[FFmpeg-cvslog] swscale: remove AMD3DNOW "optimizations".

Reimar Döffinger Reimar.Doeffinger at gmx.de
Wed May 25 07:29:15 CEST 2011


On 25 May 2011, at 06:37, git at videolan.org (Ronald S. Bultje) wrote:
> ffmpeg | branch: master | Ronald S. Bultje <rsbultje at gmail.com> | Tue May 24 10:19:41 2011 -0400| [1dd4f4be5a82409a162b42b120fc5054fef9d899] | committer: Ronald S. Bultje
> 
> swscale: remove AMD3DNOW "optimizations".
> 
> The functions are identical to their MMX counterparts. Thus,
> pretending that swscale is highly optimized for AMD3DNOW
> extensions is a poorly executed practical joke at best.

WTF? Using prefetch and femms is now considered a practical joke?
Did anyone actually compare the speed of the MMX and the 3DNOW functions?!?


More information about the ffmpeg-cvslog mailing list