[MPlayer-dev-eng] Re: Vorbis decoding performance

[Rich Felker]

On Mon, Aug 07, 2006 at 11:09:45PM +0200, Michael Niedermayer wrote:
> Hi
> 
> On Mon, Aug 07, 2006 at 08:22:59PM +0200, Aurelien Jacobs wrote:
> > On Wed, 02 Aug 2006 17:38:07 +0200
> > Baptiste Coudurier <baptiste.coudurier at smartjog.com> wrote:
> > 
> > > Hi
> > > 
> > > Uoti Urpala wrote:
> > > > On Wed, 2006-08-02 at 11:21 +0200, Diego Biurrun wrote:
> > > >> I sat down and did some benchmarks on my K6-III 500, Debian stable
> > > > 
> > > 
> > > Comparison on p4 2.4ghz, debian unstable:
> > 
> > Some more benchmark.
> > Target: ARM (Xscale IXP420 266MHz gcc-4.1)
> > 
> > ./mplayer -quiet -benchmark -ao pcm:fast:file=/dev/null song37.ogg
> > BENCHMARKs: VC:   0.000s VO:   0.000s A: 257.712s Sys:   0.657s =  258.369s
> > BENCHMARK%: VC:  0.0000% VO:  0.0000% A: 99.7456% Sys:  0.2544% = 100.0000%
> > 
> > ./mplayer -quiet -benchmark -afm ffmpeg -ao pcm:fast:file=/dev/null song37.ogg
> > ... still running... (more than an hour)
> 
> hmm floating point emulation is slow sure but it shouldnt be that slow ...

Why not? At least Nx slower should be expected where every (1-cycle)
opcode becomes a N-cycle invalid opcode fault and context switch to
kernelspace handler. I would expect N is somewhere between 200 and
5000.

Rich