DAG: Add computeKnownBitsForFrameIndex

Some of the AMDGPU stack addressing modes require knowing the sign
bit is zero. We used to accomplish this by custom lowering
frame indexes, and then putting an AssertZext around a
TargetFrameIndex. This required specifically looking for
the AssextZext + frame index pattern which was moderately
disgusting. The same could probably be accomplished
with a target specific node, but would still
require special handling of frame indexes.

llvm-svn: 317671

1 files changed, 13 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index fe553bc986a..1f6fafb039e 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -1288,6 +1288,19 @@ void TargetLowering::computeKnownBitsForTargetNode(const SDValue Op,
   Known.resetAll();
 }
 
+void TargetLowering::computeKnownBitsForFrameIndex(const SDValue Op,
+                                                   KnownBits &Known,
+                                                   const APInt &DemandedElts,
+                                                   const SelectionDAG &DAG,
+                                                   unsigned Depth) const {
+  assert(isa<FrameIndexSDNode>(Op) && "expected FrameIndex");
+
+  if (unsigned Align = DAG.InferPtrAlignment(Op)) {
+    // The low bits are known zero if the pointer is aligned.
+    Known.Zero.setLowBits(Log2_32(Align));
+  }
+}
+
 /// This method can be implemented by targets that want to expose additional
 /// information about sign bits to the DAG Combiner.
 unsigned TargetLowering::ComputeNumSignBitsForTargetNode(SDValue Op,