On Tue, Feb 16, 2016 at 1:09 PM, Jordan Justen <jordan.l.jus...@intel.com> wrote: > On gen7 (Ivy Bridge, Haswell), we will get a GPU hang if an indirect > dispatch is used, but one of the dimensions is 0. > > Therefore we use predicated rendering on the GPGPU_WALKER command to > handle this case. > > Fixes piglit test: spec/arb_compute_shader/zero-dispatch-size > > Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94100 > Signed-off-by: Jordan Justen <jordan.l.jus...@intel.com> > Cc: Kenneth Graunke <kenn...@whitecape.org> > Cc: Ben Widawsky <b...@bwidawsk.net> > Cc: Ilia Mirkin <imir...@alum.mit.edu>
Tested-by: Ilia Mirkin <imir...@alum.mit.edu> All the dEQP tests now pass instead of hanging the GPU. [shared_var*atomic is still broken, but I'm sure that's unrelated.] -ilia _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev