diff options
| author | Kenneth Graunke <[email protected]> | 2013-09-09 11:11:03 -0700 |
|---|---|---|
| committer | Kenneth Graunke <[email protected]> | 2013-09-10 17:52:56 -0700 |
| commit | 4e5eb8ba25054ede4798fa424e6f32b23aba0f98 (patch) | |
| tree | 9b4575c91085cab5646854851232e4ee91e09867 | |
| parent | 17eb1df7b8af800f03c5b1f35fdf4292abe32ea1 (diff) | |
i965/vec4: Only zero out unused message components when there are any.
Otherwise, coordinates with four components would result in a MOV
with a destination writemask that has no channels enabled:
mov(8) g115<1>.F 0D { align16 WE_normal NoDDChk 1Q };
At best, this is stupid: we emit code that shouldn't do anything.
Worse, it apparently causes GPU hangs (observable with Chris's
textureGather test on CubeArrays.)
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Chris Forbes <[email protected]>
Reviewed-by: Ian Romanick <[email protected]>
Cc: [email protected]
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp index a51b61baf03..86ecd214496 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp @@ -2248,8 +2248,10 @@ vec4_visitor::visit(ir_texture *ir) emit(MOV(dst_reg(MRF, param_base, ir->coordinate->type, coord_mask), coordinate)); } - emit(MOV(dst_reg(MRF, param_base, ir->coordinate->type, zero_mask), - src_reg(0))); + if (zero_mask != 0) { + emit(MOV(dst_reg(MRF, param_base, ir->coordinate->type, zero_mask), + src_reg(0))); + } /* Load the shadow comparitor */ if (ir->shadow_comparitor && ir->op != ir_txd) { emit(MOV(dst_reg(MRF, param_base + 1, ir->shadow_comparitor->type, |