From: Rusty Russell Date: Mon, 28 Jul 2008 03:02:22 +0000 (+1000) Subject: Move hash into ccan/ dir X-Git-Url: http://git.ozlabs.org/?p=ccan;a=commitdiff_plain;h=0953f929bc024a9107869a40516b89932d5482e0 Move hash into ccan/ dir --- diff --git a/ccan/hash/_info.c b/ccan/hash/_info.c new file mode 100644 index 00000000..9ce4e3ac --- /dev/null +++ b/ccan/hash/_info.c @@ -0,0 +1,25 @@ +#include + +/** + * hash - routines for hashing bytes + * + * When creating a hash table it's important to have a hash function + * which mixes well and is fast. This package supplies such functions. + * + * The hash functions come in two flavors: the normal ones and the + * stable ones. The normal ones can vary from machine-to-machine and + * may change if we find better or faster hash algorithms in future. + * The stable ones will always give the same results on any computer, + * and on any version of this package. + */ +int main(int argc, char *argv[]) +{ + if (argc != 2) + return 1; + + if (strcmp(argv[1], "depends") == 0) { + return 0; + } + + return 1; +} diff --git a/ccan/hash/hash.c b/ccan/hash/hash.c new file mode 100644 index 00000000..886101a1 --- /dev/null +++ b/ccan/hash/hash.c @@ -0,0 +1,1003 @@ +/* +------------------------------------------------------------------------------- +lookup3.c, by Bob Jenkins, May 2006, Public Domain. + +These are functions for producing 32-bit hashes for hash table lookup. +hash_word(), 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 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 hash_word(). 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 SELF_TEST 1 + +#if 0 +#include /* defines printf for tests */ +#include /* defines time_t for timings in the test */ +#include /* defines uint32_t etc */ +#include /* attempt to define endianness */ +#endif + +#include "hash/hash.h" +#ifdef linux +# include /* attempt to define endianness */ +#endif + +/* + * My best guess at if you are big-endian or little-endian. This may + * need adjustment. + */ +#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && \ + __BYTE_ORDER == __LITTLE_ENDIAN) || \ + (defined(i386) || defined(__i386__) || defined(__i486__) || \ + defined(__i586__) || defined(__i686__) || defined(vax) || defined(MIPSEL)) +# define HASH_LITTLE_ENDIAN 1 +# define HASH_BIG_ENDIAN 0 +#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \ + __BYTE_ORDER == __BIG_ENDIAN) || \ + (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel)) +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 1 +#else +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 0 +#endif + +#define hashsize(n) ((uint32_t)1<<(n)) +#define hashmask(n) (hashsize(n)-1) +#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 hash_word() 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 hash_word() only because + hashlittle() has to dance around fitting the key bytes into registers. +-------------------------------------------------------------------- +*/ +uint32_t hash_u32( +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; +} + + +#if 0 +/* +-------------------------------------------------------------------- +hash_word2() -- same as hash_word(), but take two seeds and return two +32-bit values. pc and pb must both be nonnull, and *pc and *pb must +both be initialized with seeds. If you pass in (*pb)==0, the output +(*pc) will be the same as the return value from hash_word(). +-------------------------------------------------------------------- +*/ +void hash_word2 ( +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 *pc, /* IN: seed OUT: primary hash value */ +uint32_t *pb) /* IN: more seed OUT: secondary hash value */ +{ + uint32_t a,b,c; + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)(length<<2)) + *pc; + c += *pb; + + /*------------------------------------------------- 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 */ + *pc=c; *pb=b; +} +#endif + +/* +------------------------------------------------------------------------------- +hashlittle() -- hash a variable-length key into a 32-bit value + k : the key (the unaligned variable-length array of bytes) + length : the length of the key, counting by bytes + initval : can be any 4-byte value +Returns a 32-bit value. Every bit of the key affects every bit of +the return value. Two keys differing by one or two bits will have +totally different hash values. + +The best hash table sizes are powers of 2. There is no need to do +mod a prime (mod is sooo slow!). If you need less than 32 bits, +use a bitmask. For example, if you need only 10 bits, do + h = (h & hashmask(10)); +In which case, the hash table should have hashsize(10) elements. + +If you are hashing n strings (uint8_t **)k, do it like this: + for (i=0, h=0; i 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]&0xffffff" actually reads beyond the end of the string, but + * then masks off the part it's not allowed to read. Because the + * string is aligned, the masked-off tail is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff; a+=k[0]; break; + case 6 : b+=k[1]&0xffff; a+=k[0]; break; + case 5 : b+=k[1]&0xff; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff; break; + case 2 : a+=k[0]&0xffff; break; + case 1 : a+=k[0]&0xff; break; + case 0 : return c; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ + case 1 : a+=k8[0]; break; + case 0 : return c; + } + +#endif /* !valgrind */ + + } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { + const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ + const uint8_t *k8; + + /*--------------- all but last block: aligned reads and different mixing */ + while (length > 12) + { + a += k[0] + (((uint32_t)k[1])<<16); + b += k[2] + (((uint32_t)k[3])<<16); + c += k[4] + (((uint32_t)k[5])<<16); + mix(a,b,c); + length -= 12; + k += 6; + } + + /*----------------------------- handle the last (probably partial) block */ + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[4]+(((uint32_t)k[5])<<16); + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=k[4]; + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=k[2]; + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=k[0]; + break; + case 1 : a+=k8[0]; + break; + case 0 : return c; /* zero length requires no mixing */ + } + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + a += ((uint32_t)k[1])<<8; + a += ((uint32_t)k[2])<<16; + a += ((uint32_t)k[3])<<24; + b += k[4]; + b += ((uint32_t)k[5])<<8; + b += ((uint32_t)k[6])<<16; + b += ((uint32_t)k[7])<<24; + c += k[8]; + c += ((uint32_t)k[9])<<8; + c += ((uint32_t)k[10])<<16; + c += ((uint32_t)k[11])<<24; + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=((uint32_t)k[11])<<24; + case 11: c+=((uint32_t)k[10])<<16; + case 10: c+=((uint32_t)k[9])<<8; + case 9 : c+=k[8]; + case 8 : b+=((uint32_t)k[7])<<24; + case 7 : b+=((uint32_t)k[6])<<16; + case 6 : b+=((uint32_t)k[5])<<8; + case 5 : b+=k[4]; + case 4 : a+=((uint32_t)k[3])<<24; + case 3 : a+=((uint32_t)k[2])<<16; + case 2 : a+=((uint32_t)k[1])<<8; + case 1 : a+=k[0]; + break; + case 0 : return c; + } + } + + final(a,b,c); + return c; +} + +#if 0 +/* + * hashlittle2: return 2 32-bit hash values + * + * This is identical to hashlittle(), except it returns two 32-bit hash + * values instead of just one. This is good enough for hash table + * lookup with 2^^64 buckets, or if you want a second hash if you're not + * happy with the first, or if you want a