[Mesa-dev] [PATCH] nv50/ir: replace the right def in global cse

[Ilia Mirkin]

GlobalCSE looks for phi nodes with identically-defined sources, and
replaces them with one of the (identical) instructions.

However the defining instruction might have multiple defs, so we have to
replace the one that the original phi node was pointing at.

Observed when playing around with st_glsl_to_tgsi optimization settings,
this produced a shader where a texture op was being propagated. We would
always end up setting its first def instead of the one the phi node was
pointing at.

Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
 .../drivers/nouveau/codegen/nv50_ir_peephole.cpp    | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 24caf18..aa56078 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -3028,7 +3028,7 @@ bool
 GlobalCSE::visit(BasicBlock *bb)
 {
    Instruction *phi, *next, *ik;
-   int s;
+   int s, d;
 
    // TODO: maybe do this with OP_UNION, too
 
@@ -3048,13 +3048,18 @@ GlobalCSE::visit(BasicBlock *bb)
       }
       if (!phi->srcExists(s)) {
          Instruction *entry = bb->getEntry();
-         ik->bb->remove(ik);
-         if (!entry || entry->op != OP_JOIN)
-            bb->insertHead(ik);
-         else
-            bb->insertAfter(entry, ik);
-         ik->setDef(0, phi->getDef(0));
-         delete_Instruction(prog, phi);
+         for (d = 0; ik->defExists(d); ++d)
+            if (ik->getDef(d) == phi->getSrc(0))
+               break;
+         if (ik->defExists(d)) {
+            ik->bb->remove(ik);
+            if (!entry || entry->op != OP_JOIN)
+               bb->insertHead(ik);
+            else
+               bb->insertAfter(entry, ik);
+            ik->setDef(d, phi->getDef(0));
+            delete_Instruction(prog, phi);
+         }
       }
    }
 
-- 
2.4.10