diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -12621,6 +12621,14 @@
   return SDValue();
 }
 
+static bool isBroadcastShuffleMask(ArrayRef<int> Mask) {
+  return isUndefOrEqual(Mask, 0);
+}
+
+static bool isNoopOrBroadcastShuffleMask(ArrayRef<int> Mask) {
+  return isNoopShuffleMask(Mask) || isBroadcastShuffleMask(Mask);
+}
+
 /// Generic routine to decompose a shuffle and blend into independent
 /// blends and permutes.
 ///
@@ -12654,6 +12662,38 @@
     }
   }
 
+  // If we effectively only demand the 0'th element of \p Input, and not only
+  // as 0'th element, then broadcast said input,
+  // and change \p InputMask to be a no-op (identity) mask.
+  auto canonicalizeBroadcastableInput = [DL, VT, &Subtarget,
+                                         &DAG](SDValue &Input,
+                                               MutableArrayRef<int> InputMask) {
+    unsigned EltSizeInBits = Input.getScalarValueSizeInBits();
+    if (!Subtarget.hasAVX2() &&
+        (!Subtarget.hasAVX() || EltSizeInBits < 32 || !MayFoldLoad(Input)))
+      return;
+    if (isNoopShuffleMask(InputMask))
+      return;
+    assert(isBroadcastShuffleMask(InputMask) &&
+           "Expected to demand only the 0'th element.");
+    Input = DAG.getNode(X86ISD::VBROADCAST, DL, VT, Input);
+    for (auto I : enumerate(InputMask)) {
+      int &InputMaskElt = I.value();
+      if (InputMaskElt >= 0)
+        InputMaskElt = I.index();
+    }
+  };
+
+  // Currently, we may need to produce one shuffle per input, and blend results.
+  // It is possible that the shuffle for one of the inputs is already a no-op.
+  // See if we can simplify non-no-op shuffles into broadcasts,
+  // which we consider to be strictly better than an arbitrary shuffle.
+  if (isNoopOrBroadcastShuffleMask(V1Mask) &&
+      isNoopOrBroadcastShuffleMask(V2Mask)) {
+    canonicalizeBroadcastableInput(V1, V1Mask);
+    canonicalizeBroadcastableInput(V2, V2Mask);
+  }
+
   // Try to lower with the simpler initial blend/unpack/rotate strategies unless
   // one of the input shuffles would be a no-op. We prefer to shuffle inputs as
   // the shuffle may be able to fold with a load or other benefit. However, when
diff --git a/llvm/test/CodeGen/X86/copy-low-subvec-elt-to-high-subvec-elt.ll b/llvm/test/CodeGen/X86/copy-low-subvec-elt-to-high-subvec-elt.ll
--- a/llvm/test/CodeGen/X86/copy-low-subvec-elt-to-high-subvec-elt.ll
+++ b/llvm/test/CodeGen/X86/copy-low-subvec-elt-to-high-subvec-elt.ll
@@ -284,7 +284,7 @@
 define <4 x i64> @vec256_eltty_i64_source_subvec_0_target_subvec_mask_3_binary(<4 x i64> %x, <4 x i64> %y) nounwind {
 ; CHECK-LABEL: vec256_eltty_i64_source_subvec_0_target_subvec_mask_3_binary:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vbroadcastsd %xmm1, %ymm1
+; CHECK-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,1]
 ; CHECK-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
 ; CHECK-NEXT:    retq
   %r = shufflevector <4 x i64> %x, <4 x i64> %y, <4 x i32> <i32 0, i32 4, i32 2, i32 4>
@@ -741,7 +741,7 @@
 define <32 x i8> @vec256_eltty_i8_source_subvec_0_target_subvec_mask_1_binary(<32 x i8> %x, <32 x i8> %y) nounwind {
 ; CHECK-LABEL: vec256_eltty_i8_source_subvec_0_target_subvec_mask_1_binary:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0]
+; CHECK-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; CHECK-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; CHECK-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; CHECK-NEXT:    retq
@@ -763,8 +763,7 @@
 define <32 x i8> @vec256_eltty_i8_source_subvec_0_target_subvec_mask_2_binary(<32 x i8> %x, <32 x i8> %y) nounwind {
 ; CHECK-LABEL: vec256_eltty_i8_source_subvec_0_target_subvec_mask_2_binary:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0]
-; CHECK-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm1
+; CHECK-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; CHECK-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0]
 ; CHECK-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; CHECK-NEXT:    retq
@@ -800,7 +799,7 @@
 ; CHECK-LABEL: vec256_eltty_i8_source_subvec_1_target_subvec_mask_1_unary:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; CHECK-NEXT:    vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0]
+; CHECK-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; CHECK-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; CHECK-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; CHECK-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/horizontal-sum.ll b/llvm/test/CodeGen/X86/horizontal-sum.ll
