On Mon, 1 Nov 2004, Stefan Fendt wrote:
> On Sat, 30 Oct 2004 00:33:40 -0700 (PDT)
> "Steven M. Schultz" <[EMAIL PROTECTED]> wrote:
>
> > That does make one curious, doesn't it, why the MMX SAD code in
> > yuvdenoise (which was copied/adapted from the mpeg2enc routines)
>
> That one in yuvdenoise wasn't ... I hacked it myself. So it doesn't make me wonder
> why it is so slow... :)
Oh, ok - the code looked similar to the utils/mmxsse routines so I
thought perhaps you used those routines as a starting point.
Hope I didn't insult your code too much ;) With the inlined C code
yuvdenoise runs just as quickly on a PPC system as it does on a IA32
system so I'm happy.
Cheers,
Steven Schultz
-------------------------------------------------------
This SF.Net email is sponsored by:
Sybase ASE Linux Express Edition - download now for FREE
LinuxWorld Reader's Choice Award Winner for best database on Linux.
http://ads.osdn.com/?ad_id=5588&alloc_id=12065&op=click
_______________________________________________
Mjpeg-users mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/mjpeg-users
