On Mon, 2009-12-28 at 13:27 +0100, Maarten Maathuis wrote: > Why does it help to allocate the sys_ptr up front, why does that avoid > migration (i would except sys_ptr to be allocated when needed)?
If the system copy is only allocated on a software fallback, the GPU copy still needs to be read back at that point. The purpose of all this code is to avoid that by keeping both copies in sync all the time. -- Earthling Michel Dänzer | http://www.vmware.com Libre software enthusiast | Debian, X and DRI developer _______________________________________________ xorg-devel mailing list [email protected] http://lists.x.org/mailman/listinfo/xorg-devel
