[X86][LLVM]Expanding Supports lowerInterleavedStore() in X86InterleavedAccess (VF8 stride 4).

[m_zuckerman]

Summary

This patch expands the support of lowerInterleavedStore to 8x8i stride 4.

LLVM creates suboptimal shuffle code-gen for AVX2. In overall, this patch is a specific fix for the pattern (Strid=4 VF=8) and we plan to include more patterns in the future.

The patch goal is to optimize the following sequence:
At the end of the computation, we have xmm2, xmm0, xmm12 and xmm3 holding
each 8 chars:

c0, c1, , c7
m0, m1, , m7
y0, y1, , y7
k0, k1, ., k7

And these need to be transposed/interleaved and stored like so:

c0 m0 y0 k0 c1 m1 y1 k1 c2 m2 y2 k2 c3 m3 y3 k3 ....

[RKSimon]

lib/Target/X86/X86InterleavedAccess.cpp

213

createLowUnpackMask

[Farhana]

lib/Target/X86/X86InterleavedAccess.cpp

213

Can you please add some comments about what this function does?

[Farhana]

lib/Target/X86/X86InterleavedAccess.cpp

134

Please remove the extra space after "&&".

215

Please remove the unknown character.

219

Is there anything special about this unpackMask? Why do we need a separate unpackmask generator? Why aren't you extending the createUnpackShuffleMask()? If createLowUnpackMask is unpacking in a different way than createUnpackShuffleMask() that distinction should be documented and clearly noted why we need a separate unpackMask-creator.

[Farhana]

lib/Target/X86/X86InterleavedAccess.cpp

134

Do we also need to check DL.getTypeSizeInBits(ShuffleVecTy) == 256 here?

[m_zuckerman]

lib/Target/X86/X86InterleavedAccess.cpp

134

Yes since in default mode, the compose function creates 4 xmm where only half of the wide is been used. I want that high bits will be left undef so I am checking 4*xmm = 256 in the next step will fill the undef part.

219

The regular unpack function doesn't create * 2XN * as we need in this case and creates only half from one vector and another half from the second vector. In mine function, we use all the vector and the not only half. For the backend, the result is the same but the way they create is different.

[m_zuckerman]

Ping

[zvi]

If this patch is still in review please rebase it.

[zvi]

lib/Target/X86/X86InterleavedAccess.cpp

218

'unsigned' looks like a more suitable type, That will also allow 'i' in the for loop below to be of 'unsigned' type, and that is better because it is being pushed into Mask, a container of type 'uint32_t'.

228

The comment doesn't address the special case v8i8. Can you please explain why the exception is needed?

230

*scaleVectorType

248

Can you please commit these minor changes: leaner computation of VT and Half, variable renaming in a couple of lines below as an NFC commit and rebase this patch?

279

I think it would be better to create a function that handles the v8i8 case instead of having these if's + early exit. It will also allow reomving the if from scaleVectorType to the point where it may not be needed.

[zvi]

LGTM, thanks!

lib/Target/X86/X86InterleavedAccess.cpp

if (isa<LoadInst>(Inst)) {
     WideInstSize = DL.getTypeSizeInBits(Shuffles[0]->getType());
 
   // We support shuffle represents stride 4 for byte type with size of
   // WideInstSize.
   if (ShuffleElemSize == 64 && WideInstSize == 1024 && Factor == 4)
      return true;
 
   if (ShuffleElemSize == 8 && isa<StoreInst>(Inst) && Factor == 4 &&
-      (WideInstSize == 512 || WideInstSize == 1024))
+      (WideInstSize == 256 || WideInstSize == 512 || WideInstSize == 1024))
      return true;
 
   if (ShuffleElemSize == 8 && isa<LoadInst>(Inst) && Factor == 3 &&
       (WideInstSize == 384 || WideInstSize == 768))
      return true;
 
   return false;
 }
 
 void X86InterleavedAccessGroup::decompose(
     Instruction *VecInst, unsigned NumSubVectors, VectorType *SubVecTy,
     SmallVectorImpl<Instruction *> &DecomposedVectors) {
static void createConcatShuffleMask(int NumElements,
   int NumHalfElements = NumElements / 2;
   int Offset = Low ? 0 : NumHalfElements;
   for (int i = 0; i < NumHalfElements; ++i)
     Mask.push_back(i + Offset);
   for (int i = 0; i < NumHalfElements; ++i)
     Mask.push_back(i + Offset + NumElements);
 }
 
+//  createLowUnpackMask returns shuffle mask of size  2 * N.
+//  The shuffle pattern is as following :
+//  (0, NumElements, 1, NumElements + 1, ... , NumElements - 1,
+//  2 * NumElements - 1).
+//  We are assuming that VF*type = half Xmm.
+static void createLowUnpackMask(int NumElements,
+                                SmallVectorImpl<uint32_t> &Mask, MVT VT) {
+  int VectorSize = VT.getSizeInBits();
+  assert(VectorSize == 64 && "Supporting only at half xmm");
+  for (int i = 0; i < NumElements; ++i) {
+    Mask.push_back(i);
+    Mask.push_back(i + NumElements);
+  }
+}
+
+// Changing the scale of the vector type by reducing the number of elements and
+// doubling the scalar size.
+static MVT scaleVevtorType(MVT VT) {
+  if (VT == MVT::v8i8)
+    return MVT::v8i16;
+  unsigned ScalarSize = VT.getVectorElementType().getScalarSizeInBits() * 2;
+  return MVT::getVectorVT(MVT::getIntegerVT(ScalarSize),
+                          VT.getVectorNumElements() / 2);
+}
+
 void X86InterleavedAccessGroup::interleave8bitStride4(
     ArrayRef<Instruction *> Matrix, SmallVectorImpl<Value *> &TransposedMatrix,
     unsigned numberOfElement) {
 
   // Example: Assuming we start from the following vectors:
   // Matrix[0]= c0 c1 c2 c3 c4 ... c31
   // Matrix[1]= m0 m1 m2 m3 m4 ... m31
   // Matrix[2]= y0 y1 y2 y3 y4 ... y31
   // Matrix[3]= k0 k1 k2 k3 k4 ... k31
 
-  Type *VecTyepVt = VectorType::get(Type::getInt8Ty(Shuffles[0]->getContext()),
-                                    numberOfElement);
-  Type *VecTyepVtHalf = VectorType::get(
-      Type::getInt16Ty(Shuffles[0]->getContext()), numberOfElement / 2);
-  MVT VT = MVT::getVT(VecTyepVt);
-  MVT HalfVT = MVT::getVT(VecTyepVtHalf);
-
-  TransposedMatrix.resize(4);
+  MVT VT = MVT::getVectorVT(MVT::i8, numberOfElement);
+  MVT HalfVT = scaleVevtorType(VT);
 
-  SmallVector<uint32_t, 32> MaskHighTemp;
-  SmallVector<uint32_t, 32> MaskLowTemp;
+  SmallVector<uint32_t, 32> MaskHigh;
+  SmallVector<uint32_t, 32> MaskLow;
   SmallVector<uint32_t, 32> MaskHighTemp1;
   SmallVector<uint32_t, 32> MaskLowTemp1;
-  SmallVector<uint32_t, 32> MaskHighTemp2;
-  SmallVector<uint32_t, 32> MaskLowTemp2;
+  SmallVector<uint32_t, 32> MaskHighWord;
+  SmallVector<uint32_t, 32> MaskLowWord;
   SmallVector<uint32_t, 32> ConcatLow;
   SmallVector<uint32_t, 32> ConcatHigh;
 
   // MaskHighTemp and MaskLowTemp built in the vpunpckhbw and vpunpcklbw X86
   // shuffle pattern.
 
