[XviD-devel] Question about bvop decoding
Edouard Gomez
ed.gomez at free.fr
Wed Jul 21 22:41:02 CEST 2004
skal (skal at planet-d.net) wrote:
> a) fwd predict into buf1
> b) bwd predict into buf2
> c) average buf1 and buf2 and send to pic.
>
> Now it's pretty obvious you're loosing
> time in Memory I/O and 16/8bits conversion
> during steps b) and c). These two could be
> merged into a single 'averaging' bwd predicting
> step.
>
> Now, if you dig very hard into this mailing list's
> archive, you may find that i once, a long time
> ago, sent ASM code that does combined b)+c) steps...:)
I've been looking for Skal in all our archives (painfull as we
don't have search engine indexing the ML) and i found no
optimization for this:
from july 2002 to July 2004, i've found plenty of ideas, and
interesting posts but no bf interpolate code/not optimizations
idea. Could you be kind enough to post the link or, much
better, post the code again ?
Btw, gruel had an idea how to speedup encoding by skipping
Trellis optim on chroma blocks, no one answered... i think
i'll give a try just to see if speed boost is worth it.
--
Edouard Gomez
More information about the XviD-devel
mailing list