lib/include/__clang_cuda_device_functions.h | 4 +- lib/include/__clang_cuda_libdevice_declares.h | 4 +- lib/include/__clang_cuda_math.h | 6 +- lib/include/__clang_cuda_runtime_wrapper.h | 4 +- lib/include/__clang_hip_math.h | 363 +- lib/include/__clang_hip_runtime_wrapper.h | 60 +- lib/include/__stdarg___gnuc_va_list.h | 13 + lib/include/__stdarg___va_copy.h | 12 + lib/include/__stdarg_va_arg.h | 22 + lib/include/__stdarg_va_copy.h | 12 + lib/include/__stdarg_va_list.h | 13 + lib/include/__stddef_max_align_t.h | 2 +- lib/include/__stddef_null.h | 29 + lib/include/__stddef_nullptr_t.h | 29 + lib/include/__stddef_offsetof.h | 17 + lib/include/__stddef_ptrdiff_t.h | 20 + lib/include/__stddef_rsize_t.h | 20 + lib/include/__stddef_size_t.h | 20 + lib/include/__stddef_unreachable.h | 21 + lib/include/__stddef_wchar_t.h | 28 + lib/include/__stddef_wint_t.h | 15 + lib/include/adcintrin.h | 160 + lib/include/adxintrin.h | 143 +- lib/include/altivec.h | 43 +- lib/include/ammintrin.h | 8 +- lib/include/arm_acle.h | 142 +- lib/include/arm_neon.h | 412 +- lib/include/arm_sme.h | 2412 ++++++++++ lib/include/arm_sme_draft_spec_subject_to_change.h | 642 --- lib/include/arm_sve.h | 7737 ++++++++++++++++++++++++++++++-- lib/include/arm_vector_types.h | 345 ++ lib/include/avx2intrin.h | 27 +- lib/include/avx512bf16intrin.h | 5 +- lib/include/avx512bitalgintrin.h | 5 +- lib/include/avx512bwintrin.h | 66 +- lib/include/avx512cdintrin.h | 4 +- lib/include/avx512dqintrin.h | 6 +- lib/include/avx512fintrin.h | 10 +- lib/include/avx512fp16intrin.h | 10 +- lib/include/avx512ifmaintrin.h | 4 +- lib/include/avx512ifmavlintrin.h | 10 +- lib/include/avx512pfintrin.h | 5 - lib/include/avx512vbmi2intrin.h | 2 +- lib/include/avx512vbmiintrin.h | 5 +- lib/include/avx512vbmivlintrin.h | 11 +- lib/include/avx512vlbf16intrin.h | 14 +- lib/include/avx512vlbitalgintrin.h | 10 +- lib/include/avx512vlbwintrin.h | 10 +- lib/include/avx512vlcdintrin.h | 11 +- lib/include/avx512vldqintrin.h | 10 +- lib/include/avx512vlfp16intrin.h | 4 +- lib/include/avx512vlintrin.h | 10 +- lib/include/avx512vlvbmi2intrin.h | 10 +- lib/include/avx512vlvnniintrin.h | 10 +- lib/include/avx512vlvp2intersectintrin.h | 10 +- lib/include/avx512vnniintrin.h | 5 +- lib/include/avx512vp2intersectintrin.h | 5 +- lib/include/avx512vpopcntdqintrin.h | 4 +- lib/include/avx512vpopcntdqvlintrin.h | 8 +- lib/include/avxintrin.h | 14 +- lib/include/bmiintrin.h | 277 +- lib/include/cuda_wrappers/bits/basic_string.h | 9 + lib/include/cuda_wrappers/bits/basic_string.tcc | 9 + lib/include/emmintrin.h | 20 +- lib/include/gfniintrin.h | 29 +- lib/include/ia32intrin.h | 818 +++- lib/include/immintrin.h | 69 +- lib/include/intrin.h | 16 + lib/include/larchintrin.h | 14 +- lib/include/lasxintrin.h | 3884 ++++++++++++++++ lib/include/limits.h | 6 +- lib/include/llvm_libc_wrappers/assert.h | 34 + lib/include/llvm_libc_wrappers/ctype.h | 17 + lib/include/llvm_libc_wrappers/stdio.h | 52 +- lib/include/llvm_libc_wrappers/stdlib.h | 5 +- lib/include/llvm_libc_wrappers/string.h | 65 +- lib/include/llvm_libc_wrappers/time.h | 34 + lib/include/lsxintrin.h | 3750 ++++++++++++++++ lib/include/mmintrin.h | 12 +- lib/include/module.modulemap | 157 +- lib/include/opencl-c-base.h | 5 + lib/include/openmp_wrappers/cmath | 2 +- lib/include/pmmintrin.h | 5 +- lib/include/ppc_wrappers/nmmintrin.h | 26 + lib/include/ppc_wrappers/smmintrin.h | 50 +- lib/include/riscv_bitmanip.h | 195 + lib/include/riscv_crypto.h | 170 + lib/include/riscv_ntlh.h | 8 +- lib/include/riscv_vector.h | 31 + lib/include/smmintrin.h | 6 +- lib/include/stdalign.h | 4 +- lib/include/stdarg.h | 90 +- lib/include/stdatomic.h | 8 +- lib/include/stdckdint.h | 42 + lib/include/stddef.h | 166 +- lib/include/stdint.h | 67 +- lib/include/stdnoreturn.h | 4 +- lib/include/tmmintrin.h | 9 +- lib/include/usermsrintrin.h | 51 + lib/include/vaesintrin.h | 6 +- lib/include/vecintrin.h | 416 +- lib/include/x86gprintrin.h | 5 + lib/include/xmmintrin.h | 14 +- 103 files changed, 21212 insertions(+), 2508 deletions(-)