[X86][LLVM]Expanding Supports lowerInterleavedStore() in X86InterleavedAccess (VF16 stride 4).

[m_zuckerman]

Summary

This patch expands the support of lowerInterleavedStore to 16x8i stride 4.

LLVM creates suboptimal shuffle code-gen for AVX2. In overall, this patch is a specific fix for the pattern (Strid=4 VF=16) 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 ymm2, ymm0, ymm12 and ymm3 holding
each 16 chars:

c0, c1, , c16
m0, m1, , m16
y0, y1, , y16
k0, k1, ., k16

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 ....

[m_zuckerman]

Small modification on the function name

[guyblank]

lib/Target/X86/X86InterleavedAccess.cpp

109

the comment is a bit misleading since it depends on whether we are loading or storing. can you expand the comment to state exactly what is supported?

129

you can use ShuffleElemSize

130

you can early exit at the beginning of the function on !Subtarget.hasAVX()

130

so this check isn't needed in the previous if?

Can you try to simplify this function? its getting overly complicated IMO.

371

maybe pass NumSubVecElems to interleave8bitStride4 and have it calculate the MVTs ?

[Farhana]

lib/Target/X86/X86InterleavedAccess.cpp

111

Can you please compress this into one line? Otherwise, it looks good to me.

[DavidKreitzer]

lib/Target/X86/X86InterleavedAccess.cpp

130

Can you try to simplify this function? its getting overly complicated IMO.

+1
I would personally be fine with doing that in an NFC follow-up patch.

Otherwise, this LGTM.

[guyblank]

LGTM with one minor comment.

lib/Target/X86/X86InterleavedAccess.cpp

210

you can use MVT::getVectorVT() directly, without creating the Type first.

lib/Target/X86/X86InterleavedAccess.cpp

class X86InterleavedAccessGroup {
   ///   In-V3 = s1, s2, s3, s4
   /// OutputVectors:
   ///   Out-V0 = p1, q1, r1, s1
   ///   Out-V1 = p2, q2, r2, s2
   ///   Out-V2 = p3, q3, r3, s3
   ///   Out-V3 = P4, q4, r4, s4
   void transpose_4x4(ArrayRef<Instruction *> InputVectors,
                      SmallVectorImpl<Value *> &TransposedMatrix);
-  void interleave8bit_32x4(ArrayRef<Instruction *> InputVectors,
-                          SmallVectorImpl<Value *> &TransposedMatrix);
+  void interleave8bitStride4(ArrayRef<Instruction *> InputVectors,
+                             SmallVectorImpl<Value *> &TransposedMatrix,
+                             unsigned NumSubVecElems);
+
 public:
   /// In order to form an interleaved access group X86InterleavedAccessGroup
   /// requires a wide-load instruction \p 'I', a group of interleaved-vectors
   /// \p Shuffs, reference to the first indices of each interleaved-vector
   /// \p 'Ind' and the interleaving stride factor \p F. In order to generate
   /// X86-specific instructions/intrinsics it also requires the underlying
   /// target information \p STarget.
   explicit X86InterleavedAccessGroup(Instruction *I,

 };
 } // end anonymous namespace
 
 bool X86InterleavedAccessGroup::isSupported() const {
   VectorType *ShuffleVecTy = Shuffles[0]->getType();
   Type *ShuffleEltTy = ShuffleVecTy->getVectorElementType();
   unsigned ShuffleElemSize = DL.getTypeSizeInBits(ShuffleEltTy);
   unsigned SupportedNumElem = 4;
-  if (ShuffleElemSize == 8)
-    SupportedNumElem = 32;
   unsigned WideInstSize;
 
-  // Currently, lowering is supported for the following vectors:
-  // 1. 4-element vectors of 64 bits on AVX.
-  // 2. 32-element vectors of 8 bits on AVX.
+  // Currently, lowering is supported for the following vectors with stride 4:
+  // 1. Store and load of 4-element vectors of 64 bits on AVX.
+  // 2. Store of 16/32-element vectors of 8 bits on AVX.
+  if (!Subtarget.hasAVX() || Factor != 4)
+    return false;
+
   if (isa<LoadInst>(Inst)) {
     if (DL.getTypeSizeInBits(ShuffleVecTy) !=
         SupportedNumElem * ShuffleElemSize)
       return false;
 
