[Mesa-dev] i965/vec4 (nir): Plan to implement cmod_propagation on vec4

[Alejandro Piñeiro]

On 28/09/15 17:05, Jason Ekstrand wrote:
>
>
> On Sep 28, 2015 2:09 AM, "Alejandro Piñeiro" <apinheiro at igalia.com
> <mailto:apinheiro at igalia.com>> wrote:
> >
> > Hi,
> >
> > TL;DR:
> >
> > as there are several people working on improving the shader quality at
> > vec4 using NIR, to avoid overlapping, Im explicitly announcing that this
> > week I will work on implement an equivalent to fs_cmod_propagation but
> > for the vec4 case.
> >
> > More details:
> >
> > While checking shader-db HURT regressions, shaders like these:
> > unity/15.shader_test
> > warzone2100/1.shader_test
> > humus-celshading/4.shader_test
> >
> > are emitting extra movs when conditions are involved. Writing the
> > equivalent fs shader, I found those are optimized by
> > opt_cmod_propagation. I vaguely remembered that Jason mentioned it some
> > months ago, and I found this email [1], where he suggest to implement
> > that pass. So just in case someone else was already doing that, Im
> > sending this email.
>
> Hey Alejandro,
>
> First off, thanks for working on this.  Now that we've fixed the type
> issues in copy propagation and register coalesce, I think this is
> probably the last major back end issue required for getting decent
> results out of NIR.  Not that more work can't be done (it always can)
> but this solves the last known NIR->backend translation issue.
>
> I do have one comment for you to think about.  In the fs backend we
> never move a flag result *to* a GRF.  We only ever use a CMP with a
> GRF destination. In vec4, for our implementation of nir_op_banyN and
> nir_op_ballN, we do something like this:
>
> CMP null a b
> MOV reg 0ud
> MOV(+f0.0) reg 0xffffffffud
>
> Where wise the ANY4H or ALL4H predicate on the second MOV.  We should
> pick up on this as a CMP that generates a special predicate so that a
> MOV.nz that moves it to the flag actually tur s into a use of the ANY
> or ALL predicate.
>

Ok, thanks for the hints. But probably I will try to get the basic
functionality working, based on the current brw_fs_cmod_propagation, and
then try to be smarter based on your comments.

BTW, I realized that there is a unit test test_fs_cmod_propagation. I
assume that a vec4 equivalent is expected, and will work on that more or
less at the same time I work on the optimization pass. Just saying in
case I'm wrong.

Best regards

-- 
Alejandro Piñeiro (apinheiro at igalia.com)

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/mesa-dev/attachments/20150928/300059c9/attachment.html>