[MPlayer-dev-eng] [PATCH] replacement for internal mpg123 fork (mp3lib), Final version?

[Diego Biurrun]

On Thu, May 20, 2010 at 11:28:01AM +0200, Thomas Orgis wrote:
> Am Sun, 16 May 2010 22:02:51 +0200
> schrieb Thomas Orgis <thomas-forum at orgis.org>: 
> 
> > Apart from just accepting the sub-par performance with old mpg123
> > (which might or might not be relevant for realtime decoding), we do have
> > the option to feed data in larger blocks
> 
> Ping. Any decision on the mpg123 stuff? I'm about to release mpg123
> 1.13 soon, which will have proper performance with the current version
> of the mplayer mpg123 patch... do you want me to provide a switch in
> ad_mpg123 between feeding packets with pts and bigger lumps for optimal
> efficiency with old mpg123? Please give a sign.
> 
> Diego: Do you actually confirm my observation about the feeder code
> being faster with bigger chunks (>=1K)? Does http://mpg123.org/snapshot
> fix the speed regression on your K6-III?

I've been busy the past few days.  I'll try to make some time for
benchmarks over the weekend.

Diego