[Ffmpeg-devel] [PATCH] Faster rgb32tobgr32

[Trent Piepho]

On Tue, 17 Apr 2007, Ivo wrote:
> On Tuesday 17 April 2007 16:51, Trent Piepho wrote:
> > On Tue, 17 Apr 2007, Ivo wrote:
> > > The following patch makes rgb32tobgr32 slightly faster by avoiding an
> > > extra add and a cmp.
> > >
> > > Old C Code, Avg of ten runs: 68345307
> > > New C Code, Avg of ten runs: 67644935
> > >
> > > Old MMX2 Code, Avg of ten runs: 66875441
> > > New MMX2 Code, Avg of ten runs: 65855368
> >
> > Don't suppose you know the variance of the ten runs?
>
> Old C code,    Avg: 68521191  Var: 2213928285808
> New C code,    Avg: 67644935  Var: 970441093200

Might be faster.  The significance level isn't very high.

> Old MMX2 code, Avg: 66875441  Var: 10001941746808
> New MMX2 code, Avg: 65855368  Var: 650060307672

No significant difference.

With a variance so big, it's not possible to say differences so small are
significant.  The two orders of magnitude difference in variance between
the old and new code makes me suspect something is wrong with your testing
methodology.