Just a thought, would it be better to move this check into the eliminate_find_live_channel optimisation? That way it could catch sources that become immediates through later optimisations. One problem with this that I've seen before is that eliminating the FIND_LIVE_CHANNEL doesn't cause the subsequent BROADCAST to be eliminated because the copy propagation doesn't work. I made this patch a while ago but I never posted it anywhere because it's a of a kludge and it would probably be better to fix the copy propagation:
https://github.com/bpeel/mesa/commit/e4c3286075f891f466fb8558106d2aaa Either way though I don't think it would do any harm to have Kristian's patch as well even if we did improve elimintate_find_live_channel so it is: Reviewed-by: Neil Roberts <n...@linux.intel.com> - Neil Kristian Høgsberg Kristensen <k...@bitplanet.net> writes: > An immdiate is already uniform so just return it up front. Without this, > brw_fs_surface_builder ends up passing immediate surface indices through > SHADER_OPCODE_BROADCAST. This writes to a stride 0 dst, which we can't > constant propagate out of, and further, we don't constant propagate into > the typed/untype read/write opcodes at all. The end result is that all > typed/untyped read/write/atomics end up as indirect sends. > > Code generation should always produce either an immediate or an actual > indirect surface index, so we can fix this by just special casing > immediates in emit_uniformize. > > Signed-off-by: Kristian Høgsberg Kristensen <k...@bitplanet.net> > --- > src/mesa/drivers/dri/i965/brw_fs_builder.h | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/src/mesa/drivers/dri/i965/brw_fs_builder.h > b/src/mesa/drivers/dri/i965/brw_fs_builder.h > index df10a9d..98ce71e 100644 > --- a/src/mesa/drivers/dri/i965/brw_fs_builder.h > +++ b/src/mesa/drivers/dri/i965/brw_fs_builder.h > @@ -394,6 +394,9 @@ namespace brw { > const dst_reg chan_index = component(vgrf(BRW_REGISTER_TYPE_UD), 0); > const dst_reg dst = component(vgrf(src.type), 0); > > + if (src.file == IMM) > + return src; > + > ubld.emit(SHADER_OPCODE_FIND_LIVE_CHANNEL, chan_index); > ubld.emit(SHADER_OPCODE_BROADCAST, dst, src, chan_index); > > -- > 2.6.2 > > _______________________________________________ > 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
