replace lookup3 with MurmurHash3murmur3

See http://code.google.com/p/smhasher/wiki/MurmurHash3

Performance quotes from there are 2.5 times what lookup3 can do, for
32 bit variant, which is what we use:

Lookup3_x86_32       - 1234 mb/sec
Lookup3_x64_32       - 1265 mb/sec

MurmurHash3_x86_32   - 3105 mb/sec

New files are released to the public domain, keeping them that way.

6 files changed, 404 insertions, 803 deletions

diff --git a/src/Makefile.am b/src/Makefile.am
index 2695614..1900b5a 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -45,8 +45,8 @@ qxl_drv_la_SOURCES =				\
 	qxl_mem.c				\
 	mspace.c				\
 	mspace.h				\
-	lookup3.c				\
-	lookup3.h				\
+	murmurhash3.c				\
+	murmurhash3.h				\
 	qxl_cursor.c
 endif
 
@@ -80,7 +80,7 @@ spiceqxl_drv_la_SOURCES =				\
 	qxl_mem.c				\
 	mspace.c				\
 	mspace.h				\
-	lookup3.c				\
-	lookup3.h				\
+	murmurhash3.c				\
+	murmurhash3.h				\
 	qxl_cursor.c
 endif
diff --git a/src/lookup3.c b/src/lookup3.c
deleted file mode 100644
index b37ca51..0000000
--- a/src/lookup3.c
+++ /dev/null
@@ -1,769 +0,0 @@
-/*
--------------------------------------------------------------------------------
-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 <stdio.h>      /* defines printf for tests */
-#include <time.h>       /* defines time_t for timings in the test */
-#include "lookup3.h"
-#ifdef linux
-# include <endian.h>    /* 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 hashword() is identical to hashlittle() on little-endian
- machines, and identical to hashbig() on big-endian machines,
- except that the length has to be measured in uint32_ts rather than in
- bytes.  hashlittle() is more complicated than hashword() only because
- hashlittle() has to dance around fitting the key bytes into registers.
---------------------------------------------------------------------
-*/
-uint32_t hashword(
-    const uint32_t *k,                   /* the key, an array of uint32_t values */
-    size_t          length,               /* the length of the key, in uint32_ts */
-    uint32_t        initval)         /* the previous hash, or an arbitrary value */
-{
-  uint32_t a,b,c;
-
-  /* Set up the internal state */
-  a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval;
-
-  /*------------------------------------------------- handle most of the key */
-  while (length > 3)
-  {
-    a += k[0];
-    b += k[1];
-    c += k[2];
-    mix(a,b,c);
-    length -= 3;
-    k += 3;
-  }
-
-  /*------------------------------------------- handle the last 3 uint32_t's */
-  switch(length)                     /* all the case statements fall through */
-  { 
-  case 3 : c+=k[2];
-  case 2 : b+=k[1];
-  case 1 : a+=k[0];
-    final(a,b,c);
-  case 0:     /* case 0: nothing left to add */
-    break;
-  }
-  /*------------------------------------------------------ report the result */
-  return c;
-}
-
-
-/*
---------------------------------------------------------------------
-hashword2() -- same as hashword(), 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().
---------------------------------------------------------------------
-*/
-void hashword2 (
-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;
-}
-
-
-/*
--------------------------------------------------------------------------------
-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<n; ++i) h = hashlittle( k[i], len[i], h);
-
-By Bob Jenkins, 2006.  bob_jenkins@burtleburtle.net.  You may use this
-code any way you wish, private, educational, or commercial.  It's free.
-
-Use for hash table lookup, or anything where one collision in 2^^32 is
-acceptable.  Do NOT use for cryptographic purposes.