probably-unique 64-bit ID for + * the key. *pc is better mixed than *pb, so use *pc first. If you want + * a 64-bit value do something like "*pc + (((uint64_t)*pb)<<32)". + */ +void hashlittle2( + const void *key, /* the key to hash */ + size_t length, /* length of the key */ + uint32_t *pc, /* IN: primary initval, OUT: primary hash */ + uint32_t *pb) /* IN: secondary initval, OUT: secondary hash */ +{ + uint32_t a,b,c; /* internal state */ + union { const void *ptr; size_t i; } u; /* needed for Mac Powerbook G4 */ + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)length) + *pc; + c += *pb; + + u.ptr = key; + if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) { + const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ + const uint8_t *k8; + + /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]&0xffffff" actually reads beyond the end of the string, but + * then masks off the part it's not allowed to read. Because the + * string is aligned, the masked-off tail is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff; a+=k[0]; break; + case 6 : b+=k[1]&0xffff; a+=k[0]; break; + case 5 : b+=k[1]&0xff; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff; break; + case 2 : a+=k[0]&0xffff; break; + case 1 : a+=k[0]&0xff; break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ + case 1 : a+=k8[0]; break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + +#endif /* !valgrind */ + + } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { + const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ + const uint8_t *k8; + + /*--------------- all but last block: aligned reads and different mixing */ + while (length > 12) + { + a += k[0] + (((uint32_t)k[1])<<16); + b += k[2] + (((uint32_t)k[3])<<16); + c += k[4] + (((uint32_t)k[5])<<16); + mix(a,b,c); + length -= 12; + k += 6; + } + + /*----------------------------- handle the last (probably partial) block */ + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[4]+(((uint32_t)k[5])<<16); + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=k[4]; + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=k[2]; + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=k[0]; + break; + case 1 : a+=k8[0]; + break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + a += ((uint32_t)k[1])<<8; + a += ((uint32_t)k[2])<<16; + a += ((uint32_t)k[3])<<24; + b += k[4]; + b += ((uint32_t)k[5])<<8; + b += ((uint32_t)k[6])<<16; + b += ((uint32_t)k[7])<<24; + c += k[8]; + c += ((uint32_t)k[9])<<8; + c += ((uint32_t)k[10])<<16; + c += ((uint32_t)k[11])<<24; + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=((uint32_t)k[11])<<24; + case 11: c+=((uint32_t)k[10])<<16; + case 10: c+=((uint32_t)k[9])<<8; + case 9 : c+=k[8]; + case 8 : b+=((uint32_t)k[7])<<24; + case 7 : b+=((uint32_t)k[6])<<16; + case 6 : b+=((uint32_t)k[5])<<8; + case 5 : b+=k[4]; + case 4 : a+=((uint32_t)k[3])<<24; + case 3 : a+=((uint32_t)k[2])<<16; + case 2 : a+=((uint32_t)k[1])<<8; + case 1 : a+=k[0]; + break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + } + + final(a,b,c); + *pc=c; *pb=b; +} +#endif + + +/* + * hashbig(): + * This is the same as hash_word() on big-endian machines. It is different + * from hashlittle() on all machines. hashbig() takes advantage of + * big-endian byte ordering. + */ +static uint32_t hashbig( const void *key, size_t length, uint32_t initval) +{ + uint32_t a,b,c; + union { const void *ptr; size_t i; } u; /* to cast key to (size_t) happily */ + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)length) + initval; + + u.ptr = key; + if (HASH_BIG_ENDIAN && ((u.i & 0x3) == 0)) { + const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ +#ifdef VALGRIND + const uint8_t *k8; +#endif + + /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]<<8" actually reads beyond the end of the string, but + * then shifts out the part it's not allowed to read. Because the + * string is aligned, the illegal read is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff00; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff0000; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff000000; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff00; a+=k[0]; break; + case 6 : b+=k[1]&0xffff0000; a+=k[0]; break; + case 5 : b+=k[1]&0xff000000; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff00; break; + case 2 : a+=k[0]&0xffff0000; break; + case 1 : a+=k[0]&0xff000000; break; + case 0 : return c; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + + k8 = (const uint8_t *)k; + switch(length) /* all the case statements fall through */ + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<8; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<16; /* fall through */ + case 9 : c+=((uint32_t)k8[8])<<24; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<8; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<16; /* fall through */ + case 5 : b+=((uint32_t)k8[4])<<24; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<8; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<16; /* fall through */ + case 1 : a+=((uint32_t)k8[0])<<24; break; + case 0 : return c; + } + +#endif /* !VALGRIND */ + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += ((uint32_t)k[0])<<24; + a += ((uint32_t)k[1])<<16; + a += ((uint32_t)k[2])<<8; + a += ((uint32_t)k[3]); + b += ((uint32_t)k[4])<<24; + b += ((uint32_t)k[5])<<16; + b += ((uint32_t)k[6])<<8; + b += ((uint32_t)k[7]); + c += ((uint32_t)k[8])<<24; + c += ((uint32_t)k[9])<<16; + c += ((uint32_t)k[10])<<8; + c += ((uint32_t)k[11]); + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=k[11]; + case 11: c+=((uint32_t)k[10])<<8; + case 10: c+=((uint32_t)k[9])<<16; + case 9 : c+=((uint32_t)k[8])<<24; + case 8 : b+=k[7]; + case 7 : b+=((uint32_t)k[6])<<8; + case 6 : b+=((uint32_t)k[5])<<16; + case 5 : b+=((uint32_t)k[4])<<24; + case 4 : a+=k[3]; + case 3 : a+=((uint32_t)k[2])<<8; + case 2 : a+=((uint32_t)k[1])<<16; + case 1 : a+=((uint32_t)k[0])<<24; + break; + case 0 : return c; + } + } + + final(a,b,c); + return c; +} + +uint32_t hash_any_stable(const void *key, size_t length, uint32_t base) +{ + /* We use hashlittle as our stable hash. */ + return hashlittle(key, length, base); +} + +uint32_t hash_any(const void *key, size_t length, uint32_t base) +{ + if (HASH_BIG_ENDIAN) + return hashbig(key, length, base); + else + /* We call hash_any_stable not hashlittle. This way we know + * that hashlittle will be inlined in hash_any_stable. */ + return hash_any_stable(key, length, base); +} + +#ifdef SELF_TEST + +/* used for timings */ +void driver1() +{ + uint8_t buf[256]; + uint32_t i; + uint32_t h=0; + time_t a,z; + + time(&a); + for (i=0; i<256; ++i) buf[i] = 'x'; + for (i=0; i<1; ++i) + { + h = hashlittle(&buf[0],1,h); + } + time(&z); + if (z-a > 0) printf("time %d %.8x\n", z-a, h); +} + +/* check that every input bit changes every output bit half the time */ +#define HASHSTATE 1 +#define HASHLEN 1 +#define MAXPAIR 60 +#define MAXLEN 70 +void driver2() +{ + uint8_t qa[MAXLEN+1], qb[MAXLEN+2], *a = &qa[0], *b = &qb[1]; + uint32_t c[HASHSTATE], d[HASHSTATE], i=0, j=0, k, l, m=0, z; + uint32_t e[HASHSTATE],f[HASHSTATE],g[HASHSTATE],h[HASHSTATE]; + uint32_t x[HASHSTATE],y[HASHSTATE]; + uint32_t hlen; + + printf("No more than %d trials should ever be needed \n",MAXPAIR/2); + for (hlen=0; hlen < MAXLEN; ++hlen) + { + z=0; + for (i=0; i>(8-j)); + c[0] = hashlittle(a, hlen, m); + b[i] ^= ((k+1)<>(8-j)); + d[0] = hashlittle(b, hlen, m); + /* check