889	}	53603	}
62890	#else
62891	__ai uint16_t vqrshlh_u16(uint16_t __p0, uint16_t __p1) {
62892	uint16_t __ret;
62893	__ret = (uint16_t) __builtin_neon_vqrshlh_u16(__p0, __p1);
62894	return __ret;
62895	}
62896	#endif
62897
62898	#ifdef __LITTLE_ENDIAN__
62899	__ai int8_t vqrshlb_s8(int8_t __p0, int8_t __p1) {
62900	int8_t __ret;
62901	__ret = (int8_t) __builtin_neon_vqrshlb_s8(__p0, __p1);
62902	return __ret;
62903	}
62904	#else
62905	__ai int8_t vqrshlb_s8(int8_t __p0, int8_t __p1) {	53604	__ai int8_t vqrshlb_s8(int8_t __p0, int8_t __p1) {
62906	int8_t __ret;	53605	int8_t __ret;
62907	__ret = (int8_t) __builtin_neon_vqrshlb_s8(__p0, __p1);	53606	__ret = (int8_t) __builtin_neon_vqrshlb_s8(__p0, __p1);
62908	return __ret;	53607	return __ret;
62909	}	53608	}
62910	#endif
62911
62912	#ifdef __LITTLE_ENDIAN__
62913	__ai int32_t vqrshls_s32(int32_t __p0, int32_t __p1) {
62914	int32_t __ret;
62915	__ret = (int32_t) __builtin_neon_vqrshls_s32(__p0, __p1);
62916	return __ret;
62917	}
62918	#else
62919	__ai int32_t vqrshls_s32(int32_t __p0, int32_t __p1) {	53609	__ai int32_t vqrshls_s32(int32_t __p0, int32_t __p1) {
62920	int32_t __ret;	53610	int32_t __ret;
62921	__ret = (int32_t) __builtin_neon_vqrshls_s32(__p0, __p1);	53611	__ret = (int32_t) __builtin_neon_vqrshls_s32(__p0, __p1);
62922	return __ret;	53612	return __ret;
62923	}	53613	}
62924	#endif
62925
62926	#ifdef __LITTLE_ENDIAN__
62927	__ai int64_t vqrshld_s64(int64_t __p0, int64_t __p1) {	53614	__ai int64_t vqrshld_s64(int64_t __p0, int64_t __p1) {
62928	int64_t __ret;	53615	int64_t __ret;
62929	__ret = (int64_t) __builtin_neon_vqrshld_s64(__p0, __p1);	53616	__ret = (int64_t) __builtin_neon_vqrshld_s64(__p0, __p1);
62930	return __ret;	53617	return __ret;
62931	}	53618	}
62932	#else
62933	__ai int64_t vqrshld_s64(int64_t __p0, int64_t __p1) {
62934	int64_t __ret;
62935	__ret = (int64_t) __builtin_neon_vqrshld_s64(__p0, __p1);
62936	return __ret;
62937	}
62938	#endif
62939
62940	#ifdef __LITTLE_ENDIAN__
62941	__ai int16_t vqrshlh_s16(int16_t __p0, int16_t __p1) {	53619	__ai int16_t vqrshlh_s16(int16_t __p0, int16_t __p1) {
62942	int16_t __ret;	53620	int16_t __ret;
62943	__ret = (int16_t) __builtin_neon_vqrshlh_s16(__p0, __p1);	53621	__ret = (int16_t) __builtin_neon_vqrshlh_s16(__p0, __p1);
62944	return __ret;	53622	return __ret;
62945	}	53623	}
62946	#else
62947	__ai int16_t vqrshlh_s16(int16_t __p0, int16_t __p1) {
62948	int16_t __ret;
62949	__ret = (int16_t) __builtin_neon_vqrshlh_s16(__p0, __p1);
62950	return __ret;
62951	}
62952	#endif
62953
62954	#ifdef __LITTLE_ENDIAN__	53624	#ifdef __LITTLE_ENDIAN__
62955	#define vqrshrn_high_n_u32(__p0_182, __p1_182, __p2_182) __extension__ ({ \	53625	#define vqrshrn_high_n_u32(__p0_176, __p1_176, __p2_176) __extension__ ({ \
62956	uint16x4_t __s0_182 = __p0_182; \	53626	uint16x4_t __s0_176 = __p0_176; \
62957	uint32x4_t __s1_182 = __p1_182; \	53627	uint32x4_t __s1_176 = __p1_176; \
62958	uint16x8_t __ret_182; \	53628	uint16x8_t __ret_176; \
62959	__ret_182 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_182), (uint16x4_t)(vqrshrn_n_u32(__s1_182, __p2_182)))); \	53629	__ret_176 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_176), (uint16x4_t)(vqrshrn_n_u32(__s1_176, __p2_176)))); \
62960	__ret_182; \	53630	__ret_176; \
62961	})	53631	})
62962	#else	53632	#else
62963	#define vqrshrn_high_n_u32(__p0_183, __p1_183, __p2_183) __extension__ ({ \	53633	#define vqrshrn_high_n_u32(__p0_177, __p1_177, __p2_177) __extension__ ({ \
62964	uint16x4_t __s0_183 = __p0_183; \	53634	uint16x4_t __s0_177 = __p0_177; \
62965	uint32x4_t __s1_183 = __p1_183; \	53635	uint32x4_t __s1_177 = __p1_177; \
62966	uint16x4_t __rev0_183; __rev0_183 = __builtin_shufflevector(__s0_183, __s0_183, 3, 2, 1, 0); \	53636	uint16x4_t __rev0_177; __rev0_177 = __builtin_shufflevector(__s0_177, __s0_177, 3, 2, 1, 0); \
62967	uint32x4_t __rev1_183; __rev1_183 = __builtin_shufflevector(__s1_183, __s1_183, 3, 2, 1, 0); \	53637	uint32x4_t __rev1_177; __rev1_177 = __builtin_shufflevector(__s1_177, __s1_177, 3, 2, 1, 0); \
62968	uint16x8_t __ret_183; \	53638	uint16x8_t __ret_177; \
62969	__ret_183 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_183), (uint16x4_t)(__noswap_vqrshrn_n_u32(__rev1_183, __p2_183)))); \	53639	__ret_177 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_177), (uint16x4_t)(__noswap_vqrshrn_n_u32(__rev1_177, __p2_177)))); \
62970	__ret_183 = __builtin_shufflevector(__ret_183, __ret_183, 7, 6, 5, 4, 3, 2, 1, 0); \	53640	__ret_177 = __builtin_shufflevector(__ret_177, __ret_177, 7, 6, 5, 4, 3, 2, 1, 0); \
62971	__ret_183; \	53641	__ret_177; \
62972	})	53642	})
62973	#endif	53643	#endif
62974		53644
62975	#ifdef __LITTLE_ENDIAN__	53645	#ifdef __LITTLE_ENDIAN__
62976	#define vqrshrn_high_n_u64(__p0_184, __p1_184, __p2_184) __extension__ ({ \	53646	#define vqrshrn_high_n_u64(__p0_178, __p1_178, __p2_178) __extension__ ({ \
62977	uint32x2_t __s0_184 = __p0_184; \	53647	uint32x2_t __s0_178 = __p0_178; \
62978	uint64x2_t __s1_184 = __p1_184; \	53648	uint64x2_t __s1_178 = __p1_178; \
62979	uint32x4_t __ret_184; \	53649	uint32x4_t __ret_178; \
62980	__ret_184 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_184), (uint32x2_t)(vqrshrn_n_u64(__s1_184, __p2_184)))); \	53650	__ret_178 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_178), (uint32x2_t)(vqrshrn_n_u64(__s1_178, __p2_178)))); \
62981	__ret_184; \	53651	__ret_178; \
62982	})	53652	})
62983	#else	53653	#else
62984	#define vqrshrn_high_n_u64(__p0_185, __p1_185, __p2_185) __extension__ ({ \	53654	#define vqrshrn_high_n_u64(__p0_179, __p1_179, __p2_179) __extension__ ({ \
62985	uint32x2_t __s0_185 = __p0_185; \	53655	uint32x2_t __s0_179 = __p0_179; \
62986	uint64x2_t __s1_185 = __p1_185; \	53656	uint64x2_t __s1_179 = __p1_179; \
62987	uint32x2_t __rev0_185; __rev0_185 = __builtin_shufflevector(__s0_185, __s0_185, 1, 0); \	53657	uint32x2_t __rev0_179; __rev0_179 = __builtin_shufflevector(__s0_179, __s0_179, 1, 0); \
62988	uint64x2_t __rev1_185; __rev1_185 = __builtin_shufflevector(__s1_185, __s1_185, 1, 0); \	53658	uint64x2_t __rev1_179; __rev1_179 = __builtin_shufflevector(__s1_179, __s1_179, 1, 0); \
62989	uint32x4_t __ret_185; \	53659	uint32x4_t __ret_179; \
62990	__ret_185 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_185), (uint32x2_t)(__noswap_vqrshrn_n_u64(__rev1_185, __p2_185)))); \	53660	__ret_179 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_179), (uint32x2_t)(__noswap_vqrshrn_n_u64(__rev1_179, __p2_179)))); \
62991	__ret_185 = __builtin_shufflevector(__ret_185, __ret_185, 3, 2, 1, 0); \	53661	__ret_179 = __builtin_shufflevector(__ret_179, __ret_179, 3, 2, 1, 0); \
62992	__ret_185; \	53662	__ret_179; \
62993	})	53663	})
62994	#endif	53664	#endif
62995		53665
62996	#ifdef __LITTLE_ENDIAN__	53666	#ifdef __LITTLE_ENDIAN__
62997	#define vqrshrn_high_n_u16(__p0_186, __p1_186, __p2_186) __extension__ ({ \	53667	#define vqrshrn_high_n_u16(__p0_180, __p1_180, __p2_180) __extension__ ({ \
62998	uint8x8_t __s0_186 = __p0_186; \	53668	uint8x8_t __s0_180 = __p0_180; \
62999	uint16x8_t __s1_186 = __p1_186; \	53669	uint16x8_t __s1_180 = __p1_180; \
63000	uint8x16_t __ret_186; \	53670	uint8x16_t __ret_180; \
63001	__ret_186 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_186), (uint8x8_t)(vqrshrn_n_u16(__s1_186, __p2_186)))); \	53671	__ret_180 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_180), (uint8x8_t)(vqrshrn_n_u16(__s1_180, __p2_180)))); \
63002	__ret_186; \	53672	__ret_180; \
63003	})	53673	})
63004	#else	53674	#else
63005	#define vqrshrn_high_n_u16(__p0_187, __p1_187, __p2_187) __extension__ ({ \	53675	#define vqrshrn_high_n_u16(__p0_181, __p1_181, __p2_181) __extension__ ({ \
63006	uint8x8_t __s0_187 = __p0_187; \	53676	uint8x8_t __s0_181 = __p0_181; \
63007	uint16x8_t __s1_187 = __p1_187; \	53677	uint16x8_t __s1_181 = __p1_181; \
63008	uint8x8_t __rev0_187; __rev0_187 = __builtin_shufflevector(__s0_187, __s0_187, 7, 6, 5, 4, 3, 2, 1, 0); \	53678	uint8x8_t __rev0_181; __rev0_181 = __builtin_shufflevector(__s0_181, __s0_181, 7, 6, 5, 4, 3, 2, 1, 0); \
63009	uint16x8_t __rev1_187; __rev1_187 = __builtin_shufflevector(__s1_187, __s1_187, 7, 6, 5, 4, 3, 2, 1, 0); \	53679	uint16x8_t __rev1_181; __rev1_181 = __builtin_shufflevector(__s1_181, __s1_181, 7, 6, 5, 4, 3, 2, 1, 0); \
63010	uint8x16_t __ret_187; \	53680	uint8x16_t __ret_181; \
63011	__ret_187 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_187), (uint8x8_t)(__noswap_vqrshrn_n_u16(__rev1_187, __p2_187)))); \	53681	__ret_181 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_181), (uint8x8_t)(__noswap_vqrshrn_n_u16(__rev1_181, __p2_181)))); \
63012	__ret_187 = __builtin_shufflevector(__ret_187, __ret_187, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	53682	__ret_181 = __builtin_shufflevector(__ret_181, __ret_181, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63013	__ret_187; \	53683	__ret_181; \
63014	})	53684	})
63015	#endif	53685	#endif
63016		53686
63017	#ifdef __LITTLE_ENDIAN__	53687	#ifdef __LITTLE_ENDIAN__
63018	#define vqrshrn_high_n_s32(__p0_188, __p1_188, __p2_188) __extension__ ({ \	53688	#define vqrshrn_high_n_s32(__p0_182, __p1_182, __p2_182) __extension__ ({ \
63019	int16x4_t __s0_188 = __p0_188; \	53689	int16x4_t __s0_182 = __p0_182; \
63020	int32x4_t __s1_188 = __p1_188; \	53690	int32x4_t __s1_182 = __p1_182; \
63021	int16x8_t __ret_188; \	53691	int16x8_t __ret_182; \
63022	__ret_188 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_188), (int16x4_t)(vqrshrn_n_s32(__s1_188, __p2_188)))); \	53692	__ret_182 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_182), (int16x4_t)(vqrshrn_n_s32(__s1_182, __p2_182)))); \
63023	__ret_188; \	53693	__ret_182; \
63024	})	53694	})
63025	#else	53695	#else
63026	#define vqrshrn_high_n_s32(__p0_189, __p1_189, __p2_189) __extension__ ({ \	53696	#define vqrshrn_high_n_s32(__p0_183, __p1_183, __p2_183) __extension__ ({ \
63027	int16x4_t __s0_189 = __p0_189; \	53697	int16x4_t __s0_183 = __p0_183; \
63028	int32x4_t __s1_189 = __p1_189; \	53698	int32x4_t __s1_183 = __p1_183; \
63029	int16x4_t __rev0_189; __rev0_189 = __builtin_shufflevector(__s0_189, __s0_189, 3, 2, 1, 0); \	53699	int16x4_t __rev0_183; __rev0_183 = __builtin_shufflevector(__s0_183, __s0_183, 3, 2, 1, 0); \
63030	int32x4_t __rev1_189; __rev1_189 = __builtin_shufflevector(__s1_189, __s1_189, 3, 2, 1, 0); \	53700	int32x4_t __rev1_183; __rev1_183 = __builtin_shufflevector(__s1_183, __s1_183, 3, 2, 1, 0); \
63031	int16x8_t __ret_189; \	53701	int16x8_t __ret_183; \
63032	__ret_189 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_189), (int16x4_t)(__noswap_vqrshrn_n_s32(__rev1_189, __p2_189)))); \	53702	__ret_183 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_183), (int16x4_t)(__noswap_vqrshrn_n_s32(__rev1_183, __p2_183)))); \
63033	__ret_189 = __builtin_shufflevector(__ret_189, __ret_189, 7, 6, 5, 4, 3, 2, 1, 0); \	53703	__ret_183 = __builtin_shufflevector(__ret_183, __ret_183, 7, 6, 5, 4, 3, 2, 1, 0); \
63034	__ret_189; \	53704	__ret_183; \
63035	})	53705	})
63036	#endif	53706	#endif
63037		53707
63038	#ifdef __LITTLE_ENDIAN__	53708	#ifdef __LITTLE_ENDIAN__
63039	#define vqrshrn_high_n_s64(__p0_190, __p1_190, __p2_190) __extension__ ({ \	53709	#define vqrshrn_high_n_s64(__p0_184, __p1_184, __p2_184) __extension__ ({ \
63040	int32x2_t __s0_190 = __p0_190; \	53710	int32x2_t __s0_184 = __p0_184; \
63041	int64x2_t __s1_190 = __p1_190; \	53711	int64x2_t __s1_184 = __p1_184; \
63042	int32x4_t __ret_190; \	53712	int32x4_t __ret_184; \
63043	__ret_190 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_190), (int32x2_t)(vqrshrn_n_s64(__s1_190, __p2_190)))); \	53713	__ret_184 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_184), (int32x2_t)(vqrshrn_n_s64(__s1_184, __p2_184)))); \
63044	__ret_190; \	53714	__ret_184; \
63045	})	53715	})
63046	#else	53716	#else
63047	#define vqrshrn_high_n_s64(__p0_191, __p1_191, __p2_191) __extension__ ({ \	53717	#define vqrshrn_high_n_s64(__p0_185, __p1_185, __p2_185) __extension__ ({ \
63048	int32x2_t __s0_191 = __p0_191; \	53718	int32x2_t __s0_185 = __p0_185; \
63049	int64x2_t __s1_191 = __p1_191; \	53719	int64x2_t __s1_185 = __p1_185; \
63050	int32x2_t __rev0_191; __rev0_191 = __builtin_shufflevector(__s0_191, __s0_191, 1, 0); \	53720	int32x2_t __rev0_185; __rev0_185 = __builtin_shufflevector(__s0_185, __s0_185, 1, 0); \
63051	int64x2_t __rev1_191; __rev1_191 = __builtin_shufflevector(__s1_191, __s1_191, 1, 0); \	53721	int64x2_t __rev1_185; __rev1_185 = __builtin_shufflevector(__s1_185, __s1_185, 1, 0); \
63052	int32x4_t __ret_191; \	53722	int32x4_t __ret_185; \
63053	__ret_191 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_191), (int32x2_t)(__noswap_vqrshrn_n_s64(__rev1_191, __p2_191)))); \	53723	__ret_185 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_185), (int32x2_t)(__noswap_vqrshrn_n_s64(__rev1_185, __p2_185)))); \
63054	__ret_191 = __builtin_shufflevector(__ret_191, __ret_191, 3, 2, 1, 0); \	53724	__ret_185 = __builtin_shufflevector(__ret_185, __ret_185, 3, 2, 1, 0); \
63055	__ret_191; \	53725	__ret_185; \
63056	})	53726	})
63057	#endif	53727	#endif
63058		53728
63059	#ifdef __LITTLE_ENDIAN__	53729	#ifdef __LITTLE_ENDIAN__
63060	#define vqrshrn_high_n_s16(__p0_192, __p1_192, __p2_192) __extension__ ({ \	53730	#define vqrshrn_high_n_s16(__p0_186, __p1_186, __p2_186) __extension__ ({ \
63061	int8x8_t __s0_192 = __p0_192; \	53731	int8x8_t __s0_186 = __p0_186; \
63062	int16x8_t __s1_192 = __p1_192; \	53732	int16x8_t __s1_186 = __p1_186; \
63063	int8x16_t __ret_192; \	53733	int8x16_t __ret_186; \
63064	__ret_192 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_192), (int8x8_t)(vqrshrn_n_s16(__s1_192, __p2_192)))); \	53734	__ret_186 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_186), (int8x8_t)(vqrshrn_n_s16(__s1_186, __p2_186)))); \
63065	__ret_192; \	53735	__ret_186; \
63066	})	53736	})
63067	#else	53737	#else
63068	#define vqrshrn_high_n_s16(__p0_193, __p1_193, __p2_193) __extension__ ({ \	53738	#define vqrshrn_high_n_s16(__p0_187, __p1_187, __p2_187) __extension__ ({ \
63069	int8x8_t __s0_193 = __p0_193; \	53739	int8x8_t __s0_187 = __p0_187; \
63070	int16x8_t __s1_193 = __p1_193; \	53740	int16x8_t __s1_187 = __p1_187; \
63071	int8x8_t __rev0_193; __rev0_193 = __builtin_shufflevector(__s0_193, __s0_193, 7, 6, 5, 4, 3, 2, 1, 0); \	53741	int8x8_t __rev0_187; __rev0_187 = __builtin_shufflevector(__s0_187, __s0_187, 7, 6, 5, 4, 3, 2, 1, 0); \
63072	int16x8_t __rev1_193; __rev1_193 = __builtin_shufflevector(__s1_193, __s1_193, 7, 6, 5, 4, 3, 2, 1, 0); \	53742	int16x8_t __rev1_187; __rev1_187 = __builtin_shufflevector(__s1_187, __s1_187, 7, 6, 5, 4, 3, 2, 1, 0); \
63073	int8x16_t __ret_193; \	53743	int8x16_t __ret_187; \
63074	__ret_193 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_193), (int8x8_t)(__noswap_vqrshrn_n_s16(__rev1_193, __p2_193)))); \	53744	__ret_187 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_187), (int8x8_t)(__noswap_vqrshrn_n_s16(__rev1_187, __p2_187)))); \
63075	__ret_193 = __builtin_shufflevector(__ret_193, __ret_193, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	53745	__ret_187 = __builtin_shufflevector(__ret_187, __ret_187, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63076	__ret_193; \	53746	__ret_187; \
63077	})	53747	})
63078	#endif	53748	#endif
63079		53749
63080	#ifdef __LITTLE_ENDIAN__
63081	#define vqrshrns_n_u32(__p0, __p1) __extension__ ({ \	53750	#define vqrshrns_n_u32(__p0, __p1) __extension__ ({ \
63082	uint32_t __s0 = __p0; \	53751	uint32_t __s0 = __p0; \
63083	uint16_t __ret; \	53752	uint16_t __ret; \
63084	__ret = (uint16_t) __builtin_neon_vqrshrns_n_u32(__s0, __p1); \	53753	__ret = (uint16_t) __builtin_neon_vqrshrns_n_u32(__s0, __p1); \
63085	__ret; \	53754	__ret; \
63086	})	53755	})
63087	#else
63088	#define vqrshrns_n_u32(__p0, __p1) __extension__ ({ \
63089	uint32_t __s0 = __p0; \
63090	uint16_t __ret; \
63091	__ret = (uint16_t) __builtin_neon_vqrshrns_n_u32(__s0, __p1); \
63092	__ret; \
63093	})
63094	#endif
63095
63096	#ifdef __LITTLE_ENDIAN__
63097	#define vqrshrnd_n_u64(__p0, __p1) __extension__ ({ \
63098	uint64_t __s0 = __p0; \
63099	uint32_t __ret; \
63100	__ret = (uint32_t) __builtin_neon_vqrshrnd_n_u64(__s0, __p1); \
63101	__ret; \
63102	})
63103	#else
63104	#define vqrshrnd_n_u64(__p0, __p1) __extension__ ({ \	53756	#define vqrshrnd_n_u64(__p0, __p1) __extension__ ({ \
63105	uint64_t __s0 = __p0; \	53757	uint64_t __s0 = __p0; \
63106	uint32_t __ret; \	53758	uint32_t __ret; \
63107	__ret = (uint32_t) __builtin_neon_vqrshrnd_n_u64(__s0, __p1); \	53759	__ret = (uint32_t) __builtin_neon_vqrshrnd_n_u64(__s0, __p1); \
63108	__ret; \	53760	__ret; \
63109	})	53761	})
63110	#endif
63111
63112	#ifdef __LITTLE_ENDIAN__
63113	#define vqrshrnh_n_u16(__p0, __p1) __extension__ ({ \	53762	#define vqrshrnh_n_u16(__p0, __p1) __extension__ ({ \
63114	uint16_t __s0 = __p0; \	53763	uint16_t __s0 = __p0; \
63115	uint8_t __ret; \	53764	uint8_t __ret; \
63116	__ret = (uint8_t) __builtin_neon_vqrshrnh_n_u16(__s0, __p1); \	53765	__ret = (uint8_t) __builtin_neon_vqrshrnh_n_u16(__s0, __p1); \
63117	__ret; \	53766	__ret; \
63118	})	53767	})
63119	#else
63120	#define vqrshrnh_n_u16(__p0, __p1) __extension__ ({ \
63121	uint16_t __s0 = __p0; \
63122	uint8_t __ret; \
63123	__ret = (uint8_t) __builtin_neon_vqrshrnh_n_u16(__s0, __p1); \
63124	__ret; \
63125	})
63126	#endif
63127
63128	#ifdef __LITTLE_ENDIAN__
63129	#define vqrshrns_n_s32(__p0, __p1) __extension__ ({ \	53768	#define vqrshrns_n_s32(__p0, __p1) __extension__ ({ \
63130	int32_t __s0 = __p0; \	53769	int32_t __s0 = __p0; \
63131	int16_t __ret; \	53770	int16_t __ret; \
63132	__ret = (int16_t) __builtin_neon_vqrshrns_n_s32(__s0, __p1); \	53771	__ret = (int16_t) __builtin_neon_vqrshrns_n_s32(__s0, __p1); \
63133	__ret; \	53772	__ret; \
63134	})	53773	})
63135	#else
63136	#define vqrshrns_n_s32(__p0, __p1) __extension__ ({ \
63137	int32_t __s0 = __p0; \
63138	int16_t __ret; \
63139	__ret = (int16_t) __builtin_neon_vqrshrns_n_s32(__s0, __p1); \
63140	__ret; \
63141	})
63142	#endif
63143
63144	#ifdef __LITTLE_ENDIAN__
63145	#define vqrshrnd_n_s64(__p0, __p1) __extension__ ({ \
63146	int64_t __s0 = __p0; \
63147	int32_t __ret; \
63148	__ret = (int32_t) __builtin_neon_vqrshrnd_n_s64(__s0, __p1); \
63149	__ret; \
63150	})
63151	#else
63152	#define vqrshrnd_n_s64(__p0, __p1) __extension__ ({ \	53774	#define vqrshrnd_n_s64(__p0, __p1) __extension__ ({ \
63153	int64_t __s0 = __p0; \	53775	int64_t __s0 = __p0; \
63154	int32_t __ret; \	53776	int32_t __ret; \
63155	__ret = (int32_t) __builtin_neon_vqrshrnd_n_s64(__s0, __p1); \	53777	__ret = (int32_t) __builtin_neon_vqrshrnd_n_s64(__s0, __p1); \
63156	__ret; \	53778	__ret; \
63157	})	53779	})
63158	#endif
63159
63160	#ifdef __LITTLE_ENDIAN__
63161	#define vqrshrnh_n_s16(__p0, __p1) __extension__ ({ \	53780	#define vqrshrnh_n_s16(__p0, __p1) __extension__ ({ \
63162	int16_t __s0 = __p0; \	53781	int16_t __s0 = __p0; \
63163	int8_t __ret; \	53782	int8_t __ret; \
63164	__ret = (int8_t) __builtin_neon_vqrshrnh_n_s16(__s0, __p1); \	53783	__ret = (int8_t) __builtin_neon_vqrshrnh_n_s16(__s0, __p1); \
63165	__ret; \	53784	__ret; \
63166	})	53785	})
63167	#else
63168	#define vqrshrnh_n_s16(__p0, __p1) __extension__ ({ \
63169	int16_t __s0 = __p0; \
63170	int8_t __ret; \
63171	__ret = (int8_t) __builtin_neon_vqrshrnh_n_s16(__s0, __p1); \
63172	__ret; \
63173	})
63174	#endif
63175
63176	#ifdef __LITTLE_ENDIAN__	53786	#ifdef __LITTLE_ENDIAN__
63177	#define vqrshrun_high_n_s32(__p0_194, __p1_194, __p2_194) __extension__ ({ \	53787	#define vqrshrun_high_n_s32(__p0_188, __p1_188, __p2_188) __extension__ ({ \
63178	int16x4_t __s0_194 = __p0_194; \	53788	int16x4_t __s0_188 = __p0_188; \
63179	int32x4_t __s1_194 = __p1_194; \	53789	int32x4_t __s1_188 = __p1_188; \
63180	int16x8_t __ret_194; \	53790	int16x8_t __ret_188; \
63181	__ret_194 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_194), (int16x4_t)(vqrshrun_n_s32(__s1_194, __p2_194)))); \	53791	__ret_188 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_188), (int16x4_t)(vqrshrun_n_s32(__s1_188, __p2_188)))); \
63182	__ret_194; \	53792	__ret_188; \
63183	})	53793	})
63184	#else	53794	#else
63185	#define vqrshrun_high_n_s32(__p0_195, __p1_195, __p2_195) __extension__ ({ \	53795	#define vqrshrun_high_n_s32(__p0_189, __p1_189, __p2_189) __extension__ ({ \
63186	int16x4_t __s0_195 = __p0_195; \	53796	int16x4_t __s0_189 = __p0_189; \
63187	int32x4_t __s1_195 = __p1_195; \	53797	int32x4_t __s1_189 = __p1_189; \
63188	int16x4_t __rev0_195; __rev0_195 = __builtin_shufflevector(__s0_195, __s0_195, 3, 2, 1, 0); \	53798	int16x4_t __rev0_189; __rev0_189 = __builtin_shufflevector(__s0_189, __s0_189, 3, 2, 1, 0); \
63189	int32x4_t __rev1_195; __rev1_195 = __builtin_shufflevector(__s1_195, __s1_195, 3, 2, 1, 0); \	53799	int32x4_t __rev1_189; __rev1_189 = __builtin_shufflevector(__s1_189, __s1_189, 3, 2, 1, 0); \
63190	int16x8_t __ret_195; \	53800	int16x8_t __ret_189; \
63191	__ret_195 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_195), (int16x4_t)(__noswap_vqrshrun_n_s32(__rev1_195, __p2_195)))); \	53801	__ret_189 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_189), (int16x4_t)(__noswap_vqrshrun_n_s32(__rev1_189, __p2_189)))); \
63192	__ret_195 = __builtin_shufflevector(__ret_195, __ret_195, 7, 6, 5, 4, 3, 2, 1, 0); \	53802	__ret_189 = __builtin_shufflevector(__ret_189, __ret_189, 7, 6, 5, 4, 3, 2, 1, 0); \
63193	__ret_195; \	53803	__ret_189; \
63194	})	53804	})
63195	#endif	53805	#endif
63196		53806
63197	#ifdef __LITTLE_ENDIAN__	53807	#ifdef __LITTLE_ENDIAN__
63198	#define vqrshrun_high_n_s64(__p0_196, __p1_196, __p2_196) __extension__ ({ \	53808	#define vqrshrun_high_n_s64(__p0_190, __p1_190, __p2_190) __extension__ ({ \
63199	int32x2_t __s0_196 = __p0_196; \	53809	int32x2_t __s0_190 = __p0_190; \
63200	int64x2_t __s1_196 = __p1_196; \	53810	int64x2_t __s1_190 = __p1_190; \
63201	int32x4_t __ret_196; \	53811	int32x4_t __ret_190; \
63202	__ret_196 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_196), (int32x2_t)(vqrshrun_n_s64(__s1_196, __p2_196)))); \	53812	__ret_190 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_190), (int32x2_t)(vqrshrun_n_s64(__s1_190, __p2_190)))); \
63203	__ret_196; \	53813	__ret_190; \
63204	})	53814	})
63205	#else	53815	#else
63206	#define vqrshrun_high_n_s64(__p0_197, __p1_197, __p2_197) __extension__ ({ \	53816	#define vqrshrun_high_n_s64(__p0_191, __p1_191, __p2_191) __extension__ ({ \
63207	int32x2_t __s0_197 = __p0_197; \	53817	int32x2_t __s0_191 = __p0_191; \
63208	int64x2_t __s1_197 = __p1_197; \	53818	int64x2_t __s1_191 = __p1_191; \
63209	int32x2_t __rev0_197; __rev0_197 = __builtin_shufflevector(__s0_197, __s0_197, 1, 0); \	53819	int32x2_t __rev0_191; __rev0_191 = __builtin_shufflevector(__s0_191, __s0_191, 1, 0); \
63210	int64x2_t __rev1_197; __rev1_197 = __builtin_shufflevector(__s1_197, __s1_197, 1, 0); \	53820	int64x2_t __rev1_191; __rev1_191 = __builtin_shufflevector(__s1_191, __s1_191, 1, 0); \
63211	int32x4_t __ret_197; \	53821	int32x4_t __ret_191; \
63212	__ret_197 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_197), (int32x2_t)(__noswap_vqrshrun_n_s64(__rev1_197, __p2_197)))); \	53822	__ret_191 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_191), (int32x2_t)(__noswap_vqrshrun_n_s64(__rev1_191, __p2_191)))); \
63213	__ret_197 = __builtin_shufflevector(__ret_197, __ret_197, 3, 2, 1, 0); \	53823	__ret_191 = __builtin_shufflevector(__ret_191, __ret_191, 3, 2, 1, 0); \
63214	__ret_197; \	53824	__ret_191; \
63215	})	53825	})
63216	#endif	53826	#endif
63217		53827
63218	#ifdef __LITTLE_ENDIAN__	53828	#ifdef __LITTLE_ENDIAN__
63219	#define vqrshrun_high_n_s16(__p0_198, __p1_198, __p2_198) __extension__ ({ \	53829	#define vqrshrun_high_n_s16(__p0_192, __p1_192, __p2_192) __extension__ ({ \
63220	int8x8_t __s0_198 = __p0_198; \	53830	int8x8_t __s0_192 = __p0_192; \
63221	int16x8_t __s1_198 = __p1_198; \	53831	int16x8_t __s1_192 = __p1_192; \
63222	int8x16_t __ret_198; \	53832	int8x16_t __ret_192; \
63223	__ret_198 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_198), (int8x8_t)(vqrshrun_n_s16(__s1_198, __p2_198)))); \	53833	__ret_192 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_192), (int8x8_t)(vqrshrun_n_s16(__s1_192, __p2_192)))); \
63224	__ret_198; \	53834	__ret_192; \
63225	})	53835	})
63226	#else	53836	#else
63227	#define vqrshrun_high_n_s16(__p0_199, __p1_199, __p2_199) __extension__ ({ \	53837	#define vqrshrun_high_n_s16(__p0_193, __p1_193, __p2_193) __extension__ ({ \
63228	int8x8_t __s0_199 = __p0_199; \	53838	int8x8_t __s0_193 = __p0_193; \
63229	int16x8_t __s1_199 = __p1_199; \	53839	int16x8_t __s1_193 = __p1_193; \
63230	int8x8_t __rev0_199; __rev0_199 = __builtin_shufflevector(__s0_199, __s0_199, 7, 6, 5, 4, 3, 2, 1, 0); \	53840	int8x8_t __rev0_193; __rev0_193 = __builtin_shufflevector(__s0_193, __s0_193, 7, 6, 5, 4, 3, 2, 1, 0); \
63231	int16x8_t __rev1_199; __rev1_199 = __builtin_shufflevector(__s1_199, __s1_199, 7, 6, 5, 4, 3, 2, 1, 0); \	53841	int16x8_t __rev1_193; __rev1_193 = __builtin_shufflevector(__s1_193, __s1_193, 7, 6, 5, 4, 3, 2, 1, 0); \
63232	int8x16_t __ret_199; \	53842	int8x16_t __ret_193; \
63233	__ret_199 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_199), (int8x8_t)(__noswap_vqrshrun_n_s16(__rev1_199, __p2_199)))); \	53843	__ret_193 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_193), (int8x8_t)(__noswap_vqrshrun_n_s16(__rev1_193, __p2_193)))); \
63234	__ret_199 = __builtin_shufflevector(__ret_199, __ret_199, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	53844	__ret_193 = __builtin_shufflevector(__ret_193, __ret_193, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63235	__ret_199; \	53845	__ret_193; \
63236	})	53846	})
63237	#endif	53847	#endif
63238		53848
63239	#ifdef __LITTLE_ENDIAN__
63240	#define vqrshruns_n_s32(__p0, __p1) __extension__ ({ \
63241	int32_t __s0 = __p0; \
63242	int16_t __ret; \
63243	__ret = (int16_t) __builtin_neon_vqrshruns_n_s32(__s0, __p1); \
63244	__ret; \
63245	})
63246	#else
63247	#define vqrshruns_n_s32(__p0, __p1) __extension__ ({ \	53849	#define vqrshruns_n_s32(__p0, __p1) __extension__ ({ \
63248	int32_t __s0 = __p0; \	53850	int32_t __s0 = __p0; \
63249	int16_t __ret; \	53851	int16_t __ret; \
63250	__ret = (int16_t) __builtin_neon_vqrshruns_n_s32(__s0, __p1); \	53852	__ret = (int16_t) __builtin_neon_vqrshruns_n_s32(__s0, __p1); \
63251	__ret; \	53853	__ret; \
63252	})	53854	})
63253	#endif
63254
63255	#ifdef __LITTLE_ENDIAN__
63256	#define vqrshrund_n_s64(__p0, __p1) __extension__ ({ \
63257	int64_t __s0 = __p0; \
63258	int32_t __ret; \
63259	__ret = (int32_t) __builtin_neon_vqrshrund_n_s64(__s0, __p1); \
63260	__ret; \
63261	})
63262	#else
63263	#define vqrshrund_n_s64(__p0, __p1) __extension__ ({ \	53855	#define vqrshrund_n_s64(__p0, __p1) __extension__ ({ \
63264	int64_t __s0 = __p0; \	53856	int64_t __s0 = __p0; \
63265	int32_t __ret; \	53857	int32_t __ret; \
63266	__ret = (int32_t) __builtin_neon_vqrshrund_n_s64(__s0, __p1); \	53858	__ret = (int32_t) __builtin_neon_vqrshrund_n_s64(__s0, __p1); \
63267	__ret; \	53859	__ret; \
63268	})	53860	})
63269	#endif
63270
63271	#ifdef __LITTLE_ENDIAN__
63272	#define vqrshrunh_n_s16(__p0, __p1) __extension__ ({ \
63273	int16_t __s0 = __p0; \
63274	int8_t __ret; \
63275	__ret = (int8_t) __builtin_neon_vqrshrunh_n_s16(__s0, __p1); \
63276	__ret; \
63277	})
63278	#else
63279	#define vqrshrunh_n_s16(__p0, __p1) __extension__ ({ \	53861	#define vqrshrunh_n_s16(__p0, __p1) __extension__ ({ \
63280	int16_t __s0 = __p0; \	53862	int16_t __s0 = __p0; \
63281	int8_t __ret; \	53863	int8_t __ret; \
63282	__ret = (int8_t) __builtin_neon_vqrshrunh_n_s16(__s0, __p1); \	53864	__ret = (int8_t) __builtin_neon_vqrshrunh_n_s16(__s0, __p1); \
63283	__ret; \	53865	__ret; \
63284	})	53866	})
63285	#endif
63286
63287	#ifdef __LITTLE_ENDIAN__
63288	__ai uint8_t vqshlb_u8(uint8_t __p0, uint8_t __p1) {
63289	uint8_t __ret;
63290	__ret = (uint8_t) __builtin_neon_vqshlb_u8(__p0, __p1);
63291	return __ret;
63292	}
63293	#else
63294	__ai uint8_t vqshlb_u8(uint8_t __p0, uint8_t __p1) {	53867	__ai uint8_t vqshlb_u8(uint8_t __p0, uint8_t __p1) {
63295	uint8_t __ret;	53868	uint8_t __ret;
63296	__ret = (uint8_t) __builtin_neon_vqshlb_u8(__p0, __p1);	53869	__ret = (uint8_t) __builtin_neon_vqshlb_u8(__p0, __p1);
63297	return __ret;	53870	return __ret;
63298	}	53871	}
63299	#endif
63300
63301	#ifdef __LITTLE_ENDIAN__
63302	__ai uint32_t vqshls_u32(uint32_t __p0, uint32_t __p1) {
63303	uint32_t __ret;
63304	__ret = (uint32_t) __builtin_neon_vqshls_u32(__p0, __p1);
63305	return __ret;
63306	}
63307	#else
63308	__ai uint32_t vqshls_u32(uint32_t __p0, uint32_t __p1) {	53872	__ai uint32_t vqshls_u32(uint32_t __p0, uint32_t __p1) {
63309	uint32_t __ret;	53873	uint32_t __ret;
63310	__ret = (uint32_t) __builtin_neon_vqshls_u32(__p0, __p1);	53874	__ret = (uint32_t) __builtin_neon_vqshls_u32(__p0, __p1);
63311	return __ret;	53875	return __ret;
63312	}	53876	}
63313	#endif
63314
63315	#ifdef __LITTLE_ENDIAN__
63316	__ai uint64_t vqshld_u64(uint64_t __p0, uint64_t __p1) {
63317	uint64_t __ret;
63318	__ret = (uint64_t) __builtin_neon_vqshld_u64(__p0, __p1);
63319	return __ret;
63320	}
63321	#else
63322	__ai uint64_t vqshld_u64(uint64_t __p0, uint64_t __p1) {	53877	__ai uint64_t vqshld_u64(uint64_t __p0, uint64_t __p1) {
63323	uint64_t __ret;	53878	uint64_t __ret;
63324	__ret = (uint64_t) __builtin_neon_vqshld_u64(__p0, __p1);	53879	__ret = (uint64_t) __builtin_neon_vqshld_u64(__p0, __p1);
63325	return __ret;	53880	return __ret;
63326	}	53881	}
63327	#endif
63328
63329	#ifdef __LITTLE_ENDIAN__
63330	__ai uint16_t vqshlh_u16(uint16_t __p0, uint16_t __p1) {
63331	uint16_t __ret;
63332	__ret = (uint16_t) __builtin_neon_vqshlh_u16(__p0, __p1);
63333	return __ret;
63334	}
63335	#else
63336	__ai uint16_t vqshlh_u16(uint16_t __p0, uint16_t __p1) {	53882	__ai uint16_t vqshlh_u16(uint16_t __p0, uint16_t __p1) {
63337	uint16_t __ret;	53883	uint16_t __ret;
63338	__ret = (uint16_t) __builtin_neon_vqshlh_u16(__p0, __p1);	53884	__ret = (uint16_t) __builtin_neon_vqshlh_u16(__p0, __p1);
63339	return __ret;	53885	return __ret;
63340	}	53886	}
63341	#endif
63342
63343	#ifdef __LITTLE_ENDIAN__
63344	__ai int8_t vqshlb_s8(int8_t __p0, int8_t __p1) {
63345	int8_t __ret;
63346	__ret = (int8_t) __builtin_neon_vqshlb_s8(__p0, __p1);
63347	return __ret;
63348	}
63349	#else
63350	__ai int8_t vqshlb_s8(int8_t __p0, int8_t __p1) {	53887	__ai int8_t vqshlb_s8(int8_t __p0, int8_t __p1) {
63351	int8_t __ret;	53888	int8_t __ret;
63352	__ret = (int8_t) __builtin_neon_vqshlb_s8(__p0, __p1);	53889	__ret = (int8_t) __builtin_neon_vqshlb_s8(__p0, __p1);
63353	return __ret;	53890	return __ret;
63354	}	53891	}
63355	#endif
63356
63357	#ifdef __LITTLE_ENDIAN__
63358	__ai int32_t vqshls_s32(int32_t __p0, int32_t __p1) {
63359	int32_t __ret;
63360	__ret = (int32_t) __builtin_neon_vqshls_s32(__p0, __p1);
63361	return __ret;
63362	}
63363	#else
63364	__ai int32_t vqshls_s32(int32_t __p0, int32_t __p1) {	53892	__ai int32_t vqshls_s32(int32_t __p0, int32_t __p1) {
63365	int32_t __ret;	53893	int32_t __ret;
63366	__ret = (int32_t) __builtin_neon_vqshls_s32(__p0, __p1);	53894	__ret = (int32_t) __builtin_neon_vqshls_s32(__p0, __p1);
63367	return __ret;	53895	return __ret;
63368	}	53896	}
63369	#endif
63370
63371	#ifdef __LITTLE_ENDIAN__
63372	__ai int64_t vqshld_s64(int64_t __p0, int64_t __p1) {
63373	int64_t __ret;
63374	__ret = (int64_t) __builtin_neon_vqshld_s64(__p0, __p1);
63375	return __ret;
63376	}
63377	#else
63378	__ai int64_t vqshld_s64(int64_t __p0, int64_t __p1) {	53897	__ai int64_t vqshld_s64(int64_t __p0, int64_t __p1) {
63379	int64_t __ret;	53898	int64_t __ret;
63380	__ret = (int64_t) __builtin_neon_vqshld_s64(__p0, __p1);	53899	__ret = (int64_t) __builtin_neon_vqshld_s64(__p0, __p1);
63381	return __ret;	53900	return __ret;
63382	}	53901	}
63383	#endif
63384
63385	#ifdef __LITTLE_ENDIAN__
63386	__ai int16_t vqshlh_s16(int16_t __p0, int16_t __p1) {
63387	int16_t __ret;
63388	__ret = (int16_t) __builtin_neon_vqshlh_s16(__p0, __p1);
63389	return __ret;
63390	}
63391	#else
63392	__ai int16_t vqshlh_s16(int16_t __p0, int16_t __p1) {	53902	__ai int16_t vqshlh_s16(int16_t __p0, int16_t __p1) {
63393	int16_t __ret;	53903	int16_t __ret;
63394	__ret = (int16_t) __builtin_neon_vqshlh_s16(__p0, __p1);	53904	__ret = (int16_t) __builtin_neon_vqshlh_s16(__p0, __p1);
63395	return __ret;	53905	return __ret;
63396	}	53906	}
63397	#endif
63398
63399	#ifdef __LITTLE_ENDIAN__
63400	#define vqshlb_n_u8(__p0, __p1) __extension__ ({ \
63401	uint8_t __s0 = __p0; \
63402	uint8_t __ret; \
63403	__ret = (uint8_t) __builtin_neon_vqshlb_n_u8(__s0, __p1); \
63404	__ret; \
63405	})
63406	#else
63407	#define vqshlb_n_u8(__p0, __p1) __extension__ ({ \	53907	#define vqshlb_n_u8(__p0, __p1) __extension__ ({ \
63408	uint8_t __s0 = __p0; \	53908	uint8_t __s0 = __p0; \
63409	uint8_t __ret; \	53909	uint8_t __ret; \
63410	__ret = (uint8_t) __builtin_neon_vqshlb_n_u8(__s0, __p1); \	53910	__ret = (uint8_t) __builtin_neon_vqshlb_n_u8(__s0, __p1); \
63411	__ret; \	53911	__ret; \
63412	})	53912	})
63413	#endif
63414
63415	#ifdef __LITTLE_ENDIAN__
63416	#define vqshls_n_u32(__p0, __p1) __extension__ ({ \
63417	uint32_t __s0 = __p0; \
63418	uint32_t __ret; \
63419	__ret = (uint32_t) __builtin_neon_vqshls_n_u32(__s0, __p1); \
63420	__ret; \
63421	})
63422	#else
63423	#define vqshls_n_u32(__p0, __p1) __extension__ ({ \	53913	#define vqshls_n_u32(__p0, __p1) __extension__ ({ \
63424	uint32_t __s0 = __p0; \	53914	uint32_t __s0 = __p0; \
63425	uint32_t __ret; \	53915	uint32_t __ret; \
63426	__ret = (uint32_t) __builtin_neon_vqshls_n_u32(__s0, __p1); \	53916	__ret = (uint32_t) __builtin_neon_vqshls_n_u32(__s0, __p1); \
63427	__ret; \	53917	__ret; \
63428	})	53918	})
63429	#endif
63430
63431	#ifdef __LITTLE_ENDIAN__
63432	#define vqshld_n_u64(__p0, __p1) __extension__ ({ \
63433	uint64_t __s0 = __p0; \
63434	uint64_t __ret; \
63435	__ret = (uint64_t) __builtin_neon_vqshld_n_u64(__s0, __p1); \
63436	__ret; \
63437	})
63438	#else
63439	#define vqshld_n_u64(__p0, __p1) __extension__ ({ \	53919	#define vqshld_n_u64(__p0, __p1) __extension__ ({ \
63440	uint64_t __s0 = __p0; \	53920	uint64_t __s0 = __p0; \
63441	uint64_t __ret; \	53921	uint64_t __ret; \
63442	__ret = (uint64_t) __builtin_neon_vqshld_n_u64(__s0, __p1); \	53922	__ret = (uint64_t) __builtin_neon_vqshld_n_u64(__s0, __p1); \
63443	__ret; \	53923	__ret; \
63444	})	53924	})
63445	#endif
63446
63447	#ifdef __LITTLE_ENDIAN__
63448	#define vqshlh_n_u16(__p0, __p1) __extension__ ({ \
63449	uint16_t __s0 = __p0; \
63450	uint16_t __ret; \
63451	__ret = (uint16_t) __builtin_neon_vqshlh_n_u16(__s0, __p1); \
63452	__ret; \
63453	})
63454	#else
63455	#define vqshlh_n_u16(__p0, __p1) __extension__ ({ \	53925	#define vqshlh_n_u16(__p0, __p1) __extension__ ({ \
63456	uint16_t __s0 = __p0; \	53926	uint16_t __s0 = __p0; \
63457	uint16_t __ret; \	53927	uint16_t __ret; \
63458	__ret = (uint16_t) __builtin_neon_vqshlh_n_u16(__s0, __p1); \	53928	__ret = (uint16_t) __builtin_neon_vqshlh_n_u16(__s0, __p1); \
63459	__ret; \	53929	__ret; \
63460	})	53930	})
63461	#endif
63462
63463	#ifdef __LITTLE_ENDIAN__
63464	#define vqshlb_n_s8(__p0, __p1) __extension__ ({ \
63465	int8_t __s0 = __p0; \
63466	int8_t __ret; \
63467	__ret = (int8_t) __builtin_neon_vqshlb_n_s8(__s0, __p1); \
63468	__ret; \
63469	})
63470	#else
63471	#define vqshlb_n_s8(__p0, __p1) __extension__ ({ \	53931	#define vqshlb_n_s8(__p0, __p1) __extension__ ({ \
63472	int8_t __s0 = __p0; \	53932	int8_t __s0 = __p0; \
63473	int8_t __ret; \	53933	int8_t __ret; \
63474	__ret = (int8_t) __builtin_neon_vqshlb_n_s8(__s0, __p1); \	53934	__ret = (int8_t) __builtin_neon_vqshlb_n_s8(__s0, __p1); \
63475	__ret; \	53935	__ret; \
63476	})	53936	})
63477	#endif
63478
63479	#ifdef __LITTLE_ENDIAN__
63480	#define vqshls_n_s32(__p0, __p1) __extension__ ({ \
63481	int32_t __s0 = __p0; \
63482	int32_t __ret; \
63483	__ret = (int32_t) __builtin_neon_vqshls_n_s32(__s0, __p1); \
63484	__ret; \
63485	})
63486	#else
63487	#define vqshls_n_s32(__p0, __p1) __extension__ ({ \	53937	#define vqshls_n_s32(__p0, __p1) __extension__ ({ \
63488	int32_t __s0 = __p0; \	53938	int32_t __s0 = __p0; \
63489	int32_t __ret; \	53939	int32_t __ret; \
63490	__ret = (int32_t) __builtin_neon_vqshls_n_s32(__s0, __p1); \	53940	__ret = (int32_t) __builtin_neon_vqshls_n_s32(__s0, __p1); \
63491	__ret; \	53941	__ret; \
63492	})	53942	})
63493	#endif
63494
63495	#ifdef __LITTLE_ENDIAN__
63496	#define vqshld_n_s64(__p0, __p1) __extension__ ({ \
63497	int64_t __s0 = __p0; \
63498	int64_t __ret; \
63499	__ret = (int64_t) __builtin_neon_vqshld_n_s64(__s0, __p1); \
63500	__ret; \
63501	})
63502	#else
63503	#define vqshld_n_s64(__p0, __p1) __extension__ ({ \	53943	#define vqshld_n_s64(__p0, __p1) __extension__ ({ \
63504	int64_t __s0 = __p0; \	53944	int64_t __s0 = __p0; \
63505	int64_t __ret; \	53945	int64_t __ret; \
63506	__ret = (int64_t) __builtin_neon_vqshld_n_s64(__s0, __p1); \	53946	__ret = (int64_t) __builtin_neon_vqshld_n_s64(__s0, __p1); \
63507	__ret; \	53947	__ret; \
63508	})	53948	})
63509	#endif
63510
63511	#ifdef __LITTLE_ENDIAN__
63512	#define vqshlh_n_s16(__p0, __p1) __extension__ ({ \
63513	int16_t __s0 = __p0; \
63514	int16_t __ret; \
63515	__ret = (int16_t) __builtin_neon_vqshlh_n_s16(__s0, __p1); \
63516	__ret; \
63517	})
63518	#else
63519	#define vqshlh_n_s16(__p0, __p1) __extension__ ({ \	53949	#define vqshlh_n_s16(__p0, __p1) __extension__ ({ \
63520	int16_t __s0 = __p0; \	53950	int16_t __s0 = __p0; \
63521	int16_t __ret; \	53951	int16_t __ret; \
63522	__ret = (int16_t) __builtin_neon_vqshlh_n_s16(__s0, __p1); \	53952	__ret = (int16_t) __builtin_neon_vqshlh_n_s16(__s0, __p1); \
63523	__ret; \	53953	__ret; \
63524	})	53954	})
63525	#endif
63526
63527	#ifdef __LITTLE_ENDIAN__
63528	#define vqshlub_n_s8(__p0, __p1) __extension__ ({ \
63529	int8_t __s0 = __p0; \
63530	int8_t __ret; \
63531	__ret = (int8_t) __builtin_neon_vqshlub_n_s8(__s0, __p1); \
63532	__ret; \
63533	})
63534	#else
63535	#define vqshlub_n_s8(__p0, __p1) __extension__ ({ \	53955	#define vqshlub_n_s8(__p0, __p1) __extension__ ({ \
63536	int8_t __s0 = __p0; \	53956	int8_t __s0 = __p0; \
63537	int8_t __ret; \	53957	int8_t __ret; \
63538	__ret = (int8_t) __builtin_neon_vqshlub_n_s8(__s0, __p1); \	53958	__ret = (int8_t) __builtin_neon_vqshlub_n_s8(__s0, __p1); \
63539	__ret; \	53959	__ret; \
63540	})	53960	})
63541	#endif
63542
63543	#ifdef __LITTLE_ENDIAN__
63544	#define vqshlus_n_s32(__p0, __p1) __extension__ ({ \
63545	int32_t __s0 = __p0; \
63546	int32_t __ret; \
63547	__ret = (int32_t) __builtin_neon_vqshlus_n_s32(__s0, __p1); \
63548	__ret; \
63549	})
63550	#else
63551	#define vqshlus_n_s32(__p0, __p1) __extension__ ({ \	53961	#define vqshlus_n_s32(__p0, __p1) __extension__ ({ \
63552	int32_t __s0 = __p0; \	53962	int32_t __s0 = __p0; \
63553	int32_t __ret; \	53963	int32_t __ret; \
63554	__ret = (int32_t) __builtin_neon_vqshlus_n_s32(__s0, __p1); \	53964	__ret = (int32_t) __builtin_neon_vqshlus_n_s32(__s0, __p1); \
63555	__ret; \	53965	__ret; \
63556	})	53966	})
63557	#endif
63558
63559	#ifdef __LITTLE_ENDIAN__
63560	#define vqshlud_n_s64(__p0, __p1) __extension__ ({ \
63561	int64_t __s0 = __p0; \
63562	int64_t __ret; \
63563	__ret = (int64_t) __builtin_neon_vqshlud_n_s64(__s0, __p1); \
63564	__ret; \
63565	})
63566	#else
63567	#define vqshlud_n_s64(__p0, __p1) __extension__ ({ \	53967	#define vqshlud_n_s64(__p0, __p1) __extension__ ({ \
63568	int64_t __s0 = __p0; \	53968	int64_t __s0 = __p0; \
63569	int64_t __ret; \	53969	int64_t __ret; \
63570	__ret = (int64_t) __builtin_neon_vqshlud_n_s64(__s0, __p1); \	53970	__ret = (int64_t) __builtin_neon_vqshlud_n_s64(__s0, __p1); \
63571	__ret; \	53971	__ret; \
63572	})	53972	})
63573	#endif
63574
63575	#ifdef __LITTLE_ENDIAN__
63576	#define vqshluh_n_s16(__p0, __p1) __extension__ ({ \
63577	int16_t __s0 = __p0; \
63578	int16_t __ret; \
63579	__ret = (int16_t) __builtin_neon_vqshluh_n_s16(__s0, __p1); \
63580	__ret; \
63581	})
63582	#else
63583	#define vqshluh_n_s16(__p0, __p1) __extension__ ({ \	53973	#define vqshluh_n_s16(__p0, __p1) __extension__ ({ \
63584	int16_t __s0 = __p0; \	53974	int16_t __s0 = __p0; \
63585	int16_t __ret; \	53975	int16_t __ret; \
63586	__ret = (int16_t) __builtin_neon_vqshluh_n_s16(__s0, __p1); \	53976	__ret = (int16_t) __builtin_neon_vqshluh_n_s16(__s0, __p1); \
63587	__ret; \	53977	__ret; \
63588	})	53978	})
63589	#endif
63590
63591	#ifdef __LITTLE_ENDIAN__	53979	#ifdef __LITTLE_ENDIAN__
63592	#define vqshrn_high_n_u32(__p0_200, __p1_200, __p2_200) __extension__ ({ \	53980	#define vqshrn_high_n_u32(__p0_194, __p1_194, __p2_194) __extension__ ({ \
63593	uint16x4_t __s0_200 = __p0_200; \	53981	uint16x4_t __s0_194 = __p0_194; \
63594	uint32x4_t __s1_200 = __p1_200; \	53982	uint32x4_t __s1_194 = __p1_194; \
63595	uint16x8_t __ret_200; \	53983	uint16x8_t __ret_194; \
63596	__ret_200 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_200), (uint16x4_t)(vqshrn_n_u32(__s1_200, __p2_200)))); \	53984	__ret_194 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_194), (uint16x4_t)(vqshrn_n_u32(__s1_194, __p2_194)))); \
63597	__ret_200; \	53985	__ret_194; \
63598	})	53986	})
63599	#else	53987	#else
63600	#define vqshrn_high_n_u32(__p0_201, __p1_201, __p2_201) __extension__ ({ \	53988	#define vqshrn_high_n_u32(__p0_195, __p1_195, __p2_195) __extension__ ({ \
63601	uint16x4_t __s0_201 = __p0_201; \	53989	uint16x4_t __s0_195 = __p0_195; \
63602	uint32x4_t __s1_201 = __p1_201; \	53990	uint32x4_t __s1_195 = __p1_195; \
63603	uint16x4_t __rev0_201; __rev0_201 = __builtin_shufflevector(__s0_201, __s0_201, 3, 2, 1, 0); \	53991	uint16x4_t __rev0_195; __rev0_195 = __builtin_shufflevector(__s0_195, __s0_195, 3, 2, 1, 0); \
63604	uint32x4_t __rev1_201; __rev1_201 = __builtin_shufflevector(__s1_201, __s1_201, 3, 2, 1, 0); \	53992	uint32x4_t __rev1_195; __rev1_195 = __builtin_shufflevector(__s1_195, __s1_195, 3, 2, 1, 0); \
63605	uint16x8_t __ret_201; \	53993	uint16x8_t __ret_195; \
63606	__ret_201 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_201), (uint16x4_t)(__noswap_vqshrn_n_u32(__rev1_201, __p2_201)))); \	53994	__ret_195 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_195), (uint16x4_t)(__noswap_vqshrn_n_u32(__rev1_195, __p2_195)))); \
63607	__ret_201 = __builtin_shufflevector(__ret_201, __ret_201, 7, 6, 5, 4, 3, 2, 1, 0); \	53995	__ret_195 = __builtin_shufflevector(__ret_195, __ret_195, 7, 6, 5, 4, 3, 2, 1, 0); \
63608	__ret_201; \	53996	__ret_195; \
63609	})	53997	})
63610	#endif	53998	#endif
63611		53999
63612	#ifdef __LITTLE_ENDIAN__	54000	#ifdef __LITTLE_ENDIAN__
63613	#define vqshrn_high_n_u64(__p0_202, __p1_202, __p2_202) __extension__ ({ \	54001	#define vqshrn_high_n_u64(__p0_196, __p1_196, __p2_196) __extension__ ({ \
63614	uint32x2_t __s0_202 = __p0_202; \	54002	uint32x2_t __s0_196 = __p0_196; \
63615	uint64x2_t __s1_202 = __p1_202; \	54003	uint64x2_t __s1_196 = __p1_196; \
63616	uint32x4_t __ret_202; \	54004	uint32x4_t __ret_196; \
63617	__ret_202 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_202), (uint32x2_t)(vqshrn_n_u64(__s1_202, __p2_202)))); \	54005	__ret_196 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_196), (uint32x2_t)(vqshrn_n_u64(__s1_196, __p2_196)))); \
63618	__ret_202; \	54006	__ret_196; \
63619	})	54007	})
63620	#else	54008	#else
63621	#define vqshrn_high_n_u64(__p0_203, __p1_203, __p2_203) __extension__ ({ \	54009	#define vqshrn_high_n_u64(__p0_197, __p1_197, __p2_197) __extension__ ({ \
63622	uint32x2_t __s0_203 = __p0_203; \	54010	uint32x2_t __s0_197 = __p0_197; \
63623	uint64x2_t __s1_203 = __p1_203; \	54011	uint64x2_t __s1_197 = __p1_197; \
63624	uint32x2_t __rev0_203; __rev0_203 = __builtin_shufflevector(__s0_203, __s0_203, 1, 0); \	54012	uint32x2_t __rev0_197; __rev0_197 = __builtin_shufflevector(__s0_197, __s0_197, 1, 0); \
63625	uint64x2_t __rev1_203; __rev1_203 = __builtin_shufflevector(__s1_203, __s1_203, 1, 0); \	54013	uint64x2_t __rev1_197; __rev1_197 = __builtin_shufflevector(__s1_197, __s1_197, 1, 0); \
63626	uint32x4_t __ret_203; \	54014	uint32x4_t __ret_197; \
63627	__ret_203 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_203), (uint32x2_t)(__noswap_vqshrn_n_u64(__rev1_203, __p2_203)))); \	54015	__ret_197 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_197), (uint32x2_t)(__noswap_vqshrn_n_u64(__rev1_197, __p2_197)))); \
63628	__ret_203 = __builtin_shufflevector(__ret_203, __ret_203, 3, 2, 1, 0); \	54016	__ret_197 = __builtin_shufflevector(__ret_197, __ret_197, 3, 2, 1, 0); \
63629	__ret_203; \	54017	__ret_197; \
63630	})	54018	})
63631	#endif	54019	#endif
63632		54020
63633	#ifdef __LITTLE_ENDIAN__	54021	#ifdef __LITTLE_ENDIAN__
63634	#define vqshrn_high_n_u16(__p0_204, __p1_204, __p2_204) __extension__ ({ \	54022	#define vqshrn_high_n_u16(__p0_198, __p1_198, __p2_198) __extension__ ({ \
63635	uint8x8_t __s0_204 = __p0_204; \	54023	uint8x8_t __s0_198 = __p0_198; \
63636	uint16x8_t __s1_204 = __p1_204; \	54024	uint16x8_t __s1_198 = __p1_198; \
63637	uint8x16_t __ret_204; \	54025	uint8x16_t __ret_198; \
63638	__ret_204 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_204), (uint8x8_t)(vqshrn_n_u16(__s1_204, __p2_204)))); \	54026	__ret_198 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_198), (uint8x8_t)(vqshrn_n_u16(__s1_198, __p2_198)))); \
63639	__ret_204; \	54027	__ret_198; \
63640	})	54028	})
63641	#else	54029	#else
63642	#define vqshrn_high_n_u16(__p0_205, __p1_205, __p2_205) __extension__ ({ \	54030	#define vqshrn_high_n_u16(__p0_199, __p1_199, __p2_199) __extension__ ({ \
63643	uint8x8_t __s0_205 = __p0_205; \	54031	uint8x8_t __s0_199 = __p0_199; \
63644	uint16x8_t __s1_205 = __p1_205; \	54032	uint16x8_t __s1_199 = __p1_199; \
63645	uint8x8_t __rev0_205; __rev0_205 = __builtin_shufflevector(__s0_205, __s0_205, 7, 6, 5, 4, 3, 2, 1, 0); \	54033	uint8x8_t __rev0_199; __rev0_199 = __builtin_shufflevector(__s0_199, __s0_199, 7, 6, 5, 4, 3, 2, 1, 0); \
63646	uint16x8_t __rev1_205; __rev1_205 = __builtin_shufflevector(__s1_205, __s1_205, 7, 6, 5, 4, 3, 2, 1, 0); \	54034	uint16x8_t __rev1_199; __rev1_199 = __builtin_shufflevector(__s1_199, __s1_199, 7, 6, 5, 4, 3, 2, 1, 0); \
63647	uint8x16_t __ret_205; \	54035	uint8x16_t __ret_199; \
63648	__ret_205 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_205), (uint8x8_t)(__noswap_vqshrn_n_u16(__rev1_205, __p2_205)))); \	54036	__ret_199 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_199), (uint8x8_t)(__noswap_vqshrn_n_u16(__rev1_199, __p2_199)))); \
63649	__ret_205 = __builtin_shufflevector(__ret_205, __ret_205, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	54037	__ret_199 = __builtin_shufflevector(__ret_199, __ret_199, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63650	__ret_205; \	54038	__ret_199; \
63651	})	54039	})
63652	#endif	54040	#endif
63653		54041
63654	#ifdef __LITTLE_ENDIAN__	54042	#ifdef __LITTLE_ENDIAN__
63655	#define vqshrn_high_n_s32(__p0_206, __p1_206, __p2_206) __extension__ ({ \	54043	#define vqshrn_high_n_s32(__p0_200, __p1_200, __p2_200) __extension__ ({ \
63656	int16x4_t __s0_206 = __p0_206; \	54044	int16x4_t __s0_200 = __p0_200; \
63657	int32x4_t __s1_206 = __p1_206; \	54045	int32x4_t __s1_200 = __p1_200; \
63658	int16x8_t __ret_206; \	54046	int16x8_t __ret_200; \
63659	__ret_206 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_206), (int16x4_t)(vqshrn_n_s32(__s1_206, __p2_206)))); \	54047	__ret_200 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_200), (int16x4_t)(vqshrn_n_s32(__s1_200, __p2_200)))); \
63660	__ret_206; \	54048	__ret_200; \
63661	})	54049	})
63662	#else	54050	#else
63663	#define vqshrn_high_n_s32(__p0_207, __p1_207, __p2_207) __extension__ ({ \	54051	#define vqshrn_high_n_s32(__p0_201, __p1_201, __p2_201) __extension__ ({ \
63664	int16x4_t __s0_207 = __p0_207; \	54052	int16x4_t __s0_201 = __p0_201; \
63665	int32x4_t __s1_207 = __p1_207; \	54053	int32x4_t __s1_201 = __p1_201; \
63666	int16x4_t __rev0_207; __rev0_207 = __builtin_shufflevector(__s0_207, __s0_207, 3, 2, 1, 0); \	54054	int16x4_t __rev0_201; __rev0_201 = __builtin_shufflevector(__s0_201, __s0_201, 3, 2, 1, 0); \
63667	int32x4_t __rev1_207; __rev1_207 = __builtin_shufflevector(__s1_207, __s1_207, 3, 2, 1, 0); \	54055	int32x4_t __rev1_201; __rev1_201 = __builtin_shufflevector(__s1_201, __s1_201, 3, 2, 1, 0); \
63668	int16x8_t __ret_207; \	54056	int16x8_t __ret_201; \
63669	__ret_207 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_207), (int16x4_t)(__noswap_vqshrn_n_s32(__rev1_207, __p2_207)))); \	54057	__ret_201 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_201), (int16x4_t)(__noswap_vqshrn_n_s32(__rev1_201, __p2_201)))); \
63670	__ret_207 = __builtin_shufflevector(__ret_207, __ret_207, 7, 6, 5, 4, 3, 2, 1, 0); \	54058	__ret_201 = __builtin_shufflevector(__ret_201, __ret_201, 7, 6, 5, 4, 3, 2, 1, 0); \
63671	__ret_207; \	54059	__ret_201; \
63672	})	54060	})
63673	#endif	54061	#endif
63674		54062
63675	#ifdef __LITTLE_ENDIAN__	54063	#ifdef __LITTLE_ENDIAN__
63676	#define vqshrn_high_n_s64(__p0_208, __p1_208, __p2_208) __extension__ ({ \	54064	#define vqshrn_high_n_s64(__p0_202, __p1_202, __p2_202) __extension__ ({ \
63677	int32x2_t __s0_208 = __p0_208; \	54065	int32x2_t __s0_202 = __p0_202; \
63678	int64x2_t __s1_208 = __p1_208; \	54066	int64x2_t __s1_202 = __p1_202; \
63679	int32x4_t __ret_208; \	54067	int32x4_t __ret_202; \
63680	__ret_208 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_208), (int32x2_t)(vqshrn_n_s64(__s1_208, __p2_208)))); \	54068	__ret_202 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_202), (int32x2_t)(vqshrn_n_s64(__s1_202, __p2_202)))); \
63681	__ret_208; \	54069	__ret_202; \
63682	})	54070	})
63683	#else	54071	#else
63684	#define vqshrn_high_n_s64(__p0_209, __p1_209, __p2_209) __extension__ ({ \	54072	#define vqshrn_high_n_s64(__p0_203, __p1_203, __p2_203) __extension__ ({ \
63685	int32x2_t __s0_209 = __p0_209; \	54073	int32x2_t __s0_203 = __p0_203; \
63686	int64x2_t __s1_209 = __p1_209; \	54074	int64x2_t __s1_203 = __p1_203; \
63687	int32x2_t __rev0_209; __rev0_209 = __builtin_shufflevector(__s0_209, __s0_209, 1, 0); \	54075	int32x2_t __rev0_203; __rev0_203 = __builtin_shufflevector(__s0_203, __s0_203, 1, 0); \
63688	int64x2_t __rev1_209; __rev1_209 = __builtin_shufflevector(__s1_209, __s1_209, 1, 0); \	54076	int64x2_t __rev1_203; __rev1_203 = __builtin_shufflevector(__s1_203, __s1_203, 1, 0); \
63689	int32x4_t __ret_209; \	54077	int32x4_t __ret_203; \
63690	__ret_209 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_209), (int32x2_t)(__noswap_vqshrn_n_s64(__rev1_209, __p2_209)))); \	54078	__ret_203 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_203), (int32x2_t)(__noswap_vqshrn_n_s64(__rev1_203, __p2_203)))); \
63691	__ret_209 = __builtin_shufflevector(__ret_209, __ret_209, 3, 2, 1, 0); \	54079	__ret_203 = __builtin_shufflevector(__ret_203, __ret_203, 3, 2, 1, 0); \
63692	__ret_209; \	54080	__ret_203; \
63693	})	54081	})
63694	#endif	54082	#endif
63695		54083
63696	#ifdef __LITTLE_ENDIAN__	54084	#ifdef __LITTLE_ENDIAN__
63697	#define vqshrn_high_n_s16(__p0_210, __p1_210, __p2_210) __extension__ ({ \	54085	#define vqshrn_high_n_s16(__p0_204, __p1_204, __p2_204) __extension__ ({ \
63698	int8x8_t __s0_210 = __p0_210; \	54086	int8x8_t __s0_204 = __p0_204; \
63699	int16x8_t __s1_210 = __p1_210; \	54087	int16x8_t __s1_204 = __p1_204; \
63700	int8x16_t __ret_210; \	54088	int8x16_t __ret_204; \
63701	__ret_210 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_210), (int8x8_t)(vqshrn_n_s16(__s1_210, __p2_210)))); \	54089	__ret_204 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_204), (int8x8_t)(vqshrn_n_s16(__s1_204, __p2_204)))); \
63702	__ret_210; \	54090	__ret_204; \
63703	})	54091	})
63704	#else	54092	#else
63705	#define vqshrn_high_n_s16(__p0_211, __p1_211, __p2_211) __extension__ ({ \	54093	#define vqshrn_high_n_s16(__p0_205, __p1_205, __p2_205) __extension__ ({ \
63706	int8x8_t __s0_211 = __p0_211; \	54094	int8x8_t __s0_205 = __p0_205; \
63707	int16x8_t __s1_211 = __p1_211; \	54095	int16x8_t __s1_205 = __p1_205; \
63708	int8x8_t __rev0_211; __rev0_211 = __builtin_shufflevector(__s0_211, __s0_211, 7, 6, 5, 4, 3, 2, 1, 0); \	54096	int8x8_t __rev0_205; __rev0_205 = __builtin_shufflevector(__s0_205, __s0_205, 7, 6, 5, 4, 3, 2, 1, 0); \
63709	int16x8_t __rev1_211; __rev1_211 = __builtin_shufflevector(__s1_211, __s1_211, 7, 6, 5, 4, 3, 2, 1, 0); \	54097	int16x8_t __rev1_205; __rev1_205 = __builtin_shufflevector(__s1_205, __s1_205, 7, 6, 5, 4, 3, 2, 1, 0); \
63710	int8x16_t __ret_211; \	54098	int8x16_t __ret_205; \
63711	__ret_211 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_211), (int8x8_t)(__noswap_vqshrn_n_s16(__rev1_211, __p2_211)))); \	54099	__ret_205 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_205), (int8x8_t)(__noswap_vqshrn_n_s16(__rev1_205, __p2_205)))); \
63712	__ret_211 = __builtin_shufflevector(__ret_211, __ret_211, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	54100	__ret_205 = __builtin_shufflevector(__ret_205, __ret_205, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63713	__ret_211; \	54101	__ret_205; \
63714	})	54102	})
63715	#endif	54103	#endif
63716		54104
63717	#ifdef __LITTLE_ENDIAN__
63718	#define vqshrns_n_u32(__p0, __p1) __extension__ ({ \
63719	uint32_t __s0 = __p0; \
63720	uint16_t __ret; \
63721	__ret = (uint16_t) __builtin_neon_vqshrns_n_u32(__s0, __p1); \
63722	__ret; \
63723	})
63724	#else
63725	#define vqshrns_n_u32(__p0, __p1) __extension__ ({ \	54105	#define vqshrns_n_u32(__p0, __p1) __extension__ ({ \
63726	uint32_t __s0 = __p0; \	54106	uint32_t __s0 = __p0; \
63727	uint16_t __ret; \	54107	uint16_t __ret; \
63728	__ret = (uint16_t) __builtin_neon_vqshrns_n_u32(__s0, __p1); \	54108	__ret = (uint16_t) __builtin_neon_vqshrns_n_u32(__s0, __p1); \
63729	__ret; \	54109	__ret; \
63730	})	54110	})
63731	#endif
63732
63733	#ifdef __LITTLE_ENDIAN__
63734	#define vqshrnd_n_u64(__p0, __p1) __extension__ ({ \
63735	uint64_t __s0 = __p0; \
63736	uint32_t __ret; \
63737	__ret = (uint32_t) __builtin_neon_vqshrnd_n_u64(__s0, __p1); \
63738	__ret; \
63739	})
63740	#else
63741	#define vqshrnd_n_u64(__p0, __p1) __extension__ ({ \	54111	#define vqshrnd_n_u64(__p0, __p1) __extension__ ({ \
63742	uint64_t __s0 = __p0; \	54112	uint64_t __s0 = __p0; \
63743	uint32_t __ret; \	54113	uint32_t __ret; \
63744	__ret = (uint32_t) __builtin_neon_vqshrnd_n_u64(__s0, __p1); \	54114	__ret = (uint32_t) __builtin_neon_vqshrnd_n_u64(__s0, __p1); \
63745	__ret; \	54115	__ret; \
63746	})	54116	})
63747	#endif
63748
63749	#ifdef __LITTLE_ENDIAN__
63750	#define vqshrnh_n_u16(__p0, __p1) __extension__ ({ \
63751	uint16_t __s0 = __p0; \
63752	uint8_t __ret; \
63753	__ret = (uint8_t) __builtin_neon_vqshrnh_n_u16(__s0, __p1); \
63754	__ret; \
63755	})
63756	#else
63757	#define vqshrnh_n_u16(__p0, __p1) __extension__ ({ \	54117	#define vqshrnh_n_u16(__p0, __p1) __extension__ ({ \
63758	uint16_t __s0 = __p0; \	54118	uint16_t __s0 = __p0; \
63759	uint8_t __ret; \	54119	uint8_t __ret; \
63760	__ret = (uint8_t) __builtin_neon_vqshrnh_n_u16(__s0, __p1); \	54120	__ret = (uint8_t) __builtin_neon_vqshrnh_n_u16(__s0, __p1); \
63761	__ret; \	54121	__ret; \
63762	})	54122	})
63763	#endif
63764
63765	#ifdef __LITTLE_ENDIAN__
63766	#define vqshrns_n_s32(__p0, __p1) __extension__ ({ \
63767	int32_t __s0 = __p0; \
63768	int16_t __ret; \
63769	__ret = (int16_t) __builtin_neon_vqshrns_n_s32(__s0, __p1); \
63770	__ret; \
63771	})
63772	#else
63773	#define vqshrns_n_s32(__p0, __p1) __extension__ ({ \	54123	#define vqshrns_n_s32(__p0, __p1) __extension__ ({ \
63774	int32_t __s0 = __p0; \	54124	int32_t __s0 = __p0; \
63775	int16_t __ret; \	54125	int16_t __ret; \
63776	__ret = (int16_t) __builtin_neon_vqshrns_n_s32(__s0, __p1); \	54126	__ret = (int16_t) __builtin_neon_vqshrns_n_s32(__s0, __p1); \
63777	__ret; \	54127	__ret; \
63778	})	54128	})
63779	#endif
63780
63781	#ifdef __LITTLE_ENDIAN__
63782	#define vqshrnd_n_s64(__p0, __p1) __extension__ ({ \
63783	int64_t __s0 = __p0; \
63784	int32_t __ret; \
63785	__ret = (int32_t) __builtin_neon_vqshrnd_n_s64(__s0, __p1); \
63786	__ret; \
63787	})
63788	#else
63789	#define vqshrnd_n_s64(__p0, __p1) __extension__ ({ \	54129	#define vqshrnd_n_s64(__p0, __p1) __extension__ ({ \
63790	int64_t __s0 = __p0; \	54130	int64_t __s0 = __p0; \
63791	int32_t __ret; \	54131	int32_t __ret; \
63792	__ret = (int32_t) __builtin_neon_vqshrnd_n_s64(__s0, __p1); \	54132	__ret = (int32_t) __builtin_neon_vqshrnd_n_s64(__s0, __p1); \
63793	__ret; \	54133	__ret; \
63794	})	54134	})
63795	#endif
63796
63797	#ifdef __LITTLE_ENDIAN__
63798	#define vqshrnh_n_s16(__p0, __p1) __extension__ ({ \
63799	int16_t __s0 = __p0; \
63800	int8_t __ret; \
63801	__ret = (int8_t) __builtin_neon_vqshrnh_n_s16(__s0, __p1); \
63802	__ret; \
63803	})
63804	#else
63805	#define vqshrnh_n_s16(__p0, __p1) __extension__ ({ \	54135	#define vqshrnh_n_s16(__p0, __p1) __extension__ ({ \
63806	int16_t __s0 = __p0; \	54136	int16_t __s0 = __p0; \
63807	int8_t __ret; \	54137	int8_t __ret; \
63808	__ret = (int8_t) __builtin_neon_vqshrnh_n_s16(__s0, __p1); \	54138	__ret = (int8_t) __builtin_neon_vqshrnh_n_s16(__s0, __p1); \
63809	__ret; \	54139	__ret; \
63810	})	54140	})
63811	#endif
63812
63813	#ifdef __LITTLE_ENDIAN__	54141	#ifdef __LITTLE_ENDIAN__
