2 files changed, 17 insertions, 4 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 37338ab5796..7a32ce59d31 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -29387,14 +29387,14 @@ static bool matchBinaryVectorShuffle(MVT MaskVT, ArrayRef<int> Mask,
     if (isTargetShuffleEquivalent(Mask, {0, 0}) && AllowFloatDomain) {
       V2 = V1;
       V1 = (SM_SentinelUndef == Mask[0] ? DAG.getUNDEF(MVT::v4f32) : V1);
-      Shuffle = X86ISD::MOVLHPS;
-      SrcVT = DstVT = MVT::v4f32;
+      Shuffle = Subtarget.hasSSE2() ? X86ISD::UNPCKL : X86ISD::MOVLHPS;
+      SrcVT = DstVT = Subtarget.hasSSE2() ? MVT::v2f64 : MVT::v4f32;
       return true;
     }
     if (isTargetShuffleEquivalent(Mask, {1, 1}) && AllowFloatDomain) {
       V2 = V1;
-      Shuffle = X86ISD::MOVHLPS;
-      SrcVT = DstVT = MVT::v4f32;
+      Shuffle = Subtarget.hasSSE2() ? X86ISD::UNPCKH : X86ISD::MOVHLPS;
+      SrcVT = DstVT = Subtarget.hasSSE2() ? MVT::v2f64 : MVT::v4f32;
       return true;
     }
     if (isTargetShuffleEquivalent(Mask, {0, 3}) && Subtarget.hasSSE2() &&
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index c8ad7d9eabb..af40b009d97 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -862,6 +862,19 @@ let Constraints = "$src1 = $dst" in {
                       Sched<[SchedWriteFShuffle.XMM]>, NotMemoryFoldable;
 }
 
+// TODO: This is largely to trick fastisel into ignoring the pattern.
+def UnpckhUnary : PatFrag<(ops node:$src1, node:$src2),
+                          (X86Unpckh node:$src1, node:$src2), [{
+  return N->getOperand(0) == N->getOperand(1);
+}]>;
+
+let Predicates = [UseSSE2] in {
+  // TODO: This is a hack pattern to allow lowering to emit unpckh instead of
+  // movhlps for sse2 without changing a bunch of tests.
+  def : Pat<(v2f64 (UnpckhUnary VR128:$src, VR128:$src)),
+            (MOVHLPSrr VR128:$src, VR128:$src)>;
+}
+
 //===----------------------------------------------------------------------===//
 // SSE 1 & 2 - Conversion Instructions
 //===----------------------------------------------------------------------===//