diff options
| author | Ronald S. Bultje <rsbultje@gmail.com> | 2014-01-20 15:30:22 -0500 |
|---|---|---|
| committer | Ronald S. Bultje <rsbultje@gmail.com> | 2014-01-24 19:25:25 -0500 |
| commit | d43efa68bd53eecc9cea6e1081b6fb163e45665c (patch) | |
| tree | ea15479d05ffbba87f9a24dc709c0ada7532f71f /libavcodec/x86/vp9dsp_init.c | |
| parent | baf47020cd2309e57f73883b703b5e6c36c7f4df (diff) | |
| download | ffmpeg-d43efa68bd53eecc9cea6e1081b6fb163e45665c.tar.gz | |
vp9/x86: 4x4 iadst SIMD (ssse3) variants.
Cycle measurements for intra itxfm_4x4_add on ped1080p.webm:
idct_idct: 66 -> 67 cycles (noise measurement)
idct_iadst: 199 -> 79 cycles
iadst_idct: 165 -> 70 cycles
iadst_iadst: 183 -> 82 cycles
Diffstat (limited to 'libavcodec/x86/vp9dsp_init.c')
| -rw-r--r-- | libavcodec/x86/vp9dsp_init.c | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/libavcodec/x86/vp9dsp_init.c b/libavcodec/x86/vp9dsp_init.c index a61b589b4e..612da8d2b7 100644 --- a/libavcodec/x86/vp9dsp_init.c +++ b/libavcodec/x86/vp9dsp_init.c @@ -166,7 +166,7 @@ itxfm_func(iadst, idct, size, opt); \ itxfm_func(idct, iadst, size, opt); \ itxfm_func(iadst, iadst, size, opt) -itxfm_func(idct, idct, 4, ssse3); +itxfm_funcs(4, ssse3); itxfm_funcs(8, ssse3); itxfm_funcs(8, avx); itxfm_funcs(16, ssse3); @@ -250,6 +250,9 @@ av_cold void ff_vp9dsp_init_x86(VP9DSPContext *dsp) init_subpel3(0, put, ssse3); init_subpel3(1, avg, ssse3); dsp->itxfm_add[TX_4X4][DCT_DCT] = ff_vp9_idct_idct_4x4_add_ssse3; + dsp->itxfm_add[TX_4X4][ADST_DCT] = ff_vp9_idct_iadst_4x4_add_ssse3; + dsp->itxfm_add[TX_4X4][DCT_ADST] = ff_vp9_iadst_idct_4x4_add_ssse3; + dsp->itxfm_add[TX_4X4][ADST_ADST] = ff_vp9_iadst_iadst_4x4_add_ssse3; if (ARCH_X86_64) { dsp->itxfm_add[TX_8X8][DCT_DCT] = ff_vp9_idct_idct_8x8_add_ssse3; dsp->itxfm_add[TX_8X8][ADST_DCT] = ff_vp9_idct_iadst_8x8_add_ssse3; |