[Mesa-dev] Loop- and conditional-safe TGSI register merging

Marek Olšák maraeo at gmail.com
Sun Jun 29 19:03:11 PDT 2014


I tested RV670 in April and even fixed some bugs it had. I can't
complain about stability. It worked fine.

Marek

On Mon, Jun 30, 2014 at 1:18 AM, Dave Airlie <airlied at gmail.com> wrote:
>> I've rewritten the core of the register merging algorithm to be able to cope
>> in the presence of (almost) arbitrarily nested loop and conditional
>> structures. With this patch (tested on master), the Pixmark tests finally
>> work just fine and some of the shadertoy demos have started working for me,
>> too. I had been using this patch on top of Mesa 10.1.x and 10.2.x for several
>> weeks now in daily use (including 3D gaming) and have seen no regressions.
>> I'm unfortunately unable to run piglit at all as it fails the sanity check
>> due to some mysterious z-buffer readback inaccuracy.
>
> Don't worry about that bit so much, run piglit gpu.py, apply patch, rerun,
> compare for any regressions.
>
> though I'm not so sure if rv670 survives a piglit run, you can also run against
> softpipe or llvmpipe, as this should affect those as well in theory.
>
> Dave.
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/mesa-dev


More information about the mesa-dev mailing list