generic-library/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Use sse2 variant of put_pixels16() for no_rnd also. Provides a minor speed

Browse Source 
increase to e.g. vc1, snow and mpeg decoding.

Patch by Eli Friedman <eli dot friedman gmail com>.

Originally committed as revision 25259 to svn://svn.ffmpeg.org/ffmpeg/trunk
This commit is contained in:
Eli Friedman
2010-09-29 15:34:43 +00:00
committed by Ronald S. Bultje
parent 77336a5e12
commit 329d689f75
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
libavcodec/x86/dsputil_mmx.c
View File

@@ -2820,6 +2820,7 @@ void dsputil_init_mmx(DSPContext* c, AVCodecContext *avctx)
if((mm_flags & AV_CPU_FLAG_SSE2) && !(mm_flags & AV_CPU_FLAG_3DNOW)){ if((mm_flags & AV_CPU_FLAG_SSE2) && !(mm_flags & AV_CPU_FLAG_3DNOW)){
// these functions are slower than mmx on AMD, but faster on Intel // these functions are slower than mmx on AMD, but faster on Intel
c->put_pixels_tab[0][0] = put_pixels16_sse2; c->put_pixels_tab[0][0] = put_pixels16_sse2;
c->put_no_rnd_pixels_tab[0][0] = put_pixels16_sse2;
c->avg_pixels_tab[0][0] = avg_pixels16_sse2; c->avg_pixels_tab[0][0] = avg_pixels16_sse2;
H264_QPEL_FUNCS(0, 0, sse2); H264_QPEL_FUNCS(0, 0, sse2);
} }