[FFmpeg-devel] [PATCH] x86/hevc_mc: optimize AVX2 mc functions

[Christophe Gisquet]

Hi,

2015-02-12 7:29 GMT+01:00 James Almer <jamrial at gmail.com>:
> Before
> 40766 decicycles in ff_hevc_put_hevc_qpel_h64_8_avx2, 8192 runs, 0 skips
>
> After
> 37975 decicycles in ff_hevc_put_hevc_qpel_h64_8_avx2, 8192 runs, 0 skips

Looks straightforward. But now I understand why we declare using 11
xmm regs in some places, which impacts a patch that has been reviewed
and needs updating.

-- 
Christophe