runtime: move hash functions to newly created subproject
to reuse in compiler
This commit is contained in:
Svyatoslav Scherbina
@@ -0,0 +1,16 @@
|
||||
import org.jetbrains.kotlin.CompileCppToBitcode
|
||||
|
||||
// TODO: consider using some Gradle plugins to build and test
|
||||
|
||||
|
||||
task compileHash(type: CompileCppToBitcode) {
|
||||
name 'hash'
|
||||
}
|
||||
|
||||
task build {
|
||||
dependsOn compileHash
|
||||
}
|
||||
|
||||
task clean << {
|
||||
delete buildDir
|
||||
}
|
||||
@@ -0,0 +1,218 @@
|
||||
#include "City.h"
|
||||
|
||||
#include <string.h>
|
||||
|
||||
#include <algorithm>
|
||||
|
||||
namespace {
|
||||
|
||||
// Some primes between 2^63 and 2^64 for various uses.
|
||||
static const uint64_t k0 = 0xc3a5c85c97cb3127ULL;
|
||||
static const uint64_t k1 = 0xb492b66fbe98f273ULL;
|
||||
static const uint64_t k2 = 0x9ae16a3b2f90404fULL;
|
||||
|
||||
// Magic numbers for 32-bit hashing. Copied from Murmur3.
|
||||
static const uint32_t c1 = 0xcc9e2d51;
|
||||
static const uint32_t c2 = 0x1b873593;
|
||||
|
||||
uint64_t UNALIGNED_LOAD64(const char *p) {
|
||||
uint64_t result;
|
||||
memcpy(&result, p, sizeof(result));
|
||||
return result;
|
||||
}
|
||||
|
||||
uint32_t UNALIGNED_LOAD32(const char *p) {
|
||||
uint32_t result;
|
||||
memcpy(&result, p, sizeof(result));
|
||||
return result;
|
||||
}
|
||||
|
||||
#define bswap32(x) __builtin_bswap32(x)
|
||||
#define bswap64(x) __builtin_bswap64(x)
|
||||
|
||||
#ifdef WORDS_BIGENDIAN
|
||||
#define uint32_in_expected_order(x) (bswap32(x))
|
||||
#define uint64_in_expected_order(x) (bswap64(x))
|
||||
#else
|
||||
#define uint32_in_expected_order(x) (x)
|
||||
#define uint64_in_expected_order(x) (x)
|
||||
#endif
|
||||
|
||||
uint64_t Fetch64(const char *p) {
|
||||
return uint64_in_expected_order(UNALIGNED_LOAD64(p));
|
||||
}
|
||||
|
||||
uint32_t Fetch32(const char *p) {
|
||||
return uint32_in_expected_order(UNALIGNED_LOAD32(p));
|
||||
}
|
||||
|
||||
uint32_t Rotate32(uint32_t val, int shift) {
|
||||
// Avoid shifting by 32: doing so yields an undefined result.
|
||||
return shift == 0 ? val : ((val >> shift) | (val << (32 - shift)));
|
||||
}
|
||||
|
||||
// Bitwise right rotate. Normally this will compile to a single
|
||||
// instruction, especially if the shift is a manifest constant.
|
||||
uint64_t Rotate(uint64_t val, int shift) {
|
||||
// Avoid shifting by 64: doing so yields an undefined result.
|
||||
return shift == 0 ? val : ((val >> shift) | (val << (64 - shift)));
|
||||
}
|
||||
|
||||
uint64_t ShiftMix(uint64_t val) {
|
||||
return val ^ (val >> 47);
|
||||
}
|
||||
|
||||
uint64_t HashLen16(uint64_t u, uint64_t v, uint64_t mul) {
|
||||
// Murmur-inspired hashing.
