Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14617,6 +14617,38 @@
   return SDValue();
 }
 
+// Combine shuffles of splat-shuffles of the form:
+// shuffle (shuffle V, undef, splat-mask), undef, M
+// If splat-mask contains undef elements, we need to be careful about
+// introducing undef's in the folded mask which are not the result of composing
+// the masks of the shuffles.
+static SDValue combineShuffleOfSplat(ArrayRef<int> UserMask,
+                                     ShuffleVectorSDNode *Splat,
+                                     SelectionDAG &DAG) {
+  EVT VT = Splat->getValueType(0);
+  unsigned NumElts = VT.getVectorNumElements();
+  SmallVector<int, 32> NewMask;
+  // Build the new mask by composing the user shuffle's mask with the
+  // splat-shuffle's mask. This is to ensure we don't introduce undef's
+  // incorrectly to the new mask.
+  // If the user shuffle's mask element is undef, take the respective mask
+  // value from the splat-shuffle. This will increase the chances that the new
+  // mask will result in being identical to the splat-shuffle's mask, which
+  // will allow to simplify to the splat-shuffle itself.
+  for (unsigned i = 0; i < NumElts; ++i)
+    if (UserMask[i] < 0)
+      NewMask.push_back(Splat->getMaskElt(i));
+    else
+      NewMask.push_back(Splat->getMaskElt(UserMask[i]));
+  // If the new composed mask is identical to the splat-shuffle's mask, simplify
+  // to the splat-shuffle itself. Otherwise create a new shuffle with the new
+  // mask.
+  if (Splat->getMask().equals(NewMask))
+    return SDValue(Splat, 0);
+  return DAG.getVectorShuffle(VT, SDLoc(Splat), Splat->getOperand(0),
+                              Splat->getOperand(1), NewMask);
+}
+
 SDValue DAGCombiner::visitVECTOR_SHUFFLE(SDNode *N) {
   EVT VT = N->getValueType(0);
   unsigned NumElts = VT.getVectorNumElements();
@@ -14663,6 +14695,12 @@
       return DAG.getVectorShuffle(VT, SDLoc(N), N0, N1, NewMask);
   }
 
+  // A shuffle of a single vector that is a splat can always be folded.
+  if (auto *N0Shuf = dyn_cast<ShuffleVectorSDNode>(N0))
+    if (N1->isUndef() && N0Shuf->isSplat())
+      if (SDValue V = combineShuffleOfSplat(SVN->getMask(), N0Shuf, DAG))
+        return V;
+
   // If it is a splat, check if the argument vector is another splat or a
   // build_vector.
   if (SVN->isSplat() && SVN->getSplatIndex() < (int)NumElts) {
Index: test/CodeGen/X86/shuffle-of-splat-multiuses.ll
===================================================================
--- test/CodeGen/X86/shuffle-of-splat-multiuses.ll
+++ test/CodeGen/X86/shuffle-of-splat-multiuses.ll
@@ -5,9 +5,8 @@
 define <2 x double> @foo2(<2 x double> %v, <2 x double> *%p) nounwind {
 ; AVX2-LABEL: foo2:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,1]
-; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm1[1,0]
-; AVX2-NEXT:    vmovapd %xmm1, (%rdi)
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
+; AVX2-NEXT:    vmovapd %xmm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <2 x double> %v, <2 x double> undef, <2 x i32> <i32 1, i32 1>
   %res1 = shufflevector<2 x double> %res, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
@@ -18,9 +17,8 @@
 define <4 x double> @foo4(<4 x double> %v, <4 x double> *%p) nounwind {
 ; AVX2-LABEL: foo4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,2,2]
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm1[2,0,2,3]
-; AVX2-NEXT:    vmovapd %ymm1, (%rdi)
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,2]
+; AVX2-NEXT:    vmovapd %ymm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <4 x double> %v, <4 x double> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
   %res1 = shufflevector<4 x double> %res, <4 x double> undef, <4 x i32> <i32 2, i32 0, i32 undef, i32 undef>
@@ -32,10 +30,8 @@
 ; AVX2-LABEL: foo8:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,2,2]
-; AVX2-NEXT:    vmovaps {{.*#+}} ymm0 = <2,0,u,u,5,1,3,7>
-; AVX2-NEXT:    vpermps %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vmovapd %ymm1, (%rdi)
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,2]
+; AVX2-NEXT:    vmovapd %ymm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <8 x float> %v, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
   %res1 = shufflevector<8 x float> %res, <8 x float> undef, <8 x i32> <i32 2, i32 0, i32 undef, i32 undef, i32 5, i32 1, i32 3, i32 7>
@@ -76,9 +72,10 @@
 define <4 x i32> @undef_splatmask4(<4 x i32> %v, <4 x i32>* %p) nounwind {
 ; AVX2-LABEL: undef_splatmask4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
-; AVX2-NEXT:    vmovdqa %xmm1, (%rdi)
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,2,2,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
+; AVX2-NEXT:    vmovdqa %xmm0, (%rdi)
+; AVX2-NEXT:    vmovdqa %xmm1, %xmm0
 ; AVX2-NEXT:    retq
   %res = shufflevector <4 x i32> %v, <4 x i32> undef, <4 x i32> <i32 2, i32 undef, i32 2, i32 undef>
   %res1 = shufflevector <4 x i32> %res, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 undef>
@@ -89,9 +86,10 @@
 define <4 x i32> @undef_splatmask5(<4 x i32> %v, <4 x i32>* %p) nounwind {
 ; AVX2-LABEL: undef_splatmask5:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpbroadcastq %xmm0, %xmm1
-; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
-; AVX2-NEXT:    vmovdqa %xmm1, (%rdi)
+; AVX2-NEXT:    vpbroadcastd %xmm0, %xmm1
+; AVX2-NEXT:    vpbroadcastq %xmm0, %xmm0
+; AVX2-NEXT:    vmovdqa %xmm0, (%rdi)
+; AVX2-NEXT:    vmovdqa %xmm1, %xmm0
 ; AVX2-NEXT:    retq
   %res = shufflevector <4 x i32> %v, <4 x i32> undef, <4 x i32> <i32 0, i32 undef, i32 0, i32 undef>
   %res1 = shufflevector <4 x i32> %res, <4 x i32> undef, <4 x i32> <i32 0, i32 2, i32 undef, i32 3>