Index: lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- lib/Target/X86/X86ISelLowering.cpp
+++ lib/Target/X86/X86ISelLowering.cpp
@@ -5629,12 +5629,11 @@
 
       if (ExtVT == MVT::i32 || ExtVT == MVT::f32 || ExtVT == MVT::f64 ||
           (ExtVT == MVT::i64 && Subtarget->is64Bit())) {
-        if (VT.is256BitVector() || VT.is512BitVector()) {
+        if (VT.is512BitVector()) {
           SDValue ZeroVec = getZeroVector(VT, Subtarget, DAG, dl);
           return DAG.getNode(ISD::INSERT_VECTOR_ELT, dl, VT, ZeroVec,
                              Item, DAG.getIntPtrConstant(0));
         }
-        assert(VT.is128BitVector() && "Expected an SSE value type!");
         Item = DAG.getNode(ISD::SCALAR_TO_VECTOR, dl, VT, Item);
         // Turn it into a MOVL (i.e. movss, movsd, or movd) to a zero vector.
         return getShuffleVectorZeroOrUndef(Item, 0, true, Subtarget, DAG);
@@ -9315,6 +9314,15 @@
   ArrayRef<int> Mask = SVOp->getMask();
   assert(Mask.size() == 8 && "Unexpected mask size for v8 shuffle!");
 
+  // If we have a single input to the zero element, insert that into V1 if we
+  // can do so cheaply.
+  int NumV2Elements =
+      std::count_if(Mask.begin(), Mask.end(), [](int M) { return M >= 8; });
+  if (NumV2Elements == 1 && Mask[0] >= 8)
+    if (SDValue Insertion = lowerVectorShuffleAsElementInsertion(
+            MVT::v8f32, DL, V1, V2, Mask, Subtarget, DAG))
+      return Insertion;
+
   if (SDValue Blend = lowerVectorShuffleAsBlend(DL, MVT::v8f32, V1, V2, Mask,
                                                 Subtarget, DAG))
     return Blend;
Index: test/CodeGen/X86/vector-shuffle-256-v8.ll
===================================================================
--- test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -131,11 +131,10 @@
 ;
 ; AVX2-LABEL: shuffle_v8f32_70000000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    movl $7, %eax
-; AVX2-NEXT:    vpinsrd $0, %eax, %xmm1, %xmm1
+; AVX2-NEXT:    vmovd %eax, %xmm1
 ; AVX2-NEXT:    vpxor %ymm2, %ymm2, %ymm2
-; AVX2-NEXT:    vinserti128 $0, %xmm1, %ymm2, %ymm1
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3,4,5,6,7]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -961,11 +960,10 @@
 ;
 ; AVX2-LABEL: shuffle_v8i32_70000000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    movl $7, %eax
-; AVX2-NEXT:    vpinsrd $0, %eax, %xmm1, %xmm1
+; AVX2-NEXT:    vmovd %eax, %xmm1
 ; AVX2-NEXT:    vpxor %ymm2, %ymm2, %ymm2
-; AVX2-NEXT:    vinserti128 $0, %xmm1, %ymm2, %ymm1
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm1 = ymm1[0],ymm2[1,2,3,4,5,6,7]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>