On 2014.03.05 18:51:48 +0200, Ville Syrjälä wrote: > > entries = (clock / 1000) * pixel_size; > > *plane_prec_mult = (entries > 256) ? > > The threshold should also be reduced to 128 entries. >
hmm, I'll double check if this is really required or not. > > - DRAIN_LATENCY_PRECISION_32 : DRAIN_LATENCY_PRECISION_16; > > + DRAIN_LATENCY_PRECISION_64 : DRAIN_LATENCY_PRECISION_32; > > *plane_dl = (64 * (*plane_prec_mult) * 4) / ((clock / 1000) * > > pixel_size); > ^^^^^^^^^^^^^^^^^ > Maybe replace the divisor here w/ just 'entrie' since it's same thing. > Makes it a bit easier to see the relationship between this and the way > the precision is selected. > yeah, but that might be another seperate patch besides the precision multipler this one trys to fix. Thanks for review this. -- Open Source Technology Center, Intel ltd. $gpg --keyserver wwwkeys.pgp.net --recv-keys 4D781827
signature.asc
Description: Digital signature
_______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
