diff options
| author | Ilia Valiakhmetov <zakne0ne@gmail.com> | 2017-06-05 00:52:27 +0700 |
|---|---|---|
| committer | Ronald S. Bultje <rsbultje@gmail.com> | 2017-06-06 08:05:03 -0400 |
| commit | 73d9a9a6af5d00cfa9b98c7d9fc9abd0c734ba8e (patch) | |
| tree | 71bd6f602170a2baf41fd2166b73dadf1ddc4abf /libavcodec/x86/vp9dsp_init_16bpp.c | |
| parent | dc70ea8c193a08aebb1e0eeb2accc12322497ade (diff) | |
| download | ffmpeg-73d9a9a6af5d00cfa9b98c7d9fc9abd0c734ba8e.tar.gz | |
libavcodec/vp9: ipred_dl_32x32_16 avx2 implementation
vp9_diag_downleft_32x32_8bpp_c: 580.2
vp9_diag_downleft_32x32_8bpp_sse2: 75.6
vp9_diag_downleft_32x32_8bpp_ssse3: 73.7
vp9_diag_downleft_32x32_8bpp_avx: 72.7
vp9_diag_downleft_32x32_10bpp_c: 1101.2
vp9_diag_downleft_32x32_10bpp_sse2: 145.4
vp9_diag_downleft_32x32_10bpp_ssse3: 137.5
vp9_diag_downleft_32x32_10bpp_avx: 134.8
vp9_diag_downleft_32x32_10bpp_avx2: 94.0
vp9_diag_downleft_32x32_12bpp_c: 1108.5
vp9_diag_downleft_32x32_12bpp_sse2: 145.5
vp9_diag_downleft_32x32_12bpp_ssse3: 137.3
vp9_diag_downleft_32x32_12bpp_avx: 135.2
vp9_diag_downleft_32x32_12bpp_avx2: 94.0
~30% faster than avx implementation
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
Diffstat (limited to 'libavcodec/x86/vp9dsp_init_16bpp.c')
| -rw-r--r-- | libavcodec/x86/vp9dsp_init_16bpp.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/libavcodec/x86/vp9dsp_init_16bpp.c b/libavcodec/x86/vp9dsp_init_16bpp.c index 4576ff1692..d1b8fcdaef 100644 --- a/libavcodec/x86/vp9dsp_init_16bpp.c +++ b/libavcodec/x86/vp9dsp_init_16bpp.c @@ -52,6 +52,7 @@ decl_ipred_fns(dc, 16, mmxext, sse2); decl_ipred_fns(dc_top, 16, mmxext, sse2); decl_ipred_fns(dc_left, 16, mmxext, sse2); decl_ipred_fn(dl, 16, 16, avx2); +decl_ipred_fn(dl, 32, 16, avx2); #define decl_ipred_dir_funcs(type) \ decl_ipred_fns(type, 16, sse2, sse2); \ @@ -135,6 +136,7 @@ av_cold void ff_vp9dsp_init_16bpp_x86(VP9DSPContext *dsp) init_fpel_func(1, 1, 64, avg, _16, avx2); init_fpel_func(0, 1, 128, avg, _16, avx2); init_ipred_func(dl, DIAG_DOWN_LEFT, 16, 16, avx2); + init_ipred_func(dl, DIAG_DOWN_LEFT, 32, 16, avx2); } #endif /* HAVE_YASM */ |