From 19fb234e4af1ff9f58ff2fdd604ac6f6bb87ad6b Mon Sep 17 00:00:00 2001 From: Jason Garrett-Glaser Date: Fri, 14 Jan 2011 21:34:25 +0000 Subject: H.264: split luma dc idct out and implement MMX/SSE2 versions About 2.5x the speed. NOTE: the way that the asm code handles large qmuls is a bit suboptimal. If x264-style dequant was used (separate shift and qmul values), it might be possible to get some extra speed. Originally committed as revision 26336 to svn://svn.ffmpeg.org/ffmpeg/trunk --- libavcodec/h264dsp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'libavcodec/h264dsp.c') diff --git a/libavcodec/h264dsp.c b/libavcodec/h264dsp.c index c01fc77c00..c3ee06d9df 100644 --- a/libavcodec/h264dsp.c +++ b/libavcodec/h264dsp.c @@ -282,6 +282,7 @@ void ff_h264dsp_init(H264DSPContext *c) c->h264_idct8_add4 = ff_h264_idct8_add4_c; c->h264_idct_add8 = ff_h264_idct_add8_c; c->h264_idct_add16intra= ff_h264_idct_add16intra_c; + c->h264_luma_dc_dequant_idct= ff_h264_luma_dc_dequant_idct_c; c->weight_h264_pixels_tab[0]= weight_h264_pixels16x16_c; c->weight_h264_pixels_tab[1]= weight_h264_pixels16x8_c; -- cgit v1.2.3