cyclone/include/cyclone/ck_ht_hash.h
2017-01-11 22:17:26 -05:00

289 lines
6.5 KiB
C

/*
* Copyright 2012-2015 Samy Al Bahra
* Copyright 2011-2014 AppNexus, Inc.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#ifndef CK_HT_HASH_H
#define CK_HT_HASH_H
/*
* This is the Murmur hash written by Austin Appleby.
*/
#include <ck_stdint.h>
//-----------------------------------------------------------------------------
// MurmurHash3 was written by Austin Appleby, and is placed in the public
// domain. The author hereby disclaims copyright to this source code.
// Note - The x86 and x64 versions do _not_ produce the same results, as the
// algorithms are optimized for their respective platforms. You can still
// compile and run any of them on any platform, but your performance with the
// non-native version will be less than optimal.
//-----------------------------------------------------------------------------
// Platform-specific functions and macros
// Microsoft Visual Studio
#if defined(_MSC_VER)
#define FORCE_INLINE __forceinline
#include <stdlib.h>
#define ROTL32(x,y) _rotl(x,y)
#define ROTL64(x,y) _rotl64(x,y)
#define BIG_CONSTANT(x) (x)
// Other compilers
#else // defined(_MSC_VER)
#define FORCE_INLINE inline __attribute__((always_inline))
static inline uint32_t rotl32(uint32_t x, int8_t r)
{
return (x << r) | (x >> (32 - r));
}
static inline uint64_t rotl64(uint64_t x, int8_t r)
{
return (x << r) | (x >> (64 - r));
}
#define ROTL32(x,y) rotl32(x,y)
#define ROTL64(x,y) rotl64(x,y)
#define BIG_CONSTANT(x) (x##LLU)
#endif // !defined(_MSC_VER)
//-----------------------------------------------------------------------------
// Block read - if your platform needs to do endian-swapping or can only
// handle aligned reads, do the conversion here
FORCE_INLINE static uint32_t getblock(const uint32_t * p, int i)
{
return p[i];
}
//-----------------------------------------------------------------------------
// Finalization mix - force all bits of a hash block to avalanche
FORCE_INLINE static uint32_t fmix(uint32_t h)
{
h ^= h >> 16;
h *= 0x85ebca6b;
h ^= h >> 13;
h *= 0xc2b2ae35;
h ^= h >> 16;
return h;
}
//-----------------------------------------------------------------------------
static inline void MurmurHash3_x86_32(const void *key, int len,
uint32_t seed, uint32_t * out)
{
const uint8_t *data = (const uint8_t *)key;
const int nblocks = len / 4;
int i;
uint32_t h1 = seed;
uint32_t c1 = 0xcc9e2d51;
uint32_t c2 = 0x1b873593;
//----------
// body
const uint32_t *blocks = (const uint32_t *)(const void *)(data + nblocks * 4);
for (i = -nblocks; i; i++) {
uint32_t k1 = getblock(blocks, i);
k1 *= c1;
k1 = ROTL32(k1, 15);
k1 *= c2;
h1 ^= k1;
h1 = ROTL32(h1, 13);
h1 = h1 * 5 + 0xe6546b64;
}
//----------
// tail
const uint8_t *tail = (const uint8_t *)(data + nblocks * 4);
uint32_t k1 = 0;
switch (len & 3) {
case 3:
k1 ^= tail[2] << 16;
case 2:
k1 ^= tail[1] << 8;
case 1:
k1 ^= tail[0];
k1 *= c1;
k1 = ROTL32(k1, 15);
k1 *= c2;
h1 ^= k1;
};
//----------
// finalization
h1 ^= len;
h1 = fmix(h1);
*(uint32_t *) out = h1;
}
static inline uint64_t MurmurHash64A(const void *key, int len, uint64_t seed)
{
const uint64_t m = BIG_CONSTANT(0xc6a4a7935bd1e995);
const int r = 47;
uint64_t h = seed ^ (len * m);
const uint64_t *data = (const uint64_t *)key;
const uint64_t *end = data + (len / 8);
while (data != end) {
uint64_t k;
if (!((uintptr_t) data & 0x7))
k = *data++;
else {
memcpy(&k, data, sizeof(k));
data++;
}
k *= m;
k ^= k >> r;
k *= m;
h ^= k;
h *= m;
}
const unsigned char *data2 = (const unsigned char *)data;
switch (len & 7) {
case 7:
h ^= (uint64_t) (data2[6]) << 48;
case 6:
h ^= (uint64_t) (data2[5]) << 40;
case 5:
h ^= (uint64_t) (data2[4]) << 32;
case 4:
h ^= (uint64_t) (data2[3]) << 24;
case 3:
h ^= (uint64_t) (data2[2]) << 16;
case 2:
h ^= (uint64_t) (data2[1]) << 8;
case 1:
h ^= (uint64_t) (data2[0]);
h *= m;
};
h ^= h >> r;
h *= m;
h ^= h >> r;
return h;
}
// 64-bit hash for 32-bit platforms
static inline uint64_t MurmurHash64B(const void *key, int len, uint64_t seed)
{
const uint32_t m = 0x5bd1e995;
const int r = 24;
uint32_t h1 = (uint32_t) (seed) ^ len;
uint32_t h2 = (uint32_t) (seed >> 32);
const uint32_t *data = (const uint32_t *)key;
while (len >= 8) {
uint32_t k1 = *data++;
k1 *= m;
k1 ^= k1 >> r;
k1 *= m;
h1 *= m;
h1 ^= k1;
len -= 4;
uint32_t k2 = *data++;
k2 *= m;
k2 ^= k2 >> r;
k2 *= m;
h2 *= m;
h2 ^= k2;
len -= 4;
}
if (len >= 4) {
uint32_t k1 = *data++;
k1 *= m;
k1 ^= k1 >> r;
k1 *= m;
h1 *= m;
h1 ^= k1;
len -= 4;
}
switch (len) {
case 3:
h2 ^= ((const unsigned char *)data)[2] << 16;
case 2:
h2 ^= ((const unsigned char *)data)[1] << 8;
case 1:
h2 ^= ((const unsigned char *)data)[0];
h2 *= m;
};
h1 ^= h2 >> 18;
h1 *= m;
h2 ^= h1 >> 22;
h2 *= m;
h1 ^= h2 >> 17;
h1 *= m;
h2 ^= h1 >> 19;
h2 *= m;
uint64_t h = h1;
h = (h << 32) | h2;
return h;
}
#endif /* CK_HT_HASH_H */