63814	#define vqshrun_high_n_s32(__p0_212, __p1_212, __p2_212) __extension__ ({ \	54142	#define vqshrun_high_n_s32(__p0_206, __p1_206, __p2_206) __extension__ ({ \
63815	int16x4_t __s0_212 = __p0_212; \	54143	int16x4_t __s0_206 = __p0_206; \
63816	int32x4_t __s1_212 = __p1_212; \	54144	int32x4_t __s1_206 = __p1_206; \
63817	int16x8_t __ret_212; \	54145	int16x8_t __ret_206; \
63818	__ret_212 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_212), (int16x4_t)(vqshrun_n_s32(__s1_212, __p2_212)))); \	54146	__ret_206 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_206), (int16x4_t)(vqshrun_n_s32(__s1_206, __p2_206)))); \
63819	__ret_212; \	54147	__ret_206; \
63820	})	54148	})
63821	#else	54149	#else
63822	#define vqshrun_high_n_s32(__p0_213, __p1_213, __p2_213) __extension__ ({ \	54150	#define vqshrun_high_n_s32(__p0_207, __p1_207, __p2_207) __extension__ ({ \
63823	int16x4_t __s0_213 = __p0_213; \	54151	int16x4_t __s0_207 = __p0_207; \
63824	int32x4_t __s1_213 = __p1_213; \	54152	int32x4_t __s1_207 = __p1_207; \
63825	int16x4_t __rev0_213; __rev0_213 = __builtin_shufflevector(__s0_213, __s0_213, 3, 2, 1, 0); \	54153	int16x4_t __rev0_207; __rev0_207 = __builtin_shufflevector(__s0_207, __s0_207, 3, 2, 1, 0); \
63826	int32x4_t __rev1_213; __rev1_213 = __builtin_shufflevector(__s1_213, __s1_213, 3, 2, 1, 0); \	54154	int32x4_t __rev1_207; __rev1_207 = __builtin_shufflevector(__s1_207, __s1_207, 3, 2, 1, 0); \
63827	int16x8_t __ret_213; \	54155	int16x8_t __ret_207; \
63828	__ret_213 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_213), (int16x4_t)(__noswap_vqshrun_n_s32(__rev1_213, __p2_213)))); \	54156	__ret_207 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_207), (int16x4_t)(__noswap_vqshrun_n_s32(__rev1_207, __p2_207)))); \
63829	__ret_213 = __builtin_shufflevector(__ret_213, __ret_213, 7, 6, 5, 4, 3, 2, 1, 0); \	54157	__ret_207 = __builtin_shufflevector(__ret_207, __ret_207, 7, 6, 5, 4, 3, 2, 1, 0); \
63830	__ret_213; \	54158	__ret_207; \
63831	})	54159	})
63832	#endif	54160	#endif
63833		54161
63834	#ifdef __LITTLE_ENDIAN__	54162	#ifdef __LITTLE_ENDIAN__
63835	#define vqshrun_high_n_s64(__p0_214, __p1_214, __p2_214) __extension__ ({ \	54163	#define vqshrun_high_n_s64(__p0_208, __p1_208, __p2_208) __extension__ ({ \
63836	int32x2_t __s0_214 = __p0_214; \	54164	int32x2_t __s0_208 = __p0_208; \
63837	int64x2_t __s1_214 = __p1_214; \	54165	int64x2_t __s1_208 = __p1_208; \
63838	int32x4_t __ret_214; \	54166	int32x4_t __ret_208; \
63839	__ret_214 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_214), (int32x2_t)(vqshrun_n_s64(__s1_214, __p2_214)))); \	54167	__ret_208 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_208), (int32x2_t)(vqshrun_n_s64(__s1_208, __p2_208)))); \
63840	__ret_214; \	54168	__ret_208; \
63841	})	54169	})
63842	#else	54170	#else
63843	#define vqshrun_high_n_s64(__p0_215, __p1_215, __p2_215) __extension__ ({ \	54171	#define vqshrun_high_n_s64(__p0_209, __p1_209, __p2_209) __extension__ ({ \
63844	int32x2_t __s0_215 = __p0_215; \	54172	int32x2_t __s0_209 = __p0_209; \
63845	int64x2_t __s1_215 = __p1_215; \	54173	int64x2_t __s1_209 = __p1_209; \
63846	int32x2_t __rev0_215; __rev0_215 = __builtin_shufflevector(__s0_215, __s0_215, 1, 0); \	54174	int32x2_t __rev0_209; __rev0_209 = __builtin_shufflevector(__s0_209, __s0_209, 1, 0); \
63847	int64x2_t __rev1_215; __rev1_215 = __builtin_shufflevector(__s1_215, __s1_215, 1, 0); \	54175	int64x2_t __rev1_209; __rev1_209 = __builtin_shufflevector(__s1_209, __s1_209, 1, 0); \
63848	int32x4_t __ret_215; \	54176	int32x4_t __ret_209; \
63849	__ret_215 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_215), (int32x2_t)(__noswap_vqshrun_n_s64(__rev1_215, __p2_215)))); \	54177	__ret_209 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_209), (int32x2_t)(__noswap_vqshrun_n_s64(__rev1_209, __p2_209)))); \
63850	__ret_215 = __builtin_shufflevector(__ret_215, __ret_215, 3, 2, 1, 0); \	54178	__ret_209 = __builtin_shufflevector(__ret_209, __ret_209, 3, 2, 1, 0); \
63851	__ret_215; \	54179	__ret_209; \
63852	})	54180	})
63853	#endif	54181	#endif
63854		54182
63855	#ifdef __LITTLE_ENDIAN__	54183	#ifdef __LITTLE_ENDIAN__
63856	#define vqshrun_high_n_s16(__p0_216, __p1_216, __p2_216) __extension__ ({ \	54184	#define vqshrun_high_n_s16(__p0_210, __p1_210, __p2_210) __extension__ ({ \
63857	int8x8_t __s0_216 = __p0_216; \	54185	int8x8_t __s0_210 = __p0_210; \
63858	int16x8_t __s1_216 = __p1_216; \	54186	int16x8_t __s1_210 = __p1_210; \
63859	int8x16_t __ret_216; \	54187	int8x16_t __ret_210; \
63860	__ret_216 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_216), (int8x8_t)(vqshrun_n_s16(__s1_216, __p2_216)))); \	54188	__ret_210 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_210), (int8x8_t)(vqshrun_n_s16(__s1_210, __p2_210)))); \
63861	__ret_216; \	54189	__ret_210; \
63862	})	54190	})
63863	#else	54191	#else
63864	#define vqshrun_high_n_s16(__p0_217, __p1_217, __p2_217) __extension__ ({ \	54192	#define vqshrun_high_n_s16(__p0_211, __p1_211, __p2_211) __extension__ ({ \
63865	int8x8_t __s0_217 = __p0_217; \	54193	int8x8_t __s0_211 = __p0_211; \
63866	int16x8_t __s1_217 = __p1_217; \	54194	int16x8_t __s1_211 = __p1_211; \
63867	int8x8_t __rev0_217; __rev0_217 = __builtin_shufflevector(__s0_217, __s0_217, 7, 6, 5, 4, 3, 2, 1, 0); \	54195	int8x8_t __rev0_211; __rev0_211 = __builtin_shufflevector(__s0_211, __s0_211, 7, 6, 5, 4, 3, 2, 1, 0); \
63868	int16x8_t __rev1_217; __rev1_217 = __builtin_shufflevector(__s1_217, __s1_217, 7, 6, 5, 4, 3, 2, 1, 0); \	54196	int16x8_t __rev1_211; __rev1_211 = __builtin_shufflevector(__s1_211, __s1_211, 7, 6, 5, 4, 3, 2, 1, 0); \
63869	int8x16_t __ret_217; \	54197	int8x16_t __ret_211; \
63870	__ret_217 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_217), (int8x8_t)(__noswap_vqshrun_n_s16(__rev1_217, __p2_217)))); \	54198	__ret_211 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_211), (int8x8_t)(__noswap_vqshrun_n_s16(__rev1_211, __p2_211)))); \
63871	__ret_217 = __builtin_shufflevector(__ret_217, __ret_217, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	54199	__ret_211 = __builtin_shufflevector(__ret_211, __ret_211, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
63872	__ret_217; \	54200	__ret_211; \
63873	})	54201	})
63874	#endif	54202	#endif
63875		54203
63876	#ifdef __LITTLE_ENDIAN__
63877	#define vqshruns_n_s32(__p0, __p1) __extension__ ({ \
63878	int32_t __s0 = __p0; \
63879	int16_t __ret; \
63880	__ret = (int16_t) __builtin_neon_vqshruns_n_s32(__s0, __p1); \
63881	__ret; \
63882	})
63883	#else
63884	#define vqshruns_n_s32(__p0, __p1) __extension__ ({ \	54204	#define vqshruns_n_s32(__p0, __p1) __extension__ ({ \
63885	int32_t __s0 = __p0; \	54205	int32_t __s0 = __p0; \
63886	int16_t __ret; \	54206	int16_t __ret; \
63887	__ret = (int16_t) __builtin_neon_vqshruns_n_s32(__s0, __p1); \	54207	__ret = (int16_t) __builtin_neon_vqshruns_n_s32(__s0, __p1); \
63888	__ret; \	54208	__ret; \
63889	})	54209	})
63890	#endif
63891
63892	#ifdef __LITTLE_ENDIAN__
63893	#define vqshrund_n_s64(__p0, __p1) __extension__ ({ \
63894	int64_t __s0 = __p0; \
63895	int32_t __ret; \
63896	__ret = (int32_t) __builtin_neon_vqshrund_n_s64(__s0, __p1); \
63897	__ret; \
63898	})
63899	#else
63900	#define vqshrund_n_s64(__p0, __p1) __extension__ ({ \	54210	#define vqshrund_n_s64(__p0, __p1) __extension__ ({ \
63901	int64_t __s0 = __p0; \	54211	int64_t __s0 = __p0; \
63902	int32_t __ret; \	54212	int32_t __ret; \
63903	__ret = (int32_t) __builtin_neon_vqshrund_n_s64(__s0, __p1); \	54213	__ret = (int32_t) __builtin_neon_vqshrund_n_s64(__s0, __p1); \
63904	__ret; \	54214	__ret; \
63905	})	54215	})
63906	#endif
63907
63908	#ifdef __LITTLE_ENDIAN__
63909	#define vqshrunh_n_s16(__p0, __p1) __extension__ ({ \
63910	int16_t __s0 = __p0; \
63911	int8_t __ret; \
63912	__ret = (int8_t) __builtin_neon_vqshrunh_n_s16(__s0, __p1); \
63913	__ret; \
63914	})
63915	#else
63916	#define vqshrunh_n_s16(__p0, __p1) __extension__ ({ \	54216	#define vqshrunh_n_s16(__p0, __p1) __extension__ ({ \
63917	int16_t __s0 = __p0; \	54217	int16_t __s0 = __p0; \
63918	int8_t __ret; \	54218	int8_t __ret; \
63919	__ret = (int8_t) __builtin_neon_vqshrunh_n_s16(__s0, __p1); \	54219	__ret = (int8_t) __builtin_neon_vqshrunh_n_s16(__s0, __p1); \
63920	__ret; \	54220	__ret; \
63921	})	54221	})
63922	#endif
63923
63924	#ifdef __LITTLE_ENDIAN__
63925	__ai uint8_t vqsubb_u8(uint8_t __p0, uint8_t __p1) {
63926	uint8_t __ret;
63927	__ret = (uint8_t) __builtin_neon_vqsubb_u8(__p0, __p1);
63928	return __ret;
63929	}
63930	#else
63931	__ai uint8_t vqsubb_u8(uint8_t __p0, uint8_t __p1) {	54222	__ai uint8_t vqsubb_u8(uint8_t __p0, uint8_t __p1) {
63932	uint8_t __ret;	54223	uint8_t __ret;
63933	__ret = (uint8_t) __builtin_neon_vqsubb_u8(__p0, __p1);	54224	__ret = (uint8_t) __builtin_neon_vqsubb_u8(__p0, __p1);
63934	return __ret;	54225	return __ret;
63935	}	54226	}
63936	#endif
63937
63938	#ifdef __LITTLE_ENDIAN__
63939	__ai uint32_t vqsubs_u32(uint32_t __p0, uint32_t __p1) {
63940	uint32_t __ret;
63941	__ret = (uint32_t) __builtin_neon_vqsubs_u32(__p0, __p1);
63942	return __ret;
63943	}
63944	#else
63945	__ai uint32_t vqsubs_u32(uint32_t __p0, uint32_t __p1) {	54227	__ai uint32_t vqsubs_u32(uint32_t __p0, uint32_t __p1) {
63946	uint32_t __ret;	54228	uint32_t __ret;
63947	__ret = (uint32_t) __builtin_neon_vqsubs_u32(__p0, __p1);	54229	__ret = (uint32_t) __builtin_neon_vqsubs_u32(__p0, __p1);
63948	return __ret;	54230	return __ret;
63949	}	54231	}
63950	#endif
63951
63952	#ifdef __LITTLE_ENDIAN__
63953	__ai uint64_t vqsubd_u64(uint64_t __p0, uint64_t __p1) {
63954	uint64_t __ret;
63955	__ret = (uint64_t) __builtin_neon_vqsubd_u64(__p0, __p1);
63956	return __ret;
63957	}
63958	#else
63959	__ai uint64_t vqsubd_u64(uint64_t __p0, uint64_t __p1) {	54232	__ai uint64_t vqsubd_u64(uint64_t __p0, uint64_t __p1) {
63960	uint64_t __ret;	54233	uint64_t __ret;
63961	__ret = (uint64_t) __builtin_neon_vqsubd_u64(__p0, __p1);	54234	__ret = (uint64_t) __builtin_neon_vqsubd_u64(__p0, __p1);
63962	return __ret;	54235	return __ret;
63963	}	54236	}
63964	#endif
63965
63966	#ifdef __LITTLE_ENDIAN__
63967	__ai uint16_t vqsubh_u16(uint16_t __p0, uint16_t __p1) {
63968	uint16_t __ret;
63969	__ret = (uint16_t) __builtin_neon_vqsubh_u16(__p0, __p1);
63970	return __ret;
63971	}
63972	#else
63973	__ai uint16_t vqsubh_u16(uint16_t __p0, uint16_t __p1) {	54237	__ai uint16_t vqsubh_u16(uint16_t __p0, uint16_t __p1) {
63974	uint16_t __ret;	54238	uint16_t __ret;
63975	__ret = (uint16_t) __builtin_neon_vqsubh_u16(__p0, __p1);	54239	__ret = (uint16_t) __builtin_neon_vqsubh_u16(__p0, __p1);
63976	return __ret;	54240	return __ret;
63977	}	54241	}
63978	#endif
63979
63980	#ifdef __LITTLE_ENDIAN__
63981	__ai int8_t vqsubb_s8(int8_t __p0, int8_t __p1) {
63982	int8_t __ret;
63983	__ret = (int8_t) __builtin_neon_vqsubb_s8(__p0, __p1);
63984	return __ret;
63985	}
63986	#else
63987	__ai int8_t vqsubb_s8(int8_t __p0, int8_t __p1) {	54242	__ai int8_t vqsubb_s8(int8_t __p0, int8_t __p1) {
63988	int8_t __ret;	54243	int8_t __ret;
63989	__ret = (int8_t) __builtin_neon_vqsubb_s8(__p0, __p1);	54244	__ret = (int8_t) __builtin_neon_vqsubb_s8(__p0, __p1);
63990	return __ret;	54245	return __ret;
63991	}	54246	}
63992	#endif
63993
63994	#ifdef __LITTLE_ENDIAN__
63995	__ai int32_t vqsubs_s32(int32_t __p0, int32_t __p1) {
63996	int32_t __ret;
63997	__ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
63998	return __ret;
63999	}
64000	#else
64001	__ai int32_t vqsubs_s32(int32_t __p0, int32_t __p1) {	54247	__ai int32_t vqsubs_s32(int32_t __p0, int32_t __p1) {
64002	int32_t __ret;	54248	int32_t __ret;
64003	__ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);	54249	__ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
64004	return __ret;	54250	return __ret;
64005	}	54251	}
64006	__ai int32_t __noswap_vqsubs_s32(int32_t __p0, int32_t __p1) {
64007	int32_t __ret;
64008	__ret = (int32_t) __builtin_neon_vqsubs_s32(__p0, __p1);
64009	return __ret;
64010	}
64011	#endif
64012
64013	#ifdef __LITTLE_ENDIAN__
64014	__ai int64_t vqsubd_s64(int64_t __p0, int64_t __p1) {
64015	int64_t __ret;
64016	__ret = (int64_t) __builtin_neon_vqsubd_s64(__p0, __p1);
64017	return __ret;
64018	}
64019	#else
64020	__ai int64_t vqsubd_s64(int64_t __p0, int64_t __p1) {	54252	__ai int64_t vqsubd_s64(int64_t __p0, int64_t __p1) {
64021	int64_t __ret;	54253	int64_t __ret;
64022	__ret = (int64_t) __builtin_neon_vqsubd_s64(__p0, __p1);	54254	__ret = (int64_t) __builtin_neon_vqsubd_s64(__p0, __p1);
64023	return __ret;	54255	return __ret;
64024	}	54256	}
64025	#endif
64026
64027	#ifdef __LITTLE_ENDIAN__
64028	__ai int16_t vqsubh_s16(int16_t __p0, int16_t __p1) {
64029	int16_t __ret;
64030	__ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
64031	return __ret;
64032	}
64033	#else
64034	__ai int16_t vqsubh_s16(int16_t __p0, int16_t __p1) {	54257	__ai int16_t vqsubh_s16(int16_t __p0, int16_t __p1) {
64035	int16_t __ret;	54258	int16_t __ret;
64036	__ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);	54259	__ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
64037	return __ret;	54260	return __ret;
64038	}	54261	}
64039	__ai int16_t __noswap_vqsubh_s16(int16_t __p0, int16_t __p1) {
64040	int16_t __ret;
64041	__ret = (int16_t) __builtin_neon_vqsubh_s16(__p0, __p1);
64042	return __ret;
64043	}
64044	#endif
64045
64046	#ifdef __LITTLE_ENDIAN__	54262	#ifdef __LITTLE_ENDIAN__
64047	__ai poly8x8_t vqtbl1_p8(poly8x16_t __p0, uint8x8_t __p1) {	54263	__ai poly8x8_t vqtbl1_p8(poly8x16_t __p0, uint8x8_t __p1) {
64048	poly8x8_t __ret;	54264	poly8x8_t __ret;
...	@@ -65211,48 +55427,21 @@ __ai float64x2_t vrecpeq_f64(float64x2_t __p0) {	...	@@ -65211,48 +55427,21 @@ __ai float64x2_t vrecpeq_f64(float64x2_t __p0) {
65211	}	55427	}
65212	#endif	55428	#endif
65213		55429
65214	#ifdef __LITTLE_ENDIAN__
65215	__ai float64x1_t vrecpe_f64(float64x1_t __p0) {
65216	float64x1_t __ret;
65217	__ret = (float64x1_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 10);
65218	return __ret;
65219	}
65220	#else
65221	__ai float64x1_t vrecpe_f64(float64x1_t __p0) {	55430	__ai float64x1_t vrecpe_f64(float64x1_t __p0) {
65222	float64x1_t __ret;	55431	float64x1_t __ret;
65223	__ret = (float64x1_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 10);	55432	__ret = (float64x1_t) __builtin_neon_vrecpe_v((int8x8_t)__p0, 10);
65224	return __ret;	55433	return __ret;
65225	}	55434	}
65226	#endif
65227
65228	#ifdef __LITTLE_ENDIAN__
65229	__ai float64_t vrecped_f64(float64_t __p0) {	55435	__ai float64_t vrecped_f64(float64_t __p0) {
65230	float64_t __ret;	55436	float64_t __ret;
65231	__ret = (float64_t) __builtin_neon_vrecped_f64(__p0);	55437	__ret = (float64_t) __builtin_neon_vrecped_f64(__p0);
65232	return __ret;	55438	return __ret;
65233	}	55439	}
65234	#else
65235	__ai float64_t vrecped_f64(float64_t __p0) {
65236	float64_t __ret;
65237	__ret = (float64_t) __builtin_neon_vrecped_f64(__p0);
65238	return __ret;
65239	}
65240	#endif
65241
65242	#ifdef __LITTLE_ENDIAN__
65243	__ai float32_t vrecpes_f32(float32_t __p0) {
65244	float32_t __ret;
65245	__ret = (float32_t) __builtin_neon_vrecpes_f32(__p0);
65246	return __ret;
65247	}
65248	#else
65249	__ai float32_t vrecpes_f32(float32_t __p0) {	55440	__ai float32_t vrecpes_f32(float32_t __p0) {
65250	float32_t __ret;	55441	float32_t __ret;
65251	__ret = (float32_t) __builtin_neon_vrecpes_f32(__p0);	55442	__ret = (float32_t) __builtin_neon_vrecpes_f32(__p0);
65252	return __ret;	55443	return __ret;
65253	}	55444	}
65254	#endif
65255
65256	#ifdef __LITTLE_ENDIAN__	55445	#ifdef __LITTLE_ENDIAN__
65257	__ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {	55446	__ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {
65258	float64x2_t __ret;	55447	float64x2_t __ret;
...	@@ -65270,259 +55459,176 @@ __ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -65270,259 +55459,176 @@ __ai float64x2_t vrecpsq_f64(float64x2_t __p0, float64x2_t __p1) {
65270	}	55459	}
65271	#endif	55460	#endif
65272		55461
65273	#ifdef __LITTLE_ENDIAN__
65274	__ai float64x1_t vrecps_f64(float64x1_t __p0, float64x1_t __p1) {	55462	__ai float64x1_t vrecps_f64(float64x1_t __p0, float64x1_t __p1) {
65275	float64x1_t __ret;	55463	float64x1_t __ret;
65276	__ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	55464	__ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
65277	return __ret;	55465	return __ret;
65278	}	55466	}
65279	#else
65280	__ai float64x1_t vrecps_f64(float64x1_t __p0, float64x1_t __p1) {
65281	float64x1_t __ret;
65282	__ret = (float64x1_t) __builtin_neon_vrecps_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
65283	return __ret;
65284	}
65285	#endif
65286
65287	#ifdef __LITTLE_ENDIAN__
65288	__ai float64_t vrecpsd_f64(float64_t __p0, float64_t __p1) {
65289	float64_t __ret;
65290	__ret = (float64_t) __builtin_neon_vrecpsd_f64(__p0, __p1);
65291	return __ret;
65292	}
65293	#else
65294	__ai float64_t vrecpsd_f64(float64_t __p0, float64_t __p1) {	55467	__ai float64_t vrecpsd_f64(float64_t __p0, float64_t __p1) {
65295	float64_t __ret;	55468	float64_t __ret;
65296	__ret = (float64_t) __builtin_neon_vrecpsd_f64(__p0, __p1);	55469	__ret = (float64_t) __builtin_neon_vrecpsd_f64(__p0, __p1);
65297	return __ret;	55470	return __ret;
65298	}	55471	}
65299	#endif
65300
65301	#ifdef __LITTLE_ENDIAN__
65302	__ai float32_t vrecpss_f32(float32_t __p0, float32_t __p1) {
65303	float32_t __ret;
65304	__ret = (float32_t) __builtin_neon_vrecpss_f32(__p0, __p1);
65305	return __ret;
65306	}
65307	#else
65308	__ai float32_t vrecpss_f32(float32_t __p0, float32_t __p1) {	55472	__ai float32_t vrecpss_f32(float32_t __p0, float32_t __p1) {
65309	float32_t __ret;	55473	float32_t __ret;
65310	__ret = (float32_t) __builtin_neon_vrecpss_f32(__p0, __p1);	55474	__ret = (float32_t) __builtin_neon_vrecpss_f32(__p0, __p1);
65311	return __ret;	55475	return __ret;
65312	}	55476	}
65313	#endif
65314
65315	#ifdef __LITTLE_ENDIAN__
65316	__ai float64_t vrecpxd_f64(float64_t __p0) {	55477	__ai float64_t vrecpxd_f64(float64_t __p0) {
65317	float64_t __ret;	55478	float64_t __ret;
65318	__ret = (float64_t) __builtin_neon_vrecpxd_f64(__p0);	55479	__ret = (float64_t) __builtin_neon_vrecpxd_f64(__p0);
65319	return __ret;	55480	return __ret;
65320	}	55481	}
65321	#else
65322	__ai float64_t vrecpxd_f64(float64_t __p0) {
65323	float64_t __ret;
65324	__ret = (float64_t) __builtin_neon_vrecpxd_f64(__p0);
65325	return __ret;
65326	}
65327	#endif
65328
65329	#ifdef __LITTLE_ENDIAN__
65330	__ai float32_t vrecpxs_f32(float32_t __p0) {	55482	__ai float32_t vrecpxs_f32(float32_t __p0) {
65331	float32_t __ret;	55483	float32_t __ret;
65332	__ret = (float32_t) __builtin_neon_vrecpxs_f32(__p0);	55484	__ret = (float32_t) __builtin_neon_vrecpxs_f32(__p0);
65333	return __ret;	55485	return __ret;
65334	}	55486	}
65335	#else
65336	__ai float32_t vrecpxs_f32(float32_t __p0) {
65337	float32_t __ret;
65338	__ret = (float32_t) __builtin_neon_vrecpxs_f32(__p0);
65339	return __ret;
65340	}
65341	#endif
65342
65343	#ifdef __LITTLE_ENDIAN__
65344	__ai uint64_t vrshld_u64(uint64_t __p0, uint64_t __p1) {
65345	uint64_t __ret;
65346	__ret = (uint64_t) __builtin_neon_vrshld_u64(__p0, __p1);
65347	return __ret;
65348	}
65349	#else
65350	__ai uint64_t vrshld_u64(uint64_t __p0, uint64_t __p1) {	55487	__ai uint64_t vrshld_u64(uint64_t __p0, uint64_t __p1) {
65351	uint64_t __ret;	55488	uint64_t __ret;
65352	__ret = (uint64_t) __builtin_neon_vrshld_u64(__p0, __p1);	55489	__ret = (uint64_t) __builtin_neon_vrshld_u64(__p0, __p1);
65353	return __ret;	55490	return __ret;
65354	}	55491	}
65355	#endif
65356
65357	#ifdef __LITTLE_ENDIAN__
65358	__ai int64_t vrshld_s64(int64_t __p0, int64_t __p1) {
65359	int64_t __ret;
65360	__ret = (int64_t) __builtin_neon_vrshld_s64(__p0, __p1);
65361	return __ret;
65362	}
65363	#else
65364	__ai int64_t vrshld_s64(int64_t __p0, int64_t __p1) {	55492	__ai int64_t vrshld_s64(int64_t __p0, int64_t __p1) {
65365	int64_t __ret;	55493	int64_t __ret;
65366	__ret = (int64_t) __builtin_neon_vrshld_s64(__p0, __p1);	55494	__ret = (int64_t) __builtin_neon_vrshld_s64(__p0, __p1);
65367	return __ret;	55495	return __ret;
65368	}	55496	}
65369	#endif
65370
65371	#ifdef __LITTLE_ENDIAN__
65372	#define vrshrd_n_u64(__p0, __p1) __extension__ ({ \
65373	uint64_t __s0 = __p0; \
65374	uint64_t __ret; \
65375	__ret = (uint64_t) __builtin_neon_vrshrd_n_u64(__s0, __p1); \
65376	__ret; \
65377	})
65378	#else
65379	#define vrshrd_n_u64(__p0, __p1) __extension__ ({ \	55497	#define vrshrd_n_u64(__p0, __p1) __extension__ ({ \
65380	uint64_t __s0 = __p0; \	55498	uint64_t __s0 = __p0; \
65381	uint64_t __ret; \	55499	uint64_t __ret; \
65382	__ret = (uint64_t) __builtin_neon_vrshrd_n_u64(__s0, __p1); \	55500	__ret = (uint64_t) __builtin_neon_vrshrd_n_u64(__s0, __p1); \
65383	__ret; \	55501	__ret; \
65384	})	55502	})
65385	#endif
65386
65387	#ifdef __LITTLE_ENDIAN__
65388	#define vrshrd_n_s64(__p0, __p1) __extension__ ({ \
65389	int64_t __s0 = __p0; \
65390	int64_t __ret; \
65391	__ret = (int64_t) __builtin_neon_vrshrd_n_s64(__s0, __p1); \
65392	__ret; \
65393	})
65394	#else
65395	#define vrshrd_n_s64(__p0, __p1) __extension__ ({ \	55503	#define vrshrd_n_s64(__p0, __p1) __extension__ ({ \
65396	int64_t __s0 = __p0; \	55504	int64_t __s0 = __p0; \
65397	int64_t __ret; \	55505	int64_t __ret; \
65398	__ret = (int64_t) __builtin_neon_vrshrd_n_s64(__s0, __p1); \	55506	__ret = (int64_t) __builtin_neon_vrshrd_n_s64(__s0, __p1); \
65399	__ret; \	55507	__ret; \
65400	})	55508	})
65401	#endif
65402
65403	#ifdef __LITTLE_ENDIAN__	55509	#ifdef __LITTLE_ENDIAN__
65404	#define vrshrn_high_n_u32(__p0_218, __p1_218, __p2_218) __extension__ ({ \	55510	#define vrshrn_high_n_u32(__p0_212, __p1_212, __p2_212) __extension__ ({ \
65405	uint16x4_t __s0_218 = __p0_218; \	55511	uint16x4_t __s0_212 = __p0_212; \
65406	uint32x4_t __s1_218 = __p1_218; \	55512	uint32x4_t __s1_212 = __p1_212; \
65407	uint16x8_t __ret_218; \	55513	uint16x8_t __ret_212; \
65408	__ret_218 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_218), (uint16x4_t)(vrshrn_n_u32(__s1_218, __p2_218)))); \	55514	__ret_212 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_212), (uint16x4_t)(vrshrn_n_u32(__s1_212, __p2_212)))); \
65409	__ret_218; \	55515	__ret_212; \
65410	})	55516	})
65411	#else	55517	#else
65412	#define vrshrn_high_n_u32(__p0_219, __p1_219, __p2_219) __extension__ ({ \	55518	#define vrshrn_high_n_u32(__p0_213, __p1_213, __p2_213) __extension__ ({ \
65413	uint16x4_t __s0_219 = __p0_219; \	55519	uint16x4_t __s0_213 = __p0_213; \
65414	uint32x4_t __s1_219 = __p1_219; \	55520	uint32x4_t __s1_213 = __p1_213; \
65415	uint16x4_t __rev0_219; __rev0_219 = __builtin_shufflevector(__s0_219, __s0_219, 3, 2, 1, 0); \	55521	uint16x4_t __rev0_213; __rev0_213 = __builtin_shufflevector(__s0_213, __s0_213, 3, 2, 1, 0); \
65416	uint32x4_t __rev1_219; __rev1_219 = __builtin_shufflevector(__s1_219, __s1_219, 3, 2, 1, 0); \	55522	uint32x4_t __rev1_213; __rev1_213 = __builtin_shufflevector(__s1_213, __s1_213, 3, 2, 1, 0); \
65417	uint16x8_t __ret_219; \	55523	uint16x8_t __ret_213; \
65418	__ret_219 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_219), (uint16x4_t)(__noswap_vrshrn_n_u32(__rev1_219, __p2_219)))); \	55524	__ret_213 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_213), (uint16x4_t)(__noswap_vrshrn_n_u32(__rev1_213, __p2_213)))); \
65419	__ret_219 = __builtin_shufflevector(__ret_219, __ret_219, 7, 6, 5, 4, 3, 2, 1, 0); \	55525	__ret_213 = __builtin_shufflevector(__ret_213, __ret_213, 7, 6, 5, 4, 3, 2, 1, 0); \
65420	__ret_219; \	55526	__ret_213; \
65421	})	55527	})
65422	#endif	55528	#endif
65423		55529
65424	#ifdef __LITTLE_ENDIAN__	55530	#ifdef __LITTLE_ENDIAN__
65425	#define vrshrn_high_n_u64(__p0_220, __p1_220, __p2_220) __extension__ ({ \	55531	#define vrshrn_high_n_u64(__p0_214, __p1_214, __p2_214) __extension__ ({ \
65426	uint32x2_t __s0_220 = __p0_220; \	55532	uint32x2_t __s0_214 = __p0_214; \
65427	uint64x2_t __s1_220 = __p1_220; \	55533	uint64x2_t __s1_214 = __p1_214; \
65428	uint32x4_t __ret_220; \	55534	uint32x4_t __ret_214; \
65429	__ret_220 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_220), (uint32x2_t)(vrshrn_n_u64(__s1_220, __p2_220)))); \	55535	__ret_214 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_214), (uint32x2_t)(vrshrn_n_u64(__s1_214, __p2_214)))); \
65430	__ret_220; \	55536	__ret_214; \
65431	})	55537	})
65432	#else	55538	#else
65433	#define vrshrn_high_n_u64(__p0_221, __p1_221, __p2_221) __extension__ ({ \	55539	#define vrshrn_high_n_u64(__p0_215, __p1_215, __p2_215) __extension__ ({ \
65434	uint32x2_t __s0_221 = __p0_221; \	55540	uint32x2_t __s0_215 = __p0_215; \
65435	uint64x2_t __s1_221 = __p1_221; \	55541	uint64x2_t __s1_215 = __p1_215; \
65436	uint32x2_t __rev0_221; __rev0_221 = __builtin_shufflevector(__s0_221, __s0_221, 1, 0); \	55542	uint32x2_t __rev0_215; __rev0_215 = __builtin_shufflevector(__s0_215, __s0_215, 1, 0); \
65437	uint64x2_t __rev1_221; __rev1_221 = __builtin_shufflevector(__s1_221, __s1_221, 1, 0); \	55543	uint64x2_t __rev1_215; __rev1_215 = __builtin_shufflevector(__s1_215, __s1_215, 1, 0); \
65438	uint32x4_t __ret_221; \	55544	uint32x4_t __ret_215; \
65439	__ret_221 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_221), (uint32x2_t)(__noswap_vrshrn_n_u64(__rev1_221, __p2_221)))); \	55545	__ret_215 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_215), (uint32x2_t)(__noswap_vrshrn_n_u64(__rev1_215, __p2_215)))); \
65440	__ret_221 = __builtin_shufflevector(__ret_221, __ret_221, 3, 2, 1, 0); \	55546	__ret_215 = __builtin_shufflevector(__ret_215, __ret_215, 3, 2, 1, 0); \
65441	__ret_221; \	55547	__ret_215; \
65442	})	55548	})
65443	#endif	55549	#endif
65444		55550
65445	#ifdef __LITTLE_ENDIAN__	55551	#ifdef __LITTLE_ENDIAN__
65446	#define vrshrn_high_n_u16(__p0_222, __p1_222, __p2_222) __extension__ ({ \	55552	#define vrshrn_high_n_u16(__p0_216, __p1_216, __p2_216) __extension__ ({ \
65447	uint8x8_t __s0_222 = __p0_222; \	55553	uint8x8_t __s0_216 = __p0_216; \
65448	uint16x8_t __s1_222 = __p1_222; \	55554	uint16x8_t __s1_216 = __p1_216; \
65449	uint8x16_t __ret_222; \	55555	uint8x16_t __ret_216; \
65450	__ret_222 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_222), (uint8x8_t)(vrshrn_n_u16(__s1_222, __p2_222)))); \	55556	__ret_216 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_216), (uint8x8_t)(vrshrn_n_u16(__s1_216, __p2_216)))); \
65451	__ret_222; \	55557	__ret_216; \
65452	})	55558	})
65453	#else	55559	#else
65454	#define vrshrn_high_n_u16(__p0_223, __p1_223, __p2_223) __extension__ ({ \	55560	#define vrshrn_high_n_u16(__p0_217, __p1_217, __p2_217) __extension__ ({ \
65455	uint8x8_t __s0_223 = __p0_223; \	55561	uint8x8_t __s0_217 = __p0_217; \
65456	uint16x8_t __s1_223 = __p1_223; \	55562	uint16x8_t __s1_217 = __p1_217; \
65457	uint8x8_t __rev0_223; __rev0_223 = __builtin_shufflevector(__s0_223, __s0_223, 7, 6, 5, 4, 3, 2, 1, 0); \	55563	uint8x8_t __rev0_217; __rev0_217 = __builtin_shufflevector(__s0_217, __s0_217, 7, 6, 5, 4, 3, 2, 1, 0); \
65458	uint16x8_t __rev1_223; __rev1_223 = __builtin_shufflevector(__s1_223, __s1_223, 7, 6, 5, 4, 3, 2, 1, 0); \	55564	uint16x8_t __rev1_217; __rev1_217 = __builtin_shufflevector(__s1_217, __s1_217, 7, 6, 5, 4, 3, 2, 1, 0); \
65459	uint8x16_t __ret_223; \	55565	uint8x16_t __ret_217; \
65460	__ret_223 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_223), (uint8x8_t)(__noswap_vrshrn_n_u16(__rev1_223, __p2_223)))); \	55566	__ret_217 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_217), (uint8x8_t)(__noswap_vrshrn_n_u16(__rev1_217, __p2_217)))); \
65461	__ret_223 = __builtin_shufflevector(__ret_223, __ret_223, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	55567	__ret_217 = __builtin_shufflevector(__ret_217, __ret_217, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
65462	__ret_223; \	55568	__ret_217; \
65463	})	55569	})
65464	#endif	55570	#endif
65465		55571
65466	#ifdef __LITTLE_ENDIAN__	55572	#ifdef __LITTLE_ENDIAN__
65467	#define vrshrn_high_n_s32(__p0_224, __p1_224, __p2_224) __extension__ ({ \	55573	#define vrshrn_high_n_s32(__p0_218, __p1_218, __p2_218) __extension__ ({ \
65468	int16x4_t __s0_224 = __p0_224; \	55574	int16x4_t __s0_218 = __p0_218; \
65469	int32x4_t __s1_224 = __p1_224; \	55575	int32x4_t __s1_218 = __p1_218; \
65470	int16x8_t __ret_224; \	55576	int16x8_t __ret_218; \
65471	__ret_224 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_224), (int16x4_t)(vrshrn_n_s32(__s1_224, __p2_224)))); \	55577	__ret_218 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_218), (int16x4_t)(vrshrn_n_s32(__s1_218, __p2_218)))); \
65472	__ret_224; \	55578	__ret_218; \
65473	})	55579	})
65474	#else	55580	#else
65475	#define vrshrn_high_n_s32(__p0_225, __p1_225, __p2_225) __extension__ ({ \	55581	#define vrshrn_high_n_s32(__p0_219, __p1_219, __p2_219) __extension__ ({ \
65476	int16x4_t __s0_225 = __p0_225; \	55582	int16x4_t __s0_219 = __p0_219; \
65477	int32x4_t __s1_225 = __p1_225; \	55583	int32x4_t __s1_219 = __p1_219; \
65478	int16x4_t __rev0_225; __rev0_225 = __builtin_shufflevector(__s0_225, __s0_225, 3, 2, 1, 0); \	55584	int16x4_t __rev0_219; __rev0_219 = __builtin_shufflevector(__s0_219, __s0_219, 3, 2, 1, 0); \
65479	int32x4_t __rev1_225; __rev1_225 = __builtin_shufflevector(__s1_225, __s1_225, 3, 2, 1, 0); \	55585	int32x4_t __rev1_219; __rev1_219 = __builtin_shufflevector(__s1_219, __s1_219, 3, 2, 1, 0); \
65480	int16x8_t __ret_225; \	55586	int16x8_t __ret_219; \
65481	__ret_225 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_225), (int16x4_t)(__noswap_vrshrn_n_s32(__rev1_225, __p2_225)))); \	55587	__ret_219 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_219), (int16x4_t)(__noswap_vrshrn_n_s32(__rev1_219, __p2_219)))); \
65482	__ret_225 = __builtin_shufflevector(__ret_225, __ret_225, 7, 6, 5, 4, 3, 2, 1, 0); \	55588	__ret_219 = __builtin_shufflevector(__ret_219, __ret_219, 7, 6, 5, 4, 3, 2, 1, 0); \
65483	__ret_225; \	55589	__ret_219; \
65484	})	55590	})
65485	#endif	55591	#endif
65486		55592
65487	#ifdef __LITTLE_ENDIAN__	55593	#ifdef __LITTLE_ENDIAN__
65488	#define vrshrn_high_n_s64(__p0_226, __p1_226, __p2_226) __extension__ ({ \	55594	#define vrshrn_high_n_s64(__p0_220, __p1_220, __p2_220) __extension__ ({ \
65489	int32x2_t __s0_226 = __p0_226; \	55595	int32x2_t __s0_220 = __p0_220; \
65490	int64x2_t __s1_226 = __p1_226; \	55596	int64x2_t __s1_220 = __p1_220; \
65491	int32x4_t __ret_226; \	55597	int32x4_t __ret_220; \
65492	__ret_226 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_226), (int32x2_t)(vrshrn_n_s64(__s1_226, __p2_226)))); \	55598	__ret_220 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_220), (int32x2_t)(vrshrn_n_s64(__s1_220, __p2_220)))); \
65493	__ret_226; \	55599	__ret_220; \
65494	})	55600	})
65495	#else	55601	#else
65496	#define vrshrn_high_n_s64(__p0_227, __p1_227, __p2_227) __extension__ ({ \	55602	#define vrshrn_high_n_s64(__p0_221, __p1_221, __p2_221) __extension__ ({ \
65497	int32x2_t __s0_227 = __p0_227; \	55603	int32x2_t __s0_221 = __p0_221; \
65498	int64x2_t __s1_227 = __p1_227; \	55604	int64x2_t __s1_221 = __p1_221; \
65499	int32x2_t __rev0_227; __rev0_227 = __builtin_shufflevector(__s0_227, __s0_227, 1, 0); \	55605	int32x2_t __rev0_221; __rev0_221 = __builtin_shufflevector(__s0_221, __s0_221, 1, 0); \
65500	int64x2_t __rev1_227; __rev1_227 = __builtin_shufflevector(__s1_227, __s1_227, 1, 0); \	55606	int64x2_t __rev1_221; __rev1_221 = __builtin_shufflevector(__s1_221, __s1_221, 1, 0); \
65501	int32x4_t __ret_227; \	55607	int32x4_t __ret_221; \
65502	__ret_227 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_227), (int32x2_t)(__noswap_vrshrn_n_s64(__rev1_227, __p2_227)))); \	55608	__ret_221 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_221), (int32x2_t)(__noswap_vrshrn_n_s64(__rev1_221, __p2_221)))); \
65503	__ret_227 = __builtin_shufflevector(__ret_227, __ret_227, 3, 2, 1, 0); \	55609	__ret_221 = __builtin_shufflevector(__ret_221, __ret_221, 3, 2, 1, 0); \
65504	__ret_227; \	55610	__ret_221; \
65505	})	55611	})
65506	#endif	55612	#endif
65507		55613
65508	#ifdef __LITTLE_ENDIAN__	55614	#ifdef __LITTLE_ENDIAN__
65509	#define vrshrn_high_n_s16(__p0_228, __p1_228, __p2_228) __extension__ ({ \	55615	#define vrshrn_high_n_s16(__p0_222, __p1_222, __p2_222) __extension__ ({ \
65510	int8x8_t __s0_228 = __p0_228; \	55616	int8x8_t __s0_222 = __p0_222; \
65511	int16x8_t __s1_228 = __p1_228; \	55617	int16x8_t __s1_222 = __p1_222; \
65512	int8x16_t __ret_228; \	55618	int8x16_t __ret_222; \
65513	__ret_228 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_228), (int8x8_t)(vrshrn_n_s16(__s1_228, __p2_228)))); \	55619	__ret_222 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_222), (int8x8_t)(vrshrn_n_s16(__s1_222, __p2_222)))); \
65514	__ret_228; \	55620	__ret_222; \
65515	})	55621	})
65516	#else	55622	#else
65517	#define vrshrn_high_n_s16(__p0_229, __p1_229, __p2_229) __extension__ ({ \	55623	#define vrshrn_high_n_s16(__p0_223, __p1_223, __p2_223) __extension__ ({ \
65518	int8x8_t __s0_229 = __p0_229; \	55624	int8x8_t __s0_223 = __p0_223; \
65519	int16x8_t __s1_229 = __p1_229; \	55625	int16x8_t __s1_223 = __p1_223; \
65520	int8x8_t __rev0_229; __rev0_229 = __builtin_shufflevector(__s0_229, __s0_229, 7, 6, 5, 4, 3, 2, 1, 0); \	55626	int8x8_t __rev0_223; __rev0_223 = __builtin_shufflevector(__s0_223, __s0_223, 7, 6, 5, 4, 3, 2, 1, 0); \
65521	int16x8_t __rev1_229; __rev1_229 = __builtin_shufflevector(__s1_229, __s1_229, 7, 6, 5, 4, 3, 2, 1, 0); \	55627	int16x8_t __rev1_223; __rev1_223 = __builtin_shufflevector(__s1_223, __s1_223, 7, 6, 5, 4, 3, 2, 1, 0); \
65522	int8x16_t __ret_229; \	55628	int8x16_t __ret_223; \
65523	__ret_229 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_229), (int8x8_t)(__noswap_vrshrn_n_s16(__rev1_229, __p2_229)))); \	55629	__ret_223 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_223), (int8x8_t)(__noswap_vrshrn_n_s16(__rev1_223, __p2_223)))); \
65524	__ret_229 = __builtin_shufflevector(__ret_229, __ret_229, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	55630	__ret_223 = __builtin_shufflevector(__ret_223, __ret_223, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
65525	__ret_229; \	55631	__ret_223; \
65526	})	55632	})
65527	#endif	55633	#endif
65528		55634
...	@@ -65542,48 +55648,21 @@ __ai float64x2_t vrsqrteq_f64(float64x2_t __p0) {	...	@@ -65542,48 +55648,21 @@ __ai float64x2_t vrsqrteq_f64(float64x2_t __p0) {
65542	}	55648	}
65543	#endif	55649	#endif
65544		55650
65545	#ifdef __LITTLE_ENDIAN__
65546	__ai float64x1_t vrsqrte_f64(float64x1_t __p0) {
65547	float64x1_t __ret;
65548	__ret = (float64x1_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 10);
65549	return __ret;
65550	}
65551	#else
65552	__ai float64x1_t vrsqrte_f64(float64x1_t __p0) {	55651	__ai float64x1_t vrsqrte_f64(float64x1_t __p0) {
65553	float64x1_t __ret;	55652	float64x1_t __ret;
65554	__ret = (float64x1_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 10);	55653	__ret = (float64x1_t) __builtin_neon_vrsqrte_v((int8x8_t)__p0, 10);
65555	return __ret;	55654	return __ret;
65556	}	55655	}
65557	#endif
65558
65559	#ifdef __LITTLE_ENDIAN__
65560	__ai float64_t vrsqrted_f64(float64_t __p0) {
65561	float64_t __ret;
65562	__ret = (float64_t) __builtin_neon_vrsqrted_f64(__p0);
65563	return __ret;
65564	}
65565	#else
65566	__ai float64_t vrsqrted_f64(float64_t __p0) {	55656	__ai float64_t vrsqrted_f64(float64_t __p0) {
65567	float64_t __ret;	55657	float64_t __ret;
65568	__ret = (float64_t) __builtin_neon_vrsqrted_f64(__p0);	55658	__ret = (float64_t) __builtin_neon_vrsqrted_f64(__p0);
65569	return __ret;	55659	return __ret;
65570	}	55660	}
65571	#endif
65572
65573	#ifdef __LITTLE_ENDIAN__
65574	__ai float32_t vrsqrtes_f32(float32_t __p0) {
65575	float32_t __ret;
65576	__ret = (float32_t) __builtin_neon_vrsqrtes_f32(__p0);
65577	return __ret;
65578	}
65579	#else
65580	__ai float32_t vrsqrtes_f32(float32_t __p0) {	55661	__ai float32_t vrsqrtes_f32(float32_t __p0) {
65581	float32_t __ret;	55662	float32_t __ret;
65582	__ret = (float32_t) __builtin_neon_vrsqrtes_f32(__p0);	55663	__ret = (float32_t) __builtin_neon_vrsqrtes_f32(__p0);
65583	return __ret;	55664	return __ret;
65584	}	55665	}
65585	#endif
65586
65587	#ifdef __LITTLE_ENDIAN__	55666	#ifdef __LITTLE_ENDIAN__
65588	__ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {	55667	__ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {
65589	float64x2_t __ret;	55668	float64x2_t __ret;
...	@@ -65601,57 +55680,21 @@ __ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -65601,57 +55680,21 @@ __ai float64x2_t vrsqrtsq_f64(float64x2_t __p0, float64x2_t __p1) {
65601	}	55680	}
65602	#endif	55681	#endif
65603		55682
65604	#ifdef __LITTLE_ENDIAN__
65605	__ai float64x1_t vrsqrts_f64(float64x1_t __p0, float64x1_t __p1) {
65606	float64x1_t __ret;
65607	__ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
65608	return __ret;
65609	}
65610	#else
65611	__ai float64x1_t vrsqrts_f64(float64x1_t __p0, float64x1_t __p1) {	55683	__ai float64x1_t vrsqrts_f64(float64x1_t __p0, float64x1_t __p1) {
65612	float64x1_t __ret;	55684	float64x1_t __ret;
65613	__ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);	55685	__ret = (float64x1_t) __builtin_neon_vrsqrts_v((int8x8_t)__p0, (int8x8_t)__p1, 10);
65614	return __ret;	55686	return __ret;
65615	}	55687	}
65616	#endif
65617
65618	#ifdef __LITTLE_ENDIAN__
65619	__ai float64_t vrsqrtsd_f64(float64_t __p0, float64_t __p1) {
65620	float64_t __ret;
65621	__ret = (float64_t) __builtin_neon_vrsqrtsd_f64(__p0, __p1);
65622	return __ret;
65623	}
65624	#else
65625	__ai float64_t vrsqrtsd_f64(float64_t __p0, float64_t __p1) {	55688	__ai float64_t vrsqrtsd_f64(float64_t __p0, float64_t __p1) {
65626	float64_t __ret;	55689	float64_t __ret;
65627	__ret = (float64_t) __builtin_neon_vrsqrtsd_f64(__p0, __p1);	55690	__ret = (float64_t) __builtin_neon_vrsqrtsd_f64(__p0, __p1);
65628	return __ret;	55691	return __ret;
65629	}	55692	}
65630	#endif
65631
65632	#ifdef __LITTLE_ENDIAN__
65633	__ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
65634	float32_t __ret;
65635	__ret = (float32_t) __builtin_neon_vrsqrtss_f32(__p0, __p1);
65636	return __ret;
65637	}
65638	#else
65639	__ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {	55693	__ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
65640	float32_t __ret;	55694	float32_t __ret;
65641	__ret = (float32_t) __builtin_neon_vrsqrtss_f32(__p0, __p1);	55695	__ret = (float32_t) __builtin_neon_vrsqrtss_f32(__p0, __p1);
65642	return __ret;	55696	return __ret;
65643	}	55697	}
65644	#endif
65645
65646	#ifdef __LITTLE_ENDIAN__
65647	#define vrsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
65648	uint64_t __s0 = __p0; \
65649	uint64_t __s1 = __p1; \
65650	uint64_t __ret; \
65651	__ret = (uint64_t) __builtin_neon_vrsrad_n_u64(__s0, __s1, __p2); \
65652	__ret; \
65653	})
65654	#else
65655	#define vrsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \	55698	#define vrsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
65656	uint64_t __s0 = __p0; \	55699	uint64_t __s0 = __p0; \
65657	uint64_t __s1 = __p1; \	55700	uint64_t __s1 = __p1; \
...	@@ -65659,17 +55702,6 @@ __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {	...	@@ -65659,17 +55702,6 @@ __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
65659	__ret = (uint64_t) __builtin_neon_vrsrad_n_u64(__s0, __s1, __p2); \	55702	__ret = (uint64_t) __builtin_neon_vrsrad_n_u64(__s0, __s1, __p2); \
65660	__ret; \	55703	__ret; \
65661	})	55704	})
65662	#endif
65663
65664	#ifdef __LITTLE_ENDIAN__
65665	#define vrsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
65666	int64_t __s0 = __p0; \
65667	int64_t __s1 = __p1; \
65668	int64_t __ret; \
65669	__ret = (int64_t) __builtin_neon_vrsrad_n_s64(__s0, __s1, __p2); \
65670	__ret; \
65671	})
65672	#else
65673	#define vrsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \	55705	#define vrsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
65674	int64_t __s0 = __p0; \	55706	int64_t __s0 = __p0; \
65675	int64_t __s1 = __p1; \	55707	int64_t __s1 = __p1; \
...	@@ -65677,8 +55709,6 @@ __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {	...	@@ -65677,8 +55709,6 @@ __ai float32_t vrsqrtss_f32(float32_t __p0, float32_t __p1) {
65677	__ret = (int64_t) __builtin_neon_vrsrad_n_s64(__s0, __s1, __p2); \	55709	__ret = (int64_t) __builtin_neon_vrsrad_n_s64(__s0, __s1, __p2); \
65678	__ret; \	55710	__ret; \
65679	})	55711	})
65680	#endif
65681
65682	#ifdef __LITTLE_ENDIAN__	55712	#ifdef __LITTLE_ENDIAN__
65683	__ai uint16x8_t vrsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {	55713	__ai uint16x8_t vrsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
65684	uint16x8_t __ret;	55714	uint16x8_t __ret;
...	@@ -65787,37 +55817,19 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65787,37 +55817,19 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65787	}	55817	}
65788	#endif	55818	#endif
65789		55819
65790	#ifdef __LITTLE_ENDIAN__
65791	#define vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \	55820	#define vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
65792	poly64_t __s0 = __p0; \	55821	poly64_t __s0 = __p0; \
65793	poly64x1_t __s1 = __p1; \	55822	poly64x1_t __s1 = __p1; \
65794	poly64x1_t __ret; \	55823	poly64x1_t __ret; \
65795	__ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \	55824	__ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (poly64x1_t)__s1, __p2); \
65796	__ret; \	55825	__ret; \
65797	})	55826	})
65798	#else
65799	#define vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
65800	poly64_t __s0 = __p0; \
65801	poly64x1_t __s1 = __p1; \
65802	poly64x1_t __ret; \
65803	__ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
65804	__ret; \
65805	})
65806	#define __noswap_vset_lane_p64(__p0, __p1, __p2) __extension__ ({ \
65807	poly64_t __s0 = __p0; \
65808	poly64x1_t __s1 = __p1; \
65809	poly64x1_t __ret; \
65810	__ret = (poly64x1_t) __builtin_neon_vset_lane_i64(__s0, (int8x8_t)__s1, __p2); \
65811	__ret; \
65812	})
65813	#endif
65814
65815	#ifdef __LITTLE_ENDIAN__	55827	#ifdef __LITTLE_ENDIAN__
65816	#define vsetq_lane_p64(__p0, __p1, __p2) __extension__ ({ \	55828	#define vsetq_lane_p64(__p0, __p1, __p2) __extension__ ({ \
65817	poly64_t __s0 = __p0; \	55829	poly64_t __s0 = __p0; \
65818	poly64x2_t __s1 = __p1; \	55830	poly64x2_t __s1 = __p1; \
65819	poly64x2_t __ret; \	55831	poly64x2_t __ret; \
65820	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	55832	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (poly64x2_t)__s1, __p2); \
65821	__ret; \	55833	__ret; \
65822	})	55834	})
65823	#else	55835	#else
...	@@ -65826,7 +55838,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65826,7 +55838,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65826	poly64x2_t __s1 = __p1; \	55838	poly64x2_t __s1 = __p1; \
65827	poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	55839	poly64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
65828	poly64x2_t __ret; \	55840	poly64x2_t __ret; \
65829	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__rev1, __p2); \	55841	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (poly64x2_t)__rev1, __p2); \
65830	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	55842	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
65831	__ret; \	55843	__ret; \
65832	})	55844	})
...	@@ -65834,7 +55846,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65834,7 +55846,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65834	poly64_t __s0 = __p0; \	55846	poly64_t __s0 = __p0; \
65835	poly64x2_t __s1 = __p1; \	55847	poly64x2_t __s1 = __p1; \
65836	poly64x2_t __ret; \	55848	poly64x2_t __ret; \
65837	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (int8x16_t)__s1, __p2); \	55849	__ret = (poly64x2_t) __builtin_neon_vsetq_lane_i64(__s0, (poly64x2_t)__s1, __p2); \
65838	__ret; \	55850	__ret; \
65839	})	55851	})
65840	#endif	55852	#endif
...	@@ -65844,7 +55856,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65844,7 +55856,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65844	float64_t __s0 = __p0; \	55856	float64_t __s0 = __p0; \
65845	float64x2_t __s1 = __p1; \	55857	float64x2_t __s1 = __p1; \
65846	float64x2_t __ret; \	55858	float64x2_t __ret; \
65847	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (int8x16_t)__s1, __p2); \	55859	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (float64x2_t)__s1, __p2); \
65848	__ret; \	55860	__ret; \
65849	})	55861	})
65850	#else	55862	#else
...	@@ -65853,7 +55865,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65853,7 +55865,7 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65853	float64x2_t __s1 = __p1; \	55865	float64x2_t __s1 = __p1; \
65854	float64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \	55866	float64x2_t __rev1; __rev1 = __builtin_shufflevector(__s1, __s1, 1, 0); \
65855	float64x2_t __ret; \	55867	float64x2_t __ret; \
65856	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (int8x16_t)__rev1, __p2); \	55868	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (float64x2_t)__rev1, __p2); \
65857	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \	55869	__ret = __builtin_shufflevector(__ret, __ret, 1, 0); \
65858	__ret; \	55870	__ret; \
65859	})	55871	})
...	@@ -65861,371 +55873,286 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {	...	@@ -65861,371 +55873,286 @@ __ai int8x16_t vrsubhn_high_s16(int8x8_t __p0, int16x8_t __p1, int16x8_t __p2) {
65861	float64_t __s0 = __p0; \	55873	float64_t __s0 = __p0; \
65862	float64x2_t __s1 = __p1; \	55874	float64x2_t __s1 = __p1; \
65863	float64x2_t __ret; \	55875	float64x2_t __ret; \
65864	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (int8x16_t)__s1, __p2); \	55876	__ret = (float64x2_t) __builtin_neon_vsetq_lane_f64(__s0, (float64x2_t)__s1, __p2); \
65865	__ret; \	55877	__ret; \
65866	})	55878	})
65867	#endif	55879	#endif
65868		55880
65869	#ifdef __LITTLE_ENDIAN__
65870	#define vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
65871	float64_t __s0 = __p0; \
65872	float64x1_t __s1 = __p1; \
65873	float64x1_t __ret; \
65874	__ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \
65875	__ret; \
65876	})
65877	#else
65878	#define vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \	55881	#define vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
65879	float64_t __s0 = __p0; \	55882	float64_t __s0 = __p0; \
65880	float64x1_t __s1 = __p1; \	55883	float64x1_t __s1 = __p1; \
65881	float64x1_t __ret; \	55884	float64x1_t __ret; \
65882	__ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \	55885	__ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (float64x1_t)__s1, __p2); \
65883	__ret; \
65884	})
65885	#define __noswap_vset_lane_f64(__p0, __p1, __p2) __extension__ ({ \
65886	float64_t __s0 = __p0; \
65887	float64x1_t __s1 = __p1; \
65888	float64x1_t __ret; \
65889	__ret = (float64x1_t) __builtin_neon_vset_lane_f64(__s0, (int8x8_t)__s1, __p2); \
65890	__ret; \	55886	__ret; \
65891	})	55887	})
65892	#endif
65893
65894	#ifdef __LITTLE_ENDIAN__
65895	__ai uint64_t vshld_u64(uint64_t __p0, uint64_t __p1) {
65896	uint64_t __ret;
65897	__ret = (uint64_t) __builtin_neon_vshld_u64(__p0, __p1);
65898	return __ret;
65899	}
65900	#else
65901	__ai uint64_t vshld_u64(uint64_t __p0, uint64_t __p1) {	55888	__ai uint64_t vshld_u64(uint64_t __p0, uint64_t __p1) {
65902	uint64_t __ret;	55889	uint64_t __ret;
65903	__ret = (uint64_t) __builtin_neon_vshld_u64(__p0, __p1);	55890	__ret = (uint64_t) __builtin_neon_vshld_u64(__p0, __p1);
65904	return __ret;	55891	return __ret;
65905	}	55892	}
65906	#endif
65907
65908	#ifdef __LITTLE_ENDIAN__
65909	__ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
65910	int64_t __ret;
65911	__ret = (int64_t) __builtin_neon_vshld_s64(__p0, __p1);
65912	return __ret;
65913	}
65914	#else
65915	__ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {	55893	__ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
65916	int64_t __ret;	55894	int64_t __ret;
65917	__ret = (int64_t) __builtin_neon_vshld_s64(__p0, __p1);	55895	__ret = (int64_t) __builtin_neon_vshld_s64(__p0, __p1);
65918	return __ret;	55896	return __ret;
65919	}	55897	}
65920	#endif
65921
65922	#ifdef __LITTLE_ENDIAN__
65923	#define vshld_n_u64(__p0, __p1) __extension__ ({ \
65924	uint64_t __s0 = __p0; \
65925	uint64_t __ret; \
65926	__ret = (uint64_t) __builtin_neon_vshld_n_u64(__s0, __p1); \
65927	__ret; \
65928	})
65929	#else
65930	#define vshld_n_u64(__p0, __p1) __extension__ ({ \	55898	#define vshld_n_u64(__p0, __p1) __extension__ ({ \
65931	uint64_t __s0 = __p0; \	55899	uint64_t __s0 = __p0; \
65932	uint64_t __ret; \	55900	uint64_t __ret; \
65933	__ret = (uint64_t) __builtin_neon_vshld_n_u64(__s0, __p1); \	55901	__ret = (uint64_t) __builtin_neon_vshld_n_u64(__s0, __p1); \
65934	__ret; \	55902	__ret; \
65935	})	55903	})
65936	#endif
65937
65938	#ifdef __LITTLE_ENDIAN__
65939	#define vshld_n_s64(__p0, __p1) __extension__ ({ \
65940	int64_t __s0 = __p0; \
65941	int64_t __ret; \
65942	__ret = (int64_t) __builtin_neon_vshld_n_s64(__s0, __p1); \
65943	__ret; \
65944	})
65945	#else
65946	#define vshld_n_s64(__p0, __p1) __extension__ ({ \	55904	#define vshld_n_s64(__p0, __p1) __extension__ ({ \
65947	int64_t __s0 = __p0; \	55905	int64_t __s0 = __p0; \
65948	int64_t __ret; \	55906	int64_t __ret; \
65949	__ret = (int64_t) __builtin_neon_vshld_n_s64(__s0, __p1); \	55907	__ret = (int64_t) __builtin_neon_vshld_n_s64(__s0, __p1); \
65950	__ret; \	55908	__ret; \
65951	})	55909	})
65952	#endif
65953
65954	#ifdef __LITTLE_ENDIAN__	55910	#ifdef __LITTLE_ENDIAN__
65955	#define vshll_high_n_u8(__p0_230, __p1_230) __extension__ ({ \	55911	#define vshll_high_n_u8(__p0_224, __p1_224) __extension__ ({ \
65956	uint8x16_t __s0_230 = __p0_230; \	55912	uint8x16_t __s0_224 = __p0_224; \
65957	uint16x8_t __ret_230; \	55913	uint16x8_t __ret_224; \
65958	__ret_230 = (uint16x8_t)(vshll_n_u8(vget_high_u8(__s0_230), __p1_230)); \	55914	__ret_224 = (uint16x8_t)(vshll_n_u8(vget_high_u8(__s0_224), __p1_224)); \
65959	__ret_230; \	55915	__ret_224; \
65960	})	55916	})
65961	#else	55917	#else
65962	#define vshll_high_n_u8(__p0_231, __p1_231) __extension__ ({ \	55918	#define vshll_high_n_u8(__p0_225, __p1_225) __extension__ ({ \
65963	uint8x16_t __s0_231 = __p0_231; \	55919	uint8x16_t __s0_225 = __p0_225; \
65964	uint8x16_t __rev0_231; __rev0_231 = __builtin_shufflevector(__s0_231, __s0_231, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	55920	uint8x16_t __rev0_225; __rev0_225 = __builtin_shufflevector(__s0_225, __s0_225, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
65965	uint16x8_t __ret_231; \	55921	uint16x8_t __ret_225; \
65966	__ret_231 = (uint16x8_t)(__noswap_vshll_n_u8(__noswap_vget_high_u8(__rev0_231), __p1_231)); \	55922	__ret_225 = (uint16x8_t)(__noswap_vshll_n_u8(__noswap_vget_high_u8(__rev0_225), __p1_225)); \
65967	__ret_231 = __builtin_shufflevector(__ret_231, __ret_231, 7, 6, 5, 4, 3, 2, 1, 0); \	55923	__ret_225 = __builtin_shufflevector(__ret_225, __ret_225, 7, 6, 5, 4, 3, 2, 1, 0); \
65968	__ret_231; \	55924	__ret_225; \
65969	})	55925	})
65970	#endif	55926	#endif
65971		55927
65972	#ifdef __LITTLE_ENDIAN__	55928	#ifdef __LITTLE_ENDIAN__
65973	#define vshll_high_n_u32(__p0_232, __p1_232) __extension__ ({ \	55929	#define vshll_high_n_u32(__p0_226, __p1_226) __extension__ ({ \
65974	uint32x4_t __s0_232 = __p0_232; \	55930	uint32x4_t __s0_226 = __p0_226; \
65975	uint64x2_t __ret_232; \	55931	uint64x2_t __ret_226; \
65976	__ret_232 = (uint64x2_t)(vshll_n_u32(vget_high_u32(__s0_232), __p1_232)); \	55932	__ret_226 = (uint64x2_t)(vshll_n_u32(vget_high_u32(__s0_226), __p1_226)); \
65977	__ret_232; \	55933	__ret_226; \
65978	})	55934	})
65979	#else	55935	#else
65980	#define vshll_high_n_u32(__p0_233, __p1_233) __extension__ ({ \	55936	#define vshll_high_n_u32(__p0_227, __p1_227) __extension__ ({ \
65981	uint32x4_t __s0_233 = __p0_233; \	55937	uint32x4_t __s0_227 = __p0_227; \
65982	uint32x4_t __rev0_233; __rev0_233 = __builtin_shufflevector(__s0_233, __s0_233, 3, 2, 1, 0); \	55938	uint32x4_t __rev0_227; __rev0_227 = __builtin_shufflevector(__s0_227, __s0_227, 3, 2, 1, 0); \
65983	uint64x2_t __ret_233; \	55939	uint64x2_t __ret_227; \
65984	__ret_233 = (uint64x2_t)(__noswap_vshll_n_u32(__noswap_vget_high_u32(__rev0_233), __p1_233)); \	55940	__ret_227 = (uint64x2_t)(__noswap_vshll_n_u32(__noswap_vget_high_u32(__rev0_227), __p1_227)); \
65985	__ret_233 = __builtin_shufflevector(__ret_233, __ret_233, 1, 0); \	55941	__ret_227 = __builtin_shufflevector(__ret_227, __ret_227, 1, 0); \
65986	__ret_233; \	55942	__ret_227; \
65987	})	55943	})
65988	#endif	55944	#endif
65989		55945
65990	#ifdef __LITTLE_ENDIAN__	55946	#ifdef __LITTLE_ENDIAN__
65991	#define vshll_high_n_u16(__p0_234, __p1_234) __extension__ ({ \	55947	#define vshll_high_n_u16(__p0_228, __p1_228) __extension__ ({ \
65992	uint16x8_t __s0_234 = __p0_234; \	55948	uint16x8_t __s0_228 = __p0_228; \
65993	uint32x4_t __ret_234; \	55949	uint32x4_t __ret_228; \
65994	__ret_234 = (uint32x4_t)(vshll_n_u16(vget_high_u16(__s0_234), __p1_234)); \	55950	__ret_228 = (uint32x4_t)(vshll_n_u16(vget_high_u16(__s0_228), __p1_228)); \
65995	__ret_234; \	55951	__ret_228; \
65996	})	55952	})
65997	#else	55953	#else
65998	#define vshll_high_n_u16(__p0_235, __p1_235) __extension__ ({ \	55954	#define vshll_high_n_u16(__p0_229, __p1_229) __extension__ ({ \
65999	uint16x8_t __s0_235 = __p0_235; \	55955	uint16x8_t __s0_229 = __p0_229; \
66000	uint16x8_t __rev0_235; __rev0_235 = __builtin_shufflevector(__s0_235, __s0_235, 7, 6, 5, 4, 3, 2, 1, 0); \	55956	uint16x8_t __rev0_229; __rev0_229 = __builtin_shufflevector(__s0_229, __s0_229, 7, 6, 5, 4, 3, 2, 1, 0); \
66001	uint32x4_t __ret_235; \	55957	uint32x4_t __ret_229; \
66002	__ret_235 = (uint32x4_t)(__noswap_vshll_n_u16(__noswap_vget_high_u16(__rev0_235), __p1_235)); \	55958	__ret_229 = (uint32x4_t)(__noswap_vshll_n_u16(__noswap_vget_high_u16(__rev0_229), __p1_229)); \
66003	__ret_235 = __builtin_shufflevector(__ret_235, __ret_235, 3, 2, 1, 0); \	55959	__ret_229 = __builtin_shufflevector(__ret_229, __ret_229, 3, 2, 1, 0); \
66004	__ret_235; \	55960	__ret_229; \
66005	})	55961	})
66006	#endif	55962	#endif
66007		55963
66008	#ifdef __LITTLE_ENDIAN__	55964	#ifdef __LITTLE_ENDIAN__
66009	#define vshll_high_n_s8(__p0_236, __p1_236) __extension__ ({ \	55965	#define vshll_high_n_s8(__p0_230, __p1_230) __extension__ ({ \
66010	int8x16_t __s0_236 = __p0_236; \	55966	int8x16_t __s0_230 = __p0_230; \
66011	int16x8_t __ret_236; \	55967	int16x8_t __ret_230; \
66012	__ret_236 = (int16x8_t)(vshll_n_s8(vget_high_s8(__s0_236), __p1_236)); \	55968	__ret_230 = (int16x8_t)(vshll_n_s8(vget_high_s8(__s0_230), __p1_230)); \
66013	__ret_236; \	55969	__ret_230; \
66014	})	55970	})
66015	#else	55971	#else
66016	#define vshll_high_n_s8(__p0_237, __p1_237) __extension__ ({ \	55972	#define vshll_high_n_s8(__p0_231, __p1_231) __extension__ ({ \
66017	int8x16_t __s0_237 = __p0_237; \	55973	int8x16_t __s0_231 = __p0_231; \
66018	int8x16_t __rev0_237; __rev0_237 = __builtin_shufflevector(__s0_237, __s0_237, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	55974	int8x16_t __rev0_231; __rev0_231 = __builtin_shufflevector(__s0_231, __s0_231, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
66019	int16x8_t __ret_237; \	55975	int16x8_t __ret_231; \
66020	__ret_237 = (int16x8_t)(__noswap_vshll_n_s8(__noswap_vget_high_s8(__rev0_237), __p1_237)); \	55976	__ret_231 = (int16x8_t)(__noswap_vshll_n_s8(__noswap_vget_high_s8(__rev0_231), __p1_231)); \
66021	__ret_237 = __builtin_shufflevector(__ret_237, __ret_237, 7, 6, 5, 4, 3, 2, 1, 0); \	55977	__ret_231 = __builtin_shufflevector(__ret_231, __ret_231, 7, 6, 5, 4, 3, 2, 1, 0); \
66022	__ret_237; \	55978	__ret_231; \
66023	})	55979	})
66024	#endif	55980	#endif
66025		55981
66026	#ifdef __LITTLE_ENDIAN__	55982	#ifdef __LITTLE_ENDIAN__
66027	#define vshll_high_n_s32(__p0_238, __p1_238) __extension__ ({ \	55983	#define vshll_high_n_s32(__p0_232, __p1_232) __extension__ ({ \
66028	int32x4_t __s0_238 = __p0_238; \	55984	int32x4_t __s0_232 = __p0_232; \
66029	int64x2_t __ret_238; \	55985	int64x2_t __ret_232; \
66030	__ret_238 = (int64x2_t)(vshll_n_s32(vget_high_s32(__s0_238), __p1_238)); \	55986	__ret_232 = (int64x2_t)(vshll_n_s32(vget_high_s32(__s0_232), __p1_232)); \
66031	__ret_238; \	55987	__ret_232; \
66032	})	55988	})
66033	#else	55989	#else
66034	#define vshll_high_n_s32(__p0_239, __p1_239) __extension__ ({ \	55990	#define vshll_high_n_s32(__p0_233, __p1_233) __extension__ ({ \
66035	int32x4_t __s0_239 = __p0_239; \	55991	int32x4_t __s0_233 = __p0_233; \
66036	int32x4_t __rev0_239; __rev0_239 = __builtin_shufflevector(__s0_239, __s0_239, 3, 2, 1, 0); \	55992	int32x4_t __rev0_233; __rev0_233 = __builtin_shufflevector(__s0_233, __s0_233, 3, 2, 1, 0); \
66037	int64x2_t __ret_239; \	55993	int64x2_t __ret_233; \
66038	__ret_239 = (int64x2_t)(__noswap_vshll_n_s32(__noswap_vget_high_s32(__rev0_239), __p1_239)); \	55994	__ret_233 = (int64x2_t)(__noswap_vshll_n_s32(__noswap_vget_high_s32(__rev0_233), __p1_233)); \
66039	__ret_239 = __builtin_shufflevector(__ret_239, __ret_239, 1, 0); \	55995	__ret_233 = __builtin_shufflevector(__ret_233, __ret_233, 1, 0); \
66040	__ret_239; \	55996	__ret_233; \
66041	})	55997	})
66042	#endif	55998	#endif
66043		55999
66044	#ifdef __LITTLE_ENDIAN__	56000	#ifdef __LITTLE_ENDIAN__
66045	#define vshll_high_n_s16(__p0_240, __p1_240) __extension__ ({ \	56001	#define vshll_high_n_s16(__p0_234, __p1_234) __extension__ ({ \