every bit is 1, 0, set, and not set at least once */ + for (l=0; lz) z=k; + if (k==MAXPAIR) + { + printf("Some bit didn't change: "); + printf("%.8x %.8x %.8x %.8x %.8x %.8x ", + e[0],f[0],g[0],h[0],x[0],y[0]); + printf("i %d j %d m %d len %d\n", i, j, m, hlen); + } + if (z==MAXPAIR) goto done; + } + } + } + done: + if (z < MAXPAIR) + { + printf("Mix success %2d bytes %2d initvals ",i,m); + printf("required %d trials\n", z/2); + } + } + printf("\n"); +} + +/* Check for reading beyond the end of the buffer and alignment problems */ +void driver3() +{ + uint8_t buf[MAXLEN+20], *b; + uint32_t len; + uint8_t q[] = "This is the time for all good men to come to the aid of their country..."; + uint32_t h; + uint8_t qq[] = "xThis is the time for all good men to come to the aid of their country..."; + uint32_t i; + uint8_t qqq[] = "xxThis is the time for all good men to come to the aid of their country..."; + uint32_t j; + uint8_t qqqq[] = "xxxThis is the time for all good men to come to the aid of their country..."; + uint32_t ref,x,y; + uint8_t *p; + + printf("Endianness. These lines should all be the same (for values filled in):\n"); + printf("%.8x %.8x %.8x\n", + hash_word((const uint32_t *)q, (sizeof(q)-1)/4, 13), + hash_word((const uint32_t *)q, (sizeof(q)-5)/4, 13), + hash_word((const uint32_t *)q, (sizeof(q)-9)/4, 13)); + p = q; + printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", + hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), + hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), + hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), + hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), + hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), + hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); + p = &qq[1]; + printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", + hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), + hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), + hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), + hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), + hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), + hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); + p = &qqq[2]; + printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", + hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), + hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), + hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), + hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), + hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), + hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); + p = &qqqq[3]; + printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", + hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), + hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), + hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), + hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), + hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), + hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); + printf("\n"); + + /* check that hashlittle2 and hashlittle produce the same results */ + i=47; j=0; + hashlittle2(q, sizeof(q), &i, &j); + if (hashlittle(q, sizeof(q), 47) != i) + printf("hashlittle2 and hashlittle mismatch\n"); + + /* check that hash_word2 and hash_word produce the same results */ + len = 0xdeadbeef; + i=47, j=0; + hash_word2(&len, 1, &i, &j); + if (hash_word(&len, 1, 47) != i) + printf("hash_word2 and hash_word mismatch %x %x\n", + i, hash_word(&len, 1, 47)); + + /* check hashlittle doesn't read before or after the ends of the string */ + for (h=0, b=buf+1; h<8; ++h, ++b) + { + for (i=0; i +#include +#include "config.h" + +/* Stolen mostly from: lookup3.c, by Bob Jenkins, May 2006, Public Domain. + * + * http://burtleburtle.net/bob/c/lookup3.c + */ + +/** + * hash - fast hash of an array for internal use + * @p: the array or pointer to first element + * @num: the number of elements to hash + * @base: the base number to roll into the hash (usually 0) + * + * The memory region pointed to by p is combined with the base to form + * a 32-bit hash. + * + * This hash will have different results on different machines, so is + * only useful for internal hashes (ie. not hashes sent across the + * network or saved to disk). + * + * It may also change with future versions: it could even detect at runtime + * what the fastest hash to use is. + * + * See also: hash_stable. + * + * Example: + * #include "hash/hash.h" + * #include + * #include + * + * // Simple demonstration: idential strings will have the same hash, but + * // two different strings will probably not. + * int main(int argc, char *argv[]) + * { + * uint32_t hash1, hash2; + * + * if (argc != 3) + * err(1, "Usage: %s ", argv[0]); + * + * hash1 = hash(argv[1], strlen(argv[1]), 0); + * hash2 = hash(argv[2], strlen(argv[2]), 0); + * printf("Hash is %s\n", hash1 == hash2 ? "same" : "different"); + * return 0; + * } + */ +#define hash(p, num, base) hash_any((p), (num)*sizeof(*(p)), (base)) + +/** + * hash_stable - hash of an array for external use + * @p: the array or pointer to first element + * @num: the number of elements to hash + * @base: the base number to roll into the hash (usually 0) + * + * The memory region pointed to by p is combined with the base to form + * a 32-bit hash. + * + * This hash will have the same results on different machines, so can + * be used for external hashes (ie. hashes sent across the network or + * saved to disk). The results will not change in future versions of + * this module. + * + * Example: + * #include "hash/hash.h" + * #include + * #include + * + * int main(int argc, char *argv[]) + * { + * if (argc != 2) + * err(1, "Usage: %s ", argv[0]); + * + * printf("Hash stable result is %u\n", + * hash_stable(argv[1], strlen(argv[1]), 0)); + * return 0; + * } + */ +#define hash_stable(p, num, base) \ + hash_any_stable((p), (num)*sizeof(*(p)), (base)) + +/** + * hash_u32 - fast hash an array of 32-bit values for internal use + * @key: the array of uint32_t + * @num: the number of elements to hash + * @base: the base number to roll into the hash (usually 0) + * + * The array of uint32_t pointed to by @key is combined with the base + * to form a 32-bit hash. This is 2-3 times faster than hash() on small + * arrays, but the advantage vanishes over large hashes. + * + * This hash will have different results on different machines, so is + * only useful for internal hashes (ie. not hashes sent across the + * network or saved to disk). + */ +uint32_t hash_u32(const uint32_t *key, size_t num, uint32_t base); + +/** + * hash_string - very fast hash of an ascii string + * @str: the nul-terminated string + * + * The string is hashed, using a hash function optimized for ASCII and + * similar strings. It's weaker than the other hash functions. + * + * This hash may have different results on different machines, so is + * only useful for internal hashes (ie. not hashes sent across the + * network or saved to disk). The results will be different from the + * other hash functions in this module, too. + */ +static inline uint32_t hash_string(const char *string) +{ + /* This is Karl Nelson 's X31 hash. + * It's a little faster than the (much better) lookup3 hash(): 56ns vs + * 84ns on my 2GHz Intel Core Duo 2 laptop