--- a/llvm/test/CodeGen/X86/horizontal-sum.ll
+++ b/llvm/test/CodeGen/X86/horizontal-sum.ll
@@ -143,9 +143,9 @@
 ; AVX2-SLOW-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
 ; AVX2-SLOW-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,3]
 ; AVX2-SLOW-NEXT:    vphaddd %xmm3, %xmm3, %xmm1
-; AVX2-SLOW-NEXT:    vpbroadcastd %xmm1, %xmm2
-; AVX2-SLOW-NEXT:    vpaddd %xmm1, %xmm2, %xmm1
-; AVX2-SLOW-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm2 = xmm1[1,1,1,1]
+; AVX2-SLOW-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
+; AVX2-SLOW-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
 ; AVX2-SLOW-NEXT:    retq
   %5 = shufflevector <4 x i32> %0, <4 x i32> poison, <2 x i32> <i32 0, i32 2>
   %6 = shufflevector <4 x i32> %0, <4 x i32> poison, <2 x i32> <i32 1, i32 3>
@@ -463,8 +463,7 @@
 ; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
 ; AVX2-FAST-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
 ; AVX2-FAST-NEXT:    vphaddd %xmm7, %xmm6, %xmm1
-; AVX2-FAST-NEXT:    vphaddd %xmm0, %xmm0, %xmm2
-; AVX2-FAST-NEXT:    vphaddd %xmm2, %xmm1, %xmm1
+; AVX2-FAST-NEXT:    vphaddd %xmm0, %xmm1, %xmm1
 ; AVX2-FAST-NEXT:    vpbroadcastq %xmm1, %ymm1
 ; AVX2-FAST-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
 ; AVX2-FAST-NEXT:    retq
@@ -745,16 +744,16 @@
 ; AVX2-SLOW-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm4[0],xmm1[0]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm2[3,3,3,3]
 ; AVX2-SLOW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
-; AVX2-SLOW-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
-; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm1 = xmm5[0,1],xmm2[2,3]
-; AVX2-SLOW-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
-; AVX2-SLOW-NEXT:    vpbroadcastq %xmm3, %xmm1
-; AVX2-SLOW-NEXT:    vpbroadcastd %xmm3, %xmm2
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm2 = xmm5[0,1],xmm2[2,3]
+; AVX2-SLOW-NEXT:    vpbroadcastd %xmm3, %xmm4
+; AVX2-SLOW-NEXT:    vpbroadcastq %xmm3, %xmm5
+; AVX2-SLOW-NEXT:    vpaddd %xmm4, %xmm5, %xmm4
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[3]
 ; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm3[2,2,2,2]
-; AVX2-SLOW-NEXT:    vpaddd %xmm4, %xmm2, %xmm2
-; AVX2-SLOW-NEXT:    vpaddd %xmm3, %xmm2, %xmm2
-; AVX2-SLOW-NEXT:    vpaddd %xmm2, %xmm1, %xmm1
-; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm2 = xmm2[0,1,2],xmm4[3]
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
+; AVX2-SLOW-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
 ; AVX2-SLOW-NEXT:    retq
 ;
 ; AVX2-FAST-LABEL: sequential_sum_v4i32_v4i32:
@@ -769,15 +768,15 @@
 ; AVX2-FAST-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm4[0],xmm1[0]
 ; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm4 = xmm2[3,3,3,3]
 ; AVX2-FAST-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm4[0]
+; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm2 = xmm5[0,1],xmm2[2,3]
+; AVX2-FAST-NEXT:    vphaddd %xmm3, %xmm3, %xmm4
+; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm5 = xmm3[2,2,2,2]
+; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm2 = xmm2[0,1,2],xmm5[3]
+; AVX2-FAST-NEXT:    vpbroadcastd %xmm4, %xmm4
+; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[3]
+; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm3[3]
 ; AVX2-FAST-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
-; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm1 = xmm5[0,1],xmm2[2,3]
-; AVX2-FAST-NEXT:    vpaddd %xmm0, %xmm1, %xmm0
-; AVX2-FAST-NEXT:    vphaddd %xmm3, %xmm3, %xmm1
-; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm2 = xmm3[2,2,2,2]
-; AVX2-FAST-NEXT:    vpbroadcastd %xmm1, %xmm1
-; AVX2-FAST-NEXT:    vpaddd %xmm3, %xmm1, %xmm1
-; AVX2-FAST-NEXT:    vpaddd %xmm1, %xmm2, %xmm1
-; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
+; AVX2-FAST-NEXT:    vpaddd %xmm0, %xmm2, %xmm0
 ; AVX2-FAST-NEXT:    retq
   %5 = shufflevector <4 x i32> %0, <4 x i32> %1, <2 x i32> <i32 0, i32 4>
   %6 = shufflevector <4 x i32> %0, <4 x i32> %1, <2 x i32> <i32 1, i32 5>
@@ -1082,28 +1081,28 @@
 ; SSSE3-FAST-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
 ; SSSE3-FAST-NEXT:    retq
 ;
-; AVX-SLOW-LABEL: reduction_sum_v4i32_v4i32:
-; AVX-SLOW:       # %bb.0:
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,3,2,3]
-; AVX-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[1,1,1,1]
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm1[2,3,2,3]
-; AVX-SLOW-NEXT:    vpaddd %xmm5, %xmm1, %xmm1
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm1[1,1,1,1]
