This sequence (where both x and w are used afterwards) wasn't handled.
mul.sat x, y, z
...
mov.sat w, x
We assumed that if x was used after the mov.sat, that we couldn't
propagate the saturate modifier, but in fact x was already saturated.
So ignore the live range check if the producing instruction already
saturates its result. Cuts one instruction from hundreds of TF2 shaders.
total instructions in shared programs: 1995631 -> 1994951 (-0.03%)
instructions in affected programs: 155248 -> 154568 (-0.44%)
---
src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
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 4b5b5ca..079eb2e 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_saturate_propagation.cpp
@@ -47,8 +47,6 @@ opt_saturate_propagation_local(fs_visitor *v, bblock_t *block)
int src_var = v->live_intervals->var_from_reg(&inst->src[0]);
int src_end_ip = v->live_intervals->end[src_var];
- if (src_end_ip > ip && !inst->dst.equals(inst->src[0]))
- continue;
int scan_ip = ip;
bool interfered = false;
@@ -61,10 +59,15 @@ opt_saturate_propagation_local(fs_visitor *v, bblock_t
*block)
scan_inst->dst.reg == inst->src[0].reg &&
scan_inst->dst.reg_offset == inst->src[0].reg_offset &&
!scan_inst->is_partial_write()) {
- if (scan_inst->can_do_saturate()) {
- scan_inst->saturate = true;
+ if (scan_inst->saturate) {
inst->saturate = false;
progress = true;
+ } else if (src_end_ip <= ip || inst->dst.equals(inst->src[0])) {
+ if (scan_inst->can_do_saturate()) {
+ scan_inst->saturate = true;
+ inst->saturate = false;
+ progress = true;
+ }
}
break;
}
--
1.8.3.2
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
