From 1acd7d594c15aa491729c837ad3519d3469e620a Mon Sep 17 00:00:00 2001 From: "Ronald S. Bultje" Date: Mon, 18 Feb 2013 21:03:02 -0800 Subject: h264: integrate clear_blocks calls with IDCT. The non-intra-pcm branch in hl_decode_mb (simple, 8bpp) goes from 700 to 672 cycles, and the complete loop of decode_mb_cabac and hl_decode_mb (in the decode_slice loop) goes from 1759 to 1733 cycles on the clip tested (cathedral), i.e. almost 30 cycles per mb faster. Signed-off-by: Michael Niedermayer --- libavcodec/h264dsp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'libavcodec/h264dsp.c') diff --git a/libavcodec/h264dsp.c b/libavcodec/h264dsp.c index bb70d4e33e..da9e417e8e 100644 --- a/libavcodec/h264dsp.c +++ b/libavcodec/h264dsp.c @@ -66,8 +66,8 @@ void ff_h264dsp_init(H264DSPContext *c, const int bit_depth, const int chroma_fo #define FUNC(a, depth) a ## _ ## depth ## _c #define ADDPX_DSP(depth) \ - c->h264_add_pixels4 = FUNC(ff_h264_add_pixels4, depth);\ - c->h264_add_pixels8 = FUNC(ff_h264_add_pixels8, depth) + c->h264_add_pixels4_clear = FUNC(ff_h264_add_pixels4, depth);\ + c->h264_add_pixels8_clear = FUNC(ff_h264_add_pixels8, depth) if (bit_depth > 8 && bit_depth <= 16) { ADDPX_DSP(16); -- cgit v1.2.3