[Ffmpeg-devel] [PATCH] Snow mmx+sse2 asm optimizations

[Guillaume POIRIER]

Hi,

On 3/10/06, Robert Edele <yartrebo at earthlink.net> wrote:
>
> > OK, I'll wait. Could you look over Robert's patch then?... It (should be)
> > production ready...
> >
> I think I've figured out what Michael wants. I think he wanted the
> add_yblock function to be trimmed down. I've cleaned them up and
> offloaded the repetitive code into marcos, shrinking the patch by about
> 16kB while marginally speeding it up.
>
> Michael, if there's more you want done before you're willing to commit
> it, please speak up.

I've re-tested this patchset on my AMD-64, and it still works beautifully.

Unpatched
BENCHMARKs: VC:   1.367s VO:   0.000s A:   0.000s Sys:   0.020s =    1.387s
BENCHMARK%: VC: 98.5620% VO:  0.0208% A:  0.0000% Sys:  1.4172% = 100.0000%

Patched:
BENCHMARKs: VC:   1.127s VO:   0.000s A:   0.000s Sys:   0.030s =    1.158s
  CPLAYER: BENCHMARK%: VC: 97.3683% VO:  0.0242% A:  0.0000% Sys: 
2.6075% = 100.0000%

Cheers,
Guillaume
--
Reinventing the wheel certainly is annoying, but as long as all other
wheels are square...

Reimar D?ffinger