From e0f4eafb689e75d66b34c40592024c1e698b0836 Mon Sep 17 00:00:00 2001 From: Andrew Mahone Date: Mon, 1 Jun 2009 13:40:30 +0000 Subject: Add Bob Jenkins' lookup3 32-bit and 64-bit hashes to pluginlib. git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21155 a1c6a512-1295-4272-9138-f99709370657 --- apps/plugins/lib/SOURCES | 1 + apps/plugins/lib/jhash.c | 699 +++++++++++++++++++++++++++++++++++++++++++++++ apps/plugins/lib/jhash.h | 67 +++++ 3 files changed, 767 insertions(+) create mode 100644 apps/plugins/lib/jhash.c create mode 100644 apps/plugins/lib/jhash.h diff --git a/apps/plugins/lib/SOURCES b/apps/plugins/lib/SOURCES index 21a35d478a..5a6abc7848 100644 --- a/apps/plugins/lib/SOURCES +++ b/apps/plugins/lib/SOURCES @@ -1,4 +1,5 @@ gcc-support.c +jhash.c oldmenuapi.c configfile.c fixedpoint.c diff --git a/apps/plugins/lib/jhash.c b/apps/plugins/lib/jhash.c new file mode 100644 index 0000000000..780d220408 --- /dev/null +++ b/apps/plugins/lib/jhash.c @@ -0,0 +1,699 @@ +/*************************************************************************** + * __________ __ ___. + * Open \______ \ ____ ____ | | _\_ |__ _______ ___ + * Source | _// _ \_/ ___\| |/ /| __ \ / _ \ \/ / + * Jukebox | | ( <_> ) \___| < | \_\ ( <_> > < < + * Firmware |____|_ /\____/ \___ >__|_ \|___ /\____/__/\_ \ + * \/ \/ \/ \/ \/ + * $Id$ + * + * Copyright (C) 2006 Bob Jenkins + * http://burtleburtle.net/bob/c/lookup3.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY + * KIND, either express or implied. + * + ****************************************************************************/ +/* +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 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. +*/ + +#include "jhash.h" + +/* +* My best guess at if you are big-endian or little-endian. This may +* need adjustment. +*/ +#if defined(ROCKBOX_LITTLE_ENDIAN) +# define HASH_LITTLE_ENDIAN 1 +# define HASH_BIG_ENDIAN 0 +#elif defined(ROCKBOX_BIG_ENDIAN) +# 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); \ +} + +/* + k: pointer to the key, an array of uint32_t + length: number of elements in the key + initval: an initialization value + returns the 32-bit hash +*/ +uint32_t hashw(const uint32_t *k, size_t length, uint32_t initval) +{ + 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; +} + + +/* +hashw2() -- same as hashw(), 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 hashword(). + k: pointer to the key, an array of uint32_t + length: number of elements in the key + pc, pb: pointers to primary and secondary initial values, also used to store + the hash results. +*/ +void hashw2 (const uint32_t *k, size_t length, uint32_t *pc, uint32_t *pb) +{ + 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; +} + + +/* +hashs() -- hash a variable-length key into a 32-bit value + k: pointer to the key, an array of bytes + length: number of elements in the key + initval: an initialization value + returns the 32-bit hash +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 */ + 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 if ((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 +#endif + { /* 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; +} + + +/* +hashs2: return 2 32-bit hash values + k: pointer to the key, an array of bytes + length: number of elements in the key + pc, pb: pointers to primary and secondary initial values, also used to store + the hash results. +* 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 hashs2(const void *key, size_t length, uint32_t *pc, uint32_t *pb) +{ + 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 + if (((u.i & 0x3) == 0)) { + const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ + + /* 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 */ + 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 if (((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 +#endif + { /* 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; +} diff --git a/apps/plugins/lib/jhash.h b/apps/plugins/lib/jhash.h new file mode 100644 index 0000000000..97d1ac3d93 --- /dev/null +++ b/apps/plugins/lib/jhash.h @@ -0,0 +1,67 @@ +/*************************************************************************** +* __________ __ ___. +* Open \______ \ ____ ____ | | _\_ |__ _______ ___ +* Source | _// _ \_/ ___\| |/ /| __ \ / _ \ \/ / +* Jukebox | | ( <_> ) \___| < | \_\ ( <_> > < < +* Firmware |____|_ /\____/ \___ >__|_ \|___ /\____/__/\_ \ +* \/ \/ \/ \/ \/ +* $Id$ +* +* Copyright (C) 2009 by Andrew Mahone +* +* jhash.c headers +* +* This program is free software; you can redistribute it and/or +* modify it under the terms of the GNU General Public License +* as published by the Free Software Foundation; either version 2 +* of the License, or (at your option) any later version. +* +* This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY +* KIND, either express or implied. +* +****************************************************************************/ + +#ifndef _LIB_JHASH_H_ +#define _LIB_JHASH_H_ +#include /* defines uint32_t etc */ +#include +#include + +/* +hashw() -- hash an array of uint32_t into a 32-bit value + k: pointer to the key, an array of uint32_t + length: number of elements in the key + initval: an initialization value + returns the 32-bit hash +*/ +uint32_t hashw(const uint32_t *k, size_t length, uint32_t initval); + +/* +hashw() -- hash an array of uint32_t into two 32-bit values +(*pc) will be the same as the return value from hashword(). + k: pointer to the key, an array of uint32_t + length: number of elements in the key + pc, pb: pointers to primary and secondary initial values, also used to store + the hash results. +*/ +void hashw2 (const uint32_t *k, size_t length, uint32_t *pc, uint32_t *pb); + +/* +hashs() -- hash an array of bytes into a 32-bit value + k: pointer to the key, an array of bytes + length: number of elements in the key + initval: an initialization value + returns the 32-bit hash +*/ +uint32_t hashs( const void *key, size_t length, uint32_t initval); + +/* +hashs2() -- hash an array of bytes into two 32-bit values + k: pointer to the key, an array of bytes + length: number of elements in the key + pc, pb: pointers to primary and secondary initial values, also used to store + the hash results. +*/ +void hashs2(const void *key, size_t length, uint32_t *pc, uint32_t *pb); +#endif + -- cgit v1.2.3