Am Montag, 20. September 2004 21:52 schrieb Dieter Nützel: > Am Sonntag, 19. September 2004 11:21 schrieb Eric Anholt: > > The attached patch removes the mandatory emits of all state which were > > happening after each cmdbuf flush. Instead, we set a flag after a > > cmdbuf flush saying "save the state at the next unlock," which means > > memcpying the state atoms off. When we actually see the context get > > lost, then we "back up" and restore state -- make a new cmdbuf, dirty > > all state, emit it, flush it, then put the old cmdbuf back. I also > > removed the dirty/clean state lists and made a single one. The > > reasoning was that we have to walk the entire list on emit (and twice > > when the all-dirty is set) anyway, and I felt that this was cleaner. It > > also fixed some bad cmdbufs that were happening for me (drmCommandWrite: > > -22) with the CVS code. > > > > This gets about a 5% speedup for me in ipers (which I wish was more > > accurate in its reporting), > > Do you think it's only 5% for you? > > It is GREAT. > > Ipers is back when not faster ever on my system ;-) > > 31 fps, 825.000 from ~25, ~660.000 > > => 24%
But got progs/demos> IperS V1.0 Written by David Bucciarelli ([EMAIL PROTECTED]) Mesa: software DXTn compression/decompression available drmCommandWrite: -22 drmRadeonCmdBuffer: -22 (exiting) [1] Exitcode 234 ./ipers when I cycle through the drawing modes (t/b/n) during wire frame (p). -Dieter ------------------------------------------------------- This SF.Net email is sponsored by: YOU BE THE JUDGE. Be one of 170 Project Admins to receive an Apple iPod Mini FREE for your judgement on who ports your project to Linux PPC the best. Sponsored by IBM. Deadline: Sept. 24. Go here: http://sf.net/ppc_contest.php -- _______________________________________________ Dri-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/dri-devel
