On Sat, 2002-05-18 at 23:33, Benjamin Herrenschmidt wrote: > > The ideal way, but probably not possible with current APIs, would be > to have control over Xv (MC ?) allocation routines so that when the client > frames are allocated, it really gets a pair of AGP memory blocks allocated > from the AGP aperture and mapped into the client process space.
AFAIK this is how XvMC works, the client allocates surfaces from the XvMC driver. > Ideally, we could then make it cacheable, and then have Xv flush the cache > when feeding the frame to the ring. Maybe we could even have the chip display the overlay out of AGP memory directly? > >> >Anyway, I don't see any explicit synchronisation in the driver, so > >> >probably the problem is the players calling XSync(). > >> > >> Well, do we wait for DMA to finish or not ? If we do, then we are > >> doing explicit sync. > > > >Again, I don't see that in the driver, but maybe I'm just blind. > > Could be implicit as part as a wait for engine ready or a 2D sync, That's exactly what I looked for but didn't see. :) > though I yet have to look at the impl. We should try to figure out > where X is actually spending those cycles. Yep, someone who cares about this will have to do that. -- Earthling Michel D�nzer (MrCooper)/ Debian GNU/Linux (powerpc) developer XFree86 and DRI project member / CS student, Free Software enthusiast -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