|
||||
uint64_t a = (u ^ v) * mul;
|
||||
a ^= (a >> 47);
|
||||
uint64_t b = (v ^ a) * mul;
|
||||
b ^= (b >> 47);
|
||||
b *= mul;
|
||||
return b;
|
||||
}
|
||||
|
||||
typedef std::pair<uint64_t, uint64_t> uint128_t;
|
||||
|
||||
uint64_t Hash128to64(const uint128_t& x) {
|
||||
// Murmur-inspired hashing.
|
||||
const uint64_t kMul = 0x9ddfea08eb382d69ULL;
|
||||
uint64_t a = (x.first ^ x.second) * kMul;
|
||||
a ^= (a >> 47);
|
||||
uint64_t b = (x.second ^ a) * kMul;
|
||||
b ^= (b >> 47);
|
||||
b *= kMul;
|
||||
return b;
|
||||
}
|
||||
|
||||
uint64_t HashLen16(uint64_t u, uint64_t v) {
|
||||
return Hash128to64(uint128_t(u, v));
|
||||
}
|
||||
|
||||
uint64_t HashLen0to16(const char *s, size_t len) {
|
||||
if (len >= 8) {
|
||||
uint64_t mul = k2 + len * 2;
|
||||
uint64_t a = Fetch64(s) + k2;
|
||||
uint64_t b = Fetch64(s + len - 8);
|
||||
uint64_t c = Rotate(b, 37) * mul + a;
|
||||
uint64_t d = (Rotate(a, 25) + b) * mul;
|
||||
return HashLen16(c, d, mul);
|
||||
}
|
||||
if (len >= 4) {
|
||||
uint64_t mul = k2 + len * 2;
|
||||
uint64_t a = Fetch32(s);
|
||||
return HashLen16(len + (a << 3), Fetch32(s + len - 4), mul);
|
||||
}
|
||||
if (len > 0) {
|
||||
uint8_t a = s[0];
|
||||
uint8_t b = s[len >> 1];
|
||||
uint8_t c = s[len - 1];
|
||||
uint32_t y = static_cast<uint32_t>(a) + (static_cast<uint32_t>(b) << 8);
|
||||
uint32_t z = len + (static_cast<uint32_t>(c) << 2);
|
||||
return ShiftMix(y * k2 ^ z * k0) * k2;
|
||||
}
|
||||
return k2;
|
||||
}
|
||||
|
||||
// This probably works well for 16-byte strings as well, but it may be overkill
|
||||
// in that case.
|
||||
static uint64_t HashLen17to32(const char *s, size_t len) {
|
||||
uint64_t mul = k2 + len * 2;
|
||||
uint64_t a = Fetch64(s) * k1;
|
||||
uint64_t b = Fetch64(s + 8);
|
||||
uint64_t c = Fetch64(s + len - 8) * mul;
|
||||
uint64_t d = Fetch64(s + len - 16) * k2;
|
||||
return HashLen16(Rotate(a + b, 43) + Rotate(c, 30) + d,
|
||||
a + Rotate(b + k2, 18) + c, mul);
|
||||
}
|
||||
|
||||
// Return a 16-byte hash for 48 bytes. Quick and dirty.
|
||||
// Callers do best to use "random-looking" values for a and b.
|
||||
std::pair<uint64_t, uint64_t> WeakHashLen32WithSeeds(
|
||||
uint64_t w, uint64_t x, uint64_t y, uint64_t z, uint64_t a, uint64_t b) {
|
||||
a += w;
|
||||
b = Rotate(b + a + z, 21);
|
||||
uint64_t c = a;
|
||||
a += x;
|
||||
a += y;
|
||||
b += Rotate(a, 44);
|
||||
return std::make_pair(a + z, b + c);
|
||||
}
|
||||
|
||||
// Return a 16-byte hash for s[0] ... s[31], a, and b. Quick and dirty.
|
||||
std::pair<uint64_t, uint64_t> WeakHashLen32WithSeeds(
|
||||
const char* s, uint64_t a, uint64_t b) {
|
||||
return WeakHashLen32WithSeeds(Fetch64(s),
|
||||
Fetch64(s + 8),
|
||||
Fetch64(s + 16),
|
||||
Fetch64(s + 24),
|
||||
a,
|
||||
b);
|
||||
}
|
||||
|
||||
// Return an 8-byte hash for 33 to 64 bytes.
