[Ffmpeg-devel] Fixed vs. Floating Point AAC

Rich Felker dalias
Wed Mar 8 20:52:03 CET 2006


On Wed, Mar 08, 2006 at 04:54:39PM -0000, M?ns Rullg?rd wrote:
> 
> Rich Felker said:
> > On Wed, Mar 08, 2006 at 01:01:47PM +0100, Michael Niedermayer wrote:
> >> it should support both, fixed point is absolutely needed for embeded systems
> >> (and richs K6), and floating point is more accurate and faster on modern
> >> cpus, and floating point is much easier to implement
> >
> > Would you like to provide benches showing it's faster? Testing of
> > libvorbis versus tremor has shown that the integer implementation
> > (tremor) is always faster, even on the latest cpus. This is without
> > any vectorization (except possible float vectorization by gcc?); with
> > mmx/3dnow/etc the difference should be even more drastic.
> 
> libvorbis faster than tremor on Alpha.

Including the 'low precision' mode in tremor (which makes no audible
difference, i.e. you won't be able to distinguish them with
doubleblind testing)?? IIRC it's between 1.5 and 2x as fast as the
normal mode in tremor.

BTW the testing I cited was on athlon.

Rich






More information about the ffmpeg-devel mailing list