On Sat, 12 Mar 2011 04:47:23 +0800, "Zou, Nanhai" <[email protected]> wrote: > Like we have discussed. > I think set FB uncached, batch buffer and ring buffer LLC cached. > everything else LLC+MLC cached may get the best performance.
I don't see how batch or ring uncached should be faster than cache. Why send our writes all the way out to main memory before pulling them in again with the GPU?
pgppfx1ZCCzms.pgp
Description: PGP signature
_______________________________________________ Intel-gfx mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/intel-gfx
