1 files changed, 15 insertions, 5 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 73b90666c56..b79ff7f146d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -15453,7 +15453,7 @@ static SDValue partitionShuffleOfConcats(SDNode *N, SelectionDAG &DAG) {
 //
 // To deal with this, we currently use a bunch of mostly arbitrary heuristics.
 // We don't fold shuffles where one side is a non-zero constant, and we don't
-// fold shuffles if the resulting BUILD_VECTOR would have duplicate
+// fold shuffles if the resulting (non-splat) BUILD_VECTOR would have duplicate
 // non-constant operands. This seems to work out reasonably well in practice.
 static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
                                        SelectionDAG &DAG,
@@ -15477,6 +15477,15 @@ static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
       return SDValue();
   }
 
+  // If both inputs are splats of the same value then we can safely merge this
+  // to a single BUILD_VECTOR with undef elements based on the shuffle mask.
+  bool IsSplat = false;
+  auto *BV0 = dyn_cast<BuildVectorSDNode>(N0);
+  auto *BV1 = dyn_cast<BuildVectorSDNode>(N1);
+  if (BV0 && BV1)
+    if (SDValue Splat0 = BV0->getSplatValue())
+      IsSplat = (Splat0 == BV1->getSplatValue());
+
   SmallVector<SDValue, 8> Ops;
   SmallSet<SDValue, 16> DuplicateOps;
   for (int M : SVN->getMask()) {
@@ -15495,11 +15504,12 @@ static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
       }
     }
 
-    // Don't duplicate a non-constant BUILD_VECTOR operand; semantically, this is
-    // fine, but it's likely to generate low-quality code if the target can't
-    // reconstruct an appropriate shuffle.
+    // Don't duplicate a non-constant BUILD_VECTOR operand unless we're
+    // generating a splat; semantically, this is fine, but it's likely to
+    // generate low-quality code if the target can't reconstruct an appropriate
+    // shuffle.
     if (!Op.isUndef() && !isa<ConstantSDNode>(Op) && !isa<ConstantFPSDNode>(Op))
-      if (!DuplicateOps.insert(Op).second)
+      if (!IsSplat && !DuplicateOps.insert(Op).second)
         return SDValue();
 
     Ops.push_back(Op);