[Ffmpeg-devel] dirac codec

Rich Felker dalias
Tue Jun 28 17:44:52 CEST 2005


On Tue, Jun 28, 2005 at 11:12:48AM +0200, Martin Boehme wrote:
> Ivan Kalvachev wrote:
> >On 6/22/05, Martin Boehme <boehme at inb.uni-luebeck.de> wrote:
> >
> >>Rich Felker wrote:
> >>
> >>>On Wed, Jun 22, 2005 at 11:03:59AM +0300, Tuukka Toivonen wrote:
> >>>
> >>>>H.264 certainly isn't a joke even though JM requires much, much
> >>>>more powerful CPU than 10 GHz for realtime
> >>>>(at least for encoding--haven't tested decoding but it isnt fast either)
> >>>
> >>>Encoding time is irrelevant.
> >>
> >>Hmmm, can you say "live broadcast"? ;-)
> >
> >Let me try,
> >
> >"To have live broadcast use should use hardware encoders." :P
> 
> Well... wasn't the original intent of ffmpeg to grab video from a TV 
> card, encode it and send it off over the network? ;-) And then there's 
> the PVR guys, not all of whom have hardware encoders...
> 
> Just teasing... obviously, decoding performance is still a lot more 
> critical than encoding performance...
> 
> >Anyway, the true is that when we finnaly have an CPU that can decode
> >DVD resolution in realtime there won't be any DVD's, but only HD-DVD,
> >that will require 100GHz CPUs.
> 
> You probably meant _en_code there? Or are you referring to Snow?

Probably to dirac, which is much slower than snow. (10x slower or
worse?)

Rich





More information about the ffmpeg-devel mailing list