|
|
|
/*
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
lookup2.c, by Bob Jenkins, December 1996, Public Domain.
|
|
|
|
hash(), hash2(), hash3, and mix() 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 has no warranty.
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
|
|
|
|
Note:
|
|
|
|
This code was ripped and modified by Shlomi Fish. The original can
|
|
|
|
be found at http://burtleburtle.net/bob/c/lookup2.c.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
|
|
|
|
#include "lookup2.h"
|
|
|
|
|
|
|
|
|
|
|
|
#define hashsize(n) ((ub4)1<<(n))
|
|
|
|
#define hashmask(n) (hashsize(n)-1)
|
|
|
|
|
|
|
|
/*
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
mix -- mix 3 32-bit values reversibly.
|
|
|
|
For every delta with one or two bit set, and the deltas of all three
|
|
|
|
high bits or all three low bits, whether the original value of a,b,c
|
|
|
|
is almost all zero or is uniformly distributed,
|
|
|
|
* If mix() is run forward or backward, at least 32 bits in a,b,c
|
|
|
|
have at least 1/4 probability of changing.
|
|
|
|
* If mix() is run forward, every bit of c will change between 1/3 and
|
|
|
|
2/3 of the time. (Well, 22/100 and 78/100 for some 2-bit deltas.)
|
|
|
|
mix() was built out of 36 single-cycle latency instructions in a
|
|
|
|
structure that could supported 2x parallelism, like so:
|
|
|
|
a -= b;
|
|
|
|
a -= c; x = (c>>13);
|
|
|
|
b -= c; a ^= x;
|
|
|
|
b -= a; x = (a<<8);
|
|
|
|
c -= a; b ^= x;
|
|
|
|
c -= b; x = (b>>13);
|
|
|
|
...
|
|
|
|
Unfortunately, superscalar Pentiums and Sparcs can't take advantage
|
|
|
|
of that parallelism. They've also turned some of those single-cycle
|
|
|
|
latency instructions into multi-cycle latency instructions. Still,
|
|
|
|
this is the fastest good hash I could find. There were about 2^^68
|
|
|
|
to choose from. I only looked at a billion or so.
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
#define mix(a,b,c) \
|
|
|
|
{ \
|
|
|
|
a -= b; a -= c; a ^= (c>>13); \
|
|
|
|
b -= c; b -= a; b ^= (a<<8); \
|
|
|
|
c -= a; c -= b; c ^= (b>>13); \
|
|
|
|
a -= b; a -= c; a ^= (c>>12); \
|
|
|
|
b -= c; b -= a; b ^= (a<<16); \
|
|
|
|
c -= a; c -= b; c ^= (b>>5); \
|
|
|
|
a -= b; a -= c; a ^= (c>>3); \
|
|
|
|
b -= c; b -= a; b ^= (a<<10); \
|
|
|
|
c -= a; c -= b; c ^= (b>>15); \
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
This works on all machines. hash2() is identical to hash() on
|
|
|
|
little-endian machines, except that the length has to be measured
|
|
|
|
in ub4s instead of bytes. It is much faster than hash(). It
|
|
|
|
requires
|
|
|
|
-- that the key be an array of ub4's, and
|
|
|
|
-- that all your machines have the same endianness, and
|
|
|
|
-- that the length be the number of ub4's in the key
|
|
|
|
--------------------------------------------------------------------
|
|
|
|
*/
|
|
|
|
|
|
|
|
ub4 freecell_solver_lookup2_hash_function(
|
|
|
|
ub1 *k, /* the key */
|
|
|
|
ub4 length, /* the length of the key */
|
|
|
|
ub4 initval /* the previous hash, or an arbitrary value */
|
|
|
|
)
|
|
|
|
{
|
|
|
|
ub4 a,b,c,len;
|
|
|
|
|
|
|
|
/* Set up the internal state */
|
|
|
|
len = length;
|
|
|
|
a = b = 0x9e3779b9; /* the golden ratio; an arbitrary value */
|
|
|
|
c = initval; /* the previous hash value */
|
|
|
|
|
|
|
|
/*---------------------------------------- handle most of the key */
|
|
|
|
while (len >= 12)
|
|
|
|
{
|
|
|
|
a += (k[0] +((ub4)k[1]<<8) +((ub4)k[2]<<16) +((ub4)k[3]<<24));
|
|
|
|
b += (k[4] +((ub4)k[5]<<8) +((ub4)k[6]<<16) +((ub4)k[7]<<24));
|
|
|
|
c += (k[8] +((ub4)k[9]<<8) +((ub4)k[10]<<16)+((ub4)k[11]<<24));
|
|
|
|
mix(a,b,c);
|
|
|
|
k += 12; len -= 12;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*------------------------------------- handle the last 11 bytes */
|
|
|
|
c += length;
|
|
|
|
switch(len) /* all the case statements fall through */
|
|
|
|
{
|
|
|
|
case 11: c+=((ub4)k[10]<<24);
|
|
|
|
case 10: c+=((ub4)k[9]<<16);
|
|
|
|
case 9 : c+=((ub4)k[8]<<8);
|
|
|
|
/* the first byte of c is reserved for the length */
|
|
|
|
case 8 : b+=((ub4)k[7]<<24);
|
|
|
|
case 7 : b+=((ub4)k[6]<<16);
|
|
|
|
case 6 : b+=((ub4)k[5]<<8);
|
|
|
|
case 5 : b+=k[4];
|
|
|
|
case 4 : a+=((ub4)k[3]<<24);
|
|
|
|
case 3 : a+=((ub4)k[2]<<16);
|
|
|
|
case 2 : a+=((ub4)k[1]<<8);
|
|
|
|
case 1 : a+=k[0];
|
|
|
|
/* case 0: nothing left to add */
|
|
|
|
}
|
|
|
|
mix(a,b,c);
|
|
|
|
/*-------------------------------------------- report the result */
|
|
|
|
return c;
|
|
|
|
}
|