--------------------------------------------------------------------------------
-*/
-
-uint32_t hashlittle( const void *key, size_t length, uint32_t initval)
-{
-  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) + initval;
-
-  u.ptr = key;
-  if (HASH_LITTLE_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]&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;
-}
-
-
-/*
- * 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 */
-#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]&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;
-}
-
-
-
-/*
- * hashbig():
- * This is the same as hashword() on big-endian machines.  It is different
- * from hashlittle() on all machines.  hashbig() takes advantage of
- * big-endian byte ordering. 
- */
-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;
-}
-
diff --git a/src/lookup3.h b/src/lookup3.h
deleted file mode 100644
index 50c1cf4..0000000
--- a/src/lookup3.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __LOOKUP3_H
-#define __LOOKUP3_H
-
-#if defined(__GNUC__) || defined(__sun)
-
-#include <stdint.h>
-
-#else
-
-#ifdef QXLDD
-#include <windef.h>
-#include "os_dep.h"
-#else
-#include <stddef.h>
-#include <basetsd.h>
-#endif
-
-typedef UINT32 uint32_t;
-typedef UINT16 uint16_t;
-typedef UINT8 uint8_t;
-
-#endif
-
-uint32_t hashlittle( const void *key, size_t length, uint32_t initval);
-
-#endif
diff --git a/src/murmurhash3.c b/src/murmurhash3.c
new file mode 100644
index 0000000..afb7d7d
--- /dev/null
+++ b/src/murmurhash3.c
@@ -0,0 +1,357 @@
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+// Note - The x86 and x64 versions do _not_ produce the same results, as the
+// algorithms are optimized for their respective platforms. You can still
+// compile and run any of them on any platform, but your performance with the
+// non-native version will be less than optimal.
+
+#include "murmurhash3.h"
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+#define FORCE_INLINE	__forceinline
+
+#include <stdlib.h>
+
+#define ROTL32(x,y)	_rotl(x,y)
+#define ROTL64(x,y)	_rotl64(x,y)
+
+#define BIG_CONSTANT(x) (x)
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#define	FORCE_INLINE __attribute__((always_inline))
+
+static inline uint32_t rotl32 ( uint32_t x, int8_t r )
+{
+  return (x << r) | (x >> (32 - r));
+}
+
+static inline uint64_t rotl64 ( uint64_t x, int8_t r )
+{
+  return (x << r) | (x >> (64 - r));
+}
+
+#define	ROTL32(x,y)	rotl32(x,y)
+#define ROTL64(x,y)	rotl64(x,y)
+
+#define BIG_CONSTANT(x) (x##LLU)
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+// Block read - if your platform needs to do endian-swapping or can only
+// handle aligned reads, do the conversion here
+
+static FORCE_INLINE uint32_t getblock_32 ( const uint32_t * p, int i )
+{
+  return p[i];
+}
+
+static FORCE_INLINE uint64_t getblock_64 ( const uint64_t * p, int i )
+{
+  return p[i];
+}
+
+//-----------------------------------------------------------------------------
+// Finalization mix - force all bits of a hash block to avalanche
+
+static FORCE_INLINE uint32_t fmix_32 ( uint32_t h )
+{
+  h ^= h >> 16;
+  h *= 0x85ebca6b;
+  h ^= h >> 13;
+  h *= 0xc2b2ae35;
+  h ^= h >> 16;
+
+  return h;
+}
+
+//----------
+
+static FORCE_INLINE uint64_t fmix_64 ( uint64_t k )
+{
+  k ^= k >> 33;
+  k *= BIG_CONSTANT(0xff51afd7ed558ccd);
+  k ^= k >> 33;
+  k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53);
+  k ^= k >> 33;
+
+  return k;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_32 ( const void * key, int len,
+                          uint32_t seed, void * out )
+{
+  const uint8_t * data = (const uint8_t*)key;
+  const int nblocks = len / 4;
+
+  uint32_t h1 = seed;
+
+  uint32_t c1 = 0xcc9e2d51;
