hash: make rotation more obvious

* modules/hash (Depends-on): Add bitrotate and stdint.
* lib/bitrotate.h (rotl_sz, rotr_sz): New functions.
* lib/hash.c (headers): Drop limits.h.  Add stdint.h.
(SIZE_MAX): Rely on headers for definition.
(hash_string) [USE_DIFF_HASH]: Use rotl_sz.
(raw_hasher): Use rotr_sz.
Suggested by Jim Meyering.

Signed-off-by: Eric Blake <ebb9@byu.net>

diff --git a/ChangeLog b/ChangeLog
index 36027fa..70de83e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,14 @@
 2009-06-18  Eric Blake  <ebb9@byu.net>
 
+       hash: make rotation more obvious
+       * modules/hash (Depends-on): Add bitrotate and stdint.
+       * lib/bitrotate.h (rotl_sz, rotr_sz): New functions.
+       * lib/hash.c (headers): Drop limits.h.  Add stdint.h.
+       (SIZE_MAX): Rely on headers for definition.
+       (hash_string) [USE_DIFF_HASH]: Use rotl_sz.
+       (raw_hasher): Use rotr_sz.
+       Suggested by Jim Meyering.
+
        hash: fix memory leak in last patch
        * lib/hash.c (hash_rehash): Avoid memory leak.
 

diff --git a/lib/bitrotate.h b/lib/bitrotate.h
index d4911d0..63f5d56 100644 (file)
--- a/lib/bitrotate.h
+++ b/lib/bitrotate.h
@@ -1,5 +1,5 @@
 /* bitrotate.h - Rotate bits in integers
-   Copyright (C) 2008 Free Software Foundation, Inc.
+   Copyright (C) 2008, 2009 Free Software Foundation, Inc.
 
    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
@@ -19,7 +19,9 @@
 #ifndef _GL_BITROTATE_H
 #define _GL_BITROTATE_H
 
+#include <limits.h>
 #include <stdint.h>
+#include <sys/types.h>
 
 #ifdef UINT64_MAX
 /* Given an unsigned 64-bit argument X, return the value corresponding
@@ -59,6 +61,24 @@ rotr32 (uint32_t x, int n)
   return ((x >> n) | (x << (32 - n))) & UINT32_MAX;
 }
 
+/* Given a size_t argument X, return the value corresponding
+   to rotating the bits N steps to the left.  N must be between 1 and
+   (CHAR_BIT * sizeof (size_t) - 1) inclusive.  */
+static inline size_t
+rotl_sz (size_t x, int n)
+{
+  return ((x << n) | (x >> ((CHAR_BIT * sizeof x) - n))) & SIZE_MAX;
+}
+
+/* Given a size_t argument X, return the value corresponding
+   to rotating the bits N steps to the right.  N must be between 1 to
+   (CHAR_BIT * sizeof (size_t) - 1) inclusive.  */
+static inline size_t
+rotr_sz (size_t x, int n)
+{
+  return ((x >> n) | (x << ((CHAR_BIT * sizeof x) - n))) & SIZE_MAX;
+}
+
 /* Given an unsigned 16-bit argument X, return the value corresponding
    to rotating the bits N steps to the left.  N must be between 1 to
    15 inclusive, but on most relevant targets N can also be 0 and 16

diff --git a/lib/hash.c b/lib/hash.c
index dc4a1b9..a81eec7 100644 (file)
--- a/lib/hash.c
+++ b/lib/hash.c
@@ -26,9 +26,11 @@
 #include <config.h>
 
 #include "hash.h"
+
+#include "bitrotate.h"
 #include "xalloc.h"
 
-#include <limits.h>
+#include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
 
@@ -42,10 +44,6 @@
 # endif
 #endif
 
-#ifndef SIZE_MAX
-# define SIZE_MAX ((size_t) -1)
-#endif
-
 struct hash_entry
   {
     void *data;
@@ -399,10 +397,8 @@ hash_do_for_each (const Hash_table *table, Hash_processor processor,
 size_t
 hash_string (const char *string, size_t n_buckets)
 {
-# define ROTATE_LEFT(Value, Shift) \
-  ((Value) << (Shift) | (Value) >> ((sizeof (size_t) * CHAR_BIT) - (Shift)))
 # define HASH_ONE_CHAR(Value, Byte) \
-  ((Byte) + ROTATE_LEFT (Value, 7))
+  ((Byte) + rotl_sz (Value, 7))
 
   size_t value = 0;
   unsigned char ch;
@@ -411,7 +407,6 @@ hash_string (const char *string, size_t n_buckets)
     value = HASH_ONE_CHAR (value, ch);
   return value % n_buckets;
 
-# undef ROTATE_LEFT
 # undef HASH_ONE_CHAR
 }
 
@@ -488,8 +483,7 @@ raw_hasher (const void *data, size_t n)
      bits are 0.  As this tends to give poorer performance with small
      tables, we rotate the pointer value before performing division,
      in an attempt to improve hash quality.  */
-  size_t val = (size_t) data;
-  val = ((val >> 3) | (val << (CHAR_BIT * sizeof val - 3))) & SIZE_MAX;
+  size_t val = rotr_sz ((size_t) data, 3);
   return val % n;
 }
 

diff --git a/modules/hash b/modules/hash
index 05ac440..75a99da 100644 (file)
--- a/modules/hash
+++ b/modules/hash
@@ -7,7 +7,9 @@ lib/hash.h
 m4/hash.m4
 
 Depends-on:
+bitrotate
 stdbool
+stdint
 xalloc
 
 configure.ac: