[FFmpeg-devel] [PATCH] lavfi/removegrain: add x86 and x86_64 SSE2 functions

[James Almer]

On 14/07/15 8:35 PM, James Darnley wrote:
> Speed of all modes increased by a factor between 7.4 and 19.8 largely depending
> on whether bytes are unpacked into words.  Modes 2, 3, and 4 have been sped-up
> by a factor of 43 (thanks quick sort!)
> 
> All modes are available on x86_64 but only modes 1, 10, 11, 12, 13, 14, 19, 20,
> 21, and 22 are available on x86 due to the number of SIMD registers used.
> 
> With a contribution from James Almer <jamrial at gmail.com>
> ---
>  LICENSE.md                            |    1 +
>  libavfilter/removegrain.h             |   40 ++
>  libavfilter/vf_removegrain.c          |   38 +-
>  libavfilter/x86/Makefile              |    4 +
>  libavfilter/x86/vf_removegrain.asm    | 1218 +++++++++++++++++++++++++++++++++
>  libavfilter/x86/vf_removegrain_init.c |   88 +++
>  6 files changed, 1370 insertions(+), 19 deletions(-)
>  create mode 100644 libavfilter/removegrain.h
>  create mode 100644 libavfilter/x86/vf_removegrain.asm
>  create mode 100644 libavfilter/x86/vf_removegrain_init.c

Assembly looks fine and works. Any improvements or additions can be done in subsequent
patches.

Paul: Any comment? If not then please push it.