-  createUnpackShuffleMask<uint32_t>(VT, MaskHighTemp, false, false);
-  createUnpackShuffleMask<uint32_t>(VT, MaskLowTemp, true, false);
-  ArrayRef<uint32_t> MaskHigh = makeArrayRef(MaskHighTemp);
-  ArrayRef<uint32_t> MaskLow = makeArrayRef(MaskLowTemp);
-
-  // ConcatHigh and ConcatLow built in the vperm2i128 and vinserti128 X86
-  // shuffle pattern.
-
-  createConcatShuffleMask(32, ConcatLow, true);
-  createConcatShuffleMask(32, ConcatHigh, false);
-  ArrayRef<uint32_t> MaskConcatLow = makeArrayRef(ConcatLow);
-  ArrayRef<uint32_t> MaskConcatHigh = makeArrayRef(ConcatHigh);
+  createUnpackShuffleMask<uint32_t>(VT, MaskHigh, false, false);
 
   // MaskHighTemp1 and MaskLowTemp1 built in the vpunpckhdw and vpunpckldw X86
   // shuffle pattern.
 
   createUnpackShuffleMask<uint32_t>(HalfVT, MaskLowTemp1, true, false);
   createUnpackShuffleMask<uint32_t>(HalfVT, MaskHighTemp1, false, false);
-  scaleShuffleMask<uint32_t>(2, makeArrayRef(MaskHighTemp1), MaskHighTemp2);
-  scaleShuffleMask<uint32_t>(2, makeArrayRef(MaskLowTemp1), MaskLowTemp2);
-  ArrayRef<uint32_t> MaskHighWord = makeArrayRef(MaskHighTemp2);
-  ArrayRef<uint32_t> MaskLowWord = makeArrayRef(MaskLowTemp2);
+  scaleShuffleMask<uint32_t>(2, MaskHighTemp1, MaskHighWord);
+  scaleShuffleMask<uint32_t>(2, MaskLowTemp1, MaskLowWord);
 
   // IntrVec1Low  = c0  m0  c1  m1 ... c7  m7  | c16 m16 c17 m17 ... c23 m23
   // IntrVec1High = c8  m8  c9  m9 ... c15 m15 | c24 m24 c25 m25 ... c31 m31
   // IntrVec2Low  = y0  k0  y1  k1 ... y7  k7  | y16 k16 y17 k17 ... y23 k23
   // IntrVec2High = y8  k8  y9  k9 ... y15 k15 | y24 k24 y25 k25 ... y31 k31
 
-  Value *IntrVec1Low =
-      Builder.CreateShuffleVector(Matrix[0], Matrix[1], MaskLow);
-  Value *IntrVec1High =
-      Builder.CreateShuffleVector(Matrix[0], Matrix[1], MaskHigh);
-  Value *IntrVec2Low =
-      Builder.CreateShuffleVector(Matrix[2], Matrix[3], MaskLow);
-  Value *IntrVec2High =
-      Builder.CreateShuffleVector(Matrix[2], Matrix[3], MaskHigh);
+  Value *IntrVec1Low, *IntrVec1High, *IntrVec2Low, *IntrVec2High;
+  if (VT == MVT::v8i8) {
+    TransposedMatrix.resize(2);
+    createLowUnpackMask(8, MaskLow, VT);
+  } else {
+    TransposedMatrix.resize(4);
+    IntrVec1High = Builder.CreateShuffleVector(Matrix[0], Matrix[1], MaskHigh);
+    IntrVec2High = Builder.CreateShuffleVector(Matrix[2], Matrix[3], MaskHigh);
+    createUnpackShuffleMask<uint32_t>(VT, MaskLow, true, false);
+  }
+
+  IntrVec1Low = Builder.CreateShuffleVector(Matrix[0], Matrix[1], MaskLow);
+  IntrVec2Low = Builder.CreateShuffleVector(Matrix[2], Matrix[3], MaskLow);
 
   // cmyk4  cmyk5  cmyk6   cmyk7  | cmyk20 cmyk21 cmyk22 cmyk23
   // cmyk12 cmyk13 cmyk14  cmyk15 | cmyk28 cmyk29 cmyk30 cmyk31
   // cmyk0  cmyk1  cmyk2   cmyk3  | cmyk16 cmyk17 cmyk18 cmyk19
   // cmyk8  cmyk9  cmyk10  cmyk11 | cmyk24 cmyk25 cmyk26 cmyk27
 
+  Value *Low =
+      Builder.CreateShuffleVector(IntrVec1Low, IntrVec2Low, MaskLowWord);
   Value *High =
       Builder.CreateShuffleVector(IntrVec1Low, IntrVec2Low, MaskHighWord);
+
+  if (VT == MVT::v8i8) {
+    TransposedMatrix[0] = Low;
+    TransposedMatrix[1] = High;
+    return;
+  }
+
   Value *High1 =
       Builder.CreateShuffleVector(IntrVec1High, IntrVec2High, MaskHighWord);
-  Value *Low =
-      Builder.CreateShuffleVector(IntrVec1Low, IntrVec2Low, MaskLowWord);
   Value *Low1 =
       Builder.CreateShuffleVector(IntrVec1High, IntrVec2High, MaskLowWord);
 
   if (VT == MVT::v16i8) {
     TransposedMatrix[0] = Low;
     TransposedMatrix[1] = High;
     TransposedMatrix[2] = Low1;
     TransposedMatrix[3] = High1;
     return;
   }
-  // cmyk0  cmyk1  cmyk2   cmyk3  | cmyk4  cmyk5  cmyk6   cmyk7
-  // cmyk8  cmyk9  cmyk10  cmyk11 | cmyk12 cmyk13 cmyk14  cmyk15
+
+  // ConcatHigh and ConcatLow built in the vperm2i128 and vinserti128 X86
+  // shuffle pattern.
+
+  createConcatShuffleMask(numberOfElement, ConcatLow, true);
+  createConcatShuffleMask(numberOfElement, ConcatHigh, false);
+
+  // cmyk0  cmyk1  cmyk2  cmyk3   | cmyk4  cmyk5  cmyk6  cmyk7
+  // cmyk8  cmyk9  cmyk10 cmyk11  | cmyk12 cmyk13 cmyk14 cmyk15
   // cmyk16 cmyk17 cmyk18 cmyk19  | cmyk20 cmyk21 cmyk22 cmyk23
   // cmyk24 cmyk25 cmyk26 cmyk27  | cmyk28 cmyk29 cmyk30 cmyk31
 
-  TransposedMatrix[0] = Builder.CreateShuffleVector(Low, High, MaskConcatLow);
-  TransposedMatrix[1] = Builder.CreateShuffleVector(Low1, High1, MaskConcatLow);
-  TransposedMatrix[2] = Builder.CreateShuffleVector(Low, High, MaskConcatHigh);
-  TransposedMatrix[3] =
-      Builder.CreateShuffleVector(Low1, High1, MaskConcatHigh);
+  TransposedMatrix[0] = Builder.CreateShuffleVector(Low, High, ConcatLow);
+  TransposedMatrix[1] = Builder.CreateShuffleVector(Low1, High1, ConcatLow);
+  TransposedMatrix[2] = Builder.CreateShuffleVector(Low, High, ConcatHigh);
+  TransposedMatrix[3] = Builder.CreateShuffleVector(Low1, High1, ConcatHigh);
 }
 
 //  createShuffleStride returns shuffle mask of size N.
 //  The shuffle pattern is as following :
 //  {0, Stride%(VF/Lane), (2*Stride%(VF/Lane))...(VF*Stride/Lane)%(VF/Lane),
 //  (VF/ Lane) ,(VF / Lane)+Stride%(VF/Lane),...,
 //  (VF / Lane)+(VF*Stride/Lane)%(VF/Lane)}
 //  Where Lane is the # of lanes in a register:
decompose(Shuffles[0], Factor, VectorType::get(ShuffleEltTy, NumSubVecElems),
             DecomposedVectors);
 
   //   2. Transpose the interleaved-vectors into vectors of contiguous
   //      elements.
   switch (NumSubVecElems) {
   case 4:
     transpose_4x4(DecomposedVectors, TransposedVectors);
     break;
+  case 8:
   case 16:
   case 32:
     interleave8bitStride4(DecomposedVectors, TransposedVectors, NumSubVecElems);
     break;
   default:
     return false;
   }
 

test/CodeGen/X86/x86-interleaved-access.ll

; AVX512-NEXT:    retq
   store <16 x i64> %interleaved.vec, <16 x i64>* %ptr, align 16
   ret void
 }
 
 
 define void @interleaved_store_vf32_i8_stride4(<32 x i8> %x1, <32 x i8> %x2, <32 x i8> %x3, <32 x i8> %x4, <128 x i8>* %p) {
 ; AVX1-LABEL: interleaved_store_vf32_i8_stride4:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm9 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm8 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm5
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm6
-; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm7 = xmm6[0],xmm5[0],xmm6[1],xmm5[1],xmm6[2],xmm5[2],xmm6[3],xmm5[3],xmm6[4],xmm5[4],xmm6[5],xmm5[5],xmm6[6],xmm5[6],xmm6[7],xmm5[7]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm8 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm1 = xmm6[8],xmm5[8],xmm6[9],xmm5[9],xmm6[10],xmm5[10],xmm6[11],xmm5[11],xmm6[12],xmm5[12],xmm6[13],xmm5[13],xmm6[14],xmm5[14],xmm6[15],xmm5[15]
-; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm5 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
-; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm6
-; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm4 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm2 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm0 = xmm0[8],xmm6[8],xmm0[9],xmm6[9],xmm0[10],xmm6[10],xmm0[11],xmm6[11],xmm0[12],xmm6[12],xmm0[13],xmm6[13],xmm0[14],xmm6[14],xmm0[15],xmm6[15]
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm7[4],xmm4[4],xmm7[5],xmm4[5],xmm7[6],xmm4[6],xmm7[7],xmm4[7]
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm6 = xmm9[4],xmm5[4],xmm9[5],xmm5[5],xmm9[6],xmm5[6],xmm9[7],xmm5[7]
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm6, %ymm10
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm11 = xmm8[4],xmm2[4],xmm8[5],xmm2[5],xmm8[6],xmm2[6],xmm8[7],xmm2[7]
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm11, %ymm3
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm4 = xmm7[0],xmm4[0],xmm7[1],xmm4[1],xmm7[2],xmm4[2],xmm7[3],xmm4[3]
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm5 = xmm9[0],xmm5[0],xmm9[1],xmm5[1],xmm9[2],xmm5[2],xmm9[3],xmm5[3]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm9 = xmm6[8],xmm5[8],xmm6[9],xmm5[9],xmm6[10],xmm5[10],xmm6[11],xmm5[11],xmm6[12],xmm5[12],xmm6[13],xmm5[13],xmm6[14],xmm5[14],xmm6[15],xmm5[15]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm10 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
+; AVX1-NEXT:    vextractf128 $1, %ymm3, %xmm7
+; AVX1-NEXT:    vextractf128 $1, %ymm2, %xmm4
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm11 = xmm4[8],xmm7[8],xmm4[9],xmm7[9],xmm4[10],xmm7[10],xmm4[11],xmm7[11],xmm4[12],xmm7[12],xmm4[13],xmm7[13],xmm4[14],xmm7[14],xmm4[15],xmm7[15]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm6[0],xmm5[0],xmm6[1],xmm5[1],xmm6[2],xmm5[2],xmm6[3],xmm5[3],xmm6[4],xmm5[4],xmm6[5],xmm5[5],xmm6[6],xmm5[6],xmm6[7],xmm5[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm3 = xmm4[0],xmm7[0],xmm4[1],xmm7[1],xmm4[2],xmm7[2],xmm4[3],xmm7[3],xmm4[4],xmm7[4],xmm4[5],xmm7[5],xmm4[6],xmm7[6],xmm4[7],xmm7[7]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm4 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm5 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm5, %ymm4
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm8[0],xmm2[0],xmm8[1],xmm2[1],xmm8[2],xmm2[2],xmm8[3],xmm2[3]
-; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm6, %ymm4, %ymm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm11, %ymm0, %ymm2
-; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm4 = ymm4[2,3],ymm10[2,3]
-; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm3[2,3]
-; AVX1-NEXT:    vmovaps %ymm0, 96(%rdi)
-; AVX1-NEXT:    vmovaps %ymm4, 64(%rdi)
-; AVX1-NEXT:    vmovaps %ymm2, 32(%rdi)
-; AVX1-NEXT:    vmovaps %ymm1, (%rdi)
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm2 = xmm9[4],xmm11[4],xmm9[5],xmm11[5],xmm9[6],xmm11[6],xmm9[7],xmm11[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm8[4],xmm10[4],xmm8[5],xmm10[5],xmm8[6],xmm10[6],xmm8[7],xmm10[7]
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm5 = xmm9[0],xmm11[0],xmm9[1],xmm11[1],xmm9[2],xmm11[2],xmm9[3],xmm11[3]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm6 = xmm8[0],xmm10[0],xmm8[1],xmm10[1],xmm8[2],xmm10[2],xmm8[3],xmm10[3]
+; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm6, %ymm5
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm4, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm5, %ymm3
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm4[2,3],ymm1[2,3]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm5[2,3],ymm2[2,3]
+; AVX1-NEXT:    vmovaps %ymm2, 96(%rdi)
+; AVX1-NEXT:    vmovaps %ymm1, 64(%rdi)
+; AVX1-NEXT:    vmovaps %ymm3, 32(%rdi)
+; AVX1-NEXT:    vmovaps %ymm0, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: interleaved_store_vf32_i8_stride4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm4 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
-; AVX2-NEXT:    vpunpckhbw {{.*#+}} ymm0 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX2-NEXT:    vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX2-NEXT:    vpunpckhbw {{.*#+}} ymm5 = ymm2[8],ymm3[8],ymm2[9],ymm3[9],ymm2[10],ymm3[10],ymm2[11],ymm3[11],ymm2[12],ymm3[12],ymm2[13],ymm3[13],ymm2[14],ymm3[14],ymm2[15],ymm3[15],ymm2[24],ymm3[24],ymm2[25],ymm3[25],ymm2[26],ymm3[26],ymm2[27],ymm3[27],ymm2[28],ymm3[28],ymm2[29],ymm3[29],ymm2[30],ymm3[30],ymm2[31],ymm3[31]
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
 ; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm1 = ymm2[0],ymm3[0],ymm2[1],ymm3[1],ymm2[2],ymm3[2],ymm2[3],ymm3[3],ymm2[4],ymm3[4],ymm2[5],ymm3[5],ymm2[6],ymm3[6],ymm2[7],ymm3[7],ymm2[16],ymm3[16],ymm2[17],ymm3[17],ymm2[18],ymm3[18],ymm2[19],ymm3[19],ymm2[20],ymm3[20],ymm2[21],ymm3[21],ymm2[22],ymm3[22],ymm2[23],ymm3[23]
-; AVX2-NEXT:    vpunpckhbw {{.*#+}} ymm2 = ymm2[8],ymm3[8],ymm2[9],ymm3[9],ymm2[10],ymm3[10],ymm2[11],ymm3[11],ymm2[12],ymm3[12],ymm2[13],ymm3[13],ymm2[14],ymm3[14],ymm2[15],ymm3[15],ymm2[24],ymm3[24],ymm2[25],ymm3[25],ymm2[26],ymm3[26],ymm2[27],ymm3[27],ymm2[28],ymm3[28],ymm2[29],ymm3[29],ymm2[30],ymm3[30],ymm2[31],ymm3[31]
-; AVX2-NEXT:    vpunpckhwd {{.*#+}} ymm3 = ymm4[4],ymm1[4],ymm4[5],ymm1[5],ymm4[6],ymm1[6],ymm4[7],ymm1[7],ymm4[12],ymm1[12],ymm4[13],ymm1[13],ymm4[14],ymm1[14],ymm4[15],ymm1[15]
-; AVX2-NEXT:    vpunpckhwd {{.*#+}} ymm5 = ymm0[4],ymm2[4],ymm0[5],ymm2[5],ymm0[6],ymm2[6],ymm0[7],ymm2[7],ymm0[12],ymm2[12],ymm0[13],ymm2[13],ymm0[14],ymm2[14],ymm0[15],ymm2[15]
-; AVX2-NEXT:    vpunpcklwd {{.*#+}} ymm1 = ymm4[0],ymm1[0],ymm4[1],ymm1[1],ymm4[2],ymm1[2],ymm4[3],ymm1[3],ymm4[8],ymm1[8],ymm4[9],ymm1[9],ymm4[10],ymm1[10],ymm4[11],ymm1[11]
-; AVX2-NEXT:    vpunpcklwd {{.*#+}} ymm0 = ymm0[0],ymm2[0],ymm0[1],ymm2[1],ymm0[2],ymm2[2],ymm0[3],ymm2[3],ymm0[8],ymm2[8],ymm0[9],ymm2[9],ymm0[10],ymm2[10],ymm0[11],ymm2[11]
-; AVX2-NEXT:    vinserti128 $1, %xmm3, %ymm1, %ymm2
-; AVX2-NEXT:    vinserti128 $1, %xmm5, %ymm0, %ymm4
-; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
-; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],ymm5[2,3]
-; AVX2-NEXT:    vmovdqa %ymm0, 96(%rdi)
-; AVX2-NEXT:    vmovdqa %ymm1, 64(%rdi)
-; AVX2-NEXT:    vmovdqa %ymm4, 32(%rdi)
-; AVX2-NEXT:    vmovdqa %ymm2, (%rdi)
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11]
+; AVX2-NEXT:    vpunpckhwd {{.*#+}} ymm0 = ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15]
+; AVX2-NEXT:    vpunpckhwd {{.*#+}} ymm1 = ymm4[4],ymm5[4],ymm4[5],ymm5[5],ymm4[6],ymm5[6],ymm4[7],ymm5[7],ymm4[12],ymm5[12],ymm4[13],ymm5[13],ymm4[14],ymm5[14],ymm4[15],ymm5[15]
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} ymm3 = ymm4[0],ymm5[0],ymm4[1],ymm5[1],ymm4[2],ymm5[2],ymm4[3],ymm5[3],ymm4[8],ymm5[8],ymm4[9],ymm5[9],ymm4[10],ymm5[10],ymm4[11],ymm5[11]
+; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm4
+; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm3, %ymm5
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm2[2,3],ymm0[2,3]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm3[2,3],ymm1[2,3]
+; AVX2-NEXT:    vmovdqa %ymm1, 96(%rdi)
+; AVX2-NEXT:    vmovdqa %ymm0, 64(%rdi)
+; AVX2-NEXT:    vmovdqa %ymm5, 32(%rdi)
+; AVX2-NEXT:    vmovdqa %ymm4, (%rdi)
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: interleaved_store_vf32_i8_stride4:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpunpcklbw {{.*#+}} ymm4 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
-; AVX512-NEXT:    vpunpckhbw {{.*#+}} ymm0 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX512-NEXT:    vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX512-NEXT:    vpunpckhbw {{.*#+}} ymm5 = ymm2[8],ymm3[8],ymm2[9],ymm3[9],ymm2[10],ymm3[10],ymm2[11],ymm3[11],ymm2[12],ymm3[12],ymm2[13],ymm3[13],ymm2[14],ymm3[14],ymm2[15],ymm3[15],ymm2[24],ymm3[24],ymm2[25],ymm3[25],ymm2[26],ymm3[26],ymm2[27],ymm3[27],ymm2[28],ymm3[28],ymm2[29],ymm3[29],ymm2[30],ymm3[30],ymm2[31],ymm3[31]
+; AVX512-NEXT:    vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
 ; AVX512-NEXT:    vpunpcklbw {{.*#+}} ymm1 = ymm2[0],ymm3[0],ymm2[1],ymm3[1],ymm2[2],ymm3[2],ymm2[3],ymm3[3],ymm2[4],ymm3[4],ymm2[5],ymm3[5],ymm2[6],ymm3[6],ymm2[7],ymm3[7],ymm2[16],ymm3[16],ymm2[17],ymm3[17],ymm2[18],ymm3[18],ymm2[19],ymm3[19],ymm2[20],ymm3[20],ymm2[21],ymm3[21],ymm2[22],ymm3[22],ymm2[23],ymm3[23]
-; AVX512-NEXT:    vpunpckhbw {{.*#+}} ymm2 = ymm2[8],ymm3[8],ymm2[9],ymm3[9],ymm2[10],ymm3[10],ymm2[11],ymm3[11],ymm2[12],ymm3[12],ymm2[13],ymm3[13],ymm2[14],ymm3[14],ymm2[15],ymm3[15],ymm2[24],ymm3[24],ymm2[25],ymm3[25],ymm2[26],ymm3[26],ymm2[27],ymm3[27],ymm2[28],ymm3[28],ymm2[29],ymm3[29],ymm2[30],ymm3[30],ymm2[31],ymm3[31]
-; AVX512-NEXT:    vpunpckhwd {{.*#+}} ymm3 = ymm4[4],ymm1[4],ymm4[5],ymm1[5],ymm4[6],ymm1[6],ymm4[7],ymm1[7],ymm4[12],ymm1[12],ymm4[13],ymm1[13],ymm4[14],ymm1[14],ymm4[15],ymm1[15]
-; AVX512-NEXT:    vpunpckhwd {{.*#+}} ymm5 = ymm0[4],ymm2[4],ymm0[5],ymm2[5],ymm0[6],ymm2[6],ymm0[7],ymm2[7],ymm0[12],ymm2[12],ymm0[13],ymm2[13],ymm0[14],ymm2[14],ymm0[15],ymm2[15]
-; AVX512-NEXT:    vpunpcklwd {{.*#+}} ymm1 = ymm4[0],ymm1[0],ymm4[1],ymm1[1],ymm4[2],ymm1[2],ymm4[3],ymm1[3],ymm4[8],ymm1[8],ymm4[9],ymm1[9],ymm4[10],ymm1[10],ymm4[11],ymm1[11]
-; AVX512-NEXT:    vpunpcklwd {{.*#+}} ymm0 = ymm0[0],ymm2[0],ymm0[1],ymm2[1],ymm0[2],ymm2[2],ymm0[3],ymm2[3],ymm0[8],ymm2[8],ymm0[9],ymm2[9],ymm0[10],ymm2[10],ymm0[11],ymm2[11]
-; AVX512-NEXT:    vinserti128 $1, %xmm3, %ymm1, %ymm2
-; AVX512-NEXT:    vinserti128 $1, %xmm5, %ymm0, %ymm4
-; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
-; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],ymm5[2,3]
-; AVX512-NEXT:    vinserti64x4 $1, %ymm4, %zmm2, %zmm2
-; AVX512-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512-NEXT:    vpunpcklwd {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11]
+; AVX512-NEXT:    vpunpckhwd {{.*#+}} ymm0 = ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15]
+; AVX512-NEXT:    vpunpckhwd {{.*#+}} ymm1 = ymm4[4],ymm5[4],ymm4[5],ymm5[5],ymm4[6],ymm5[6],ymm4[7],ymm5[7],ymm4[12],ymm5[12],ymm4[13],ymm5[13],ymm4[14],ymm5[14],ymm4[15],ymm5[15]
+; AVX512-NEXT:    vpunpcklwd {{.*#+}} ymm3 = ymm4[0],ymm5[0],ymm4[1],ymm5[1],ymm4[2],ymm5[2],ymm4[3],ymm5[3],ymm4[8],ymm5[8],ymm4[9],ymm5[9],ymm4[10],ymm5[10],ymm4[11],ymm5[11]
+; AVX512-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm4
+; AVX512-NEXT:    vinserti128 $1, %xmm1, %ymm3, %ymm5
+; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm2[2,3],ymm0[2,3]
+; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm3[2,3],ymm1[2,3]
+; AVX512-NEXT:    vinserti64x4 $1, %ymm5, %zmm4, %zmm2
+; AVX512-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vmovdqa32 %zmm0, 64(%rdi)
 ; AVX512-NEXT:    vmovdqa32 %zmm2, (%rdi)
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %v1 = shufflevector <32 x i8> %x1, <32 x i8> %x2, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
   %v2 = shufflevector <32 x i8> %x3, <32 x i8> %x4, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
   %interleaved.vec = shufflevector <64 x i8> %v1, <64 x i8> %v2, <128 x i32> <i32 0, i32 32, i32 64, i32 96, i32 1, i32 33, i32 65, i32 97, i32 2, i32 34, i32 66, i32 98, i32 3, i32 35, i32 67, i32 99, i32 4, i32 36, i32 68, i32 100, i32 5, i32 37, i32 69, i32 101, i32 6, i32 38, i32 70, i32 102, i32 7, i32 39, i32 71, i32 103, i32 8, i32 40, i32 72, i32 104, i32 9, i32 41, i32 73, i32 105, i32 10, i32 42, i32 74, i32 106, i32 11, i32 43, i32 75, i32 107, i32 12, i32 44, i32 76, i32 108, i32 13, i32 45, i32 77, i32 109, i32 14, i32 46, i32 78, i32 110, i32 15, i32 47, i32 79, i32 111, i32 16, i32 48, i32 80, i32 112, i32 17, i32 49, i32 81, i32 113, i32 18, i32 50, i32 82, i32 114, i32 19, i32 51, i32 83, i32 115, i32 20, i32 52, i32 84, i32 116, i32 21, i32 53, i32 85, i32 117, i32 22, i32 54, i32 86, i32 118, i32 23, i32 55, i32 87, i32 119, i32 24, i32 56, i32 88, i32 120, i32 25, i32 57, i32 89, i32 121, i32 26, i32 58, i32 90, i32 122, i32 27, i32 59, i32 91, i32 123, i32 28, i32 60, i32 92, i32 124, i32 29, i32 61, i32 93, i32 125, i32 30, i32 62, i32 94, i32 126, i32 31, i32 63, i32 95, i32 127>
   store <128 x i8> %interleaved.vec, <128 x i8>* %p
 ret void
 }
 
