Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14186,10 +14186,18 @@
   EVT InVT1 = VecIn1.getValueType();
   EVT InVT2 = VecIn2.getNode() ? VecIn2.getValueType() : InVT1;
 
-  unsigned Vec2Offset = InVT1.getVectorNumElements();
+  unsigned Vec2Offset = 0;
   unsigned NumElems = VT.getVectorNumElements();
   unsigned ShuffleNumElems = NumElems;
 
+  // In case both the input vectors are extracted from same base
+  // vector we do not need extra addend (Vec2Offset) while
+  // computing shuffle mask.
+  if (!VecIn2 || !(VecIn1.getOpcode() == ISD::EXTRACT_SUBVECTOR) ||
+      !(VecIn2.getOpcode() == ISD::EXTRACT_SUBVECTOR) ||
+      !(VecIn1.getOperand(0) == VecIn2.getOperand(0)))
+    Vec2Offset = InVT1.getVectorNumElements();
+
   // We can't generate a shuffle node with mismatched input and output types.
   // Try to make the types match the type of the output.
   if (InVT1 != VT || InVT2 != VT) {
@@ -14359,6 +14367,50 @@
   if (VecIn.size() < 2)
     return SDValue();
 
+  // If all the Operands of BUILD_VECTOR extract from same
+  // vector, then split the vector efficiently based on the maximum
+  // vector access index and adjust the VectorMask and
+  // VecIn accordingly.
+  if (VecIn.size() == 2) {
+    unsigned MaxIndex = 0;
+    unsigned NearestPow2 = 0;
+    SDValue Vec = VecIn.back();
+    EVT InVT = Vec.getValueType();
+    MVT IdxTy = TLI.getVectorIdxTy(DAG.getDataLayout());
+    SmallVector<unsigned, 8> IndexVec(NumElems, 0);
+
+    for (unsigned i = 0; i < NumElems; i++) {
+      if (VectorMask[i] <= 0)
+        continue;
+      unsigned Index = N->getOperand(i).getConstantOperandVal(1);
+      IndexVec[i] = Index;
+      MaxIndex = std::max(MaxIndex, Index);
+    }
+
+    NearestPow2 = PowerOf2Ceil(MaxIndex);
+    if (InVT.isSimple() && (NearestPow2 > 2) &&
+        ((NumElems * 2) < NearestPow2)) {
+      unsigned SplitSize = NearestPow2 / 2;
+      EVT SplitVT = EVT::getVectorVT(*DAG.getContext(),
+                                     InVT.getVectorElementType(), SplitSize);
+      if (TLI.isTypeLegal(SplitVT)) {
+        SDValue VecIn2 = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SplitVT, Vec,
+                                     DAG.getConstant(SplitSize, DL, IdxTy));
+        SDValue VecIn1 = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SplitVT, Vec,
+                                     DAG.getConstant(0, DL, IdxTy));
+        VecIn.pop_back();
+        VecIn.push_back(VecIn1);
+        VecIn.push_back(VecIn2);
+
+        for (unsigned i = 0; i < NumElems; i++) {
+          if (VectorMask[i] <= 0)
+            continue;
+          VectorMask[i] = (IndexVec[i] < SplitSize) ? 1 : 2;
+        }
+      }
+    }
+  }
+
   // TODO: We want to sort the vectors by descending length, so that adjacent
   // pairs have similar length, and the longer vector is always first in the
   // pair.
Index: test/CodeGen/X86/shuffle-vs-trunc-512.ll
===================================================================
--- test/CodeGen/X86/shuffle-vs-trunc-512.ll
+++ test/CodeGen/X86/shuffle-vs-trunc-512.ll
@@ -311,83 +311,93 @@
 ;
 ; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
 ; AVX512BW:       # BB#0:
-; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
-; AVX512BW-NEXT:    vpextrb $1, %xmm0, %ecx
-; AVX512BW-NEXT:    vmovd %ecx, %xmm1
-; AVX512BW-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $13, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
-; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
-; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
-; AVX512BW-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
-; AVX512BW-NEXT:    vpextrb $1, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
-; AVX512BW-NEXT:    vpextrb $14, %xmm0, %eax
-; AVX512BW-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512BW-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
+; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512BW-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512BW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
 ; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
 ; AVX512BWVL:       # BB#0:
-; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %ecx
-; AVX512BWVL-NEXT:    vmovd %ecx, %xmm1
-; AVX512BWVL-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $13, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
-; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
-; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
-; AVX512BWVL-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
-; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
-; AVX512BWVL-NEXT:    vpextrb $14, %xmm0, %eax
-; AVX512BWVL-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BWVL-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512BWVL-NEXT:    vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512BWVL-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
+; AVX512BWVL-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