for a 10 char string. */ + uint32_t ret; + + for (ret = 0; *string; string++) + ret = (ret << 5) - ret + *string; + + return ret; +} + +/* Our underlying operations. */ +uint32_t hash_any(const void *key, size_t length, uint32_t base); +uint32_t hash_any_stable(const void *key, size_t length, uint32_t base); + +/** + * hash_pointer - hash a pointer for internal use + * @p: the pointer value to hash + * @base: the base number to roll into the hash (usually 0) + * + * The pointer p (not what p points to!) is combined with the base to form + * a 32-bit hash. + * + * This hash will have different results on different machines, so is + * only useful for internal hashes (ie. not hashes sent across the + * network or saved to disk). + * + * Example: + * #include "hash/hash.h" + * + * // Code to keep track of memory regions. + * struct region { + * struct region *chain; + * void *start; + * unsigned int size; + * }; + * // We keep a simple hash table. + * static struct region *region_hash[128]; + * + * static void add_region(struct region *r) + * { + * unsigned int h = hash_pointer(r->start); + * + * r->chain = region_hash[h]; + * region_hash[h] = r->chain; + * } + * + * static void find_region(const void *start) + * { + * struct region *r; + * + * for (r = region_hash[hash_pointer(start)]; r; r = r->chain) + * if (r->start == start) + * return r; + * return NULL; + * } + */ +static inline uint32_t hash_pointer(const void *p, uint32_t base) +{ + if (sizeof(p) % sizeof(uint32_t) == 0) { + /* This convoluted union is the right way of aliasing. */ + union { + uint32_t u32[sizeof(p) / sizeof(uint32_t)]; + const void *p; + } u; + u.p = p; + return hash_u32(u.u32, sizeof(p) / sizeof(uint32_t), base); + } else + return hash(&p, 1, base); +} +#endif /* HASH_H */ diff --git a/ccan/hash/test/run.c b/ccan/hash/test/run.c new file mode 100644 index 00000000..a10e723e --- /dev/null +++ b/ccan/hash/test/run.c @@ -0,0 +1,152 @@ +#include "hash/hash.h" +#include "tap/tap.h" +#include "hash/hash.c" +#include +#include + +#define ARRAY_WORDS 5 + +int main(int argc, char *argv[]) +{ + unsigned int i, j, k; + uint32_t array[ARRAY_WORDS], val; + char array2[sizeof(array) + sizeof(uint32_t)]; + uint32_t results[256]; + + /* Initialize array. */ + for (i = 0; i < ARRAY_WORDS; i++) + array[i] = i; + + plan_tests(55); + + /* hash_stable is guaranteed. */ + ok1(hash_stable(array, ARRAY_WORDS, 0) == 0x13305f8c); + ok1(hash_stable(array, ARRAY_WORDS, 1) == 0x171abf74); + ok1(hash_stable(array, ARRAY_WORDS, 2) == 0x7646fcc7); + ok1(hash_stable(array, ARRAY_WORDS, 4) == 0xa758ed5); + ok1(hash_stable(array, ARRAY_WORDS, 8) == 0x2dedc2e4); + ok1(hash_stable(array, ARRAY_WORDS, 16) == 0x28e2076b); + ok1(hash_stable(array, ARRAY_WORDS, 32) == 0xb73091c5); + ok1(hash_stable(array, ARRAY_WORDS, 64) == 0x87daf5db); + ok1(hash_stable(array, ARRAY_WORDS, 128) == 0xa16dfe20); + ok1(hash_stable(array, ARRAY_WORDS, 256) == 0x300c63c3); + ok1(hash_stable(array, ARRAY_WORDS, 512) == 0x255c91fc); + ok1(hash_stable(array, ARRAY_WORDS, 1024) == 0x6357b26); + ok1(hash_stable(array, ARRAY_WORDS, 2048) == 0x4bc5f339); + ok1(hash_stable(array, ARRAY_WORDS, 4096) == 0x1301617c); + ok1(hash_stable(array, ARRAY_WORDS, 8192) == 0x506792c9); + ok1(hash_stable(array, ARRAY_WORDS, 16384) == 0xcd596705); + ok1(hash_stable(array, ARRAY_WORDS, 32768) == 0xa8713cac); + ok1(hash_stable(array, ARRAY_WORDS, 65536) == 0x94d9794); + ok1(hash_stable(array, ARRAY_WORDS, 131072) == 0xac753e8); + ok1(hash_stable(array, ARRAY_WORDS, 262144) == 0xcd8bdd20); + ok1(hash_stable(array, ARRAY_WORDS, 524288) == 0xd44faf80); + ok1(hash_stable(array, ARRAY_WORDS, 1048576) == 0x2547ccbe); + ok1(hash_stable(array, ARRAY_WORDS, 2097152) == 0xbab06dbc); + ok1(hash_stable(array, ARRAY_WORDS, 4194304) == 0xaac0e882); + ok1(hash_stable(array, ARRAY_WORDS, 8388608) == 0x443f48d0); + ok1(hash_stable(array, ARRAY_WORDS, 16777216) == 0xdff49fcc); + ok1(hash_stable(array, ARRAY_WORDS, 33554432) == 0x9ce0fd65); + ok1(hash_stable(array, ARRAY_WORDS, 67108864) == 0x9ddb1def); + ok1(hash_stable(array, ARRAY_WORDS, 134217728) == 0x86096f25); + ok1(hash_stable(array, ARRAY_WORDS, 268435456) == 0xe713b7b5); + ok1(hash_stable(array, ARRAY_WORDS, 536870912) == 0x5baeffc5); + ok1(hash_stable(array, ARRAY_WORDS, 1073741824) == 0xde874f52); + ok1(hash_stable(array, ARRAY_WORDS, 2147483648U) == 0xeca13b4e); + + /* Hash should be the same, indep of memory alignment. */ + val = hash(array, sizeof(array), 0); + for (i = 0; i < sizeof(uint32_t); i++) { + memcpy(array2 + i, array, sizeof(array)); + ok(hash(array2 + i, sizeof(array), 0) != val, + "hash matched at offset %i", i); + } + + /* Hash of random values should have random distribution: + * check one byte at a time. */ + for (i = 0; i < sizeof(uint32_t); i++) { + unsigned int lowest = -1U, highest = 0; + + memset(results, 0, sizeof(results)); + + for (j = 0; j < 256000; j++) { + for (k = 0; k < ARRAY_WORDS; k++) + array[k] = random(); + results[(hash(array, sizeof(array), 0) >> i*8)&0xFF]++; + } + + for (j = 0; j < 256; j++) { + if (results[j] < lowest) + lowest = results[j]; + if (results[j] > highest) + highest = results[j]; + } + /* Expect within 20% */ + ok(lowest > 800, "Byte %i lowest %i", i, lowest); + ok(highest < 1200, "Byte %i highest %i", i, highest); + diag("Byte %i, range %u-%u", i, lowest, highest); + } + + /* Hash of pointer values should also have random distribution. */ + for (i = 0; i < sizeof(uint32_t); i++) { + unsigned int lowest = -1U, highest = 0; + char *p = malloc(256000); + + memset(results, 0, sizeof(results)); + + for (j = 0; j < 256000; j++) + results[(hash_pointer(p + j, 0) >> i*8)&0xFF]++; + free(p); + + for (j = 0; j < 256; j++) { + if (results[j] < lowest) + lowest = results[j]; + if (results[j] > highest) + highest = results[j]; + } + /* Expect within 20% */ + ok(lowest > 800, "hash_pointer byte %i lowest %i", i, lowest); + ok(highest < 1200, "hash_pointer byte %i highest %i", + i, highest); + diag("hash_pointer byte %i, range %u-%u", i, lowest, highest); + } + + /* String hash: weak, so only test bottom byte */ + for (i = 0; i < 1; i++) { + unsigned int num = 0, cursor, lowest = -1U, highest = 0; + char p[5]; + + memset(results, 0, sizeof(results)); + + memset(p, 'A', sizeof(p)); + p[sizeof(p)-1] = '\0'; + + for (;;) { + for (cursor = 0; cursor < sizeof(p)-1; cursor++) { + p[cursor]++; + if (p[cursor] <= 'z') + break; + p[cursor] = 'A'; + } + if (cursor == sizeof(p)-1) + break; + + results[(hash_string(p) >> i*8)&0xFF]++; + num++; + } + + for (j = 0; j < 256; j++) { + if (results[j] < lowest) + lowest = results[j]; + if (results[j] > highest) + highest = results[j]; + } + /* Expect within 20% */ + ok(lowest > 35000, "hash_pointer byte %i lowest %i", i, lowest); + ok(highest < 53000, "hash_pointer byte %i highest %i", + i, highest); + diag("hash_pointer byte %i, range %u-%u", i, lowest, highest); + } + + return exit_status(); +} diff --git a/hash/_info.c b/hash/_info.c deleted file mode 100644 index 66b9fc0d..00000000 --- a/hash/_info.c +++ /dev/null @@ -1,23 +0,0 @@ -/** - * hash - routines for hashing bytes - * - * When creating a hash table it's important to have a hash function - * which mixes well and is fast. This package supplies such functions. - * - * The hash functions come in two flavors: the normal ones and the - * stable ones. The normal ones can vary from machine-to-machine and - * may change if we find better or faster hash algorithms in future. - * The stable ones will always give the same results on any computer, - * and on any version of this package. - */ -int main(int argc, char *argv[]) -{ - if (argc != 2) - return 1; - - if (strcmp(argv[1], "depends") == 0) { - return 0; - } - - return 1; -} diff --git a/hash/hash.c b/hash/hash.c deleted file mode 100644 index 886101a1..00000000 --- a/hash/hash.c +++ /dev/null @@ -1,1003 +0,0 @@ -/* -------------------------------------------------------------------------------- -lookup3.c, by Bob Jenkins, May 2006, Public Domain. - -These are functions for producing 32-bit hashes for hash table lookup. -hash_word(), 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 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 hash_word(). 