[FFmpeg-devel] MPEG-2 Acceleration Refactor

[Michael Niedermayer]

Hi

On Sun, Jun 17, 2007 at 01:59:59PM +0300, Ivan Kalvachev wrote:
> 2007/6/17, Michael Niedermayer <michaelni at gmx.at>:
> > Hi
> >
> > On Sat, Jun 16, 2007 at 06:44:21PM -0700, Greg Hulands wrote:
> > > Based on the START/STOP_TIMER stuff showing the patch is actually
> > > faster I have tidied the patch a little more and removed the function
> > > prototypes to the _fast functions at the top of the file.
> > >
> > > If there are any other problems from stopping this getting committed,
> > > please let me know.
> >
> > yes, why is it faster now and was slower before?
> 
> I think nothing has changed. The functions alone are faster, the
> decoding as whole is slower ;) It's just one of the miracles of
> benchmarking.

the svn code vs. the patched code shows that the patched code is slower

the svn code + *TIMER vs. the patched code +TIMER shows that svn is
slower in _both_ the TIMER and -benchmark scores


> 
> My guess is that placing START/STOP_TIMER inside the functions in
> question changed the way they are optimized.

yes


> 
> As of why the new vs. old is slower, I think that assembler output
> would give us more clues.

yes

and as long as svn + patch is slower this patch is rejected
its also still a total mess whitespace wise

[...]

-- 
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: not available
URL: <http://lists.mplayerhq.hu/pipermail/ffmpeg-devel/attachments/20070617/3a19932d/attachment.pgp>