+; AVX512BWVL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512BWVL-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512BWVL-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512BWVL-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512BWVL-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512BWVL-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
 ; AVX512BWVL-NEXT:    vzeroupper
 ; AVX512BWVL-NEXT:    retq
   %res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
   ret <16 x i8> %res
 }
+
+define <4 x double> @PR34175(<32 x i16>* %p) {
+; AVX512F-LABEL: PR34175:
+; AVX512F:       # BB#0:
+; AVX512F-NEXT:    vmovdqu (%rdi), %ymm0
+; AVX512F-NEXT:    vmovdqu 32(%rdi), %ymm1
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512F-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512F-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
+; AVX512F-NEXT:    vpbroadcastd %xmm1, %xmm1
+; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; AVX512F-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX512F-NEXT:    vcvtdq2pd %xmm0, %ymm0
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: PR34175:
+; AVX512VL:       # BB#0:
+; AVX512VL-NEXT:    vmovdqu (%rdi), %ymm0
+; AVX512VL-NEXT:    vmovdqu 32(%rdi), %ymm1
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512VL-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX512VL-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512VL-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
+; AVX512VL-NEXT:    vpbroadcastd %xmm1, %xmm1
+; AVX512VL-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; AVX512VL-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX512VL-NEXT:    vcvtdq2pd %xmm0, %ymm0
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: PR34175:
+; AVX512BW:       # BB#0:
+; AVX512BW-NEXT:    vmovdqu64 (%rdi), %zmm0
+; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm1
+; AVX512BW-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX512BW-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
+; AVX512BW-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512BW-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX512BW-NEXT:    vpbroadcastd %xmm0, %xmm0
+; AVX512BW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
+; AVX512BW-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
+; AVX512BW-NEXT:    vcvtdq2pd %xmm0, %ymm0
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: PR34175:
+; AVX512BWVL:       # BB#0:
+; AVX512BWVL-NEXT:    vmovdqu64 (%rdi), %zmm0
+; AVX512BWVL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512BWVL-NEXT:    vmovdqa {{.*#+}} ymm2 = <0,8,16,24,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512BWVL-NEXT:    vpermi2w %ymm1, %ymm0, %ymm2
+; AVX512BWVL-NEXT:    vpmovzxwd {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
+; AVX512BWVL-NEXT:    vcvtdq2pd %xmm0, %ymm0
+; AVX512BWVL-NEXT:    retq
+  %v = load <32 x i16>, <32 x i16>* %p, align 2
+  %shuf = shufflevector <32 x i16> %v, <32 x i16> undef, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
+  %tofp = uitofp <4 x i16> %shuf to <4 x double>
+  ret <4 x double> %tofp
+}
Index: test/CodeGen/X86/vector-shuffle-512-v16.ll
===================================================================
--- test/CodeGen/X86/vector-shuffle-512-v16.ll
+++ test/CodeGen/X86/vector-shuffle-512-v16.ll
@@ -286,13 +286,10 @@
 define <4 x i32> @test_v16i32_0_1_2_12 (<16 x i32> %v) {
 ; ALL-LABEL: test_v16i32_0_1_2_12:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpextrd $1, %xmm0, %eax
-; ALL-NEXT:    vpinsrd $1, %eax, %xmm0, %xmm1
-; ALL-NEXT:    vpextrd $2, %xmm0, %eax
-; ALL-NEXT:    vpinsrd $2, %eax, %xmm1, %xmm1
-; ALL-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
-; ALL-NEXT:    vmovd %xmm0, %eax
-; ALL-NEXT:    vpinsrd $3, %eax, %xmm1, %xmm0
+; ALL-NEXT:    vextracti32x8 $1, %zmm0, %ymm1
+; ALL-NEXT:    vextracti128 $1, %ymm1, %xmm1
+; ALL-NEXT:    vpbroadcastd %xmm1, %xmm1
+; ALL-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
 ; ALL-NEXT:    vzeroupper
 ; ALL-NEXT:    retq
   %res = shufflevector <16 x i32> %v, <16 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 12>
Index: test/CodeGen/X86/vector-shuffle-512-v8.ll
===================================================================
--- test/CodeGen/X86/vector-shuffle-512-v8.ll
+++ test/CodeGen/X86/vector-shuffle-512-v8.ll
@@ -2726,20 +2726,17 @@
 define <2 x i64> @test_v8i64_2_5 (<8 x i64> %v) {
 ; AVX512F-LABEL: test_v8i64_2_5:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vextracti32x4 $2, %zmm0, %xmm1
-; AVX512F-NEXT:    vextracti32x4 $1, %zmm0, %xmm0
+; AVX512F-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
 ; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512F-32-LABEL: test_v8i64_2_5:
 ; AVX512F-32:       # BB#0:
-; AVX512F-32-NEXT:    vextracti32x4 $1, %zmm0, %xmm1
-; AVX512F-32-NEXT:    vextracti32x4 $2, %zmm0, %xmm0
-; AVX512F-32-NEXT:    vpextrd $2, %xmm0, %eax
-; AVX512F-32-NEXT:    vpinsrd $2, %eax, %xmm1, %xmm1
-; AVX512F-32-NEXT:    vpextrd $3, %xmm0, %eax
-; AVX512F-32-NEXT:    vpinsrd $3, %eax, %xmm1, %xmm0
