[FFmpeg-devel] dealing with tables in DV codec

Diego Biurrun diego
Thu Sep 11 01:53:00 CEST 2008


On Wed, Sep 10, 2008 at 08:27:33PM +0100, M?ns Rullg?rd wrote:
> Diego Biurrun <diego at biurrun.de> writes:
> 
> > On Wed, Sep 10, 2008 at 08:22:41AM +0100, M?ns Rullg?rd wrote:
> >> Diego Biurrun <diego at biurrun.de> writes:
> >> 
> >> > On Tue, Sep 09, 2008 at 01:51:06PM -0700, Roman Shaposhnik wrote:
> >> >> 
> >> >> as I promised, I tried to come with alternative ways of dealing
> >> >> with macroblock placement in DV codec, and it seems that no
> >> >> matter what I use on Xeon and Opteron it is basically a toss up.
> >> >> There's no speed gain, there's no speed loss. The tables can
> >> >> go so it is a net gain. Now, on SPARC I see a stable speed 
> >> >> loss of about ~3% or so. And I suspect that the same will
> >> >> be true on any chip with a low clock speed.
> >> >> 
> >> >> Now, I'm publishing a temporary diff to solicit public comments
> >> >> on how the calculations can be optimized even further. If nobody
> >> >> comes up with any kind of good ideas -- I don't know what to do.
> >> >> Michale has always told us that even ~3% is significant enough. 
> >> >> So it needs to be dealt with before any change can occur.
> >> >
> >> > I don't think SPARC is important.  Let me know what I will have to do
> >> > and I will benchmark on my trusty old K6-III 500.  Then you will have
> >> > numbers for a low clock speed x86 system.
> >> 
> >> Who gets to decide which machines are important?  Is K6-3 more
> >> important than SPARC?
> >
> > x86 is surely more important than SPARC
> 
> Motivate.

I have a PPC myself, but let's face it, most of the world runs x86..

> > and a K6-III is an x86 processor with relatively low clock speed...
> 
> Yes, and?

As Roman said:

  Now, on SPARC I see a stable speed loss of about ~3% or so. And I
  suspect that the same will be true on any chip with a low clock speed.

So I offered myself as tester on a low clock speed x86 system.

Diego




More information about the ffmpeg-devel mailing list