|
||||
uint64_t HashLen33to64(const char *s, size_t len) {
|
||||
uint64_t mul = k2 + len * 2;
|
||||
uint64_t a = Fetch64(s) * k2;
|
||||
uint64_t b = Fetch64(s + 8);
|
||||
uint64_t c = Fetch64(s + len - 24);
|
||||
uint64_t d = Fetch64(s + len - 32);
|
||||
uint64_t e = Fetch64(s + 16) * k2;
|
||||
uint64_t f = Fetch64(s + 24) * 9;
|
||||
uint64_t g = Fetch64(s + len - 8);
|
||||
uint64_t h = Fetch64(s + len - 16) * mul;
|
||||
uint64_t u = Rotate(a + g, 43) + (Rotate(b, 30) + c) * 9;
|
||||
uint64_t v = ((a + g) ^ d) + f + 1;
|
||||
uint64_t w = bswap64((u + v) * mul) + h;
|
||||
uint64_t x = Rotate(e + f, 42) + c;
|
||||
uint64_t y = (bswap64((v + w) * mul) + g) * mul;
|
||||
uint64_t z = e + f + c;
|
||||
a = bswap64((x + z) * mul + y) + b;
|
||||
b = ShiftMix((z + a) * mul + d + h) * mul;
|
||||
return b + x;
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
extern "C" {
|
||||
|
||||
uint64_t CityHash64(const void* data, size_t len) {
|
||||
const char* s = reinterpret_cast<const char*>(data);
|
||||
if (len <= 32) {
|
||||
if (len <= 16) {
|
||||
return HashLen0to16(s, len);
|
||||
} else {
|
||||
return HashLen17to32(s, len);
|
||||
}
|
||||
} else if (len <= 64) {
|
||||
return HashLen33to64(s, len);
|
||||
}
|
||||
|
||||
// For strings over 64 bytes we hash the end first, and then as we
|
||||
// loop we keep 56 bytes of state: v, w, x, y, and z.
|
||||
uint64_t x = Fetch64(s + len - 40);
|
||||
uint64_t y = Fetch64(s + len - 16) + Fetch64(s + len - 56);
|
||||
uint64_t z = HashLen16(Fetch64(s + len - 48) + len, Fetch64(s + len - 24));
|
||||
std::pair<uint64_t, uint64_t> v = WeakHashLen32WithSeeds(s + len - 64, len, z);
|
||||
std::pair<uint64_t, uint64_t> w = WeakHashLen32WithSeeds(s + len - 32, y + k1, x);
|
||||
x = x * k1 + Fetch64(s);
|
||||
|
||||
// Decrease len to the nearest multiple of 64, and operate on 64-byte chunks.
