Speed up software CRC-32 computation by a factor of 1.5 to 3.

Use the interleaved method of Kadatch and Jenkins in order to make
use of pipelined instructions through multiple ALUs in a single
core. This also speeds up and simplifies the combination of CRCs,
and updates the functions to pre-calculate and use an operator for
CRC combination.

1 files changed, 11 insertions, 0 deletions

diff --git a/zutil.h b/zutil.h
index 60a0bca..14277bc 100644
--- a/zutil.h
+++ b/zutil.h
@@ -42,6 +42,17 @@ typedef unsigned short ush;
 typedef ush FAR ushf;
 typedef unsigned long  ulg;
 
+#if !defined(Z_U8) && !defined(Z_SOLO) && defined(STDC)
+#  include <limits.h>
+#  if (ULONG_MAX == 0xffffffffffffffffULL)
+#    define Z_U8 unsigned long
+#  elif (ULLONG_MAX == 0xffffffffffffffffULL)
+#    define Z_U8 unsigned long long
+#  elif (UINT_MAX == 0xffffffffffffffffULL)
+#    define Z_U8 unsigned
+#  endif
+#endif
+
 extern z_const char * const z_errmsg[10]; /* indexed by 2-zlib_error */
 /* (size given to avoid silly warnings with Visual C++) */