[tremor] [PATCH] 12% global performance gain on a StrongARM

[Nicolas Pitre]

On Thu, 19 Sep 2002, dilb wrote:

> > The attached patch provides a 12% performance gain on a StrongARM SA1110
> > over current code in the CVS.  This is mostly C code shuffling so to help
> > GCC produce nearly perfect assembly on ARM.  Probably a hand optimized
> > assembly version of mdct.c could do even better, but I'll leave this task
> > to others (Dilb?).  At least this will produce the best compiler generated
> > reference to start with as well as improving performance for all
> > architectures in general.
> 
> This is a nice improvement, "félicitation" :).
> Currently, I'm working on ffmpeg's iDCT for ARM (the old one seems wrong), 
> but, as I said, as soon as the mdct.c function will stabilize, I will update 
> my assembly code.

Well, if Monty is willing to merge my patch, it'll be done as far as I'm 
concerned.  I don't think there is much more to do with the code.  I still 
have the feeling that bitrev12() could be even lighter, but that would be a 
small and localized change anyway.

> Did you compare results between your favorite CFLAGS, and mine ?

Well yes, but they don't make much difference on performances anymore.

<p>Nicolas

--- >8 ----
List archives:  http://www.xiph.org/archives/
Ogg project homepage: http://www.xiph.org/ogg/
To unsubscribe from this list, send a message to 'tremor-request at xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.