66046	int16x8_t __s0_240 = __p0_240; \	56002	int16x8_t __s0_234 = __p0_234; \
66047	int32x4_t __ret_240; \	56003	int32x4_t __ret_234; \
66048	__ret_240 = (int32x4_t)(vshll_n_s16(vget_high_s16(__s0_240), __p1_240)); \	56004	__ret_234 = (int32x4_t)(vshll_n_s16(vget_high_s16(__s0_234), __p1_234)); \
66049	__ret_240; \	56005	__ret_234; \
66050	})	56006	})
66051	#else	56007	#else
66052	#define vshll_high_n_s16(__p0_241, __p1_241) __extension__ ({ \	56008	#define vshll_high_n_s16(__p0_235, __p1_235) __extension__ ({ \
66053	int16x8_t __s0_241 = __p0_241; \	56009	int16x8_t __s0_235 = __p0_235; \
66054	int16x8_t __rev0_241; __rev0_241 = __builtin_shufflevector(__s0_241, __s0_241, 7, 6, 5, 4, 3, 2, 1, 0); \	56010	int16x8_t __rev0_235; __rev0_235 = __builtin_shufflevector(__s0_235, __s0_235, 7, 6, 5, 4, 3, 2, 1, 0); \
66055	int32x4_t __ret_241; \	56011	int32x4_t __ret_235; \
66056	__ret_241 = (int32x4_t)(__noswap_vshll_n_s16(__noswap_vget_high_s16(__rev0_241), __p1_241)); \	56012	__ret_235 = (int32x4_t)(__noswap_vshll_n_s16(__noswap_vget_high_s16(__rev0_235), __p1_235)); \
66057	__ret_241 = __builtin_shufflevector(__ret_241, __ret_241, 3, 2, 1, 0); \	56013	__ret_235 = __builtin_shufflevector(__ret_235, __ret_235, 3, 2, 1, 0); \
66058	__ret_241; \	56014	__ret_235; \
66059	})	56015	})
66060	#endif	56016	#endif
66061		56017
66062	#ifdef __LITTLE_ENDIAN__
66063	#define vshrd_n_u64(__p0, __p1) __extension__ ({ \
66064	uint64_t __s0 = __p0; \
66065	uint64_t __ret; \
66066	__ret = (uint64_t) __builtin_neon_vshrd_n_u64(__s0, __p1); \
66067	__ret; \
66068	})
66069	#else
66070	#define vshrd_n_u64(__p0, __p1) __extension__ ({ \	56018	#define vshrd_n_u64(__p0, __p1) __extension__ ({ \
66071	uint64_t __s0 = __p0; \	56019	uint64_t __s0 = __p0; \
66072	uint64_t __ret; \	56020	uint64_t __ret; \
66073	__ret = (uint64_t) __builtin_neon_vshrd_n_u64(__s0, __p1); \	56021	__ret = (uint64_t) __builtin_neon_vshrd_n_u64(__s0, __p1); \
66074	__ret; \	56022	__ret; \
66075	})	56023	})
66076	#endif
66077
66078	#ifdef __LITTLE_ENDIAN__
66079	#define vshrd_n_s64(__p0, __p1) __extension__ ({ \
66080	int64_t __s0 = __p0; \
66081	int64_t __ret; \
66082	__ret = (int64_t) __builtin_neon_vshrd_n_s64(__s0, __p1); \
66083	__ret; \
66084	})
66085	#else
66086	#define vshrd_n_s64(__p0, __p1) __extension__ ({ \	56024	#define vshrd_n_s64(__p0, __p1) __extension__ ({ \
66087	int64_t __s0 = __p0; \	56025	int64_t __s0 = __p0; \
66088	int64_t __ret; \	56026	int64_t __ret; \
66089	__ret = (int64_t) __builtin_neon_vshrd_n_s64(__s0, __p1); \	56027	__ret = (int64_t) __builtin_neon_vshrd_n_s64(__s0, __p1); \
66090	__ret; \	56028	__ret; \
66091	})	56029	})
66092	#endif
66093
66094	#ifdef __LITTLE_ENDIAN__	56030	#ifdef __LITTLE_ENDIAN__
66095	#define vshrn_high_n_u32(__p0_242, __p1_242, __p2_242) __extension__ ({ \	56031	#define vshrn_high_n_u32(__p0_236, __p1_236, __p2_236) __extension__ ({ \
66096	uint16x4_t __s0_242 = __p0_242; \	56032	uint16x4_t __s0_236 = __p0_236; \
66097	uint32x4_t __s1_242 = __p1_242; \	56033	uint32x4_t __s1_236 = __p1_236; \
66098	uint16x8_t __ret_242; \	56034	uint16x8_t __ret_236; \
66099	__ret_242 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_242), (uint16x4_t)(vshrn_n_u32(__s1_242, __p2_242)))); \	56035	__ret_236 = (uint16x8_t)(vcombine_u16((uint16x4_t)(__s0_236), (uint16x4_t)(vshrn_n_u32(__s1_236, __p2_236)))); \
66100	__ret_242; \	56036	__ret_236; \
66101	})	56037	})
66102	#else	56038	#else
66103	#define vshrn_high_n_u32(__p0_243, __p1_243, __p2_243) __extension__ ({ \	56039	#define vshrn_high_n_u32(__p0_237, __p1_237, __p2_237) __extension__ ({ \
66104	uint16x4_t __s0_243 = __p0_243; \	56040	uint16x4_t __s0_237 = __p0_237; \
66105	uint32x4_t __s1_243 = __p1_243; \	56041	uint32x4_t __s1_237 = __p1_237; \
66106	uint16x4_t __rev0_243; __rev0_243 = __builtin_shufflevector(__s0_243, __s0_243, 3, 2, 1, 0); \	56042	uint16x4_t __rev0_237; __rev0_237 = __builtin_shufflevector(__s0_237, __s0_237, 3, 2, 1, 0); \
66107	uint32x4_t __rev1_243; __rev1_243 = __builtin_shufflevector(__s1_243, __s1_243, 3, 2, 1, 0); \	56043	uint32x4_t __rev1_237; __rev1_237 = __builtin_shufflevector(__s1_237, __s1_237, 3, 2, 1, 0); \
66108	uint16x8_t __ret_243; \	56044	uint16x8_t __ret_237; \
66109	__ret_243 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_243), (uint16x4_t)(__noswap_vshrn_n_u32(__rev1_243, __p2_243)))); \	56045	__ret_237 = (uint16x8_t)(__noswap_vcombine_u16((uint16x4_t)(__rev0_237), (uint16x4_t)(__noswap_vshrn_n_u32(__rev1_237, __p2_237)))); \
66110	__ret_243 = __builtin_shufflevector(__ret_243, __ret_243, 7, 6, 5, 4, 3, 2, 1, 0); \	56046	__ret_237 = __builtin_shufflevector(__ret_237, __ret_237, 7, 6, 5, 4, 3, 2, 1, 0); \
66111	__ret_243; \	56047	__ret_237; \
66112	})	56048	})
66113	#endif	56049	#endif
66114		56050
66115	#ifdef __LITTLE_ENDIAN__	56051	#ifdef __LITTLE_ENDIAN__
66116	#define vshrn_high_n_u64(__p0_244, __p1_244, __p2_244) __extension__ ({ \	56052	#define vshrn_high_n_u64(__p0_238, __p1_238, __p2_238) __extension__ ({ \
66117	uint32x2_t __s0_244 = __p0_244; \	56053	uint32x2_t __s0_238 = __p0_238; \
66118	uint64x2_t __s1_244 = __p1_244; \	56054	uint64x2_t __s1_238 = __p1_238; \
66119	uint32x4_t __ret_244; \	56055	uint32x4_t __ret_238; \
66120	__ret_244 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_244), (uint32x2_t)(vshrn_n_u64(__s1_244, __p2_244)))); \	56056	__ret_238 = (uint32x4_t)(vcombine_u32((uint32x2_t)(__s0_238), (uint32x2_t)(vshrn_n_u64(__s1_238, __p2_238)))); \
66121	__ret_244; \	56057	__ret_238; \
66122	})	56058	})
66123	#else	56059	#else
66124	#define vshrn_high_n_u64(__p0_245, __p1_245, __p2_245) __extension__ ({ \	56060	#define vshrn_high_n_u64(__p0_239, __p1_239, __p2_239) __extension__ ({ \
66125	uint32x2_t __s0_245 = __p0_245; \	56061	uint32x2_t __s0_239 = __p0_239; \
66126	uint64x2_t __s1_245 = __p1_245; \	56062	uint64x2_t __s1_239 = __p1_239; \
66127	uint32x2_t __rev0_245; __rev0_245 = __builtin_shufflevector(__s0_245, __s0_245, 1, 0); \	56063	uint32x2_t __rev0_239; __rev0_239 = __builtin_shufflevector(__s0_239, __s0_239, 1, 0); \
66128	uint64x2_t __rev1_245; __rev1_245 = __builtin_shufflevector(__s1_245, __s1_245, 1, 0); \	56064	uint64x2_t __rev1_239; __rev1_239 = __builtin_shufflevector(__s1_239, __s1_239, 1, 0); \
66129	uint32x4_t __ret_245; \	56065	uint32x4_t __ret_239; \
66130	__ret_245 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_245), (uint32x2_t)(__noswap_vshrn_n_u64(__rev1_245, __p2_245)))); \	56066	__ret_239 = (uint32x4_t)(__noswap_vcombine_u32((uint32x2_t)(__rev0_239), (uint32x2_t)(__noswap_vshrn_n_u64(__rev1_239, __p2_239)))); \
66131	__ret_245 = __builtin_shufflevector(__ret_245, __ret_245, 3, 2, 1, 0); \	56067	__ret_239 = __builtin_shufflevector(__ret_239, __ret_239, 3, 2, 1, 0); \
66132	__ret_245; \	56068	__ret_239; \
66133	})	56069	})
66134	#endif	56070	#endif
66135		56071
66136	#ifdef __LITTLE_ENDIAN__	56072	#ifdef __LITTLE_ENDIAN__
66137	#define vshrn_high_n_u16(__p0_246, __p1_246, __p2_246) __extension__ ({ \	56073	#define vshrn_high_n_u16(__p0_240, __p1_240, __p2_240) __extension__ ({ \
66138	uint8x8_t __s0_246 = __p0_246; \	56074	uint8x8_t __s0_240 = __p0_240; \
66139	uint16x8_t __s1_246 = __p1_246; \	56075	uint16x8_t __s1_240 = __p1_240; \
66140	uint8x16_t __ret_246; \	56076	uint8x16_t __ret_240; \
66141	__ret_246 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_246), (uint8x8_t)(vshrn_n_u16(__s1_246, __p2_246)))); \	56077	__ret_240 = (uint8x16_t)(vcombine_u8((uint8x8_t)(__s0_240), (uint8x8_t)(vshrn_n_u16(__s1_240, __p2_240)))); \
66142	__ret_246; \	56078	__ret_240; \
66143	})	56079	})
66144	#else	56080	#else
66145	#define vshrn_high_n_u16(__p0_247, __p1_247, __p2_247) __extension__ ({ \	56081	#define vshrn_high_n_u16(__p0_241, __p1_241, __p2_241) __extension__ ({ \
66146	uint8x8_t __s0_247 = __p0_247; \	56082	uint8x8_t __s0_241 = __p0_241; \
66147	uint16x8_t __s1_247 = __p1_247; \	56083	uint16x8_t __s1_241 = __p1_241; \
66148	uint8x8_t __rev0_247; __rev0_247 = __builtin_shufflevector(__s0_247, __s0_247, 7, 6, 5, 4, 3, 2, 1, 0); \	56084	uint8x8_t __rev0_241; __rev0_241 = __builtin_shufflevector(__s0_241, __s0_241, 7, 6, 5, 4, 3, 2, 1, 0); \
66149	uint16x8_t __rev1_247; __rev1_247 = __builtin_shufflevector(__s1_247, __s1_247, 7, 6, 5, 4, 3, 2, 1, 0); \	56085	uint16x8_t __rev1_241; __rev1_241 = __builtin_shufflevector(__s1_241, __s1_241, 7, 6, 5, 4, 3, 2, 1, 0); \
66150	uint8x16_t __ret_247; \	56086	uint8x16_t __ret_241; \
66151	__ret_247 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_247), (uint8x8_t)(__noswap_vshrn_n_u16(__rev1_247, __p2_247)))); \	56087	__ret_241 = (uint8x16_t)(__noswap_vcombine_u8((uint8x8_t)(__rev0_241), (uint8x8_t)(__noswap_vshrn_n_u16(__rev1_241, __p2_241)))); \
66152	__ret_247 = __builtin_shufflevector(__ret_247, __ret_247, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	56088	__ret_241 = __builtin_shufflevector(__ret_241, __ret_241, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
66153	__ret_247; \	56089	__ret_241; \
66154	})	56090	})
66155	#endif	56091	#endif
66156		56092
66157	#ifdef __LITTLE_ENDIAN__	56093	#ifdef __LITTLE_ENDIAN__
66158	#define vshrn_high_n_s32(__p0_248, __p1_248, __p2_248) __extension__ ({ \	56094	#define vshrn_high_n_s32(__p0_242, __p1_242, __p2_242) __extension__ ({ \
66159	int16x4_t __s0_248 = __p0_248; \	56095	int16x4_t __s0_242 = __p0_242; \
66160	int32x4_t __s1_248 = __p1_248; \	56096	int32x4_t __s1_242 = __p1_242; \
66161	int16x8_t __ret_248; \	56097	int16x8_t __ret_242; \
66162	__ret_248 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_248), (int16x4_t)(vshrn_n_s32(__s1_248, __p2_248)))); \	56098	__ret_242 = (int16x8_t)(vcombine_s16((int16x4_t)(__s0_242), (int16x4_t)(vshrn_n_s32(__s1_242, __p2_242)))); \
66163	__ret_248; \	56099	__ret_242; \
66164	})	56100	})
66165	#else	56101	#else
66166	#define vshrn_high_n_s32(__p0_249, __p1_249, __p2_249) __extension__ ({ \	56102	#define vshrn_high_n_s32(__p0_243, __p1_243, __p2_243) __extension__ ({ \
66167	int16x4_t __s0_249 = __p0_249; \	56103	int16x4_t __s0_243 = __p0_243; \
66168	int32x4_t __s1_249 = __p1_249; \	56104	int32x4_t __s1_243 = __p1_243; \
66169	int16x4_t __rev0_249; __rev0_249 = __builtin_shufflevector(__s0_249, __s0_249, 3, 2, 1, 0); \	56105	int16x4_t __rev0_243; __rev0_243 = __builtin_shufflevector(__s0_243, __s0_243, 3, 2, 1, 0); \
66170	int32x4_t __rev1_249; __rev1_249 = __builtin_shufflevector(__s1_249, __s1_249, 3, 2, 1, 0); \	56106	int32x4_t __rev1_243; __rev1_243 = __builtin_shufflevector(__s1_243, __s1_243, 3, 2, 1, 0); \
66171	int16x8_t __ret_249; \	56107	int16x8_t __ret_243; \
66172	__ret_249 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_249), (int16x4_t)(__noswap_vshrn_n_s32(__rev1_249, __p2_249)))); \	56108	__ret_243 = (int16x8_t)(__noswap_vcombine_s16((int16x4_t)(__rev0_243), (int16x4_t)(__noswap_vshrn_n_s32(__rev1_243, __p2_243)))); \
66173	__ret_249 = __builtin_shufflevector(__ret_249, __ret_249, 7, 6, 5, 4, 3, 2, 1, 0); \	56109	__ret_243 = __builtin_shufflevector(__ret_243, __ret_243, 7, 6, 5, 4, 3, 2, 1, 0); \
66174	__ret_249; \	56110	__ret_243; \
66175	})	56111	})
66176	#endif	56112	#endif
66177		56113
66178	#ifdef __LITTLE_ENDIAN__	56114	#ifdef __LITTLE_ENDIAN__
66179	#define vshrn_high_n_s64(__p0_250, __p1_250, __p2_250) __extension__ ({ \	56115	#define vshrn_high_n_s64(__p0_244, __p1_244, __p2_244) __extension__ ({ \
66180	int32x2_t __s0_250 = __p0_250; \	56116	int32x2_t __s0_244 = __p0_244; \
66181	int64x2_t __s1_250 = __p1_250; \	56117	int64x2_t __s1_244 = __p1_244; \
66182	int32x4_t __ret_250; \	56118	int32x4_t __ret_244; \
66183	__ret_250 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_250), (int32x2_t)(vshrn_n_s64(__s1_250, __p2_250)))); \	56119	__ret_244 = (int32x4_t)(vcombine_s32((int32x2_t)(__s0_244), (int32x2_t)(vshrn_n_s64(__s1_244, __p2_244)))); \
66184	__ret_250; \	56120	__ret_244; \
66185	})	56121	})
66186	#else	56122	#else
66187	#define vshrn_high_n_s64(__p0_251, __p1_251, __p2_251) __extension__ ({ \	56123	#define vshrn_high_n_s64(__p0_245, __p1_245, __p2_245) __extension__ ({ \
66188	int32x2_t __s0_251 = __p0_251; \	56124	int32x2_t __s0_245 = __p0_245; \
66189	int64x2_t __s1_251 = __p1_251; \	56125	int64x2_t __s1_245 = __p1_245; \
66190	int32x2_t __rev0_251; __rev0_251 = __builtin_shufflevector(__s0_251, __s0_251, 1, 0); \	56126	int32x2_t __rev0_245; __rev0_245 = __builtin_shufflevector(__s0_245, __s0_245, 1, 0); \
66191	int64x2_t __rev1_251; __rev1_251 = __builtin_shufflevector(__s1_251, __s1_251, 1, 0); \	56127	int64x2_t __rev1_245; __rev1_245 = __builtin_shufflevector(__s1_245, __s1_245, 1, 0); \
66192	int32x4_t __ret_251; \	56128	int32x4_t __ret_245; \
66193	__ret_251 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_251), (int32x2_t)(__noswap_vshrn_n_s64(__rev1_251, __p2_251)))); \	56129	__ret_245 = (int32x4_t)(__noswap_vcombine_s32((int32x2_t)(__rev0_245), (int32x2_t)(__noswap_vshrn_n_s64(__rev1_245, __p2_245)))); \
66194	__ret_251 = __builtin_shufflevector(__ret_251, __ret_251, 3, 2, 1, 0); \	56130	__ret_245 = __builtin_shufflevector(__ret_245, __ret_245, 3, 2, 1, 0); \
66195	__ret_251; \	56131	__ret_245; \
66196	})	56132	})
66197	#endif	56133	#endif
66198		56134
66199	#ifdef __LITTLE_ENDIAN__	56135	#ifdef __LITTLE_ENDIAN__
66200	#define vshrn_high_n_s16(__p0_252, __p1_252, __p2_252) __extension__ ({ \	56136	#define vshrn_high_n_s16(__p0_246, __p1_246, __p2_246) __extension__ ({ \
66201	int8x8_t __s0_252 = __p0_252; \	56137	int8x8_t __s0_246 = __p0_246; \
66202	int16x8_t __s1_252 = __p1_252; \	56138	int16x8_t __s1_246 = __p1_246; \
66203	int8x16_t __ret_252; \	56139	int8x16_t __ret_246; \
66204	__ret_252 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_252), (int8x8_t)(vshrn_n_s16(__s1_252, __p2_252)))); \	56140	__ret_246 = (int8x16_t)(vcombine_s8((int8x8_t)(__s0_246), (int8x8_t)(vshrn_n_s16(__s1_246, __p2_246)))); \
66205	__ret_252; \	56141	__ret_246; \
66206	})	56142	})
66207	#else	56143	#else
66208	#define vshrn_high_n_s16(__p0_253, __p1_253, __p2_253) __extension__ ({ \	56144	#define vshrn_high_n_s16(__p0_247, __p1_247, __p2_247) __extension__ ({ \
66209	int8x8_t __s0_253 = __p0_253; \	56145	int8x8_t __s0_247 = __p0_247; \
66210	int16x8_t __s1_253 = __p1_253; \	56146	int16x8_t __s1_247 = __p1_247; \
66211	int8x8_t __rev0_253; __rev0_253 = __builtin_shufflevector(__s0_253, __s0_253, 7, 6, 5, 4, 3, 2, 1, 0); \	56147	int8x8_t __rev0_247; __rev0_247 = __builtin_shufflevector(__s0_247, __s0_247, 7, 6, 5, 4, 3, 2, 1, 0); \
66212	int16x8_t __rev1_253; __rev1_253 = __builtin_shufflevector(__s1_253, __s1_253, 7, 6, 5, 4, 3, 2, 1, 0); \	56148	int16x8_t __rev1_247; __rev1_247 = __builtin_shufflevector(__s1_247, __s1_247, 7, 6, 5, 4, 3, 2, 1, 0); \
66213	int8x16_t __ret_253; \	56149	int8x16_t __ret_247; \
66214	__ret_253 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_253), (int8x8_t)(__noswap_vshrn_n_s16(__rev1_253, __p2_253)))); \	56150	__ret_247 = (int8x16_t)(__noswap_vcombine_s8((int8x8_t)(__rev0_247), (int8x8_t)(__noswap_vshrn_n_s16(__rev1_247, __p2_247)))); \
66215	__ret_253 = __builtin_shufflevector(__ret_253, __ret_253, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \	56151	__ret_247 = __builtin_shufflevector(__ret_247, __ret_247, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0); \
66216	__ret_253; \	56152	__ret_247; \
66217	})	56153	})
66218	#endif	56154	#endif
66219		56155
66220	#ifdef __LITTLE_ENDIAN__
66221	#define vslid_n_u64(__p0, __p1, __p2) __extension__ ({ \
66222	uint64_t __s0 = __p0; \
66223	uint64_t __s1 = __p1; \
66224	uint64_t __ret; \
66225	__ret = (uint64_t) __builtin_neon_vslid_n_u64(__s0, __s1, __p2); \
66226	__ret; \
66227	})
66228	#else
66229	#define vslid_n_u64(__p0, __p1, __p2) __extension__ ({ \	56156	#define vslid_n_u64(__p0, __p1, __p2) __extension__ ({ \
66230	uint64_t __s0 = __p0; \	56157	uint64_t __s0 = __p0; \
66231	uint64_t __s1 = __p1; \	56158	uint64_t __s1 = __p1; \
...	@@ -66233,17 +56160,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {	...	@@ -66233,17 +56160,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
66233	__ret = (uint64_t) __builtin_neon_vslid_n_u64(__s0, __s1, __p2); \	56160	__ret = (uint64_t) __builtin_neon_vslid_n_u64(__s0, __s1, __p2); \
66234	__ret; \	56161	__ret; \
66235	})	56162	})
66236	#endif
66237
66238	#ifdef __LITTLE_ENDIAN__
66239	#define vslid_n_s64(__p0, __p1, __p2) __extension__ ({ \
66240	int64_t __s0 = __p0; \
66241	int64_t __s1 = __p1; \
66242	int64_t __ret; \
66243	__ret = (int64_t) __builtin_neon_vslid_n_s64(__s0, __s1, __p2); \
66244	__ret; \
66245	})
66246	#else
66247	#define vslid_n_s64(__p0, __p1, __p2) __extension__ ({ \	56163	#define vslid_n_s64(__p0, __p1, __p2) __extension__ ({ \
66248	int64_t __s0 = __p0; \	56164	int64_t __s0 = __p0; \
66249	int64_t __s1 = __p1; \	56165	int64_t __s1 = __p1; \
...	@@ -66251,17 +56167,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {	...	@@ -66251,17 +56167,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
66251	__ret = (int64_t) __builtin_neon_vslid_n_s64(__s0, __s1, __p2); \	56167	__ret = (int64_t) __builtin_neon_vslid_n_s64(__s0, __s1, __p2); \
66252	__ret; \	56168	__ret; \
66253	})	56169	})
66254	#endif
66255
66256	#ifdef __LITTLE_ENDIAN__
66257	#define vsli_n_p64(__p0, __p1, __p2) __extension__ ({ \
66258	poly64x1_t __s0 = __p0; \
66259	poly64x1_t __s1 = __p1; \
66260	poly64x1_t __ret; \
66261	__ret = (poly64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
66262	__ret; \
66263	})
66264	#else
66265	#define vsli_n_p64(__p0, __p1, __p2) __extension__ ({ \	56170	#define vsli_n_p64(__p0, __p1, __p2) __extension__ ({ \
66266	poly64x1_t __s0 = __p0; \	56171	poly64x1_t __s0 = __p0; \
66267	poly64x1_t __s1 = __p1; \	56172	poly64x1_t __s1 = __p1; \
...	@@ -66269,8 +56174,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {	...	@@ -66269,8 +56174,6 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
66269	__ret = (poly64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \	56174	__ret = (poly64x1_t) __builtin_neon_vsli_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
66270	__ret; \	56175	__ret; \
66271	})	56176	})
66272	#endif
66273
66274	#ifdef __LITTLE_ENDIAN__	56177	#ifdef __LITTLE_ENDIAN__
66275	#define vsliq_n_p64(__p0, __p1, __p2) __extension__ ({ \	56178	#define vsliq_n_p64(__p0, __p1, __p2) __extension__ ({ \
66276	poly64x2_t __s0 = __p0; \	56179	poly64x2_t __s0 = __p0; \
...	@@ -66292,62 +56195,26 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {	...	@@ -66292,62 +56195,26 @@ __ai int64_t vshld_s64(int64_t __p0, int64_t __p1) {
66292	})	56195	})
66293	#endif	56196	#endif
66294		56197
66295	#ifdef __LITTLE_ENDIAN__
66296	__ai uint8_t vsqaddb_u8(uint8_t __p0, int8_t __p1) {
66297	uint8_t __ret;
66298	__ret = (uint8_t) __builtin_neon_vsqaddb_u8(__p0, __p1);
66299	return __ret;
66300	}
66301	#else
66302	__ai uint8_t vsqaddb_u8(uint8_t __p0, int8_t __p1) {	56198	__ai uint8_t vsqaddb_u8(uint8_t __p0, int8_t __p1) {
66303	uint8_t __ret;	56199	uint8_t __ret;
66304	__ret = (uint8_t) __builtin_neon_vsqaddb_u8(__p0, __p1);	56200	__ret = (uint8_t) __builtin_neon_vsqaddb_u8(__p0, __p1);
66305	return __ret;	56201	return __ret;
66306	}	56202	}
66307	#endif
66308
66309	#ifdef __LITTLE_ENDIAN__
66310	__ai uint32_t vsqadds_u32(uint32_t __p0, int32_t __p1) {
66311	uint32_t __ret;
66312	__ret = (uint32_t) __builtin_neon_vsqadds_u32(__p0, __p1);
66313	return __ret;
66314	}
66315	#else
66316	__ai uint32_t vsqadds_u32(uint32_t __p0, int32_t __p1) {	56203	__ai uint32_t vsqadds_u32(uint32_t __p0, int32_t __p1) {
66317	uint32_t __ret;	56204	uint32_t __ret;
66318	__ret = (uint32_t) __builtin_neon_vsqadds_u32(__p0, __p1);	56205	__ret = (uint32_t) __builtin_neon_vsqadds_u32(__p0, __p1);
66319	return __ret;	56206	return __ret;
66320	}	56207	}
66321	#endif
66322
66323	#ifdef __LITTLE_ENDIAN__
66324	__ai uint64_t vsqaddd_u64(uint64_t __p0, int64_t __p1) {
66325	uint64_t __ret;
66326	__ret = (uint64_t) __builtin_neon_vsqaddd_u64(__p0, __p1);
66327	return __ret;
66328	}
66329	#else
66330	__ai uint64_t vsqaddd_u64(uint64_t __p0, int64_t __p1) {	56208	__ai uint64_t vsqaddd_u64(uint64_t __p0, int64_t __p1) {
66331	uint64_t __ret;	56209	uint64_t __ret;
66332	__ret = (uint64_t) __builtin_neon_vsqaddd_u64(__p0, __p1);	56210	__ret = (uint64_t) __builtin_neon_vsqaddd_u64(__p0, __p1);
66333	return __ret;	56211	return __ret;
66334	}	56212	}
66335	#endif
66336
66337	#ifdef __LITTLE_ENDIAN__
66338	__ai uint16_t vsqaddh_u16(uint16_t __p0, int16_t __p1) {
66339	uint16_t __ret;
66340	__ret = (uint16_t) __builtin_neon_vsqaddh_u16(__p0, __p1);
66341	return __ret;
66342	}
66343	#else
66344	__ai uint16_t vsqaddh_u16(uint16_t __p0, int16_t __p1) {	56213	__ai uint16_t vsqaddh_u16(uint16_t __p0, int16_t __p1) {
66345	uint16_t __ret;	56214	uint16_t __ret;
66346	__ret = (uint16_t) __builtin_neon_vsqaddh_u16(__p0, __p1);	56215	__ret = (uint16_t) __builtin_neon_vsqaddh_u16(__p0, __p1);
66347	return __ret;	56216	return __ret;
66348	}	56217	}
66349	#endif
66350
66351	#ifdef __LITTLE_ENDIAN__	56218	#ifdef __LITTLE_ENDIAN__
66352	__ai uint8x16_t vsqaddq_u8(uint8x16_t __p0, int8x16_t __p1) {	56219	__ai uint8x16_t vsqaddq_u8(uint8x16_t __p0, int8x16_t __p1) {
66353	uint8x16_t __ret;	56220	uint8x16_t __ret;
...	@@ -66450,20 +56317,11 @@ __ai uint32x2_t vsqadd_u32(uint32x2_t __p0, int32x2_t __p1) {	...	@@ -66450,20 +56317,11 @@ __ai uint32x2_t vsqadd_u32(uint32x2_t __p0, int32x2_t __p1) {
66450	}	56317	}
66451	#endif	56318	#endif
66452		56319
66453	#ifdef __LITTLE_ENDIAN__
66454	__ai uint64x1_t vsqadd_u64(uint64x1_t __p0, int64x1_t __p1) {
66455	uint64x1_t __ret;
66456	__ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
66457	return __ret;
66458	}
66459	#else
66460	__ai uint64x1_t vsqadd_u64(uint64x1_t __p0, int64x1_t __p1) {	56320	__ai uint64x1_t vsqadd_u64(uint64x1_t __p0, int64x1_t __p1) {
66461	uint64x1_t __ret;	56321	uint64x1_t __ret;
66462	__ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	56322	__ret = (uint64x1_t) __builtin_neon_vsqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
66463	return __ret;	56323	return __ret;
66464	}	56324	}
66465	#endif
66466
66467	#ifdef __LITTLE_ENDIAN__	56325	#ifdef __LITTLE_ENDIAN__
66468	__ai uint16x4_t vsqadd_u16(uint16x4_t __p0, int16x4_t __p1) {	56326	__ai uint16x4_t vsqadd_u16(uint16x4_t __p0, int16x4_t __p1) {
66469	uint16x4_t __ret;	56327	uint16x4_t __ret;
...	@@ -66513,20 +56371,11 @@ __ai float32x4_t vsqrtq_f32(float32x4_t __p0) {	...	@@ -66513,20 +56371,11 @@ __ai float32x4_t vsqrtq_f32(float32x4_t __p0) {
66513	}	56371	}
66514	#endif	56372	#endif
66515		56373
66516	#ifdef __LITTLE_ENDIAN__
66517	__ai float64x1_t vsqrt_f64(float64x1_t __p0) {
66518	float64x1_t __ret;
66519	__ret = (float64x1_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 10);
66520	return __ret;
66521	}
66522	#else
66523	__ai float64x1_t vsqrt_f64(float64x1_t __p0) {	56374	__ai float64x1_t vsqrt_f64(float64x1_t __p0) {
66524	float64x1_t __ret;	56375	float64x1_t __ret;
66525	__ret = (float64x1_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 10);	56376	__ret = (float64x1_t) __builtin_neon_vsqrt_v((int8x8_t)__p0, 10);
66526	return __ret;	56377	return __ret;
66527	}	56378	}
66528	#endif
66529
66530	#ifdef __LITTLE_ENDIAN__	56379	#ifdef __LITTLE_ENDIAN__
66531	__ai float32x2_t vsqrt_f32(float32x2_t __p0) {	56380	__ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66532	float32x2_t __ret;	56381	float32x2_t __ret;
...	@@ -66543,7 +56392,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66543,7 +56392,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66543	}	56392	}
66544	#endif	56393	#endif
66545		56394
66546	#ifdef __LITTLE_ENDIAN__
66547	#define vsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \	56395	#define vsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
66548	uint64_t __s0 = __p0; \	56396	uint64_t __s0 = __p0; \
66549	uint64_t __s1 = __p1; \	56397	uint64_t __s1 = __p1; \
...	@@ -66551,25 +56399,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66551,25 +56399,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66551	__ret = (uint64_t) __builtin_neon_vsrad_n_u64(__s0, __s1, __p2); \	56399	__ret = (uint64_t) __builtin_neon_vsrad_n_u64(__s0, __s1, __p2); \
66552	__ret; \	56400	__ret; \
66553	})	56401	})
66554	#else
66555	#define vsrad_n_u64(__p0, __p1, __p2) __extension__ ({ \
66556	uint64_t __s0 = __p0; \
66557	uint64_t __s1 = __p1; \
66558	uint64_t __ret; \
66559	__ret = (uint64_t) __builtin_neon_vsrad_n_u64(__s0, __s1, __p2); \
66560	__ret; \
66561	})
66562	#endif
66563
66564	#ifdef __LITTLE_ENDIAN__
66565	#define vsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
66566	int64_t __s0 = __p0; \
66567	int64_t __s1 = __p1; \
66568	int64_t __ret; \
66569	__ret = (int64_t) __builtin_neon_vsrad_n_s64(__s0, __s1, __p2); \
66570	__ret; \
66571	})
66572	#else
66573	#define vsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \	56402	#define vsrad_n_s64(__p0, __p1, __p2) __extension__ ({ \
66574	int64_t __s0 = __p0; \	56403	int64_t __s0 = __p0; \
66575	int64_t __s1 = __p1; \	56404	int64_t __s1 = __p1; \
...	@@ -66577,17 +56406,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66577,17 +56406,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66577	__ret = (int64_t) __builtin_neon_vsrad_n_s64(__s0, __s1, __p2); \	56406	__ret = (int64_t) __builtin_neon_vsrad_n_s64(__s0, __s1, __p2); \
66578	__ret; \	56407	__ret; \
66579	})	56408	})
66580	#endif
66581
66582	#ifdef __LITTLE_ENDIAN__
66583	#define vsrid_n_u64(__p0, __p1, __p2) __extension__ ({ \
66584	uint64_t __s0 = __p0; \
66585	uint64_t __s1 = __p1; \
66586	uint64_t __ret; \
66587	__ret = (uint64_t) __builtin_neon_vsrid_n_u64(__s0, __s1, __p2); \
66588	__ret; \
66589	})
66590	#else
66591	#define vsrid_n_u64(__p0, __p1, __p2) __extension__ ({ \	56409	#define vsrid_n_u64(__p0, __p1, __p2) __extension__ ({ \
66592	uint64_t __s0 = __p0; \	56410	uint64_t __s0 = __p0; \
66593	uint64_t __s1 = __p1; \	56411	uint64_t __s1 = __p1; \
...	@@ -66595,17 +56413,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66595,17 +56413,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66595	__ret = (uint64_t) __builtin_neon_vsrid_n_u64(__s0, __s1, __p2); \	56413	__ret = (uint64_t) __builtin_neon_vsrid_n_u64(__s0, __s1, __p2); \
66596	__ret; \	56414	__ret; \
66597	})	56415	})
66598	#endif
66599
66600	#ifdef __LITTLE_ENDIAN__
66601	#define vsrid_n_s64(__p0, __p1, __p2) __extension__ ({ \
66602	int64_t __s0 = __p0; \
66603	int64_t __s1 = __p1; \
66604	int64_t __ret; \
66605	__ret = (int64_t) __builtin_neon_vsrid_n_s64(__s0, __s1, __p2); \
66606	__ret; \
66607	})
66608	#else
66609	#define vsrid_n_s64(__p0, __p1, __p2) __extension__ ({ \	56416	#define vsrid_n_s64(__p0, __p1, __p2) __extension__ ({ \
66610	int64_t __s0 = __p0; \	56417	int64_t __s0 = __p0; \
66611	int64_t __s1 = __p1; \	56418	int64_t __s1 = __p1; \
...	@@ -66613,17 +56420,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66613,17 +56420,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66613	__ret = (int64_t) __builtin_neon_vsrid_n_s64(__s0, __s1, __p2); \	56420	__ret = (int64_t) __builtin_neon_vsrid_n_s64(__s0, __s1, __p2); \
66614	__ret; \	56421	__ret; \
66615	})	56422	})
66616	#endif
66617
66618	#ifdef __LITTLE_ENDIAN__
66619	#define vsri_n_p64(__p0, __p1, __p2) __extension__ ({ \
66620	poly64x1_t __s0 = __p0; \
66621	poly64x1_t __s1 = __p1; \
66622	poly64x1_t __ret; \
66623	__ret = (poly64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
66624	__ret; \
66625	})
66626	#else
66627	#define vsri_n_p64(__p0, __p1, __p2) __extension__ ({ \	56423	#define vsri_n_p64(__p0, __p1, __p2) __extension__ ({ \
66628	poly64x1_t __s0 = __p0; \	56424	poly64x1_t __s0 = __p0; \
66629	poly64x1_t __s1 = __p1; \	56425	poly64x1_t __s1 = __p1; \
...	@@ -66631,8 +56427,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66631,8 +56427,6 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66631	__ret = (poly64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \	56427	__ret = (poly64x1_t) __builtin_neon_vsri_n_v((int8x8_t)__s0, (int8x8_t)__s1, __p2, 6); \
66632	__ret; \	56428	__ret; \
66633	})	56429	})
66634	#endif
66635
66636	#ifdef __LITTLE_ENDIAN__	56430	#ifdef __LITTLE_ENDIAN__
66637	#define vsriq_n_p64(__p0, __p1, __p2) __extension__ ({ \	56431	#define vsriq_n_p64(__p0, __p1, __p2) __extension__ ({ \
66638	poly64x2_t __s0 = __p0; \	56432	poly64x2_t __s0 = __p0; \
...	@@ -66654,18 +56448,10 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66654,18 +56448,10 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66654	})	56448	})
66655	#endif	56449	#endif
66656		56450
66657	#ifdef __LITTLE_ENDIAN__
66658	#define vst1_p64(__p0, __p1) __extension__ ({ \
66659	poly64x1_t __s1 = __p1; \
66660	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 6); \
66661	})
66662	#else
66663	#define vst1_p64(__p0, __p1) __extension__ ({ \	56451	#define vst1_p64(__p0, __p1) __extension__ ({ \
66664	poly64x1_t __s1 = __p1; \	56452	poly64x1_t __s1 = __p1; \
66665	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 6); \	56453	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 6); \
66666	})	56454	})
66667	#endif
66668
66669	#ifdef __LITTLE_ENDIAN__	56455	#ifdef __LITTLE_ENDIAN__
66670	#define vst1q_p64(__p0, __p1) __extension__ ({ \	56456	#define vst1q_p64(__p0, __p1) __extension__ ({ \
66671	poly64x2_t __s1 = __p1; \	56457	poly64x2_t __s1 = __p1; \
...	@@ -66692,30 +56478,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66692,30 +56478,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66692	})	56478	})
66693	#endif	56479	#endif
66694		56480
66695	#ifdef __LITTLE_ENDIAN__
66696	#define vst1_f64(__p0, __p1) __extension__ ({ \
66697	float64x1_t __s1 = __p1; \
66698	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 10); \
66699	})
66700	#else
66701	#define vst1_f64(__p0, __p1) __extension__ ({ \	56481	#define vst1_f64(__p0, __p1) __extension__ ({ \
66702	float64x1_t __s1 = __p1; \	56482	float64x1_t __s1 = __p1; \
66703	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 10); \	56483	__builtin_neon_vst1_v(__p0, (int8x8_t)__s1, 10); \
66704	})	56484	})
66705	#endif
66706
66707	#ifdef __LITTLE_ENDIAN__
66708	#define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
66709	poly64x1_t __s1 = __p1; \
66710	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
66711	})
66712	#else
66713	#define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({ \	56485	#define vst1_lane_p64(__p0, __p1, __p2) __extension__ ({ \
66714	poly64x1_t __s1 = __p1; \	56486	poly64x1_t __s1 = __p1; \
66715	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \	56487	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 6); \
66716	})	56488	})
66717	#endif
66718
66719	#ifdef __LITTLE_ENDIAN__	56489	#ifdef __LITTLE_ENDIAN__
66720	#define vst1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \	56490	#define vst1q_lane_p64(__p0, __p1, __p2) __extension__ ({ \
66721	poly64x2_t __s1 = __p1; \	56491	poly64x2_t __s1 = __p1; \
...	@@ -66742,30 +56512,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66742,30 +56512,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66742	})	56512	})
66743	#endif	56513	#endif
66744		56514
66745	#ifdef __LITTLE_ENDIAN__
66746	#define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
66747	float64x1_t __s1 = __p1; \
66748	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
66749	})
66750	#else
66751	#define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56515	#define vst1_lane_f64(__p0, __p1, __p2) __extension__ ({ \
66752	float64x1_t __s1 = __p1; \	56516	float64x1_t __s1 = __p1; \
66753	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \	56517	__builtin_neon_vst1_lane_v(__p0, (int8x8_t)__s1, __p2, 10); \
66754	})	56518	})
66755	#endif
66756
66757	#ifdef __LITTLE_ENDIAN__
66758	#define vst1_p64_x2(__p0, __p1) __extension__ ({ \
66759	poly64x1x2_t __s1 = __p1; \
66760	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
66761	})
66762	#else
66763	#define vst1_p64_x2(__p0, __p1) __extension__ ({ \	56519	#define vst1_p64_x2(__p0, __p1) __extension__ ({ \
66764	poly64x1x2_t __s1 = __p1; \	56520	poly64x1x2_t __s1 = __p1; \
66765	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \	56521	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
66766	})	56522	})
66767	#endif
66768
66769	#ifdef __LITTLE_ENDIAN__	56523	#ifdef __LITTLE_ENDIAN__
66770	#define vst1q_p64_x2(__p0, __p1) __extension__ ({ \	56524	#define vst1q_p64_x2(__p0, __p1) __extension__ ({ \
66771	poly64x2x2_t __s1 = __p1; \	56525	poly64x2x2_t __s1 = __p1; \
...	@@ -66784,7 +56538,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66784,7 +56538,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66784	#ifdef __LITTLE_ENDIAN__	56538	#ifdef __LITTLE_ENDIAN__
66785	#define vst1q_f64_x2(__p0, __p1) __extension__ ({ \	56539	#define vst1q_f64_x2(__p0, __p1) __extension__ ({ \
66786	float64x2x2_t __s1 = __p1; \	56540	float64x2x2_t __s1 = __p1; \
66787	__builtin_neon_vst1q_x2_v(__p0, __s1.val[0], __s1.val[1], 42); \	56541	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 42); \
66788	})	56542	})
66789	#else	56543	#else
66790	#define vst1q_f64_x2(__p0, __p1) __extension__ ({ \	56544	#define vst1q_f64_x2(__p0, __p1) __extension__ ({ \
...	@@ -66792,34 +56546,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66792,34 +56546,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66792	float64x2x2_t __rev1; \	56546	float64x2x2_t __rev1; \
66793	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56547	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
66794	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56548	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
66795	__builtin_neon_vst1q_x2_v(__p0, __rev1.val[0], __rev1.val[1], 42); \	56549	__builtin_neon_vst1q_x2_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 42); \
66796	})	56550	})
66797	#endif	56551	#endif
66798		56552
66799	#ifdef __LITTLE_ENDIAN__
66800	#define vst1_f64_x2(__p0, __p1) __extension__ ({ \	56553	#define vst1_f64_x2(__p0, __p1) __extension__ ({ \
66801	float64x1x2_t __s1 = __p1; \	56554	float64x1x2_t __s1 = __p1; \
66802	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 10); \	56555	__builtin_neon_vst1_x2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 10); \
66803	})
66804	#else
66805	#define vst1_f64_x2(__p0, __p1) __extension__ ({ \
66806	float64x1x2_t __s1 = __p1; \
66807	__builtin_neon_vst1_x2_v(__p0, __s1.val[0], __s1.val[1], 10); \
66808	})
66809	#endif
66810
66811	#ifdef __LITTLE_ENDIAN__
66812	#define vst1_p64_x3(__p0, __p1) __extension__ ({ \
66813	poly64x1x3_t __s1 = __p1; \
66814	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
66815	})	56556	})
66816	#else
66817	#define vst1_p64_x3(__p0, __p1) __extension__ ({ \	56557	#define vst1_p64_x3(__p0, __p1) __extension__ ({ \
66818	poly64x1x3_t __s1 = __p1; \	56558	poly64x1x3_t __s1 = __p1; \
66819	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \	56559	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
66820	})	56560	})
66821	#endif
66822
66823	#ifdef __LITTLE_ENDIAN__	56561	#ifdef __LITTLE_ENDIAN__
66824	#define vst1q_p64_x3(__p0, __p1) __extension__ ({ \	56562	#define vst1q_p64_x3(__p0, __p1) __extension__ ({ \
66825	poly64x2x3_t __s1 = __p1; \	56563	poly64x2x3_t __s1 = __p1; \
...	@@ -66839,7 +56577,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66839,7 +56577,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66839	#ifdef __LITTLE_ENDIAN__	56577	#ifdef __LITTLE_ENDIAN__
66840	#define vst1q_f64_x3(__p0, __p1) __extension__ ({ \	56578	#define vst1q_f64_x3(__p0, __p1) __extension__ ({ \
66841	float64x2x3_t __s1 = __p1; \	56579	float64x2x3_t __s1 = __p1; \
66842	__builtin_neon_vst1q_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 42); \	56580	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 42); \
66843	})	56581	})
66844	#else	56582	#else
66845	#define vst1q_f64_x3(__p0, __p1) __extension__ ({ \	56583	#define vst1q_f64_x3(__p0, __p1) __extension__ ({ \
...	@@ -66848,34 +56586,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66848,34 +56586,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66848	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56586	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
66849	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56587	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
66850	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	56588	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
66851	__builtin_neon_vst1q_x3_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 42); \	56589	__builtin_neon_vst1q_x3_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 42); \
66852	})	56590	})
66853	#endif	56591	#endif
66854		56592
66855	#ifdef __LITTLE_ENDIAN__
66856	#define vst1_f64_x3(__p0, __p1) __extension__ ({ \	56593	#define vst1_f64_x3(__p0, __p1) __extension__ ({ \
66857	float64x1x3_t __s1 = __p1; \	56594	float64x1x3_t __s1 = __p1; \
66858	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 10); \	56595	__builtin_neon_vst1_x3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 10); \
66859	})	56596	})
66860	#else
66861	#define vst1_f64_x3(__p0, __p1) __extension__ ({ \
66862	float64x1x3_t __s1 = __p1; \
66863	__builtin_neon_vst1_x3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 10); \
66864	})
66865	#endif
66866
66867	#ifdef __LITTLE_ENDIAN__
66868	#define vst1_p64_x4(__p0, __p1) __extension__ ({ \
66869	poly64x1x4_t __s1 = __p1; \
66870	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
66871	})
66872	#else
66873	#define vst1_p64_x4(__p0, __p1) __extension__ ({ \	56597	#define vst1_p64_x4(__p0, __p1) __extension__ ({ \
66874	poly64x1x4_t __s1 = __p1; \	56598	poly64x1x4_t __s1 = __p1; \
66875	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \	56599	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
66876	})	56600	})
66877	#endif
66878
66879	#ifdef __LITTLE_ENDIAN__	56601	#ifdef __LITTLE_ENDIAN__
66880	#define vst1q_p64_x4(__p0, __p1) __extension__ ({ \	56602	#define vst1q_p64_x4(__p0, __p1) __extension__ ({ \
66881	poly64x2x4_t __s1 = __p1; \	56603	poly64x2x4_t __s1 = __p1; \
...	@@ -66896,7 +56618,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66896,7 +56618,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66896	#ifdef __LITTLE_ENDIAN__	56618	#ifdef __LITTLE_ENDIAN__
66897	#define vst1q_f64_x4(__p0, __p1) __extension__ ({ \	56619	#define vst1q_f64_x4(__p0, __p1) __extension__ ({ \
66898	float64x2x4_t __s1 = __p1; \	56620	float64x2x4_t __s1 = __p1; \
66899	__builtin_neon_vst1q_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 42); \	56621	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 42); \
66900	})	56622	})
66901	#else	56623	#else
66902	#define vst1q_f64_x4(__p0, __p1) __extension__ ({ \	56624	#define vst1q_f64_x4(__p0, __p1) __extension__ ({ \
...	@@ -66906,34 +56628,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66906,34 +56628,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66906	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56628	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
66907	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	56629	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
66908	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	56630	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
66909	__builtin_neon_vst1q_x4_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 42); \	56631	__builtin_neon_vst1q_x4_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 42); \
66910	})	56632	})
66911	#endif	56633	#endif
66912		56634
66913	#ifdef __LITTLE_ENDIAN__
66914	#define vst1_f64_x4(__p0, __p1) __extension__ ({ \	56635	#define vst1_f64_x4(__p0, __p1) __extension__ ({ \
66915	float64x1x4_t __s1 = __p1; \	56636	float64x1x4_t __s1 = __p1; \
66916	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 10); \	56637	__builtin_neon_vst1_x4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 10); \
66917	})
66918	#else
66919	#define vst1_f64_x4(__p0, __p1) __extension__ ({ \
66920	float64x1x4_t __s1 = __p1; \
66921	__builtin_neon_vst1_x4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 10); \
66922	})
66923	#endif
66924
66925	#ifdef __LITTLE_ENDIAN__
66926	#define vst2_p64(__p0, __p1) __extension__ ({ \
66927	poly64x1x2_t __s1 = __p1; \
66928	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
66929	})	56638	})
66930	#else
66931	#define vst2_p64(__p0, __p1) __extension__ ({ \	56639	#define vst2_p64(__p0, __p1) __extension__ ({ \
66932	poly64x1x2_t __s1 = __p1; \	56640	poly64x1x2_t __s1 = __p1; \
66933	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \	56641	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 6); \
66934	})	56642	})
66935	#endif
66936
66937	#ifdef __LITTLE_ENDIAN__	56643	#ifdef __LITTLE_ENDIAN__
66938	#define vst2q_p64(__p0, __p1) __extension__ ({ \	56644	#define vst2q_p64(__p0, __p1) __extension__ ({ \
66939	poly64x2x2_t __s1 = __p1; \	56645	poly64x2x2_t __s1 = __p1; \
...	@@ -66967,7 +56673,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66967,7 +56673,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66967	#ifdef __LITTLE_ENDIAN__	56673	#ifdef __LITTLE_ENDIAN__
66968	#define vst2q_f64(__p0, __p1) __extension__ ({ \	56674	#define vst2q_f64(__p0, __p1) __extension__ ({ \
66969	float64x2x2_t __s1 = __p1; \	56675	float64x2x2_t __s1 = __p1; \
66970	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 42); \	56676	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 42); \
66971	})	56677	})
66972	#else	56678	#else
66973	#define vst2q_f64(__p0, __p1) __extension__ ({ \	56679	#define vst2q_f64(__p0, __p1) __extension__ ({ \
...	@@ -66975,14 +56681,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66975,14 +56681,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66975	float64x2x2_t __rev1; \	56681	float64x2x2_t __rev1; \
66976	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56682	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
66977	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56683	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
66978	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 42); \	56684	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 42); \
66979	})	56685	})
66980	#endif	56686	#endif
66981		56687
66982	#ifdef __LITTLE_ENDIAN__	56688	#ifdef __LITTLE_ENDIAN__
66983	#define vst2q_s64(__p0, __p1) __extension__ ({ \	56689	#define vst2q_s64(__p0, __p1) __extension__ ({ \
66984	int64x2x2_t __s1 = __p1; \	56690	int64x2x2_t __s1 = __p1; \
66985	__builtin_neon_vst2q_v(__p0, __s1.val[0], __s1.val[1], 35); \	56691	__builtin_neon_vst2q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], 35); \
66986	})	56692	})
66987	#else	56693	#else
66988	#define vst2q_s64(__p0, __p1) __extension__ ({ \	56694	#define vst2q_s64(__p0, __p1) __extension__ ({ \
...	@@ -66990,34 +56696,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -66990,34 +56696,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
66990	int64x2x2_t __rev1; \	56696	int64x2x2_t __rev1; \
66991	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56697	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
66992	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56698	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
66993	__builtin_neon_vst2q_v(__p0, __rev1.val[0], __rev1.val[1], 35); \	56699	__builtin_neon_vst2q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], 35); \
66994	})	56700	})
66995	#endif	56701	#endif
66996		56702
66997	#ifdef __LITTLE_ENDIAN__
66998	#define vst2_f64(__p0, __p1) __extension__ ({ \	56703	#define vst2_f64(__p0, __p1) __extension__ ({ \
66999	float64x1x2_t __s1 = __p1; \	56704	float64x1x2_t __s1 = __p1; \
67000	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 10); \	56705	__builtin_neon_vst2_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], 10); \
67001	})
67002	#else
67003	#define vst2_f64(__p0, __p1) __extension__ ({ \
67004	float64x1x2_t __s1 = __p1; \
67005	__builtin_neon_vst2_v(__p0, __s1.val[0], __s1.val[1], 10); \
67006	})
67007	#endif
67008
67009	#ifdef __LITTLE_ENDIAN__
67010	#define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67011	poly64x1x2_t __s1 = __p1; \
67012	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
67013	})	56706	})
67014	#else
67015	#define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({ \	56707	#define vst2_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67016	poly64x1x2_t __s1 = __p1; \	56708	poly64x1x2_t __s1 = __p1; \
67017	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \	56709	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 6); \
67018	})	56710	})
67019	#endif
67020
67021	#ifdef __LITTLE_ENDIAN__	56711	#ifdef __LITTLE_ENDIAN__
67022	#define vst2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	56712	#define vst2q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
67023	poly8x16x2_t __s1 = __p1; \	56713	poly8x16x2_t __s1 = __p1; \
...	@@ -67096,7 +56786,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67096,7 +56786,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67096	#ifdef __LITTLE_ENDIAN__	56786	#ifdef __LITTLE_ENDIAN__
67097	#define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56787	#define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67098	float64x2x2_t __s1 = __p1; \	56788	float64x2x2_t __s1 = __p1; \
67099	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 42); \	56789	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 42); \
67100	})	56790	})
67101	#else	56791	#else
67102	#define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56792	#define vst2q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67104,14 +56794,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67104,14 +56794,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67104	float64x2x2_t __rev1; \	56794	float64x2x2_t __rev1; \
67105	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56795	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67106	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56796	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67107	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 42); \	56797	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 42); \
67108	})	56798	})
67109	#endif	56799	#endif
67110		56800
67111	#ifdef __LITTLE_ENDIAN__	56801	#ifdef __LITTLE_ENDIAN__
67112	#define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	56802	#define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67113	int64x2x2_t __s1 = __p1; \	56803	int64x2x2_t __s1 = __p1; \
67114	__builtin_neon_vst2q_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 35); \	56804	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], __p2, 35); \
67115	})	56805	})
67116	#else	56806	#else
67117	#define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	56807	#define vst2q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67119,58 +56809,26 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67119,58 +56809,26 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67119	int64x2x2_t __rev1; \	56809	int64x2x2_t __rev1; \
67120	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56810	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67121	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56811	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67122	__builtin_neon_vst2q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __p2, 35); \	56812	__builtin_neon_vst2q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], __p2, 35); \
67123	})	56813	})
67124	#endif	56814	#endif
67125		56815
67126	#ifdef __LITTLE_ENDIAN__
67127	#define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67128	uint64x1x2_t __s1 = __p1; \
67129	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
67130	})
67131	#else
67132	#define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({ \	56816	#define vst2_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67133	uint64x1x2_t __s1 = __p1; \	56817	uint64x1x2_t __s1 = __p1; \
67134	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \	56818	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 19); \
67135	})	56819	})
67136	#endif
67137
67138	#ifdef __LITTLE_ENDIAN__
67139	#define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67140	float64x1x2_t __s1 = __p1; \
67141	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 10); \
67142	})
67143	#else
67144	#define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56820	#define vst2_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67145	float64x1x2_t __s1 = __p1; \	56821	float64x1x2_t __s1 = __p1; \
67146	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 10); \	56822	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 10); \
67147	})
67148	#endif
67149
67150	#ifdef __LITTLE_ENDIAN__
67151	#define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67152	int64x1x2_t __s1 = __p1; \
67153	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 3); \
67154	})	56823	})
67155	#else
67156	#define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({ \	56824	#define vst2_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67157	int64x1x2_t __s1 = __p1; \	56825	int64x1x2_t __s1 = __p1; \
67158	__builtin_neon_vst2_lane_v(__p0, __s1.val[0], __s1.val[1], __p2, 3); \	56826	__builtin_neon_vst2_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], __p2, 3); \
67159	})
67160	#endif
67161
67162	#ifdef __LITTLE_ENDIAN__
67163	#define vst3_p64(__p0, __p1) __extension__ ({ \
67164	poly64x1x3_t __s1 = __p1; \
67165	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
67166	})	56827	})
67167	#else
67168	#define vst3_p64(__p0, __p1) __extension__ ({ \	56828	#define vst3_p64(__p0, __p1) __extension__ ({ \
67169	poly64x1x3_t __s1 = __p1; \	56829	poly64x1x3_t __s1 = __p1; \
67170	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \	56830	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 6); \
67171	})	56831	})
67172	#endif
67173
67174	#ifdef __LITTLE_ENDIAN__	56832	#ifdef __LITTLE_ENDIAN__
67175	#define vst3q_p64(__p0, __p1) __extension__ ({ \	56833	#define vst3q_p64(__p0, __p1) __extension__ ({ \
67176	poly64x2x3_t __s1 = __p1; \	56834	poly64x2x3_t __s1 = __p1; \
...	@@ -67206,7 +56864,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67206,7 +56864,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67206	#ifdef __LITTLE_ENDIAN__	56864	#ifdef __LITTLE_ENDIAN__
67207	#define vst3q_f64(__p0, __p1) __extension__ ({ \	56865	#define vst3q_f64(__p0, __p1) __extension__ ({ \
67208	float64x2x3_t __s1 = __p1; \	56866	float64x2x3_t __s1 = __p1; \
67209	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 42); \	56867	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 42); \
67210	})	56868	})
67211	#else	56869	#else
67212	#define vst3q_f64(__p0, __p1) __extension__ ({ \	56870	#define vst3q_f64(__p0, __p1) __extension__ ({ \
...	@@ -67215,14 +56873,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67215,14 +56873,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67215	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56873	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67216	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56874	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67217	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	56875	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67218	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 42); \	56876	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 42); \
67219	})	56877	})
67220	#endif	56878	#endif
67221		56879
67222	#ifdef __LITTLE_ENDIAN__	56880	#ifdef __LITTLE_ENDIAN__
67223	#define vst3q_s64(__p0, __p1) __extension__ ({ \	56881	#define vst3q_s64(__p0, __p1) __extension__ ({ \
67224	int64x2x3_t __s1 = __p1; \	56882	int64x2x3_t __s1 = __p1; \
67225	__builtin_neon_vst3q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 35); \	56883	__builtin_neon_vst3q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], 35); \
67226	})	56884	})
67227	#else	56885	#else
67228	#define vst3q_s64(__p0, __p1) __extension__ ({ \	56886	#define vst3q_s64(__p0, __p1) __extension__ ({ \
...	@@ -67231,34 +56889,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67231,34 +56889,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67231	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56889	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67232	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56890	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67233	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	56891	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67234	__builtin_neon_vst3q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], 35); \	56892	__builtin_neon_vst3q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], 35); \
67235	})	56893	})
67236	#endif	56894	#endif
67237		56895
67238	#ifdef __LITTLE_ENDIAN__
67239	#define vst3_f64(__p0, __p1) __extension__ ({ \	56896	#define vst3_f64(__p0, __p1) __extension__ ({ \
67240	float64x1x3_t __s1 = __p1; \	56897	float64x1x3_t __s1 = __p1; \
67241	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 10); \	56898	__builtin_neon_vst3_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], 10); \
67242	})
67243	#else
67244	#define vst3_f64(__p0, __p1) __extension__ ({ \
67245	float64x1x3_t __s1 = __p1; \
67246	__builtin_neon_vst3_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], 10); \
67247	})
67248	#endif
67249
67250	#ifdef __LITTLE_ENDIAN__
67251	#define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67252	poly64x1x3_t __s1 = __p1; \
67253	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
67254	})	56899	})
67255	#else
67256	#define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({ \	56900	#define vst3_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67257	poly64x1x3_t __s1 = __p1; \	56901	poly64x1x3_t __s1 = __p1; \
67258	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \	56902	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 6); \
67259	})	56903	})
67260	#endif
67261
67262	#ifdef __LITTLE_ENDIAN__	56904	#ifdef __LITTLE_ENDIAN__
67263	#define vst3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	56905	#define vst3q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
67264	poly8x16x3_t __s1 = __p1; \	56906	poly8x16x3_t __s1 = __p1; \
...	@@ -67342,7 +56984,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67342,7 +56984,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67342	#ifdef __LITTLE_ENDIAN__	56984	#ifdef __LITTLE_ENDIAN__
67343	#define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56985	#define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67344	float64x2x3_t __s1 = __p1; \	56986	float64x2x3_t __s1 = __p1; \
67345	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 42); \	56987	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 42); \
67346	})	56988	})
67347	#else	56989	#else
67348	#define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	56990	#define vst3q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67351,14 +56993,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67351,14 +56993,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67351	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	56993	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67352	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	56994	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67353	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	56995	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67354	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 42); \	56996	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 42); \
67355	})	56997	})
67356	#endif	56998	#endif
67357		56999
67358	#ifdef __LITTLE_ENDIAN__	57000	#ifdef __LITTLE_ENDIAN__
67359	#define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57001	#define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67360	int64x2x3_t __s1 = __p1; \	57002	int64x2x3_t __s1 = __p1; \
67361	__builtin_neon_vst3q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 35); \	57003	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], __p2, 35); \
67362	})	57004	})
67363	#else	57005	#else
67364	#define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57006	#define vst3q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67367,58 +57009,26 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67367,58 +57009,26 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67367	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \	57009	__rev1.val[0] = __builtin_shufflevector(__s1.val[0], __s1.val[0], 1, 0); \
67368	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	57010	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67369	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	57011	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67370	__builtin_neon_vst3q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __p2, 35); \	57012	__builtin_neon_vst3q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], __p2, 35); \
67371	})	57013	})
67372	#endif	57014	#endif
67373		57015
67374	#ifdef __LITTLE_ENDIAN__
67375	#define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({ \	57016	#define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67376	uint64x1x3_t __s1 = __p1; \	57017	uint64x1x3_t __s1 = __p1; \
67377	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \	57018	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
67378	})	57019	})