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 SELF_TEST 1 - -#if 0 -#include /* defines printf for tests */ -#include /* defines time_t for timings in the test */ -#include /* defines uint32_t etc */ -#include /* attempt to define endianness */ -#endif - -#include "hash/hash.h" -#ifdef linux -# include /* attempt to define endianness */ -#endif - -/* - * My best guess at if you are big-endian or little-endian. This may - * need adjustment. - */ -#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && \ - __BYTE_ORDER == __LITTLE_ENDIAN) || \ - (defined(i386) || defined(__i386__) || defined(__i486__) || \ - defined(__i586__) || defined(__i686__) || defined(vax) || defined(MIPSEL)) -# define HASH_LITTLE_ENDIAN 1 -# define HASH_BIG_ENDIAN 0 -#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \ - __BYTE_ORDER == __BIG_ENDIAN) || \ - (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel)) -# define HASH_LITTLE_ENDIAN 0 -# define HASH_BIG_ENDIAN 1 -#else -# define HASH_LITTLE_ENDIAN 0 -# define HASH_BIG_ENDIAN 0 -#endif - -#define hashsize(n) ((uint32_t)1<<(n)) -#define hashmask(n) (hashsize(n)-1) -#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 hash_word() 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 hash_word() only because - hashlittle() has to dance around fitting the key bytes into registers. --------------------------------------------------------------------- -*/ -uint32_t hash_u32( -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; -} - - -#if 0 -/* --------------------------------------------------------------------- -hash_word2() -- same as hash_word(), but take two seeds and return two -32-bit values. pc and pb must both be nonnull, and *pc and *pb must -both be initialized with seeds. If you pass in (*pb)==0, the output -(*pc) will be the same as the return value from hash_word(). --------------------------------------------------------------------- -*/ -void hash_word2 ( -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 *pc, /* IN: seed OUT: primary hash value */ -uint32_t *pb) /* IN: more seed OUT: secondary hash value */ -{ - uint32_t a,b,c; - - /* Set up the internal state */ - a = b = c = 0xdeadbeef + ((uint32_t)(length<<2)) + *pc; - c += *pb; - - /*------------------------------------------------- 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 */ - *pc=c; *pb=b; -} -#endif - -/* -------------------------------------------------------------------------------- -hashlittle() -- hash a variable-length key into a 32-bit value - k : the key (the unaligned variable-length array of bytes) - length : the length of the key, counting by bytes - initval : can be any 4-byte value -Returns a 32-bit value. Every bit of the key affects every bit of -the return value. Two keys differing by one or two bits will have -totally different hash values. - -The best hash table sizes are powers of 2. There is no need to do -mod a prime (mod is sooo slow!). If you need less than 32 bits, -use a bitmask. For example, if you need only 10 bits, do - h = (h & hashmask(10)); -In which case, the hash table should have hashsize(10) elements. - -If you are hashing n strings (uint8_t **)k, do it like this: - for (i=0, h=0; i 12) - { - a += k[0]; - b += k[1]; - c += k[2]; - mix(a,b,c); - length -= 12; - k += 3; - } - - /*----------------------------- handle the last (probably partial) block */ - /* - * "k[2]&0xffffff" actually reads beyond the end of the string, but - * then masks off the part it's not allowed to read. Because the - * string is aligned, the masked-off tail is in the same word as the - * rest of the string. Every machine with memory protection I've seen - * does it on word boundaries, so is OK with this. But VALGRIND will - * still catch it and complain. The masking trick does make the hash - * noticably faster for short strings (like English words). - */ -#ifndef VALGRIND - - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; - case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; - case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=k[1]&0xffffff; a+=k[0]; break; - case 6 : b+=k[1]&0xffff; a+=k[0]; break; - case 5 : b+=k[1]&0xff; a+=k[0]; break; - case 4 : a+=k[0]; break; - case 3 : a+=k[0]&0xffffff; break; - case 2 : a+=k[0]&0xffff; break; - case 1 : a+=k[0]&0xff; break; - case 0 : return c; /* zero length strings require no mixing */ - } - -#else /* make valgrind happy */ - - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ - case 1 : a+=k8[0]; break; - case 0 : return c; - } - -#endif /* !valgrind */ - - } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { - const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ - const uint8_t *k8; - - /*--------------- all but last block: aligned reads and different mixing */ - while (length > 12) - { - a += k[0] + (((uint32_t)k[1])<<16); - b += k[2] + (((uint32_t)k[3])<<16); - c += k[4] + (((uint32_t)k[5])<<16); - mix(a,b,c); - length -= 12; - k += 6; - } - - /*----------------------------- handle the last (probably partial) block */ - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[4]+(((uint32_t)k[5])<<16); - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=k[4]; - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=k[2]; - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=k[0]; - break; - case 1 : a+=k8[0]; - break; - case 0 : return c; /* zero length requires no mixing */ - } - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - a += ((uint32_t)k[1])<<8; - a += ((uint32_t)k[2])<<16; - a += ((uint32_t)k[3])<<24; - b += k[4]; - b += ((uint32_t)k[5])<<8; - b += ((uint32_t)k[6])<<16; - b += ((uint32_t)k[7])<<24; - c += k[8]; - c += ((uint32_t)k[9])<<8; - c += ((uint32_t)k[10])<<16; - c += ((uint32_t)k[11])<<24; - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=((uint32_t)k[11])<<24; - case 11: c+=((uint32_t)k[10])<<16; - case 10: c+=((uint32_t)k[9])<<8; - case 9 : c+=k[8]; - case 8 : b+=((uint32_t)k[7])<<24; - case 7 : b+=((uint32_t)k[6])<<16; - case 6 : b+=((uint32_t)k[5])<<8; - case 5 : b+=k[4]; - case 4 : a+=((uint32_t)k[3])<<24; - case 3 : a+=((uint32_t)k[2])<<16; - case 2 : a+=((uint32_t)k[1])<<8; - case 1 : a+=k[0]; - break; - case 0 : return c; - } - } - - final(a,b,c); - return c; -} - -#if 0 -/* - * hashlittle2: return 2 32-bit hash values - * - * This is identical to hashlittle(), except it returns two 32-bit hash - * values instead of just one. This is good enough for hash table - * lookup with 2^^64 buckets, or if you want a second hash if you're not - * happy with the first, or if you want a probably-unique 