authorgravatar for sahnvour@pm.meSahnvour <sahnvour@pm.me> 2019-06-27 23:21:35+02:00
committergravatar for sahnvour@pm.meSahnvour <sahnvour@pm.me> 2019-08-04 12:34:02+02:00
log6150da3df99b41f89ea01a72e6c1b76fe4c36f89
tree97afaec2d54b88e4acbd2460191b636d6355f9e3
parent5687323cd2a759dfdf9533e46e3de8cddb1b55b7

direct port of wyhash v2

also inspired by https://github.com/ManDeJan/zig-wyhash

2 files changed, 103 insertions(+), 0 deletions(-)

std/hash.zig+4
......@@ -16,6 +16,7 @@ pub const SipHash128 = siphash.SipHash128;
1616
1717pub const murmur = @import("hash/murmur.zig");
1818pub const Murmur2_32 = murmur.Murmur2_32;
19
1920pub const Murmur2_64 = murmur.Murmur2_64;
2021pub const Murmur3_32 = murmur.Murmur3_32;
2122
......@@ -23,6 +24,8 @@ pub const cityhash = @import("hash/cityhash.zig");
2324pub const CityHash32 = cityhash.CityHash32;
2425pub const CityHash64 = cityhash.CityHash64;
2526
27pub const wyhash = @import("hash/wyhash.zig").hash;
28
2629test "hash" {
2730 _ = @import("hash/adler.zig");
2831 _ = @import("hash/crc.zig");
......@@ -30,4 +33,5 @@ test "hash" {
3033 _ = @import("hash/siphash.zig");
3134 _ = @import("hash/murmur.zig");
3235 _ = @import("hash/cityhash.zig");
36 _ = @import("hash/wyhash.zig");
3337}
std/hash/wyhash.zig created+99
......@@ -0,0 +1,99 @@
1const std = @import("std");
2const mem = std.mem;
3
4const primes = [_]u64{
5 0xa0761d6478bd642f,
6 0xe7037ed1a0b428db,
7 0x8ebc6af09c88c6e3,
8 0x589965cc75374cc3,
9 0x1d8e4e27c47d124f,
10};
11
12fn read_bytes(comptime bytes: u8, data: []const u8) u64 {
13 return mem.readVarInt(u64, data[0..bytes], @import("builtin").endian);
14}
15
16fn read_8bytes_swapped(data: []const u8) u64 {
17 return (read_bytes(4, data) << 32 | read_bytes(4, data[4..]));
18}
19
20fn mum(a: u64, b: u64) u64 {
21 var r: u128 = @intCast(u128, a) * @intCast(u128, b);
22 r = (r >> 64) ^ r;
23 return @truncate(u64, r);
24}
25
26fn mix0(a: u64, b: u64, seed: u64) u64 {
27 return mum(a ^ seed ^ primes[0], b ^ seed ^ primes[1]);
28}
29
30fn mix1(a: u64, b: u64, seed: u64) u64 {
31 return mum(a ^ seed ^ primes[2], b ^ seed ^ primes[3]);
32}
33
34pub fn hash(key: []const u8, initial_seed: u64) u64 {
35 var seed = initial_seed;
36
37 var i: usize = 0;
38 while (i + 32 <= key.len) : (i += 32) {
39 seed = mix0(
40 read_bytes(8, key[i..]),
41 read_bytes(8, key[i + 8 ..]),
42 seed,
43 ) ^ mix1(
44 read_bytes(8, key[i + 16 ..]),
45 read_bytes(8, key[i + 24 ..]),
46 seed,
47 );
48 }
49
50 const rem_len = @truncate(u5, key.len);
51 const rem_key = key[i..];
52 seed = switch (rem_len) {
53 0 => seed,
54 1 => mix0(read_bytes(1, rem_key), primes[4], seed),
55 2 => mix0(read_bytes(2, rem_key), primes[4], seed),
56 3 => mix0((read_bytes(2, rem_key) << 8) | read_bytes(1, rem_key[2..]), primes[4], seed),
57 4 => mix0(read_bytes(4, rem_key), primes[4], seed),
58 5 => mix0((read_bytes(4, rem_key) << 8) | read_bytes(1, rem_key[4..]), primes[4], seed),
59 6 => mix0((read_bytes(4, rem_key) << 16) | read_bytes(2, rem_key[4..]), primes[4], seed),
60 7 => mix0((read_bytes(4, rem_key) << 24) | (read_bytes(2, rem_key[4..]) << 8) | read_bytes(1, rem_key[6..]), primes[4], seed),
61 8 => mix0(read_8bytes_swapped(rem_key), primes[4], seed),