67379	#else
67380	#define vst3_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67381	uint64x1x3_t __s1 = __p1; \
67382	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 19); \
67383	})
67384	#endif
67385
67386	#ifdef __LITTLE_ENDIAN__
67387	#define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67388	float64x1x3_t __s1 = __p1; \
67389	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 10); \
67390	})
67391	#else
67392	#define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({ \	57020	#define vst3_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67393	float64x1x3_t __s1 = __p1; \	57021	float64x1x3_t __s1 = __p1; \
67394	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 10); \	57022	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 10); \
67395	})
67396	#endif
67397
67398	#ifdef __LITTLE_ENDIAN__
67399	#define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67400	int64x1x3_t __s1 = __p1; \
67401	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 3); \
67402	})	57023	})
67403	#else
67404	#define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57024	#define vst3_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67405	int64x1x3_t __s1 = __p1; \	57025	int64x1x3_t __s1 = __p1; \
67406	__builtin_neon_vst3_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __p2, 3); \	57026	__builtin_neon_vst3_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], __p2, 3); \
67407	})
67408	#endif
67409
67410	#ifdef __LITTLE_ENDIAN__
67411	#define vst4_p64(__p0, __p1) __extension__ ({ \
67412	poly64x1x4_t __s1 = __p1; \
67413	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
67414	})	57027	})
67415	#else
67416	#define vst4_p64(__p0, __p1) __extension__ ({ \	57028	#define vst4_p64(__p0, __p1) __extension__ ({ \
67417	poly64x1x4_t __s1 = __p1; \	57029	poly64x1x4_t __s1 = __p1; \
67418	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \	57030	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 6); \
67419	})	57031	})
67420	#endif
67421
67422	#ifdef __LITTLE_ENDIAN__	57032	#ifdef __LITTLE_ENDIAN__
67423	#define vst4q_p64(__p0, __p1) __extension__ ({ \	57033	#define vst4q_p64(__p0, __p1) __extension__ ({ \
67424	poly64x2x4_t __s1 = __p1; \	57034	poly64x2x4_t __s1 = __p1; \
...	@@ -67456,7 +57066,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67456,7 +57066,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67456	#ifdef __LITTLE_ENDIAN__	57066	#ifdef __LITTLE_ENDIAN__
67457	#define vst4q_f64(__p0, __p1) __extension__ ({ \	57067	#define vst4q_f64(__p0, __p1) __extension__ ({ \
67458	float64x2x4_t __s1 = __p1; \	57068	float64x2x4_t __s1 = __p1; \
67459	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 42); \	57069	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 42); \
67460	})	57070	})
67461	#else	57071	#else
67462	#define vst4q_f64(__p0, __p1) __extension__ ({ \	57072	#define vst4q_f64(__p0, __p1) __extension__ ({ \
...	@@ -67466,14 +57076,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67466,14 +57076,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67466	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	57076	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67467	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	57077	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67468	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	57078	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
67469	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 42); \	57079	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 42); \
67470	})	57080	})
67471	#endif	57081	#endif
67472		57082
67473	#ifdef __LITTLE_ENDIAN__	57083	#ifdef __LITTLE_ENDIAN__
67474	#define vst4q_s64(__p0, __p1) __extension__ ({ \	57084	#define vst4q_s64(__p0, __p1) __extension__ ({ \
67475	int64x2x4_t __s1 = __p1; \	57085	int64x2x4_t __s1 = __p1; \
67476	__builtin_neon_vst4q_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 35); \	57086	__builtin_neon_vst4q_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], 35); \
67477	})	57087	})
67478	#else	57088	#else
67479	#define vst4q_s64(__p0, __p1) __extension__ ({ \	57089	#define vst4q_s64(__p0, __p1) __extension__ ({ \
...	@@ -67483,34 +57093,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67483,34 +57093,18 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67483	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	57093	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67484	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	57094	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67485	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	57095	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
67486	__builtin_neon_vst4q_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], 35); \	57096	__builtin_neon_vst4q_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], 35); \
67487	})	57097	})
67488	#endif	57098	#endif
67489		57099
67490	#ifdef __LITTLE_ENDIAN__
67491	#define vst4_f64(__p0, __p1) __extension__ ({ \	57100	#define vst4_f64(__p0, __p1) __extension__ ({ \
67492	float64x1x4_t __s1 = __p1; \	57101	float64x1x4_t __s1 = __p1; \
67493	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 10); \	57102	__builtin_neon_vst4_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], 10); \
67494	})	57103	})
67495	#else
67496	#define vst4_f64(__p0, __p1) __extension__ ({ \
67497	float64x1x4_t __s1 = __p1; \
67498	__builtin_neon_vst4_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], 10); \
67499	})
67500	#endif
67501
67502	#ifdef __LITTLE_ENDIAN__
67503	#define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67504	poly64x1x4_t __s1 = __p1; \
67505	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
67506	})
67507	#else
67508	#define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({ \	57104	#define vst4_lane_p64(__p0, __p1, __p2) __extension__ ({ \
67509	poly64x1x4_t __s1 = __p1; \	57105	poly64x1x4_t __s1 = __p1; \
67510	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \	57106	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 6); \
67511	})	57107	})
67512	#endif
67513
67514	#ifdef __LITTLE_ENDIAN__	57108	#ifdef __LITTLE_ENDIAN__
67515	#define vst4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \	57109	#define vst4q_lane_p8(__p0, __p1, __p2) __extension__ ({ \
67516	poly8x16x4_t __s1 = __p1; \	57110	poly8x16x4_t __s1 = __p1; \
...	@@ -67599,7 +57193,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67599,7 +57193,7 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67599	#ifdef __LITTLE_ENDIAN__	57193	#ifdef __LITTLE_ENDIAN__
67600	#define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	57194	#define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67601	float64x2x4_t __s1 = __p1; \	57195	float64x2x4_t __s1 = __p1; \
67602	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 42); \	57196	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 42); \
67603	})	57197	})
67604	#else	57198	#else
67605	#define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \	57199	#define vst4q_lane_f64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67609,14 +57203,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67609,14 +57203,14 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67609	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	57203	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67610	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	57204	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67611	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	57205	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
67612	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 42); \	57206	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 42); \
67613	})	57207	})
67614	#endif	57208	#endif
67615		57209
67616	#ifdef __LITTLE_ENDIAN__	57210	#ifdef __LITTLE_ENDIAN__
67617	#define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57211	#define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67618	int64x2x4_t __s1 = __p1; \	57212	int64x2x4_t __s1 = __p1; \
67619	__builtin_neon_vst4q_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 35); \	57213	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__s1.val[0], (int8x16_t)__s1.val[1], (int8x16_t)__s1.val[2], (int8x16_t)__s1.val[3], __p2, 35); \
67620	})	57214	})
67621	#else	57215	#else
67622	#define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57216	#define vst4q_lane_s64(__p0, __p1, __p2) __extension__ ({ \
...	@@ -67626,86 +57220,36 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {	...	@@ -67626,86 +57220,36 @@ __ai float32x2_t vsqrt_f32(float32x2_t __p0) {
67626	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \	57220	__rev1.val[1] = __builtin_shufflevector(__s1.val[1], __s1.val[1], 1, 0); \
67627	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \	57221	__rev1.val[2] = __builtin_shufflevector(__s1.val[2], __s1.val[2], 1, 0); \
67628	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \	57222	__rev1.val[3] = __builtin_shufflevector(__s1.val[3], __s1.val[3], 1, 0); \
67629	__builtin_neon_vst4q_lane_v(__p0, __rev1.val[0], __rev1.val[1], __rev1.val[2], __rev1.val[3], __p2, 35); \	57223	__builtin_neon_vst4q_lane_v(__p0, (int8x16_t)__rev1.val[0], (int8x16_t)__rev1.val[1], (int8x16_t)__rev1.val[2], (int8x16_t)__rev1.val[3], __p2, 35); \
67630	})	57224	})
67631	#endif	57225	#endif
67632		57226
67633	#ifdef __LITTLE_ENDIAN__
67634	#define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67635	uint64x1x4_t __s1 = __p1; \
67636	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
67637	})
67638	#else
67639	#define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({ \	57227	#define vst4_lane_u64(__p0, __p1, __p2) __extension__ ({ \
67640	uint64x1x4_t __s1 = __p1; \	57228	uint64x1x4_t __s1 = __p1; \
67641	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \	57229	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 19); \
67642	})	57230	})
67643	#endif
67644
67645	#ifdef __LITTLE_ENDIAN__
67646	#define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67647	float64x1x4_t __s1 = __p1; \
67648	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 10); \
67649	})
67650	#else
67651	#define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({ \	57231	#define vst4_lane_f64(__p0, __p1, __p2) __extension__ ({ \
67652	float64x1x4_t __s1 = __p1; \	57232	float64x1x4_t __s1 = __p1; \
67653	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 10); \	57233	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 10); \
67654	})
67655	#endif
67656
67657	#ifdef __LITTLE_ENDIAN__
67658	#define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67659	int64x1x4_t __s1 = __p1; \
67660	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 3); \
67661	})	57234	})
67662	#else
67663	#define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({ \	57235	#define vst4_lane_s64(__p0, __p1, __p2) __extension__ ({ \
67664	int64x1x4_t __s1 = __p1; \	57236	int64x1x4_t __s1 = __p1; \
67665	__builtin_neon_vst4_lane_v(__p0, __s1.val[0], __s1.val[1], __s1.val[2], __s1.val[3], __p2, 3); \	57237	__builtin_neon_vst4_lane_v(__p0, (int8x8_t)__s1.val[0], (int8x8_t)__s1.val[1], (int8x8_t)__s1.val[2], (int8x8_t)__s1.val[3], __p2, 3); \
67666	})
67667	#endif
67668
67669	#ifdef __LITTLE_ENDIAN__
67670	#define vstrq_p128(__p0, __p1) __extension__ ({ \
67671	poly128_t __s1 = __p1; \
67672	__builtin_neon_vstrq_p128(__p0, __s1); \
67673	})	57238	})
67674	#else
67675	#define vstrq_p128(__p0, __p1) __extension__ ({ \	57239	#define vstrq_p128(__p0, __p1) __extension__ ({ \
67676	poly128_t __s1 = __p1; \	57240	poly128_t __s1 = __p1; \
67677	__builtin_neon_vstrq_p128(__p0, __s1); \	57241	__builtin_neon_vstrq_p128(__p0, __s1); \
67678	})	57242	})
67679	#endif
67680
67681	#ifdef __LITTLE_ENDIAN__
67682	__ai uint64_t vsubd_u64(uint64_t __p0, uint64_t __p1) {
67683	uint64_t __ret;
67684	__ret = (uint64_t) __builtin_neon_vsubd_u64(__p0, __p1);
67685	return __ret;
67686	}
67687	#else
67688	__ai uint64_t vsubd_u64(uint64_t __p0, uint64_t __p1) {	57243	__ai uint64_t vsubd_u64(uint64_t __p0, uint64_t __p1) {
67689	uint64_t __ret;	57244	uint64_t __ret;
67690	__ret = (uint64_t) __builtin_neon_vsubd_u64(__p0, __p1);	57245	__ret = (uint64_t) __builtin_neon_vsubd_u64(__p0, __p1);
67691	return __ret;	57246	return __ret;
67692	}	57247	}
67693	#endif
67694
67695	#ifdef __LITTLE_ENDIAN__
67696	__ai int64_t vsubd_s64(int64_t __p0, int64_t __p1) {
67697	int64_t __ret;
67698	__ret = (int64_t) __builtin_neon_vsubd_s64(__p0, __p1);
67699	return __ret;
67700	}
67701	#else
67702	__ai int64_t vsubd_s64(int64_t __p0, int64_t __p1) {	57248	__ai int64_t vsubd_s64(int64_t __p0, int64_t __p1) {
67703	int64_t __ret;	57249	int64_t __ret;
67704	__ret = (int64_t) __builtin_neon_vsubd_s64(__p0, __p1);	57250	__ret = (int64_t) __builtin_neon_vsubd_s64(__p0, __p1);
67705	return __ret;	57251	return __ret;
67706	}	57252	}
67707	#endif
67708
67709	#ifdef __LITTLE_ENDIAN__	57253	#ifdef __LITTLE_ENDIAN__
67710	__ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {	57254	__ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {
67711	float64x2_t __ret;	57255	float64x2_t __ret;
...	@@ -67723,20 +57267,11 @@ __ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {	...	@@ -67723,20 +57267,11 @@ __ai float64x2_t vsubq_f64(float64x2_t __p0, float64x2_t __p1) {
67723	}	57267	}
67724	#endif	57268	#endif
67725		57269
67726	#ifdef __LITTLE_ENDIAN__
67727	__ai float64x1_t vsub_f64(float64x1_t __p0, float64x1_t __p1) {
67728	float64x1_t __ret;
67729	__ret = __p0 - __p1;
67730	return __ret;
67731	}
67732	#else
67733	__ai float64x1_t vsub_f64(float64x1_t __p0, float64x1_t __p1) {	57270	__ai float64x1_t vsub_f64(float64x1_t __p0, float64x1_t __p1) {
67734	float64x1_t __ret;	57271	float64x1_t __ret;
67735	__ret = __p0 - __p1;	57272	__ret = __p0 - __p1;
67736	return __ret;	57273	return __ret;
67737	}	57274	}
67738	#endif
67739
67740	#ifdef __LITTLE_ENDIAN__	57275	#ifdef __LITTLE_ENDIAN__
67741	__ai uint16x8_t vsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {	57276	__ai uint16x8_t vsubhn_high_u32(uint16x4_t __p0, uint32x4_t __p1, uint32x4_t __p2) {
67742	uint16x8_t __ret;	57277	uint16x8_t __ret;
...	@@ -68797,20 +58332,11 @@ __ai int16x4_t vtrn2_s16(int16x4_t __p0, int16x4_t __p1) {	...	@@ -68797,20 +58332,11 @@ __ai int16x4_t vtrn2_s16(int16x4_t __p0, int16x4_t __p1) {
68797	}	58332	}
68798	#endif	58333	#endif
68799		58334
68800	#ifdef __LITTLE_ENDIAN__
68801	__ai uint64x1_t vtst_p64(poly64x1_t __p0, poly64x1_t __p1) {
68802	uint64x1_t __ret;
68803	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68804	return __ret;
68805	}
68806	#else
68807	__ai uint64x1_t vtst_p64(poly64x1_t __p0, poly64x1_t __p1) {	58335	__ai uint64x1_t vtst_p64(poly64x1_t __p0, poly64x1_t __p1) {
68808	uint64x1_t __ret;	58336	uint64x1_t __ret;
68809	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	58337	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68810	return __ret;	58338	return __ret;
68811	}	58339	}
68812	#endif
68813
68814	#ifdef __LITTLE_ENDIAN__	58340	#ifdef __LITTLE_ENDIAN__
68815	__ai uint64x2_t vtstq_p64(poly64x2_t __p0, poly64x2_t __p1) {	58341	__ai uint64x2_t vtstq_p64(poly64x2_t __p0, poly64x2_t __p1) {
68816	uint64x2_t __ret;	58342	uint64x2_t __ret;
...	@@ -68862,118 +58388,46 @@ __ai uint64x2_t vtstq_s64(int64x2_t __p0, int64x2_t __p1) {	...	@@ -68862,118 +58388,46 @@ __ai uint64x2_t vtstq_s64(int64x2_t __p0, int64x2_t __p1) {
68862	}	58388	}
68863	#endif	58389	#endif
68864		58390
68865	#ifdef __LITTLE_ENDIAN__
68866	__ai uint64x1_t vtst_u64(uint64x1_t __p0, uint64x1_t __p1) {	58391	__ai uint64x1_t vtst_u64(uint64x1_t __p0, uint64x1_t __p1) {
68867	uint64x1_t __ret;	58392	uint64x1_t __ret;
68868	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	58393	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68869	return __ret;	58394	return __ret;
68870	}	58395	}
68871	#else
68872	__ai uint64x1_t vtst_u64(uint64x1_t __p0, uint64x1_t __p1) {
68873	uint64x1_t __ret;
68874	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68875	return __ret;
68876	}
68877	#endif
68878
68879	#ifdef __LITTLE_ENDIAN__
68880	__ai uint64x1_t vtst_s64(int64x1_t __p0, int64x1_t __p1) {
68881	uint64x1_t __ret;
68882	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68883	return __ret;
68884	}
68885	#else
68886	__ai uint64x1_t vtst_s64(int64x1_t __p0, int64x1_t __p1) {	58396	__ai uint64x1_t vtst_s64(int64x1_t __p0, int64x1_t __p1) {
68887	uint64x1_t __ret;	58397	uint64x1_t __ret;
68888	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);	58398	__ret = (uint64x1_t) __builtin_neon_vtst_v((int8x8_t)__p0, (int8x8_t)__p1, 19);
68889	return __ret;	58399	return __ret;
68890	}	58400	}
68891	#endif
68892
68893	#ifdef __LITTLE_ENDIAN__
68894	__ai uint64_t vtstd_u64(uint64_t __p0, uint64_t __p1) {
68895	uint64_t __ret;
68896	__ret = (uint64_t) __builtin_neon_vtstd_u64(__p0, __p1);
68897	return __ret;
68898	}
68899	#else
68900	__ai uint64_t vtstd_u64(uint64_t __p0, uint64_t __p1) {	58401	__ai uint64_t vtstd_u64(uint64_t __p0, uint64_t __p1) {
68901	uint64_t __ret;	58402	uint64_t __ret;
68902	__ret = (uint64_t) __builtin_neon_vtstd_u64(__p0, __p1);	58403	__ret = (uint64_t) __builtin_neon_vtstd_u64(__p0, __p1);
68903	return __ret;	58404	return __ret;
68904	}	58405	}
68905	#endif
68906
68907	#ifdef __LITTLE_ENDIAN__
68908	__ai int64_t vtstd_s64(int64_t __p0, int64_t __p1) {
68909	int64_t __ret;
68910	__ret = (int64_t) __builtin_neon_vtstd_s64(__p0, __p1);
68911	return __ret;
68912	}
68913	#else
68914	__ai int64_t vtstd_s64(int64_t __p0, int64_t __p1) {	58406	__ai int64_t vtstd_s64(int64_t __p0, int64_t __p1) {
68915	int64_t __ret;	58407	int64_t __ret;
68916	__ret = (int64_t) __builtin_neon_vtstd_s64(__p0, __p1);	58408	__ret = (int64_t) __builtin_neon_vtstd_s64(__p0, __p1);
68917	return __ret;	58409	return __ret;
68918	}	58410	}
68919	#endif
68920
68921	#ifdef __LITTLE_ENDIAN__
68922	__ai int8_t vuqaddb_s8(int8_t __p0, uint8_t __p1) {
68923	int8_t __ret;
68924	__ret = (int8_t) __builtin_neon_vuqaddb_s8(__p0, __p1);
68925	return __ret;
68926	}
68927	#else
68928	__ai int8_t vuqaddb_s8(int8_t __p0, uint8_t __p1) {	58411	__ai int8_t vuqaddb_s8(int8_t __p0, uint8_t __p1) {
68929	int8_t __ret;	58412	int8_t __ret;
68930	__ret = (int8_t) __builtin_neon_vuqaddb_s8(__p0, __p1);	58413	__ret = (int8_t) __builtin_neon_vuqaddb_s8(__p0, __p1);
68931	return __ret;	58414	return __ret;
68932	}	58415	}
68933	#endif
68934
68935	#ifdef __LITTLE_ENDIAN__
68936	__ai int32_t vuqadds_s32(int32_t __p0, uint32_t __p1) {	58416	__ai int32_t vuqadds_s32(int32_t __p0, uint32_t __p1) {
68937	int32_t __ret;	58417	int32_t __ret;
68938	__ret = (int32_t) __builtin_neon_vuqadds_s32(__p0, __p1);	58418	__ret = (int32_t) __builtin_neon_vuqadds_s32(__p0, __p1);
68939	return __ret;	58419	return __ret;
68940	}	58420	}
68941	#else
68942	__ai int32_t vuqadds_s32(int32_t __p0, uint32_t __p1) {
68943	int32_t __ret;
68944	__ret = (int32_t) __builtin_neon_vuqadds_s32(__p0, __p1);
68945	return __ret;
68946	}
68947	#endif
68948
68949	#ifdef __LITTLE_ENDIAN__
68950	__ai int64_t vuqaddd_s64(int64_t __p0, uint64_t __p1) {
68951	int64_t __ret;
68952	__ret = (int64_t) __builtin_neon_vuqaddd_s64(__p0, __p1);
68953	return __ret;
68954	}
68955	#else
68956	__ai int64_t vuqaddd_s64(int64_t __p0, uint64_t __p1) {	58421	__ai int64_t vuqaddd_s64(int64_t __p0, uint64_t __p1) {
68957	int64_t __ret;	58422	int64_t __ret;
68958	__ret = (int64_t) __builtin_neon_vuqaddd_s64(__p0, __p1);	58423	__ret = (int64_t) __builtin_neon_vuqaddd_s64(__p0, __p1);
68959	return __ret;	58424	return __ret;
68960	}	58425	}
68961	#endif
68962
68963	#ifdef __LITTLE_ENDIAN__
68964	__ai int16_t vuqaddh_s16(int16_t __p0, uint16_t __p1) {	58426	__ai int16_t vuqaddh_s16(int16_t __p0, uint16_t __p1) {
68965	int16_t __ret;	58427	int16_t __ret;
68966	__ret = (int16_t) __builtin_neon_vuqaddh_s16(__p0, __p1);	58428	__ret = (int16_t) __builtin_neon_vuqaddh_s16(__p0, __p1);
68967	return __ret;	58429	return __ret;
68968	}	58430	}
68969	#else
68970	__ai int16_t vuqaddh_s16(int16_t __p0, uint16_t __p1) {
68971	int16_t __ret;
68972	__ret = (int16_t) __builtin_neon_vuqaddh_s16(__p0, __p1);
68973	return __ret;
68974	}
68975	#endif
68976
68977	#ifdef __LITTLE_ENDIAN__	58431	#ifdef __LITTLE_ENDIAN__
68978	__ai int8x16_t vuqaddq_s8(int8x16_t __p0, uint8x16_t __p1) {	58432	__ai int8x16_t vuqaddq_s8(int8x16_t __p0, uint8x16_t __p1) {
68979	int8x16_t __ret;	58433	int8x16_t __ret;
...	@@ -69076,20 +58530,11 @@ __ai int32x2_t vuqadd_s32(int32x2_t __p0, uint32x2_t __p1) {	...	@@ -69076,20 +58530,11 @@ __ai int32x2_t vuqadd_s32(int32x2_t __p0, uint32x2_t __p1) {
69076	}	58530	}
69077	#endif	58531	#endif
69078		58532
69079	#ifdef __LITTLE_ENDIAN__
69080	__ai int64x1_t vuqadd_s64(int64x1_t __p0, uint64x1_t __p1) {	58533	__ai int64x1_t vuqadd_s64(int64x1_t __p0, uint64x1_t __p1) {
69081	int64x1_t __ret;	58534	int64x1_t __ret;
69082	__ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);	58535	__ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
69083	return __ret;	58536	return __ret;
69084	}	58537	}
69085	#else
69086	__ai int64x1_t vuqadd_s64(int64x1_t __p0, uint64x1_t __p1) {
69087	int64x1_t __ret;
69088	__ret = (int64x1_t) __builtin_neon_vuqadd_v((int8x8_t)__p0, (int8x8_t)__p1, 3);
69089	return __ret;
69090	}
69091	#endif
69092
69093	#ifdef __LITTLE_ENDIAN__	58538	#ifdef __LITTLE_ENDIAN__
69094	__ai int16x4_t vuqadd_s16(int16x4_t __p0, uint16x4_t __p1) {	58539	__ai int16x4_t vuqadd_s16(int16x4_t __p0, uint16x4_t __p1) {
69095	int16x4_t __ret;	58540	int16x4_t __ret;
...	@@ -71157,60 +60602,60 @@ __ai int32x4_t vaddw_s16(int32x4_t __p0, int16x4_t __p1) {	...	@@ -71157,60 +60602,60 @@ __ai int32x4_t vaddw_s16(int32x4_t __p0, int16x4_t __p1) {
71157	#endif	60602	#endif
71158		60603
71159	#ifdef __LITTLE_ENDIAN__	60604	#ifdef __LITTLE_ENDIAN__
71160	#define vget_lane_f16(__p0_254, __p1_254) __extension__ ({ \	60605	#define vget_lane_f16(__p0_248, __p1_248) __extension__ ({ \
71161	float16x4_t __s0_254 = __p0_254; \	60606	float16x4_t __s0_248 = __p0_248; \
71162	float16_t __ret_254; \	60607	float16_t __ret_248; \
71163	float16x4_t __reint_254 = __s0_254; \	60608	float16x4_t __reint_248 = __s0_248; \
71164	int16_t __reint1_254 = vget_lane_s16((int16x4_t ) &__reint_254, __p1_254); \	60609	int16_t __reint1_248 = vget_lane_s16((int16x4_t ) &__reint_248, __p1_248); \
71165	__ret_254 = (float16_t ) &__reint1_254; \	60610	__ret_248 = (float16_t ) &__reint1_248; \
71166	__ret_254; \	60611	__ret_248; \
71167	})	60612	})
71168	#else	60613	#else
71169	#define vget_lane_f16(__p0_255, __p1_255) __extension__ ({ \	60614	#define vget_lane_f16(__p0_249, __p1_249) __extension__ ({ \
71170	float16x4_t __s0_255 = __p0_255; \	60615	float16x4_t __s0_249 = __p0_249; \
71171	float16x4_t __rev0_255; __rev0_255 = __builtin_shufflevector(__s0_255, __s0_255, 3, 2, 1, 0); \	60616	float16x4_t __rev0_249; __rev0_249 = __builtin_shufflevector(__s0_249, __s0_249, 3, 2, 1, 0); \
71172	float16_t __ret_255; \	60617	float16_t __ret_249; \
71173	float16x4_t __reint_255 = __rev0_255; \	60618	float16x4_t __reint_249 = __rev0_249; \
71174	int16_t __reint1_255 = __noswap_vget_lane_s16((int16x4_t ) &__reint_255, __p1_255); \	60619	int16_t __reint1_249 = __noswap_vget_lane_s16((int16x4_t ) &__reint_249, __p1_249); \
71175	__ret_255 = (float16_t ) &__reint1_255; \	60620	__ret_249 = (float16_t ) &__reint1_249; \
71176	__ret_255; \	60621	__ret_249; \
71177	})	60622	})
71178	#define __noswap_vget_lane_f16(__p0_256, __p1_256) __extension__ ({ \	60623	#define __noswap_vget_lane_f16(__p0_250, __p1_250) __extension__ ({ \
71179	float16x4_t __s0_256 = __p0_256; \	60624	float16x4_t __s0_250 = __p0_250; \
71180	float16_t __ret_256; \	60625	float16_t __ret_250; \
71181	float16x4_t __reint_256 = __s0_256; \	60626	float16x4_t __reint_250 = __s0_250; \
71182	int16_t __reint1_256 = __noswap_vget_lane_s16((int16x4_t ) &__reint_256, __p1_256); \	60627	int16_t __reint1_250 = __noswap_vget_lane_s16((int16x4_t ) &__reint_250, __p1_250); \
71183	__ret_256 = (float16_t ) &__reint1_256; \	60628	__ret_250 = (float16_t ) &__reint1_250; \
71184	__ret_256; \	60629	__ret_250; \
71185	})	60630	})
71186	#endif	60631	#endif
71187		60632
71188	#ifdef __LITTLE_ENDIAN__	60633	#ifdef __LITTLE_ENDIAN__
71189	#define vgetq_lane_f16(__p0_257, __p1_257) __extension__ ({ \	60634	#define vgetq_lane_f16(__p0_251, __p1_251) __extension__ ({ \
71190	float16x8_t __s0_257 = __p0_257; \	60635	float16x8_t __s0_251 = __p0_251; \
71191	float16_t __ret_257; \	60636	float16_t __ret_251; \
71192	float16x8_t __reint_257 = __s0_257; \	60637	float16x8_t __reint_251 = __s0_251; \
71193	int16_t __reint1_257 = vgetq_lane_s16((int16x8_t ) &__reint_257, __p1_257); \	60638	int16_t __reint1_251 = vgetq_lane_s16((int16x8_t ) &__reint_251, __p1_251); \
71194	__ret_257 = (float16_t ) &__reint1_257; \	60639	__ret_251 = (float16_t ) &__reint1_251; \
71195	__ret_257; \	60640	__ret_251; \
71196	})	60641	})
71197	#else	60642	#else
71198	#define vgetq_lane_f16(__p0_258, __p1_258) __extension__ ({ \	60643	#define vgetq_lane_f16(__p0_252, __p1_252) __extension__ ({ \
71199	float16x8_t __s0_258 = __p0_258; \	60644	float16x8_t __s0_252 = __p0_252; \
71200	float16x8_t __rev0_258; __rev0_258 = __builtin_shufflevector(__s0_258, __s0_258, 7, 6, 5, 4, 3, 2, 1, 0); \	60645	float16x8_t __rev0_252; __rev0_252 = __builtin_shufflevector(__s0_252, __s0_252, 7, 6, 5, 4, 3, 2, 1, 0); \
71201	float16_t __ret_258; \	60646	float16_t __ret_252; \
71202	float16x8_t __reint_258 = __rev0_258; \	60647	float16x8_t __reint_252 = __rev0_252; \
71203	int16_t __reint1_258 = __noswap_vgetq_lane_s16((int16x8_t ) &__reint_258, __p1_258); \	60648	int16_t __reint1_252 = __noswap_vgetq_lane_s16((int16x8_t ) &__reint_252, __p1_252); \
71204	__ret_258 = (float16_t ) &__reint1_258; \	60649	__ret_252 = (float16_t ) &__reint1_252; \
71205	__ret_258; \	60650	__ret_252; \
71206	})	60651	})
71207	#define __noswap_vgetq_lane_f16(__p0_259, __p1_259) __extension__ ({ \	60652	#define __noswap_vgetq_lane_f16(__p0_253, __p1_253) __extension__ ({ \
71208	float16x8_t __s0_259 = __p0_259; \	60653	float16x8_t __s0_253 = __p0_253; \
71209	float16_t __ret_259; \	60654	float16_t __ret_253; \
71210	float16x8_t __reint_259 = __s0_259; \	60655	float16x8_t __reint_253 = __s0_253; \
71211	int16_t __reint1_259 = __noswap_vgetq_lane_s16((int16x8_t ) &__reint_259, __p1_259); \	60656	int16_t __reint1_253 = __noswap_vgetq_lane_s16((int16x8_t ) &__reint_253, __p1_253); \
71212	__ret_259 = (float16_t ) &__reint1_259; \	60657	__ret_253 = (float16_t ) &__reint1_253; \
71213	__ret_259; \	60658	__ret_253; \
71214	})	60659	})
71215	#endif	60660	#endif
71216		60661
...	@@ -71859,705 +61304,669 @@ __ai int32x4_t __noswap_vmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2	...	@@ -71859,705 +61304,669 @@ __ai int32x4_t __noswap_vmlsl_n_s16(int32x4_t __p0, int16x4_t __p1, int16_t __p2
71859	#endif	61304	#endif
71860		61305
71861	#ifdef __LITTLE_ENDIAN__	61306	#ifdef __LITTLE_ENDIAN__
71862	#define vset_lane_f16(__p0_260, __p1_260, __p2_260) __extension__ ({ \	61307	#define vset_lane_f16(__p0_254, __p1_254, __p2_254) __extension__ ({ \
71863	float16_t __s0_260 = __p0_260; \	61308	float16_t __s0_254 = __p0_254; \
		61309	float16x4_t __s1_254 = __p1_254; \
		61310	float16x4_t __ret_254; \
		61311	float16_t __reint_254 = __s0_254; \
		61312	float16x4_t __reint1_254 = __s1_254; \
		61313	int16x4_t __reint2_254 = vset_lane_s16((int16_t ) &__reint_254, (int16x4_t ) &__reint1_254, __p2_254); \
		61314	__ret_254 = (float16x4_t ) &__reint2_254; \
		61315	__ret_254; \
		61316	})
		61317	#else
		61318	#define vset_lane_f16(__p0_255, __p1_255, __p2_255) __extension__ ({ \
		61319	float16_t __s0_255 = __p0_255; \
		61320	float16x4_t __s1_255 = __p1_255; \
		61321	float16x4_t __rev1_255; __rev1_255 = __builtin_shufflevector(__s1_255, __s1_255, 3, 2, 1, 0); \
		61322	float16x4_t __ret_255; \
		61323	float16_t __reint_255 = __s0_255; \
		61324	float16x4_t __reint1_255 = __rev1_255; \
		61325	int16x4_t __reint2_255 = __noswap_vset_lane_s16((int16_t ) &__reint_255, (int16x4_t ) &__reint1_255, __p2_255); \
		61326	__ret_255 = (float16x4_t ) &__reint2_255; \
		61327	__ret_255 = __builtin_shufflevector(__ret_255, __ret_255, 3, 2, 1, 0); \
		61328	__ret_255; \
		61329	})
		61330	#endif
		61331
		61332	#ifdef __LITTLE_ENDIAN__
		61333	#define vsetq_lane_f16(__p0_256, __p1_256, __p2_256) __extension__ ({ \
		61334	float16_t __s0_256 = __p0_256; \
		61335	float16x8_t __s1_256 = __p1_256; \
		61336	float16x8_t __ret_256; \
		61337	float16_t __reint_256 = __s0_256; \
		61338	float16x8_t __reint1_256 = __s1_256; \
		61339	int16x8_t __reint2_256 = vsetq_lane_s16((int16_t ) &__reint_256, (int16x8_t ) &__reint1_256, __p2_256); \
		61340	__ret_256 = (float16x8_t ) &__reint2_256; \
		61341	__ret_256; \
		61342	})
		61343	#else
		61344	#define vsetq_lane_f16(__p0_257, __p1_257, __p2_257) __extension__ ({ \
		61345	float16_t __s0_257 = __p0_257; \
		61346	float16x8_t __s1_257 = __p1_257; \
		61347	float16x8_t __rev1_257; __rev1_257 = __builtin_shufflevector(__s1_257, __s1_257, 7, 6, 5, 4, 3, 2, 1, 0); \
		61348	float16x8_t __ret_257; \
		61349	float16_t __reint_257 = __s0_257; \
		61350	float16x8_t __reint1_257 = __rev1_257; \
		61351	int16x8_t __reint2_257 = __noswap_vsetq_lane_s16((int16_t ) &__reint_257, (int16x8_t ) &__reint1_257, __p2_257); \
		61352	__ret_257 = (float16x8_t ) &__reint2_257; \
		61353	__ret_257 = __builtin_shufflevector(__ret_257, __ret_257, 7, 6, 5, 4, 3, 2, 1, 0); \
		61354	__ret_257; \
		61355	})
		61356	#endif
		61357
		61358	#if defined(__ARM_FEATURE_FP16FML) && defined(__aarch64__)
		61359	#ifdef __LITTLE_ENDIAN__
		61360	#define vfmlalq_lane_high_f16(__p0_258, __p1_258, __p2_258, __p3_258) __extension__ ({ \
		61361	float32x4_t __s0_258 = __p0_258; \
		61362	float16x8_t __s1_258 = __p1_258; \
		61363	float16x4_t __s2_258 = __p2_258; \
		61364	float32x4_t __ret_258; \
		61365	__ret_258 = vfmlalq_high_f16(__s0_258, __s1_258, (float16x8_t) {vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258), vget_lane_f16(__s2_258, __p3_258)}); \
		61366	__ret_258; \
		61367	})
		61368	#else
		61369	#define vfmlalq_lane_high_f16(__p0_259, __p1_259, __p2_259, __p3_259) __extension__ ({ \
		61370	float32x4_t __s0_259 = __p0_259; \
		61371	float16x8_t __s1_259 = __p1_259; \
		61372	float16x4_t __s2_259 = __p2_259; \
		61373	float32x4_t __rev0_259; __rev0_259 = __builtin_shufflevector(__s0_259, __s0_259, 3, 2, 1, 0); \
		61374	float16x8_t __rev1_259; __rev1_259 = __builtin_shufflevector(__s1_259, __s1_259, 7, 6, 5, 4, 3, 2, 1, 0); \
		61375	float16x4_t __rev2_259; __rev2_259 = __builtin_shufflevector(__s2_259, __s2_259, 3, 2, 1, 0); \
		61376	float32x4_t __ret_259; \
		61377	__ret_259 = __noswap_vfmlalq_high_f16(__rev0_259, __rev1_259, (float16x8_t) {__noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259), __noswap_vget_lane_f16(__rev2_259, __p3_259)}); \
		61378	__ret_259 = __builtin_shufflevector(__ret_259, __ret_259, 3, 2, 1, 0); \
		61379	__ret_259; \
		61380	})
		61381	#endif
		61382
		61383	#ifdef __LITTLE_ENDIAN__
		61384	#define vfmlal_lane_high_f16(__p0_260, __p1_260, __p2_260, __p3_260) __extension__ ({ \
		61385	float32x2_t __s0_260 = __p0_260; \
71864	float16x4_t __s1_260 = __p1_260; \	61386	float16x4_t __s1_260 = __p1_260; \
71865	float16x4_t __ret_260; \	61387	float16x4_t __s2_260 = __p2_260; \
71866	float16_t __reint_260 = __s0_260; \	61388	float32x2_t __ret_260; \
71867	float16x4_t __reint1_260 = __s1_260; \	61389	__ret_260 = vfmlal_high_f16(__s0_260, __s1_260, (float16x4_t) {vget_lane_f16(__s2_260, __p3_260), vget_lane_f16(__s2_260, __p3_260), vget_lane_f16(__s2_260, __p3_260), vget_lane_f16(__s2_260, __p3_260)}); \
71868	int16x4_t __reint2_260 = vset_lane_s16((int16_t ) &__reint_260, (int16x4_t ) &__reint1_260, __p2_260); \
71869	__ret_260 = (float16x4_t ) &__reint2_260; \
71870	__ret_260; \	61390	__ret_260; \
71871	})	61391	})
71872	#else	61392	#else
71873	#define vset_lane_f16(__p0_261, __p1_261, __p2_261) __extension__ ({ \	61393	#define vfmlal_lane_high_f16(__p0_261, __p1_261, __p2_261, __p3_261) __extension__ ({ \
71874	float16_t __s0_261 = __p0_261; \	61394	float32x2_t __s0_261 = __p0_261; \
71875	float16x4_t __s1_261 = __p1_261; \	61395	float16x4_t __s1_261 = __p1_261; \
		61396	float16x4_t __s2_261 = __p2_261; \
		61397	float32x2_t __rev0_261; __rev0_261 = __builtin_shufflevector(__s0_261, __s0_261, 1, 0); \
71876	float16x4_t __rev1_261; __rev1_261 = __builtin_shufflevector(__s1_261, __s1_261, 3, 2, 1, 0); \	61398	float16x4_t __rev1_261; __rev1_261 = __builtin_shufflevector(__s1_261, __s1_261, 3, 2, 1, 0); \
71877	float16x4_t __ret_261; \	61399	float16x4_t __rev2_261; __rev2_261 = __builtin_shufflevector(__s2_261, __s2_261, 3, 2, 1, 0); \
71878	float16_t __reint_261 = __s0_261; \	61400	float32x2_t __ret_261; \
71879	float16x4_t __reint1_261 = __rev1_261; \	61401	__ret_261 = __noswap_vfmlal_high_f16(__rev0_261, __rev1_261, (float16x4_t) {__noswap_vget_lane_f16(__rev2_261, __p3_261), __noswap_vget_lane_f16(__rev2_261, __p3_261), __noswap_vget_lane_f16(__rev2_261, __p3_261), __noswap_vget_lane_f16(__rev2_261, __p3_261)}); \
71880	int16x4_t __reint2_261 = __noswap_vset_lane_s16((int16_t ) &__reint_261, (int16x4_t ) &__reint1_261, __p2_261); \	61402	__ret_261 = __builtin_shufflevector(__ret_261, __ret_261, 1, 0); \
71881	__ret_261 = (float16x4_t ) &__reint2_261; \
71882	__ret_261 = __builtin_shufflevector(__ret_261, __ret_261, 3, 2, 1, 0); \
71883	__ret_261; \	61403	__ret_261; \
71884	})	61404	})
71885	#endif	61405	#endif
71886		61406
71887	#ifdef __LITTLE_ENDIAN__	61407	#ifdef __LITTLE_ENDIAN__
71888	#define vsetq_lane_f16(__p0_262, __p1_262, __p2_262) __extension__ ({ \	61408	#define vfmlalq_lane_low_f16(__p0_262, __p1_262, __p2_262, __p3_262) __extension__ ({ \
71889	float16_t __s0_262 = __p0_262; \	61409	float32x4_t __s0_262 = __p0_262; \
71890	float16x8_t __s1_262 = __p1_262; \	61410	float16x8_t __s1_262 = __p1_262; \
71891	float16x8_t __ret_262; \	61411	float16x4_t __s2_262 = __p2_262; \
71892	float16_t __reint_262 = __s0_262; \	61412	float32x4_t __ret_262; \
71893	float16x8_t __reint1_262 = __s1_262; \	61413	__ret_262 = vfmlalq_low_f16(__s0_262, __s1_262, (float16x8_t) {vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262), vget_lane_f16(__s2_262, __p3_262)}); \
71894	int16x8_t __reint2_262 = vsetq_lane_s16((int16_t ) &__reint_262, (int16x8_t ) &__reint1_262, __p2_262); \
71895	__ret_262 = (float16x8_t ) &__reint2_262; \
71896	__ret_262; \	61414	__ret_262; \
71897	})	61415	})
71898	#else	61416	#else
71899	#define vsetq_lane_f16(__p0_263, __p1_263, __p2_263) __extension__ ({ \	61417	#define vfmlalq_lane_low_f16(__p0_263, __p1_263, __p2_263, __p3_263) __extension__ ({ \
71900	float16_t __s0_263 = __p0_263; \	61418	float32x4_t __s0_263 = __p0_263; \
71901	float16x8_t __s1_263 = __p1_263; \	61419	float16x8_t __s1_263 = __p1_263; \
		61420	float16x4_t __s2_263 = __p2_263; \
		61421	float32x4_t __rev0_263; __rev0_263 = __builtin_shufflevector(__s0_263, __s0_263, 3, 2, 1, 0); \
71902	float16x8_t __rev1_263; __rev1_263 = __builtin_shufflevector(__s1_263, __s1_263, 7, 6, 5, 4, 3, 2, 1, 0); \	61422	float16x8_t __rev1_263; __rev1_263 = __builtin_shufflevector(__s1_263, __s1_263, 7, 6, 5, 4, 3, 2, 1, 0); \
71903	float16x8_t __ret_263; \	61423	float16x4_t __rev2_263; __rev2_263 = __builtin_shufflevector(__s2_263, __s2_263, 3, 2, 1, 0); \
71904	float16_t __reint_263 = __s0_263; \	61424	float32x4_t __ret_263; \
71905	float16x8_t __reint1_263 = __rev1_263; \	61425	__ret_263 = __noswap_vfmlalq_low_f16(__rev0_263, __rev1_263, (float16x8_t) {__noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263), __noswap_vget_lane_f16(__rev2_263, __p3_263)}); \
71906	int16x8_t __reint2_263 = __noswap_vsetq_lane_s16((int16_t ) &__reint_263, (int16x8_t ) &__reint1_263, __p2_263); \	61426	__ret_263 = __builtin_shufflevector(__ret_263, __ret_263, 3, 2, 1, 0); \
71907	__ret_263 = (float16x8_t ) &__reint2_263; \
71908	__ret_263 = __builtin_shufflevector(__ret_263, __ret_263, 7, 6, 5, 4, 3, 2, 1, 0); \
71909	__ret_263; \	61427	__ret_263; \
71910	})	61428	})
71911	#endif	61429	#endif
71912		61430
71913	#if defined(__ARM_FEATURE_FP16FML) && defined(__aarch64__)
71914	#ifdef __LITTLE_ENDIAN__	61431	#ifdef __LITTLE_ENDIAN__
71915	#define vfmlalq_lane_high_f16(__p0_264, __p1_264, __p2_264, __p3_264) __extension__ ({ \	61432	#define vfmlal_lane_low_f16(__p0_264, __p1_264, __p2_264, __p3_264) __extension__ ({ \
71916	float32x4_t __s0_264 = __p0_264; \	61433	float32x2_t __s0_264 = __p0_264; \
71917	float16x8_t __s1_264 = __p1_264; \	61434	float16x4_t __s1_264 = __p1_264; \
71918	float16x4_t __s2_264 = __p2_264; \	61435	float16x4_t __s2_264 = __p2_264; \
71919	float32x4_t __ret_264; \	61436	float32x2_t __ret_264; \
71920	__ret_264 = vfmlalq_high_f16(__s0_264, __s1_264, (float16x8_t) {vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264)}); \	61437	__ret_264 = vfmlal_low_f16(__s0_264, __s1_264, (float16x4_t) {vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264), vget_lane_f16(__s2_264, __p3_264)}); \
71921	__ret_264; \	61438	__ret_264; \
71922	})	61439	})
71923	#else	61440	#else
71924	#define vfmlalq_lane_high_f16(__p0_265, __p1_265, __p2_265, __p3_265) __extension__ ({ \	61441	#define vfmlal_lane_low_f16(__p0_265, __p1_265, __p2_265, __p3_265) __extension__ ({ \
71925	float32x4_t __s0_265 = __p0_265; \	61442	float32x2_t __s0_265 = __p0_265; \
71926	float16x8_t __s1_265 = __p1_265; \	61443	float16x4_t __s1_265 = __p1_265; \
71927	float16x4_t __s2_265 = __p2_265; \	61444	float16x4_t __s2_265 = __p2_265; \
71928	float32x4_t __rev0_265; __rev0_265 = __builtin_shufflevector(__s0_265, __s0_265, 3, 2, 1, 0); \	61445	float32x2_t __rev0_265; __rev0_265 = __builtin_shufflevector(__s0_265, __s0_265, 1, 0); \
71929	float16x8_t __rev1_265; __rev1_265 = __builtin_shufflevector(__s1_265, __s1_265, 7, 6, 5, 4, 3, 2, 1, 0); \	61446	float16x4_t __rev1_265; __rev1_265 = __builtin_shufflevector(__s1_265, __s1_265, 3, 2, 1, 0); \
71930	float16x4_t __rev2_265; __rev2_265 = __builtin_shufflevector(__s2_265, __s2_265, 3, 2, 1, 0); \	61447	float16x4_t __rev2_265; __rev2_265 = __builtin_shufflevector(__s2_265, __s2_265, 3, 2, 1, 0); \
71931	float32x4_t __ret_265; \	61448	float32x2_t __ret_265; \
71932	__ret_265 = __noswap_vfmlalq_high_f16(__rev0_265, __rev1_265, (float16x8_t) {__noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265)}); \	61449	__ret_265 = __noswap_vfmlal_low_f16(__rev0_265, __rev1_265, (float16x4_t) {__noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265), __noswap_vget_lane_f16(__rev2_265, __p3_265)}); \
71933	__ret_265 = __builtin_shufflevector(__ret_265, __ret_265, 3, 2, 1, 0); \	61450	__ret_265 = __builtin_shufflevector(__ret_265, __ret_265, 1, 0); \
71934	__ret_265; \	61451	__ret_265; \
71935	})	61452	})
71936	#endif	61453	#endif
71937		61454
71938	#ifdef __LITTLE_ENDIAN__	61455	#ifdef __LITTLE_ENDIAN__
71939	#define vfmlal_lane_high_f16(__p0_266, __p1_266, __p2_266, __p3_266) __extension__ ({ \	61456	#define vfmlalq_laneq_high_f16(__p0_266, __p1_266, __p2_266, __p3_266) __extension__ ({ \
71940	float32x2_t __s0_266 = __p0_266; \	61457	float32x4_t __s0_266 = __p0_266; \
71941	float16x4_t __s1_266 = __p1_266; \	61458	float16x8_t __s1_266 = __p1_266; \
71942	float16x4_t __s2_266 = __p2_266; \	61459	float16x8_t __s2_266 = __p2_266; \
71943	float32x2_t __ret_266; \	61460	float32x4_t __ret_266; \
71944	__ret_266 = vfmlal_high_f16(__s0_266, __s1_266, (float16x4_t) {vget_lane_f16(__s2_266, __p3_266), vget_lane_f16(__s2_266, __p3_266), vget_lane_f16(__s2_266, __p3_266), vget_lane_f16(__s2_266, __p3_266)}); \	61461	__ret_266 = vfmlalq_high_f16(__s0_266, __s1_266, (float16x8_t) {vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266), vgetq_lane_f16(__s2_266, __p3_266)}); \
71945	__ret_266; \	61462	__ret_266; \
71946	})	61463	})
71947	#else	61464	#else
71948	#define vfmlal_lane_high_f16(__p0_267, __p1_267, __p2_267, __p3_267) __extension__ ({ \	61465	#define vfmlalq_laneq_high_f16(__p0_267, __p1_267, __p2_267, __p3_267) __extension__ ({ \
71949	float32x2_t __s0_267 = __p0_267; \	61466	float32x4_t __s0_267 = __p0_267; \
71950	float16x4_t __s1_267 = __p1_267; \	61467	float16x8_t __s1_267 = __p1_267; \
71951	float16x4_t __s2_267 = __p2_267; \	61468	float16x8_t __s2_267 = __p2_267; \
71952	float32x2_t __rev0_267; __rev0_267 = __builtin_shufflevector(__s0_267, __s0_267, 1, 0); \	61469	float32x4_t __rev0_267; __rev0_267 = __builtin_shufflevector(__s0_267, __s0_267, 3, 2, 1, 0); \
71953	float16x4_t __rev1_267; __rev1_267 = __builtin_shufflevector(__s1_267, __s1_267, 3, 2, 1, 0); \	61470	float16x8_t __rev1_267; __rev1_267 = __builtin_shufflevector(__s1_267, __s1_267, 7, 6, 5, 4, 3, 2, 1, 0); \
71954	float16x4_t __rev2_267; __rev2_267 = __builtin_shufflevector(__s2_267, __s2_267, 3, 2, 1, 0); \	61471	float16x8_t __rev2_267; __rev2_267 = __builtin_shufflevector(__s2_267, __s2_267, 7, 6, 5, 4, 3, 2, 1, 0); \
71955	float32x2_t __ret_267; \	61472	float32x4_t __ret_267; \
71956	__ret_267 = __noswap_vfmlal_high_f16(__rev0_267, __rev1_267, (float16x4_t) {__noswap_vget_lane_f16(__rev2_267, __p3_267), __noswap_vget_lane_f16(__rev2_267, __p3_267), __noswap_vget_lane_f16(__rev2_267, __p3_267), __noswap_vget_lane_f16(__rev2_267, __p3_267)}); \	61473	__ret_267 = __noswap_vfmlalq_high_f16(__rev0_267, __rev1_267, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267), __noswap_vgetq_lane_f16(__rev2_267, __p3_267)}); \
71957	__ret_267 = __builtin_shufflevector(__ret_267, __ret_267, 1, 0); \	61474	__ret_267 = __builtin_shufflevector(__ret_267, __ret_267, 3, 2, 1, 0); \
71958	__ret_267; \	61475	__ret_267; \
71959	})	61476	})
71960	#endif	61477	#endif
71961		61478
71962	#ifdef __LITTLE_ENDIAN__	61479	#ifdef __LITTLE_ENDIAN__
71963	#define vfmlalq_lane_low_f16(__p0_268, __p1_268, __p2_268, __p3_268) __extension__ ({ \	61480	#define vfmlal_laneq_high_f16(__p0_268, __p1_268, __p2_268, __p3_268) __extension__ ({ \
71964	float32x4_t __s0_268 = __p0_268; \	61481	float32x2_t __s0_268 = __p0_268; \
71965	float16x8_t __s1_268 = __p1_268; \	61482	float16x4_t __s1_268 = __p1_268; \
71966	float16x4_t __s2_268 = __p2_268; \	61483	float16x8_t __s2_268 = __p2_268; \
71967	float32x4_t __ret_268; \	61484	float32x2_t __ret_268; \
71968	__ret_268 = vfmlalq_low_f16(__s0_268, __s1_268, (float16x8_t) {vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268), vget_lane_f16(__s2_268, __p3_268)}); \	61485	__ret_268 = vfmlal_high_f16(__s0_268, __s1_268, (float16x4_t) {vgetq_lane_f16(__s2_268, __p3_268), vgetq_lane_f16(__s2_268, __p3_268), vgetq_lane_f16(__s2_268, __p3_268), vgetq_lane_f16(__s2_268, __p3_268)}); \
71969	__ret_268; \	61486	__ret_268; \
71970	})	61487	})
71971	#else	61488	#else
71972	#define vfmlalq_lane_low_f16(__p0_269, __p1_269, __p2_269, __p3_269) __extension__ ({ \	61489	#define vfmlal_laneq_high_f16(__p0_269, __p1_269, __p2_269, __p3_269) __extension__ ({ \
71973	float32x4_t __s0_269 = __p0_269; \	61490	float32x2_t __s0_269 = __p0_269; \
71974	float16x8_t __s1_269 = __p1_269; \	61491	float16x4_t __s1_269 = __p1_269; \
71975	float16x4_t __s2_269 = __p2_269; \	61492	float16x8_t __s2_269 = __p2_269; \
71976	float32x4_t __rev0_269; __rev0_269 = __builtin_shufflevector(__s0_269, __s0_269, 3, 2, 1, 0); \	61493	float32x2_t __rev0_269; __rev0_269 = __builtin_shufflevector(__s0_269, __s0_269, 1, 0); \
71977	float16x8_t __rev1_269; __rev1_269 = __builtin_shufflevector(__s1_269, __s1_269, 7, 6, 5, 4, 3, 2, 1, 0); \	61494	float16x4_t __rev1_269; __rev1_269 = __builtin_shufflevector(__s1_269, __s1_269, 3, 2, 1, 0); \
71978	float16x4_t __rev2_269; __rev2_269 = __builtin_shufflevector(__s2_269, __s2_269, 3, 2, 1, 0); \	61495	float16x8_t __rev2_269; __rev2_269 = __builtin_shufflevector(__s2_269, __s2_269, 7, 6, 5, 4, 3, 2, 1, 0); \
71979	float32x4_t __ret_269; \	61496	float32x2_t __ret_269; \
71980	__ret_269 = __noswap_vfmlalq_low_f16(__rev0_269, __rev1_269, (float16x8_t) {__noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269), __noswap_vget_lane_f16(__rev2_269, __p3_269)}); \	61497	__ret_269 = __noswap_vfmlal_high_f16(__rev0_269, __rev1_269, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_269, __p3_269), __noswap_vgetq_lane_f16(__rev2_269, __p3_269), __noswap_vgetq_lane_f16(__rev2_269, __p3_269), __noswap_vgetq_lane_f16(__rev2_269, __p3_269)}); \
71981	__ret_269 = __builtin_shufflevector(__ret_269, __ret_269, 3, 2, 1, 0); \	61498	__ret_269 = __builtin_shufflevector(__ret_269, __ret_269, 1, 0); \
71982	__ret_269; \	61499	__ret_269; \
71983	})	61500	})
71984	#endif	61501	#endif
71985		61502
71986	#ifdef __LITTLE_ENDIAN__	61503	#ifdef __LITTLE_ENDIAN__
71987	#define vfmlal_lane_low_f16(__p0_270, __p1_270, __p2_270, __p3_270) __extension__ ({ \	61504	#define vfmlalq_laneq_low_f16(__p0_270, __p1_270, __p2_270, __p3_270) __extension__ ({ \
71988	float32x2_t __s0_270 = __p0_270; \	61505	float32x4_t __s0_270 = __p0_270; \
71989	float16x4_t __s1_270 = __p1_270; \	61506	float16x8_t __s1_270 = __p1_270; \
71990	float16x4_t __s2_270 = __p2_270; \	61507	float16x8_t __s2_270 = __p2_270; \
71991	float32x2_t __ret_270; \	61508	float32x4_t __ret_270; \
71992	__ret_270 = vfmlal_low_f16(__s0_270, __s1_270, (float16x4_t) {vget_lane_f16(__s2_270, __p3_270), vget_lane_f16(__s2_270, __p3_270), vget_lane_f16(__s2_270, __p3_270), vget_lane_f16(__s2_270, __p3_270)}); \	61509	__ret_270 = vfmlalq_low_f16(__s0_270, __s1_270, (float16x8_t) {vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270), vgetq_lane_f16(__s2_270, __p3_270)}); \
71993	__ret_270; \	61510	__ret_270; \
71994	})	61511	})
71995	#else	61512	#else
71996	#define vfmlal_lane_low_f16(__p0_271, __p1_271, __p2_271, __p3_271) __extension__ ({ \	61513	#define vfmlalq_laneq_low_f16(__p0_271, __p1_271, __p2_271, __p3_271) __extension__ ({ \
71997	float32x2_t __s0_271 = __p0_271; \	61514	float32x4_t __s0_271 = __p0_271; \
71998	float16x4_t __s1_271 = __p1_271; \	61515	float16x8_t __s1_271 = __p1_271; \
71999	float16x4_t __s2_271 = __p2_271; \	61516	float16x8_t __s2_271 = __p2_271; \
72000	float32x2_t __rev0_271; __rev0_271 = __builtin_shufflevector(__s0_271, __s0_271, 1, 0); \	61517	float32x4_t __rev0_271; __rev0_271 = __builtin_shufflevector(__s0_271, __s0_271, 3, 2, 1, 0); \
72001	float16x4_t __rev1_271; __rev1_271 = __builtin_shufflevector(__s1_271, __s1_271, 3, 2, 1, 0); \	61518	float16x8_t __rev1_271; __rev1_271 = __builtin_shufflevector(__s1_271, __s1_271, 7, 6, 5, 4, 3, 2, 1, 0); \
72002	float16x4_t __rev2_271; __rev2_271 = __builtin_shufflevector(__s2_271, __s2_271, 3, 2, 1, 0); \	61519	float16x8_t __rev2_271; __rev2_271 = __builtin_shufflevector(__s2_271, __s2_271, 7, 6, 5, 4, 3, 2, 1, 0); \
72003	float32x2_t __ret_271; \	61520	float32x4_t __ret_271; \
72004	__ret_271 = __noswap_vfmlal_low_f16(__rev0_271, __rev1_271, (float16x4_t) {__noswap_vget_lane_f16(__rev2_271, __p3_271), __noswap_vget_lane_f16(__rev2_271, __p3_271), __noswap_vget_lane_f16(__rev2_271, __p3_271), __noswap_vget_lane_f16(__rev2_271, __p3_271)}); \	61521	__ret_271 = __noswap_vfmlalq_low_f16(__rev0_271, __rev1_271, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271), __noswap_vgetq_lane_f16(__rev2_271, __p3_271)}); \
72005	__ret_271 = __builtin_shufflevector(__ret_271, __ret_271, 1, 0); \	61522	__ret_271 = __builtin_shufflevector(__ret_271, __ret_271, 3, 2, 1, 0); \
72006	__ret_271; \	61523	__ret_271; \
72007	})	61524	})
72008	#endif	61525	#endif
72009		61526
72010	#ifdef __LITTLE_ENDIAN__	61527	#ifdef __LITTLE_ENDIAN__
72011	#define vfmlalq_laneq_high_f16(__p0_272, __p1_272, __p2_272, __p3_272) __extension__ ({ \	61528	#define vfmlal_laneq_low_f16(__p0_272, __p1_272, __p2_272, __p3_272) __extension__ ({ \
72012	float32x4_t __s0_272 = __p0_272; \	61529	float32x2_t __s0_272 = __p0_272; \
72013	float16x8_t __s1_272 = __p1_272; \	61530	float16x4_t __s1_272 = __p1_272; \
72014	float16x8_t __s2_272 = __p2_272; \	61531	float16x8_t __s2_272 = __p2_272; \
72015	float32x4_t __ret_272; \	61532	float32x2_t __ret_272; \
72016	__ret_272 = vfmlalq_high_f16(__s0_272, __s1_272, (float16x8_t) {vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272)}); \	61533	__ret_272 = vfmlal_low_f16(__s0_272, __s1_272, (float16x4_t) {vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272), vgetq_lane_f16(__s2_272, __p3_272)}); \
72017	__ret_272; \	61534	__ret_272; \
72018	})	61535	})
72019	#else	61536	#else
72020	#define vfmlalq_laneq_high_f16(__p0_273, __p1_273, __p2_273, __p3_273) __extension__ ({ \	61537	#define vfmlal_laneq_low_f16(__p0_273, __p1_273, __p2_273, __p3_273) __extension__ ({ \
72021	float32x4_t __s0_273 = __p0_273; \	61538	float32x2_t __s0_273 = __p0_273; \
72022	float16x8_t __s1_273 = __p1_273; \	61539	float16x4_t __s1_273 = __p1_273; \
72023	float16x8_t __s2_273 = __p2_273; \	61540	float16x8_t __s2_273 = __p2_273; \
72024	float32x4_t __rev0_273; __rev0_273 = __builtin_shufflevector(__s0_273, __s0_273, 3, 2, 1, 0); \	61541	float32x2_t __rev0_273; __rev0_273 = __builtin_shufflevector(__s0_273, __s0_273, 1, 0); \
72025	float16x8_t __rev1_273; __rev1_273 = __builtin_shufflevector(__s1_273, __s1_273, 7, 6, 5, 4, 3, 2, 1, 0); \	61542	float16x4_t __rev1_273; __rev1_273 = __builtin_shufflevector(__s1_273, __s1_273, 3, 2, 1, 0); \
72026	float16x8_t __rev2_273; __rev2_273 = __builtin_shufflevector(__s2_273, __s2_273, 7, 6, 5, 4, 3, 2, 1, 0); \	61543	float16x8_t __rev2_273; __rev2_273 = __builtin_shufflevector(__s2_273, __s2_273, 7, 6, 5, 4, 3, 2, 1, 0); \
72027	float32x4_t __ret_273; \	61544	float32x2_t __ret_273; \
72028	__ret_273 = __noswap_vfmlalq_high_f16(__rev0_273, __rev1_273, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273)}); \	61545	__ret_273 = __noswap_vfmlal_low_f16(__rev0_273, __rev1_273, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273), __noswap_vgetq_lane_f16(__rev2_273, __p3_273)}); \
72029	__ret_273 = __builtin_shufflevector(__ret_273, __ret_273, 3, 2, 1, 0); \	61546	__ret_273 = __builtin_shufflevector(__ret_273, __ret_273, 1, 0); \
72030	__ret_273; \	61547	__ret_273; \
72031	})	61548	})
72032	#endif	61549	#endif
72033		61550
72034	#ifdef __LITTLE_ENDIAN__	61551	#ifdef __LITTLE_ENDIAN__
72035	#define vfmlal_laneq_high_f16(__p0_274, __p1_274, __p2_274, __p3_274) __extension__ ({ \	61552	#define vfmlslq_lane_high_f16(__p0_274, __p1_274, __p2_274, __p3_274) __extension__ ({ \
72036	float32x2_t __s0_274 = __p0_274; \	61553	float32x4_t __s0_274 = __p0_274; \
72037	float16x4_t __s1_274 = __p1_274; \	61554	float16x8_t __s1_274 = __p1_274; \
72038	float16x8_t __s2_274 = __p2_274; \	61555	float16x4_t __s2_274 = __p2_274; \
72039	float32x2_t __ret_274; \	61556	float32x4_t __ret_274; \
72040	__ret_274 = vfmlal_high_f16(__s0_274, __s1_274, (float16x4_t) {vgetq_lane_f16(__s2_274, __p3_274), vgetq_lane_f16(__s2_274, __p3_274), vgetq_lane_f16(__s2_274, __p3_274), vgetq_lane_f16(__s2_274, __p3_274)}); \	61557	__ret_274 = vfmlslq_high_f16(__s0_274, __s1_274, (float16x8_t) {vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274), vget_lane_f16(__s2_274, __p3_274)}); \
72041	__ret_274; \	61558	__ret_274; \
72042	})	61559	})
72043	#else	61560	#else
72044	#define vfmlal_laneq_high_f16(__p0_275, __p1_275, __p2_275, __p3_275) __extension__ ({ \	61561	#define vfmlslq_lane_high_f16(__p0_275, __p1_275, __p2_275, __p3_275) __extension__ ({ \
72045	float32x2_t __s0_275 = __p0_275; \	61562	float32x4_t __s0_275 = __p0_275; \
72046	float16x4_t __s1_275 = __p1_275; \	61563	float16x8_t __s1_275 = __p1_275; \
72047	float16x8_t __s2_275 = __p2_275; \	61564	float16x4_t __s2_275 = __p2_275; \
72048	float32x2_t __rev0_275; __rev0_275 = __builtin_shufflevector(__s0_275, __s0_275, 1, 0); \	61565	float32x4_t __rev0_275; __rev0_275 = __builtin_shufflevector(__s0_275, __s0_275, 3, 2, 1, 0); \
72049	float16x4_t __rev1_275; __rev1_275 = __builtin_shufflevector(__s1_275, __s1_275, 3, 2, 1, 0); \	61566	float16x8_t __rev1_275; __rev1_275 = __builtin_shufflevector(__s1_275, __s1_275, 7, 6, 5, 4, 3, 2, 1, 0); \
72050	float16x8_t __rev2_275; __rev2_275 = __builtin_shufflevector(__s2_275, __s2_275, 7, 6, 5, 4, 3, 2, 1, 0); \	61567	float16x4_t __rev2_275; __rev2_275 = __builtin_shufflevector(__s2_275, __s2_275, 3, 2, 1, 0); \
72051	float32x2_t __ret_275; \	61568	float32x4_t __ret_275; \
72052	__ret_275 = __noswap_vfmlal_high_f16(__rev0_275, __rev1_275, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_275, __p3_275), __noswap_vgetq_lane_f16(__rev2_275, __p3_275), __noswap_vgetq_lane_f16(__rev2_275, __p3_275), __noswap_vgetq_lane_f16(__rev2_275, __p3_275)}); \	61569	__ret_275 = __noswap_vfmlslq_high_f16(__rev0_275, __rev1_275, (float16x8_t) {__noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275), __noswap_vget_lane_f16(__rev2_275, __p3_275)}); \
72053	__ret_275 = __builtin_shufflevector(__ret_275, __ret_275, 1, 0); \	61570	__ret_275 = __builtin_shufflevector(__ret_275, __ret_275, 3, 2, 1, 0); \
72054	__ret_275; \	61571	__ret_275; \
72055	})	61572	})
72056	#endif	61573	#endif
72057		61574
72058	#ifdef __LITTLE_ENDIAN__	61575	#ifdef __LITTLE_ENDIAN__
72059	#define vfmlalq_laneq_low_f16(__p0_276, __p1_276, __p2_276, __p3_276) __extension__ ({ \	61576	#define vfmlsl_lane_high_f16(__p0_276, __p1_276, __p2_276, __p3_276) __extension__ ({ \
72060	float32x4_t __s0_276 = __p0_276; \	61577	float32x2_t __s0_276 = __p0_276; \
72061	float16x8_t __s1_276 = __p1_276; \	61578	float16x4_t __s1_276 = __p1_276; \
72062	float16x8_t __s2_276 = __p2_276; \	61579	float16x4_t __s2_276 = __p2_276; \
72063	float32x4_t __ret_276; \	61580	float32x2_t __ret_276; \
72064	__ret_276 = vfmlalq_low_f16(__s0_276, __s1_276, (float16x8_t) {vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276), vgetq_lane_f16(__s2_276, __p3_276)}); \	61581	__ret_276 = vfmlsl_high_f16(__s0_276, __s1_276, (float16x4_t) {vget_lane_f16(__s2_276, __p3_276), vget_lane_f16(__s2_276, __p3_276), vget_lane_f16(__s2_276, __p3_276), vget_lane_f16(__s2_276, __p3_276)}); \
72065	__ret_276; \	61582	__ret_276; \
72066	})	61583	})
72067	#else	61584	#else
72068	#define vfmlalq_laneq_low_f16(__p0_277, __p1_277, __p2_277, __p3_277) __extension__ ({ \	61585	#define vfmlsl_lane_high_f16(__p0_277, __p1_277, __p2_277, __p3_277) __extension__ ({ \
72069	float32x4_t __s0_277 = __p0_277; \	61586	float32x2_t __s0_277 = __p0_277; \
72070	float16x8_t __s1_277 = __p1_277; \	61587	float16x4_t __s1_277 = __p1_277; \
72071	float16x8_t __s2_277 = __p2_277; \	61588	float16x4_t __s2_277 = __p2_277; \
72072	float32x4_t __rev0_277; __rev0_277 = __builtin_shufflevector(__s0_277, __s0_277, 3, 2, 1, 0); \	61589	float32x2_t __rev0_277; __rev0_277 = __builtin_shufflevector(__s0_277, __s0_277, 1, 0); \
72073	float16x8_t __rev1_277; __rev1_277 = __builtin_shufflevector(__s1_277, __s1_277, 7, 6, 5, 4, 3, 2, 1, 0); \	61590	float16x4_t __rev1_277; __rev1_277 = __builtin_shufflevector(__s1_277, __s1_277, 3, 2, 1, 0); \
72074	float16x8_t __rev2_277; __rev2_277 = __builtin_shufflevector(__s2_277, __s2_277, 7, 6, 5, 4, 3, 2, 1, 0); \	61591	float16x4_t __rev2_277; __rev2_277 = __builtin_shufflevector(__s2_277, __s2_277, 3, 2, 1, 0); \
72075	float32x4_t __ret_277; \	61592	float32x2_t __ret_277; \
72076	__ret_277 = __noswap_vfmlalq_low_f16(__rev0_277, __rev1_277, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277), __noswap_vgetq_lane_f16(__rev2_277, __p3_277)}); \	61593	__ret_277 = __noswap_vfmlsl_high_f16(__rev0_277, __rev1_277, (float16x4_t) {__noswap_vget_lane_f16(__rev2_277, __p3_277), __noswap_vget_lane_f16(__rev2_277, __p3_277), __noswap_vget_lane_f16(__rev2_277, __p3_277), __noswap_vget_lane_f16(__rev2_277, __p3_277)}); \
72077	__ret_277 = __builtin_shufflevector(__ret_277, __ret_277, 3, 2, 1, 0); \	61594	__ret_277 = __builtin_shufflevector(__ret_277, __ret_277, 1, 0); \
72078	__ret_277; \	61595	__ret_277; \
72079	})	61596	})
72080	#endif	61597	#endif
72081		61598
72082	#ifdef __LITTLE_ENDIAN__	61599	#ifdef __LITTLE_ENDIAN__
72083	#define vfmlal_laneq_low_f16(__p0_278, __p1_278, __p2_278, __p3_278) __extension__ ({ \	61600	#define vfmlslq_lane_low_f16(__p0_278, __p1_278, __p2_278, __p3_278) __extension__ ({ \
72084	float32x2_t __s0_278 = __p0_278; \	61601	float32x4_t __s0_278 = __p0_278; \
72085	float16x4_t __s1_278 = __p1_278; \	61602	float16x8_t __s1_278 = __p1_278; \
72086	float16x8_t __s2_278 = __p2_278; \	61603	float16x4_t __s2_278 = __p2_278; \
72087	float32x2_t __ret_278; \	61604	float32x4_t __ret_278; \
72088	__ret_278 = vfmlal_low_f16(__s0_278, __s1_278, (float16x4_t) {vgetq_lane_f16(__s2_278, __p3_278), vgetq_lane_f16(__s2_278, __p3_278), vgetq_lane_f16(__s2_278, __p3_278), vgetq_lane_f16(__s2_278, __p3_278)}); \	61605	__ret_278 = vfmlslq_low_f16(__s0_278, __s1_278, (float16x8_t) {vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278), vget_lane_f16(__s2_278, __p3_278)}); \
72089	__ret_278; \	61606	__ret_278; \
72090	})	61607	})
72091	#else	61608	#else
72092	#define vfmlal_laneq_low_f16(__p0_279, __p1_279, __p2_279, __p3_279) __extension__ ({ \	61609	#define vfmlslq_lane_low_f16(__p0_279, __p1_279, __p2_279, __p3_279) __extension__ ({ \
72093	float32x2_t __s0_279 = __p0_279; \	61610	float32x4_t __s0_279 = __p0_279; \
72094	float16x4_t __s1_279 = __p1_279; \	61611	float16x8_t __s1_279 = __p1_279; \
72095	float16x8_t __s2_279 = __p2_279; \	61612	float16x4_t __s2_279 = __p2_279; \
72096	float32x2_t __rev0_279; __rev0_279 = __builtin_shufflevector(__s0_279, __s0_279, 1, 0); \	61613	float32x4_t __rev0_279; __rev0_279 = __builtin_shufflevector(__s0_279, __s0_279, 3, 2, 1, 0); \
