vp9_diag_downright_32x32_12bpp_c: 429.7
vp9_diag_downright_32x32_12bpp_sse2: 158.9
vp9_diag_downright_32x32_12bpp_ssse3: 144.6
vp9_diag_downright_32x32_12bpp_avx: 141.0
vp9_diag_downright_32x32_12bpp_avx2: 73.8
Almost 50% faster than avx implementation
---
libavcodec/x86/vp9dsp_init_16bpp.c|
Hi,
On Sun, Jun 25, 2017 at 10:42 AM, Ilia Valiakhmetov
wrote:
> vp9_diag_downright_32x32_12bpp_c: 429.7
> vp9_diag_downright_32x32_12bpp_sse2: 158.9
> vp9_diag_downright_32x32_12bpp_ssse3: 144.6
> vp9_diag_downright_32x32_12bpp_avx: 141.0
> vp9_diag_downright_32x32_12bpp_avx2: 73.8
>
> Almost 5