LM
/
u-boot
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

zlib: Optimize decompression 

This patch optimizes the direct copy procedure.
Uses get_unaligned() but only in one place.
The copy loop just above this one can also use this
optimization, but I havn't done so as I have not tested if it
is a win there too.
On my MPC8321 this is about 17% faster on my JFFS2 root FS
than the original. No speed test has been performed in u-boot.

Size increase on ppc: 484 bytes

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Acked-by: Peter Korsgaard <jacmet@sunsite.dk>
This commit is contained in:
Joakim Tjernlund 2009-11-19 13:22:44 +01:00 committed by Wolfgang Denk
parent 20dde48bca
commit cd514aeb99
1 changed files with 44 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
lib_generic/zlib.c
View File

@ -26,8 +26,10 @@
#define ZUTIL_H #define ZUTIL_H
#define ZLIB_INTERNAL #define ZLIB_INTERNAL
#include "u-boot/zlib.h"
#include <common.h> #include <common.h>
#include <compiler.h>
#include <asm/unaligned.h>
#include "u-boot/zlib.h"
/* To avoid a build time warning */ /* To avoid a build time warning */
#ifdef STDC #ifdef STDC
#include <malloc.h> #include <malloc.h>
@ -400,6 +402,7 @@ void inflate_fast OF((z_streamp strm, unsigned start));
*/ */
#define OFF 1 #define OFF 1
#define PUP(a) *++(a) #define PUP(a) *++(a)
#define UP_UNALIGNED(a) get_unaligned(++(a))
/* /*
Decode literal, length, and distance codes and write out the resulting Decode literal, length, and distance codes and write out the resulting
@ -616,18 +619,47 @@ unsigned start; /* inflate()'s starting value for strm->avail_out */
} }
} }
else { else {
unsigned short *sout;
unsigned long loops;
from = out - dist; /* copy direct from output */ from = out - dist; /* copy direct from output */
do { /* minimum length is three */ /* minimum length is three */
PUP(out) = PUP(from); /* Align out addr */
PUP(out) = PUP(from); if (!((long)(out - 1 + OFF) & 1)) {
PUP(out) = PUP(from); PUP(out) = PUP(from);
len -= 3; len--;
} while (len > 2); }
if (len) { sout = (unsigned short *)(out - OFF);
PUP(out) = PUP(from); if (dist > 2 ) {
if (len > 1) unsigned short *sfrom;
PUP(out) = PUP(from);
} sfrom = (unsigned short *)(from - OFF);
loops = len >> 1;
do
PUP(sout) = UP_UNALIGNED(sfrom);
while (--loops);
out = (unsigned char *)sout + OFF;
from = (unsigned char *)sfrom + OFF;
} else { /* dist == 1 or dist == 2 */
unsigned short pat16;
pat16 = *(sout-2+2*OFF);
if (dist == 1)
#if defined(__BIG_ENDIAN)
pat16 = (pat16 & 0xff) | ((pat16 & 0xff ) << 8);
#elif defined(__LITTLE_ENDIAN)
pat16 = (pat16 & 0xff00) | ((pat16 & 0xff00 ) >> 8);
#else
#error __BIG_ENDIAN nor __LITTLE_ENDIAN is defined
#endif
loops = len >> 1;
do
PUP(sout) = pat16;
while (--loops);
out = (unsigned char *)sout + OFF;
}
if (len & 1)
PUP(out) = PUP(from);
} }
} }
else if ((op & 64) == 0) { /* 2nd level distance code */ else if ((op & 64) == 0) { /* 2nd level distance code */