[PATCH] R600/SI: Legalize INSERT_SUBREG instructions during PostISelFolding

Tom Stellard thomas.stellard at amd.com
Fri Oct 3 08:38:55 PDT 2014


LLVM assumes INSERT_SUBREG will always have register operands, so
we need to legalize non-register operands, like FrameIndexes, to
avoid random assertion failures.
---
 lib/Target/R600/SIISelLowering.cpp | 27 +++++++++++++++++++++++++++
 test/CodeGen/R600/insert_subreg.ll | 15 +++++++++++++++
 2 files changed, 42 insertions(+)
 create mode 100644 test/CodeGen/R600/insert_subreg.ll

diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp
index f042aaa..4c0d22d 100644
--- a/lib/Target/R600/SIISelLowering.cpp
+++ b/lib/Target/R600/SIISelLowering.cpp
@@ -1923,6 +1923,30 @@ void SITargetLowering::adjustWritemask(MachineSDNode *&Node,
   }
 }
 
+/// \brief Legalize INSERT_SUBREG instructions with frame index operands.
+/// LLVM assumes that all INSERT_SUBREG inputs are registers.
+static void LegalizeInsertSubreg(MachineSDNode *InsertSubreg,
+                                 SelectionDAG &DAG) {
+
+  assert(InsertSubreg->getMachineOpcode() == AMDGPU::INSERT_SUBREG);
+
+  SmallVector <SDValue, 8> Ops;
+  for (unsigned i = 0; i < 2; ++i) {
+    if (!isa<FrameIndexSDNode>(InsertSubreg->getOperand(i))) {
+      Ops.push_back(InsertSubreg->getOperand(i));
+      continue;
+    }
+
+    SDLoc DL(InsertSubreg);
+    Ops.push_back(SDValue(DAG.getMachineNode(AMDGPU::S_MOV_B32, DL,
+                                     InsertSubreg->getOperand(i).getValueType(),
+                                     InsertSubreg->getOperand(i)), 0));
+  }
+
+  DAG.UpdateNodeOperands(InsertSubreg, Ops[0], Ops[1],
+                         InsertSubreg->getOperand(2));
+}
+
 /// \brief Fold the instructions after selecting them.
 SDNode *SITargetLowering::PostISelFolding(MachineSDNode *Node,
                                           SelectionDAG &DAG) const {
@@ -1933,6 +1957,9 @@ SDNode *SITargetLowering::PostISelFolding(MachineSDNode *Node,
   if (TII->isMIMG(Node->getMachineOpcode()))
     adjustWritemask(Node, DAG);
 
+  if (Node->getMachineOpcode() == AMDGPU::INSERT_SUBREG)
+    LegalizeInsertSubreg(Node, DAG);
+
   return legalizeOperands(Node, DAG);
 }
 
diff --git a/test/CodeGen/R600/insert_subreg.ll b/test/CodeGen/R600/insert_subreg.ll
new file mode 100644
index 0000000..c9b22ec
--- /dev/null
+++ b/test/CodeGen/R600/insert_subreg.ll
@@ -0,0 +1,15 @@
+; RUN: llc -march=r600 -mcpu=SI -mattr=-promote-alloca -verify-machineinstrs < %s 2>&1 | FileCheck %s
+
+; Test that INSERT_SUBREG instructions don't have non-register operands after
+; instruction selection.
+
+; Make sure this doesn't crash
+; CHECK-LABEL: test:
+define void @test(i64 addrspace(1)* %out) {
+entry:
+  %tmp0 = alloca [16 x i32]
+  %tmp1 = ptrtoint [16 x i32]* %tmp0 to i32
+  %tmp2 = sext i32 %tmp1 to i64
+  store i64 %tmp2, i64 addrspace(1)* %out
+  ret void
+}
-- 
1.8.5.5




More information about the llvm-commits mailing list