|
||||
len = (len - 1) & ~static_cast<size_t>(63);
|
||||
do {
|
||||
x = Rotate(x + y + v.first + Fetch64(s + 8), 37) * k1;
|
||||
y = Rotate(y + v.second + Fetch64(s + 48), 42) * k1;
|
||||
x ^= w.second;
|
||||
y += v.first + Fetch64(s + 40);
|
||||
z = Rotate(z + w.first, 33) * k1;
|
||||
v = WeakHashLen32WithSeeds(s, v.second * k1, x + w.first);
|
||||
w = WeakHashLen32WithSeeds(s + 32, z + w.second, y + Fetch64(s + 16));
|
||||
std::swap(z, x);
|
||||
s += 64;
|
||||
len -= 64;
|
||||
} while (len != 0);
|
||||
return HashLen16(HashLen16(v.first, w.first) + ShiftMix(y) * k1 + z,
|
||||
HashLen16(v.second, w.second) + x);
|
||||
}
|
||||
|
||||
} // extern "C"
|
||||
@@ -0,0 +1,175 @@
|
||||
/*
|
||||
SHA-1 in C
|
||||
By Steve Reid <steve@edmweb.com>
|
||||
100% Public Domain
|
||||
|
||||
Test Vectors (from FIPS PUB 180-1)
|
||||
"abc"
|
||||
A9993E36 4706816A BA3E2571 7850C26C 9CD0D89D
|
||||
"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"
|
||||
84983E44 1C3BD26E BAAE4AA1 F95129E5 E54670F1
|
||||
A million repetitions of "a"
|
||||
34AA973C D4C4DAA4 F61EEB2B DBAD2731 6534016F
|
||||
*/
|
||||
|
||||
/* #define LITTLE_ENDIAN * This should be #define'd already, if true. */
|
||||
/* #define SHA1HANDSOFF * Copies data before messing with it. */
|
||||
|
||||
#define SHA1HANDSOFF
|
||||
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#include "Sha1.h"
|
||||
|
||||
#define rol(value, bits) (((value) << (bits)) | ((value) >> (32 - (bits))))
|
||||
|
||||
/* blk0() and blk() perform the initial expand. */
|
||||
/* I got the idea of expanding during the round function from SSLeay */
|
||||
#if BYTE_ORDER == LITTLE_ENDIAN
|
||||
#define blk0(i) (block->l[i] = (rol(block->l[i],24)&0xFF00FF00) \
|
||||
|(rol(block->l[i],8)&0x00FF00FF))
|
||||
#elif BYTE_ORDER == BIG_ENDIAN
|
||||
#define blk0(i) block->l[i]
|
||||
#else
|
||||
#error "Endianness not defined!"
|
||||
#endif
|
||||
#define blk(i) (block->l[i&15] = rol(block->l[(i+13)&15]^block->l[(i+8)&15] \
|
||||
^block->l[(i+2)&15]^block->l[i&15],1))
|
||||
|
||||
/* (R0+R1), R2, R3, R4 are the different operations used in SHA1 */
|
||||
#define R0(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk0(i)+0x5A827999+rol(v,5);w=rol(w,30);
|
||||
#define R1(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk(i)+0x5A827999+rol(v,5);w=rol(w,30);
|
||||
#define R2(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0x6ED9EBA1+rol(v,5);w=rol(w,30);
|
||||
#define R3(v,w,x,y,z,i) z+=(((w|x)&y)|(w&x))+blk(i)+0x8F1BBCDC+rol(v,5);w=rol(w,30);
|
||||
#define R4(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0xCA62C1D6+rol(v,5);w=rol(w,30);
|
||||
|
||||
/* Hash a single 512-bit block. This is the core of the algorithm. */
|
||||
static void SHA1Transform(uint32_t state[5], const unsigned char buffer[64])
|
||||
{
|
||||
uint32_t a, b, c, d, e;
|
||||
typedef union {
|
||||
unsigned char c[64];
|
||||
uint32_t l[16];
|
||||
} CHAR64LONG16;
|
||||
#ifdef SHA1HANDSOFF
|
||||
CHAR64LONG16 block[1]; /* use array to appear as a pointer */
|
||||
memcpy(block, buffer, 64);
|
||||
#else
|
||||
/* The following had better never be used because it causes the
|
||||
* pointer-to-const buffer to be cast into a pointer to non-const.
|
||||
* And the result is written through. I threw a "const" in, hoping
|
||||
* this will cause a diagnostic.
