nv50/ir: fix false global CSE on instructions with multiple defs

If an instruction has multiple defs, we have to do a lot more checks to
make sure that we can move it forward. Among other things, various code
likes to do

    a, b = tex()
    if () c = a
    else c = b

which means that a single phi node will have results pointing at the
same instruction. We obviously can't propagate the tex in this case, but
properly accounting for this situation is tricky. Just don't try for
instructions with multiple defs.

This fixes about 20 shaders in shader-db, including the dolphin efb2ram
shader.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 684998e817b67b062e715988772199d930ae5499..81ee111a1b095a6f2a7abf2bae91d388be6baa94 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -3075,6 +3075,8 @@ GlobalCSE::visit(BasicBlock *bb)
       ik = phi->getSrc(0)->getInsn();
       if (!ik)
          continue; // probably a function input
+      if (ik->defCount(0xff) > 1)
+         continue; // too painful to check if we can really push this forward
       for (s = 1; phi->srcExists(s); ++s) {
          if (phi->getSrc(s)->refCount() > 1)
             break;