 define void @interleaved_store_vf16_i8_stride4(<16 x i8> %x1, <16 x i8> %x2, <16 x i8> %x3, <16 x i8> %x4, <64 x i8>* %p) {
 ; AVX1-LABEL: interleaved_store_vf16_i8_stride4:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm4 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm4 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm5 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
-; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm2 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
-; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm0, %ymm0
-; AVX1-NEXT:    vmovaps %ymm0, 32(%rdi)
-; AVX1-NEXT:    vmovaps %ymm1, (%rdi)
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm3, %ymm1
+; AVX1-NEXT:    vmovaps %ymm1, 32(%rdi)
+; AVX1-NEXT:    vmovaps %ymm0, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: interleaved_store_vf16_i8_stride4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpcklbw {{.*#+}} xmm4 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; AVX2-NEXT:    vpunpckhbw {{.*#+}} xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX2-NEXT:    vpunpckhbw {{.*#+}} xmm4 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX2-NEXT:    vpunpckhbw {{.*#+}} xmm5 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX2-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
-; AVX2-NEXT:    vpunpckhbw {{.*#+}} xmm2 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
-; AVX2-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
-; AVX2-NEXT:    vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
-; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
-; AVX2-NEXT:    vinserti128 $1, %xmm3, %ymm1, %ymm1
-; AVX2-NEXT:    vinserti128 $1, %xmm5, %ymm0, %ymm0
-; AVX2-NEXT:    vmovdqa %ymm0, 32(%rdi)
-; AVX2-NEXT:    vmovdqa %ymm1, (%rdi)
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX2-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7]
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
+; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm0
+; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm3, %ymm1
+; AVX2-NEXT:    vmovdqa %ymm1, 32(%rdi)
+; AVX2-NEXT:    vmovdqa %ymm0, (%rdi)
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: interleaved_store_vf16_i8_stride4:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    vpunpcklbw {{.*#+}} xmm4 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
-; AVX512-NEXT:    vpunpckhbw {{.*#+}} xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX512-NEXT:    vpunpckhbw {{.*#+}} xmm4 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
+; AVX512-NEXT:    vpunpckhbw {{.*#+}} xmm5 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
+; AVX512-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX512-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
-; AVX512-NEXT:    vpunpckhbw {{.*#+}} xmm2 = xmm2[8],xmm3[8],xmm2[9],xmm3[9],xmm2[10],xmm3[10],xmm2[11],xmm3[11],xmm2[12],xmm3[12],xmm2[13],xmm3[13],xmm2[14],xmm3[14],xmm2[15],xmm3[15]
-; AVX512-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm4[4],xmm1[4],xmm4[5],xmm1[5],xmm4[6],xmm1[6],xmm4[7],xmm1[7]
-; AVX512-NEXT:    vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3]
-; AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
-; AVX512-NEXT:    vinserti128 $1, %xmm3, %ymm1, %ymm1
-; AVX512-NEXT:    vinserti128 $1, %xmm5, %ymm0, %ymm0
-; AVX512-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
+; AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX512-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX512-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7]
+; AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
+; AVX512-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm0
+; AVX512-NEXT:    vinserti128 $1, %xmm1, %ymm3, %ymm1
+; AVX512-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vmovdqa32 %zmm0, (%rdi)
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 %v1 = shufflevector <16 x i8> %x1, <16 x i8> %x2, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 %v2 = shufflevector <16 x i8> %x3, <16 x i8> %x4, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 %interleaved.vec = shufflevector <32 x i8> %v1, <32 x i8> %v2, <64 x i32> <i32 0,i32 16,i32 32,i32 48,i32 1,i32 17,i32 33,i32 49,i32 2,i32 18,i32 34,i32 50,i32 3,i32 19,i32 35,i32 51,i32 4,i32 20,i32 36,i32 52,i32 5,i32 21,i32 37,i32 53,i32 6,i32 22,i32 38,i32 54,i32 7,i32 23,i32 39,i32 55,i32 8,i32 24,i32 40,i32 56,i32 9,i32 25,i32 41,i32 57,i32 10,i32 26,i32 42,i32 58,i32 11,i32 27,i32 43,i32 59,i32 12,i32 28,i32 44,i32 60,i32 13,i32 29,i32 45,i32 61,i32 14,i32 30,i32 46,i32 62,i32 15,i32 31,i32 47,i32 63>
 store <64 x i8> %interleaved.vec, <64 x i8>* %p
 ret void
; AVX512-NEXT:    retq
 
