[FFmpeg-devel] [PATCH 5/7] Merged second and third inner loops
Michael Niedermayer
michaelni at gmx.at
Sat Mar 28 02:50:15 CET 2015
On Fri, Mar 27, 2015 at 04:51:46PM -0400, Tucker DiNapoli wrote:
> ---
> libpostproc/postprocess_template.c | 20 +-------------------
> 1 file changed, 1 insertion(+), 19 deletions(-)
iam not sure how you plan to optimize the code in SSE2/AVX2
if you merge the loops again into a long chain of operations which
are applied to an area roughly 8x8
before this you have 4 8x8 blocks you can use in AVX2 or SSE2
[...]
--
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB
He who knows, does not speak. He who speaks, does not know. -- Lao Tsu
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 181 bytes
Desc: Digital signature
URL: <https://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20150328/95c70829/attachment.asc>
More information about the ffmpeg-devel
mailing list