[Zlib-devel] [PING] Improve longest_match performance

[Andreas Krebbel]

Hi,

I've verified that the attached patch helps code generation a lot with zlib 1.2.8 and GCC head (4.9).

The patch just does some very simple type promotions in order to help target platforms where some of
the zero/sign extend instructions are missing or slow.

Please consider the patch for inclusion into the next release. Thanks!

Bye,

-Andreas-



Index: zlib/deflate.c
===================================================================
--- zlib.orig/deflate.c 2013-05-03 13:29:35.648710587 +0200
+++ zlib/deflate.c      2013-05-03 13:29:35.678710589 +0200
@@ -1145,15 +1145,16 @@ local void lm_init (s)
 /* For 80x86 and 680x0, an optimized version will be provided in match.asm or
  * match.S. The code will be functionally equivalent.
  */
-local uInt longest_match(s, cur_match)
+local uInt longest_match(s, pcur_match)
     deflate_state *s;
-    IPos cur_match;                             /* current match */
+    IPos pcur_match;                             /* current match */
 {
+    ptrdiff_t cur_match = pcur_match; /* extend to pointer width */
     unsigned chain_length = s->max_chain_length;/* max hash chain length */
     register Bytef *scan = s->window + s->strstart; /* current string */
     register Bytef *match;                       /* matched string */
     register int len;                           /* length of current match */
-    int best_len = s->prev_length;              /* best match length so far */
+    ptrdiff_t best_len = s->prev_length;              /* best match length so far */
     int nice_match = s->nice_match;             /* stop if match long enough */
     IPos limit = s->strstart > (IPos)MAX_DIST(s) ?
         s->strstart - (IPos)MAX_DIST(s) : NIL;
@@ -1168,12 +1169,12 @@ local uInt longest_match(s, cur_match)
      * Try with and without -DUNALIGNED_OK to check.
      */
     register Bytef *strend = s->window + s->strstart + MAX_MATCH - 1;
-    register ush scan_start = *(ushf*)scan;
-    register ush scan_end   = *(ushf*)(scan+best_len-1);
+    register uInt scan_start = *(ushf*)scan;
+    register uInt scan_end   = *(ushf*)(scan+best_len-1);
 #else
     register Bytef *strend = s->window + s->strstart + MAX_MATCH;
-    register Byte scan_end1  = scan[best_len-1];
-    register Byte scan_end   = scan[best_len];
+    register uInt scan_end1  = scan[best_len-1];
+    register uInt scan_end   = scan[best_len];
 #endif

     /* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16.