-; AVX-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm2[2,3,2,3]
-; AVX-SLOW-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm2[1,1,1,1]
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm6 = xmm3[2,3,2,3]
-; AVX-SLOW-NEXT:    vpaddd %xmm6, %xmm3, %xmm3
-; AVX-SLOW-NEXT:    vpshufd {{.*#+}} xmm6 = xmm3[1,1,1,1]
-; AVX-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
-; AVX-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
-; AVX-SLOW-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
-; AVX-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
-; AVX-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
-; AVX-SLOW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
-; AVX-SLOW-NEXT:    retq
+; AVX1-SLOW-LABEL: reduction_sum_v4i32_v4i32:
+; AVX1-SLOW:       # %bb.0:
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,3,2,3]
+; AVX1-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[1,1,1,1]
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm1[2,3,2,3]
+; AVX1-SLOW-NEXT:    vpaddd %xmm5, %xmm1, %xmm1
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm1[1,1,1,1]
+; AVX1-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm2[2,3,2,3]
+; AVX1-SLOW-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm2[1,1,1,1]
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm6 = xmm3[2,3,2,3]
+; AVX1-SLOW-NEXT:    vpaddd %xmm6, %xmm3, %xmm3
+; AVX1-SLOW-NEXT:    vpshufd {{.*#+}} xmm6 = xmm3[1,1,1,1]
+; AVX1-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1]
+; AVX1-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; AVX1-SLOW-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
+; AVX1-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
+; AVX1-SLOW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX1-SLOW-NEXT:    retq
 ;
 ; AVX1-FAST-LABEL: reduction_sum_v4i32_v4i32:
 ; AVX1-FAST:       # %bb.0:
@@ -1122,6 +1121,28 @@
 ; AVX1-FAST-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
 ; AVX1-FAST-NEXT:    retq
 ;
+; AVX2-SLOW-LABEL: reduction_sum_v4i32_v4i32:
+; AVX2-SLOW:       # %bb.0:
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,3,2,3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[1,1,1,1]
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm1[2,3,2,3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm5, %xmm1, %xmm1
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm2[2,3,2,3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm5, %xmm2, %xmm2
+; AVX2-SLOW-NEXT:    vpshufd {{.*#+}} xmm5 = xmm3[2,3,2,3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm5, %xmm3, %xmm3
+; AVX2-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm5 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm4 = xmm4[0],xmm1[1],xmm4[2,3]
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm4 = xmm4[0,1],xmm5[2,3]
+; AVX2-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-SLOW-NEXT:    vpbroadcastd %xmm3, %xmm1
+; AVX2-SLOW-NEXT:    vpbroadcastd %xmm2, %xmm2
+; AVX2-SLOW-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
+; AVX2-SLOW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX2-SLOW-NEXT:    vpaddd %xmm4, %xmm0, %xmm0
+; AVX2-SLOW-NEXT:    retq
+;
 ; AVX2-FAST-LABEL: reduction_sum_v4i32_v4i32:
 ; AVX2-FAST:       # %bb.0:
 ; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,3,2,3]
@@ -1134,7 +1155,7 @@
 ; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm2 = xmm3[2,3,2,3]
 ; AVX2-FAST-NEXT:    vpaddd %xmm2, %xmm3, %xmm2
 ; AVX2-FAST-NEXT:    vphaddd %xmm2, %xmm1, %xmm1
-; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,0,2]
+; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
 ; AVX2-FAST-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
 ; AVX2-FAST-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
 ; AVX2-FAST-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/oddshuffles.ll b/llvm/test/CodeGen/X86/oddshuffles.ll
--- a/llvm/test/CodeGen/X86/oddshuffles.ll
+++ b/llvm/test/CodeGen/X86/oddshuffles.ll
@@ -2280,7 +2280,8 @@
 ;
 ; AVX2-FAST-LABEL: splat_v3i32:
 ; AVX2-FAST:       # %bb.0:
-; AVX2-FAST-NEXT:    vmovq {{.*#+}} xmm1 = mem[0],zero
+; AVX2-FAST-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
+; AVX2-FAST-NEXT:    vpinsrd $2, 8(%rdi), %xmm0, %xmm1
 ; AVX2-FAST-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-FAST-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3,4,5,6,7]
 ; AVX2-FAST-NEXT:    vpshufb {{.*#+}} ymm1 = zero,zero,zero,zero,zero,zero,zero,zero,ymm1[0,1,2,3],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero