nvc0/ir: handle a load's reg result not being used for locked variants

For a load locked, we might not use the first result but the second
result is the predicate result of the locking. In that case the load
splitting logic doesn't apply (which is designed for splitting 128-bit
loads). Instead we take the predicate and move it into the first
position (as having a dead result in first def's position upsets all
sorts of things including RA). Update the emitters to deal with this as
well.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Tested-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>

1 files changed, 17 insertions, 3 deletions

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
index 6a5981d..27d9b8e 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp
@@ -2080,15 +2080,29 @@ CodeEmitterGK110::emitLOAD(const Instruction *i)
    code[1] |= offset >> 9;
 
    // Locked store on shared memory can fail.
+   int r = 0, p = -1;
    if (i->src(0).getFile() == FILE_MEMORY_SHARED &&
        i->subOp == NV50_IR_SUBOP_LOAD_LOCKED) {
-      assert(i->defExists(1));
-      defId(i->def(1), 32 + 16);
+      if (i->def(0).getFile() == FILE_PREDICATE) { // p, #
+         r = -1;
+         p = 0;
+      } else if (i->defExists(1)) { // r, p
+         p = 1;
+      } else {
+         assert(!"Expected predicate dest for load locked");
+      }
    }
 
    emitPredicate(i);
 
-   defId(i->def(0), 2);
+   if (r >= 0)
+      defId(i->def(r), 2);
+   else
+      code[0] |= 255 << 2;
+
+   if (p >= 0)
+      defId(i->def(p), 32 + 16);
+
    if (i->getIndirect(0, 0)) {
       srcId(i->src(0).getIndirect(0), 10);
       if (i->getIndirect(0, 0)->reg.size == 8)