72097	float16x4_t __rev1_279; __rev1_279 = __builtin_shufflevector(__s1_279, __s1_279, 3, 2, 1, 0); \	61614	float16x8_t __rev1_279; __rev1_279 = __builtin_shufflevector(__s1_279, __s1_279, 7, 6, 5, 4, 3, 2, 1, 0); \
72098	float16x8_t __rev2_279; __rev2_279 = __builtin_shufflevector(__s2_279, __s2_279, 7, 6, 5, 4, 3, 2, 1, 0); \	61615	float16x4_t __rev2_279; __rev2_279 = __builtin_shufflevector(__s2_279, __s2_279, 3, 2, 1, 0); \
72099	float32x2_t __ret_279; \	61616	float32x4_t __ret_279; \
72100	__ret_279 = __noswap_vfmlal_low_f16(__rev0_279, __rev1_279, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_279, __p3_279), __noswap_vgetq_lane_f16(__rev2_279, __p3_279), __noswap_vgetq_lane_f16(__rev2_279, __p3_279), __noswap_vgetq_lane_f16(__rev2_279, __p3_279)}); \	61617	__ret_279 = __noswap_vfmlslq_low_f16(__rev0_279, __rev1_279, (float16x8_t) {__noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279), __noswap_vget_lane_f16(__rev2_279, __p3_279)}); \
72101	__ret_279 = __builtin_shufflevector(__ret_279, __ret_279, 1, 0); \	61618	__ret_279 = __builtin_shufflevector(__ret_279, __ret_279, 3, 2, 1, 0); \
72102	__ret_279; \	61619	__ret_279; \
72103	})	61620	})
72104	#endif	61621	#endif
72105		61622
72106	#ifdef __LITTLE_ENDIAN__	61623	#ifdef __LITTLE_ENDIAN__
72107	#define vfmlslq_lane_high_f16(__p0_280, __p1_280, __p2_280, __p3_280) __extension__ ({ \	61624	#define vfmlsl_lane_low_f16(__p0_280, __p1_280, __p2_280, __p3_280) __extension__ ({ \
72108	float32x4_t __s0_280 = __p0_280; \	61625	float32x2_t __s0_280 = __p0_280; \
72109	float16x8_t __s1_280 = __p1_280; \	61626	float16x4_t __s1_280 = __p1_280; \
72110	float16x4_t __s2_280 = __p2_280; \	61627	float16x4_t __s2_280 = __p2_280; \
72111	float32x4_t __ret_280; \	61628	float32x2_t __ret_280; \
72112	__ret_280 = vfmlslq_high_f16(__s0_280, __s1_280, (float16x8_t) {vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280)}); \	61629	__ret_280 = vfmlsl_low_f16(__s0_280, __s1_280, (float16x4_t) {vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280), vget_lane_f16(__s2_280, __p3_280)}); \
72113	__ret_280; \	61630	__ret_280; \
72114	})	61631	})
72115	#else	61632	#else
72116	#define vfmlslq_lane_high_f16(__p0_281, __p1_281, __p2_281, __p3_281) __extension__ ({ \	61633	#define vfmlsl_lane_low_f16(__p0_281, __p1_281, __p2_281, __p3_281) __extension__ ({ \
72117	float32x4_t __s0_281 = __p0_281; \	61634	float32x2_t __s0_281 = __p0_281; \
72118	float16x8_t __s1_281 = __p1_281; \	61635	float16x4_t __s1_281 = __p1_281; \
72119	float16x4_t __s2_281 = __p2_281; \	61636	float16x4_t __s2_281 = __p2_281; \
72120	float32x4_t __rev0_281; __rev0_281 = __builtin_shufflevector(__s0_281, __s0_281, 3, 2, 1, 0); \	61637	float32x2_t __rev0_281; __rev0_281 = __builtin_shufflevector(__s0_281, __s0_281, 1, 0); \
72121	float16x8_t __rev1_281; __rev1_281 = __builtin_shufflevector(__s1_281, __s1_281, 7, 6, 5, 4, 3, 2, 1, 0); \	61638	float16x4_t __rev1_281; __rev1_281 = __builtin_shufflevector(__s1_281, __s1_281, 3, 2, 1, 0); \
72122	float16x4_t __rev2_281; __rev2_281 = __builtin_shufflevector(__s2_281, __s2_281, 3, 2, 1, 0); \	61639	float16x4_t __rev2_281; __rev2_281 = __builtin_shufflevector(__s2_281, __s2_281, 3, 2, 1, 0); \
72123	float32x4_t __ret_281; \	61640	float32x2_t __ret_281; \
72124	__ret_281 = __noswap_vfmlslq_high_f16(__rev0_281, __rev1_281, (float16x8_t) {__noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281)}); \	61641	__ret_281 = __noswap_vfmlsl_low_f16(__rev0_281, __rev1_281, (float16x4_t) {__noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281), __noswap_vget_lane_f16(__rev2_281, __p3_281)}); \
72125	__ret_281 = __builtin_shufflevector(__ret_281, __ret_281, 3, 2, 1, 0); \	61642	__ret_281 = __builtin_shufflevector(__ret_281, __ret_281, 1, 0); \
72126	__ret_281; \	61643	__ret_281; \
72127	})	61644	})
72128	#endif	61645	#endif
72129		61646
72130	#ifdef __LITTLE_ENDIAN__	61647	#ifdef __LITTLE_ENDIAN__
72131	#define vfmlsl_lane_high_f16(__p0_282, __p1_282, __p2_282, __p3_282) __extension__ ({ \	61648	#define vfmlslq_laneq_high_f16(__p0_282, __p1_282, __p2_282, __p3_282) __extension__ ({ \
72132	float32x2_t __s0_282 = __p0_282; \	61649	float32x4_t __s0_282 = __p0_282; \
72133	float16x4_t __s1_282 = __p1_282; \	61650	float16x8_t __s1_282 = __p1_282; \
72134	float16x4_t __s2_282 = __p2_282; \	61651	float16x8_t __s2_282 = __p2_282; \
72135	float32x2_t __ret_282; \	61652	float32x4_t __ret_282; \
72136	__ret_282 = vfmlsl_high_f16(__s0_282, __s1_282, (float16x4_t) {vget_lane_f16(__s2_282, __p3_282), vget_lane_f16(__s2_282, __p3_282), vget_lane_f16(__s2_282, __p3_282), vget_lane_f16(__s2_282, __p3_282)}); \	61653	__ret_282 = vfmlslq_high_f16(__s0_282, __s1_282, (float16x8_t) {vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282), vgetq_lane_f16(__s2_282, __p3_282)}); \
72137	__ret_282; \	61654	__ret_282; \
72138	})	61655	})
72139	#else	61656	#else
72140	#define vfmlsl_lane_high_f16(__p0_283, __p1_283, __p2_283, __p3_283) __extension__ ({ \	61657	#define vfmlslq_laneq_high_f16(__p0_283, __p1_283, __p2_283, __p3_283) __extension__ ({ \
72141	float32x2_t __s0_283 = __p0_283; \	61658	float32x4_t __s0_283 = __p0_283; \
72142	float16x4_t __s1_283 = __p1_283; \	61659	float16x8_t __s1_283 = __p1_283; \
72143	float16x4_t __s2_283 = __p2_283; \	61660	float16x8_t __s2_283 = __p2_283; \
72144	float32x2_t __rev0_283; __rev0_283 = __builtin_shufflevector(__s0_283, __s0_283, 1, 0); \	61661	float32x4_t __rev0_283; __rev0_283 = __builtin_shufflevector(__s0_283, __s0_283, 3, 2, 1, 0); \
72145	float16x4_t __rev1_283; __rev1_283 = __builtin_shufflevector(__s1_283, __s1_283, 3, 2, 1, 0); \	61662	float16x8_t __rev1_283; __rev1_283 = __builtin_shufflevector(__s1_283, __s1_283, 7, 6, 5, 4, 3, 2, 1, 0); \
72146	float16x4_t __rev2_283; __rev2_283 = __builtin_shufflevector(__s2_283, __s2_283, 3, 2, 1, 0); \	61663	float16x8_t __rev2_283; __rev2_283 = __builtin_shufflevector(__s2_283, __s2_283, 7, 6, 5, 4, 3, 2, 1, 0); \
72147	float32x2_t __ret_283; \	61664	float32x4_t __ret_283; \
72148	__ret_283 = __noswap_vfmlsl_high_f16(__rev0_283, __rev1_283, (float16x4_t) {__noswap_vget_lane_f16(__rev2_283, __p3_283), __noswap_vget_lane_f16(__rev2_283, __p3_283), __noswap_vget_lane_f16(__rev2_283, __p3_283), __noswap_vget_lane_f16(__rev2_283, __p3_283)}); \	61665	__ret_283 = __noswap_vfmlslq_high_f16(__rev0_283, __rev1_283, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283), __noswap_vgetq_lane_f16(__rev2_283, __p3_283)}); \
72149	__ret_283 = __builtin_shufflevector(__ret_283, __ret_283, 1, 0); \	61666	__ret_283 = __builtin_shufflevector(__ret_283, __ret_283, 3, 2, 1, 0); \
72150	__ret_283; \	61667	__ret_283; \
72151	})	61668	})
72152	#endif	61669	#endif
72153		61670
72154	#ifdef __LITTLE_ENDIAN__	61671	#ifdef __LITTLE_ENDIAN__
72155	#define vfmlslq_lane_low_f16(__p0_284, __p1_284, __p2_284, __p3_284) __extension__ ({ \	61672	#define vfmlsl_laneq_high_f16(__p0_284, __p1_284, __p2_284, __p3_284) __extension__ ({ \
72156	float32x4_t __s0_284 = __p0_284; \	61673	float32x2_t __s0_284 = __p0_284; \
72157	float16x8_t __s1_284 = __p1_284; \	61674	float16x4_t __s1_284 = __p1_284; \
72158	float16x4_t __s2_284 = __p2_284; \	61675	float16x8_t __s2_284 = __p2_284; \
72159	float32x4_t __ret_284; \	61676	float32x2_t __ret_284; \
72160	__ret_284 = vfmlslq_low_f16(__s0_284, __s1_284, (float16x8_t) {vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284), vget_lane_f16(__s2_284, __p3_284)}); \	61677	__ret_284 = vfmlsl_high_f16(__s0_284, __s1_284, (float16x4_t) {vgetq_lane_f16(__s2_284, __p3_284), vgetq_lane_f16(__s2_284, __p3_284), vgetq_lane_f16(__s2_284, __p3_284), vgetq_lane_f16(__s2_284, __p3_284)}); \
72161	__ret_284; \	61678	__ret_284; \
72162	})	61679	})
72163	#else	61680	#else
72164	#define vfmlslq_lane_low_f16(__p0_285, __p1_285, __p2_285, __p3_285) __extension__ ({ \	61681	#define vfmlsl_laneq_high_f16(__p0_285, __p1_285, __p2_285, __p3_285) __extension__ ({ \
72165	float32x4_t __s0_285 = __p0_285; \	61682	float32x2_t __s0_285 = __p0_285; \
72166	float16x8_t __s1_285 = __p1_285; \	61683	float16x4_t __s1_285 = __p1_285; \
72167	float16x4_t __s2_285 = __p2_285; \	61684	float16x8_t __s2_285 = __p2_285; \
72168	float32x4_t __rev0_285; __rev0_285 = __builtin_shufflevector(__s0_285, __s0_285, 3, 2, 1, 0); \	61685	float32x2_t __rev0_285; __rev0_285 = __builtin_shufflevector(__s0_285, __s0_285, 1, 0); \
72169	float16x8_t __rev1_285; __rev1_285 = __builtin_shufflevector(__s1_285, __s1_285, 7, 6, 5, 4, 3, 2, 1, 0); \	61686	float16x4_t __rev1_285; __rev1_285 = __builtin_shufflevector(__s1_285, __s1_285, 3, 2, 1, 0); \
72170	float16x4_t __rev2_285; __rev2_285 = __builtin_shufflevector(__s2_285, __s2_285, 3, 2, 1, 0); \	61687	float16x8_t __rev2_285; __rev2_285 = __builtin_shufflevector(__s2_285, __s2_285, 7, 6, 5, 4, 3, 2, 1, 0); \
72171	float32x4_t __ret_285; \	61688	float32x2_t __ret_285; \
72172	__ret_285 = __noswap_vfmlslq_low_f16(__rev0_285, __rev1_285, (float16x8_t) {__noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285), __noswap_vget_lane_f16(__rev2_285, __p3_285)}); \	61689	__ret_285 = __noswap_vfmlsl_high_f16(__rev0_285, __rev1_285, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_285, __p3_285), __noswap_vgetq_lane_f16(__rev2_285, __p3_285), __noswap_vgetq_lane_f16(__rev2_285, __p3_285), __noswap_vgetq_lane_f16(__rev2_285, __p3_285)}); \
72173	__ret_285 = __builtin_shufflevector(__ret_285, __ret_285, 3, 2, 1, 0); \	61690	__ret_285 = __builtin_shufflevector(__ret_285, __ret_285, 1, 0); \
72174	__ret_285; \	61691	__ret_285; \
72175	})	61692	})
72176	#endif	61693	#endif
72177		61694
72178	#ifdef __LITTLE_ENDIAN__	61695	#ifdef __LITTLE_ENDIAN__
72179	#define vfmlsl_lane_low_f16(__p0_286, __p1_286, __p2_286, __p3_286) __extension__ ({ \	61696	#define vfmlslq_laneq_low_f16(__p0_286, __p1_286, __p2_286, __p3_286) __extension__ ({ \
72180	float32x2_t __s0_286 = __p0_286; \	61697	float32x4_t __s0_286 = __p0_286; \
72181	float16x4_t __s1_286 = __p1_286; \	61698	float16x8_t __s1_286 = __p1_286; \
72182	float16x4_t __s2_286 = __p2_286; \	61699	float16x8_t __s2_286 = __p2_286; \
72183	float32x2_t __ret_286; \	61700	float32x4_t __ret_286; \
72184	__ret_286 = vfmlsl_low_f16(__s0_286, __s1_286, (float16x4_t) {vget_lane_f16(__s2_286, __p3_286), vget_lane_f16(__s2_286, __p3_286), vget_lane_f16(__s2_286, __p3_286), vget_lane_f16(__s2_286, __p3_286)}); \	61701	__ret_286 = vfmlslq_low_f16(__s0_286, __s1_286, (float16x8_t) {vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286), vgetq_lane_f16(__s2_286, __p3_286)}); \
72185	__ret_286; \	61702	__ret_286; \
72186	})	61703	})
72187	#else	61704	#else
72188	#define vfmlsl_lane_low_f16(__p0_287, __p1_287, __p2_287, __p3_287) __extension__ ({ \	61705	#define vfmlslq_laneq_low_f16(__p0_287, __p1_287, __p2_287, __p3_287) __extension__ ({ \
72189	float32x2_t __s0_287 = __p0_287; \	61706	float32x4_t __s0_287 = __p0_287; \
72190	float16x4_t __s1_287 = __p1_287; \	61707	float16x8_t __s1_287 = __p1_287; \
72191	float16x4_t __s2_287 = __p2_287; \	61708	float16x8_t __s2_287 = __p2_287; \
72192	float32x2_t __rev0_287; __rev0_287 = __builtin_shufflevector(__s0_287, __s0_287, 1, 0); \	61709	float32x4_t __rev0_287; __rev0_287 = __builtin_shufflevector(__s0_287, __s0_287, 3, 2, 1, 0); \
72193	float16x4_t __rev1_287; __rev1_287 = __builtin_shufflevector(__s1_287, __s1_287, 3, 2, 1, 0); \	61710	float16x8_t __rev1_287; __rev1_287 = __builtin_shufflevector(__s1_287, __s1_287, 7, 6, 5, 4, 3, 2, 1, 0); \
72194	float16x4_t __rev2_287; __rev2_287 = __builtin_shufflevector(__s2_287, __s2_287, 3, 2, 1, 0); \	61711	float16x8_t __rev2_287; __rev2_287 = __builtin_shufflevector(__s2_287, __s2_287, 7, 6, 5, 4, 3, 2, 1, 0); \
72195	float32x2_t __ret_287; \	61712	float32x4_t __ret_287; \
72196	__ret_287 = __noswap_vfmlsl_low_f16(__rev0_287, __rev1_287, (float16x4_t) {__noswap_vget_lane_f16(__rev2_287, __p3_287), __noswap_vget_lane_f16(__rev2_287, __p3_287), __noswap_vget_lane_f16(__rev2_287, __p3_287), __noswap_vget_lane_f16(__rev2_287, __p3_287)}); \	61713	__ret_287 = __noswap_vfmlslq_low_f16(__rev0_287, __rev1_287, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287), __noswap_vgetq_lane_f16(__rev2_287, __p3_287)}); \
72197	__ret_287 = __builtin_shufflevector(__ret_287, __ret_287, 1, 0); \	61714	__ret_287 = __builtin_shufflevector(__ret_287, __ret_287, 3, 2, 1, 0); \
72198	__ret_287; \	61715	__ret_287; \
72199	})	61716	})
72200	#endif	61717	#endif
72201		61718
72202	#ifdef __LITTLE_ENDIAN__	61719	#ifdef __LITTLE_ENDIAN__
72203	#define vfmlslq_laneq_high_f16(__p0_288, __p1_288, __p2_288, __p3_288) __extension__ ({ \	61720	#define vfmlsl_laneq_low_f16(__p0_288, __p1_288, __p2_288, __p3_288) __extension__ ({ \
72204	float32x4_t __s0_288 = __p0_288; \	61721	float32x2_t __s0_288 = __p0_288; \
72205	float16x8_t __s1_288 = __p1_288; \	61722	float16x4_t __s1_288 = __p1_288; \
72206	float16x8_t __s2_288 = __p2_288; \	61723	float16x8_t __s2_288 = __p2_288; \
72207	float32x4_t __ret_288; \	61724	float32x2_t __ret_288; \
72208	__ret_288 = vfmlslq_high_f16(__s0_288, __s1_288, (float16x8_t) {vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288)}); \	61725	__ret_288 = vfmlsl_low_f16(__s0_288, __s1_288, (float16x4_t) {vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288), vgetq_lane_f16(__s2_288, __p3_288)}); \
72209	__ret_288; \	61726	__ret_288; \
72210	})	61727	})
72211	#else	61728	#else
72212	#define vfmlslq_laneq_high_f16(__p0_289, __p1_289, __p2_289, __p3_289) __extension__ ({ \	61729	#define vfmlsl_laneq_low_f16(__p0_289, __p1_289, __p2_289, __p3_289) __extension__ ({ \
72213	float32x4_t __s0_289 = __p0_289; \	61730	float32x2_t __s0_289 = __p0_289; \
72214	float16x8_t __s1_289 = __p1_289; \	61731	float16x4_t __s1_289 = __p1_289; \
72215	float16x8_t __s2_289 = __p2_289; \	61732	float16x8_t __s2_289 = __p2_289; \
72216	float32x4_t __rev0_289; __rev0_289 = __builtin_shufflevector(__s0_289, __s0_289, 3, 2, 1, 0); \	61733	float32x2_t __rev0_289; __rev0_289 = __builtin_shufflevector(__s0_289, __s0_289, 1, 0); \
72217	float16x8_t __rev1_289; __rev1_289 = __builtin_shufflevector(__s1_289, __s1_289, 7, 6, 5, 4, 3, 2, 1, 0); \	61734	float16x4_t __rev1_289; __rev1_289 = __builtin_shufflevector(__s1_289, __s1_289, 3, 2, 1, 0); \
72218	float16x8_t __rev2_289; __rev2_289 = __builtin_shufflevector(__s2_289, __s2_289, 7, 6, 5, 4, 3, 2, 1, 0); \	61735	float16x8_t __rev2_289; __rev2_289 = __builtin_shufflevector(__s2_289, __s2_289, 7, 6, 5, 4, 3, 2, 1, 0); \
72219	float32x4_t __ret_289; \	61736	float32x2_t __ret_289; \
72220	__ret_289 = __noswap_vfmlslq_high_f16(__rev0_289, __rev1_289, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289)}); \	61737	__ret_289 = __noswap_vfmlsl_low_f16(__rev0_289, __rev1_289, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289), __noswap_vgetq_lane_f16(__rev2_289, __p3_289)}); \
72221	__ret_289 = __builtin_shufflevector(__ret_289, __ret_289, 3, 2, 1, 0); \	61738	__ret_289 = __builtin_shufflevector(__ret_289, __ret_289, 1, 0); \
72222	__ret_289; \	61739	__ret_289; \
72223	})	61740	})
72224	#endif	61741	#endif
72225		61742
		61743	#endif
		61744	#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(__aarch64__)
72226	#ifdef __LITTLE_ENDIAN__	61745	#ifdef __LITTLE_ENDIAN__
72227	#define vfmlsl_laneq_high_f16(__p0_290, __p1_290, __p2_290, __p3_290) __extension__ ({ \	61746	#define vmulh_lane_f16(__p0_290, __p1_290, __p2_290) __extension__ ({ \
72228	float32x2_t __s0_290 = __p0_290; \	61747	float16_t __s0_290 = __p0_290; \
72229	float16x4_t __s1_290 = __p1_290; \	61748	float16x4_t __s1_290 = __p1_290; \
72230	float16x8_t __s2_290 = __p2_290; \	61749	float16_t __ret_290; \
72231	float32x2_t __ret_290; \	61750	__ret_290 = __s0_290 * vget_lane_f16(__s1_290, __p2_290); \
72232	__ret_290 = vfmlsl_high_f16(__s0_290, __s1_290, (float16x4_t) {vgetq_lane_f16(__s2_290, __p3_290), vgetq_lane_f16(__s2_290, __p3_290), vgetq_lane_f16(__s2_290, __p3_290), vgetq_lane_f16(__s2_290, __p3_290)}); \
72233	__ret_290; \	61751	__ret_290; \
72234	})	61752	})
72235	#else	61753	#else
72236	#define vfmlsl_laneq_high_f16(__p0_291, __p1_291, __p2_291, __p3_291) __extension__ ({ \	61754	#define vmulh_lane_f16(__p0_291, __p1_291, __p2_291) __extension__ ({ \
72237	float32x2_t __s0_291 = __p0_291; \	61755	float16_t __s0_291 = __p0_291; \
72238	float16x4_t __s1_291 = __p1_291; \	61756	float16x4_t __s1_291 = __p1_291; \
72239	float16x8_t __s2_291 = __p2_291; \
72240	float32x2_t __rev0_291; __rev0_291 = __builtin_shufflevector(__s0_291, __s0_291, 1, 0); \
72241	float16x4_t __rev1_291; __rev1_291 = __builtin_shufflevector(__s1_291, __s1_291, 3, 2, 1, 0); \	61757	float16x4_t __rev1_291; __rev1_291 = __builtin_shufflevector(__s1_291, __s1_291, 3, 2, 1, 0); \
72242	float16x8_t __rev2_291; __rev2_291 = __builtin_shufflevector(__s2_291, __s2_291, 7, 6, 5, 4, 3, 2, 1, 0); \	61758	float16_t __ret_291; \
72243	float32x2_t __ret_291; \	61759	__ret_291 = __s0_291 * __noswap_vget_lane_f16(__rev1_291, __p2_291); \
72244	__ret_291 = __noswap_vfmlsl_high_f16(__rev0_291, __rev1_291, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_291, __p3_291), __noswap_vgetq_lane_f16(__rev2_291, __p3_291), __noswap_vgetq_lane_f16(__rev2_291, __p3_291), __noswap_vgetq_lane_f16(__rev2_291, __p3_291)}); \
72245	__ret_291 = __builtin_shufflevector(__ret_291, __ret_291, 1, 0); \
72246	__ret_291; \	61760	__ret_291; \
72247	})	61761	})
72248	#endif	61762	#endif
72249		61763
72250	#ifdef __LITTLE_ENDIAN__	61764	#ifdef __LITTLE_ENDIAN__
72251	#define vfmlslq_laneq_low_f16(__p0_292, __p1_292, __p2_292, __p3_292) __extension__ ({ \	61765	#define vmulh_laneq_f16(__p0_292, __p1_292, __p2_292) __extension__ ({ \
72252	float32x4_t __s0_292 = __p0_292; \	61766	float16_t __s0_292 = __p0_292; \
72253	float16x8_t __s1_292 = __p1_292; \	61767	float16x8_t __s1_292 = __p1_292; \
72254	float16x8_t __s2_292 = __p2_292; \	61768	float16_t __ret_292; \
72255	float32x4_t __ret_292; \	61769	__ret_292 = __s0_292 * vgetq_lane_f16(__s1_292, __p2_292); \
72256	__ret_292 = vfmlslq_low_f16(__s0_292, __s1_292, (float16x8_t) {vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292), vgetq_lane_f16(__s2_292, __p3_292)}); \
72257	__ret_292; \	61770	__ret_292; \
72258	})	61771	})
72259	#else	61772	#else
72260	#define vfmlslq_laneq_low_f16(__p0_293, __p1_293, __p2_293, __p3_293) __extension__ ({ \	61773	#define vmulh_laneq_f16(__p0_293, __p1_293, __p2_293) __extension__ ({ \
72261	float32x4_t __s0_293 = __p0_293; \	61774	float16_t __s0_293 = __p0_293; \
72262	float16x8_t __s1_293 = __p1_293; \	61775	float16x8_t __s1_293 = __p1_293; \
72263	float16x8_t __s2_293 = __p2_293; \
72264	float32x4_t __rev0_293; __rev0_293 = __builtin_shufflevector(__s0_293, __s0_293, 3, 2, 1, 0); \
72265	float16x8_t __rev1_293; __rev1_293 = __builtin_shufflevector(__s1_293, __s1_293, 7, 6, 5, 4, 3, 2, 1, 0); \	61776	float16x8_t __rev1_293; __rev1_293 = __builtin_shufflevector(__s1_293, __s1_293, 7, 6, 5, 4, 3, 2, 1, 0); \
72266	float16x8_t __rev2_293; __rev2_293 = __builtin_shufflevector(__s2_293, __s2_293, 7, 6, 5, 4, 3, 2, 1, 0); \	61777	float16_t __ret_293; \
72267	float32x4_t __ret_293; \	61778	__ret_293 = __s0_293 * __noswap_vgetq_lane_f16(__rev1_293, __p2_293); \
72268	__ret_293 = __noswap_vfmlslq_low_f16(__rev0_293, __rev1_293, (float16x8_t) {__noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293), __noswap_vgetq_lane_f16(__rev2_293, __p3_293)}); \
72269	__ret_293 = __builtin_shufflevector(__ret_293, __ret_293, 3, 2, 1, 0); \
72270	__ret_293; \	61779	__ret_293; \
72271	})	61780	})
72272	#endif	61781	#endif
72273		61782
72274	#ifdef __LITTLE_ENDIAN__
72275	#define vfmlsl_laneq_low_f16(__p0_294, __p1_294, __p2_294, __p3_294) __extension__ ({ \
72276	float32x2_t __s0_294 = __p0_294; \
72277	float16x4_t __s1_294 = __p1_294; \
72278	float16x8_t __s2_294 = __p2_294; \
72279	float32x2_t __ret_294; \
72280	__ret_294 = vfmlsl_low_f16(__s0_294, __s1_294, (float16x4_t) {vgetq_lane_f16(__s2_294, __p3_294), vgetq_lane_f16(__s2_294, __p3_294), vgetq_lane_f16(__s2_294, __p3_294), vgetq_lane_f16(__s2_294, __p3_294)}); \
72281	__ret_294; \
72282	})
72283	#else
72284	#define vfmlsl_laneq_low_f16(__p0_295, __p1_295, __p2_295, __p3_295) __extension__ ({ \
72285	float32x2_t __s0_295 = __p0_295; \
72286	float16x4_t __s1_295 = __p1_295; \
72287	float16x8_t __s2_295 = __p2_295; \
72288	float32x2_t __rev0_295; __rev0_295 = __builtin_shufflevector(__s0_295, __s0_295, 1, 0); \
72289	float16x4_t __rev1_295; __rev1_295 = __builtin_shufflevector(__s1_295, __s1_295, 3, 2, 1, 0); \
72290	float16x8_t __rev2_295; __rev2_295 = __builtin_shufflevector(__s2_295, __s2_295, 7, 6, 5, 4, 3, 2, 1, 0); \
72291	float32x2_t __ret_295; \
72292	__ret_295 = __noswap_vfmlsl_low_f16(__rev0_295, __rev1_295, (float16x4_t) {__noswap_vgetq_lane_f16(__rev2_295, __p3_295), __noswap_vgetq_lane_f16(__rev2_295, __p3_295), __noswap_vgetq_lane_f16(__rev2_295, __p3_295), __noswap_vgetq_lane_f16(__rev2_295, __p3_295)}); \
72293	__ret_295 = __builtin_shufflevector(__ret_295, __ret_295, 1, 0); \
72294	__ret_295; \
72295	})
72296	#endif
72297
72298	#endif
72299	#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(__aarch64__)
72300	#ifdef __LITTLE_ENDIAN__
72301	#define vmulh_lane_f16(__p0_296, __p1_296, __p2_296) __extension__ ({ \
72302	float16_t __s0_296 = __p0_296; \
72303	float16x4_t __s1_296 = __p1_296; \
72304	float16_t __ret_296; \
72305	__ret_296 = __s0_296 * vget_lane_f16(__s1_296, __p2_296); \
72306	__ret_296; \
72307	})
72308	#else
72309	#define vmulh_lane_f16(__p0_297, __p1_297, __p2_297) __extension__ ({ \
72310	float16_t __s0_297 = __p0_297; \
72311	float16x4_t __s1_297 = __p1_297; \
72312	float16x4_t __rev1_297; __rev1_297 = __builtin_shufflevector(__s1_297, __s1_297, 3, 2, 1, 0); \
72313	float16_t __ret_297; \
72314	__ret_297 = __s0_297 * __noswap_vget_lane_f16(__rev1_297, __p2_297); \
72315	__ret_297; \
72316	})
72317	#endif
72318
72319	#ifdef __LITTLE_ENDIAN__
72320	#define vmulh_laneq_f16(__p0_298, __p1_298, __p2_298) __extension__ ({ \
72321	float16_t __s0_298 = __p0_298; \
72322	float16x8_t __s1_298 = __p1_298; \
72323	float16_t __ret_298; \
72324	__ret_298 = __s0_298 * vgetq_lane_f16(__s1_298, __p2_298); \
72325	__ret_298; \
72326	})
72327	#else
72328	#define vmulh_laneq_f16(__p0_299, __p1_299, __p2_299) __extension__ ({ \
72329	float16_t __s0_299 = __p0_299; \
72330	float16x8_t __s1_299 = __p1_299; \
72331	float16x8_t __rev1_299; __rev1_299 = __builtin_shufflevector(__s1_299, __s1_299, 7, 6, 5, 4, 3, 2, 1, 0); \
72332	float16_t __ret_299; \
72333	__ret_299 = __s0_299 * __noswap_vgetq_lane_f16(__rev1_299, __p2_299); \
72334	__ret_299; \
72335	})
72336	#endif
72337
72338	#endif	61783	#endif
72339	#if defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)	61784	#if defined(__ARM_FEATURE_QRDMX) && defined(__aarch64__)
72340	#ifdef __LITTLE_ENDIAN__
72341	__ai int32_t vqrdmlahs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {	61785	__ai int32_t vqrdmlahs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
72342	int32_t __ret;	61786	int32_t __ret;
72343	__ret = vqadds_s32(__p0, vqrdmulhs_s32(__p1, __p2));	61787	__ret = vqadds_s32(__p0, vqrdmulhs_s32(__p1, __p2));
72344	return __ret;	61788	return __ret;
72345	}	61789	}
72346	#else
72347	__ai int32_t vqrdmlahs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
72348	int32_t __ret;
72349	__ret = __noswap_vqadds_s32(__p0, __noswap_vqrdmulhs_s32(__p1, __p2));
72350	return __ret;
72351	}
72352	#endif
72353
72354	#ifdef __LITTLE_ENDIAN__
72355	__ai int16_t vqrdmlahh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {	61790	__ai int16_t vqrdmlahh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
72356	int16_t __ret;	61791	int16_t __ret;
72357	__ret = vqaddh_s16(__p0, vqrdmulhh_s16(__p1, __p2));	61792	__ret = vqaddh_s16(__p0, vqrdmulhh_s16(__p1, __p2));
72358	return __ret;	61793	return __ret;
72359	}	61794	}
72360	#else
72361	__ai int16_t vqrdmlahh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
72362	int16_t __ret;
72363	__ret = __noswap_vqaddh_s16(__p0, __noswap_vqrdmulhh_s16(__p1, __p2));
72364	return __ret;
72365	}
72366	#endif
72367
72368	#ifdef __LITTLE_ENDIAN__	61795	#ifdef __LITTLE_ENDIAN__
72369	#define vqrdmlahs_lane_s32(__p0_300, __p1_300, __p2_300, __p3_300) __extension__ ({ \	61796	#define vqrdmlahs_lane_s32(__p0_294, __p1_294, __p2_294, __p3_294) __extension__ ({ \
72370	int32_t __s0_300 = __p0_300; \	61797	int32_t __s0_294 = __p0_294; \
72371	int32_t __s1_300 = __p1_300; \	61798	int32_t __s1_294 = __p1_294; \
72372	int32x2_t __s2_300 = __p2_300; \	61799	int32x2_t __s2_294 = __p2_294; \
72373	int32_t __ret_300; \	61800	int32_t __ret_294; \
72374	__ret_300 = vqadds_s32(__s0_300, vqrdmulhs_s32(__s1_300, vget_lane_s32(__s2_300, __p3_300))); \	61801	__ret_294 = vqadds_s32(__s0_294, vqrdmulhs_s32(__s1_294, vget_lane_s32(__s2_294, __p3_294))); \
72375	__ret_300; \	61802	__ret_294; \
72376	})	61803	})
72377	#else	61804	#else
72378	#define vqrdmlahs_lane_s32(__p0_301, __p1_301, __p2_301, __p3_301) __extension__ ({ \	61805	#define vqrdmlahs_lane_s32(__p0_295, __p1_295, __p2_295, __p3_295) __extension__ ({ \
72379	int32_t __s0_301 = __p0_301; \	61806	int32_t __s0_295 = __p0_295; \
72380	int32_t __s1_301 = __p1_301; \	61807	int32_t __s1_295 = __p1_295; \
72381	int32x2_t __s2_301 = __p2_301; \	61808	int32x2_t __s2_295 = __p2_295; \
72382	int32x2_t __rev2_301; __rev2_301 = __builtin_shufflevector(__s2_301, __s2_301, 1, 0); \	61809	int32x2_t __rev2_295; __rev2_295 = __builtin_shufflevector(__s2_295, __s2_295, 1, 0); \
72383	int32_t __ret_301; \	61810	int32_t __ret_295; \
72384	__ret_301 = __noswap_vqadds_s32(__s0_301, __noswap_vqrdmulhs_s32(__s1_301, __noswap_vget_lane_s32(__rev2_301, __p3_301))); \	61811	__ret_295 = vqadds_s32(__s0_295, vqrdmulhs_s32(__s1_295, __noswap_vget_lane_s32(__rev2_295, __p3_295))); \
72385	__ret_301; \	61812	__ret_295; \
72386	})	61813	})
72387	#endif	61814	#endif
72388		61815
72389	#ifdef __LITTLE_ENDIAN__	61816	#ifdef __LITTLE_ENDIAN__
72390	#define vqrdmlahh_lane_s16(__p0_302, __p1_302, __p2_302, __p3_302) __extension__ ({ \	61817	#define vqrdmlahh_lane_s16(__p0_296, __p1_296, __p2_296, __p3_296) __extension__ ({ \
72391	int16_t __s0_302 = __p0_302; \	61818	int16_t __s0_296 = __p0_296; \
72392	int16_t __s1_302 = __p1_302; \	61819	int16_t __s1_296 = __p1_296; \
72393	int16x4_t __s2_302 = __p2_302; \	61820	int16x4_t __s2_296 = __p2_296; \
72394	int16_t __ret_302; \	61821	int16_t __ret_296; \
72395	__ret_302 = vqaddh_s16(__s0_302, vqrdmulhh_s16(__s1_302, vget_lane_s16(__s2_302, __p3_302))); \	61822	__ret_296 = vqaddh_s16(__s0_296, vqrdmulhh_s16(__s1_296, vget_lane_s16(__s2_296, __p3_296))); \
72396	__ret_302; \	61823	__ret_296; \
72397	})	61824	})
72398	#else	61825	#else
72399	#define vqrdmlahh_lane_s16(__p0_303, __p1_303, __p2_303, __p3_303) __extension__ ({ \	61826	#define vqrdmlahh_lane_s16(__p0_297, __p1_297, __p2_297, __p3_297) __extension__ ({ \
72400	int16_t __s0_303 = __p0_303; \	61827	int16_t __s0_297 = __p0_297; \
72401	int16_t __s1_303 = __p1_303; \	61828	int16_t __s1_297 = __p1_297; \
72402	int16x4_t __s2_303 = __p2_303; \	61829	int16x4_t __s2_297 = __p2_297; \
72403	int16x4_t __rev2_303; __rev2_303 = __builtin_shufflevector(__s2_303, __s2_303, 3, 2, 1, 0); \	61830	int16x4_t __rev2_297; __rev2_297 = __builtin_shufflevector(__s2_297, __s2_297, 3, 2, 1, 0); \
72404	int16_t __ret_303; \	61831	int16_t __ret_297; \
72405	__ret_303 = __noswap_vqaddh_s16(__s0_303, __noswap_vqrdmulhh_s16(__s1_303, __noswap_vget_lane_s16(__rev2_303, __p3_303))); \	61832	__ret_297 = vqaddh_s16(__s0_297, vqrdmulhh_s16(__s1_297, __noswap_vget_lane_s16(__rev2_297, __p3_297))); \
72406	__ret_303; \	61833	__ret_297; \
72407	})	61834	})
72408	#endif	61835	#endif
72409		61836
72410	#ifdef __LITTLE_ENDIAN__	61837	#ifdef __LITTLE_ENDIAN__
72411	#define vqrdmlahs_laneq_s32(__p0_304, __p1_304, __p2_304, __p3_304) __extension__ ({ \	61838	#define vqrdmlahs_laneq_s32(__p0_298, __p1_298, __p2_298, __p3_298) __extension__ ({ \
72412	int32_t __s0_304 = __p0_304; \	61839	int32_t __s0_298 = __p0_298; \
72413	int32_t __s1_304 = __p1_304; \	61840	int32_t __s1_298 = __p1_298; \
72414	int32x4_t __s2_304 = __p2_304; \	61841	int32x4_t __s2_298 = __p2_298; \
72415	int32_t __ret_304; \	61842	int32_t __ret_298; \
72416	__ret_304 = vqadds_s32(__s0_304, vqrdmulhs_s32(__s1_304, vgetq_lane_s32(__s2_304, __p3_304))); \	61843	__ret_298 = vqadds_s32(__s0_298, vqrdmulhs_s32(__s1_298, vgetq_lane_s32(__s2_298, __p3_298))); \
72417	__ret_304; \	61844	__ret_298; \
72418	})	61845	})
72419	#else	61846	#else
72420	#define vqrdmlahs_laneq_s32(__p0_305, __p1_305, __p2_305, __p3_305) __extension__ ({ \	61847	#define vqrdmlahs_laneq_s32(__p0_299, __p1_299, __p2_299, __p3_299) __extension__ ({ \
72421	int32_t __s0_305 = __p0_305; \	61848	int32_t __s0_299 = __p0_299; \
72422	int32_t __s1_305 = __p1_305; \	61849	int32_t __s1_299 = __p1_299; \
72423	int32x4_t __s2_305 = __p2_305; \	61850	int32x4_t __s2_299 = __p2_299; \
72424	int32x4_t __rev2_305; __rev2_305 = __builtin_shufflevector(__s2_305, __s2_305, 3, 2, 1, 0); \	61851	int32x4_t __rev2_299; __rev2_299 = __builtin_shufflevector(__s2_299, __s2_299, 3, 2, 1, 0); \
72425	int32_t __ret_305; \	61852	int32_t __ret_299; \
72426	__ret_305 = __noswap_vqadds_s32(__s0_305, __noswap_vqrdmulhs_s32(__s1_305, __noswap_vgetq_lane_s32(__rev2_305, __p3_305))); \	61853	__ret_299 = vqadds_s32(__s0_299, vqrdmulhs_s32(__s1_299, __noswap_vgetq_lane_s32(__rev2_299, __p3_299))); \
72427	__ret_305; \	61854	__ret_299; \
72428	})	61855	})
72429	#endif	61856	#endif
72430		61857
72431	#ifdef __LITTLE_ENDIAN__	61858	#ifdef __LITTLE_ENDIAN__
72432	#define vqrdmlahh_laneq_s16(__p0_306, __p1_306, __p2_306, __p3_306) __extension__ ({ \	61859	#define vqrdmlahh_laneq_s16(__p0_300, __p1_300, __p2_300, __p3_300) __extension__ ({ \
72433	int16_t __s0_306 = __p0_306; \	61860	int16_t __s0_300 = __p0_300; \
72434	int16_t __s1_306 = __p1_306; \	61861	int16_t __s1_300 = __p1_300; \
72435	int16x8_t __s2_306 = __p2_306; \	61862	int16x8_t __s2_300 = __p2_300; \
72436	int16_t __ret_306; \	61863	int16_t __ret_300; \
72437	__ret_306 = vqaddh_s16(__s0_306, vqrdmulhh_s16(__s1_306, vgetq_lane_s16(__s2_306, __p3_306))); \	61864	__ret_300 = vqaddh_s16(__s0_300, vqrdmulhh_s16(__s1_300, vgetq_lane_s16(__s2_300, __p3_300))); \
72438	__ret_306; \	61865	__ret_300; \
72439	})	61866	})
72440	#else	61867	#else
72441	#define vqrdmlahh_laneq_s16(__p0_307, __p1_307, __p2_307, __p3_307) __extension__ ({ \	61868	#define vqrdmlahh_laneq_s16(__p0_301, __p1_301, __p2_301, __p3_301) __extension__ ({ \
72442	int16_t __s0_307 = __p0_307; \	61869	int16_t __s0_301 = __p0_301; \
72443	int16_t __s1_307 = __p1_307; \	61870	int16_t __s1_301 = __p1_301; \
72444	int16x8_t __s2_307 = __p2_307; \	61871	int16x8_t __s2_301 = __p2_301; \
72445	int16x8_t __rev2_307; __rev2_307 = __builtin_shufflevector(__s2_307, __s2_307, 7, 6, 5, 4, 3, 2, 1, 0); \	61872	int16x8_t __rev2_301; __rev2_301 = __builtin_shufflevector(__s2_301, __s2_301, 7, 6, 5, 4, 3, 2, 1, 0); \
72446	int16_t __ret_307; \	61873	int16_t __ret_301; \
72447	__ret_307 = __noswap_vqaddh_s16(__s0_307, __noswap_vqrdmulhh_s16(__s1_307, __noswap_vgetq_lane_s16(__rev2_307, __p3_307))); \	61874	__ret_301 = vqaddh_s16(__s0_301, vqrdmulhh_s16(__s1_301, __noswap_vgetq_lane_s16(__rev2_301, __p3_301))); \
72448	__ret_307; \	61875	__ret_301; \
72449	})	61876	})
72450	#endif	61877	#endif
72451		61878
72452	#ifdef __LITTLE_ENDIAN__
72453	__ai int32_t vqrdmlshs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {	61879	__ai int32_t vqrdmlshs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
72454	int32_t __ret;	61880	int32_t __ret;
72455	__ret = vqsubs_s32(__p0, vqrdmulhs_s32(__p1, __p2));	61881	__ret = vqsubs_s32(__p0, vqrdmulhs_s32(__p1, __p2));
72456	return __ret;	61882	return __ret;
72457	}	61883	}
72458	#else
72459	__ai int32_t vqrdmlshs_s32(int32_t __p0, int32_t __p1, int32_t __p2) {
72460	int32_t __ret;
72461	__ret = __noswap_vqsubs_s32(__p0, __noswap_vqrdmulhs_s32(__p1, __p2));
72462	return __ret;
72463	}
72464	#endif
72465
72466	#ifdef __LITTLE_ENDIAN__
72467	__ai int16_t vqrdmlshh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {	61884	__ai int16_t vqrdmlshh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
72468	int16_t __ret;	61885	int16_t __ret;
72469	__ret = vqsubh_s16(__p0, vqrdmulhh_s16(__p1, __p2));	61886	__ret = vqsubh_s16(__p0, vqrdmulhh_s16(__p1, __p2));
72470	return __ret;	61887	return __ret;
72471	}	61888	}
72472	#else
72473	__ai int16_t vqrdmlshh_s16(int16_t __p0, int16_t __p1, int16_t __p2) {
72474	int16_t __ret;
72475	__ret = __noswap_vqsubh_s16(__p0, __noswap_vqrdmulhh_s16(__p1, __p2));
72476	return __ret;
72477	}
72478	#endif
72479
72480	#ifdef __LITTLE_ENDIAN__	61889	#ifdef __LITTLE_ENDIAN__
72481	#define vqrdmlshs_lane_s32(__p0_308, __p1_308, __p2_308, __p3_308) __extension__ ({ \	61890	#define vqrdmlshs_lane_s32(__p0_302, __p1_302, __p2_302, __p3_302) __extension__ ({ \
72482	int32_t __s0_308 = __p0_308; \	61891	int32_t __s0_302 = __p0_302; \
72483	int32_t __s1_308 = __p1_308; \	61892	int32_t __s1_302 = __p1_302; \
72484	int32x2_t __s2_308 = __p2_308; \	61893	int32x2_t __s2_302 = __p2_302; \
72485	int32_t __ret_308; \	61894	int32_t __ret_302; \
72486	__ret_308 = vqsubs_s32(__s0_308, vqrdmulhs_s32(__s1_308, vget_lane_s32(__s2_308, __p3_308))); \	61895	__ret_302 = vqsubs_s32(__s0_302, vqrdmulhs_s32(__s1_302, vget_lane_s32(__s2_302, __p3_302))); \
72487	__ret_308; \	61896	__ret_302; \
72488	})	61897	})
72489	#else	61898	#else
72490	#define vqrdmlshs_lane_s32(__p0_309, __p1_309, __p2_309, __p3_309) __extension__ ({ \	61899	#define vqrdmlshs_lane_s32(__p0_303, __p1_303, __p2_303, __p3_303) __extension__ ({ \
72491	int32_t __s0_309 = __p0_309; \	61900	int32_t __s0_303 = __p0_303; \
72492	int32_t __s1_309 = __p1_309; \	61901	int32_t __s1_303 = __p1_303; \
72493	int32x2_t __s2_309 = __p2_309; \	61902	int32x2_t __s2_303 = __p2_303; \
72494	int32x2_t __rev2_309; __rev2_309 = __builtin_shufflevector(__s2_309, __s2_309, 1, 0); \	61903	int32x2_t __rev2_303; __rev2_303 = __builtin_shufflevector(__s2_303, __s2_303, 1, 0); \
72495	int32_t __ret_309; \	61904	int32_t __ret_303; \
72496	__ret_309 = __noswap_vqsubs_s32(__s0_309, __noswap_vqrdmulhs_s32(__s1_309, __noswap_vget_lane_s32(__rev2_309, __p3_309))); \	61905	__ret_303 = vqsubs_s32(__s0_303, vqrdmulhs_s32(__s1_303, __noswap_vget_lane_s32(__rev2_303, __p3_303))); \
72497	__ret_309; \	61906	__ret_303; \
72498	})	61907	})
72499	#endif	61908	#endif
72500		61909
72501	#ifdef __LITTLE_ENDIAN__	61910	#ifdef __LITTLE_ENDIAN__
72502	#define vqrdmlshh_lane_s16(__p0_310, __p1_310, __p2_310, __p3_310) __extension__ ({ \	61911	#define vqrdmlshh_lane_s16(__p0_304, __p1_304, __p2_304, __p3_304) __extension__ ({ \
72503	int16_t __s0_310 = __p0_310; \	61912	int16_t __s0_304 = __p0_304; \
72504	int16_t __s1_310 = __p1_310; \	61913	int16_t __s1_304 = __p1_304; \
72505	int16x4_t __s2_310 = __p2_310; \	61914	int16x4_t __s2_304 = __p2_304; \
72506	int16_t __ret_310; \	61915	int16_t __ret_304; \
72507	__ret_310 = vqsubh_s16(__s0_310, vqrdmulhh_s16(__s1_310, vget_lane_s16(__s2_310, __p3_310))); \	61916	__ret_304 = vqsubh_s16(__s0_304, vqrdmulhh_s16(__s1_304, vget_lane_s16(__s2_304, __p3_304))); \
72508	__ret_310; \	61917	__ret_304; \
72509	})	61918	})
72510	#else	61919	#else
72511	#define vqrdmlshh_lane_s16(__p0_311, __p1_311, __p2_311, __p3_311) __extension__ ({ \	61920	#define vqrdmlshh_lane_s16(__p0_305, __p1_305, __p2_305, __p3_305) __extension__ ({ \
72512	int16_t __s0_311 = __p0_311; \	61921	int16_t __s0_305 = __p0_305; \
72513	int16_t __s1_311 = __p1_311; \	61922	int16_t __s1_305 = __p1_305; \
72514	int16x4_t __s2_311 = __p2_311; \	61923	int16x4_t __s2_305 = __p2_305; \
72515	int16x4_t __rev2_311; __rev2_311 = __builtin_shufflevector(__s2_311, __s2_311, 3, 2, 1, 0); \	61924	int16x4_t __rev2_305; __rev2_305 = __builtin_shufflevector(__s2_305, __s2_305, 3, 2, 1, 0); \
72516	int16_t __ret_311; \	61925	int16_t __ret_305; \
72517	__ret_311 = __noswap_vqsubh_s16(__s0_311, __noswap_vqrdmulhh_s16(__s1_311, __noswap_vget_lane_s16(__rev2_311, __p3_311))); \	61926	__ret_305 = vqsubh_s16(__s0_305, vqrdmulhh_s16(__s1_305, __noswap_vget_lane_s16(__rev2_305, __p3_305))); \
72518	__ret_311; \	61927	__ret_305; \
72519	})	61928	})
72520	#endif	61929	#endif
72521		61930
72522	#ifdef __LITTLE_ENDIAN__	61931	#ifdef __LITTLE_ENDIAN__
72523	#define vqrdmlshs_laneq_s32(__p0_312, __p1_312, __p2_312, __p3_312) __extension__ ({ \	61932	#define vqrdmlshs_laneq_s32(__p0_306, __p1_306, __p2_306, __p3_306) __extension__ ({ \
72524	int32_t __s0_312 = __p0_312; \	61933	int32_t __s0_306 = __p0_306; \
72525	int32_t __s1_312 = __p1_312; \	61934	int32_t __s1_306 = __p1_306; \
72526	int32x4_t __s2_312 = __p2_312; \	61935	int32x4_t __s2_306 = __p2_306; \
72527	int32_t __ret_312; \	61936	int32_t __ret_306; \
72528	__ret_312 = vqsubs_s32(__s0_312, vqrdmulhs_s32(__s1_312, vgetq_lane_s32(__s2_312, __p3_312))); \	61937	__ret_306 = vqsubs_s32(__s0_306, vqrdmulhs_s32(__s1_306, vgetq_lane_s32(__s2_306, __p3_306))); \
72529	__ret_312; \	61938	__ret_306; \
72530	})	61939	})
72531	#else	61940	#else
72532	#define vqrdmlshs_laneq_s32(__p0_313, __p1_313, __p2_313, __p3_313) __extension__ ({ \	61941	#define vqrdmlshs_laneq_s32(__p0_307, __p1_307, __p2_307, __p3_307) __extension__ ({ \
72533	int32_t __s0_313 = __p0_313; \	61942	int32_t __s0_307 = __p0_307; \
72534	int32_t __s1_313 = __p1_313; \	61943	int32_t __s1_307 = __p1_307; \
72535	int32x4_t __s2_313 = __p2_313; \	61944	int32x4_t __s2_307 = __p2_307; \
72536	int32x4_t __rev2_313; __rev2_313 = __builtin_shufflevector(__s2_313, __s2_313, 3, 2, 1, 0); \	61945	int32x4_t __rev2_307; __rev2_307 = __builtin_shufflevector(__s2_307, __s2_307, 3, 2, 1, 0); \
72537	int32_t __ret_313; \	61946	int32_t __ret_307; \
72538	__ret_313 = __noswap_vqsubs_s32(__s0_313, __noswap_vqrdmulhs_s32(__s1_313, __noswap_vgetq_lane_s32(__rev2_313, __p3_313))); \	61947	__ret_307 = vqsubs_s32(__s0_307, vqrdmulhs_s32(__s1_307, __noswap_vgetq_lane_s32(__rev2_307, __p3_307))); \
72539	__ret_313; \	61948	__ret_307; \
72540	})	61949	})
72541	#endif	61950	#endif
72542		61951
72543	#ifdef __LITTLE_ENDIAN__	61952	#ifdef __LITTLE_ENDIAN__
72544	#define vqrdmlshh_laneq_s16(__p0_314, __p1_314, __p2_314, __p3_314) __extension__ ({ \	61953	#define vqrdmlshh_laneq_s16(__p0_308, __p1_308, __p2_308, __p3_308) __extension__ ({ \
72545	int16_t __s0_314 = __p0_314; \	61954	int16_t __s0_308 = __p0_308; \
72546	int16_t __s1_314 = __p1_314; \	61955	int16_t __s1_308 = __p1_308; \
72547	int16x8_t __s2_314 = __p2_314; \	61956	int16x8_t __s2_308 = __p2_308; \
72548	int16_t __ret_314; \	61957	int16_t __ret_308; \
72549	__ret_314 = vqsubh_s16(__s0_314, vqrdmulhh_s16(__s1_314, vgetq_lane_s16(__s2_314, __p3_314))); \	61958	__ret_308 = vqsubh_s16(__s0_308, vqrdmulhh_s16(__s1_308, vgetq_lane_s16(__s2_308, __p3_308))); \
72550	__ret_314; \	61959	__ret_308; \
72551	})	61960	})
72552	#else	61961	#else
72553	#define vqrdmlshh_laneq_s16(__p0_315, __p1_315, __p2_315, __p3_315) __extension__ ({ \	61962	#define vqrdmlshh_laneq_s16(__p0_309, __p1_309, __p2_309, __p3_309) __extension__ ({ \
72554	int16_t __s0_315 = __p0_315; \	61963	int16_t __s0_309 = __p0_309; \
72555	int16_t __s1_315 = __p1_315; \	61964	int16_t __s1_309 = __p1_309; \
72556	int16x8_t __s2_315 = __p2_315; \	61965	int16x8_t __s2_309 = __p2_309; \
72557	int16x8_t __rev2_315; __rev2_315 = __builtin_shufflevector(__s2_315, __s2_315, 7, 6, 5, 4, 3, 2, 1, 0); \	61966	int16x8_t __rev2_309; __rev2_309 = __builtin_shufflevector(__s2_309, __s2_309, 7, 6, 5, 4, 3, 2, 1, 0); \
72558	int16_t __ret_315; \	61967	int16_t __ret_309; \
72559	__ret_315 = __noswap_vqsubh_s16(__s0_315, __noswap_vqrdmulhh_s16(__s1_315, __noswap_vgetq_lane_s16(__rev2_315, __p3_315))); \	61968	__ret_309 = vqsubh_s16(__s0_309, vqrdmulhh_s16(__s1_309, __noswap_vgetq_lane_s16(__rev2_309, __p3_309))); \
72560	__ret_315; \	61969	__ret_309; \
72561	})	61970	})
72562	#endif	61971	#endif
72563		61972
...	@@ -72870,161 +62279,139 @@ __ai int32x4_t vaddw_high_s16(int32x4_t __p0, int16x8_t __p1) {	...	@@ -72870,161 +62279,139 @@ __ai int32x4_t vaddw_high_s16(int32x4_t __p0, int16x8_t __p1) {
72870	#endif	62279	#endif
72871		62280
72872	#ifdef __LITTLE_ENDIAN__	62281	#ifdef __LITTLE_ENDIAN__
72873	#define vcopyq_lane_p64(__p0_316, __p1_316, __p2_316, __p3_316) __extension__ ({ \	62282	#define vcopyq_lane_p64(__p0_310, __p1_310, __p2_310, __p3_310) __extension__ ({ \
		62283	poly64x2_t __s0_310 = __p0_310; \
		62284	poly64x1_t __s2_310 = __p2_310; \
		62285	poly64x2_t __ret_310; \
		62286	__ret_310 = vsetq_lane_p64(vget_lane_p64(__s2_310, __p3_310), __s0_310, __p1_310); \
		62287	__ret_310; \
		62288	})
		62289	#else
		62290	#define vcopyq_lane_p64(__p0_311, __p1_311, __p2_311, __p3_311) __extension__ ({ \
		62291	poly64x2_t __s0_311 = __p0_311; \
		62292	poly64x1_t __s2_311 = __p2_311; \
		62293	poly64x2_t __rev0_311; __rev0_311 = __builtin_shufflevector(__s0_311, __s0_311, 1, 0); \
		62294	poly64x2_t __ret_311; \
		62295	__ret_311 = __noswap_vsetq_lane_p64(vget_lane_p64(__s2_311, __p3_311), __rev0_311, __p1_311); \
		62296	__ret_311 = __builtin_shufflevector(__ret_311, __ret_311, 1, 0); \
		62297	__ret_311; \
		62298	})
		62299	#endif
		62300
		62301	#ifdef __LITTLE_ENDIAN__
		62302	#define vcopyq_lane_f64(__p0_312, __p1_312, __p2_312, __p3_312) __extension__ ({ \
		62303	float64x2_t __s0_312 = __p0_312; \
		62304	float64x1_t __s2_312 = __p2_312; \
		62305	float64x2_t __ret_312; \
		62306	__ret_312 = vsetq_lane_f64(vget_lane_f64(__s2_312, __p3_312), __s0_312, __p1_312); \
		62307	__ret_312; \
		62308	})
		62309	#else
		62310	#define vcopyq_lane_f64(__p0_313, __p1_313, __p2_313, __p3_313) __extension__ ({ \
		62311	float64x2_t __s0_313 = __p0_313; \
		62312	float64x1_t __s2_313 = __p2_313; \
		62313	float64x2_t __rev0_313; __rev0_313 = __builtin_shufflevector(__s0_313, __s0_313, 1, 0); \
		62314	float64x2_t __ret_313; \
		62315	__ret_313 = __noswap_vsetq_lane_f64(vget_lane_f64(__s2_313, __p3_313), __rev0_313, __p1_313); \
		62316	__ret_313 = __builtin_shufflevector(__ret_313, __ret_313, 1, 0); \
		62317	__ret_313; \
		62318	})
		62319	#endif
		62320
		62321	#define vcopy_lane_p64(__p0_314, __p1_314, __p2_314, __p3_314) __extension__ ({ \
		62322	poly64x1_t __s0_314 = __p0_314; \
		62323	poly64x1_t __s2_314 = __p2_314; \
		62324	poly64x1_t __ret_314; \
		62325	__ret_314 = vset_lane_p64(vget_lane_p64(__s2_314, __p3_314), __s0_314, __p1_314); \
		62326	__ret_314; \
		62327	})
		62328	#define vcopy_lane_f64(__p0_315, __p1_315, __p2_315, __p3_315) __extension__ ({ \
		62329	float64x1_t __s0_315 = __p0_315; \
		62330	float64x1_t __s2_315 = __p2_315; \
		62331	float64x1_t __ret_315; \
		62332	__ret_315 = vset_lane_f64(vget_lane_f64(__s2_315, __p3_315), __s0_315, __p1_315); \
		62333	__ret_315; \
		62334	})
		62335	#ifdef __LITTLE_ENDIAN__
		62336	#define vcopyq_laneq_p64(__p0_316, __p1_316, __p2_316, __p3_316) __extension__ ({ \
72874	poly64x2_t __s0_316 = __p0_316; \	62337	poly64x2_t __s0_316 = __p0_316; \
72875	poly64x1_t __s2_316 = __p2_316; \	62338	poly64x2_t __s2_316 = __p2_316; \
72876	poly64x2_t __ret_316; \	62339	poly64x2_t __ret_316; \
72877	__ret_316 = vsetq_lane_p64(vget_lane_p64(__s2_316, __p3_316), __s0_316, __p1_316); \	62340	__ret_316 = vsetq_lane_p64(vgetq_lane_p64(__s2_316, __p3_316), __s0_316, __p1_316); \
72878	__ret_316; \	62341	__ret_316; \
72879	})	62342	})
72880	#else	62343	#else
72881	#define vcopyq_lane_p64(__p0_317, __p1_317, __p2_317, __p3_317) __extension__ ({ \	62344	#define vcopyq_laneq_p64(__p0_317, __p1_317, __p2_317, __p3_317) __extension__ ({ \
72882	poly64x2_t __s0_317 = __p0_317; \	62345	poly64x2_t __s0_317 = __p0_317; \
72883	poly64x1_t __s2_317 = __p2_317; \	62346	poly64x2_t __s2_317 = __p2_317; \
72884	poly64x2_t __rev0_317; __rev0_317 = __builtin_shufflevector(__s0_317, __s0_317, 1, 0); \	62347	poly64x2_t __rev0_317; __rev0_317 = __builtin_shufflevector(__s0_317, __s0_317, 1, 0); \
		62348	poly64x2_t __rev2_317; __rev2_317 = __builtin_shufflevector(__s2_317, __s2_317, 1, 0); \
72885	poly64x2_t __ret_317; \	62349	poly64x2_t __ret_317; \
72886	__ret_317 = __noswap_vsetq_lane_p64(__noswap_vget_lane_p64(__s2_317, __p3_317), __rev0_317, __p1_317); \	62350	__ret_317 = __noswap_vsetq_lane_p64(__noswap_vgetq_lane_p64(__rev2_317, __p3_317), __rev0_317, __p1_317); \
72887	__ret_317 = __builtin_shufflevector(__ret_317, __ret_317, 1, 0); \	62351	__ret_317 = __builtin_shufflevector(__ret_317, __ret_317, 1, 0); \
72888	__ret_317; \	62352	__ret_317; \
72889	})	62353	})
72890	#endif	62354	#endif
72891		62355
72892	#ifdef __LITTLE_ENDIAN__	62356	#ifdef __LITTLE_ENDIAN__
72893	#define vcopyq_lane_f64(__p0_318, __p1_318, __p2_318, __p3_318) __extension__ ({ \	62357	#define vcopyq_laneq_f64(__p0_318, __p1_318, __p2_318, __p3_318) __extension__ ({ \
72894	float64x2_t __s0_318 = __p0_318; \	62358	float64x2_t __s0_318 = __p0_318; \
72895	float64x1_t __s2_318 = __p2_318; \	62359	float64x2_t __s2_318 = __p2_318; \
72896	float64x2_t __ret_318; \	62360	float64x2_t __ret_318; \
72897	__ret_318 = vsetq_lane_f64(vget_lane_f64(__s2_318, __p3_318), __s0_318, __p1_318); \	62361	__ret_318 = vsetq_lane_f64(vgetq_lane_f64(__s2_318, __p3_318), __s0_318, __p1_318); \
72898	__ret_318; \	62362	__ret_318; \
72899	})	62363	})
72900	#else	62364	#else
72901	#define vcopyq_lane_f64(__p0_319, __p1_319, __p2_319, __p3_319) __extension__ ({ \	62365	#define vcopyq_laneq_f64(__p0_319, __p1_319, __p2_319, __p3_319) __extension__ ({ \
72902	float64x2_t __s0_319 = __p0_319; \	62366	float64x2_t __s0_319 = __p0_319; \
72903	float64x1_t __s2_319 = __p2_319; \	62367	float64x2_t __s2_319 = __p2_319; \
72904	float64x2_t __rev0_319; __rev0_319 = __builtin_shufflevector(__s0_319, __s0_319, 1, 0); \	62368	float64x2_t __rev0_319; __rev0_319 = __builtin_shufflevector(__s0_319, __s0_319, 1, 0); \
		62369	float64x2_t __rev2_319; __rev2_319 = __builtin_shufflevector(__s2_319, __s2_319, 1, 0); \
72905	float64x2_t __ret_319; \	62370	float64x2_t __ret_319; \
72906	__ret_319 = __noswap_vsetq_lane_f64(__noswap_vget_lane_f64(__s2_319, __p3_319), __rev0_319, __p1_319); \	62371	__ret_319 = __noswap_vsetq_lane_f64(__noswap_vgetq_lane_f64(__rev2_319, __p3_319), __rev0_319, __p1_319); \
72907	__ret_319 = __builtin_shufflevector(__ret_319, __ret_319, 1, 0); \	62372	__ret_319 = __builtin_shufflevector(__ret_319, __ret_319, 1, 0); \
72908	__ret_319; \	62373	__ret_319; \
72909	})	62374	})
72910	#endif	62375	#endif
72911		62376
72912	#ifdef __LITTLE_ENDIAN__	62377	#ifdef __LITTLE_ENDIAN__
72913	#define vcopy_lane_p64(__p0_320, __p1_320, __p2_320, __p3_320) __extension__ ({ \	62378	#define vcopy_laneq_p64(__p0_320, __p1_320, __p2_320, __p3_320) __extension__ ({ \
72914	poly64x1_t __s0_320 = __p0_320; \	62379	poly64x1_t __s0_320 = __p0_320; \
72915	poly64x1_t __s2_320 = __p2_320; \	62380	poly64x2_t __s2_320 = __p2_320; \
72916	poly64x1_t __ret_320; \	62381	poly64x1_t __ret_320; \
72917	__ret_320 = vset_lane_p64(vget_lane_p64(__s2_320, __p3_320), __s0_320, __p1_320); \	62382	__ret_320 = vset_lane_p64(vgetq_lane_p64(__s2_320, __p3_320), __s0_320, __p1_320); \
72918	__ret_320; \	62383	__ret_320; \
72919	})	62384	})
72920	#else	62385	#else
72921	#define vcopy_lane_p64(__p0_321, __p1_321, __p2_321, __p3_321) __extension__ ({ \	62386	#define vcopy_laneq_p64(__p0_321, __p1_321, __p2_321, __p3_321) __extension__ ({ \
72922	poly64x1_t __s0_321 = __p0_321; \	62387	poly64x1_t __s0_321 = __p0_321; \
72923	poly64x1_t __s2_321 = __p2_321; \	62388	poly64x2_t __s2_321 = __p2_321; \
		62389	poly64x2_t __rev2_321; __rev2_321 = __builtin_shufflevector(__s2_321, __s2_321, 1, 0); \
72924	poly64x1_t __ret_321; \	62390	poly64x1_t __ret_321; \
72925	__ret_321 = __noswap_vset_lane_p64(__noswap_vget_lane_p64(__s2_321, __p3_321), __s0_321, __p1_321); \	62391	__ret_321 = vset_lane_p64(__noswap_vgetq_lane_p64(__rev2_321, __p3_321), __s0_321, __p1_321); \
72926	__ret_321; \	62392	__ret_321; \
72927	})	62393	})
72928	#endif	62394	#endif
72929		62395
72930	#ifdef __LITTLE_ENDIAN__	62396	#ifdef __LITTLE_ENDIAN__
72931	#define vcopy_lane_f64(__p0_322, __p1_322, __p2_322, __p3_322) __extension__ ({ \	62397	#define vcopy_laneq_f64(__p0_322, __p1_322, __p2_322, __p3_322) __extension__ ({ \
72932	float64x1_t __s0_322 = __p0_322; \	62398	float64x1_t __s0_322 = __p0_322; \
72933	float64x1_t __s2_322 = __p2_322; \	62399	float64x2_t __s2_322 = __p2_322; \
72934	float64x1_t __ret_322; \	62400	float64x1_t __ret_322; \
72935	__ret_322 = vset_lane_f64(vget_lane_f64(__s2_322, __p3_322), __s0_322, __p1_322); \	62401	__ret_322 = vset_lane_f64(vgetq_lane_f64(__s2_322, __p3_322), __s0_322, __p1_322); \
72936	__ret_322; \	62402	__ret_322; \
72937	})	62403	})
72938	#else	62404	#else
72939	#define vcopy_lane_f64(__p0_323, __p1_323, __p2_323, __p3_323) __extension__ ({ \	62405	#define vcopy_laneq_f64(__p0_323, __p1_323, __p2_323, __p3_323) __extension__ ({ \
72940	float64x1_t __s0_323 = __p0_323; \	62406	float64x1_t __s0_323 = __p0_323; \
72941	float64x1_t __s2_323 = __p2_323; \	62407	float64x2_t __s2_323 = __p2_323; \
		62408	float64x2_t __rev2_323; __rev2_323 = __builtin_shufflevector(__s2_323, __s2_323, 1, 0); \
72942	float64x1_t __ret_323; \	62409	float64x1_t __ret_323; \
72943	__ret_323 = __noswap_vset_lane_f64(__noswap_vget_lane_f64(__s2_323, __p3_323), __s0_323, __p1_323); \	62410	__ret_323 = vset_lane_f64(__noswap_vgetq_lane_f64(__rev2_323, __p3_323), __s0_323, __p1_323); \
72944	__ret_323; \	62411	__ret_323; \
72945	})	62412	})
72946	#endif	62413	#endif
72947		62414
72948	#ifdef __LITTLE_ENDIAN__
72949	#define vcopyq_laneq_p64(__p0_324, __p1_324, __p2_324, __p3_324) __extension__ ({ \
72950	poly64x2_t __s0_324 = __p0_324; \
72951	poly64x2_t __s2_324 = __p2_324; \
72952	poly64x2_t __ret_324; \
72953	__ret_324 = vsetq_lane_p64(vgetq_lane_p64(__s2_324, __p3_324), __s0_324, __p1_324); \
72954	__ret_324; \
72955	})
72956	#else
72957	#define vcopyq_laneq_p64(__p0_325, __p1_325, __p2_325, __p3_325) __extension__ ({ \
72958	poly64x2_t __s0_325 = __p0_325; \
72959	poly64x2_t __s2_325 = __p2_325; \
72960	poly64x2_t __rev0_325; __rev0_325 = __builtin_shufflevector(__s0_325, __s0_325, 1, 0); \
72961	poly64x2_t __rev2_325; __rev2_325 = __builtin_shufflevector(__s2_325, __s2_325, 1, 0); \
72962	poly64x2_t __ret_325; \
72963	__ret_325 = __noswap_vsetq_lane_p64(__noswap_vgetq_lane_p64(__rev2_325, __p3_325), __rev0_325, __p1_325); \
72964	__ret_325 = __builtin_shufflevector(__ret_325, __ret_325, 1, 0); \
72965	__ret_325; \
72966	})
72967	#endif
72968
72969	#ifdef __LITTLE_ENDIAN__
72970	#define vcopyq_laneq_f64(__p0_326, __p1_326, __p2_326, __p3_326) __extension__ ({ \
72971	float64x2_t __s0_326 = __p0_326; \
72972	float64x2_t __s2_326 = __p2_326; \
72973	float64x2_t __ret_326; \
72974	__ret_326 = vsetq_lane_f64(vgetq_lane_f64(__s2_326, __p3_326), __s0_326, __p1_326); \
72975	__ret_326; \
72976	})
72977	#else
72978	#define vcopyq_laneq_f64(__p0_327, __p1_327, __p2_327, __p3_327) __extension__ ({ \
72979	float64x2_t __s0_327 = __p0_327; \
72980	float64x2_t __s2_327 = __p2_327; \
72981	float64x2_t __rev0_327; __rev0_327 = __builtin_shufflevector(__s0_327, __s0_327, 1, 0); \
72982	float64x2_t __rev2_327; __rev2_327 = __builtin_shufflevector(__s2_327, __s2_327, 1, 0); \
72983	float64x2_t __ret_327; \
72984	__ret_327 = __noswap_vsetq_lane_f64(__noswap_vgetq_lane_f64(__rev2_327, __p3_327), __rev0_327, __p1_327); \
72985	__ret_327 = __builtin_shufflevector(__ret_327, __ret_327, 1, 0); \
72986	__ret_327; \
72987	})
72988	#endif
72989
72990	#ifdef __LITTLE_ENDIAN__
72991	#define vcopy_laneq_p64(__p0_328, __p1_328, __p2_328, __p3_328) __extension__ ({ \
72992	poly64x1_t __s0_328 = __p0_328; \
72993	poly64x2_t __s2_328 = __p2_328; \
72994	poly64x1_t __ret_328; \
72995	__ret_328 = vset_lane_p64(vgetq_lane_p64(__s2_328, __p3_328), __s0_328, __p1_328); \
72996	__ret_328; \
72997	})
72998	#else
72999	#define vcopy_laneq_p64(__p0_329, __p1_329, __p2_329, __p3_329) __extension__ ({ \
73000	poly64x1_t __s0_329 = __p0_329; \
73001	poly64x2_t __s2_329 = __p2_329; \
73002	poly64x2_t __rev2_329; __rev2_329 = __builtin_shufflevector(__s2_329, __s2_329, 1, 0); \
73003	poly64x1_t __ret_329; \
73004	__ret_329 = __noswap_vset_lane_p64(__noswap_vgetq_lane_p64(__rev2_329, __p3_329), __s0_329, __p1_329); \
73005	__ret_329; \
73006	})
73007	#endif
73008
73009	#ifdef __LITTLE_ENDIAN__
73010	#define vcopy_laneq_f64(__p0_330, __p1_330, __p2_330, __p3_330) __extension__ ({ \
73011	float64x1_t __s0_330 = __p0_330; \
73012	float64x2_t __s2_330 = __p2_330; \
73013	float64x1_t __ret_330; \
73014	__ret_330 = vset_lane_f64(vgetq_lane_f64(__s2_330, __p3_330), __s0_330, __p1_330); \
73015	__ret_330; \
73016	})
73017	#else
73018	#define vcopy_laneq_f64(__p0_331, __p1_331, __p2_331, __p3_331) __extension__ ({ \
73019	float64x1_t __s0_331 = __p0_331; \
73020	float64x2_t __s2_331 = __p2_331; \
73021	float64x2_t __rev2_331; __rev2_331 = __builtin_shufflevector(__s2_331, __s2_331, 1, 0); \
73022	float64x1_t __ret_331; \
73023	__ret_331 = __noswap_vset_lane_f64(__noswap_vgetq_lane_f64(__rev2_331, __p3_331), __s0_331, __p1_331); \
73024	__ret_331; \
73025	})
73026	#endif
73027
73028	#ifdef __LITTLE_ENDIAN__	62415	#ifdef __LITTLE_ENDIAN__
73029	__ai uint16x8_t vmlal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {	62416	__ai uint16x8_t vmlal_high_u8(uint16x8_t __p0, uint8x16_t __p1, uint8x16_t __p2) {
73030	uint16x8_t __ret;	62417	uint16x8_t __ret;
...	@@ -73377,52 +62764,38 @@ __ai int32x4_t vmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {	...	@@ -73377,52 +62764,38 @@ __ai int32x4_t vmlsl_high_n_s16(int32x4_t __p0, int16x8_t __p1, int16_t __p2) {
73377	}	62764	}
73378	#endif	62765	#endif
73379		62766
73380	#ifdef __LITTLE_ENDIAN__	62767	#define vmulx_lane_f64(__p0_324, __p1_324, __p2_324) __extension__ ({ \
73381	#define vmulx_lane_f64(__p0_332, __p1_332, __p2_332) __extension__ ({ \	62768	float64x1_t __s0_324 = __p0_324; \
73382	float64x1_t __s0_332 = __p0_332; \	62769	float64x1_t __s1_324 = __p1_324; \
73383	float64x1_t __s1_332 = __p1_332; \	62770	float64x1_t __ret_324; \
73384	float64x1_t __ret_332; \	62771	float64_t __x_324 = vget_lane_f64(__s0_324, 0); \
73385	float64_t __x_332 = vget_lane_f64(__s0_332, 0); \	62772	float64_t __y_324 = vget_lane_f64(__s1_324, __p2_324); \
73386	float64_t __y_332 = vget_lane_f64(__s1_332, __p2_332); \	62773	float64_t __z_324 = vmulxd_f64(__x_324, __y_324); \
73387	float64_t __z_332 = vmulxd_f64(__x_332, __y_332); \	62774	__ret_324 = vset_lane_f64(__z_324, __s0_324, __p2_324); \
73388	__ret_332 = vset_lane_f64(__z_332, __s0_332, __p2_332); \	62775	__ret_324; \
73389	__ret_332; \
73390	})
73391	#else
73392	#define vmulx_lane_f64(__p0_333, __p1_333, __p2_333) __extension__ ({ \
73393	float64x1_t __s0_333 = __p0_333; \
73394	float64x1_t __s1_333 = __p1_333; \
73395	float64x1_t __ret_333; \
73396	float64_t __x_333 = __noswap_vget_lane_f64(__s0_333, 0); \
73397	float64_t __y_333 = __noswap_vget_lane_f64(__s1_333, __p2_333); \
73398	float64_t __z_333 = __noswap_vmulxd_f64(__x_333, __y_333); \
73399	__ret_333 = __noswap_vset_lane_f64(__z_333, __s0_333, __p2_333); \
73400	__ret_333; \
73401	})	62776	})
73402	#endif
73403
73404	#ifdef __LITTLE_ENDIAN__	62777	#ifdef __LITTLE_ENDIAN__
73405	#define vmulx_laneq_f64(__p0_334, __p1_334, __p2_334) __extension__ ({ \	62778	#define vmulx_laneq_f64(__p0_325, __p1_325, __p2_325) __extension__ ({ \
73406	float64x1_t __s0_334 = __p0_334; \	62779	float64x1_t __s0_325 = __p0_325; \
73407	float64x2_t __s1_334 = __p1_334; \	62780	float64x2_t __s1_325 = __p1_325; \
73408	float64x1_t __ret_334; \	62781	float64x1_t __ret_325; \
73409	float64_t __x_334 = vget_lane_f64(__s0_334, 0); \	62782	float64_t __x_325 = vget_lane_f64(__s0_325, 0); \
73410	float64_t __y_334 = vgetq_lane_f64(__s1_334, __p2_334); \	62783	float64_t __y_325 = vgetq_lane_f64(__s1_325, __p2_325); \
73411	float64_t __z_334 = vmulxd_f64(__x_334, __y_334); \	62784	float64_t __z_325 = vmulxd_f64(__x_325, __y_325); \
73412	__ret_334 = vset_lane_f64(__z_334, __s0_334, 0); \	62785	__ret_325 = vset_lane_f64(__z_325, __s0_325, 0); \
73413	__ret_334; \	62786	__ret_325; \
73414	})	62787	})
73415	#else	62788	#else
73416	#define vmulx_laneq_f64(__p0_335, __p1_335, __p2_335) __extension__ ({ \	62789	#define vmulx_laneq_f64(__p0_326, __p1_326, __p2_326) __extension__ ({ \
73417	float64x1_t __s0_335 = __p0_335; \	62790	float64x1_t __s0_326 = __p0_326; \
73418	float64x2_t __s1_335 = __p1_335; \	62791	float64x2_t __s1_326 = __p1_326; \
73419	float64x2_t __rev1_335; __rev1_335 = __builtin_shufflevector(__s1_335, __s1_335, 1, 0); \	62792	float64x2_t __rev1_326; __rev1_326 = __builtin_shufflevector(__s1_326, __s1_326, 1, 0); \
73420	float64x1_t __ret_335; \	62793	float64x1_t __ret_326; \
73421	float64_t __x_335 = __noswap_vget_lane_f64(__s0_335, 0); \	62794	float64_t __x_326 = vget_lane_f64(__s0_326, 0); \
73422	float64_t __y_335 = __noswap_vgetq_lane_f64(__rev1_335, __p2_335); \	62795	float64_t __y_326 = __noswap_vgetq_lane_f64(__rev1_326, __p2_326); \
73423	float64_t __z_335 = __noswap_vmulxd_f64(__x_335, __y_335); \	62796	float64_t __z_326 = vmulxd_f64(__x_326, __y_326); \
73424	__ret_335 = __noswap_vset_lane_f64(__z_335, __s0_335, 0); \	62797	__ret_326 = vset_lane_f64(__z_326, __s0_326, 0); \
73425	__ret_335; \	62798	__ret_326; \
73426	})	62799	})
73427	#endif	62800	#endif
73428		62801