   ret <32 x i1> %res
 }
 
 define void @interleaved_store_vf8_i8_stride4(<8 x i8> %x1, <8 x i8> %x2, <8 x i8> %x3, <8 x i8> %x4, <32 x i8>* %p) {
 ; AVX1-LABEL: interleaved_store_vf8_i8_stride4:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u>
-; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm3
-; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
-; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,8,1,9,2,10,3,11,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
 ; AVX1-NEXT:    vmovaps %ymm0, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX-LABEL: interleaved_store_vf8_i8_stride4:
 ; AVX:       # BB#0:
 ; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; AVX-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
-; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u>
-; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm3
-; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
-; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
-; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,8,1,9,2,10,3,11,u,u,u,u,u,u,u,u>
 ; AVX-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX-NEXT:    vinserti128 $1, %xmm2, %ymm0, %ymm0
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX-NEXT:    vinserti128 $1, %xmm0, %ymm2, %ymm0
 ; AVX-NEXT:    vmovdqa %ymm0, (%rdi)
 ; AVX-NEXT:    vzeroupper
 ; AVX-NEXT:    retq
 %v1 = shufflevector <8 x i8> %x1, <8 x i8> %x2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 %v2 = shufflevector <8 x i8> %x2, <8 x i8> %x3, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 %interleaved.vec = shufflevector <16 x i8> %v1, <16 x i8> %v2, <32 x i32> <i32 0,i32 8,i32 16,i32 24,i32 1,i32 9,i32 17,i32 25,i32 2,i32 10,i32 18,i32 26,i32 3,i32 11,i32 19,i32 27,i32 4,i32 12,i32 20,i32 28,i32 5,i32 13,i32 21,i32 29,i32 6,i32 14,i32 22,i32 30,i32 7,i32 15,i32 23,i32 31>
 store <32 x i8> %interleaved.vec, <32 x i8>* %p
 ret void

test/Transforms/InterleavedAccess/X86/interleavedStore.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -mtriple=x86_64-pc-linux -mattr=+avx2 -interleaved-access -S | FileCheck %s
 
