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>

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 6a5981daadf93731f552883db1a032caec2ab06c..27d9b8e16895591ea3d4129b9933e1452ed47b0d 100644 (file)
--- 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)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
index 596293ed2dfb9634bef5a58ecb8208ea245886a8..1bb962f9e26310a9cf192205fa6a6f7435d4fb15 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_nvc0.cpp
@@ -1874,17 +1874,31 @@ CodeEmitterNVC0::emitLOAD(const Instruction *i)
    }
    code[1] = opc;
 
+   int r = 0, p = -1;
    if (i->src(0).getFile() == FILE_MEMORY_SHARED) {
       if (i->subOp == NV50_IR_SUBOP_LOAD_LOCKED) {
-         assert(i->defExists(1));
-         if (targ->getChipset() >= NVISA_GK104_CHIPSET)
-            defId(i->def(1), 8);
-         else
-            defId(i->def(1), 32 + 18);
+         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");
+         }
       }
    }
 
-   defId(i->def(0), 14);
+   if (r >= 0)
+      defId(i->def(r), 14);
+   else
+      code[0] |= 63 << 14;
+
+   if (p >= 0) {
+      if (targ->getChipset() >= NVISA_GK104_CHIPSET)
+         defId(i->def(p), 8);
+      else
+         defId(i->def(p), 32 + 18);
+   }
 
    setAddressByFile(i->src(0));
    srcId(i->src(0).getIndirect(0), 20);

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index cd801f342ddc6f9846645ffcfcd96f84b89c6ce9..32131884c5f3963925cc60d7fc844d17242913dc 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -3265,14 +3265,20 @@ DeadCodeElim::visit(BasicBlock *bb)
          ++deadCount;
          delete_Instruction(prog, i);
       } else
-      if (i->defExists(1) && (i->op == OP_VFETCH || i->op == OP_LOAD)) {
+      if (i->defExists(1) &&
+          i->subOp == 0 &&
+          (i->op == OP_VFETCH || i->op == OP_LOAD)) {
          checkSplitLoad(i);
       } else
       if (i->defExists(0) && !i->getDef(0)->refCount()) {
          if (i->op == OP_ATOM ||
              i->op == OP_SUREDP ||
-             i->op == OP_SUREDB)
+             i->op == OP_SUREDB) {
             i->setDef(0, NULL);
+         } else if (i->op == OP_LOAD && i->subOp == NV50_IR_SUBOP_LOAD_LOCKED) {
+            i->setDef(0, i->getDef(1));
+            i->setDef(1, NULL);
+         }
       }
    }
    return true;