|
||||
*/
|
||||
CHAR64LONG16* block = (const CHAR64LONG16*)buffer;
|
||||
#endif
|
||||
/* Copy context->state[] to working vars */
|
||||
a = state[0];
|
||||
b = state[1];
|
||||
c = state[2];
|
||||
d = state[3];
|
||||
e = state[4];
|
||||
/* 4 rounds of 20 operations each. Loop unrolled. */
|
||||
R0(a,b,c,d,e, 0); R0(e,a,b,c,d, 1); R0(d,e,a,b,c, 2); R0(c,d,e,a,b, 3);
|
||||
R0(b,c,d,e,a, 4); R0(a,b,c,d,e, 5); R0(e,a,b,c,d, 6); R0(d,e,a,b,c, 7);
|
||||
R0(c,d,e,a,b, 8); R0(b,c,d,e,a, 9); R0(a,b,c,d,e,10); R0(e,a,b,c,d,11);
|
||||
R0(d,e,a,b,c,12); R0(c,d,e,a,b,13); R0(b,c,d,e,a,14); R0(a,b,c,d,e,15);
|
||||
R1(e,a,b,c,d,16); R1(d,e,a,b,c,17); R1(c,d,e,a,b,18); R1(b,c,d,e,a,19);
|
||||
R2(a,b,c,d,e,20); R2(e,a,b,c,d,21); R2(d,e,a,b,c,22); R2(c,d,e,a,b,23);
|
||||
R2(b,c,d,e,a,24); R2(a,b,c,d,e,25); R2(e,a,b,c,d,26); R2(d,e,a,b,c,27);
|
||||
R2(c,d,e,a,b,28); R2(b,c,d,e,a,29); R2(a,b,c,d,e,30); R2(e,a,b,c,d,31);
|
||||
R2(d,e,a,b,c,32); R2(c,d,e,a,b,33); R2(b,c,d,e,a,34); R2(a,b,c,d,e,35);
|
||||
R2(e,a,b,c,d,36); R2(d,e,a,b,c,37); R2(c,d,e,a,b,38); R2(b,c,d,e,a,39);
|
||||
R3(a,b,c,d,e,40); R3(e,a,b,c,d,41); R3(d,e,a,b,c,42); R3(c,d,e,a,b,43);
|
||||
R3(b,c,d,e,a,44); R3(a,b,c,d,e,45); R3(e,a,b,c,d,46); R3(d,e,a,b,c,47);
|
||||
R3(c,d,e,a,b,48); R3(b,c,d,e,a,49); R3(a,b,c,d,e,50); R3(e,a,b,c,d,51);
|
||||
R3(d,e,a,b,c,52); R3(c,d,e,a,b,53); R3(b,c,d,e,a,54); R3(a,b,c,d,e,55);
|
||||
R3(e,a,b,c,d,56); R3(d,e,a,b,c,57); R3(c,d,e,a,b,58); R3(b,c,d,e,a,59);
|
||||
R4(a,b,c,d,e,60); R4(e,a,b,c,d,61); R4(d,e,a,b,c,62); R4(c,d,e,a,b,63);
|
||||
R4(b,c,d,e,a,64); R4(a,b,c,d,e,65); R4(e,a,b,c,d,66); R4(d,e,a,b,c,67);
|
||||
R4(c,d,e,a,b,68); R4(b,c,d,e,a,69); R4(a,b,c,d,e,70); R4(e,a,b,c,d,71);
|
||||
R4(d,e,a,b,c,72); R4(c,d,e,a,b,73); R4(b,c,d,e,a,74); R4(a,b,c,d,e,75);
|
||||
R4(e,a,b,c,d,76); R4(d,e,a,b,c,77); R4(c,d,e,a,b,78); R4(b,c,d,e,a,79);
|
||||
/* Add the working vars back into context.state[] */
|
||||
state[0] += a;
|
||||
state[1] += b;
|
||||
state[2] += c;
|
||||
state[3] += d;
|
||||
state[4] += e;
|
||||
/* Wipe variables */
|
||||
a = b = c = d = e = 0;
|
||||
#ifdef SHA1HANDSOFF
|
||||
memset(block, '\0', sizeof(block));
|
||||
#endif
|
||||
}
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* SHA1Init - Initialize new context */
|
||||
void SHA1Init(SHA1_CTX* context)
|
||||
{
|
||||
/* SHA1 initialization constants */
|
||||
context->state[0] = 0x67452301;
|
||||
context->state[1] = 0xEFCDAB89;
|
||||
context->state[2] = 0x98BADCFE;
|
||||
context->state[3] = 0x10325476;
|
||||
context->state[4] = 0xC3D2E1F0;
|
||||
context->count[0] = context->count[1] = 0;
|
||||
}
|
||||
|
||||
|
||||
/* Run your data through this. */
