[x264-devel] What about optimization based on Intel SSE4.1

[Bartosz Kulicki]

On Jan 21, 2008 1:05 PM, Tomas Carnecky <tom at dbservice.com> wrote:

> Jean-Pierre MORARD wrote:
> > Dear all,
> >
> > "There are 14 video-oriented instructions for accelerating subpixel
> > filtering, search, and 4x4 SAD (sum of absolute differences—a
> > performance-critical part of H.264 encoding)" - source:
> >
> http://arstechnica.com/news.ars/post/20070417-intel-details-penryn-performance-sse4.html
> >
> > Is there already someone working on that optimization ?
>
> I don't think so, but search the archives, IIRC there have been some
> discussions about the advantages/disadvantages of sse4.
>
> http://mailman.videolan.org/pipermail/x264-devel/2008-January/003955.html
>
> tom
> _______________________________________________
> x264-devel mailing list
> x264-devel at videolan.org
> http://mailman.videolan.org/listinfo/x264-devel
>


According to this

http://www.anandtech.com/cpuchipsets/intel/showdoc.aspx?i=3195&p=4

Intel's Penryn provides nice speedup in DIVX and TMPG encoding.

-- 
Bart
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.videolan.org/pipermail/x264-devel/attachments/20080122/00902ea0/attachment.htm