 define void @interleaved_store_vf32_i8_stride4(<32 x i8> %x1, <32 x i8> %x2, <32 x i8> %x3, <32 x i8> %x4, <128 x i8>* %p) {
 ; CHECK-LABEL: @interleaved_store_vf32_i8_stride4(
 ; CHECK-NEXT:    [[V1:%.*]] = shufflevector <32 x i8> [[X1:%.*]], <32 x i8> [[X2:%.*]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[V2:%.*]] = shufflevector <32 x i8> [[X3:%.*]], <32 x i8> [[X4:%.*]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <64 x i8> [[V1]], <64 x i8> [[V2]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <64 x i8> [[V1]], <64 x i8> [[V2]], <32 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <64 x i8> [[V1]], <64 x i8> [[V2]], <32 x i32> <i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95>
 ; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <64 x i8> [[V1]], <64 x i8> [[V2]], <32 x i32> <i32 96, i32 97, i32 98, i32 99, i32 100, i32 101, i32 102, i32 103, i32 104, i32 105, i32 106, i32 107, i32 108, i32 109, i32 110, i32 111, i32 112, i32 113, i32 114, i32 115, i32 116, i32 117, i32 118, i32 119, i32 120, i32 121, i32 122, i32 123, i32 124, i32 125, i32 126, i32 127>
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <32 x i8> [[TMP1]], <32 x i8> [[TMP2]], <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <32 x i8> [[TMP1]], <32 x i8> [[TMP2]], <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <32 x i8> [[TMP3]], <32 x i8> [[TMP4]], <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
-; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <32 x i8> [[TMP3]], <32 x i8> [[TMP4]], <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
-; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <32 x i8> [[TMP5]], <32 x i8> [[TMP7]], <32 x i32> <i32 8, i32 9, i32 40, i32 41, i32 10, i32 11, i32 42, i32 43, i32 12, i32 13, i32 44, i32 45, i32 14, i32 15, i32 46, i32 47, i32 24, i32 25, i32 56, i32 57, i32 26, i32 27, i32 58, i32 59, i32 28, i32 29, i32 60, i32 61, i32 30, i32 31, i32 62, i32 63>
-; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <32 x i8> [[TMP6]], <32 x i8> [[TMP8]], <32 x i32> <i32 8, i32 9, i32 40, i32 41, i32 10, i32 11, i32 42, i32 43, i32 12, i32 13, i32 44, i32 45, i32 14, i32 15, i32 46, i32 47, i32 24, i32 25, i32 56, i32 57, i32 26, i32 27, i32 58, i32 59, i32 28, i32 29, i32 60, i32 61, i32 30, i32 31, i32 62, i32 63>
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <32 x i8> [[TMP5]], <32 x i8> [[TMP7]], <32 x i32> <i32 0, i32 1, i32 32, i32 33, i32 2, i32 3, i32 34, i32 35, i32 4, i32 5, i32 36, i32 37, i32 6, i32 7, i32 38, i32 39, i32 16, i32 17, i32 48, i32 49, i32 18, i32 19, i32 50, i32 51, i32 20, i32 21, i32 52, i32 53, i32 22, i32 23, i32 54, i32 55>
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <32 x i8> [[TMP6]], <32 x i8> [[TMP8]], <32 x i32> <i32 0, i32 1, i32 32, i32 33, i32 2, i32 3, i32 34, i32 35, i32 4, i32 5, i32 36, i32 37, i32 6, i32 7, i32 38, i32 39, i32 16, i32 17, i32 48, i32 49, i32 18, i32 19, i32 50, i32 51, i32 20, i32 21, i32 52, i32 53, i32 22, i32 23, i32 54, i32 55>
-; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <32 x i8> [[TMP11]], <32 x i8> [[TMP9]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
-; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <32 x i8> [[TMP12]], <32 x i8> [[TMP10]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
-; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <32 x i8> [[TMP11]], <32 x i8> [[TMP9]], <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT:    [[TMP16:%.*]] = shufflevector <32 x i8> [[TMP12]], <32 x i8> [[TMP10]], <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <32 x i8> [[TMP1]], <32 x i8> [[TMP2]], <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <32 x i8> [[TMP3]], <32 x i8> [[TMP4]], <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
+; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <32 x i8> [[TMP1]], <32 x i8> [[TMP2]], <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
+; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <32 x i8> [[TMP3]], <32 x i8> [[TMP4]], <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
+; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <32 x i8> [[TMP7]], <32 x i8> [[TMP8]], <32 x i32> <i32 0, i32 1, i32 32, i32 33, i32 2, i32 3, i32 34, i32 35, i32 4, i32 5, i32 36, i32 37, i32 6, i32 7, i32 38, i32 39, i32 16, i32 17, i32 48, i32 49, i32 18, i32 19, i32 50, i32 51, i32 20, i32 21, i32 52, i32 53, i32 22, i32 23, i32 54, i32 55>
+; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <32 x i8> [[TMP7]], <32 x i8> [[TMP8]], <32 x i32> <i32 8, i32 9, i32 40, i32 41, i32 10, i32 11, i32 42, i32 43, i32 12, i32 13, i32 44, i32 45, i32 14, i32 15, i32 46, i32 47, i32 24, i32 25, i32 56, i32 57, i32 26, i32 27, i32 58, i32 59, i32 28, i32 29, i32 60, i32 61, i32 30, i32 31, i32 62, i32 63>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <32 x i8> [[TMP5]], <32 x i8> [[TMP6]], <32 x i32> <i32 8, i32 9, i32 40, i32 41, i32 10, i32 11, i32 42, i32 43, i32 12, i32 13, i32 44, i32 45, i32 14, i32 15, i32 46, i32 47, i32 24, i32 25, i32 56, i32 57, i32 26, i32 27, i32 58, i32 59, i32 28, i32 29, i32 60, i32 61, i32 30, i32 31, i32 62, i32 63>
+; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <32 x i8> [[TMP5]], <32 x i8> [[TMP6]], <32 x i32> <i32 0, i32 1, i32 32, i32 33, i32 2, i32 3, i32 34, i32 35, i32 4, i32 5, i32 36, i32 37, i32 6, i32 7, i32 38, i32 39, i32 16, i32 17, i32 48, i32 49, i32 18, i32 19, i32 50, i32 51, i32 20, i32 21, i32 52, i32 53, i32 22, i32 23, i32 54, i32 55>
+; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <32 x i8> [[TMP9]], <32 x i8> [[TMP10]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <32 x i8> [[TMP12]], <32 x i8> [[TMP11]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
+; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <32 x i8> [[TMP9]], <32 x i8> [[TMP10]], <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
+; CHECK-NEXT:    [[TMP16:%.*]] = shufflevector <32 x i8> [[TMP12]], <32 x i8> [[TMP11]], <32 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <32 x i8> [[TMP13]], <32 x i8> [[TMP14]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <32 x i8> [[TMP15]], <32 x i8> [[TMP16]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    [[TMP19:%.*]] = shufflevector <64 x i8> [[TMP17]], <64 x i8> [[TMP18]], <128 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95, i32 96, i32 97, i32 98, i32 99, i32 100, i32 101, i32 102, i32 103, i32 104, i32 105, i32 106, i32 107, i32 108, i32 109, i32 110, i32 111, i32 112, i32 113, i32 114, i32 115, i32 116, i32 117, i32 118, i32 119, i32 120, i32 121, i32 122, i32 123, i32 124, i32 125, i32 126, i32 127>
 ; CHECK-NEXT:    store <128 x i8> [[TMP19]], <128 x i8>* [[P:%.*]]
 ; CHECK-NEXT:    ret void
 ;
   %v1 = shufflevector <32 x i8> %x1, <32 x i8> %x2, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
   %v2 = shufflevector <32 x i8> %x3, <32 x i8> %x4, <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
   %interleaved.vec = shufflevector <64 x i8> %v1, <64 x i8> %v2, <128 x i32> <i32 0, i32 32, i32 64, i32 96, i32 1, i32 33, i32 65, i32 97, i32 2, i32 34, i32 66, i32 98, i32 3, i32 35, i32 67, i32 99, i32 4, i32 36, i32 68, i32 100, i32 5, i32 37, i32 69, i32 101, i32 6, i32 38, i32 70, i32 102, i32 7, i32 39, i32 71, i32 103, i32 8, i32 40, i32 72, i32 104, i32 9, i32 41, i32 73, i32 105, i32 10, i32 42, i32 74, i32 106, i32 11, i32 43, i32 75, i32 107, i32 12, i32 44, i32 76, i32 108, i32 13, i32 45, i32 77, i32 109, i32 14, i32 46, i32 78, i32 110, i32 15, i32 47, i32 79, i32 111, i32 16, i32 48, i32 80, i32 112, i32 17, i32 49, i32 81, i32 113, i32 18, i32 50, i32 82, i32 114, i32 19, i32 51, i32 83, i32 115, i32 20, i32 52, i32 84, i32 116, i32 21, i32 53, i32 85, i32 117, i32 22, i32 54, i32 86, i32 118, i32 23, i32 55, i32 87, i32 119, i32 24, i32 56, i32 88, i32 120, i32 25, i32 57, i32 89, i32 121, i32 26, i32 58, i32 90, i32 122, i32 27, i32 59, i32 91, i32 123, i32 28, i32 60, i32 92, i32 124, i32 29, i32 61, i32 93, i32 125, i32 30, i32 62, i32 94, i32 126, i32 31, i32 63, i32 95, i32 127>
   store <128 x i8> %interleaved.vec, <128 x i8>* %p
   ret void
 }
 