+  uint32_t c2 = 0x1b873593;
+
+  const uint32_t * blocks;
+  const uint8_t * tail;
+
+  uint32_t k1;
+
+  int i;
+  //----------
+  // body
+
+  blocks = (const uint32_t *)(data + nblocks*4);
+
+  for(i = -nblocks; i; i++)
+  {
+    k1 = getblock_32(blocks,i);
+
+    k1 *= c1;
+    k1 = ROTL32(k1,15);
+    k1 *= c2;
+
+    h1 ^= k1;
+    h1 = ROTL32(h1,13);
+    h1 = h1*5+0xe6546b64;
+  }
+
+  //----------
+  // tail
+
+  tail = (const uint8_t*)(data + nblocks*4);
+
+  k1 = 0;
+
+  switch(len & 3)
+  {
+  case 3: k1 ^= tail[2] << 16;
+  case 2: k1 ^= tail[1] << 8;
+  case 1: k1 ^= tail[0];
+          k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+  };
+
+  //----------
+  // finalization
+
+  h1 ^= len;
+
+  h1 = fmix_32(h1);
+
+  *(uint32_t*)out = h1;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_128 ( const void * key, const int len,
+                           uint32_t seed, void * out )
+{
+  const uint8_t * data = (const uint8_t*)key;
+  const int nblocks = len / 16;
+
+  uint32_t h1 = seed;
+  uint32_t h2 = seed;
+  uint32_t h3 = seed;
+  uint32_t h4 = seed;
+
+  uint32_t c1 = 0x239b961b;
+  uint32_t c2 = 0xab0e9789;
+  uint32_t c3 = 0x38b34ae5;
+  uint32_t c4 = 0xa1e38b93;
+
+  uint32_t k1;
+  uint32_t k2;
+  uint32_t k3;
+  uint32_t k4;
+
+  const uint32_t * blocks;
+  const uint8_t * tail;
+
+  int i;
+
+  //----------
+  // body
+
+  blocks = (const uint32_t *)(data + nblocks*16);
+
+  for(i = -nblocks; i; i++)
+  {
+    k1 = getblock_32(blocks,i*4+0);
+    k2 = getblock_32(blocks,i*4+1);
+    k3 = getblock_32(blocks,i*4+2);
+    k4 = getblock_32(blocks,i*4+3);
+
+    k1 *= c1; k1  = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+
+    h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b;
+
+    k2 *= c2; k2  = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+
+    h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747;
+
+    k3 *= c3; k3  = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+
+    h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35;
+
+    k4 *= c4; k4  = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+
+    h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17;
+  }
+
+  //----------
+  // tail
+
+  tail = (const uint8_t*)(data + nblocks*16);
+
+  k1 = 0;
+  k2 = 0;
+  k3 = 0;
+  k4 = 0;
+
+  switch(len & 15)
+  {
+  case 15: k4 ^= tail[14] << 16;
+  case 14: k4 ^= tail[13] << 8;
+  case 13: k4 ^= tail[12] << 0;
+           k4 *= c4; k4  = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+
+  case 12: k3 ^= tail[11] << 24;
+  case 11: k3 ^= tail[10] << 16;
+  case 10: k3 ^= tail[ 9] << 8;
+  case  9: k3 ^= tail[ 8] << 0;
+           k3 *= c3; k3  = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+
+  case  8: k2 ^= tail[ 7] << 24;
+  case  7: k2 ^= tail[ 6] << 16;
+  case  6: k2 ^= tail[ 5] << 8;
+  case  5: k2 ^= tail[ 4] << 0;
+           k2 *= c2; k2  = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+
+  case  4: k1 ^= tail[ 3] << 24;
+  case  3: k1 ^= tail[ 2] << 16;
+  case  2: k1 ^= tail[ 1] << 8;
+  case  1: k1 ^= tail[ 0] << 0;
+           k1 *= c1; k1  = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+  };
+
+  //----------
+  // finalization
+
+  h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len;
+
+  h1 += h2; h1 += h3; h1 += h4;
+  h2 += h1; h3 += h1; h4 += h1;
+
+  h1 = fmix_32(h1);
+  h2 = fmix_32(h2);
+  h3 = fmix_32(h3);
+  h4 = fmix_32(h4);
+
+  h1 += h2; h1 += h3; h1 += h4;
+  h2 += h1; h3 += h1; h4 += h1;
+
+  ((uint32_t*)out)[0] = h1;
+  ((uint32_t*)out)[1] = h2;
+  ((uint32_t*)out)[2] = h3;
+  ((uint32_t*)out)[3] = h4;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x64_128 ( const void * key, const int len,
