From b647ce0239f6cf85623652e8c2497154ae6b3f44 Mon Sep 17 00:00:00 2001 From: Antonio Huete Jimenez Date: Wed, 16 May 2012 12:53:09 +0200 Subject: [PATCH] libkern - Bring Bob Jenkins hash algorithm. - Taken from FreeBSD - Also included a little testing program that gives approximate numbers. Generating random buffer ... CRC32 100000 LOOPS dataset 1024 bytes ... 4 collisions. Elapsed 515 msec Jenkins 100000 LOOPS dataset 1024 bytes ... 2 collisions. Elapsed 296 msec FNV 32 100000 LOOPS dataset 1024 bytes ... 2 collisions. Elapsed 164 msec --- sys/libkern/jenkins.h | 185 ++++++++++++++++++++++++++++++++++++++++++++ tools/test/hashes/Makefile | 9 ++ tools/test/hashes/main.c | 159 +++++++++++++++++++++++++++++++++++++ 3 files changed, 353 insertions(+), 0 deletions(-) create mode 100644 sys/libkern/jenkins.h create mode 100644 tools/test/hashes/Makefile create mode 100644 tools/test/hashes/main.c diff --git a/sys/libkern/jenkins.h b/sys/libkern/jenkins.h new file mode 100644 index 0000000..0846ae8 --- /dev/null +++ b/sys/libkern/jenkins.h @@ -0,0 +1,185 @@ +#ifndef __LIBKERN_JENKINS_H__ +#define __LIBKERN_JENKINS_H__ +/* + * Taken from http://burtleburtle.net/bob/c/lookup3.c + * $FreeBSD$ + */ + +/* +------------------------------------------------------------------------------- + lookup3.c, by Bob Jenkins, May 2006, Public Domain. + + These are functions for producing 32-bit hashes for hash table lookup. + hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() + are externally useful functions. Routines to test the hash are included + if SELF_TEST is defined. You can use this free for any purpose. It's in + the public domain. It has no warranty. + + You probably want to use hashlittle(). hashlittle() and hashbig() + hash byte arrays. hashlittle() is faster than hashbig() on + little-endian machines. Intel and AMD are little-endian machines. + On second thought, you probably want hashlittle2(), which is identical to + hashlittle() except it returns two 32-bit hashes for the price of one. + You could implement hashbig2() if you wanted but I haven't bothered here. + + If you want to find a hash of, say, exactly 7 integers, do + a = i1; b = i2; c = i3; + mix(a,b,c); + a += i4; b += i5; c += i6; + mix(a,b,c); + a += i7; + final(a,b,c); + then use c as the hash value. If you have a variable length array of + 4-byte integers to hash, use hashword(). If you have a byte array (like + a character string), use hashlittle(). If you have several byte arrays, or + a mix of things, see the comments above hashlittle(). + + Why is this so big? I read 12 bytes at a time into 3 4-byte integers, + then mix those integers. This is fast (you can do a lot more thorough + mixing with 12*3 instructions on 3 integers than you can with 3 instructions + on 1 byte), but shoehorning those bytes into integers efficiently is messy. +------------------------------------------------------------------------------- +*/ + +#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k)))) + +/* +------------------------------------------------------------------------------- +mix -- mix 3 32-bit values reversibly. + +This is reversible, so any information in (a,b,c) before mix() is +still in (a,b,c) after mix(). + +If four pairs of (a,b,c) inputs are run through mix(), or through +mix() in reverse, there are at least 32 bits of the output that +are sometimes the same for one pair and different for another pair. +This was tested for: +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that +satisfy this are + 4 6 8 16 19 4 + 9 15 3 18 27 15 + 14 9 3 7 17 3 +Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing +for "differ" defined as + with a one-bit base and a two-bit delta. I +used http://burtleburtle.net/bob/hash/avalanche.html to choose +the operations, constants, and arrangements of the variables. + +This does not achieve avalanche. There are input bits of (a,b,c) +that fail to affect some output bits of (a,b,c), especially of a. The +most thoroughly mixed value is c, but it doesn't really even achieve +avalanche in c. + +This allows some parallelism. Read-after-writes are good at doubling +the number of bits affected, so the goal of mixing pulls in the opposite +direction as the goal of parallelism. I did what I could. Rotates +seem to cost as much as shifts on every machine I could lay my hands +on, and rotates are much kinder to the top and bottom bits, so I used +rotates. +------------------------------------------------------------------------------- +*/ +#define mix(a,b,c) \ +{ \ + a -= c; a ^= rot(c, 4); c += b; \ + b -= a; b ^= rot(a, 6); a += c; \ + c -= b; c ^= rot(b, 8); b += a; \ + a -= c; a ^= rot(c,16); c += b; \ + b -= a; b ^= rot(a,19); a += c; \ + c -= b; c ^= rot(b, 4); b += a; \ +} + +/* +------------------------------------------------------------------------------- +final -- final mixing of 3 32-bit values (a,b,c) into c + +Pairs of (a,b,c) values differing in only a few bits will usually +produce values of c that look totally different. This was tested for +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +These constants passed: + 14 11 25 16 4 14 24 + 12 14 25 16 4 14 24 +and these came close: + 4 8 15 26 3 22 24 + 10 8 15 26 3 22 24 + 11 8 15 26 3 22 24 +------------------------------------------------------------------------------- +*/ +#define final(a,b,c) \ +{ \ + c ^= b; c -= rot(b,14); \ + a ^= c; a -= rot(c,11); \ + b ^= a; b -= rot(a,25); \ + c ^= b; c -= rot(b,16); \ + a ^= c; a -= rot(c,4); \ + b ^= a; b -= rot(a,14); \ + c ^= b; c -= rot(b,24); \ +} + +/* +-------------------------------------------------------------------- + This works on all machines. To be useful, it requires + -- that the key be an array of uint32_t's, and + -- that the length be the number of uint32_t's in the key + + The function hashword() is identical to hashlittle() on little-endian + machines, and identical to hashbig() on big-endian machines, + except that the length has to be measured in uint32_ts rather than in + bytes. hashlittle() is more complicated than hashword() only because + hashlittle() has to dance around fitting the key bytes into registers. +-------------------------------------------------------------------- +*/ +static uint32_t +jenkins_hashword( + const uint32_t *k, /* the key, an array of uint32_t values */ + size_t length, /* the length of the key, in uint32_ts */ + uint32_t initval /* the previous hash, or an arbitrary value */ +) +{ + uint32_t a,b,c; + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval; + + /*------------------------------------------------- handle most of the key */ + while (length > 3) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 3; + k += 3; + } + + /*------------------------------------------- handle the last 3 uint32_t's */ + switch(length) /* all the case statements fall through */ + { + case 3 : c+=k[2]; + case 2 : b+=k[1]; + case 1 : a+=k[0]; + final(a,b,c); + case 0: /* case 0: nothing left to add */ + break; + } + /*------------------------------------------------------ report the result */ + return c; +} +#endif diff --git a/tools/test/hashes/Makefile b/tools/test/hashes/Makefile new file mode 100644 index 0000000..fcafe5d --- /dev/null +++ b/tools/test/hashes/Makefile @@ -0,0 +1,9 @@ +PROG= hashes +SRCS= main.c crc32.c +CFLAGS = -O0 -pg + +.PATH: ${.CURDIR}/../../../sys/libkern + +NOMAN= sorry + +.include diff --git a/tools/test/hashes/main.c b/tools/test/hashes/main.c new file mode 100644 index 0000000..4df22a6 --- /dev/null +++ b/tools/test/hashes/main.c @@ -0,0 +1,159 @@ +#include +#include +#include +#include +#include +#include + + +#define SIZE MAXPATHLEN +#ifndef LOOPS +#define LOOPS 100000 +#endif +uint8_t buf[LOOPS][SIZE]; + +extern uint32_t crc32(const void *buf, size_t size); + +uint32_t *crclst; +uint32_t *jenlst; +uint32_t *fnvlst; + + +void +fillcrap(void) +{ + int i; + printf("Generating random buffer ...\n"); + + for (i = 0; i < LOOPS; i++) + arc4random_buf(buf[i], SIZE); +} + +int cmphash(const void *a, const void *b) +{ + uint32_t h1 = *(uint32_t *)a; + uint32_t h2 = *(uint32_t *)b; + + if (h1 == h2) + return 0; + else + if (h1 < h2) + return -1; + else + return 1; +} + +int +getcollisions(uint32_t *lst) +{ + int col, i; + col = 0; + + for (i = 1; i < LOOPS; i++) { + if ((cmphash(&lst[i-1], &lst[i])) == 0) + col++; + } + + return col; + +} + +void +test_crc32(void) +{ + uint32_t crc; + int i, col; + clock_t s, f; + int ms; + + crclst = malloc(LOOPS * sizeof(*crclst)); + + printf("CRC32 %d LOOPS dataset %d bytes ... ", LOOPS, SIZE); + s = clock(); + for (i = 0; i < LOOPS; i++) { + crc = crc32((char *)buf[i], SIZE); + crclst[i] = crc; + } + f = clock(); + + qsort(crclst, LOOPS, sizeof(uint32_t), cmphash); + + ms = ((double)(f - s))/CLOCKS_PER_SEC * 1000; + + col = getcollisions(crclst); + printf("%d collisions. Elapsed %d msec\n", col, ms); + + +} + +void +test_jenkins(void) +{ + uint32_t h; + int i, col; + clock_t s, f; + int ms; + + col = 0; + + jenlst = malloc(LOOPS * sizeof(*jenlst)); + + printf("Jenkins %d LOOPS dataset %d bytes ... ", LOOPS, SIZE); + s = clock(); + for (i = 0; i < LOOPS; i++) { + h = jenkins_hashword((const uint32_t *)buf[i], (sizeof(buf[i])-1)/4, 13); + jenlst[i] = h; + } + f = clock(); + + qsort(jenlst, LOOPS, sizeof(uint32_t), cmphash); + + ms = ((double)(f - s))/CLOCKS_PER_SEC * 1000; + + col = getcollisions(jenlst); + printf("%d collisions. Elapsed %d msec\n", col, ms); + +} + +void +test_fnv(void) +{ + uint32_t fnv = FNV1_32_INIT; + int i, col; + clock_t s, f; + int ms; + + col = 0; + + fnvlst = malloc(LOOPS * sizeof(*fnvlst)); + + printf("FNV 32 %d LOOPS dataset %d bytes ... ", LOOPS, SIZE); + s = clock(); + for (i = 0; i < LOOPS; i++) { + fnv = fnv_32_buf(buf[i], (sizeof(buf[i])-1)/4, fnv); + fnvlst[i] = fnv; + } + f = clock(); + + qsort(fnvlst, LOOPS, sizeof(uint32_t), cmphash); + + col = getcollisions(fnvlst); + ms = ((double)(f - s))/CLOCKS_PER_SEC * 1000; + + printf("%d collisions. Elapsed %d msec\n", col, ms); + + +} + +int +main(int argc, char *argv[]) +{ + int i, j; + + fillcrap(); + test_crc32(); + test_jenkins(); + test_fnv(); + + return 0; +} -- 1.7.7.2