lib/include/avx512bwintrin.h+6-6

...	@@ -1731,13 +1731,13 @@ _mm512_loadu_epi16 (void const *__P)	...	@@ -1731,13 +1731,13 @@ _mm512_loadu_epi16 (void const *__P)
1731	struct __loadu_epi16 {	1731	struct __loadu_epi16 {
1732	__m512i_u __v;	1732	__m512i_u __v;
1733	} __attribute__((__packed__, __may_alias__));	1733	} __attribute__((__packed__, __may_alias__));
1734	return ((struct __loadu_epi16*)__P)->__v;	1734	return ((const struct __loadu_epi16*)__P)->__v;
1735	}	1735	}
1736		1736
1737	static __inline__ __m512i __DEFAULT_FN_ATTRS512	1737	static __inline__ __m512i __DEFAULT_FN_ATTRS512
1738	_mm512_mask_loadu_epi16 (__m512i __W, __mmask32 __U, void const *__P)	1738	_mm512_mask_loadu_epi16 (__m512i __W, __mmask32 __U, void const *__P)
1739	{	1739	{
1740	return (__m512i) __builtin_ia32_loaddquhi512_mask ((__v32hi *) __P,	1740	return (__m512i) __builtin_ia32_loaddquhi512_mask ((const __v32hi *) __P,
1741	(__v32hi) __W,	1741	(__v32hi) __W,
1742	(__mmask32) __U);	1742	(__mmask32) __U);
1743	}	1743	}
...	@@ -1745,7 +1745,7 @@ _mm512_mask_loadu_epi16 (__m512i __W, __mmask32 __U, void const *__P)	...	@@ -1745,7 +1745,7 @@ _mm512_mask_loadu_epi16 (__m512i __W, __mmask32 __U, void const *__P)
1745	static __inline__ __m512i __DEFAULT_FN_ATTRS512	1745	static __inline__ __m512i __DEFAULT_FN_ATTRS512
1746	_mm512_maskz_loadu_epi16 (__mmask32 __U, void const *__P)	1746	_mm512_maskz_loadu_epi16 (__mmask32 __U, void const *__P)
1747	{	1747	{
1748	return (__m512i) __builtin_ia32_loaddquhi512_mask ((__v32hi *) __P,	1748	return (__m512i) __builtin_ia32_loaddquhi512_mask ((const __v32hi *) __P,
1749	(__v32hi)	1749	(__v32hi)
1750	_mm512_setzero_si512 (),	1750	_mm512_setzero_si512 (),
1751	(__mmask32) __U);	1751	(__mmask32) __U);
...	@@ -1757,13 +1757,13 @@ _mm512_loadu_epi8 (void const *__P)	...	@@ -1757,13 +1757,13 @@ _mm512_loadu_epi8 (void const *__P)
1757	struct __loadu_epi8 {	1757	struct __loadu_epi8 {
1758	__m512i_u __v;	1758	__m512i_u __v;
1759	} __attribute__((__packed__, __may_alias__));	1759	} __attribute__((__packed__, __may_alias__));
1760	return ((struct __loadu_epi8*)__P)->__v;	1760	return ((const struct __loadu_epi8*)__P)->__v;
1761	}	1761	}
1762		1762
1763	static __inline__ __m512i __DEFAULT_FN_ATTRS512	1763	static __inline__ __m512i __DEFAULT_FN_ATTRS512
1764	_mm512_mask_loadu_epi8 (__m512i __W, __mmask64 __U, void const *__P)	1764	_mm512_mask_loadu_epi8 (__m512i __W, __mmask64 __U, void const *__P)
1765	{	1765	{
1766	return (__m512i) __builtin_ia32_loaddquqi512_mask ((__v64qi *) __P,	1766	return (__m512i) __builtin_ia32_loaddquqi512_mask ((const __v64qi *) __P,
1767	(__v64qi) __W,	1767	(__v64qi) __W,
1768	(__mmask64) __U);	1768	(__mmask64) __U);
1769	}	1769	}
...	@@ -1771,7 +1771,7 @@ _mm512_mask_loadu_epi8 (__m512i __W, __mmask64 __U, void const *__P)	...	@@ -1771,7 +1771,7 @@ _mm512_mask_loadu_epi8 (__m512i __W, __mmask64 __U, void const *__P)
1771	static __inline__ __m512i __DEFAULT_FN_ATTRS512	1771	static __inline__ __m512i __DEFAULT_FN_ATTRS512
1772	_mm512_maskz_loadu_epi8 (__mmask64 __U, void const *__P)	1772	_mm512_maskz_loadu_epi8 (__mmask64 __U, void const *__P)
1773	{	1773	{
1774	return (__m512i) __builtin_ia32_loaddquqi512_mask ((__v64qi *) __P,	1774	return (__m512i) __builtin_ia32_loaddquqi512_mask ((const __v64qi *) __P,
1775	(__v64qi)	1775	(__v64qi)
1776	_mm512_setzero_si512 (),	1776	_mm512_setzero_si512 (),
1777	(__mmask64) __U);	1777	(__mmask64) __U);

lib/include/avx512fintrin.h+36-19

 @@ -4305,7 +4305,7 @@ _mm512_loadu_si512 (void const *__P)
   struct __loadu_si512 {
     __m512i_u __v;
   } __attribute__((__packed__, __may_alias__));
-  return ((struct __loadu_si512*)__P)->__v;
+  return ((const struct __loadu_si512*)__P)->__v;
 }
 static __inline __m512i __DEFAULT_FN_ATTRS512
 @@ -4314,7 +4314,7 @@ _mm512_loadu_epi32 (void const *__P)
   struct __loadu_epi32 {
     __m512i_u __v;
   } __attribute__((__packed__, __may_alias__));
-  return ((struct __loadu_epi32*)__P)->__v;
+  return ((const struct __loadu_epi32*)__P)->__v;
 }
 static __inline __m512i __DEFAULT_FN_ATTRS512
 @@ -4341,7 +4341,7 @@ _mm512_loadu_epi64 (void const *__P)
   struct __loadu_epi64 {
     __m512i_u __v;
   } __attribute__((__packed__, __may_alias__));
-  return ((struct __loadu_epi64*)__P)->__v;
+  return ((const struct __loadu_epi64*)__P)->__v;
 }
 static __inline __m512i __DEFAULT_FN_ATTRS512
 @@ -4401,7 +4401,7 @@ _mm512_loadu_pd(void const *__p)
   struct __loadu_pd {
     __m512d_u __v;
   } __attribute__((__packed__, __may_alias__));
-  return ((struct __loadu_pd*)__p)->__v;
+  return ((const struct __loadu_pd*)__p)->__v;
 }
 static __inline __m512 __DEFAULT_FN_ATTRS512
 @@ -4410,13 +4410,13 @@ _mm512_loadu_ps(void const *__p)
   struct __loadu_ps {
     __m512_u __v;
   } __attribute__((__packed__, __may_alias__));
-  return ((struct __loadu_ps*)__p)->__v;
+  return ((const struct __loadu_ps*)__p)->__v;
 }
 static __inline __m512 __DEFAULT_FN_ATTRS512
 _mm512_load_ps(void const *__p)
 {
-  return *(__m512*)__p;
+  return *(const __m512*)__p;
 }
 static __inline __m512 __DEFAULT_FN_ATTRS512
 @@ -4439,7 +4439,7 @@ _mm512_maskz_load_ps(__mmask16 __U, void const *__P)
 static __inline __m512d __DEFAULT_FN_ATTRS512
 _mm512_load_pd(void const *__p)
 {
-  return *(__m512d*)__p;
+  return *(const __m512d*)__p;
 }
 static __inline __m512d __DEFAULT_FN_ATTRS512
 @@ -4462,19 +4462,19 @@ _mm512_maskz_load_pd(__mmask8 __U, void const *__P)
 static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_load_si512 (void const *__P)
 {
-  return *(__m512i *) __P;
+  return *(const __m512i *) __P;
 }
 static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_load_epi32 (void const *__P)
 {
-  return *(__m512i *) __P;
+  return *(const __m512i *) __P;
 }
 static __inline __m512i __DEFAULT_FN_ATTRS512
 _mm512_load_epi64 (void const *__P)
 {
-  return *(__m512i *) __P;
+  return *(const __m512i *) __P;
 }
 /* SIMD store ops */
 @@ -7658,13 +7658,13 @@ _mm512_maskz_getexp_ps (__mmask16 __U, __m512 __A)
 #define _mm512_i32gather_ps(index, addr, scale) \
   (__m512)__builtin_ia32_gathersiv16sf((__v16sf)_mm512_undefined_ps(), \
                                        (void const *)(addr), \
-                                       (__v16sf)(__m512)(index), \
+                                       (__v16si)(__m512)(index), \
                                        (__mmask16)-1, (int)(scale))
 #define _mm512_mask_i32gather_ps(v1_old, mask, index, addr, scale) \
   (__m512)__builtin_ia32_gathersiv16sf((__v16sf)(__m512)(v1_old), \
                                        (void const *)(addr), \
-                                       (__v16sf)(__m512)(index), \
+                                       (__v16si)(__m512)(index), \
                                        (__mmask16)(mask), (int)(scale))
 #define _mm512_i32gather_epi32(index, addr, scale) \
 @@ -8436,7 +8436,7 @@ _store_mask16(__mmask16 *__A, __mmask16 __B) {
 }
 static __inline__ void __DEFAULT_FN_ATTRS512
-_mm512_stream_si512 (__m512i * __P, __m512i __A)
+_mm512_stream_si512 (void * __P, __m512i __A)
 {
   typedef __v8di __v8di_aligned __attribute__((aligned(64)));
   __builtin_nontemporal_store((__v8di_aligned)__A, (__v8di_aligned*)__P);
 @@ -8450,14 +8450,14 @@ _mm512_stream_load_si512 (void const *__P)
 }
 static __inline__ void __DEFAULT_FN_ATTRS512
-_mm512_stream_pd (double *__P, __m512d __A)
+_mm512_stream_pd (void *__P, __m512d __A)
 {
   typedef __v8df __v8df_aligned __attribute__((aligned(64)));
   __builtin_nontemporal_store((__v8df_aligned)__A, (__v8df_aligned*)__P);
 }
 static __inline__ void __DEFAULT_FN_ATTRS512
-_mm512_stream_ps (float *__P, __m512 __A)
+_mm512_stream_ps (void *__P, __m512 __A)
 {
   typedef __v16sf __v16sf_aligned __attribute__((aligned(64)));
   __builtin_nontemporal_store((__v16sf_aligned)__A, (__v16sf_aligned*)__P);
 @@ -8724,13 +8724,13 @@ _mm_mask_load_ss (__m128 __W, __mmask8 __U, const float* __A)
                                                 (__v4sf)_mm_setzero_ps(),
                                                 0, 4, 4, 4);
-  return (__m128) __builtin_ia32_loadss128_mask ((__v4sf *) __A, src, __U & 1);
+  return (__m128) __builtin_ia32_loadss128_mask ((const __v4sf *) __A, src, __U & 1);
 }
 static __inline__ __m128 __DEFAULT_FN_ATTRS128
 _mm_maskz_load_ss (__mmask8 __U, const float* __A)
 {
-  return (__m128)__builtin_ia32_loadss128_mask ((__v4sf *) __A,
+  return (__m128)__builtin_ia32_loadss128_mask ((const __v4sf *) __A,
                                                 (__v4sf) _mm_setzero_ps(),
                                                 __U & 1);
 }
 @@ -8742,13 +8742,13 @@ _mm_mask_load_sd (__m128d __W, __mmask8 __U, const double* __A)
                                                  (__v2df)_mm_setzero_pd(),
                                                  0, 2);
-  return (__m128d) __builtin_ia32_loadsd128_mask ((__v2df *) __A, src, __U & 1);
+  return (__m128d) __builtin_ia32_loadsd128_mask ((const __v2df *) __A, src, __U & 1);
 }
 static __inline__ __m128d __DEFAULT_FN_ATTRS128
 _mm_maskz_load_sd (__mmask8 __U, const double* __A)
 {
-  return (__m128d) __builtin_ia32_loadsd128_mask ((__v2df *) __A,
+  return (__m128d) __builtin_ia32_loadsd128_mask ((const __v2df *) __A,
                                                   (__v2df) _mm_setzero_pd(),
                                                   __U & 1);
 }
 @@ -9659,6 +9659,23 @@ _mm512_mask_reduce_min_ps(__mmask16 __M, __m512 __V) {
 }
 #undef _mm512_mask_reduce_operator
+/// Moves the least significant 32 bits of a vector of [16 x i32] to a
+///    32-bit signed integer value.
+///
+/// \headerfile <x86intrin.h>
+///
+/// This intrinsic corresponds to the <c> VMOVD / MOVD </c> instruction.
+///
+/// \param __A
+///    A vector of [16 x i32]. The least significant 32 bits are moved to the
+///    destination.
+/// \returns A 32-bit signed integer containing the moved value.
+static __inline__ int __DEFAULT_FN_ATTRS512
+_mm512_cvtsi512_si32(__m512i __A) {
+  __v16si __b = (__v16si)__A;
+  return __b[0];
+}
 #undef __DEFAULT_FN_ATTRS512
 #undef __DEFAULT_FN_ATTRS128
 #undef __DEFAULT_FN_ATTRS

lib/include/avx512vlbwintrin.h+12-12

...	@@ -2289,13 +2289,13 @@ _mm_loadu_epi16 (void const *__P)	...	@@ -2289,13 +2289,13 @@ _mm_loadu_epi16 (void const *__P)
2289	struct __loadu_epi16 {	2289	struct __loadu_epi16 {
2290	__m128i_u __v;	2290	__m128i_u __v;
2291	} __attribute__((__packed__, __may_alias__));	2291	} __attribute__((__packed__, __may_alias__));
2292	return ((struct __loadu_epi16*)__P)->__v;	2292	return ((const struct __loadu_epi16*)__P)->__v;
2293	}	2293	}
2294		2294
2295	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2295	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2296	_mm_mask_loadu_epi16 (__m128i __W, __mmask8 __U, void const *__P)	2296	_mm_mask_loadu_epi16 (__m128i __W, __mmask8 __U, void const *__P)
2297	{	2297	{
2298	return (__m128i) __builtin_ia32_loaddquhi128_mask ((__v8hi *) __P,	2298	return (__m128i) __builtin_ia32_loaddquhi128_mask ((const __v8hi *) __P,
2299	(__v8hi) __W,	2299	(__v8hi) __W,
2300	(__mmask8) __U);	2300	(__mmask8) __U);
2301	}	2301	}
...	@@ -2303,7 +2303,7 @@ _mm_mask_loadu_epi16 (__m128i __W, __mmask8 __U, void const *__P)	...	@@ -2303,7 +2303,7 @@ _mm_mask_loadu_epi16 (__m128i __W, __mmask8 __U, void const *__P)
2303	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2303	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2304	_mm_maskz_loadu_epi16 (__mmask8 __U, void const *__P)	2304	_mm_maskz_loadu_epi16 (__mmask8 __U, void const *__P)
2305	{	2305	{
2306	return (__m128i) __builtin_ia32_loaddquhi128_mask ((__v8hi *) __P,	2306	return (__m128i) __builtin_ia32_loaddquhi128_mask ((const __v8hi *) __P,
2307	(__v8hi)	2307	(__v8hi)
2308	_mm_setzero_si128 (),	2308	_mm_setzero_si128 (),
2309	(__mmask8) __U);	2309	(__mmask8) __U);
...	@@ -2315,13 +2315,13 @@ _mm256_loadu_epi16 (void const *__P)	...	@@ -2315,13 +2315,13 @@ _mm256_loadu_epi16 (void const *__P)
2315	struct __loadu_epi16 {	2315	struct __loadu_epi16 {
2316	__m256i_u __v;	2316	__m256i_u __v;
2317	} __attribute__((__packed__, __may_alias__));	2317	} __attribute__((__packed__, __may_alias__));
2318	return ((struct __loadu_epi16*)__P)->__v;	2318	return ((const struct __loadu_epi16*)__P)->__v;
2319	}	2319	}
2320		2320
2321	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2321	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2322	_mm256_mask_loadu_epi16 (__m256i __W, __mmask16 __U, void const *__P)	2322	_mm256_mask_loadu_epi16 (__m256i __W, __mmask16 __U, void const *__P)
2323	{	2323	{
2324	return (__m256i) __builtin_ia32_loaddquhi256_mask ((__v16hi *) __P,	2324	return (__m256i) __builtin_ia32_loaddquhi256_mask ((const __v16hi *) __P,
2325	(__v16hi) __W,	2325	(__v16hi) __W,
2326	(__mmask16) __U);	2326	(__mmask16) __U);
2327	}	2327	}
...	@@ -2329,7 +2329,7 @@ _mm256_mask_loadu_epi16 (__m256i __W, __mmask16 __U, void const *__P)	...	@@ -2329,7 +2329,7 @@ _mm256_mask_loadu_epi16 (__m256i __W, __mmask16 __U, void const *__P)
2329	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2329	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2330	_mm256_maskz_loadu_epi16 (__mmask16 __U, void const *__P)	2330	_mm256_maskz_loadu_epi16 (__mmask16 __U, void const *__P)
2331	{	2331	{
2332	return (__m256i) __builtin_ia32_loaddquhi256_mask ((__v16hi *) __P,	2332	return (__m256i) __builtin_ia32_loaddquhi256_mask ((const __v16hi *) __P,
2333	(__v16hi)	2333	(__v16hi)
2334	_mm256_setzero_si256 (),	2334	_mm256_setzero_si256 (),
2335	(__mmask16) __U);	2335	(__mmask16) __U);
...	@@ -2341,13 +2341,13 @@ _mm_loadu_epi8 (void const *__P)	...	@@ -2341,13 +2341,13 @@ _mm_loadu_epi8 (void const *__P)
2341	struct __loadu_epi8 {	2341	struct __loadu_epi8 {
2342	__m128i_u __v;	2342	__m128i_u __v;
2343	} __attribute__((__packed__, __may_alias__));	2343	} __attribute__((__packed__, __may_alias__));
2344	return ((struct __loadu_epi8*)__P)->__v;	2344	return ((const struct __loadu_epi8*)__P)->__v;
2345	}	2345	}
2346		2346
2347	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2347	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2348	_mm_mask_loadu_epi8 (__m128i __W, __mmask16 __U, void const *__P)	2348	_mm_mask_loadu_epi8 (__m128i __W, __mmask16 __U, void const *__P)
2349	{	2349	{
2350	return (__m128i) __builtin_ia32_loaddquqi128_mask ((__v16qi *) __P,	2350	return (__m128i) __builtin_ia32_loaddquqi128_mask ((const __v16qi *) __P,
2351	(__v16qi) __W,	2351	(__v16qi) __W,
2352	(__mmask16) __U);	2352	(__mmask16) __U);
2353	}	2353	}
...	@@ -2355,7 +2355,7 @@ _mm_mask_loadu_epi8 (__m128i __W, __mmask16 __U, void const *__P)	...	@@ -2355,7 +2355,7 @@ _mm_mask_loadu_epi8 (__m128i __W, __mmask16 __U, void const *__P)
2355	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2355	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2356	_mm_maskz_loadu_epi8 (__mmask16 __U, void const *__P)	2356	_mm_maskz_loadu_epi8 (__mmask16 __U, void const *__P)
2357	{	2357	{
2358	return (__m128i) __builtin_ia32_loaddquqi128_mask ((__v16qi *) __P,	2358	return (__m128i) __builtin_ia32_loaddquqi128_mask ((const __v16qi *) __P,
2359	(__v16qi)	2359	(__v16qi)
2360	_mm_setzero_si128 (),	2360	_mm_setzero_si128 (),
2361	(__mmask16) __U);	2361	(__mmask16) __U);
...	@@ -2367,13 +2367,13 @@ _mm256_loadu_epi8 (void const *__P)	...	@@ -2367,13 +2367,13 @@ _mm256_loadu_epi8 (void const *__P)
2367	struct __loadu_epi8 {	2367	struct __loadu_epi8 {
2368	__m256i_u __v;	2368	__m256i_u __v;
2369	} __attribute__((__packed__, __may_alias__));	2369	} __attribute__((__packed__, __may_alias__));
2370	return ((struct __loadu_epi8*)__P)->__v;	2370	return ((const struct __loadu_epi8*)__P)->__v;
2371	}	2371	}
2372		2372
2373	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2373	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2374	_mm256_mask_loadu_epi8 (__m256i __W, __mmask32 __U, void const *__P)	2374	_mm256_mask_loadu_epi8 (__m256i __W, __mmask32 __U, void const *__P)
2375	{	2375	{
2376	return (__m256i) __builtin_ia32_loaddquqi256_mask ((__v32qi *) __P,	2376	return (__m256i) __builtin_ia32_loaddquqi256_mask ((const __v32qi *) __P,
2377	(__v32qi) __W,	2377	(__v32qi) __W,
2378	(__mmask32) __U);	2378	(__mmask32) __U);
2379	}	2379	}
...	@@ -2381,7 +2381,7 @@ _mm256_mask_loadu_epi8 (__m256i __W, __mmask32 __U, void const *__P)	...	@@ -2381,7 +2381,7 @@ _mm256_mask_loadu_epi8 (__m256i __W, __mmask32 __U, void const *__P)
2381	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2381	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2382	_mm256_maskz_loadu_epi8 (__mmask32 __U, void const *__P)	2382	_mm256_maskz_loadu_epi8 (__mmask32 __U, void const *__P)
2383	{	2383	{
2384	return (__m256i) __builtin_ia32_loaddquqi256_mask ((__v32qi *) __P,	2384	return (__m256i) __builtin_ia32_loaddquqi256_mask ((const __v32qi *) __P,
2385	(__v32qi)	2385	(__v32qi)
2386	_mm256_setzero_si256 (),	2386	_mm256_setzero_si256 (),
2387	(__mmask32) __U);	2387	(__mmask32) __U);

