[SCM] libav/experimental: factor out common subexprssion (gcc of course is too stupid to do this ...) 5% faster avg_h264_chroma_mc2_mmx2() 10% faster put_h264_chroma_mc2_mmx2()
siretart at users.alioth.debian.org
siretart at users.alioth.debian.org
Sun Jun 30 15:56:10 UTC 2013
The following commit has been merged in the experimental branch:
commit 7c4fd7eb0c8d05041a879c5ad69319d6161a6bd8
Author: Michael Niedermayer <michaelni at gmx.at>
Date: Fri Feb 9 12:37:38 2007 +0000
factor out common subexprssion (gcc of course is too stupid to do this ...)
5% faster avg_h264_chroma_mc2_mmx2()
10% faster put_h264_chroma_mc2_mmx2()
Originally committed as revision 7898 to svn://svn.ffmpeg.org/ffmpeg/trunk
diff --git a/libavcodec/i386/dsputil_h264_template_mmx.c b/libavcodec/i386/dsputil_h264_template_mmx.c
index 4eefc8b..f85c992 100644
--- a/libavcodec/i386/dsputil_h264_template_mmx.c
+++ b/libavcodec/i386/dsputil_h264_template_mmx.c
@@ -265,8 +265,9 @@ static void H264_CHROMA_MC4_TMPL(uint8_t *dst/*align 4*/, uint8_t *src/*align 1*
#ifdef H264_CHROMA_MC2_TMPL
static void H264_CHROMA_MC2_TMPL(uint8_t *dst/*align 2*/, uint8_t *src/*align 1*/, int stride, int h, int x, int y)
{
- int CD=((1<<16)-1)*x*y + 8*y;
- int AB=((8<<16)-8)*x + 64 - CD;
+ int tmp = ((1<<16)-1)*x + 8;
+ int CD= tmp*y;
+ int AB= (tmp<<3) - CD;
asm volatile(
/* mm5 = {A,B,A,B} */
/* mm6 = {C,D,C,D} */
--
Libav/FFmpeg packaging
More information about the pkg-multimedia-commits
mailing list