+; AVX512F-32-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; AVX512F-32-NEXT:    vextracti128 $1, %ymm0, %xmm0
+; AVX512F-32-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = shufflevector <8 x i64> %v, <8 x i64> undef, <2 x i32> <i32 2, i32 5>
Index: test/CodeGen/X86/x86-interleaved-access.ll
===================================================================
--- test/CodeGen/X86/x86-interleaved-access.ll
+++ test/CodeGen/X86/x86-interleaved-access.ll
@@ -567,37 +567,37 @@
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; AVX2-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
-; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm3
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm4, %xmm3, %xmm5
-; AVX2-NEXT:    vpshufb %xmm4, %xmm1, %xmm4
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
-; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm5
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm6 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm6, %xmm5, %xmm7
-; AVX2-NEXT:    vpshufb %xmm6, %xmm0, %xmm6
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
-; AVX2-NEXT:    vpblendd {{.*#+}} xmm4 = xmm6[0,1],xmm4[2,3]
-; AVX2-NEXT:    vpcmpeqb %xmm4, %xmm2, %xmm2
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <u,u,u,u,2,6,10,14,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm4, %xmm3, %xmm6
-; AVX2-NEXT:    vpshufb %xmm4, %xmm1, %xmm4
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm6 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm6, %xmm5, %xmm7
-; AVX2-NEXT:    vpshufb %xmm6, %xmm0, %xmm6
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1]
-; AVX2-NEXT:    vpblendd {{.*#+}} xmm4 = xmm6[0,1],xmm4[2,3]
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm6 = <u,u,u,u,3,7,11,15,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm6, %xmm3, %xmm3
-; AVX2-NEXT:    vpshufb %xmm6, %xmm1, %xmm1
-; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
-; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
-; AVX2-NEXT:    vpshufb %xmm3, %xmm5, %xmm5
-; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vextracti128 $1, %ymm1, %xmm4
+; AVX2-NEXT:    vpshufb %xmm3, %xmm4, %xmm5
+; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm3
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm3[0],xmm5[0],xmm3[1],xmm5[1]
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm5 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm6
+; AVX2-NEXT:    vpshufb %xmm5, %xmm6, %xmm7
+; AVX2-NEXT:    vpshufb %xmm5, %xmm0, %xmm5
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm3 = xmm5[0,1],xmm3[2,3]
+; AVX2-NEXT:    vpcmpeqb %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <u,u,u,u,2,6,10,14,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm3, %xmm4, %xmm5
+; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm3
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm3[0],xmm5[0],xmm3[1],xmm5[1]
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm5 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm5, %xmm6, %xmm7
+; AVX2-NEXT:    vpshufb %xmm5, %xmm0, %xmm5
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm5 = xmm5[0],xmm7[0],xmm5[1],xmm7[1]
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm3 = xmm5[0,1],xmm3[2,3]
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm5 = <u,u,u,u,3,7,11,15,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
+; AVX2-NEXT:    vpshufb %xmm5, %xmm1, %xmm1
+; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1]
+; AVX2-NEXT:    vmovdqa {{.*#+}} xmm4 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX2-NEXT:    vpshufb %xmm4, %xmm6, %xmm5
+; AVX2-NEXT:    vpshufb %xmm4, %xmm0, %xmm0
 ; AVX2-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm5[0],xmm0[1],xmm5[1]
 ; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
-; AVX2-NEXT:    vpcmpeqb %xmm0, %xmm4, %xmm0
+; AVX2-NEXT:    vpcmpeqb %xmm0, %xmm3, %xmm0
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
 ; AVX2-NEXT:    vpand %xmm1, %xmm2, %xmm2
 ; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
@@ -836,15 +836,15 @@
 ; AVX512-NEXT:    vpmovdw %zmm1, %ymm3
 ; AVX512-NEXT:    vinserti64x4 $1, %ymm3, %zmm2, %zmm2
 ; AVX512-NEXT:    vpmovwb %zmm2, %ymm8
-; AVX512-NEXT:    vmovdqa {{.*#+}} xmm7 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
 ; AVX512-NEXT:    vextracti64x4 $1, %zmm1, %ymm14
 ; AVX512-NEXT:    vextracti128 $1, %ymm14, %xmm9
+; AVX512-NEXT:    vmovdqa {{.*#+}} xmm7 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
 ; AVX512-NEXT:    vpshufb %xmm7, %xmm9, %xmm4
 ; AVX512-NEXT:    vpshufb %xmm7, %xmm14, %xmm5
 ; AVX512-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm5[0],xmm4[0],xmm5[1],xmm4[1]
 ; AVX512-NEXT:    vinserti128 $1, %xmm4, %ymm0, %ymm5
-; AVX512-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
 ; AVX512-NEXT:    vextracti128 $1, %ymm1, %xmm10
+; AVX512-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
 ; AVX512-NEXT:    vpshufb %xmm3, %xmm10, %xmm6
 ; AVX512-NEXT:    vpshufb %xmm3, %xmm1, %xmm4
 ; AVX512-NEXT:    vpunpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]