When an instruction's result was consumed by multiple mov.sat
instructions, we would decide that we couldn't move the saturate
modifier because something else was using the result, even though it was
just another mov.sat!
total instructions in shared programs: 4275598 -> 4274842 (-0.02%)
instructions in affected programs: 75634 -> 74878 (-1.00%)
---
src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
b/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
index 6f8f8d0..6f7fb6c 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
@@ -67,7 +67,8 @@ opt_saturate_propagation_local(fs_visitor *v, bblock_t *block)
break;
}
for (int i = 0; i < scan_inst->sources; i++) {
- if (scan_inst->src[i].file == GRF &&
+ if ((scan_inst->opcode != BRW_OPCODE_MOV || !scan_inst->saturate)
&&
+ scan_inst->src[i].file == GRF &&
scan_inst->src[i].reg == inst->src[0].reg &&
scan_inst->src[i].reg_offset == inst->src[0].reg_offset) {
interfered = true;
--
1.8.5.5
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