lib/include/avx512vlintrin.h+56-56

...	@@ -2505,7 +2505,7 @@ _mm256_maskz_expand_epi64 (__mmask8 __U, __m256i __A) {	...	@@ -2505,7 +2505,7 @@ _mm256_maskz_expand_epi64 (__mmask8 __U, __m256i __A) {
2505		2505
2506	static __inline__ __m128d __DEFAULT_FN_ATTRS128	2506	static __inline__ __m128d __DEFAULT_FN_ATTRS128
2507	_mm_mask_expandloadu_pd (__m128d __W, __mmask8 __U, void const *__P) {	2507	_mm_mask_expandloadu_pd (__m128d __W, __mmask8 __U, void const *__P) {
2508	return (__m128d) __builtin_ia32_expandloaddf128_mask ((__v2df *) __P,	2508	return (__m128d) __builtin_ia32_expandloaddf128_mask ((const __v2df *) __P,
2509	(__v2df) __W,	2509	(__v2df) __W,
2510	(__mmask8)	2510	(__mmask8)
2511	__U);	2511	__U);
...	@@ -2513,7 +2513,7 @@ _mm_mask_expandloadu_pd (__m128d __W, __mmask8 __U, void const *__P) {	...	@@ -2513,7 +2513,7 @@ _mm_mask_expandloadu_pd (__m128d __W, __mmask8 __U, void const *__P) {
2513		2513
2514	static __inline__ __m128d __DEFAULT_FN_ATTRS128	2514	static __inline__ __m128d __DEFAULT_FN_ATTRS128
2515	_mm_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {	2515	_mm_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {
2516	return (__m128d) __builtin_ia32_expandloaddf128_mask ((__v2df *) __P,	2516	return (__m128d) __builtin_ia32_expandloaddf128_mask ((const __v2df *) __P,
2517	(__v2df)	2517	(__v2df)
2518	_mm_setzero_pd (),	2518	_mm_setzero_pd (),
2519	(__mmask8)	2519	(__mmask8)
...	@@ -2522,7 +2522,7 @@ _mm_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {	...	@@ -2522,7 +2522,7 @@ _mm_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {
2522		2522
2523	static __inline__ __m256d __DEFAULT_FN_ATTRS256	2523	static __inline__ __m256d __DEFAULT_FN_ATTRS256
2524	_mm256_mask_expandloadu_pd (__m256d __W, __mmask8 __U, void const *__P) {	2524	_mm256_mask_expandloadu_pd (__m256d __W, __mmask8 __U, void const *__P) {
2525	return (__m256d) __builtin_ia32_expandloaddf256_mask ((__v4df *) __P,	2525	return (__m256d) __builtin_ia32_expandloaddf256_mask ((const __v4df *) __P,
2526	(__v4df) __W,	2526	(__v4df) __W,
2527	(__mmask8)	2527	(__mmask8)
2528	__U);	2528	__U);
...	@@ -2530,7 +2530,7 @@ _mm256_mask_expandloadu_pd (__m256d __W, __mmask8 __U, void const *__P) {	...	@@ -2530,7 +2530,7 @@ _mm256_mask_expandloadu_pd (__m256d __W, __mmask8 __U, void const *__P) {
2530		2530
2531	static __inline__ __m256d __DEFAULT_FN_ATTRS256	2531	static __inline__ __m256d __DEFAULT_FN_ATTRS256
2532	_mm256_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {	2532	_mm256_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {
2533	return (__m256d) __builtin_ia32_expandloaddf256_mask ((__v4df *) __P,	2533	return (__m256d) __builtin_ia32_expandloaddf256_mask ((const __v4df *) __P,
2534	(__v4df)	2534	(__v4df)
2535	_mm256_setzero_pd (),	2535	_mm256_setzero_pd (),
2536	(__mmask8)	2536	(__mmask8)
...	@@ -2539,7 +2539,7 @@ _mm256_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {	...	@@ -2539,7 +2539,7 @@ _mm256_maskz_expandloadu_pd (__mmask8 __U, void const *__P) {
2539		2539
2540	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2540	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2541	_mm_mask_expandloadu_epi64 (__m128i __W, __mmask8 __U, void const *__P) {	2541	_mm_mask_expandloadu_epi64 (__m128i __W, __mmask8 __U, void const *__P) {
2542	return (__m128i) __builtin_ia32_expandloaddi128_mask ((__v2di *) __P,	2542	return (__m128i) __builtin_ia32_expandloaddi128_mask ((const __v2di *) __P,
2543	(__v2di) __W,	2543	(__v2di) __W,
2544	(__mmask8)	2544	(__mmask8)
2545	__U);	2545	__U);
...	@@ -2547,7 +2547,7 @@ _mm_mask_expandloadu_epi64 (__m128i __W, __mmask8 __U, void const *__P) {	...	@@ -2547,7 +2547,7 @@ _mm_mask_expandloadu_epi64 (__m128i __W, __mmask8 __U, void const *__P) {
2547		2547
2548	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2548	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2549	_mm_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {	2549	_mm_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {
2550	return (__m128i) __builtin_ia32_expandloaddi128_mask ((__v2di *) __P,	2550	return (__m128i) __builtin_ia32_expandloaddi128_mask ((const __v2di *) __P,
2551	(__v2di)	2551	(__v2di)
2552	_mm_setzero_si128 (),	2552	_mm_setzero_si128 (),
2553	(__mmask8)	2553	(__mmask8)
...	@@ -2557,7 +2557,7 @@ _mm_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {	...	@@ -2557,7 +2557,7 @@ _mm_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {
2557	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2557	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2558	_mm256_mask_expandloadu_epi64 (__m256i __W, __mmask8 __U,	2558	_mm256_mask_expandloadu_epi64 (__m256i __W, __mmask8 __U,
2559	void const *__P) {	2559	void const *__P) {
2560	return (__m256i) __builtin_ia32_expandloaddi256_mask ((__v4di *) __P,	2560	return (__m256i) __builtin_ia32_expandloaddi256_mask ((const __v4di *) __P,
2561	(__v4di) __W,	2561	(__v4di) __W,
2562	(__mmask8)	2562	(__mmask8)
2563	__U);	2563	__U);
...	@@ -2565,7 +2565,7 @@ _mm256_mask_expandloadu_epi64 (__m256i __W, __mmask8 __U,	...	@@ -2565,7 +2565,7 @@ _mm256_mask_expandloadu_epi64 (__m256i __W, __mmask8 __U,
2565		2565
2566	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2566	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2567	_mm256_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {	2567	_mm256_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {
2568	return (__m256i) __builtin_ia32_expandloaddi256_mask ((__v4di *) __P,	2568	return (__m256i) __builtin_ia32_expandloaddi256_mask ((const __v4di *) __P,
2569	(__v4di)	2569	(__v4di)
2570	_mm256_setzero_si256 (),	2570	_mm256_setzero_si256 (),
2571	(__mmask8)	2571	(__mmask8)
...	@@ -2574,14 +2574,14 @@ _mm256_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {	...	@@ -2574,14 +2574,14 @@ _mm256_maskz_expandloadu_epi64 (__mmask8 __U, void const *__P) {
2574		2574
2575	static __inline__ __m128 __DEFAULT_FN_ATTRS128	2575	static __inline__ __m128 __DEFAULT_FN_ATTRS128
2576	_mm_mask_expandloadu_ps (__m128 __W, __mmask8 __U, void const *__P) {	2576	_mm_mask_expandloadu_ps (__m128 __W, __mmask8 __U, void const *__P) {
2577	return (__m128) __builtin_ia32_expandloadsf128_mask ((__v4sf *) __P,	2577	return (__m128) __builtin_ia32_expandloadsf128_mask ((const __v4sf *) __P,
2578	(__v4sf) __W,	2578	(__v4sf) __W,
2579	(__mmask8) __U);	2579	(__mmask8) __U);
2580	}	2580	}
2581		2581
2582	static __inline__ __m128 __DEFAULT_FN_ATTRS128	2582	static __inline__ __m128 __DEFAULT_FN_ATTRS128
2583	_mm_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {	2583	_mm_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {
2584	return (__m128) __builtin_ia32_expandloadsf128_mask ((__v4sf *) __P,	2584	return (__m128) __builtin_ia32_expandloadsf128_mask ((const __v4sf *) __P,
2585	(__v4sf)	2585	(__v4sf)
2586	_mm_setzero_ps (),	2586	_mm_setzero_ps (),
2587	(__mmask8)	2587	(__mmask8)
...	@@ -2590,14 +2590,14 @@ _mm_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {	...	@@ -2590,14 +2590,14 @@ _mm_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {
2590		2590
2591	static __inline__ __m256 __DEFAULT_FN_ATTRS256	2591	static __inline__ __m256 __DEFAULT_FN_ATTRS256
2592	_mm256_mask_expandloadu_ps (__m256 __W, __mmask8 __U, void const *__P) {	2592	_mm256_mask_expandloadu_ps (__m256 __W, __mmask8 __U, void const *__P) {
2593	return (__m256) __builtin_ia32_expandloadsf256_mask ((__v8sf *) __P,	2593	return (__m256) __builtin_ia32_expandloadsf256_mask ((const __v8sf *) __P,
2594	(__v8sf) __W,	2594	(__v8sf) __W,
2595	(__mmask8) __U);	2595	(__mmask8) __U);
2596	}	2596	}
2597		2597
2598	static __inline__ __m256 __DEFAULT_FN_ATTRS256	2598	static __inline__ __m256 __DEFAULT_FN_ATTRS256
2599	_mm256_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {	2599	_mm256_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {
2600	return (__m256) __builtin_ia32_expandloadsf256_mask ((__v8sf *) __P,	2600	return (__m256) __builtin_ia32_expandloadsf256_mask ((const __v8sf *) __P,
2601	(__v8sf)	2601	(__v8sf)
2602	_mm256_setzero_ps (),	2602	_mm256_setzero_ps (),
2603	(__mmask8)	2603	(__mmask8)
...	@@ -2606,7 +2606,7 @@ _mm256_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {	...	@@ -2606,7 +2606,7 @@ _mm256_maskz_expandloadu_ps (__mmask8 __U, void const *__P) {
2606		2606
2607	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2607	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2608	_mm_mask_expandloadu_epi32 (__m128i __W, __mmask8 __U, void const *__P) {	2608	_mm_mask_expandloadu_epi32 (__m128i __W, __mmask8 __U, void const *__P) {
2609	return (__m128i) __builtin_ia32_expandloadsi128_mask ((__v4si *) __P,	2609	return (__m128i) __builtin_ia32_expandloadsi128_mask ((const __v4si *) __P,
2610	(__v4si) __W,	2610	(__v4si) __W,
2611	(__mmask8)	2611	(__mmask8)
2612	__U);	2612	__U);
...	@@ -2614,7 +2614,7 @@ _mm_mask_expandloadu_epi32 (__m128i __W, __mmask8 __U, void const *__P) {	...	@@ -2614,7 +2614,7 @@ _mm_mask_expandloadu_epi32 (__m128i __W, __mmask8 __U, void const *__P) {
2614		2614
2615	static __inline__ __m128i __DEFAULT_FN_ATTRS128	2615	static __inline__ __m128i __DEFAULT_FN_ATTRS128
2616	_mm_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {	2616	_mm_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {
2617	return (__m128i) __builtin_ia32_expandloadsi128_mask ((__v4si *) __P,	2617	return (__m128i) __builtin_ia32_expandloadsi128_mask ((const __v4si *) __P,
2618	(__v4si)	2618	(__v4si)
2619	_mm_setzero_si128 (),	2619	_mm_setzero_si128 (),
2620	(__mmask8) __U);	2620	(__mmask8) __U);
...	@@ -2623,7 +2623,7 @@ _mm_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {	...	@@ -2623,7 +2623,7 @@ _mm_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {
2623	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2623	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2624	_mm256_mask_expandloadu_epi32 (__m256i __W, __mmask8 __U,	2624	_mm256_mask_expandloadu_epi32 (__m256i __W, __mmask8 __U,
2625	void const *__P) {	2625	void const *__P) {
2626	return (__m256i) __builtin_ia32_expandloadsi256_mask ((__v8si *) __P,	2626	return (__m256i) __builtin_ia32_expandloadsi256_mask ((const __v8si *) __P,
2627	(__v8si) __W,	2627	(__v8si) __W,
2628	(__mmask8)	2628	(__mmask8)
2629	__U);	2629	__U);
...	@@ -2631,7 +2631,7 @@ _mm256_mask_expandloadu_epi32 (__m256i __W, __mmask8 __U,	...	@@ -2631,7 +2631,7 @@ _mm256_mask_expandloadu_epi32 (__m256i __W, __mmask8 __U,
2631		2631
2632	static __inline__ __m256i __DEFAULT_FN_ATTRS256	2632	static __inline__ __m256i __DEFAULT_FN_ATTRS256
2633	_mm256_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {	2633	_mm256_maskz_expandloadu_epi32 (__mmask8 __U, void const *__P) {
2634	return (__m256i) __builtin_ia32_expandloadsi256_mask ((__v8si *) __P,	2634	return (__m256i) __builtin_ia32_expandloadsi256_mask ((const __v8si *) __P,
2635	(__v8si)	2635	(__v8si)
2636	_mm256_setzero_si256 (),	2636	_mm256_setzero_si256 (),
2637	(__mmask8)	2637	(__mmask8)
...	@@ -5073,13 +5073,13 @@ _mm256_maskz_mov_epi32 (__mmask8 __U, __m256i __A)	...	@@ -5073,13 +5073,13 @@ _mm256_maskz_mov_epi32 (__mmask8 __U, __m256i __A)
5073	static __inline __m128i __DEFAULT_FN_ATTRS128	5073	static __inline __m128i __DEFAULT_FN_ATTRS128
5074	_mm_load_epi32 (void const *__P)	5074	_mm_load_epi32 (void const *__P)
5075	{	5075	{
5076	return (__m128i ) __P;	5076	return (const __m128i ) __P;
5077	}	5077	}
5078		5078
5079	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5079	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5080	_mm_mask_load_epi32 (__m128i __W, __mmask8 __U, void const *__P)	5080	_mm_mask_load_epi32 (__m128i __W, __mmask8 __U, void const *__P)
5081	{	5081	{
5082	return (__m128i) __builtin_ia32_movdqa32load128_mask ((__v4si *) __P,	5082	return (__m128i) __builtin_ia32_movdqa32load128_mask ((const __v4si *) __P,
5083	(__v4si) __W,	5083	(__v4si) __W,
5084	(__mmask8)	5084	(__mmask8)
5085	__U);	5085	__U);
...	@@ -5088,7 +5088,7 @@ _mm_mask_load_epi32 (__m128i __W, __mmask8 __U, void const *__P)	...	@@ -5088,7 +5088,7 @@ _mm_mask_load_epi32 (__m128i __W, __mmask8 __U, void const *__P)
5088	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5088	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5089	_mm_maskz_load_epi32 (__mmask8 __U, void const *__P)	5089	_mm_maskz_load_epi32 (__mmask8 __U, void const *__P)
5090	{	5090	{
5091	return (__m128i) __builtin_ia32_movdqa32load128_mask ((__v4si *) __P,	5091	return (__m128i) __builtin_ia32_movdqa32load128_mask ((const __v4si *) __P,
5092	(__v4si)	5092	(__v4si)
5093	_mm_setzero_si128 (),	5093	_mm_setzero_si128 (),
5094	(__mmask8)	5094	(__mmask8)
...	@@ -5098,13 +5098,13 @@ _mm_maskz_load_epi32 (__mmask8 __U, void const *__P)	...	@@ -5098,13 +5098,13 @@ _mm_maskz_load_epi32 (__mmask8 __U, void const *__P)
5098	static __inline __m256i __DEFAULT_FN_ATTRS256	5098	static __inline __m256i __DEFAULT_FN_ATTRS256
5099	_mm256_load_epi32 (void const *__P)	5099	_mm256_load_epi32 (void const *__P)
5100	{	5100	{
5101	return (__m256i ) __P;	5101	return (const __m256i ) __P;
5102	}	5102	}
5103		5103
5104	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5104	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5105	_mm256_mask_load_epi32 (__m256i __W, __mmask8 __U, void const *__P)	5105	_mm256_mask_load_epi32 (__m256i __W, __mmask8 __U, void const *__P)
5106	{	5106	{
5107	return (__m256i) __builtin_ia32_movdqa32load256_mask ((__v8si *) __P,	5107	return (__m256i) __builtin_ia32_movdqa32load256_mask ((const __v8si *) __P,
5108	(__v8si) __W,	5108	(__v8si) __W,
5109	(__mmask8)	5109	(__mmask8)
5110	__U);	5110	__U);
...	@@ -5113,7 +5113,7 @@ _mm256_mask_load_epi32 (__m256i __W, __mmask8 __U, void const *__P)	...	@@ -5113,7 +5113,7 @@ _mm256_mask_load_epi32 (__m256i __W, __mmask8 __U, void const *__P)
5113	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5113	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5114	_mm256_maskz_load_epi32 (__mmask8 __U, void const *__P)	5114	_mm256_maskz_load_epi32 (__mmask8 __U, void const *__P)
5115	{	5115	{
5116	return (__m256i) __builtin_ia32_movdqa32load256_mask ((__v8si *) __P,	5116	return (__m256i) __builtin_ia32_movdqa32load256_mask ((const __v8si *) __P,
5117	(__v8si)	5117	(__v8si)
5118	_mm256_setzero_si256 (),	5118	_mm256_setzero_si256 (),
5119	(__mmask8)	5119	(__mmask8)
...	@@ -5183,13 +5183,13 @@ _mm256_maskz_mov_epi64 (__mmask8 __U, __m256i __A)	...	@@ -5183,13 +5183,13 @@ _mm256_maskz_mov_epi64 (__mmask8 __U, __m256i __A)
5183	static __inline __m128i __DEFAULT_FN_ATTRS128	5183	static __inline __m128i __DEFAULT_FN_ATTRS128
5184	_mm_load_epi64 (void const *__P)	5184	_mm_load_epi64 (void const *__P)
5185	{	5185	{
5186	return (__m128i ) __P;	5186	return (const __m128i ) __P;
5187	}	5187	}
5188		5188
5189	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5189	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5190	_mm_mask_load_epi64 (__m128i __W, __mmask8 __U, void const *__P)	5190	_mm_mask_load_epi64 (__m128i __W, __mmask8 __U, void const *__P)
5191	{	5191	{
5192	return (__m128i) __builtin_ia32_movdqa64load128_mask ((__v2di *) __P,	5192	return (__m128i) __builtin_ia32_movdqa64load128_mask ((const __v2di *) __P,
5193	(__v2di) __W,	5193	(__v2di) __W,
5194	(__mmask8)	5194	(__mmask8)
5195	__U);	5195	__U);
...	@@ -5198,7 +5198,7 @@ _mm_mask_load_epi64 (__m128i __W, __mmask8 __U, void const *__P)	...	@@ -5198,7 +5198,7 @@ _mm_mask_load_epi64 (__m128i __W, __mmask8 __U, void const *__P)
5198	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5198	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5199	_mm_maskz_load_epi64 (__mmask8 __U, void const *__P)	5199	_mm_maskz_load_epi64 (__mmask8 __U, void const *__P)
5200	{	5200	{
5201	return (__m128i) __builtin_ia32_movdqa64load128_mask ((__v2di *) __P,	5201	return (__m128i) __builtin_ia32_movdqa64load128_mask ((const __v2di *) __P,
5202	(__v2di)	5202	(__v2di)
5203	_mm_setzero_si128 (),	5203	_mm_setzero_si128 (),
5204	(__mmask8)	5204	(__mmask8)
...	@@ -5208,13 +5208,13 @@ _mm_maskz_load_epi64 (__mmask8 __U, void const *__P)	...	@@ -5208,13 +5208,13 @@ _mm_maskz_load_epi64 (__mmask8 __U, void const *__P)
5208	static __inline __m256i __DEFAULT_FN_ATTRS256	5208	static __inline __m256i __DEFAULT_FN_ATTRS256
5209	_mm256_load_epi64 (void const *__P)	5209	_mm256_load_epi64 (void const *__P)
5210	{	5210	{
5211	return (__m256i ) __P;	5211	return (const __m256i ) __P;
5212	}	5212	}
5213		5213
5214	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5214	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5215	_mm256_mask_load_epi64 (__m256i __W, __mmask8 __U, void const *__P)	5215	_mm256_mask_load_epi64 (__m256i __W, __mmask8 __U, void const *__P)
5216	{	5216	{
5217	return (__m256i) __builtin_ia32_movdqa64load256_mask ((__v4di *) __P,	5217	return (__m256i) __builtin_ia32_movdqa64load256_mask ((const __v4di *) __P,
5218	(__v4di) __W,	5218	(__v4di) __W,
5219	(__mmask8)	5219	(__mmask8)
5220	__U);	5220	__U);
...	@@ -5223,7 +5223,7 @@ _mm256_mask_load_epi64 (__m256i __W, __mmask8 __U, void const *__P)	...	@@ -5223,7 +5223,7 @@ _mm256_mask_load_epi64 (__m256i __W, __mmask8 __U, void const *__P)
5223	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5223	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5224	_mm256_maskz_load_epi64 (__mmask8 __U, void const *__P)	5224	_mm256_maskz_load_epi64 (__mmask8 __U, void const *__P)
5225	{	5225	{
5226	return (__m256i) __builtin_ia32_movdqa64load256_mask ((__v4di *) __P,	5226	return (__m256i) __builtin_ia32_movdqa64load256_mask ((const __v4di *) __P,
5227	(__v4di)	5227	(__v4di)
5228	_mm256_setzero_si256 (),	5228	_mm256_setzero_si256 (),
5229	(__mmask8)	5229	(__mmask8)
...	@@ -5430,7 +5430,7 @@ _mm256_maskz_set1_epi64 (__mmask8 __M, long long __A)	...	@@ -5430,7 +5430,7 @@ _mm256_maskz_set1_epi64 (__mmask8 __M, long long __A)
5430	static __inline__ __m128d __DEFAULT_FN_ATTRS128	5430	static __inline__ __m128d __DEFAULT_FN_ATTRS128
5431	_mm_mask_load_pd (__m128d __W, __mmask8 __U, void const *__P)	5431	_mm_mask_load_pd (__m128d __W, __mmask8 __U, void const *__P)
5432	{	5432	{
5433	return (__m128d) __builtin_ia32_loadapd128_mask ((__v2df *) __P,	5433	return (__m128d) __builtin_ia32_loadapd128_mask ((const __v2df *) __P,
5434	(__v2df) __W,	5434	(__v2df) __W,
5435	(__mmask8) __U);	5435	(__mmask8) __U);
5436	}	5436	}
...	@@ -5438,7 +5438,7 @@ _mm_mask_load_pd (__m128d __W, __mmask8 __U, void const *__P)	...	@@ -5438,7 +5438,7 @@ _mm_mask_load_pd (__m128d __W, __mmask8 __U, void const *__P)
5438	static __inline__ __m128d __DEFAULT_FN_ATTRS128	5438	static __inline__ __m128d __DEFAULT_FN_ATTRS128
5439	_mm_maskz_load_pd (__mmask8 __U, void const *__P)	5439	_mm_maskz_load_pd (__mmask8 __U, void const *__P)
5440	{	5440	{
5441	return (__m128d) __builtin_ia32_loadapd128_mask ((__v2df *) __P,	5441	return (__m128d) __builtin_ia32_loadapd128_mask ((const __v2df *) __P,
5442	(__v2df)	5442	(__v2df)
5443	_mm_setzero_pd (),	5443	_mm_setzero_pd (),
5444	(__mmask8) __U);	5444	(__mmask8) __U);
...	@@ -5447,7 +5447,7 @@ _mm_maskz_load_pd (__mmask8 __U, void const *__P)	...	@@ -5447,7 +5447,7 @@ _mm_maskz_load_pd (__mmask8 __U, void const *__P)
5447	static __inline__ __m256d __DEFAULT_FN_ATTRS256	5447	static __inline__ __m256d __DEFAULT_FN_ATTRS256
5448	_mm256_mask_load_pd (__m256d __W, __mmask8 __U, void const *__P)	5448	_mm256_mask_load_pd (__m256d __W, __mmask8 __U, void const *__P)
5449	{	5449	{
5450	return (__m256d) __builtin_ia32_loadapd256_mask ((__v4df *) __P,	5450	return (__m256d) __builtin_ia32_loadapd256_mask ((const __v4df *) __P,
5451	(__v4df) __W,	5451	(__v4df) __W,
5452	(__mmask8) __U);	5452	(__mmask8) __U);
5453	}	5453	}
...	@@ -5455,7 +5455,7 @@ _mm256_mask_load_pd (__m256d __W, __mmask8 __U, void const *__P)	...	@@ -5455,7 +5455,7 @@ _mm256_mask_load_pd (__m256d __W, __mmask8 __U, void const *__P)
5455	static __inline__ __m256d __DEFAULT_FN_ATTRS256	5455	static __inline__ __m256d __DEFAULT_FN_ATTRS256
5456	_mm256_maskz_load_pd (__mmask8 __U, void const *__P)	5456	_mm256_maskz_load_pd (__mmask8 __U, void const *__P)
5457	{	5457	{
5458	return (__m256d) __builtin_ia32_loadapd256_mask ((__v4df *) __P,	5458	return (__m256d) __builtin_ia32_loadapd256_mask ((const __v4df *) __P,
5459	(__v4df)	5459	(__v4df)
5460	_mm256_setzero_pd (),	5460	_mm256_setzero_pd (),
5461	(__mmask8) __U);	5461	(__mmask8) __U);
...	@@ -5464,7 +5464,7 @@ _mm256_maskz_load_pd (__mmask8 __U, void const *__P)	...	@@ -5464,7 +5464,7 @@ _mm256_maskz_load_pd (__mmask8 __U, void const *__P)
5464	static __inline__ __m128 __DEFAULT_FN_ATTRS128	5464	static __inline__ __m128 __DEFAULT_FN_ATTRS128
5465	_mm_mask_load_ps (__m128 __W, __mmask8 __U, void const *__P)	5465	_mm_mask_load_ps (__m128 __W, __mmask8 __U, void const *__P)
5466	{	5466	{
5467	return (__m128) __builtin_ia32_loadaps128_mask ((__v4sf *) __P,	5467	return (__m128) __builtin_ia32_loadaps128_mask ((const __v4sf *) __P,
5468	(__v4sf) __W,	5468	(__v4sf) __W,
5469	(__mmask8) __U);	5469	(__mmask8) __U);
5470	}	5470	}
...	@@ -5472,7 +5472,7 @@ _mm_mask_load_ps (__m128 __W, __mmask8 __U, void const *__P)	...	@@ -5472,7 +5472,7 @@ _mm_mask_load_ps (__m128 __W, __mmask8 __U, void const *__P)
5472	static __inline__ __m128 __DEFAULT_FN_ATTRS128	5472	static __inline__ __m128 __DEFAULT_FN_ATTRS128
5473	_mm_maskz_load_ps (__mmask8 __U, void const *__P)	5473	_mm_maskz_load_ps (__mmask8 __U, void const *__P)
5474	{	5474	{
5475	return (__m128) __builtin_ia32_loadaps128_mask ((__v4sf *) __P,	5475	return (__m128) __builtin_ia32_loadaps128_mask ((const __v4sf *) __P,
5476	(__v4sf)	5476	(__v4sf)
5477	_mm_setzero_ps (),	5477	_mm_setzero_ps (),
5478	(__mmask8) __U);	5478	(__mmask8) __U);
...	@@ -5481,7 +5481,7 @@ _mm_maskz_load_ps (__mmask8 __U, void const *__P)	...	@@ -5481,7 +5481,7 @@ _mm_maskz_load_ps (__mmask8 __U, void const *__P)
5481	static __inline__ __m256 __DEFAULT_FN_ATTRS256	5481	static __inline__ __m256 __DEFAULT_FN_ATTRS256
5482	_mm256_mask_load_ps (__m256 __W, __mmask8 __U, void const *__P)	5482	_mm256_mask_load_ps (__m256 __W, __mmask8 __U, void const *__P)
5483	{	5483	{
5484	return (__m256) __builtin_ia32_loadaps256_mask ((__v8sf *) __P,	5484	return (__m256) __builtin_ia32_loadaps256_mask ((const __v8sf *) __P,
5485	(__v8sf) __W,	5485	(__v8sf) __W,
5486	(__mmask8) __U);	5486	(__mmask8) __U);
5487	}	5487	}
...	@@ -5489,7 +5489,7 @@ _mm256_mask_load_ps (__m256 __W, __mmask8 __U, void const *__P)	...	@@ -5489,7 +5489,7 @@ _mm256_mask_load_ps (__m256 __W, __mmask8 __U, void const *__P)
5489	static __inline__ __m256 __DEFAULT_FN_ATTRS256	5489	static __inline__ __m256 __DEFAULT_FN_ATTRS256
5490	_mm256_maskz_load_ps (__mmask8 __U, void const *__P)	5490	_mm256_maskz_load_ps (__mmask8 __U, void const *__P)
5491	{	5491	{
5492	return (__m256) __builtin_ia32_loadaps256_mask ((__v8sf *) __P,	5492	return (__m256) __builtin_ia32_loadaps256_mask ((const __v8sf *) __P,
5493	(__v8sf)	5493	(__v8sf)
5494	_mm256_setzero_ps (),	5494	_mm256_setzero_ps (),
5495	(__mmask8) __U);	5495	(__mmask8) __U);
...	@@ -5501,13 +5501,13 @@ _mm_loadu_epi64 (void const *__P)	...	@@ -5501,13 +5501,13 @@ _mm_loadu_epi64 (void const *__P)
5501	struct __loadu_epi64 {	5501	struct __loadu_epi64 {
5502	__m128i_u __v;	5502	__m128i_u __v;
5503	} __attribute__((__packed__, __may_alias__));	5503	} __attribute__((__packed__, __may_alias__));
5504	return ((struct __loadu_epi64*)__P)->__v;	5504	return ((const struct __loadu_epi64*)__P)->__v;
5505	}	5505	}
5506		5506
5507	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5507	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5508	_mm_mask_loadu_epi64 (__m128i __W, __mmask8 __U, void const *__P)	5508	_mm_mask_loadu_epi64 (__m128i __W, __mmask8 __U, void const *__P)
5509	{	5509	{
5510	return (__m128i) __builtin_ia32_loaddqudi128_mask ((__v2di *) __P,	5510	return (__m128i) __builtin_ia32_loaddqudi128_mask ((const __v2di *) __P,
5511	(__v2di) __W,	5511	(__v2di) __W,
5512	(__mmask8) __U);	5512	(__mmask8) __U);
5513	}	5513	}
...	@@ -5515,7 +5515,7 @@ _mm_mask_loadu_epi64 (__m128i __W, __mmask8 __U, void const *__P)	...	@@ -5515,7 +5515,7 @@ _mm_mask_loadu_epi64 (__m128i __W, __mmask8 __U, void const *__P)
5515	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5515	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5516	_mm_maskz_loadu_epi64 (__mmask8 __U, void const *__P)	5516	_mm_maskz_loadu_epi64 (__mmask8 __U, void const *__P)
5517	{	5517	{
5518	return (__m128i) __builtin_ia32_loaddqudi128_mask ((__v2di *) __P,	5518	return (__m128i) __builtin_ia32_loaddqudi128_mask ((const __v2di *) __P,
5519	(__v2di)	5519	(__v2di)
5520	_mm_setzero_si128 (),	5520	_mm_setzero_si128 (),
5521	(__mmask8) __U);	5521	(__mmask8) __U);
...	@@ -5527,13 +5527,13 @@ _mm256_loadu_epi64 (void const *__P)	...	@@ -5527,13 +5527,13 @@ _mm256_loadu_epi64 (void const *__P)
5527	struct __loadu_epi64 {	5527	struct __loadu_epi64 {
5528	__m256i_u __v;	5528	__m256i_u __v;
5529	} __attribute__((__packed__, __may_alias__));	5529	} __attribute__((__packed__, __may_alias__));
5530	return ((struct __loadu_epi64*)__P)->__v;	5530	return ((const struct __loadu_epi64*)__P)->__v;
5531	}	5531	}
5532		5532
5533	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5533	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5534	_mm256_mask_loadu_epi64 (__m256i __W, __mmask8 __U, void const *__P)	5534	_mm256_mask_loadu_epi64 (__m256i __W, __mmask8 __U, void const *__P)
5535	{	5535	{
5536	return (__m256i) __builtin_ia32_loaddqudi256_mask ((__v4di *) __P,	5536	return (__m256i) __builtin_ia32_loaddqudi256_mask ((const __v4di *) __P,
5537	(__v4di) __W,	5537	(__v4di) __W,
5538	(__mmask8) __U);	5538	(__mmask8) __U);
5539	}	5539	}
...	@@ -5541,7 +5541,7 @@ _mm256_mask_loadu_epi64 (__m256i __W, __mmask8 __U, void const *__P)	...	@@ -5541,7 +5541,7 @@ _mm256_mask_loadu_epi64 (__m256i __W, __mmask8 __U, void const *__P)
5541	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5541	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5542	_mm256_maskz_loadu_epi64 (__mmask8 __U, void const *__P)	5542	_mm256_maskz_loadu_epi64 (__mmask8 __U, void const *__P)
5543	{	5543	{
5544	return (__m256i) __builtin_ia32_loaddqudi256_mask ((__v4di *) __P,	5544	return (__m256i) __builtin_ia32_loaddqudi256_mask ((const __v4di *) __P,
5545	(__v4di)	5545	(__v4di)
5546	_mm256_setzero_si256 (),	5546	_mm256_setzero_si256 (),
5547	(__mmask8) __U);	5547	(__mmask8) __U);
...	@@ -5553,13 +5553,13 @@ _mm_loadu_epi32 (void const *__P)	...	@@ -5553,13 +5553,13 @@ _mm_loadu_epi32 (void const *__P)
5553	struct __loadu_epi32 {	5553	struct __loadu_epi32 {
5554	__m128i_u __v;	5554	__m128i_u __v;
5555	} __attribute__((__packed__, __may_alias__));	5555	} __attribute__((__packed__, __may_alias__));
5556	return ((struct __loadu_epi32*)__P)->__v;	5556	return ((const struct __loadu_epi32*)__P)->__v;
5557	}	5557	}
5558		5558
5559	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5559	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5560	_mm_mask_loadu_epi32 (__m128i __W, __mmask8 __U, void const *__P)	5560	_mm_mask_loadu_epi32 (__m128i __W, __mmask8 __U, void const *__P)
5561	{	5561	{
5562	return (__m128i) __builtin_ia32_loaddqusi128_mask ((__v4si *) __P,	5562	return (__m128i) __builtin_ia32_loaddqusi128_mask ((const __v4si *) __P,
5563	(__v4si) __W,	5563	(__v4si) __W,
5564	(__mmask8) __U);	5564	(__mmask8) __U);
5565	}	5565	}
...	@@ -5567,7 +5567,7 @@ _mm_mask_loadu_epi32 (__m128i __W, __mmask8 __U, void const *__P)	...	@@ -5567,7 +5567,7 @@ _mm_mask_loadu_epi32 (__m128i __W, __mmask8 __U, void const *__P)
5567	static __inline__ __m128i __DEFAULT_FN_ATTRS128	5567	static __inline__ __m128i __DEFAULT_FN_ATTRS128
5568	_mm_maskz_loadu_epi32 (__mmask8 __U, void const *__P)	5568	_mm_maskz_loadu_epi32 (__mmask8 __U, void const *__P)
5569	{	5569	{
5570	return (__m128i) __builtin_ia32_loaddqusi128_mask ((__v4si *) __P,	5570	return (__m128i) __builtin_ia32_loaddqusi128_mask ((const __v4si *) __P,
5571	(__v4si)	5571	(__v4si)
5572	_mm_setzero_si128 (),	5572	_mm_setzero_si128 (),
5573	(__mmask8) __U);	5573	(__mmask8) __U);
...	@@ -5579,13 +5579,13 @@ _mm256_loadu_epi32 (void const *__P)	...	@@ -5579,13 +5579,13 @@ _mm256_loadu_epi32 (void const *__P)
5579	struct __loadu_epi32 {	5579	struct __loadu_epi32 {
5580	__m256i_u __v;	5580	__m256i_u __v;
5581	} __attribute__((__packed__, __may_alias__));	5581	} __attribute__((__packed__, __may_alias__));
5582	return ((struct __loadu_epi32*)__P)->__v;	5582	return ((const struct __loadu_epi32*)__P)->__v;
5583	}	5583	}
5584		5584
5585	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5585	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5586	_mm256_mask_loadu_epi32 (__m256i __W, __mmask8 __U, void const *__P)	5586	_mm256_mask_loadu_epi32 (__m256i __W, __mmask8 __U, void const *__P)
5587	{	5587	{
5588	return (__m256i) __builtin_ia32_loaddqusi256_mask ((__v8si *) __P,	5588	return (__m256i) __builtin_ia32_loaddqusi256_mask ((const __v8si *) __P,
5589	(__v8si) __W,	5589	(__v8si) __W,
5590	(__mmask8) __U);	5590	(__mmask8) __U);
5591	}	5591	}
...	@@ -5593,7 +5593,7 @@ _mm256_mask_loadu_epi32 (__m256i __W, __mmask8 __U, void const *__P)	...	@@ -5593,7 +5593,7 @@ _mm256_mask_loadu_epi32 (__m256i __W, __mmask8 __U, void const *__P)
5593	static __inline__ __m256i __DEFAULT_FN_ATTRS256	5593	static __inline__ __m256i __DEFAULT_FN_ATTRS256
5594	_mm256_maskz_loadu_epi32 (__mmask8 __U, void const *__P)	5594	_mm256_maskz_loadu_epi32 (__mmask8 __U, void const *__P)
5595	{	5595	{
5596	return (__m256i) __builtin_ia32_loaddqusi256_mask ((__v8si *) __P,	5596	return (__m256i) __builtin_ia32_loaddqusi256_mask ((const __v8si *) __P,
5597	(__v8si)	5597	(__v8si)
5598	_mm256_setzero_si256 (),	5598	_mm256_setzero_si256 (),
5599	(__mmask8) __U);	5599	(__mmask8) __U);
...	@@ -5602,7 +5602,7 @@ _mm256_maskz_loadu_epi32 (__mmask8 __U, void const *__P)	...	@@ -5602,7 +5602,7 @@ _mm256_maskz_loadu_epi32 (__mmask8 __U, void const *__P)
5602	static __inline__ __m128d __DEFAULT_FN_ATTRS128	5602	static __inline__ __m128d __DEFAULT_FN_ATTRS128
5603	_mm_mask_loadu_pd (__m128d __W, __mmask8 __U, void const *__P)	5603	_mm_mask_loadu_pd (__m128d __W, __mmask8 __U, void const *__P)
5604	{	5604	{
5605	return (__m128d) __builtin_ia32_loadupd128_mask ((__v2df *) __P,	5605	return (__m128d) __builtin_ia32_loadupd128_mask ((const __v2df *) __P,
5606	(__v2df) __W,	5606	(__v2df) __W,
5607	(__mmask8) __U);	5607	(__mmask8) __U);
5608	}	5608	}
...	@@ -5610,7 +5610,7 @@ _mm_mask_loadu_pd (__m128d __W, __mmask8 __U, void const *__P)	...	@@ -5610,7 +5610,7 @@ _mm_mask_loadu_pd (__m128d __W, __mmask8 __U, void const *__P)
5610	static __inline__ __m128d __DEFAULT_FN_ATTRS128	5610	static __inline__ __m128d __DEFAULT_FN_ATTRS128
5611	_mm_maskz_loadu_pd (__mmask8 __U, void const *__P)	5611	_mm_maskz_loadu_pd (__mmask8 __U, void const *__P)
5612	{	5612	{
5613	return (__m128d) __builtin_ia32_loadupd128_mask ((__v2df *) __P,	5613	return (__m128d) __builtin_ia32_loadupd128_mask ((const __v2df *) __P,
5614	(__v2df)	5614	(__v2df)
5615	_mm_setzero_pd (),	5615	_mm_setzero_pd (),
5616	(__mmask8) __U);	5616	(__mmask8) __U);
...	@@ -5619,7 +5619,7 @@ _mm_maskz_loadu_pd (__mmask8 __U, void const *__P)	...	@@ -5619,7 +5619,7 @@ _mm_maskz_loadu_pd (__mmask8 __U, void const *__P)
5619	static __inline__ __m256d __DEFAULT_FN_ATTRS256	5619	static __inline__ __m256d __DEFAULT_FN_ATTRS256
5620	_mm256_mask_loadu_pd (__m256d __W, __mmask8 __U, void const *__P)	5620	_mm256_mask_loadu_pd (__m256d __W, __mmask8 __U, void const *__P)
5621	{	5621	{
5622	return (__m256d) __builtin_ia32_loadupd256_mask ((__v4df *) __P,	5622	return (__m256d) __builtin_ia32_loadupd256_mask ((const __v4df *) __P,
5623	(__v4df) __W,	5623	(__v4df) __W,
5624	(__mmask8) __U);	5624	(__mmask8) __U);
5625	}	5625	}
...	@@ -5627,7 +5627,7 @@ _mm256_mask_loadu_pd (__m256d __W, __mmask8 __U, void const *__P)	...	@@ -5627,7 +5627,7 @@ _mm256_mask_loadu_pd (__m256d __W, __mmask8 __U, void const *__P)
5627	static __inline__ __m256d __DEFAULT_FN_ATTRS256	5627	static __inline__ __m256d __DEFAULT_FN_ATTRS256
5628	_mm256_maskz_loadu_pd (__mmask8 __U, void const *__P)	5628	_mm256_maskz_loadu_pd (__mmask8 __U, void const *__P)
5629	{	5629	{
5630	return (__m256d) __builtin_ia32_loadupd256_mask ((__v4df *) __P,	5630	return (__m256d) __builtin_ia32_loadupd256_mask ((const __v4df *) __P,
5631	(__v4df)	5631	(__v4df)
5632	_mm256_setzero_pd (),	5632	_mm256_setzero_pd (),
5633	(__mmask8) __U);	5633	(__mmask8) __U);
...	@@ -5636,7 +5636,7 @@ _mm256_maskz_loadu_pd (__mmask8 __U, void const *__P)	...	@@ -5636,7 +5636,7 @@ _mm256_maskz_loadu_pd (__mmask8 __U, void const *__P)
5636	static __inline__ __m128 __DEFAULT_FN_ATTRS128	5636	static __inline__ __m128 __DEFAULT_FN_ATTRS128
5637	_mm_mask_loadu_ps (__m128 __W, __mmask8 __U, void const *__P)	5637	_mm_mask_loadu_ps (__m128 __W, __mmask8 __U, void const *__P)
5638	{	5638	{
5639	return (__m128) __builtin_ia32_loadups128_mask ((__v4sf *) __P,	5639	return (__m128) __builtin_ia32_loadups128_mask ((const __v4sf *) __P,
5640	(__v4sf) __W,	5640	(__v4sf) __W,
5641	(__mmask8) __U);	5641	(__mmask8) __U);
5642	}	5642	}
...	@@ -5644,7 +5644,7 @@ _mm_mask_loadu_ps (__m128 __W, __mmask8 __U, void const *__P)	...	@@ -5644,7 +5644,7 @@ _mm_mask_loadu_ps (__m128 __W, __mmask8 __U, void const *__P)
5644	static __inline__ __m128 __DEFAULT_FN_ATTRS128	5644	static __inline__ __m128 __DEFAULT_FN_ATTRS128
5645	_mm_maskz_loadu_ps (__mmask8 __U, void const *__P)	5645	_mm_maskz_loadu_ps (__mmask8 __U, void const *__P)
5646	{	5646	{
5647	return (__m128) __builtin_ia32_loadups128_mask ((__v4sf *) __P,	5647	return (__m128) __builtin_ia32_loadups128_mask ((const __v4sf *) __P,
5648	(__v4sf)	5648	(__v4sf)
5649	_mm_setzero_ps (),	5649	_mm_setzero_ps (),
5650	(__mmask8) __U);	5650	(__mmask8) __U);
...	@@ -5653,7 +5653,7 @@ _mm_maskz_loadu_ps (__mmask8 __U, void const *__P)	...	@@ -5653,7 +5653,7 @@ _mm_maskz_loadu_ps (__mmask8 __U, void const *__P)
5653	static __inline__ __m256 __DEFAULT_FN_ATTRS256	5653	static __inline__ __m256 __DEFAULT_FN_ATTRS256
5654	_mm256_mask_loadu_ps (__m256 __W, __mmask8 __U, void const *__P)	5654	_mm256_mask_loadu_ps (__m256 __W, __mmask8 __U, void const *__P)
5655	{	5655	{
5656	return (__m256) __builtin_ia32_loadups256_mask ((__v8sf *) __P,	5656	return (__m256) __builtin_ia32_loadups256_mask ((const __v8sf *) __P,
5657	(__v8sf) __W,	5657	(__v8sf) __W,
5658	(__mmask8) __U);	5658	(__mmask8) __U);
5659	}	5659	}
...	@@ -5661,7 +5661,7 @@ _mm256_mask_loadu_ps (__m256 __W, __mmask8 __U, void const *__P)	...	@@ -5661,7 +5661,7 @@ _mm256_mask_loadu_ps (__m256 __W, __mmask8 __U, void const *__P)
5661	static __inline__ __m256 __DEFAULT_FN_ATTRS256	5661	static __inline__ __m256 __DEFAULT_FN_ATTRS256
5662	_mm256_maskz_loadu_ps (__mmask8 __U, void const *__P)	5662	_mm256_maskz_loadu_ps (__mmask8 __U, void const *__P)
5663	{	5663	{
5664	return (__m256) __builtin_ia32_loadups256_mask ((__v8sf *) __P,	5664	return (__m256) __builtin_ia32_loadups256_mask ((const __v8sf *) __P,
5665	(__v8sf)	5665	(__v8sf)
5666	_mm256_setzero_ps (),	5666	_mm256_setzero_ps (),
5667	(__mmask8) __U);	5667	(__mmask8) __U);

lib/include/avxintrin.h+5-5

lib/include/bmiintrin.h+92-83

...	@@ -14,27 +14,13 @@	...	@@ -14,27 +14,13 @@
14	#ifndef __BMIINTRIN_H	14	#ifndef __BMIINTRIN_H
15	#define __BMIINTRIN_H	15	#define __BMIINTRIN_H
16		16
17	#define _tzcnt_u16(a) (__tzcnt_u16((a)))
18
19	#define _andn_u32(a, b) (__andn_u32((a), (b)))
20
21	/* _bextr_u32 != __bextr_u32 */
22	#define _blsi_u32(a) (__blsi_u32((a)))
23
24	#define _blsmsk_u32(a) (__blsmsk_u32((a)))
25
26	#define _blsr_u32(a) (__blsr_u32((a)))
27
28	#define _tzcnt_u32(a) (__tzcnt_u32((a)))
29
30	/* Define the default attributes for the functions in this file. */
31	#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("bmi")))
32
33	/* Allow using the tzcnt intrinsics even for non-BMI targets. Since the TZCNT	17	/* Allow using the tzcnt intrinsics even for non-BMI targets. Since the TZCNT
34	instruction behaves as BSF on non-BMI targets, there is code that expects	18	instruction behaves as BSF on non-BMI targets, there is code that expects
35	to use it as a potentially faster version of BSF. */	19	to use it as a potentially faster version of BSF. */
36	#define __RELAXED_FN_ATTRS __attribute__((__always_inline__, __nodebug__))	20	#define __RELAXED_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
37		21
		22	#define _tzcnt_u16(a) (__tzcnt_u16((a)))
		23
38	/// Counts the number of trailing zero bits in the operand.	24	/// Counts the number of trailing zero bits in the operand.
39	///	25	///
40	/// \headerfile <x86intrin.h>	26	/// \headerfile <x86intrin.h>
...	@@ -51,6 +37,94 @@ __tzcnt_u16(unsigned short __X)	...	@@ -51,6 +37,94 @@ __tzcnt_u16(unsigned short __X)
51	return __builtin_ia32_tzcnt_u16(__X);	37	return __builtin_ia32_tzcnt_u16(__X);
52	}	38	}
53		39
		40	/// Counts the number of trailing zero bits in the operand.
		41	///
		42	/// \headerfile <x86intrin.h>
		43	///
		44	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
		45	///
		46	/// \param __X
		47	/// An unsigned 32-bit integer whose trailing zeros are to be counted.
		48	/// \returns An unsigned 32-bit integer containing the number of trailing zero
		49	/// bits in the operand.
		50	static __inline__ unsigned int __RELAXED_FN_ATTRS
		51	__tzcnt_u32(unsigned int __X)
		52	{
		53	return __builtin_ia32_tzcnt_u32(__X);
		54	}
		55
		56	/// Counts the number of trailing zero bits in the operand.
		57	///
		58	/// \headerfile <x86intrin.h>
		59	///
		60	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
		61	///
		62	/// \param __X
		63	/// An unsigned 32-bit integer whose trailing zeros are to be counted.
		64	/// \returns An 32-bit integer containing the number of trailing zero bits in
		65	/// the operand.
		66	static __inline__ int __RELAXED_FN_ATTRS
		67	_mm_tzcnt_32(unsigned int __X)
		68	{
		69	return __builtin_ia32_tzcnt_u32(__X);
		70	}
		71
		72	#define _tzcnt_u32(a) (__tzcnt_u32((a)))
		73
		74	#ifdef __x86_64__
		75
		76	/// Counts the number of trailing zero bits in the operand.
		77	///
		78	/// \headerfile <x86intrin.h>
		79	///
		80	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
		81	///
		82	/// \param __X
		83	/// An unsigned 64-bit integer whose trailing zeros are to be counted.
		84	/// \returns An unsigned 64-bit integer containing the number of trailing zero
		85	/// bits in the operand.
		86	static __inline__ unsigned long long __RELAXED_FN_ATTRS
		87	__tzcnt_u64(unsigned long long __X)
		88	{
		89	return __builtin_ia32_tzcnt_u64(__X);
		90	}
		91
		92	/// Counts the number of trailing zero bits in the operand.
		93	///
		94	/// \headerfile <x86intrin.h>
		95	///
		96	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
		97	///
		98	/// \param __X
		99	/// An unsigned 64-bit integer whose trailing zeros are to be counted.
		100	/// \returns An 64-bit integer containing the number of trailing zero bits in
		101	/// the operand.
		102	static __inline__ long long __RELAXED_FN_ATTRS
		103	_mm_tzcnt_64(unsigned long long __X)
		104	{
		105	return __builtin_ia32_tzcnt_u64(__X);
		106	}
		107
		108	#define _tzcnt_u64(a) (__tzcnt_u64((a)))
		109
		110	#endif /* __x86_64__ */
		111
		112	#undef __RELAXED_FN_ATTRS
		113
		114	#if !defined(_MSC_VER) \|\| __has_feature(modules) \|\| defined(__BMI__)
		115
		116	/* Define the default attributes for the functions in this file. */
		117	#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("bmi")))
		118
		119	#define _andn_u32(a, b) (__andn_u32((a), (b)))
		120
		121	/* _bextr_u32 != __bextr_u32 */
		122	#define _blsi_u32(a) (__blsi_u32((a)))
		123
		124	#define _blsmsk_u32(a) (__blsmsk_u32((a)))
		125
		126	#define _blsr_u32(a) (__blsr_u32((a)))
		127
54	/// Performs a bitwise AND of the second operand with the one's	128	/// Performs a bitwise AND of the second operand with the one's
55	/// complement of the first operand.	129	/// complement of the first operand.
56	///	130	///
...	@@ -169,38 +243,6 @@ __blsr_u32(unsigned int __X)	...	@@ -169,38 +243,6 @@ __blsr_u32(unsigned int __X)
169	return __X & (__X - 1);	243	return __X & (__X - 1);
170	}	244	}
171		245
172	/// Counts the number of trailing zero bits in the operand.
173	///
174	/// \headerfile <x86intrin.h>
175	///
176	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
177	///
178	/// \param __X
179	/// An unsigned 32-bit integer whose trailing zeros are to be counted.
180	/// \returns An unsigned 32-bit integer containing the number of trailing zero
181	/// bits in the operand.
182	static __inline__ unsigned int __RELAXED_FN_ATTRS
183	__tzcnt_u32(unsigned int __X)
184	{
185	return __builtin_ia32_tzcnt_u32(__X);
186	}
187
188	/// Counts the number of trailing zero bits in the operand.
189	///
190	/// \headerfile <x86intrin.h>
191	///
192	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
193	///
194	/// \param __X
195	/// An unsigned 32-bit integer whose trailing zeros are to be counted.
196	/// \returns An 32-bit integer containing the number of trailing zero bits in
197	/// the operand.
198	static __inline__ int __RELAXED_FN_ATTRS
199	_mm_tzcnt_32(unsigned int __X)
200	{
201	return __builtin_ia32_tzcnt_u32(__X);
202	}
203
204	#ifdef __x86_64__	246	#ifdef __x86_64__
205		247
206	#define _andn_u64(a, b) (__andn_u64((a), (b)))	248	#define _andn_u64(a, b) (__andn_u64((a), (b)))
...	@@ -212,8 +254,6 @@ _mm_tzcnt_32(unsigned int __X)	...	@@ -212,8 +254,6 @@ _mm_tzcnt_32(unsigned int __X)
212		254
213	#define _blsr_u64(a) (__blsr_u64((a)))	255	#define _blsr_u64(a) (__blsr_u64((a)))
214		256
215	#define _tzcnt_u64(a) (__tzcnt_u64((a)))
216
217	/// Performs a bitwise AND of the second operand with the one's	257	/// Performs a bitwise AND of the second operand with the one's
218	/// complement of the first operand.	258	/// complement of the first operand.
219	///	259	///
...	@@ -332,41 +372,10 @@ __blsr_u64(unsigned long long __X)	...	@@ -332,41 +372,10 @@ __blsr_u64(unsigned long long __X)
332	return __X & (__X - 1);	372	return __X & (__X - 1);
333	}	373	}
334		374
335	/// Counts the number of trailing zero bits in the operand.
336	///
337	/// \headerfile <x86intrin.h>
338	///
339	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
340	///
341	/// \param __X
342	/// An unsigned 64-bit integer whose trailing zeros are to be counted.
343	/// \returns An unsigned 64-bit integer containing the number of trailing zero
344	/// bits in the operand.
345	static __inline__ unsigned long long __RELAXED_FN_ATTRS
346	__tzcnt_u64(unsigned long long __X)
347	{
348	return __builtin_ia32_tzcnt_u64(__X);
349	}
350
351	/// Counts the number of trailing zero bits in the operand.
352	///
353	/// \headerfile <x86intrin.h>
354	///
355	/// This intrinsic corresponds to the <c> TZCNT </c> instruction.
356	///
357	/// \param __X
358	/// An unsigned 64-bit integer whose trailing zeros are to be counted.
359	/// \returns An 64-bit integer containing the number of trailing zero bits in
360	/// the operand.
361	static __inline__ long long __RELAXED_FN_ATTRS
362	_mm_tzcnt_64(unsigned long long __X)
363	{
364	return __builtin_ia32_tzcnt_u64(__X);
365	}
366
367	#endif /* __x86_64__ */	375	#endif /* __x86_64__ */
368		376
369	#undef __DEFAULT_FN_ATTRS	377	#undef __DEFAULT_FN_ATTRS
370	#undef __RELAXED_FN_ATTRS	378
		379	#endif /* !defined(_MSC_VER) \|\| __has_feature(modules) \|\| defined(__BMI__) */
371		380
372	#endif /* __BMIINTRIN_H */	381	#endif /* __BMIINTRIN_H */

lib/include/cpuid.h+2-2

...	@@ -38,8 +38,8 @@	...	@@ -38,8 +38,8 @@
38	#define signature_TM2_ecx 0x3638784d	38	#define signature_TM2_ecx 0x3638784d
39	/* NSC: "Geode by NSC" */	39	/* NSC: "Geode by NSC" */
40	#define signature_NSC_ebx 0x646f6547	40	#define signature_NSC_ebx 0x646f6547
41	#define signature_NSC_edx 0x43534e20	41	#define signature_NSC_edx 0x79622065
42	#define signature_NSC_ecx 0x79622065	42	#define signature_NSC_ecx 0x43534e20
43	/* NEXGEN: "NexGenDriven" */	43	/* NEXGEN: "NexGenDriven" */
44	#define signature_NEXGEN_ebx 0x4778654e	44	#define signature_NEXGEN_ebx 0x4778654e
45	#define signature_NEXGEN_edx 0x72446e65	45	#define signature_NEXGEN_edx 0x72446e65

lib/include/emmintrin.h+14-14

lib/include/ia32intrin.h+68

...	@@ -195,6 +195,74 @@ __writeeflags(unsigned int __f)	...	@@ -195,6 +195,74 @@ __writeeflags(unsigned int __f)
195	}	195	}
196	#endif /* !__x86_64__ */	196	#endif /* !__x86_64__ */
197		197
		198	/** Cast a 32-bit float value to a 32-bit unsigned integer value
		199	*
		200	* \headerfile <x86intrin.h>
		201	* This intrinsic corresponds to the <c> VMOVD / MOVD </c> instruction in x86_64,
		202	* and corresponds to the <c> VMOVL / MOVL </c> instruction in ia32.
		203	*
		204	* \param __A
		205	* A 32-bit float value.
		206	* \returns a 32-bit unsigned integer containing the converted value.
		207	*/
		208	static __inline__ unsigned int __attribute__((__always_inline__))
		209	_castf32_u32(float __A) {
		210	unsigned int D;
		211	__builtin_memcpy(&D, &__A, sizeof(__A));
		212	return D;
		213	}
		214
		215	/** Cast a 64-bit float value to a 64-bit unsigned integer value
		216	*
		217	* \headerfile <x86intrin.h>
		218	* This intrinsic corresponds to the <c> VMOVQ / MOVQ </c> instruction in x86_64,
		219	* and corresponds to the <c> VMOVL / MOVL </c> instruction in ia32.
		220	*
		221	* \param __A
		222	* A 64-bit float value.
		223	* \returns a 64-bit unsigned integer containing the converted value.
		224	*/
		225	static __inline__ unsigned long long __attribute__((__always_inline__))
		226	_castf64_u64(double __A) {
		227	unsigned long long D;
		228	__builtin_memcpy(&D, &__A, sizeof(__A));
		229	return D;
		230	}
		231
		232	/** Cast a 32-bit unsigned integer value to a 32-bit float value
		233	*
		234	* \headerfile <x86intrin.h>
		235	* This intrinsic corresponds to the <c> VMOVQ / MOVQ </c> instruction in x86_64,
		236	* and corresponds to the <c> FLDS </c> instruction in ia32.
		237	*
		238	* \param __A
		239	* A 32-bit unsigned integer value.
		240	* \returns a 32-bit float value containing the converted value.
		241	*/
		242	static __inline__ float __attribute__((__always_inline__))
		243	_castu32_f32(unsigned int __A) {
		244	float D;
		245	__builtin_memcpy(&D, &__A, sizeof(__A));
		246	return D;
		247	}
		248
		249	/** Cast a 64-bit unsigned integer value to a 64-bit float value
		250	*
		251	* \headerfile <x86intrin.h>
		252	* This intrinsic corresponds to the <c> VMOVQ / MOVQ </c> instruction in x86_64,
		253	* and corresponds to the <c> FLDL </c> instruction in ia32.
		254	*
		255	* \param __A
		256	* A 64-bit unsigned integer value.
		257	* \returns a 64-bit float value containing the converted value.
		258	*/
		259	static __inline__ double __attribute__((__always_inline__))
		260	_castu64_f64(unsigned long long __A) {
		261	double D;
		262	__builtin_memcpy(&D, &__A, sizeof(__A));
		263	return D;
		264	}
		265
198	/** Adds the unsigned integer operand to the CRC-32C checksum of the	266	/** Adds the unsigned integer operand to the CRC-32C checksum of the
199	* unsigned char operand.	267	* unsigned char operand.
200	*	268	*

