On Wed, 2011-10-19 at 10:49 -0400, Tom Stellard wrote: > On Fri, 2011-10-07 at 10:14 -0400, Vadim Girlin wrote: > > Hi, > > > > Recently I've been working on the shader optimization for r600g, and now > > I have the initial working implementation of simple alu scheduler and > > register allocator. It has no piglit regressions, though it's still a > > work in progress and there are known issues with some applications. > > > > I've pushed the working branch to github: > > https://github.com/VadimGirlin/mesa/tree/r600_shader_opt > > Hi Vadim, > > What's the current status of this branch? Is there anything in there > that is stable and ready to merge? >
I think it's not ready yet. I'm still working on the features such as barrier bit usage for parallel execution of the alu and fetch instructions. Experiments with some relatively simple algorithms for this doesn't show any benefits, so I'm thinking about rewriting the scheduler to use more complex approach. So far simple unification of the fetch instructions to minimize mixing of the different clause types (without using barrier bit for parallel execution) gives the best result for me (this is already implemented in my branch, though it might need still uncommitted patch to reduce register pressure in some cases). Also there are regressions with some applications. Currently I'm mostly working on the new features, but probably at least all known issues should be fixed before trying to merge it. And finally it will need the cleanup and coding style fixes. Vadim > -Tom > > > > _______________________________________________ > mesa-dev mailing list > mesa-dev@lists.freedesktop.org > http://lists.freedesktop.org/mailman/listinfo/mesa-dev _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