 define void @interleaved_store_vf16_i8_stride4(<16 x i8> %x1, <16 x i8> %x2, <16 x i8> %x3, <16 x i8> %x4, <64 x i8>* %p) {
 ; CHECK-LABEL: @interleaved_store_vf16_i8_stride4(
 ; CHECK-NEXT:    [[V1:%.*]] = shufflevector <16 x i8> [[X1:%.*]], <16 x i8> [[X2:%.*]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; CHECK-NEXT:    [[V2:%.*]] = shufflevector <16 x i8> [[X3:%.*]], <16 x i8> [[X4:%.*]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <32 x i8> [[V1]], <32 x i8> [[V2]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <32 x i8> [[V1]], <32 x i8> [[V2]], <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <32 x i8> [[V1]], <32 x i8> [[V2]], <16 x i32> <i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47>
 ; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <32 x i8> [[V1]], <32 x i8> [[V2]], <16 x i32> <i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP7]], <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
-; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <16 x i8> [[TMP6]], <16 x i8> [[TMP8]], <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP7]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <16 x i8> [[TMP6]], <16 x i8> [[TMP8]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
-; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <16 x i8> [[TMP11]], <16 x i8> [[TMP9]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
-; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x i8> [[TMP12]], <16 x i8> [[TMP10]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
+; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <16 x i8> [[TMP1]], <16 x i8> [[TMP2]], <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> [[TMP4]], <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <16 x i8> [[TMP7]], <16 x i8> [[TMP8]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
+; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <16 x i8> [[TMP7]], <16 x i8> [[TMP8]], <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP6]], <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP6]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
+; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <16 x i8> [[TMP9]], <16 x i8> [[TMP10]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x i8> [[TMP12]], <16 x i8> [[TMP11]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 ; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <32 x i8> [[TMP13]], <32 x i8> [[TMP14]], <64 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63>
 ; CHECK-NEXT:    store <64 x i8> [[TMP15]], <64 x i8>* [[P:%.*]]
 ; CHECK-NEXT:    ret void
 ;
 %v1 = shufflevector <16 x i8> %x1, <16 x i8> %x2, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 %v2 = shufflevector <16 x i8> %x3, <16 x i8> %x4, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
 %interleaved.vec = shufflevector <32 x i8> %v1, <32 x i8> %v2, <64 x i32> <i32 0,i32 16,i32 32,i32 48,i32 1,i32 17,i32 33,i32 49,i32 2,i32 18,i32 34,i32 50,i32 3,i32 19,i32 35,i32 51,i32 4,i32 20,i32 36,i32 52,i32 5,i32 21,i32 37,i32 53,i32 6,i32 22,i32 38,i32 54,i32 7,i32 23,i32 39,i32 55,i32 8,i32 24,i32 40,i32 56,i32 9,i32 25,i32 41,i32 57,i32 10,i32 26,i32 42,i32 58,i32 11,i32 27,i32 43,i32 59,i32 12,i32 28,i32 44,i32 60,i32 13,i32 29,i32 45,i32 61,i32 14,i32 30,i32 46,i32 62,i32 15,i32 31,i32 47,i32 63>
 store <64 x i8> %interleaved.vec, <64 x i8>* %p
 ret void
 }
 
 define void @interleaved_store_vf8_i8_stride4(<8 x i8> %x1, <8 x i8> %x2, <8 x i8> %x3, <8 x i8> %x4, <32 x i8>* %p) {
 ; CHECK-LABEL: @interleaved_store_vf8_i8_stride4(
 ; CHECK-NEXT:    [[V1:%.*]] = shufflevector <8 x i8> [[X1:%.*]], <8 x i8> [[X2:%.*]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[V2:%.*]] = shufflevector <8 x i8> [[X2]], <8 x i8> [[X3:%.*]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <16 x i8> [[V1]], <16 x i8> [[V2]], <32 x i32> <i32 0, i32 8, i32 16, i32 24, i32 1, i32 9, i32 17, i32 25, i32 2, i32 10, i32 18, i32 26, i32 3, i32 11, i32 19, i32 27, i32 4, i32 12, i32 20, i32 28, i32 5, i32 13, i32 21, i32 29, i32 6, i32 14, i32 22, i32 30, i32 7, i32 15, i32 23, i32 31>
-; CHECK-NEXT:    store <32 x i8> [[INTERLEAVED_VEC]], <32 x i8>* [[P:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i8> [[V1]], <16 x i8> [[V2]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i8> [[V1]], <16 x i8> [[V2]], <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <16 x i8> [[V1]], <16 x i8> [[V2]], <8 x i32> <i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <16 x i8> [[V1]], <16 x i8> [[V2]], <8 x i32> <i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i8> [[TMP1]], <8 x i8> [[TMP2]], <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <8 x i8> [[TMP3]], <8 x i8> [[TMP4]], <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP6]], <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 2, i32 3, i32 18, i32 19, i32 4, i32 5, i32 20, i32 21, i32 6, i32 7, i32 22, i32 23>
+; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <16 x i8> [[TMP5]], <16 x i8> [[TMP6]], <16 x i32> <i32 8, i32 9, i32 24, i32 25, i32 10, i32 11, i32 26, i32 27, i32 12, i32 13, i32 28, i32 29, i32 14, i32 15, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <16 x i8> [[TMP7]], <16 x i8> [[TMP8]], <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
+; CHECK-NEXT:    store <32 x i8> [[TMP9]], <32 x i8>* [[P:%.*]]
 ; CHECK-NEXT:    ret void
 ;
   %v1 = shufflevector <8 x i8> %x1, <8 x i8> %x2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   %v2 = shufflevector <8 x i8> %x2, <8 x i8> %x3, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
   %interleaved.vec = shufflevector <16 x i8> %v1, <16 x i8> %v2, <32 x i32> <i32 0,i32 8,i32 16,i32 24,i32 1,i32 9,i32 17,i32 25,i32 2,i32 10,i32 18,i32 26,i32 3,i32 11,i32 19,i32 27,i32 4,i32 12,i32 20,i32 28,i32 5,i32 13,i32 21,i32 29,i32 6,i32 14,i32 22,i32 30,i32 7,i32 15,i32 23,i32 31>
   store <32 x i8> %interleaved.vec, <32 x i8>* %p
 ret void
 }