Equivalent to commit 4eebeb but with sel operations. In this case
we select the PredCtrl based on the writemask.
This change allows cmod propagation to optimize out several
instructions.
Shader-db numbers:
total instructions in shared programs: 6235835 -> 6228008 (-0.13%)
instructions in affected programs: 219850 -> 212023 (-3.56%)
total loops in shared programs: 1979 -> 1979 (0.00%)
helped: 1192
HURT: 0
---
src/mesa/drivers/dri/i965/brw_vec4_nir.cpp | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
index 0f04f65..bc86be6 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
@@ -1437,8 +1437,24 @@ vec4_visitor::nir_emit_alu(nir_alu_instr *instr)
case nir_op_bcsel:
emit(CMP(dst_null_d(), op[0], src_reg(0), BRW_CONDITIONAL_NZ));
inst = emit(BRW_OPCODE_SEL, dst, op[1], op[2]);
- inst->predicate = BRW_PREDICATE_NORMAL;
+ switch (dst.writemask) {
+ case WRITEMASK_X:
+ inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_X;
+ break;
+ case WRITEMASK_Y:
+ inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_Y;
+ break;
+ case WRITEMASK_Z:
+ inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_Z;
+ break;
+ case WRITEMASK_W:
+ inst->predicate = BRW_PREDICATE_ALIGN16_REPLICATE_W;
+ break;
+ default:
+ inst->predicate = BRW_PREDICATE_NORMAL;
break;
+ }
+ break;
case nir_op_fdot_replicated2:
inst = emit(BRW_OPCODE_DP2, dst, op[0], op[1]);
--
2.1.4
_______________________________________________
mesa-dev mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
