[FFmpeg-devel] [flamefest-start] A little something on MMX/SSE intrinsics

[Michael Niedermayer]

On Wed, Feb 27, 2008 at 03:29:56PM -0500, Alexander Strange wrote:
> On Wed, Feb 27, 2008 at 3:24 PM, Luca Barbato <lu_zero at gentoo.org> wrote:
> > Michael Niedermayer wrote:
> >  > On Wed, Feb 27, 2008 at 05:42:58PM +0200, Ivan Kalvachev wrote:
> >  >> On Wed, Feb 27, 2008 at 4:31 PM, Reimar D?ffinger
> >  >> <Reimar.Doeffinger at stud.uni-karlsruhe.de> wrote:
> >  >>> Hello,
> >  >>>  yet another case of someone relearning "intrinsics are still a mess and
> >  >>>  compilers still much too stupid" ;-) :
> >  >>>  http://www.virtualdub.org/blog/pivot/entry.php?id=188#body
> >  >>>
> >  >>>  Let's see if we can make today the flame-heaviest day in FFmpeg history
> >  >>>  :-)
> >  >> Nice read.
> >  >>
> >  >> I'd just like to add that there is already architecture in FFmpeg that
> >  >> is entirely optimized on intrinsics - AltiVect. There were few
> >  >> fundamental problems with it and I'm not sure if they have been
> >  >> successfully solved. These include things like generating code that
> >  >> picks up processor SIMD dialect at runtime.
> >  >
> >  > You just found us a new SOC qualification task
> >  > rewrite intrinsics to proper asm()
> >  >
> >
> >  And benchmark the result ^^;
> >
> >  lu
> 
> I don't think anyone can get Altivec asm to work better than
> intrinsics on more than one CPU - PPC is really, really
> scheduling-sensitive, especially the G5 and Cell.

Until i see benchmarks id guess gcc+intrinsics will be slower than
unsheduled naively written asm()


> 
> I guess you can always try, though, but don't do anything to
> discourage people who know altivec from adding more. There's still a
> lot missing from H.264.

Code is either well written or should be rejected.
Intrinsics != well written.

[...]
-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

Concerning the gods, I have no means of knowing whether they exist or not
or of what sort they may be, because of the obscurity of the subject, and
the brevity of human life -- Protagoras
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: Digital signature
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20080227/76d00092/attachment.pgp>