[MPlayer-dev-eng] [PATCH] autoq support for control()

[Arpi]

Hi,

> > anyway, imho libavcodec could be even faster... at least compared to mp1e it
> > is still ~50% slower, at least on my system.
> 
> 	With P frames ?
not. I only

> 	Is mp1e based on ffmpeg ? At least freshmeat says that.
nope. librte is based on mp1e and ffmpeg. it's just a wrapper and grabbing
tool over them. the mp1e is an overoptimized mpeg 1 encoder from scratch.

> 	Also a lot of overhead could reduced if you concentrate on MPEG1 only
> :(
hmm

> > i've noticed that mp1e uses 2 nasty tricks: aligned globals, even for dct
> > temp blocks and so on - it may save one register and extra indexing so it
> > may speed up things. the other trick is cache optimization, similar to
> > libmpeg2's slices, so instead of doing various steps (like dct coding,
> > huffman coding etc) on small macroblocks, it group things, like dct for
> > while slice, then huffman for whole slice etc.
> 
> 	I should see the cache trick, maybe there are others; because %50
> faster is a lot !


A'rpi / Astral & ESP-team

--
"I don't RTFM? Wow. What's the meaning of this? It's new for me."
	-- Martin Baum, a tipical MPlayer user...