ruby-changes:4253
From: ko1@a...
Date: Tue, 11 Mar 2008 11:00:40 +0900 (JST)
Subject: [ruby-changes:4253] matz - Ruby:r15743 (trunk): * string.c (hash): replaced by MurmurHash described in
matz 2008-03-11 10:20:25 +0900 (Tue, 11 Mar 2008)
New Revision: 15743
Modified files:
trunk/ChangeLog
trunk/string.c
Log:
* string.c (hash): replaced by MurmurHash described in
<http://murmurhash.googlepages.com/>.
http://svn.ruby-lang.org/cgi-bin/viewvc.cgi/trunk/string.c?r1=15743&r2=15742&diff_format=u
http://svn.ruby-lang.org/cgi-bin/viewvc.cgi/trunk/ChangeLog?r1=15743&r2=15742&diff_format=u
Index: ChangeLog
===================================================================
--- ChangeLog (revision 15742)
+++ ChangeLog (revision 15743)
@@ -1,3 +1,8 @@
+Tue Mar 11 10:19:10 2008 Yukihiro Matsumoto <matz@r...>
+
+ * string.c (hash): replaced by MurmurHash described in
+ <http://murmurhash.googlepages.com/>.
+
Tue Mar 11 09:52:49 2008 Yukihiro Matsumoto <matz@r...>
* string.c (rb_str_comparable): empty strings in any encoding are
Index: string.c
===================================================================
--- string.c (revision 15742)
+++ string.c (revision 15743)
@@ -1685,122 +1685,41 @@
return rb_str_append(str1, str2);
}
-typedef unsigned int ub4; /* unsigned 4-byte quantities */
-typedef unsigned char ub1; /* unsigned 1-byte quantities */
+/* MurmurHash described in http://murmurhash.googlepages.com/ */
+unsigned int
+hash(const unsigned char * data, int len, unsigned int h)
+{
+ const unsigned int m = 0x7fd652ad;
+ const int r = 16;
-#define hashsize(n) ((ub4)1<<(n))
-#define hashmask(n) (hashsize(n)-1)
+ h += 0xdeadbeef;
-/*
---------------------------------------------------------------------
-mix -- mix 3 32-bit values reversibly.
-For every delta with one or two bits 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); \
-}
+ while(len >= 4) {
+ h += *(unsigned int *)data;
+ h *= m;
+ h ^= h >> r;
-/*
---------------------------------------------------------------------
-hash() -- hash a variable-length key into a 32-bit value
- k : the key (the unaligned variable-length array of bytes)
- len : 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. Every 1-bit and 2-bit delta achieves avalanche.
-About 6*len+35 instructions.
+ data += 4;
+ len -= 4;
+ }
-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.
+ switch(len) {
+ case 3:
+ h += data[2] << 16;
+ case 2:
+ h += data[1] << 8;
+ case 1:
+ h += data[0];
+ h *= m;
+ h ^= h >> r;
+ };
-If you are hashing n strings (ub1 **)k, do it like this:
- for (i=0, h=0; i<n; ++i) h = hash( k[i], len[i], h);
+ h *= m;
+ h ^= h >> 10;
+ h *= m;
+ h ^= h >> 17;
-By Bob Jenkins, 1996. bob_jenkins@b... You may use this
-code any way you wish, private, educational, or commercial. It's free.
-
-See http://burtleburtle.net/bob/hash/evahash.html
-Use for hash table lookup, or anything where one collision in 2^^32 is
-acceptable. Do NOT use for cryptographic purposes.
---------------------------------------------------------------------
-*/
-
-static ub4
-hash(const ub1 *k, ub4 length, ub4 initval)
- /* k: the key */
- /* length: the length of the key */
- /* initval: the previous hash, or an arbitrary value */
-{
- register 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;
+ return h;
}
int
--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/