Re: [FFmpeg-devel] [PATCH 5/5] avcodec/h264: add avx 8-bit h264_idct_dc_add

2017-04-06 Thread James Almer
On 4/6/2017 1:01 PM, James Darnley wrote: > On 2017-04-05 06:05, James Almer wrote: >> On 4/4/2017 10:53 PM, James Darnley wrote: >>> Haswell: >>> - 1.02x faster (405±0.7 vs. 397±0.8 decicycles) compared with mmxext >>> >>> Skylake-U: >>> - 1.06x faster (498±1.8 vs. 470±1.3 decicycles) compared w

Re: [FFmpeg-devel] [PATCH 5/5] avcodec/h264: add avx 8-bit h264_idct_dc_add

2017-04-06 Thread James Darnley
On 2017-04-05 06:05, James Almer wrote: > On 4/4/2017 10:53 PM, James Darnley wrote: >> Haswell: >> - 1.02x faster (405±0.7 vs. 397±0.8 decicycles) compared with mmxext >> >> Skylake-U: >> - 1.06x faster (498±1.8 vs. 470±1.3 decicycles) compared with mmxext >> --- >> libavcodec/x86/h264_idct.asm

Re: [FFmpeg-devel] [PATCH 5/5] avcodec/h264: add avx 8-bit h264_idct_dc_add

2017-04-04 Thread James Almer
On 4/4/2017 10:53 PM, James Darnley wrote: > Haswell: > - 1.02x faster (405±0.7 vs. 397±0.8 decicycles) compared with mmxext > > Skylake-U: > - 1.06x faster (498±1.8 vs. 470±1.3 decicycles) compared with mmxext > --- > libavcodec/x86/h264_idct.asm | 20 > libavcodec/x86/h2

[FFmpeg-devel] [PATCH 5/5] avcodec/h264: add avx 8-bit h264_idct_dc_add

2017-04-04 Thread James Darnley
Haswell: - 1.02x faster (405±0.7 vs. 397±0.8 decicycles) compared with mmxext Skylake-U: - 1.06x faster (498±1.8 vs. 470±1.3 decicycles) compared with mmxext --- libavcodec/x86/h264_idct.asm | 20 libavcodec/x86/h264dsp_init.c | 2 ++ 2 files changed, 22 insertions(+) di