62 9 => mix0(read_8bytes_swapped(rem_key), read_bytes(1, rem_key[8..]), seed),
63 10 => mix0(read_8bytes_swapped(rem_key), read_bytes(2, rem_key[8..]), seed),
64 11 => mix0(read_8bytes_swapped(rem_key), (read_bytes(2, rem_key[8..]) << 8) | read_bytes(1, rem_key[10..]), seed),
65 12 => mix0(read_8bytes_swapped(rem_key), read_bytes(4, rem_key[8..]), seed),
66 13 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 8) | read_bytes(1, rem_key[12..]), seed),
67 14 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 16) | read_bytes(2, rem_key[12..]), seed),
68 15 => mix0(read_8bytes_swapped(rem_key), (read_bytes(4, rem_key[8..]) << 24) | (read_bytes(2, rem_key[12..]) << 8) | read_bytes(1, rem_key[14..]), seed),
69 16 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed),
70 17 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(1, rem_key[16..]), primes[4], seed),
71 18 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(2, rem_key[16..]), primes[4], seed),
72 19 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(2, rem_key[16..]) << 8) | read_bytes(1, rem_key[18..]), primes[4], seed),
73 20 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_bytes(4, rem_key[16..]), primes[4], seed),
74 21 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 8) | read_bytes(1, rem_key[20..]), primes[4], seed),
75 22 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 16) | read_bytes(2, rem_key[20..]), primes[4], seed),
76 23 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1((read_bytes(4, rem_key[16..]) << 24) | (read_bytes(2, rem_key[20..]) << 8) | read_bytes(1, rem_key[22..]), primes[4], seed),
77 24 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), primes[4], seed),
78 25 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(1, rem_key[24..]), seed),
79 26 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(2, rem_key[24..]), seed),
80 27 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(2, rem_key[24..]) << 8) | read_bytes(1, rem_key[26..]), seed),
81 28 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), read_bytes(4, rem_key[24..]), seed),
82 29 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 8) | read_bytes(1, rem_key[28..]), seed),
83 30 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 16) | read_bytes(2, rem_key[28..]), seed),
84 31 => mix0(read_8bytes_swapped(rem_key), read_8bytes_swapped(rem_key[8..]), seed) ^ mix1(read_8bytes_swapped(rem_key[16..]), (read_bytes(4, rem_key[24..]) << 24) | (read_bytes(2, rem_key[28..]) << 8) | read_bytes(1, rem_key[30..]), seed),
85 };
86
87 return mum(seed ^ key.len, primes[4]);
88}
89
90test "test vectors" {
91 const expectEqual = std.testing.expectEqual;
92 expectEqual(hash("", 0), 0x0);
93 expectEqual(hash("a", 1), 0xbed235177f41d328);
94 expectEqual(hash("abc", 2), 0xbe348debe59b27c3);
95 expectEqual(hash("message digest", 3), 0x37320f657213a290);
96 expectEqual(hash("abcdefghijklmnopqrstuvwxyz", 4), 0xd0b270e1d8a7019c);
97 expectEqual(hash("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789", 5), 0x602a1894d3bbfe7f);
98 expectEqual(hash("12345678901234567890123456789012345678901234567890123456789012345678901234567890", 6), 0x829e9c148b75970e);
99}