64-bit ID for - * the key. *pc is better mixed than *pb, so use *pc first. If you want - * a 64-bit value do something like "*pc + (((uint64_t)*pb)<<32)". - */ -void hashlittle2( - const void *key, /* the key to hash */ - size_t length, /* length of the key */ - uint32_t *pc, /* IN: primary initval, OUT: primary hash */ - uint32_t *pb) /* IN: secondary initval, OUT: secondary hash */ -{ - uint32_t a,b,c; /* internal state */ - union { const void *ptr; size_t i; } u; /* needed for Mac Powerbook G4 */ - - /* Set up the internal state */ - a = b = c = 0xdeadbeef + ((uint32_t)length) + *pc; - c += *pb; - - u.ptr = key; - if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) { - const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ - const uint8_t *k8; - - /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - b += k[1]; - c += k[2]; - mix(a,b,c); - length -= 12; - k += 3; - } - - /*----------------------------- handle the last (probably partial) block */ - /* - * "k[2]&0xffffff" actually reads beyond the end of the string, but - * then masks off the part it's not allowed to read. Because the - * string is aligned, the masked-off tail is in the same word as the - * rest of the string. Every machine with memory protection I've seen - * does it on word boundaries, so is OK with this. But VALGRIND will - * still catch it and complain. The masking trick does make the hash - * noticably faster for short strings (like English words). - */ -#ifndef VALGRIND - - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; - case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; - case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=k[1]&0xffffff; a+=k[0]; break; - case 6 : b+=k[1]&0xffff; a+=k[0]; break; - case 5 : b+=k[1]&0xff; a+=k[0]; break; - case 4 : a+=k[0]; break; - case 3 : a+=k[0]&0xffffff; break; - case 2 : a+=k[0]&0xffff; break; - case 1 : a+=k[0]&0xff; break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - -#else /* make valgrind happy */ - - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ - case 1 : a+=k8[0]; break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - -#endif /* !valgrind */ - - } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { - const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ - const uint8_t *k8; - - /*--------------- all but last block: aligned reads and different mixing */ - while (length > 12) - { - a += k[0] + (((uint32_t)k[1])<<16); - b += k[2] + (((uint32_t)k[3])<<16); - c += k[4] + (((uint32_t)k[5])<<16); - mix(a,b,c); - length -= 12; - k += 6; - } - - /*----------------------------- handle the last (probably partial) block */ - k8 = (const uint8_t *)k; - switch(length) - { - case 12: c+=k[4]+(((uint32_t)k[5])<<16); - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ - case 10: c+=k[4]; - b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 9 : c+=k8[8]; /* fall through */ - case 8 : b+=k[2]+(((uint32_t)k[3])<<16); - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ - case 6 : b+=k[2]; - a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 5 : b+=k8[4]; /* fall through */ - case 4 : a+=k[0]+(((uint32_t)k[1])<<16); - break; - case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ - case 2 : a+=k[0]; - break; - case 1 : a+=k8[0]; - break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - a += ((uint32_t)k[1])<<8; - a += ((uint32_t)k[2])<<16; - a += ((uint32_t)k[3])<<24; - b += k[4]; - b += ((uint32_t)k[5])<<8; - b += ((uint32_t)k[6])<<16; - b += ((uint32_t)k[7])<<24; - c += k[8]; - c += ((uint32_t)k[9])<<8; - c += ((uint32_t)k[10])<<16; - c += ((uint32_t)k[11])<<24; - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=((uint32_t)k[11])<<24; - case 11: c+=((uint32_t)k[10])<<16; - case 10: c+=((uint32_t)k[9])<<8; - case 9 : c+=k[8]; - case 8 : b+=((uint32_t)k[7])<<24; - case 7 : b+=((uint32_t)k[6])<<16; - case 6 : b+=((uint32_t)k[5])<<8; - case 5 : b+=k[4]; - case 4 : a+=((uint32_t)k[3])<<24; - case 3 : a+=((uint32_t)k[2])<<16; - case 2 : a+=((uint32_t)k[1])<<8; - case 1 : a+=k[0]; - break; - case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ - } - } - - final(a,b,c); - *pc=c; *pb=b; -} -#endif - - -/* - * hashbig(): - * This is the same as hash_word() on big-endian machines. It is different - * from hashlittle() on all machines. hashbig() takes advantage of - * big-endian byte ordering. - */ -static uint32_t hashbig( const void *key, size_t length, uint32_t initval) -{ - uint32_t a,b,c; - union { const void *ptr; size_t i; } u; /* to cast key to (size_t) happily */ - - /* Set up the internal state */ - a = b = c = 0xdeadbeef + ((uint32_t)length) + initval; - - u.ptr = key; - if (HASH_BIG_ENDIAN && ((u.i & 0x3) == 0)) { - const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ -#ifdef VALGRIND - const uint8_t *k8; -#endif - - /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ - while (length > 12) - { - a += k[0]; - b += k[1]; - c += k[2]; - mix(a,b,c); - length -= 12; - k += 3; - } - - /*----------------------------- handle the last (probably partial) block */ - /* - * "k[2]<<8" actually reads beyond the end of the string, but - * then shifts out the part it's not allowed to read. Because the - * string is aligned, the illegal read is in the same word as the - * rest of the string. Every machine with memory protection I've seen - * does it on word boundaries, so is OK with this. But VALGRIND will - * still catch it and complain. The masking trick does make the hash - * noticably faster for short strings (like English words). - */ -#ifndef VALGRIND - - switch(length) - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=k[2]&0xffffff00; b+=k[1]; a+=k[0]; break; - case 10: c+=k[2]&0xffff0000; b+=k[1]; a+=k[0]; break; - case 9 : c+=k[2]&0xff000000; b+=k[1]; a+=k[0]; break; - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=k[1]&0xffffff00; a+=k[0]; break; - case 6 : b+=k[1]&0xffff0000; a+=k[0]; break; - case 5 : b+=k[1]&0xff000000; a+=k[0]; break; - case 4 : a+=k[0]; break; - case 3 : a+=k[0]&0xffffff00; break; - case 2 : a+=k[0]&0xffff0000; break; - case 1 : a+=k[0]&0xff000000; break; - case 0 : return c; /* zero length strings require no mixing */ - } - -#else /* make valgrind happy */ - - k8 = (const uint8_t *)k; - switch(length) /* all the case statements fall through */ - { - case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; - case 11: c+=((uint32_t)k8[10])<<8; /* fall through */ - case 10: c+=((uint32_t)k8[9])<<16; /* fall through */ - case 9 : c+=((uint32_t)k8[8])<<24; /* fall through */ - case 8 : b+=k[1]; a+=k[0]; break; - case 7 : b+=((uint32_t)k8[6])<<8; /* fall through */ - case 6 : b+=((uint32_t)k8[5])<<16; /* fall through */ - case 5 : b+=((uint32_t)k8[4])<<24; /* fall through */ - case 4 : a+=k[0]; break; - case 3 : a+=((uint32_t)k8[2])<<8; /* fall through */ - case 2 : a+=((uint32_t)k8[1])<<16; /* fall through */ - case 1 : a+=((uint32_t)k8[0])<<24; break; - case 0 : return c; - } - -#endif /* !VALGRIND */ - - } else { /* need to read the key one byte at a time */ - const uint8_t *k = (const uint8_t *)key; - - /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ - while (length > 12) - { - a += ((uint32_t)k[0])<<24; - a += ((uint32_t)k[1])<<16; - a += ((uint32_t)k[2])<<8; - a += ((uint32_t)k[3]); - b += ((uint32_t)k[4])<<24; - b += ((uint32_t)k[5])<<16; - b += ((uint32_t)k[6])<<8; - b += ((uint32_t)k[7]); - c += ((uint32_t)k[8])<<24; - c += ((uint32_t)k[9])<<16; - c += ((uint32_t)k[10])<<8; - c += ((uint32_t)k[11]); - mix(a,b,c); - length -= 12; - k += 12; - } - - /*-------------------------------- last block: affect all 32 bits of (c) */ - switch(length) /* all the case statements fall through */ - { - case 12: c+=k[11]; - case 11: c+=((uint32_t)k[10])<<8; - case 10: c+=((uint32_t)k[9])<<16; - case 9 : c+=((uint32_t)k[8])<<24; - case 8 : b+=k[7]; - case 7 : b+=((uint32_t)k[6])<<8; - case 6 : b+=((uint32_t)k[5])<<16; - case 5 : b+=((uint32_t)k[4])<<24; - case 4 : a+=k[3]; - case 3 : a+=((uint32_t)k[2])<<8; - case 2 : a+=((uint32_t)k[1])<<16; - case 1 : a+=((uint32_t)k[0])<<24; - break; - case 0 : return c; - } - } - - final(a,b,c); - return c; -} - -uint32_t hash_any_stable(const void *key, size_t length, uint32_t base) -{ - /* We use hashlittle as our stable hash. */ - return hashlittle(key, length, base); -} - -uint32_t hash_any(const void *key, size_t length, uint32_t base) -{ - if (HASH_BIG_ENDIAN) - return hashbig(key, length, base); - else - /* We call hash_any_stable not hashlittle. This way we know - * that hashlittle will be inlined in hash_any_stable. */ - return hash_any_stable(key, length, base); -} - -#ifdef SELF_TEST - -/* used for timings */ -void driver1() -{ - uint8_t buf[256]; - uint32_t i; - uint32_t h=0; - time_t a,z; - - time(&a); - for (i=0; i<256; ++i) buf[i] = 'x'; - for (i=0; i<1; ++i) - { - h = hashlittle(&buf[0],1,h); - } - time(&z); - if (z-a > 0) printf("time %d %.8x\n", z-a, h); -} - -/* check that every input bit changes every output bit half the time */ -#define HASHSTATE 1 -#define HASHLEN 1 -#define MAXPAIR 60 -#define MAXLEN 70 -void driver2() -{ - uint8_t qa[MAXLEN+1], qb[MAXLEN+2], *a = &qa[0], *b = &qb[1]; - uint32_t c[HASHSTATE], d[HASHSTATE], i=0, j=0, k, l, m=0, z; - uint32_t e[HASHSTATE],f[HASHSTATE],g[HASHSTATE],h[HASHSTATE]; - uint32_t x[HASHSTATE],y[HASHSTATE]; - uint32_t hlen; - - printf("No more than %d trials should ever be needed \n",MAXPAIR/2); - for (hlen=0; hlen < MAXLEN; ++hlen) - { - z=0; - for (i=0; i>(8-j)); - c[0] = hashlittle(a, hlen, m); - b[i] ^= ((k+1)<>(8-j)); - d[0] = hashlittle(b, hlen, m); - /* check every bit is 1, 0, set, and not set at least once */ - for (l=0; lz) z=k; - if (k==MAXPAIR) - { - printf("Some bit didn't change: "); - printf("%.8x %.8x %.8x %.8x %.8x %.8x ", - e[0],f[0],g[0],h[0],x[0],y[0]); - printf("i %d j %d m %d len %d\n", i, j, m, hlen); - } - if (z==MAXPAIR) goto done; - } - } - } - done: - if (z < MAXPAIR) - { - printf("Mix success %2d bytes %2d initvals ",i,m); - printf("required %d trials\n", z/2); - } - } - printf("\n"); -} - -/* Check for reading beyond the end of the buffer and alignment problems */ -void driver3() -{ - uint8_t buf[MAXLEN+20], *b; - uint32_t len; - uint8_t q[] = "This is the time for all good men to come to the aid of their country..."; - uint32_t h; - uint8_t qq[] = "xThis is the time for all good men to come to the aid of their country..."; - uint32_t i; - uint8_t qqq[] = "xxThis is the time for all good men to come to the aid of their country..."; - uint32_t j; - uint8_t qqqq[] = "xxxThis is the time for all good men to come to the aid of their country..."; - uint32_t ref,x,y; - uint8_t *p; - - printf("Endianness. These lines should all be the same (for values filled in):\n"); - printf("%.8x %.8x %.8x\n", - hash_word((const uint32_t *)q, (sizeof(q)-1)/4, 13), - hash_word((const uint32_t *)q, (sizeof(q)-5)/4, 13), - hash_word((const uint32_t *)q, (sizeof(q)-9)/4, 13)); - p = q; - printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", - hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), - hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), - hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), - hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), - hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), - hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); - p = &qq[1]; - printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", - hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), - hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), - hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), - hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), - hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), - hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); - p = &qqq[2]; - printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", - hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), - hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), - hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), - hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), - hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), - hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); - p = &qqqq[3]; - printf("%.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x %.8x\n", - hashlittle(p, sizeof(q)-1, 13), hashlittle(p, sizeof(q)-2, 13), - hashlittle(p, sizeof(q)-3, 13), hashlittle(p, sizeof(q)-4, 13), - hashlittle(p, sizeof(q)-5, 13), hashlittle(p, sizeof(q)-6, 13), - hashlittle(p, sizeof(q)-7, 13), hashlittle(p, sizeof(q)-8, 13), - hashlittle(p, sizeof(q)-9, 13), hashlittle(p, sizeof(q)-10, 13), - hashlittle(p, sizeof(q)-11, 13), hashlittle(p, sizeof(q)-12, 13)); - printf("\n"); - - /* check that hashlittle2 and hashlittle produce the same results */ - i=47; j=0; - hashlittle2(q, sizeof(q), &i, &j); - if (hashlittle(q, sizeof(q), 47) != i) - printf("hashlittle2 and hashlittle mismatch\n"); - - /* check that hash_word2 and hash_word produce the same results */ - len = 0xdeadbeef; - i=47, j=0; - hash_word2(&len, 1, &i, &j); - if (hash_word(&len, 1, 47) != i) - printf("hash_word2 and hash_word mismatch %x %x\n", - i, hash_word(&len, 1, 47)); - - /* check hashlittle doesn't read before or after the ends of the string */ - for (h=0, b=buf+1; h<8; ++h, ++b) - { - for (i=0; i -#include -#include "config.h" - -/* Stolen mostly from: lookup3.c, by Bob Jenkins, May 2006, Public Domain. - * - * http://burtleburtle.net/bob/c/lookup3.c - */ - -/** - * hash - fast hash of an array for internal use - * @p: the array or pointer to first element - * @num: the number of elements to hash - * @base: the base number to roll into the hash (usually 0) - * - * The memory region pointed to by p is combined with the base to form - * a 32-bit hash. - * - * This hash will have different results on different machines, so is - * only useful for internal hashes (ie. not hashes sent across the - * network or saved to disk). - * - * It may also change with future versions: it could even detect at runtime - * what the fastest hash to use is. - * - * See also: hash_stable. - * - * Example: - * #include "hash/hash.h" - * #include - * #include - * - * // Simple demonstration: idential strings will have the same hash, but - * // two different strings will probably not. - * int main(int argc, char *argv[]) - * { - * uint32_t hash1, hash2; - * - * if (argc != 3) - * err(1, "Usage: %s ", argv[0]); - * - * hash1 = hash(argv[1], strlen(argv[1]), 0); - * hash2 = hash(argv[2], strlen(argv[2]), 0); - * printf("Hash is %s\n", hash1 == hash2 ? "same" : "different"); - * return 0; - * } - */ -#define hash(p, num, base) hash_any((p), (num)*sizeof(*(p)), (base)) - -/** - * hash_stable - hash of an array for external use - * @p: the array or pointer to first element - * @num: the number of elements to hash - * @base: the base number to roll into the hash (usually 0) - * - * The memory region pointed to by p is combined with the base to form - * a 32-bit hash. - * - * This hash will have the same results on different machines, so can - * be used for external hashes (ie. not hashes sent across the network - * or saved to disk). The results will not change in future versions - * of this package. - * - * Example: - * #include "hash/hash.h" - * #include - * #include - * - * int main(int argc, char *argv[]) - * { - * if (argc != 2) - * err(1, "Usage: %s ", argv[0]); - * - * printf("Hash stable result is %u\n", - * hash_stable(argv[1], strlen(argv[1]), 0)); - * return 0; - * } - */ -#define hash_stable(p, num, base) \ - hash_any_stable((p), (num)*sizeof(*(p)), (base)) - -/** - * hash_u32 - fast hash an array of 32-bit values for internal use - * @key: the array of uint32_t - * @num: the number of elements to hash - * @base: the base number to roll into the hash (usually 0) - * - * The array of uint32_t pointed to by @key is combined with the base - * to form a 32-bit hash. This is 2-3 times faster than hash() on small - * arrays, but the advantage vanishes over large hashes. - * - * This hash will have different results on different machines, so is - * only useful for internal hashes (ie. not hashes sent across the - * network or saved to disk). - */ -uint32_t hash_u32(const uint32_t *key, size_t num, uint32_t base); - -/* Our underlying operations. */ -uint32_t hash_any(const void *key, size_t length, uint32_t base); -uint32_t hash_any_stable(const void *key, size_t length, uint32_t base); - -/** - * hash_pointer - hash a pointer for internal use - * @p: the pointer value to hash - * @base: the base number to roll into the hash (usually 0) - * - * The pointer p (not what p points to!) is combined with the base to form - * a 32-bit hash. - * - * This hash will have different results on different machines, so is - * only useful for internal hashes (ie. not hashes sent across the - * network or saved to disk). - * - * Example: - * #include "hash/hash.h" - * - * // Code to keep track of memory regions. - * struct region { - * struct region *chain; - * void *start; - * unsigned int size; - * }; - * // We keep a simple hash table. - * static struct region *region_hash[128]; - * - * static void add_region(struct region *r) - * { - * unsigned int h = hash_pointer(r->start); - * - * r->chain = region_hash[h]; - * region_hash[h] = r->chain; - * } - * - * static void find_region(const void *start) - * { - * struct region *r; - * - * for (r = region_hash[hash_pointer(start)]; r; r = r->chain) - * if (r->start == start) - * return r; - * return NULL; - * } - */ -static inline uint32_t hash_pointer(const void *p, uint32_t base) -{ - if (sizeof(p) % sizeof(uint32_t) == 0) { - /* This convoluted union is the right way of aliasing. */ - union { - uint32_t u32[sizeof(p) / sizeof(uint32_t)]; - const void *p; - } u; - u.p = p; - return hash_u32(u.u32, sizeof(p) / sizeof(uint32_t), base); - } - return hash(&p, 1, base); -} -#endif /* HASH_H */ diff --git a/hash/test/run.c b/hash/test/run.c deleted file mode 100644 index 89ab0a9d..00000000 --- a/hash/test/run.c +++ /dev/null @@ -1,115 +0,0 @@ -#include "hash/hash.h" -#include "tap/tap.h" -#include "hash/hash.c" -#include -#include - -#define ARRAY_WORDS 5 - -int main(int argc, char *argv[]) -{ - unsigned int i, j, k; - uint32_t array[ARRAY_WORDS], val; - char array2[sizeof(array) + sizeof(uint32_t)]; - uint32_t results[256]; - - /* Initialize array. */ - for (i = 0; i < ARRAY_WORDS; i++) - array[i] = i; - - plan_tests(53); - - /* hash_stable is guaranteed. */ - ok1(hash_stable(array, ARRAY_WORDS, 0) == 0x13305f8c); - ok1(hash_stable(array, ARRAY_WORDS, 1) == 0x171abf74); - ok1(hash_stable(array, ARRAY_WORDS, 2) == 0x7646fcc7); - ok1(hash_stable(array, ARRAY_WORDS, 4) == 0xa758ed5); - ok1(hash_stable(array, ARRAY_WORDS, 8) == 0x2dedc2e4); - ok1(hash_stable(array, ARRAY_WORDS, 16) == 0x28e2076b); - ok1(hash_stable(array, ARRAY_WORDS, 32) == 0xb73091c5); - ok1(hash_stable(array, ARRAY_WORDS, 64) == 0x87daf5db); - ok1(hash_stable(array, ARRAY_WORDS, 128) == 0xa16dfe20); - ok1(hash_stable(array, ARRAY_WORDS, 256) == 0x300c63c3); - ok1(hash_stable(array, ARRAY_WORDS, 512) == 0x255c91fc); - ok1(hash_stable(array, ARRAY_WORDS, 1024) == 0x6357b26); - ok1(hash_stable(array, ARRAY_WORDS, 2048) == 0x4bc5f339); - ok1(hash_stable(array, ARRAY_WORDS, 4096) == 0x1301617c); - ok1(hash_stable(array, ARRAY_WORDS, 8192) == 0x506792c9); - ok1(hash_stable(array, ARRAY_WORDS, 16384) == 0xcd596705); - ok1(hash_stable(array, ARRAY_WORDS, 32768) == 0xa8713cac); - ok1(hash_stable(array, ARRAY_WORDS, 65536) == 0x94d9794); - ok1(hash_stable(array, ARRAY_WORDS, 131072) == 0xac753e8); - ok1(hash_stable(array, ARRAY_WORDS, 262144) == 0xcd8bdd20); - ok1(hash_stable(array, ARRAY_WORDS, 524288) == 0xd44faf80); - ok1(hash_stable(array, ARRAY_WORDS, 1048576) == 0x2547ccbe); - ok1(hash_stable(array, ARRAY_WORDS, 2097152) == 0xbab06dbc); - ok1(hash_stable(array, ARRAY_WORDS, 4194304) == 0xaac0e882); - ok1(hash_stable(array, ARRAY_WORDS, 8388608) == 0x443f48d0); - ok1(hash_stable(array, ARRAY_WORDS, 16777216) == 0xdff49fcc); - ok1(hash_stable(array, ARRAY_WORDS, 33554432) == 0x9ce0fd65); - ok1(hash_stable(array, ARRAY_WORDS, 67108864) == 0x9ddb1def); - ok1(hash_stable(array, ARRAY_WORDS, 134217728) == 0x86096f25); - ok1(hash_stable(array, ARRAY_WORDS, 268435456) == 0xe713b7b5); - ok1(hash_stable(array, ARRAY_WORDS, 536870912) == 0x5baeffc5); - ok1(hash_stable(array, ARRAY_WORDS, 1073741824) == 0xde874f52); - ok1(hash_stable(array, ARRAY_WORDS, 2147483648U) == 0xeca13b4e); - - /* Hash should be the same, indep of memory alignment. */ - val = hash(array, sizeof(array), 0); - for (i = 0; i < sizeof(uint32_t); i++) { - memcpy(array2 + i, array, sizeof(array)); - ok(hash(array2 + i, sizeof(array), 0) != val, - "hash matched at offset %i", i); - } - - /* Hash of random values should have random distribution: - * check one byte at a time. */ - for (i = 0; i < sizeof(uint32_t); i++) { - unsigned int lowest = -1U, highest = 0; - - memset(results, 0, sizeof(results)); - - for (j = 0; j < 256000; j++) { - for (k = 0; k < ARRAY_WORDS; k++) - array[k] = random(); - results[(hash(array, sizeof(array), 0) >> i*8)&0xFF]++; - } - - for (j = 0; j < 256; j++) { - if (results[j] < lowest) - lowest = results[j]; - if (results[j] > highest) - highest = results[j]; - } - /* Expect within 20% */ - ok(lowest > 800, "Byte %i lowest %i", i, lowest); - ok(highest < 1200, "Byte %i highest %i", i, highest); - diag("Byte %i, range %u-%u", i, lowest, highest); - } - - /* Hash of pointer values should also have random distribution. */ - for (i = 0; i < sizeof(uint32_t); i++) { - unsigned int lowest = -1U, highest = 0; - char *p = malloc(256000); - - memset(results, 0, sizeof(results)); - - for (j = 0; j < 256000; j++) - results[(hash_pointer(p + j, 0) >> i*8)&0xFF]++; - free(p); - - for (j = 0; j < 256; j++) { - if (results[j] < lowest) - lowest = results[j]; - if (results[j] > highest) - highest = results[j]; - } - /* Expect within 20% */ - ok(lowest > 800, "hash_pointer byte %i lowest %i", i, lowest); - ok(highest < 1200, "hash_pointer byte %i highest %i", - i, highest); - diag("hash_pointer byte %i, range %u-%u", i, lowest, highest); - } - - return exit_status(); -}