RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-02-12 09:39:46 +00:00
Code Issues Projects Releases Wiki Activity

avcodec/h264: enable sse2 chroma deblock/loop filter functions

Browse Source 
Between 1.00 and 1.16 times faster on Intel Yorkfield Core 2 Quad.
Between 1.11 and 1.39 times faster on Intel Kaby Lake Pentium.
This commit is contained in:
James Darnley 2017-02-22 01:17:06 +01:00
parent cd893b9307
commit 33de0fee2c
2 changed files with 11 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
libavcodec/x86/h264_deblock.asm
View File

@ -1252,6 +1252,7 @@ RET
%endmacro ; DEBLOCK_CHROMA_XMM
DEBLOCK_CHROMA_XMM sse2
DEBLOCK_CHROMA_XMM avx
;-----------------------------------------------------------------------------

10
libavcodec/x86/h264dsp_init.c
View File

@ -304,6 +304,16 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
#if ARCH_X86_64
c->h264_h_loop_filter_luma_mbaff = ff_deblock_h_luma_mbaff_8_sse2;
#endif
c->h264_v_loop_filter_chroma = ff_deblock_v_chroma_8_sse2;
c->h264_v_loop_filter_chroma_intra = ff_deblock_v_chroma_intra_8_sse2;
if (chroma_format_idc <= 1) {
c->h264_h_loop_filter_chroma = ff_deblock_h_chroma_8_sse2;
c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma_intra_8_sse2;
} else {
c->h264_h_loop_filter_chroma = ff_deblock_h_chroma422_8_sse2;
c->h264_h_loop_filter_chroma_intra = ff_deblock_h_chroma422_intra_8_sse2;
}
}
if (EXTERNAL_SSSE3(cpu_flags)) {
c->biweight_h264_pixels_tab[0] = ff_h264_biweight_16_ssse3;