2 files changed, 42 insertions, 21 deletions

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index b2f970b447..44d43a1d07 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -8990,12 +8990,32 @@ SDValue DAGCombiner::visitEXTRACT_SUBVECTOR(SDNode* N) {
   EVT NVT = N->getValueType(0);
   SDValue V = N->getOperand(0);
 
+  if (V->getOpcode() == ISD::CONCAT_VECTORS) {
+    // Combine:
+    //    (extract_subvec (concat V1, V2, ...), i)
+    // Into:
+    //    Vi if possible
+    // Only operand 0 is checked as 'concat' assumes all inputs of the same type.
+    if (V->getOperand(0).getValueType() != NVT)
+      return SDValue();
+    unsigned Idx = dyn_cast<ConstantSDNode>(N->getOperand(1))->getZExtValue();
+    unsigned NumElems = NVT.getVectorNumElements();
+    assert((Idx % NumElems) == 0 &&
+           "IDX in concat is not a multiple of the result vector length.");
+    return V->getOperand(Idx / NumElems);
+  }
+
+  // Skip bitcasting
+  if (V->getOpcode() == ISD::BITCAST)
+    V = V.getOperand(0);
+
   if (V->getOpcode() == ISD::INSERT_SUBVECTOR) {
+    DebugLoc dl = N->getDebugLoc();
     // Handle only simple case where vector being inserted and vector
     // being extracted are of same type, and are half size of larger vectors.
     EVT BigVT = V->getOperand(0).getValueType();
     EVT SmallVT = V->getOperand(1).getValueType();
-    if (NVT != SmallVT || NVT.getSizeInBits()*2 != BigVT.getSizeInBits())
+    if (!NVT.bitsEq(SmallVT) || NVT.getSizeInBits()*2 != BigVT.getSizeInBits())
       return SDValue();
 
     // Only handle cases where both indexes are constants with the same type.
@@ -9008,30 +9028,18 @@ SDValue DAGCombiner::visitEXTRACT_SUBVECTOR(SDNode* N) {
       // Combine:
       //    (extract_subvec (insert_subvec V1, V2, InsIdx), ExtIdx)
       // Into:
-      //    indices are equal => V1
+      //    indices are equal or bit offsets are equal => V1
       //    otherwise => (extract_subvec V1, ExtIdx)
-      if (InsIdx->getZExtValue() == ExtIdx->getZExtValue())
-        return V->getOperand(1);
-      return DAG.getNode(ISD::EXTRACT_SUBVECTOR, N->getDebugLoc(), NVT,
-                         V->getOperand(0), N->getOperand(1));
+      if (InsIdx->getZExtValue() * SmallVT.getScalarType().getSizeInBits() ==
+          ExtIdx->getZExtValue() * NVT.getScalarType().getSizeInBits())
+        return DAG.getNode(ISD::BITCAST, dl, NVT, V->getOperand(1));
+      return DAG.getNode(ISD::EXTRACT_SUBVECTOR, dl, NVT,
+                         DAG.getNode(ISD::BITCAST, dl,
+                                     N->getOperand(0).getValueType(),
+                                     V->getOperand(0)), N->getOperand(1));
     }
   }
 
-  if (V->getOpcode() == ISD::CONCAT_VECTORS) {
-    // Combine:
-    //    (extract_subvec (concat V1, V2, ...), i)
-    // Into:
-    //    Vi if possible
-    // Only operand 0 is checked as 'concat' assumes all inputs of the same type.
-    if (V->getOperand(0).getValueType() != NVT)
-      return SDValue();
-    unsigned Idx = dyn_cast<ConstantSDNode>(N->getOperand(1))->getZExtValue();
-    unsigned NumElems = NVT.getVectorNumElements();
-    assert((Idx % NumElems) == 0 &&
-           "IDX in concat is not a multiple of the result vector length.");
-    return V->getOperand(Idx / NumElems);
-  }
-
   return SDValue();
 }
 
diff --git a/test/CodeGen/X86/avx-load-store.ll b/test/CodeGen/X86/avx-load-store.ll
index 432852d47d..0afaff830d 100644
--- a/test/CodeGen/X86/avx-load-store.ll
+++ b/test/CodeGen/X86/avx-load-store.ll
@@ -114,3 +114,16 @@ cif_mixed_test_any_check:                         ; preds = %cif_mask_mixed
   unreachable
 }
 
+; CHECK: add8i32
+; CHECK: vmovups
+; CHECK: vmovups
+; CHECK-NOT: vinsertf128
+; CHECK-NOT: vextractf128
+; CHECK: vmovups
+; CHECK: vmovups
+define void @add8i32(<8 x i32>* %ret, <8 x i32>* %bp) nounwind {
+  %b = load <8 x i32>* %bp, align 1
+  %x = add <8 x i32> zeroinitializer, %b
+  store <8 x i32> %x, <8 x i32>* %ret, align 1
+  ret void
+}