[Mesa-dev] Fixed function fragment shader to GLSL

[Eric Anholt]

On Tue, 18 Oct 2011 11:39:16 -0700 (PDT), Jakob Bornecrantz <jakob at vmware.com> wrote:
> ----- Original Message -----
> > Here's this patch series again, part of the kill-Mesa-IR goal we have
> > for next release.  It's been no regressions for me for a while, I was
> > just trying to track down a 2% performance regression on gen6.  It
> > turns out that on my gen4 system, it's no performance regression, and
> > on gen7 (at least according to testing with the followon patches to
> > use the new coegen), it's a ~4% performance win.
> > 
> > While many things were learned in the process, the cause of the 2%
> > loss appears to come down to some GPU instruction pipelining issue
> > with lots of handwaving on my part.  When using the new backend, we
> > generate like 1/3 fewer instructions (after accounting for the 8/16
> > compile).
> > 
> > I'm not including the patches for using the new backend quite yet, as
> > there's a functional regression on gm45 in the new backend that I
> > need to track down first.
> 
> Hi, I know I told you to wait till Monday but I didn't get around to
> take a look at the changes, sorry about that, tho I would have
> appreciated that you at least pinged me before you pushed the changes.

After a far-longer-than-reasonably-required review timeframe, you asked
me to delay even longer and made a commitment to review by then.  You
failed at that commitment.

It's been 9 months in which if you actually cared you would have done
something.  You didn't.

> While you say tested the changes I assume you didn't test any Gallium
> driver (which you probably should since the only real driver in use
> today that isn't Gallium is i965).

Wrong.  I tested and fixed softpipe for you (broken GLSL support), after
waiting a long time for you to do it.

> I'm also assuming this patch series will have the previous set of
> regressions as I outlined the last time this was up for discussion.
> 
> http://article.gmane.org/gmane.comp.video.mesa3d.devel/24837

No, because other optimization passes were added in the meantime,
because GLSL codegen matters.

Apps are using GLSL now.  If there are still regressions in codegen
quality from this change, that's highlighting that your GLSL support has
issues that affect apps and should be fixed, not that this change is
broken.

(However, last time I tested, glean texcombine is actually emitting
fewer Mesa IR instructions now than it did before the change.  So there
likely isn't even any problem).

> Also I would appreciated these kind of change the whole world changes
> to have a larger Acked-by/Reviewed-by base the just one other guy
> using the same test set as the author.

I look forward to your patches making improvements.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 197 bytes
Desc: not available
URL: <http://lists.freedesktop.org/archives/mesa-dev/attachments/20111018/3471d41a/attachment.pgp>