[Theora-dev] FPGA implementation/ players speed?

Ivan Popov pin at medic.chalmers.se
Wed Mar 9 04:14:27 PST 2005

On Wed, Mar 09, 2005 at 12:20:03PM +0100, j at thing.net wrote:
> its the work wim posted to the list some time ago.
> the the mmx patches from VP3HoSwiYO boost decoding
> significantly?

Yes, definitely, on Andrey's clip it makes 40% difference
compared to the other patch, and over 50% compared to the original code.
(Or 29% and 36% if you calculate from the bigger number instead :)

(3.775 user seconds spent compared to
 5.314 with "encoder" mmx patches and
 5.889 without any patches)

> if so, how hard would it be to add
> them to theora-mmx? 

No idea. I am not sufficiently into MMX-programming...
It should be doable, anyway! :)


More information about the Theora-dev mailing list