+                           const uint32_t seed, void * out )
+{
+  const uint8_t * data = (const uint8_t*)key;
+  const int nblocks = len / 16;
+
+  uint64_t h1 = seed;
+  uint64_t h2 = seed;
+
+  uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
+  uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f);
+
+  const uint64_t * blocks;
+  const uint8_t * tail;
+
+  uint64_t k1;
+  uint64_t k2;
+
+  int i;
+  //----------
+  // body
+
+  blocks = (const uint64_t *)(data);
+
+  for(i = 0; i < nblocks; i++)
+  {
+    k1 = getblock_64(blocks,i*2+0);
+    k2 = getblock_64(blocks,i*2+1);
+
+    k1 *= c1; k1  = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
+
+    h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;
+
+    k2 *= c2; k2  = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
+
+    h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
+  }
+
+  //----------
+  // tail
+
+  tail = (const uint8_t*)(data + nblocks*16);
+
+  k1 = 0;
+  k2 = 0;
+
+  switch(len & 15)
+  {
+  case 15: k2 ^= ((uint64_t)tail[14]) << 48;
+  case 14: k2 ^= ((uint64_t)tail[13]) << 40;
+  case 13: k2 ^= ((uint64_t)tail[12]) << 32;
+  case 12: k2 ^= ((uint64_t)tail[11]) << 24;
+  case 11: k2 ^= ((uint64_t)tail[10]) << 16;
+  case 10: k2 ^= ((uint64_t)tail[ 9]) << 8;
+  case  9: k2 ^= ((uint64_t)tail[ 8]) << 0;
+           k2 *= c2; k2  = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
+
+  case  8: k1 ^= ((uint64_t)tail[ 7]) << 56;
+  case  7: k1 ^= ((uint64_t)tail[ 6]) << 48;
+  case  6: k1 ^= ((uint64_t)tail[ 5]) << 40;
+  case  5: k1 ^= ((uint64_t)tail[ 4]) << 32;
+  case  4: k1 ^= ((uint64_t)tail[ 3]) << 24;
+  case  3: k1 ^= ((uint64_t)tail[ 2]) << 16;
+  case  2: k1 ^= ((uint64_t)tail[ 1]) << 8;
+  case  1: k1 ^= ((uint64_t)tail[ 0]) << 0;
+           k1 *= c1; k1  = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
+  };
+
+  //----------
+  // finalization
+
+  h1 ^= len; h2 ^= len;
+
+  h1 += h2;
+  h2 += h1;
+
+  h1 = fmix_64(h1);
+  h2 = fmix_64(h2);
+
+  h1 += h2;
+  h2 += h1;
+
+  ((uint64_t*)out)[0] = h1;
+  ((uint64_t*)out)[1] = h2;
+}
+
+//-----------------------------------------------------------------------------
diff --git a/src/murmurhash3.h b/src/murmurhash3.h
new file mode 100644
index 0000000..2a35de1
--- /dev/null
+++ b/src/murmurhash3.h
@@ -0,0 +1,39 @@
+// Source: http://code.google.com/p/smhasher/wiki/MurmurHash3
+
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH3_H_
+#define _MURMURHASH3_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_32  ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out );
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH3_H_
diff --git a/src/qxl_image.c b/src/qxl_image.c
index aceac1e..8e5127d 100644
--- a/src/qxl_image.c
+++ b/src/qxl_image.c
@@ -28,7 +28,7 @@
 #include <assert.h>
 #include <stdlib.h>
 #include "qxl.h"
-#include "lookup3.h"
+#include "murmurhash3.h"
 
 typedef struct image_info_t image_info_t;
 
@@ -46,7 +46,7 @@ static unsigned int
 hash_and_copy (const uint8_t *src, int src_stride,
 	       uint8_t *dest, int dest_stride,
 	       int bytes_per_pixel, int width, int height,
-	       unsigned int hash)
+	       uint32_t hash)
 {
     int i;
   
@@ -59,7 +59,7 @@ hash_and_copy (const uint8_t *src, int src_stride,
 	if (dest)
 	    memcpy (dest_line, src_line, n_bytes);
 
-	hash = hashlittle (src_line, n_bytes, hash);
+	MurmurHash3_x86_32 (src_line, n_bytes, hash, &hash);
     }
 
     return hash;
@@ -129,7 +129,7 @@ qxl_image_create (qxl_screen_t *qxl, const uint8_t *data,
 		  int x, int y, int width, int height,
 		  int stride, int Bpp, Bool fallback)
 {
-	unsigned int hash;
+	uint32_t hash;
 	image_info_t *info;
 	struct QXLImage *image;
 	struct QXLDataChunk *head;