[Mesa-dev] [PATCH 0/7] GLSL: Lowering small conditional branches

[Nicolai Hähnle]

Patches 1, 2, 4 - 6:

Reviewed-by: Nicolai Hähnle <nicolai.haehnle at amd.com>

I have one pending LLVM patch related to indirect addressing. Not sure 
if that's related to the regressions, but it may be.

Cheers,
Nicolai

On 29.10.2016 01:13, Marek Olšák wrote:
> Hi,
>
> this series enables lowering small branches for radeonsi, but other
> drivers can enable it too. The GLSL compiler computes a cost per
> branch and then either lowers the branch if the cost is low enough,
> or keeps it.
>
> It will take some time before LLVM learns to do this too and that
> seems to be more involved, and we need a solution for Mesa now.
>
> There are 4 piglit regressions, which could be an uncovered radeonsi
> bug. Softpipe is unaffected. We might hold off pushing the last patch
> depending on how serious the regressions are.
>
> The reason why this is so important to us is that it reduces VGPR
> spilling:
>     Spilled VGPRs: 368 -> 96 (-73.91 %)
>     Scratch VGPRs: 1344 -> 1060 (-21.13 %) dwords per thread
>
> Please review.
>
> Marek
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev
>