|
||||
void SHA1Update(SHA1_CTX* context, const unsigned char* data, uint32_t len)
|
||||
{
|
||||
uint32_t i, j;
|
||||
|
||||
j = context->count[0];
|
||||
if ((context->count[0] += len << 3) < j)
|
||||
context->count[1]++;
|
||||
context->count[1] += (len>>29);
|
||||
j = (j >> 3) & 63;
|
||||
if ((j + len) > 63) {
|
||||
memcpy(&context->buffer[j], data, (i = 64-j));
|
||||
SHA1Transform(context->state, context->buffer);
|
||||
for ( ; i + 63 < len; i += 64) {
|
||||
SHA1Transform(context->state, &data[i]);
|
||||
}
|
||||
j = 0;
|
||||
}
|
||||
else i = 0;
|
||||
memcpy(&context->buffer[j], &data[i], len - i);
|
||||
}
|
||||
|
||||
/* Add padding and return the message digest. */
|
||||
void SHA1Final(unsigned char digest[20], SHA1_CTX* context)
|
||||
{
|
||||
unsigned i;
|
||||
unsigned char finalcount[8];
|
||||
unsigned char c;
|
||||
|
||||
for (i = 0; i < 8; i++) {
|
||||
finalcount[i] = (unsigned char)((context->count[(i >= 4 ? 0 : 1)]
|
||||
>> ((3-(i & 3)) * 8) ) & 255); /* Endian independent */
|
||||
}
|
||||
c = 0200;
|
||||
SHA1Update(context, &c, 1);
|
||||
while ((context->count[0] & 504) != 448) {
|
||||
c = 0000;
|
||||
SHA1Update(context, &c, 1);
|
||||
}
|
||||
SHA1Update(context, finalcount, 8); /* Should cause a SHA1Transform() */
|
||||
for (i = 0; i < 20; i++) {
|
||||
digest[i] = (unsigned char)
|
||||
((context->state[i>>2] >> ((3-(i & 3)) * 8) ) & 255);
|
||||
}
|
||||
/* Wipe variables */
|
||||
memset(context, '\0', sizeof(*context));
|
||||
memset(&finalcount, '\0', sizeof(finalcount));
|
||||
}
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
@@ -0,0 +1,20 @@
|
||||
#ifndef RUNTIME_CITY_H
|
||||
#define RUNTIME_CITY_H
|
||||
|
||||
// CityHash, by Geoff Pike and Jyrki Alakuijala.
|
||||
|
||||
#include <stddef.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
// Hash function for a byte array.
|
||||
uint64_t CityHash64(const void* buf, size_t len);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif // RUNTIME_CITY_H
|
||||
@@ -0,0 +1,27 @@
|
||||
#ifndef RUNTIME_SHA1_H
|
||||
#define RUNTIME_SHA1_H
|
||||
/*
|
||||
SHA-1 in C
|
||||
By Steve Reid <steve@edmweb.com>
|
||||
100% Public Domain
|
||||
*/
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
typedef struct SHA1_CTX {
|
||||
uint32_t state[5];
|
||||
uint32_t count[2];
|
||||
unsigned char buffer[64];
|
||||
} SHA1_CTX;
|
||||
|
||||
void SHA1Init(SHA1_CTX* context);
|
||||
void SHA1Update(SHA1_CTX* context, const unsigned char* data, uint32_t len);
|
||||
void SHA1Final(unsigned char digest[20], SHA1_CTX* context);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif // RUNTIME_UTIL_SHA1_H
|
||||
Reference in New Issue
Block a user