lib/include/immintrin.h+4-5

...	@@ -64,9 +64,8 @@	...	@@ -64,9 +64,8 @@
64	#include <vpclmulqdqintrin.h>	64	#include <vpclmulqdqintrin.h>
65	#endif	65	#endif
66		66
67	#if !defined(_MSC_VER) \|\| __has_feature(modules) \|\| defined(__BMI__)	67	/* No feature check desired due to internal checks */
68	#include <bmiintrin.h>	68	#include <bmiintrin.h>
69	#endif
70		69
71	#if !defined(_MSC_VER) \|\| __has_feature(modules) \|\| defined(__BMI2__)	70	#if !defined(_MSC_VER) \|\| __has_feature(modules) \|\| defined(__BMI2__)
72	#include <bmi2intrin.h>	71	#include <bmi2intrin.h>
...	@@ -302,7 +301,7 @@ _loadbe_i16(void const * __P) {	...	@@ -302,7 +301,7 @@ _loadbe_i16(void const * __P) {
302	struct __loadu_i16 {	301	struct __loadu_i16 {
303	short __v;	302	short __v;
304	} __attribute__((__packed__, __may_alias__));	303	} __attribute__((__packed__, __may_alias__));
305	return __builtin_bswap16(((struct __loadu_i16*)__P)->__v);	304	return __builtin_bswap16(((const struct __loadu_i16*)__P)->__v);
306	}	305	}
307		306
308	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))	307	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))
...	@@ -318,7 +317,7 @@ _loadbe_i32(void const * __P) {	...	@@ -318,7 +317,7 @@ _loadbe_i32(void const * __P) {
318	struct __loadu_i32 {	317	struct __loadu_i32 {
319	int __v;	318	int __v;
320	} __attribute__((__packed__, __may_alias__));	319	} __attribute__((__packed__, __may_alias__));
321	return __builtin_bswap32(((struct __loadu_i32*)__P)->__v);	320	return __builtin_bswap32(((const struct __loadu_i32*)__P)->__v);
322	}	321	}
323		322
324	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))	323	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))
...	@@ -335,7 +334,7 @@ _loadbe_i64(void const * __P) {	...	@@ -335,7 +334,7 @@ _loadbe_i64(void const * __P) {
335	struct __loadu_i64 {	334	struct __loadu_i64 {
336	long long __v;	335	long long __v;
337	} __attribute__((__packed__, __may_alias__));	336	} __attribute__((__packed__, __may_alias__));
338	return __builtin_bswap64(((struct __loadu_i64*)__P)->__v);	337	return __builtin_bswap64(((const struct __loadu_i64*)__P)->__v);
339	}	338	}
340		339
341	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))	340	static __inline__ void __attribute__((__always_inline__, __nodebug__, __target__("movbe")))

lib/include/intrin.h+16-10

 @@ -36,6 +36,12 @@
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
+#if __x86_64__
+#define __LPTRINT_TYPE__ __int64
+#else
+#define __LPTRINT_TYPE__ long
+#endif
 #ifdef __cplusplus
 extern "C" {
 #endif
 @@ -94,8 +100,7 @@ void __outword(unsigned short, unsigned short);
 void __outwordstring(unsigned short, unsigned short *, unsigned long);
 unsigned long __readcr0(void);
 unsigned long __readcr2(void);
-static __inline__
+unsigned __LPTRINT_TYPE__ __readcr3(void);
-unsigned long __readcr3(void);
 unsigned long __readcr4(void);
 unsigned long __readcr8(void);
 unsigned int __readdr(unsigned int);
 @@ -132,7 +137,7 @@ void __vmx_vmptrst(unsigned __int64 *);
 void __wbinvd(void);
 void __writecr0(unsigned int);
 static __inline__
-void __writecr3(unsigned int);
+void __writecr3(unsigned __INTPTR_TYPE__);
 void __writecr4(unsigned int);
 void __writecr8(unsigned int);
 void __writedr(unsigned int, unsigned int);
 @@ -164,7 +169,6 @@ long _InterlockedExchangeAdd_HLEAcquire(long volatile *, long);
 long _InterlockedExchangeAdd_HLERelease(long volatile *, long);
 __int64 _InterlockedExchangeAdd64_HLEAcquire(__int64 volatile *, __int64);
 __int64 _InterlockedExchangeAdd64_HLERelease(__int64 volatile *, __int64);
-void __cdecl _invpcid(unsigned int, void *);
 static __inline__ void
 __attribute__((__deprecated__("use other intrinsics or C++11 atomics instead")))
 _ReadBarrier(void);
 @@ -565,24 +569,26 @@ __readmsr(unsigned long __register) {
   __asm__ ("rdmsr" : "=d"(__edx), "=a"(__eax) : "c"(__register));
   return (((unsigned __int64)__edx) << 32) | (unsigned __int64)__eax;
 }
+#endif
-static __inline__ unsigned long __DEFAULT_FN_ATTRS
+static __inline__ unsigned __LPTRINT_TYPE__ __DEFAULT_FN_ATTRS
 __readcr3(void) {
-  unsigned long __cr3_val;
+  unsigned __LPTRINT_TYPE__ __cr3_val;
-  __asm__ __volatile__ ("mov %%cr3, %0" : "=q"(__cr3_val) : : "memory");
+  __asm__ __volatile__ ("mov %%cr3, %0" : "=r"(__cr3_val) : : "memory");
   return __cr3_val;
 }
 static __inline__ void __DEFAULT_FN_ATTRS
-__writecr3(unsigned int __cr3_val) {
+__writecr3(unsigned __INTPTR_TYPE__ __cr3_val) {
-  __asm__ ("mov %0, %%cr3" : : "q"(__cr3_val) : "memory");
+  __asm__ ("mov %0, %%cr3" : : "r"(__cr3_val) : "memory");
 }
-#endif
 #ifdef __cplusplus
 }
 #endif
+#undef __LPTRINT_TYPE__
 #undef __DEFAULT_FN_ATTRS
 #endif /* __INTRIN_H */

lib/include/mwaitxintrin.h+2-2

...	@@ -17,9 +17,9 @@	...	@@ -17,9 +17,9 @@
17	/* Define the default attributes for the functions in this file. */	17	/* Define the default attributes for the functions in this file. */
18	#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("mwaitx")))	18	#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("mwaitx")))
19	static __inline__ void __DEFAULT_FN_ATTRS	19	static __inline__ void __DEFAULT_FN_ATTRS
20	_mm_monitorx(void const * __p, unsigned __extensions, unsigned __hints)	20	_mm_monitorx(void * __p, unsigned __extensions, unsigned __hints)
21	{	21	{
22	__builtin_ia32_monitorx((void *)__p, __extensions, __hints);	22	__builtin_ia32_monitorx(__p, __extensions, __hints);
23	}	23	}
24		24
25	static __inline__ void __DEFAULT_FN_ATTRS	25	static __inline__ void __DEFAULT_FN_ATTRS

lib/include/opencl-c-base.h+1-1

...	@@ -406,7 +406,7 @@ typedef enum memory_order	...	@@ -406,7 +406,7 @@ typedef enum memory_order
406	#define CLK_OUT_OF_RESOURCES -5	406	#define CLK_OUT_OF_RESOURCES -5
407		407
408	#define CLK_NULL_QUEUE 0	408	#define CLK_NULL_QUEUE 0
409	#define CLK_NULL_EVENT (__builtin_astype(((void*)(__SIZE_MAX__)), clk_event_t))	409	#define CLK_NULL_EVENT (__builtin_astype(((__SIZE_MAX__)), clk_event_t))
410		410
411	// execution model related definitions	411	// execution model related definitions
412	#define CLK_ENQUEUE_FLAGS_NO_WAIT 0x0	412	#define CLK_ENQUEUE_FLAGS_NO_WAIT 0x0

lib/include/pmmintrin.h+1-1

...	@@ -263,7 +263,7 @@ _mm_movedup_pd(__m128d __a)	...	@@ -263,7 +263,7 @@ _mm_movedup_pd(__m128d __a)
263	static __inline__ void __DEFAULT_FN_ATTRS	263	static __inline__ void __DEFAULT_FN_ATTRS
264	_mm_monitor(void const *__p, unsigned __extensions, unsigned __hints)	264	_mm_monitor(void const *__p, unsigned __extensions, unsigned __hints)
265	{	265	{
266	__builtin_ia32_monitor((void *)__p, __extensions, __hints);	266	__builtin_ia32_monitor(__p, __extensions, __hints);
267	}	267	}
268		268
269	/// Used with the MONITOR instruction to wait while the processor is in	269	/// Used with the MONITOR instruction to wait while the processor is in

lib/include/ppc_wrappers/emmintrin.h+8-2

...	@@ -35,6 +35,8 @@	...	@@ -35,6 +35,8 @@
35	#ifndef EMMINTRIN_H_	35	#ifndef EMMINTRIN_H_
36	#define EMMINTRIN_H_	36	#define EMMINTRIN_H_
37		37
		38	#if defined(__linux__) && defined(__ppc64__)
		39
38	#include <altivec.h>	40	#include <altivec.h>
39		41
40	/* We need definitions from the SSE header files. */	42	/* We need definitions from the SSE header files. */
...	@@ -1747,7 +1749,7 @@ _mm_sll_epi64 (__m128i __A, __m128i __B)	...	@@ -1747,7 +1749,7 @@ _mm_sll_epi64 (__m128i __A, __m128i __B)
1747	lshift = vec_splat ((__v2du) __B, 0);	1749	lshift = vec_splat ((__v2du) __B, 0);
1748	shmask = vec_cmplt (lshift, shmax);	1750	shmask = vec_cmplt (lshift, shmax);
1749	result = vec_sl ((__v2du) __A, lshift);	1751	result = vec_sl ((__v2du) __A, lshift);
1750	result = vec_sel ((__v2du) shmask, result, shmask);	1752	result = (__v2du)vec_sel ((__v2df) shmask, (__v2df)result, shmask);
1751		1753
1752	return (__m128i) result;	1754	return (__m128i) result;
1753	}	1755	}
...	@@ -1841,7 +1843,7 @@ _mm_srl_epi64 (__m128i __A, __m128i __B)	...	@@ -1841,7 +1843,7 @@ _mm_srl_epi64 (__m128i __A, __m128i __B)
1841	rshift = vec_splat ((__v2du) __B, 0);	1843	rshift = vec_splat ((__v2du) __B, 0);
1842	shmask = vec_cmplt (rshift, shmax);	1844	shmask = vec_cmplt (rshift, shmax);
1843	result = vec_sr ((__v2du) __A, rshift);	1845	result = vec_sr ((__v2du) __A, rshift);
1844	result = vec_sel ((__v2du) shmask, result, shmask);	1846	result = (__v2du)vec_sel ((__v2df) shmask, (__v2df)result, shmask);
1845		1847
1846	return (__m128i) result;	1848	return (__m128i) result;
1847	}	1849	}
...	@@ -2315,4 +2317,8 @@ _mm_castsi128_pd(__m128i __A)	...	@@ -2315,4 +2317,8 @@ _mm_castsi128_pd(__m128i __A)
2315	return (__m128d) __A;	2317	return (__m128d) __A;
2316	}	2318	}
2317		2319
		2320	#else
		2321	#include_next <emmintrin.h>
		2322	#endif /* defined(__linux__) && defined(__ppc64__) */
		2323
2318	#endif /* EMMINTRIN_H_ */	2324	#endif /* EMMINTRIN_H_ */

lib/include/ppc_wrappers/mm_malloc.h+6

...	@@ -10,6 +10,8 @@	...	@@ -10,6 +10,8 @@
10	#ifndef _MM_MALLOC_H_INCLUDED	10	#ifndef _MM_MALLOC_H_INCLUDED
11	#define _MM_MALLOC_H_INCLUDED	11	#define _MM_MALLOC_H_INCLUDED
12		12
		13	#if defined(__linux__) && defined(__ppc64__)
		14
13	#include <stdlib.h>	15	#include <stdlib.h>
14		16
15	/* We can't depend on <stdlib.h> since the prototype of posix_memalign	17	/* We can't depend on <stdlib.h> since the prototype of posix_memalign
...	@@ -41,4 +43,8 @@ _mm_free (void * ptr)	...	@@ -41,4 +43,8 @@ _mm_free (void * ptr)
41	free (ptr);	43	free (ptr);
42	}	44	}
43		45
		46	#else
		47	#include_next <mm_malloc.h>
		48	#endif
		49
44	#endif /* _MM_MALLOC_H_INCLUDED */	50	#endif /* _MM_MALLOC_H_INCLUDED */

lib/include/ppc_wrappers/mmintrin.h+7

...	@@ -35,6 +35,8 @@	...	@@ -35,6 +35,8 @@
35	#ifndef _MMINTRIN_H_INCLUDED	35	#ifndef _MMINTRIN_H_INCLUDED
36	#define _MMINTRIN_H_INCLUDED	36	#define _MMINTRIN_H_INCLUDED
37		37
		38	#if defined(__linux__) && defined(__ppc64__)
		39
38	#include <altivec.h>	40	#include <altivec.h>
39	/* The Intel API is flexible enough that we must allow aliasing with other	41	/* The Intel API is flexible enough that we must allow aliasing with other
40	vector types, and their scalar components. */	42	vector types, and their scalar components. */
...	@@ -1440,4 +1442,9 @@ extern __inline __m64	...	@@ -1440,4 +1442,9 @@ extern __inline __m64
1440	return (res.as_m64);	1442	return (res.as_m64);
1441	#endif	1443	#endif
1442	}	1444	}
		1445
		1446	#else
		1447	#include_next <mmintrin.h>
		1448	#endif /* defined(__linux__) && defined(__ppc64__) */
		1449
1443	#endif /* _MMINTRIN_H_INCLUDED */	1450	#endif /* _MMINTRIN_H_INCLUDED */

lib/include/ppc_wrappers/pmmintrin.h created+150

...	@@ -0,0 +1,150 @@
1	/*===---- pmmintrin.h - Implementation of SSE3 intrinsics on PowerPC -------===
2	*
3	* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4	* See https://llvm.org/LICENSE.txt for license information.
5	* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6	*
7	*===-----------------------------------------------------------------------===
8	*/
9
10	/* Implemented from the specification included in the Intel C++ Compiler
11	User Guide and Reference, version 9.0. */
12
13	#ifndef NO_WARN_X86_INTRINSICS
14	/* This header is distributed to simplify porting x86_64 code that
15	makes explicit use of Intel intrinsics to powerpc64le.
16	It is the user's responsibility to determine if the results are
17	acceptable and make additional changes as necessary.
18	Note that much code that uses Intel intrinsics can be rewritten in
19	standard C or GNU C extensions, which are more portable and better
20	optimized across multiple targets.
21
22	In the specific case of X86 SSE3 intrinsics, the PowerPC VMX/VSX ISA
23	is a good match for most SIMD operations. However the Horizontal
24	add/sub requires the data pairs be permuted into a separate
25	registers with vertical even/odd alignment for the operation.
26	And the addsub operation requires the sign of only the even numbered
27	elements be flipped (xored with -0.0).
28	For larger blocks of code using these intrinsic implementations,
29	the compiler be should be able to schedule instructions to avoid
30	additional latency.
31
32	In the specific case of the monitor and mwait instructions there are
33	no direct equivalent in the PowerISA at this time. So those
34	intrinsics are not implemented. */
35	#error "Please read comment above. Use -DNO_WARN_X86_INTRINSICS to disable this warning."
36	#endif
37
38	#ifndef PMMINTRIN_H_
39	#define PMMINTRIN_H_
40
41	#if defined(__linux__) && defined(__ppc64__)
42
43	/* We need definitions from the SSE2 and SSE header files*/
44	#include <emmintrin.h>
45
46	extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
47	_mm_addsub_ps (__m128 __X, __m128 __Y)
48	{
49	const __v4sf even_n0 = {-0.0, 0.0, -0.0, 0.0};
50	__v4sf even_neg_Y = vec_xor(__Y, even_n0);
51	return (__m128) vec_add (__X, even_neg_Y);
52	}
53
54	extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
55	_mm_addsub_pd (__m128d __X, __m128d __Y)
56	{
57	const __v2df even_n0 = {-0.0, 0.0};
58	__v2df even_neg_Y = vec_xor(__Y, even_n0);
59	return (__m128d) vec_add (__X, even_neg_Y);
60	}
61
62	extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
63	_mm_hadd_ps (__m128 __X, __m128 __Y)
64	{
65	__vector unsigned char xform2 = {
66	0x00, 0x01, 0x02, 0x03,
67	0x08, 0x09, 0x0A, 0x0B,
68	0x10, 0x11, 0x12, 0x13,
69	0x18, 0x19, 0x1A, 0x1B
70	};
71	__vector unsigned char xform1 = {
72	0x04, 0x05, 0x06, 0x07,
73	0x0C, 0x0D, 0x0E, 0x0F,
74	0x14, 0x15, 0x16, 0x17,
75	0x1C, 0x1D, 0x1E, 0x1F
76	};
77	return (__m128) vec_add (vec_perm ((__v4sf) __X, (__v4sf) __Y, xform2),
78	vec_perm ((__v4sf) __X, (__v4sf) __Y, xform1));
79	}
80
81	extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
82	_mm_hsub_ps (__m128 __X, __m128 __Y)
83	{
84	__vector unsigned char xform2 = {
85	0x00, 0x01, 0x02, 0x03,
86	0x08, 0x09, 0x0A, 0x0B,
87	0x10, 0x11, 0x12, 0x13,
88	0x18, 0x19, 0x1A, 0x1B
89	};
90	__vector unsigned char xform1 = {
91	0x04, 0x05, 0x06, 0x07,
92	0x0C, 0x0D, 0x0E, 0x0F,
93	0x14, 0x15, 0x16, 0x17,
94	0x1C, 0x1D, 0x1E, 0x1F
95	};
96	return (__m128) vec_sub (vec_perm ((__v4sf) __X, (__v4sf) __Y, xform2),
97	vec_perm ((__v4sf) __X, (__v4sf) __Y, xform1));
98	}
99
100	extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
101	_mm_hadd_pd (__m128d __X, __m128d __Y)
102	{
103	return (__m128d) vec_add (vec_mergeh ((__v2df) __X, (__v2df)__Y),
104	vec_mergel ((__v2df) __X, (__v2df)__Y));
105	}
106
107	extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
108	_mm_hsub_pd (__m128d __X, __m128d __Y)
109	{
110	return (__m128d) vec_sub (vec_mergeh ((__v2df) __X, (__v2df)__Y),
111	vec_mergel ((__v2df) __X, (__v2df)__Y));
112	}
113
114	extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
115	_mm_movehdup_ps (__m128 __X)
116	{
117	return (__m128)vec_mergeo ((__v4su)__X, (__v4su)__X);
118	}
119
120	extern __inline __m128 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
121	_mm_moveldup_ps (__m128 __X)
122	{
123	return (__m128)vec_mergee ((__v4su)__X, (__v4su)__X);
124	}
125
126	extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
127	_mm_loaddup_pd (double const *__P)
128	{
129	return (__m128d) vec_splats (*__P);
130	}
131
132	extern __inline __m128d __attribute__((__gnu_inline__, __always_inline__, __artificial__))
133	_mm_movedup_pd (__m128d __X)
134	{
135	return _mm_shuffle_pd (__X, __X, _MM_SHUFFLE2 (0,0));
136	}
137
138	extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, __artificial__))
139	_mm_lddqu_si128 (__m128i const *__P)
140	{
141	return (__m128i) (vec_vsx_ld(0, (signed int const *)__P));
142	}
143
144	/* POWER8 / POWER9 have no equivalent for _mm_monitor nor _mm_wait. */
145
146	#else
147	#include_next <pmmintrin.h>
148	#endif /* defined(__linux__) && defined(__ppc64__) */
149
150	#endif /* PMMINTRIN_H_ */

lib/include/ppc_wrappers/smmintrin.h created+85

...	@@ -0,0 +1,85 @@
1	/*===---- smmintrin.h - Implementation of SSE4 intrinsics on PowerPC -------===
2	*
3	* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4	* See https://llvm.org/LICENSE.txt for license information.
5	* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6	*
7	*===-----------------------------------------------------------------------===
8	*/
9
10	/* Implemented from the specification included in the Intel C++ Compiler
11	User Guide and Reference, version 9.0.
12
13	NOTE: This is NOT a complete implementation of the SSE4 intrinsics! */
14
15	#ifndef NO_WARN_X86_INTRINSICS
16	/* This header is distributed to simplify porting x86_64 code that
17	makes explicit use of Intel intrinsics to powerp64/powerpc64le.
18
19	It is the user's responsibility to determine if the results are
20	acceptable and make additional changes as necessary.
21
22	Note that much code that uses Intel intrinsics can be rewritten in
23	standard C or GNU C extensions, which are more portable and better
24	optimized across multiple targets. */
25	#error \
26	"Please read comment above. Use -DNO_WARN_X86_INTRINSICS to disable this error."
27	#endif
28
29	#ifndef SMMINTRIN_H_
30	#define SMMINTRIN_H_
31
32	#if defined(__linux__) && defined(__ppc64__)
33
34	#include <altivec.h>
35	#include <emmintrin.h>
36
37	extern __inline int
38	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
39	_mm_extract_epi8(__m128i __X, const int __N) {
40	return (unsigned char)((__v16qi)__X)[__N & 15];
41	}
42
43	extern __inline int
44	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
45	_mm_extract_epi32(__m128i __X, const int __N) {
46	return ((__v4si)__X)[__N & 3];
47	}
48
49	extern __inline int
50	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
51	_mm_extract_epi64(__m128i __X, const int __N) {
52	return ((__v2di)__X)[__N & 1];
53	}
54
55	extern __inline int
56	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
57	_mm_extract_ps(__m128 __X, const int __N) {
58	return ((__v4si)__X)[__N & 3];
59	}
60
61	extern __inline __m128i
62	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
63	_mm_blend_epi16(__m128i __A, __m128i __B, const int __imm8) {
64	__v16qi __charmask = vec_splats((signed char)__imm8);
65	__charmask = vec_gb(__charmask);
66	__v8hu __shortmask = (__v8hu)vec_unpackh(__charmask);
67	#ifdef __BIG_ENDIAN__
68	__shortmask = vec_reve(__shortmask);
69	#endif
70	return (__m128i)vec_sel((__v8hu)__A, (__v8hu)__B, __shortmask);
71	}
72
73	extern __inline __m128i
74	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
75	_mm_blendv_epi8(__m128i __A, __m128i __B, __m128i __mask) {
76	const __v16qu __seven = vec_splats((unsigned char)0x07);
77	__v16qu __lmask = vec_sra((__v16qu)__mask, __seven);
78	return (__m128i)vec_sel((__v16qu)__A, (__v16qu)__B, __lmask);
79	}
80
81	#else
82	#include_next <smmintrin.h>
83	#endif /* defined(__linux__) && defined(__ppc64__) */
84
85	#endif /* _SMMINTRIN_H_ */

lib/include/ppc_wrappers/tmmintrin.h created+495

...	@@ -0,0 +1,495 @@
1	/*===---- tmmintrin.h - Implementation of SSSE3 intrinsics on PowerPC ------===
2	*
3	* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4	* See https://llvm.org/LICENSE.txt for license information.
5	* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6	*
7	*===-----------------------------------------------------------------------===
8	*/
9
10	/* Implemented from the specification included in the Intel C++ Compiler
11	User Guide and Reference, version 9.0. */
12
13	#ifndef NO_WARN_X86_INTRINSICS
14	/* This header is distributed to simplify porting x86_64 code that
15	makes explicit use of Intel intrinsics to powerpc64le.
16
17	It is the user's responsibility to determine if the results are
18	acceptable and make additional changes as necessary.
19
20	Note that much code that uses Intel intrinsics can be rewritten in
21	standard C or GNU C extensions, which are more portable and better
22	optimized across multiple targets. */
23	#endif
24
25	#ifndef TMMINTRIN_H_
26	#define TMMINTRIN_H_
27
28	#if defined(__linux__) && defined(__ppc64__)
29
30	#include <altivec.h>
31
32	/* We need definitions from the SSE header files. */
33	#include <pmmintrin.h>
34
35	extern __inline __m128i
36	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
37	_mm_abs_epi16 (__m128i __A)
38	{
39	return (__m128i) vec_abs ((__v8hi) __A);
40	}
41
42	extern __inline __m128i
43	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
44	_mm_abs_epi32 (__m128i __A)
45	{
46	return (__m128i) vec_abs ((__v4si) __A);
47	}
48
49	extern __inline __m128i
50	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
51	_mm_abs_epi8 (__m128i __A)
52	{
53	return (__m128i) vec_abs ((__v16qi) __A);
54	}
55
56	extern __inline __m64
57	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
58	_mm_abs_pi16 (__m64 __A)
59	{
60	__v8hi __B = (__v8hi) (__v2du) { __A, __A };
61	return (__m64) ((__v2du) vec_abs (__B))[0];
62	}
63
64	extern __inline __m64
65	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
66	_mm_abs_pi32 (__m64 __A)
67	{
68	__v4si __B = (__v4si) (__v2du) { __A, __A };
69	return (__m64) ((__v2du) vec_abs (__B))[0];
70	}
71
72	extern __inline __m64
73	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
74	_mm_abs_pi8 (__m64 __A)
75	{
76	__v16qi __B = (__v16qi) (__v2du) { __A, __A };
77	return (__m64) ((__v2du) vec_abs (__B))[0];
78	}
79
80	extern __inline __m128i
81	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
82	_mm_alignr_epi8 (__m128i __A, __m128i __B, const unsigned int __count)
83	{
84	if (__builtin_constant_p (__count) && __count < 16)
85	{
86	#ifdef __LITTLE_ENDIAN__
87	__A = (__m128i) vec_reve ((__v16qu) __A);
88	__B = (__m128i) vec_reve ((__v16qu) __B);
89	#endif
90	__A = (__m128i) vec_sld ((__v16qu) __B, (__v16qu) __A, __count);
91	#ifdef __LITTLE_ENDIAN__
92	__A = (__m128i) vec_reve ((__v16qu) __A);
93	#endif
94	return __A;
95	}
96
97	if (__count == 0)
98	return __B;
99
100	if (__count >= 16)
101	{
102	if (__count >= 32)
103	{
104	const __v16qu zero = { 0 };
105	return (__m128i) zero;
106	}
107	else
108	{
109	const __v16qu __shift =
110	vec_splats ((unsigned char) ((__count - 16) * 8));
111	#ifdef __LITTLE_ENDIAN__
112	return (__m128i) vec_sro ((__v16qu) __A, __shift);
113	#else
114	return (__m128i) vec_slo ((__v16qu) __A, __shift);
115	#endif
116	}
117	}
118	else
119	{
120	const __v16qu __shiftA =
121	vec_splats ((unsigned char) ((16 - __count) * 8));
122	const __v16qu __shiftB = vec_splats ((unsigned char) (__count * 8));
123	#ifdef __LITTLE_ENDIAN__
124	__A = (__m128i) vec_slo ((__v16qu) __A, __shiftA);
125	__B = (__m128i) vec_sro ((__v16qu) __B, __shiftB);
126	#else
127	__A = (__m128i) vec_sro ((__v16qu) __A, __shiftA);
128	__B = (__m128i) vec_slo ((__v16qu) __B, __shiftB);
129	#endif
130	return (__m128i) vec_or ((__v16qu) __A, (__v16qu) __B);
131	}
132	}
133
134	extern __inline __m64
135	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
136	_mm_alignr_pi8 (__m64 __A, __m64 __B, unsigned int __count)
137	{
138	if (__count < 16)
139	{
140	__v2du __C = { __B, __A };
141	#ifdef __LITTLE_ENDIAN__
142	const __v4su __shift = { __count << 3, 0, 0, 0 };
143	__C = (__v2du) vec_sro ((__v16qu) __C, (__v16qu) __shift);
144	#else
145	const __v4su __shift = { 0, 0, 0, __count << 3 };
146	__C = (__v2du) vec_slo ((__v16qu) __C, (__v16qu) __shift);
147	#endif
148	return (__m64) __C[0];
149	}
150	else
151	{
152	const __m64 __zero = { 0 };
153	return __zero;
154	}
155	}
156
157	extern __inline __m128i
158	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
159	_mm_hadd_epi16 (__m128i __A, __m128i __B)
160	{
161	const __v16qu __P =
162	{ 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29 };
163	const __v16qu __Q =
164	{ 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 };
165	__v8hi __C = vec_perm ((__v8hi) __A, (__v8hi) __B, __P);
166	__v8hi __D = vec_perm ((__v8hi) __A, (__v8hi) __B, __Q);
167	return (__m128i) vec_add (__C, __D);
168	}
169
170	extern __inline __m128i
171	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
172	_mm_hadd_epi32 (__m128i __A, __m128i __B)
173	{
174	const __v16qu __P =
175	{ 0, 1, 2, 3, 8, 9, 10, 11, 16, 17, 18, 19, 24, 25, 26, 27 };
176	const __v16qu __Q =
177	{ 4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 23, 28, 29, 30, 31 };
178	__v4si __C = vec_perm ((__v4si) __A, (__v4si) __B, __P);
179	__v4si __D = vec_perm ((__v4si) __A, (__v4si) __B, __Q);
180	return (__m128i) vec_add (__C, __D);
181	}
182
183	extern __inline __m64
184	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
185	_mm_hadd_pi16 (__m64 __A, __m64 __B)
186	{
187	__v8hi __C = (__v8hi) (__v2du) { __A, __B };
188	const __v16qu __P =
189	{ 0, 1, 4, 5, 8, 9, 12, 13, 0, 1, 4, 5, 8, 9, 12, 13 };
190	const __v16qu __Q =
191	{ 2, 3, 6, 7, 10, 11, 14, 15, 2, 3, 6, 7, 10, 11, 14, 15 };
192	__v8hi __D = vec_perm (__C, __C, __Q);
193	__C = vec_perm (__C, __C, __P);
194	__C = vec_add (__C, __D);
195	return (__m64) ((__v2du) __C)[1];
196	}
197
198	extern __inline __m64
199	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
200	_mm_hadd_pi32 (__m64 __A, __m64 __B)
201	{
202	__v4si __C = (__v4si) (__v2du) { __A, __B };
203	const __v16qu __P =
204	{ 0, 1, 2, 3, 8, 9, 10, 11, 0, 1, 2, 3, 8, 9, 10, 11 };
205	const __v16qu __Q =
206	{ 4, 5, 6, 7, 12, 13, 14, 15, 4, 5, 6, 7, 12, 13, 14, 15 };
207	__v4si __D = vec_perm (__C, __C, __Q);
208	__C = vec_perm (__C, __C, __P);
209	__C = vec_add (__C, __D);
210	return (__m64) ((__v2du) __C)[1];
211	}
212
213	extern __inline __m128i
214	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
215	_mm_hadds_epi16 (__m128i __A, __m128i __B)
216	{
217	__v4si __C = { 0 }, __D = { 0 };
218	__C = vec_sum4s ((__v8hi) __A, __C);
219	__D = vec_sum4s ((__v8hi) __B, __D);
220	__C = (__v4si) vec_packs (__C, __D);
221	return (__m128i) __C;
222	}
223
224	extern __inline __m64
225	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
226	_mm_hadds_pi16 (__m64 __A, __m64 __B)
227	{
228	const __v4si __zero = { 0 };
229	__v8hi __C = (__v8hi) (__v2du) { __A, __B };
230	__v4si __D = vec_sum4s (__C, __zero);
231	__C = vec_packs (__D, __D);
232	return (__m64) ((__v2du) __C)[1];
233	}
234
235	extern __inline __m128i
236	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
237	_mm_hsub_epi16 (__m128i __A, __m128i __B)
238	{
239	const __v16qu __P =
240	{ 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29 };
241	const __v16qu __Q =
242	{ 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 };
243	__v8hi __C = vec_perm ((__v8hi) __A, (__v8hi) __B, __P);
244	__v8hi __D = vec_perm ((__v8hi) __A, (__v8hi) __B, __Q);
245	return (__m128i) vec_sub (__C, __D);
246	}
247
248	extern __inline __m128i
249	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
250	_mm_hsub_epi32 (__m128i __A, __m128i __B)
251	{
252	const __v16qu __P =
253	{ 0, 1, 2, 3, 8, 9, 10, 11, 16, 17, 18, 19, 24, 25, 26, 27 };
254	const __v16qu __Q =
255	{ 4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 23, 28, 29, 30, 31 };
256	__v4si __C = vec_perm ((__v4si) __A, (__v4si) __B, __P);
257	__v4si __D = vec_perm ((__v4si) __A, (__v4si) __B, __Q);
258	return (__m128i) vec_sub (__C, __D);
259	}
260
261	extern __inline __m64
262	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
263	_mm_hsub_pi16 (__m64 __A, __m64 __B)
264	{
265	const __v16qu __P =
266	{ 0, 1, 4, 5, 8, 9, 12, 13, 0, 1, 4, 5, 8, 9, 12, 13 };
267	const __v16qu __Q =
268	{ 2, 3, 6, 7, 10, 11, 14, 15, 2, 3, 6, 7, 10, 11, 14, 15 };
269	__v8hi __C = (__v8hi) (__v2du) { __A, __B };
270	__v8hi __D = vec_perm (__C, __C, __Q);
271	__C = vec_perm (__C, __C, __P);
272	__C = vec_sub (__C, __D);
273	return (__m64) ((__v2du) __C)[1];
274	}
275
276	extern __inline __m64
277	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
278	_mm_hsub_pi32 (__m64 __A, __m64 __B)
279	{
280	const __v16qu __P =
281	{ 0, 1, 2, 3, 8, 9, 10, 11, 0, 1, 2, 3, 8, 9, 10, 11 };
282	const __v16qu __Q =
283	{ 4, 5, 6, 7, 12, 13, 14, 15, 4, 5, 6, 7, 12, 13, 14, 15 };
284	__v4si __C = (__v4si) (__v2du) { __A, __B };
285	__v4si __D = vec_perm (__C, __C, __Q);
286	__C = vec_perm (__C, __C, __P);
287	__C = vec_sub (__C, __D);
288	return (__m64) ((__v2du) __C)[1];
289	}
290
291	extern __inline __m128i
292	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
293	_mm_hsubs_epi16 (__m128i __A, __m128i __B)
294	{
295	const __v16qu __P =
296	{ 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29 };
297	const __v16qu __Q =
298	{ 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 };
299	__v8hi __C = vec_perm ((__v8hi) __A, (__v8hi) __B, __P);
300	__v8hi __D = vec_perm ((__v8hi) __A, (__v8hi) __B, __Q);
301	return (__m128i) vec_subs (__C, __D);
302	}
303
304	extern __inline __m64
305	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
306	_mm_hsubs_pi16 (__m64 __A, __m64 __B)
307	{
308	const __v16qu __P =
309	{ 0, 1, 4, 5, 8, 9, 12, 13, 0, 1, 4, 5, 8, 9, 12, 13 };
310	const __v16qu __Q =
311	{ 2, 3, 6, 7, 10, 11, 14, 15, 2, 3, 6, 7, 10, 11, 14, 15 };
312	__v8hi __C = (__v8hi) (__v2du) { __A, __B };
313	__v8hi __D = vec_perm (__C, __C, __P);
314	__v8hi __E = vec_perm (__C, __C, __Q);
315	__C = vec_subs (__D, __E);
316	return (__m64) ((__v2du) __C)[1];
317	}
318
319	extern __inline __m128i
320	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
321	_mm_shuffle_epi8 (__m128i __A, __m128i __B)
322	{
323	const __v16qi __zero = { 0 };
324	__vector __bool char __select = vec_cmplt ((__v16qi) __B, __zero);
325	__v16qi __C = vec_perm ((__v16qi) __A, (__v16qi) __A, (__v16qu) __B);
326	return (__m128i) vec_sel (__C, __zero, __select);
327	}
328
329	extern __inline __m64
330	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
331	_mm_shuffle_pi8 (__m64 __A, __m64 __B)
332	{
333	const __v16qi __zero = { 0 };
334	__v16qi __C = (__v16qi) (__v2du) { __A, __A };
335	__v16qi __D = (__v16qi) (__v2du) { __B, __B };
336	__vector __bool char __select = vec_cmplt ((__v16qi) __D, __zero);
337	__C = vec_perm ((__v16qi) __C, (__v16qi) __C, (__v16qu) __D);
338	__C = vec_sel (__C, __zero, __select);
339	return (__m64) ((__v2du) (__C))[0];
340	}
341
342	extern __inline __m128i
343	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
344	_mm_sign_epi8 (__m128i __A, __m128i __B)
345	{
346	const __v16qi __zero = { 0 };
347	__v16qi __selectneg = (__v16qi) vec_cmplt ((__v16qi) __B, __zero);
348	__v16qi __selectpos =
349	(__v16qi) vec_neg ((__v16qi) vec_cmpgt ((__v16qi) __B, __zero));
350	__v16qi __conv = vec_add (__selectneg, __selectpos);
351	return (__m128i) vec_mul ((__v16qi) __A, (__v16qi) __conv);
352	}
353
354	extern __inline __m128i
355	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
356	_mm_sign_epi16 (__m128i __A, __m128i __B)
357	{
358	const __v8hi __zero = { 0 };
359	__v8hi __selectneg = (__v8hi) vec_cmplt ((__v8hi) __B, __zero);
360	__v8hi __selectpos =
361	(__v8hi) vec_neg ((__v8hi) vec_cmpgt ((__v8hi) __B, __zero));
362	__v8hi __conv = vec_add (__selectneg, __selectpos);
363	return (__m128i) vec_mul ((__v8hi) __A, (__v8hi) __conv);
364	}
365
366	extern __inline __m128i
367	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
368	_mm_sign_epi32 (__m128i __A, __m128i __B)
369	{
370	const __v4si __zero = { 0 };
371	__v4si __selectneg = (__v4si) vec_cmplt ((__v4si) __B, __zero);
372	__v4si __selectpos =
373	(__v4si) vec_neg ((__v4si) vec_cmpgt ((__v4si) __B, __zero));
374	__v4si __conv = vec_add (__selectneg, __selectpos);
375	return (__m128i) vec_mul ((__v4si) __A, (__v4si) __conv);
376	}
377
378	extern __inline __m64
379	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
380	_mm_sign_pi8 (__m64 __A, __m64 __B)
381	{
382	const __v16qi __zero = { 0 };
383	__v16qi __C = (__v16qi) (__v2du) { __A, __A };
384	__v16qi __D = (__v16qi) (__v2du) { __B, __B };
385	__C = (__v16qi) _mm_sign_epi8 ((__m128i) __C, (__m128i) __D);
386	return (__m64) ((__v2du) (__C))[0];
387	}
388
389	extern __inline __m64
390	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
391	_mm_sign_pi16 (__m64 __A, __m64 __B)
392	{
393	const __v8hi __zero = { 0 };
394	__v8hi __C = (__v8hi) (__v2du) { __A, __A };
395	__v8hi __D = (__v8hi) (__v2du) { __B, __B };
396	__C = (__v8hi) _mm_sign_epi16 ((__m128i) __C, (__m128i) __D);
397	return (__m64) ((__v2du) (__C))[0];
398	}
399
400	extern __inline __m64
401	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
402	_mm_sign_pi32 (__m64 __A, __m64 __B)
403	{
404	const __v4si __zero = { 0 };
405	__v4si __C = (__v4si) (__v2du) { __A, __A };
406	__v4si __D = (__v4si) (__v2du) { __B, __B };
407	__C = (__v4si) _mm_sign_epi32 ((__m128i) __C, (__m128i) __D);
408	return (__m64) ((__v2du) (__C))[0];
409	}
410
411	extern __inline __m128i
412	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
413	_mm_maddubs_epi16 (__m128i __A, __m128i __B)
414	{
415	__v8hi __unsigned = vec_splats ((signed short) 0x00ff);
416	__v8hi __C = vec_and (vec_unpackh ((__v16qi) __A), __unsigned);
417	__v8hi __D = vec_and (vec_unpackl ((__v16qi) __A), __unsigned);
418	__v8hi __E = vec_unpackh ((__v16qi) __B);
419	__v8hi __F = vec_unpackl ((__v16qi) __B);
420	__C = vec_mul (__C, __E);
421	__D = vec_mul (__D, __F);
422	const __v16qu __odds =
423	{ 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29 };
424	const __v16qu __evens =
425	{ 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 };
426	__E = vec_perm (__C, __D, __odds);
427	__F = vec_perm (__C, __D, __evens);
428	return (__m128i) vec_adds (__E, __F);
429	}
430
431	extern __inline __m64
432	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
433	_mm_maddubs_pi16 (__m64 __A, __m64 __B)
434	{
435	__v8hi __C = (__v8hi) (__v2du) { __A, __A };
436	__C = vec_unpackl ((__v16qi) __C);
437	const __v8hi __unsigned = vec_splats ((signed short) 0x00ff);
438	__C = vec_and (__C, __unsigned);
439	__v8hi __D = (__v8hi) (__v2du) { __B, __B };
440	__D = vec_unpackl ((__v16qi) __D);
441	__D = vec_mul (__C, __D);
442	const __v16qu __odds =
443	{ 0, 1, 4, 5, 8, 9, 12, 13, 16, 17, 20, 21, 24, 25, 28, 29 };
444	const __v16qu __evens =
445	{ 2, 3, 6, 7, 10, 11, 14, 15, 18, 19, 22, 23, 26, 27, 30, 31 };
446	__C = vec_perm (__D, __D, __odds);
447	__D = vec_perm (__D, __D, __evens);
448	__C = vec_adds (__C, __D);
449	return (__m64) ((__v2du) (__C))[0];
450	}
451
452	extern __inline __m128i
453	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
454	_mm_mulhrs_epi16 (__m128i __A, __m128i __B)
455	{
456	__v4si __C = vec_unpackh ((__v8hi) __A);
457	__v4si __D = vec_unpackh ((__v8hi) __B);
458	__C = vec_mul (__C, __D);
459	__D = vec_unpackl ((__v8hi) __A);
460	__v4si __E = vec_unpackl ((__v8hi) __B);
461	__D = vec_mul (__D, __E);
462	const __v4su __shift = vec_splats ((unsigned int) 14);
463	__C = vec_sr (__C, __shift);
464	__D = vec_sr (__D, __shift);
465	const __v4si __ones = vec_splats ((signed int) 1);
466	__C = vec_add (__C, __ones);
467	__C = vec_sr (__C, (__v4su) __ones);
468	__D = vec_add (__D, __ones);
469	__D = vec_sr (__D, (__v4su) __ones);
470	return (__m128i) vec_pack (__C, __D);
471	}
472
473	extern __inline __m64
474	__attribute__((__gnu_inline__, __always_inline__, __artificial__))
475	_mm_mulhrs_pi16 (__m64 __A, __m64 __B)
476	{
477	__v4si __C = (__v4si) (__v2du) { __A, __A };
478	__C = vec_unpackh ((__v8hi) __C);
479	__v4si __D = (__v4si) (__v2du) { __B, __B };
480	__D = vec_unpackh ((__v8hi) __D);
481	__C = vec_mul (__C, __D);
482	const __v4su __shift = vec_splats ((unsigned int) 14);
483	__C = vec_sr (__C, __shift);
484	const __v4si __ones = vec_splats ((signed int) 1);
485	__C = vec_add (__C, __ones);
486	__C = vec_sr (__C, (__v4su) __ones);
487	__v8hi __E = vec_pack (__C, __D);
488	return (__m64) ((__v2du) (__E))[0];
489	}
490
491	#else
492	#include_next <tmmintrin.h>
493	#endif /* defined(__linux__) && defined(__ppc64__) */
494
495	#endif /* TMMINTRIN_H_ */

lib/include/ppc_wrappers/xmmintrin.h+6

...	@@ -34,6 +34,8 @@	...	@@ -34,6 +34,8 @@
34	#ifndef _XMMINTRIN_H_INCLUDED	34	#ifndef _XMMINTRIN_H_INCLUDED
35	#define _XMMINTRIN_H_INCLUDED	35	#define _XMMINTRIN_H_INCLUDED
36		36
		37	#if defined(__linux__) && defined(__ppc64__)
		38
37	/* Define four value permute mask */	39	/* Define four value permute mask */
38	#define _MM_SHUFFLE(w,x,y,z) (((w) << 6) \| ((x) << 4) \| ((y) << 2) \| (z))	40	#define _MM_SHUFFLE(w,x,y,z) (((w) << 6) \| ((x) << 4) \| ((y) << 2) \| (z))
39		41
...	@@ -1835,4 +1837,8 @@ do { \	...	@@ -1835,4 +1837,8 @@ do { \
1835	/* For backward source compatibility. */	1837	/* For backward source compatibility. */
1836	//# include <emmintrin.h>	1838	//# include <emmintrin.h>
1837		1839
		1840	#else
		1841	#include_next <xmmintrin.h>
		1842	#endif /* defined(__linux__) && defined(__ppc64__) */
		1843
1838	#endif /* _XMMINTRIN_H_INCLUDED */	1844	#endif /* _XMMINTRIN_H_INCLUDED */

lib/include/xmmintrin.h+7-7

...	@@ -1627,7 +1627,7 @@ _mm_loadh_pi(__m128 __a, const __m64 *__p)	...	@@ -1627,7 +1627,7 @@ _mm_loadh_pi(__m128 __a, const __m64 *__p)
1627	struct __mm_loadh_pi_struct {	1627	struct __mm_loadh_pi_struct {
1628	__mm_loadh_pi_v2f32 __u;	1628	__mm_loadh_pi_v2f32 __u;
1629	} __attribute__((__packed__, __may_alias__));	1629	} __attribute__((__packed__, __may_alias__));
1630	__mm_loadh_pi_v2f32 __b = ((struct __mm_loadh_pi_struct*)__p)->__u;	1630	__mm_loadh_pi_v2f32 __b = ((const struct __mm_loadh_pi_struct*)__p)->__u;
1631	__m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);	1631	__m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);
1632	return __builtin_shufflevector(__a, __bb, 0, 1, 4, 5);	1632	return __builtin_shufflevector(__a, __bb, 0, 1, 4, 5);
1633	}	1633	}
...	@@ -1654,7 +1654,7 @@ _mm_loadl_pi(__m128 __a, const __m64 *__p)	...	@@ -1654,7 +1654,7 @@ _mm_loadl_pi(__m128 __a, const __m64 *__p)
1654	struct __mm_loadl_pi_struct {	1654	struct __mm_loadl_pi_struct {
1655	__mm_loadl_pi_v2f32 __u;	1655	__mm_loadl_pi_v2f32 __u;
1656	} __attribute__((__packed__, __may_alias__));	1656	} __attribute__((__packed__, __may_alias__));
1657	__mm_loadl_pi_v2f32 __b = ((struct __mm_loadl_pi_struct*)__p)->__u;	1657	__mm_loadl_pi_v2f32 __b = ((const struct __mm_loadl_pi_struct*)__p)->__u;
1658	__m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);	1658	__m128 __bb = __builtin_shufflevector(__b, __b, 0, 1, 0, 1);
1659	return __builtin_shufflevector(__a, __bb, 4, 5, 2, 3);	1659	return __builtin_shufflevector(__a, __bb, 4, 5, 2, 3);
1660	}	1660	}
...	@@ -1680,7 +1680,7 @@ _mm_load_ss(const float *__p)	...	@@ -1680,7 +1680,7 @@ _mm_load_ss(const float *__p)
1680	struct __mm_load_ss_struct {	1680	struct __mm_load_ss_struct {
1681	float __u;	1681	float __u;
1682	} __attribute__((__packed__, __may_alias__));	1682	} __attribute__((__packed__, __may_alias__));
1683	float __u = ((struct __mm_load_ss_struct*)__p)->__u;	1683	float __u = ((const struct __mm_load_ss_struct*)__p)->__u;
1684	return __extension__ (__m128){ __u, 0, 0, 0 };	1684	return __extension__ (__m128){ __u, 0, 0, 0 };
1685	}	1685	}
1686		1686
...	@@ -1702,7 +1702,7 @@ _mm_load1_ps(const float *__p)	...	@@ -1702,7 +1702,7 @@ _mm_load1_ps(const float *__p)
1702	struct __mm_load1_ps_struct {	1702	struct __mm_load1_ps_struct {
1703	float __u;	1703	float __u;
1704	} __attribute__((__packed__, __may_alias__));	1704	} __attribute__((__packed__, __may_alias__));
1705	float __u = ((struct __mm_load1_ps_struct*)__p)->__u;	1705	float __u = ((const struct __mm_load1_ps_struct*)__p)->__u;
1706	return __extension__ (__m128){ __u, __u, __u, __u };	1706	return __extension__ (__m128){ __u, __u, __u, __u };
1707	}	1707	}
1708		1708
...	@@ -1722,7 +1722,7 @@ _mm_load1_ps(const float *__p)	...	@@ -1722,7 +1722,7 @@ _mm_load1_ps(const float *__p)
1722	static __inline__ __m128 __DEFAULT_FN_ATTRS	1722	static __inline__ __m128 __DEFAULT_FN_ATTRS
1723	_mm_load_ps(const float *__p)	1723	_mm_load_ps(const float *__p)
1724	{	1724	{
1725	return (__m128)__p;	1725	return (const __m128)__p;
1726	}	1726	}
1727		1727
1728	/// Loads a 128-bit floating-point vector of [4 x float] from an	1728	/// Loads a 128-bit floating-point vector of [4 x float] from an
...	@@ -1742,7 +1742,7 @@ _mm_loadu_ps(const float *__p)	...	@@ -1742,7 +1742,7 @@ _mm_loadu_ps(const float *__p)
1742	struct __loadu_ps {	1742	struct __loadu_ps {
1743	__m128_u __v;	1743	__m128_u __v;
1744	} __attribute__((__packed__, __may_alias__));	1744	} __attribute__((__packed__, __may_alias__));
1745	return ((struct __loadu_ps*)__p)->__v;	1745	return ((const struct __loadu_ps*)__p)->__v;
1746	}	1746	}
1747		1747
1748	/// Loads four packed float values, in reverse order, from an aligned	1748	/// Loads four packed float values, in reverse order, from an aligned
...	@@ -2100,7 +2100,7 @@ _mm_storer_ps(float *__p, __m128 __a)	...	@@ -2100,7 +2100,7 @@ _mm_storer_ps(float *__p, __m128 __a)
2100	/// be generated. \n	2100	/// be generated. \n
2101	/// _MM_HINT_T2: Move data using the T2 hint. The PREFETCHT2 instruction will	2101	/// _MM_HINT_T2: Move data using the T2 hint. The PREFETCHT2 instruction will
2102	/// be generated.	2102	/// be generated.
2103	#define _mm_prefetch(a, sel) (__builtin_prefetch((void *)(a), \	2103	#define _mm_prefetch(a, sel) (__builtin_prefetch((const void *)(a), \
2104	((sel) >> 2) & 1, (sel) & 0x3))	2104	((sel) >> 2) & 1, (sel) & 0x3))
2105	#endif	2105	#endif
2106		2106

...	@@ -3069,7 +3069,7 @@ _mm256_broadcast_ps(__m128 const *__a)	...	@@ -3069,7 +3069,7 @@ _mm256_broadcast_ps(__m128 const *__a)
3069	static __inline __m256d __DEFAULT_FN_ATTRS	3069	static __inline __m256d __DEFAULT_FN_ATTRS
3070	_mm256_load_pd(double const *__p)	3070	_mm256_load_pd(double const *__p)
3071	{	3071	{
3072	return (__m256d )__p;	3072	return (const __m256d )__p;
3073	}	3073	}
3074		3074
3075	/// Loads 8 single-precision floating point values from a 32-byte aligned	3075	/// Loads 8 single-precision floating point values from a 32-byte aligned
...	@@ -3085,7 +3085,7 @@ _mm256_load_pd(double const *__p)	...	@@ -3085,7 +3085,7 @@ _mm256_load_pd(double const *__p)
3085	static __inline __m256 __DEFAULT_FN_ATTRS	3085	static __inline __m256 __DEFAULT_FN_ATTRS
3086	_mm256_load_ps(float const *__p)	3086	_mm256_load_ps(float const *__p)
3087	{	3087	{
3088	return (__m256 )__p;	3088	return (const __m256 )__p;
3089	}	3089	}
3090		3090
3091	/// Loads 4 double-precision floating point values from an unaligned	3091	/// Loads 4 double-precision floating point values from an unaligned
...	@@ -3105,7 +3105,7 @@ _mm256_loadu_pd(double const *__p)	...	@@ -3105,7 +3105,7 @@ _mm256_loadu_pd(double const *__p)
3105	struct __loadu_pd {	3105	struct __loadu_pd {
3106	__m256d_u __v;	3106	__m256d_u __v;
3107	} __attribute__((__packed__, __may_alias__));	3107	} __attribute__((__packed__, __may_alias__));
3108	return ((struct __loadu_pd*)__p)->__v;	3108	return ((const struct __loadu_pd*)__p)->__v;
3109	}	3109	}
3110		3110
3111	/// Loads 8 single-precision floating point values from an unaligned	3111	/// Loads 8 single-precision floating point values from an unaligned
...	@@ -3125,7 +3125,7 @@ _mm256_loadu_ps(float const *__p)	...	@@ -3125,7 +3125,7 @@ _mm256_loadu_ps(float const *__p)
3125	struct __loadu_ps {	3125	struct __loadu_ps {
3126	__m256_u __v;	3126	__m256_u __v;
3127	} __attribute__((__packed__, __may_alias__));	3127	} __attribute__((__packed__, __may_alias__));
3128	return ((struct __loadu_ps*)__p)->__v;	3128	return ((const struct __loadu_ps*)__p)->__v;
3129	}	3129	}
3130		3130
3131	/// Loads 256 bits of integer data from a 32-byte aligned memory	3131	/// Loads 256 bits of integer data from a 32-byte aligned memory
...	@@ -3161,7 +3161,7 @@ _mm256_loadu_si256(__m256i_u const *__p)	...	@@ -3161,7 +3161,7 @@ _mm256_loadu_si256(__m256i_u const *__p)
3161	struct __loadu_si256 {	3161	struct __loadu_si256 {
3162	__m256i_u __v;	3162	__m256i_u __v;
3163	} __attribute__((__packed__, __may_alias__));	3163	} __attribute__((__packed__, __may_alias__));
3164	return ((struct __loadu_si256*)__p)->__v;	3164	return ((const struct __loadu_si256*)__p)->__v;
3165	}	3165	}
3166		3166
3167	/// Loads 256 bits of integer data from an unaligned memory location	3167	/// Loads 256 bits of integer data from an unaligned memory location

...	@@ -1578,7 +1578,7 @@ _mm_cvtsd_f64(__m128d __a)	...	@@ -1578,7 +1578,7 @@ _mm_cvtsd_f64(__m128d __a)
1578	static __inline__ __m128d __DEFAULT_FN_ATTRS	1578	static __inline__ __m128d __DEFAULT_FN_ATTRS
1579	_mm_load_pd(double const *__dp)	1579	_mm_load_pd(double const *__dp)
1580	{	1580	{
1581	return (__m128d)__dp;	1581	return (const __m128d)__dp;
1582	}	1582	}
1583		1583
1584	/// Loads a double-precision floating-point value from a specified memory	1584	/// Loads a double-precision floating-point value from a specified memory
...	@@ -1599,7 +1599,7 @@ _mm_load1_pd(double const *__dp)	...	@@ -1599,7 +1599,7 @@ _mm_load1_pd(double const *__dp)
1599	struct __mm_load1_pd_struct {	1599	struct __mm_load1_pd_struct {
1600	double __u;	1600	double __u;
1601	} __attribute__((__packed__, __may_alias__));	1601	} __attribute__((__packed__, __may_alias__));
1602	double __u = ((struct __mm_load1_pd_struct*)__dp)->__u;	1602	double __u = ((const struct __mm_load1_pd_struct*)__dp)->__u;
1603	return __extension__ (__m128d){ __u, __u };	1603	return __extension__ (__m128d){ __u, __u };
1604	}	1604	}
1605		1605
...	@@ -1622,7 +1622,7 @@ _mm_load1_pd(double const *__dp)	...	@@ -1622,7 +1622,7 @@ _mm_load1_pd(double const *__dp)
1622	static __inline__ __m128d __DEFAULT_FN_ATTRS	1622	static __inline__ __m128d __DEFAULT_FN_ATTRS
1623	_mm_loadr_pd(double const *__dp)	1623	_mm_loadr_pd(double const *__dp)
1624	{	1624	{
1625	__m128d __u = (__m128d)__dp;	1625	__m128d __u = (const __m128d)__dp;
1626	return __builtin_shufflevector((__v2df)__u, (__v2df)__u, 1, 0);	1626	return __builtin_shufflevector((__v2df)__u, (__v2df)__u, 1, 0);
1627	}	1627	}
1628		1628
...	@@ -1643,7 +1643,7 @@ _mm_loadu_pd(double const *__dp)	...	@@ -1643,7 +1643,7 @@ _mm_loadu_pd(double const *__dp)
1643	struct __loadu_pd {	1643	struct __loadu_pd {
1644	__m128d_u __v;	1644	__m128d_u __v;
1645	} __attribute__((__packed__, __may_alias__));	1645	} __attribute__((__packed__, __may_alias__));
1646	return ((struct __loadu_pd*)__dp)->__v;	1646	return ((const struct __loadu_pd*)__dp)->__v;
1647	}	1647	}
1648		1648
1649	/// Loads a 64-bit integer value to the low element of a 128-bit integer	1649	/// Loads a 64-bit integer value to the low element of a 128-bit integer
...	@@ -1663,7 +1663,7 @@ _mm_loadu_si64(void const *__a)	...	@@ -1663,7 +1663,7 @@ _mm_loadu_si64(void const *__a)
1663	struct __loadu_si64 {	1663	struct __loadu_si64 {
1664	long long __v;	1664	long long __v;
1665	} __attribute__((__packed__, __may_alias__));	1665	} __attribute__((__packed__, __may_alias__));
1666	long long __u = ((struct __loadu_si64*)__a)->__v;	1666	long long __u = ((const struct __loadu_si64*)__a)->__v;
1667	return __extension__ (__m128i)(__v2di){__u, 0LL};	1667	return __extension__ (__m128i)(__v2di){__u, 0LL};
1668	}	1668	}
1669		1669
...	@@ -1684,7 +1684,7 @@ _mm_loadu_si32(void const *__a)	...	@@ -1684,7 +1684,7 @@ _mm_loadu_si32(void const *__a)
1684	struct __loadu_si32 {	1684	struct __loadu_si32 {
1685	int __v;	1685	int __v;
1686	} __attribute__((__packed__, __may_alias__));	1686	} __attribute__((__packed__, __may_alias__));
1687	int __u = ((struct __loadu_si32*)__a)->__v;	1687	int __u = ((const struct __loadu_si32*)__a)->__v;
1688	return __extension__ (__m128i)(__v4si){__u, 0, 0, 0};	1688	return __extension__ (__m128i)(__v4si){__u, 0, 0, 0};
1689	}	1689	}
1690		1690
...	@@ -1705,7 +1705,7 @@ _mm_loadu_si16(void const *__a)	...	@@ -1705,7 +1705,7 @@ _mm_loadu_si16(void const *__a)
1705	struct __loadu_si16 {	1705	struct __loadu_si16 {
1706	short __v;	1706	short __v;
1707	} __attribute__((__packed__, __may_alias__));	1707	} __attribute__((__packed__, __may_alias__));
1708	short __u = ((struct __loadu_si16*)__a)->__v;	1708	short __u = ((const struct __loadu_si16*)__a)->__v;
1709	return __extension__ (__m128i)(__v8hi){__u, 0, 0, 0, 0, 0, 0, 0};	1709	return __extension__ (__m128i)(__v8hi){__u, 0, 0, 0, 0, 0, 0, 0};
1710	}	1710	}
1711		1711
...	@@ -1726,7 +1726,7 @@ _mm_load_sd(double const *__dp)	...	@@ -1726,7 +1726,7 @@ _mm_load_sd(double const *__dp)
1726	struct __mm_load_sd_struct {	1726	struct __mm_load_sd_struct {
1727	double __u;	1727	double __u;
1728	} __attribute__((__packed__, __may_alias__));	1728	} __attribute__((__packed__, __may_alias__));
1729	double __u = ((struct __mm_load_sd_struct*)__dp)->__u;	1729	double __u = ((const struct __mm_load_sd_struct*)__dp)->__u;
1730	return __extension__ (__m128d){ __u, 0 };	1730	return __extension__ (__m128d){ __u, 0 };
1731	}	1731	}
1732		1732
...	@@ -1753,7 +1753,7 @@ _mm_loadh_pd(__m128d __a, double const *__dp)	...	@@ -1753,7 +1753,7 @@ _mm_loadh_pd(__m128d __a, double const *__dp)
1753	struct __mm_loadh_pd_struct {	1753	struct __mm_loadh_pd_struct {
1754	double __u;	1754	double __u;
1755	} __attribute__((__packed__, __may_alias__));	1755	} __attribute__((__packed__, __may_alias__));
1756	double __u = ((struct __mm_loadh_pd_struct*)__dp)->__u;	1756	double __u = ((const struct __mm_loadh_pd_struct*)__dp)->__u;
1757	return __extension__ (__m128d){ __a[0], __u };	1757	return __extension__ (__m128d){ __a[0], __u };
1758	}	1758	}
1759		1759
...	@@ -1780,7 +1780,7 @@ _mm_loadl_pd(__m128d __a, double const *__dp)	...	@@ -1780,7 +1780,7 @@ _mm_loadl_pd(__m128d __a, double const *__dp)
1780	struct __mm_loadl_pd_struct {	1780	struct __mm_loadl_pd_struct {
1781	double __u;	1781	double __u;
1782	} __attribute__((__packed__, __may_alias__));	1782	} __attribute__((__packed__, __may_alias__));
1783	double __u = ((struct __mm_loadl_pd_struct*)__dp)->__u;	1783	double __u = ((const struct __mm_loadl_pd_struct*)__dp)->__u;
1784	return __extension__ (__m128d){ __u, __a[1] };	1784	return __extension__ (__m128d){ __u, __a[1] };
1785	}	1785	}
1786		1786
...	@@ -2288,7 +2288,7 @@ _mm_adds_epu16(__m128i __a, __m128i __b)	...	@@ -2288,7 +2288,7 @@ _mm_adds_epu16(__m128i __a, __m128i __b)
2288	return (__m128i)__builtin_ia32_paddusw128((__v8hi)__a, (__v8hi)__b);	2288	return (__m128i)__builtin_ia32_paddusw128((__v8hi)__a, (__v8hi)__b);
2289	}	2289	}
2290		2290
2291	/// Computes the rounded avarages of corresponding elements of two	2291	/// Computes the rounded averages of corresponding elements of two
2292	/// 128-bit unsigned [16 x i8] vectors, saving each result in the	2292	/// 128-bit unsigned [16 x i8] vectors, saving each result in the
2293	/// corresponding element of a 128-bit result vector of [16 x i8].	2293	/// corresponding element of a 128-bit result vector of [16 x i8].
2294	///	2294	///
...	@@ -2308,7 +2308,7 @@ _mm_avg_epu8(__m128i __a, __m128i __b)	...	@@ -2308,7 +2308,7 @@ _mm_avg_epu8(__m128i __a, __m128i __b)
2308	return (__m128i)__builtin_ia32_pavgb128((__v16qi)__a, (__v16qi)__b);	2308	return (__m128i)__builtin_ia32_pavgb128((__v16qi)__a, (__v16qi)__b);
2309	}	2309	}
2310		2310
2311	/// Computes the rounded avarages of corresponding elements of two	2311	/// Computes the rounded averages of corresponding elements of two
2312	/// 128-bit unsigned [8 x i16] vectors, saving each result in the	2312	/// 128-bit unsigned [8 x i16] vectors, saving each result in the
2313	/// corresponding element of a 128-bit result vector of [8 x i16].	2313	/// corresponding element of a 128-bit result vector of [8 x i16].
2314	///	2314	///
...	@@ -3550,7 +3550,7 @@ _mm_loadu_si128(__m128i_u const *__p)	...	@@ -3550,7 +3550,7 @@ _mm_loadu_si128(__m128i_u const *__p)
3550	struct __loadu_si128 {	3550	struct __loadu_si128 {
3551	__m128i_u __v;	3551	__m128i_u __v;
3552	} __attribute__((__packed__, __may_alias__));	3552	} __attribute__((__packed__, __may_alias__));
3553	return ((struct __loadu_si128*)__p)->__v;	3553	return ((const struct __loadu_si128*)__p)->__v;
3554	}	3554	}
3555		3555
3556	/// Returns a vector of [2 x i64] where the lower element is taken from	3556	/// Returns a vector of [2 x i64] where the lower element is taken from
...	@@ -3571,7 +3571,7 @@ _mm_loadl_epi64(__m128i_u const *__p)	...	@@ -3571,7 +3571,7 @@ _mm_loadl_epi64(__m128i_u const *__p)
3571	struct __mm_loadl_epi64_struct {	3571	struct __mm_loadl_epi64_struct {
3572	long long __u;	3572	long long __u;
3573	} __attribute__((__packed__, __may_alias__));	3573	} __attribute__((__packed__, __may_alias__));
3574	return __extension__ (__m128i) { ((struct __mm_loadl_epi64_struct*)__p)->__u, 0};	3574	return __extension__ (__m128i) { ((const struct __mm_loadl_epi64_struct*)__p)->__u, 0};
3575	}	3575	}
3576		3576
3577	/// Generates a 128-bit vector of [4 x i32] with unspecified content.	3577	/// Generates a 128-bit vector of [4 x i32] with unspecified content.