[Ffmpeg-devel] PATCH Blackfin optimized byte swapping mechanism

Michael Niedermayer michaelni
Tue Apr 24 03:13:13 CEST 2007


Hi

On Mon, Apr 23, 2007 at 09:01:51PM -0400, Marc Hoffman wrote:
> Michael Niedermayer writes:
>  > Hi
>  > 
>  > On Mon, Apr 23, 2007 at 01:12:47PM -0400, Marc Hoffman wrote:
>  > > Michael Niedermayer writes:
>  > >  > Hi
>  > >  > 
>  > >  > On Tue, Apr 17, 2007 at 08:49:40AM -0400, Marc Hoffman wrote:
>  > >  > > Michael Niedermayer writes:
>  > >  > >  > Hi
>  > >  > >  > 
>  > >  > >  > On Tue, Apr 17, 2007 at 07:40:47AM -0400, Marc Hoffman wrote:
>  > >  > >  > Content-Description: message body text
>  > >  > >  > > 
>  > >  > >  > >  > Low level bswap primitive for the Blackfin Architecture.
>  > >  > >  > > 
>  > >  > >  > > sorry mangled patch wrong encoding last time.
>  > >  > >  > 
>  > >  > >  > what advantage do these functions have over the default?
>  > >  > >  > are they faster? if so you should provide some benchmarks
>  > >  > > 
>  > >  > > Sorry about the top post please forgive me
>  > >  > > 
>  > >  > > The current 32bit byte swap routine produces this code sequence
>  > >  > > 
>  > >  > > So I guess this is about 300% improvement in performance for this function.
>  > >  > 
>  > >  > guess is good, hard benchmark is better, its just 5min work to write a
>  > >  > loop of bswap and do a time myprog
>  > >  > also dont forget to set proper -mcpu / -march and -O3 with gcc
>  > > 
>  > > correction ~200%. Is the patch acceptable now?
>  > 
>  > not as long as it duplicates the c bswap16 and 64 functions
>  > 
> 
> No problem how do I solve that considering thats the strategy everyone
> else used?

not everyone duplicated these 2 bswap functions, ARCH_ARM does not for
example

also, just because the code in svn is a mess does not mean its ok to add
more mess

and, iam rejecting patches which are messy mostly independant upon how
difficult it is to implement a clean solution, so if it would require
rewriting bswap.h then so be it but its not needed here, simply doing
what ARCH_ARM does should work even if its not beautifull ...

if you want to cleanup bswap.h that is certainly welcome too, maybe
a bswap.h which contains just the c functions under #ifndef FOOBAR16/32/64
and then a bswap_arm.h, ...

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

Many that live deserve death. And some that die deserve life. Can you give
it to them? Then do not be too eager to deal out death in judgement. For
even the very wise cannot see all ends. -- Gandalf
-------------- 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/20070424/8d7f73eb/attachment.pgp>



More information about the ffmpeg-devel mailing list