On Aug 2, 2016 12:36 PM, "Matt Turner" <[email protected]> wrote:
>
> On Mon, Aug 1, 2016 at 8:59 PM, Kenneth Graunke <[email protected]>
wrote:
> > Previously, for every input, we moved the dispatch mask to the flag
> > register, then emitted two predicated PLN instructions, one with
> > centroid barycentric coordinates (for normal pixels), and one with
> > pixel barycentric coordinates (for unlit helper pixels).
> >
> > Instead, we can simply emit a set of predicated MOVs at the top of
> > the program which copy the pixel barycentric coordinates over the
> > centroid ones for unlit helper pixel channels.  Then, we can just
> > use normal PLNs.

I like this approach *much* better than what we did before.

Reviewed-by: Jason Ekstrand <[email protected]>

> > On Sandybridge:
> >
> > total instructions in shared programs: 7538470 -> 7534500 (-0.05%)
> > instructions in affected programs: 101268 -> 97298 (-3.92%)
> > helped: 705
> > HURT: 9 (all of which are SIMD16 programs)
>
> Reviewed-by: Matt Turner <[email protected]>
>
> Maybe wait a few days before pushing so we can confirm that my patch
> indeed doesn't cause any regressions on Gen7.

They're pretty much orthogonal so I'm not too worried about that but sure.

--Jason
_______________________________________________
mesa-dev mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/mesa-dev

Reply via email to