     WideInstSize = DL.getTypeSizeInBits(Inst->getType());
   } else
     WideInstSize = DL.getTypeSizeInBits(Shuffles[0]->getType());
 
-  if (DL.getTypeSizeInBits(ShuffleEltTy) == 8 && !isa<StoreInst>(Inst))
-    return false;
+  // We support shuffle represents stride 4 for byte type with size of
+  // WideInstSize.
+  if (ShuffleElemSize == 8 && isa<StoreInst>(Inst) &&
+      (WideInstSize == 512 || WideInstSize == 1024))
+    return true;
 
-  if (!Subtarget.hasAVX() || Factor != 4 ||
-      (ShuffleElemSize != 64 && ShuffleElemSize != 8) ||
+  if (ShuffleElemSize != 64 ||
       WideInstSize != (Factor * ShuffleElemSize * SupportedNumElem))
     return false;
 
   return true;
 }
 
 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);
 }
 
-void X86InterleavedAccessGroup::interleave8bit_32x4(
-    ArrayRef<Instruction *> Matrix,
-    SmallVectorImpl<Value *> &TransposedMatrix) {
+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);
 
   SmallVector<uint32_t, 32> MaskHighTemp;
   SmallVector<uint32_t, 32> MaskLowTemp;
   SmallVector<uint32_t, 32> MaskHighTemp1;
   SmallVector<uint32_t, 32> MaskLowTemp1;
   SmallVector<uint32_t, 32> MaskHighTemp2;
   SmallVector<uint32_t, 32> MaskLowTemp2;
   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>(MVT::v32i8, MaskHighTemp, false, false);
-  createUnpackShuffleMask<uint32_t>(MVT::v32i8, MaskLowTemp, true, false);
+  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);
 
   // MaskHighTemp1 and MaskLowTemp1 built in the vpunpckhdw and vpunpckldw X86
   // shuffle pattern.
 
-  createUnpackShuffleMask<uint32_t>(MVT::v16i16, MaskLowTemp1, true, false);
-  createUnpackShuffleMask<uint32_t>(MVT::v16i16, MaskHighTemp1, false, false);
+  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);
 
   // 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
Value *High =
       Builder.CreateShuffleVector(IntrVec1Low, IntrVec2Low, MaskHighWord);
   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
   // 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);
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 16:
   case 32:
-    interleave8bit_32x4(DecomposedVectors, TransposedVectors);
+    interleave8bitStride4(DecomposedVectors, TransposedVectors, NumSubVecElems);
     break;
   default:
     return false;
   }
 
   //   3. Concatenate the contiguous-vectors back into a wide vector.
   Value *WideVec = concatenateVectors(Builder, TransposedVectors);
 

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

; AVX512-NEXT:    retq
   %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 = 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 {{.*#+}} xmm5 = 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:    vpunpckhwd {{.*#+}} xmm6 = xmm5[4],xmm4[4],xmm5[5],xmm4[5],xmm5[6],xmm4[6],xmm5[7],xmm4[7]
-; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm4 = xmm5[0],xmm4[0],xmm5[1],xmm4[1],xmm5[2],xmm4[2],xmm5[3],xmm4[3]
-; AVX1-NEXT:    vinsertf128 $1, %xmm6, %ymm4, %ymm4
-; 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:    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:    vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[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, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
+; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm0, %ymm0
 ; AVX1-NEXT:    vmovaps %ymm0, 32(%rdi)
-; AVX1-NEXT:    vmovaps %ymm4, (%rdi)
+; AVX1-NEXT:    vmovaps %ymm1, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: interleaved_store_vf16_i8_stride4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    # kill: %XMM2<def> %XMM2<kill> %YMM2<def>
-; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<def>
-; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX2-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm1
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm2 = ymm1[u,u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23]
-; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm3 = ymm1[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm4 = ymm3[u,u,u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u]
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm5 = <u,u,255,0,u,u,255,0,u,u,255,0,u,u,255,0,u,u,0,255,u,u,0,255,u,u,0,255,u,u,0,255>
-; AVX2-NEXT:    vpblendvb %ymm5, %ymm2, %ymm4, %ymm2
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm4 = ymm0[0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u,u]
-; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm6 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm7 = ymm6[u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm8 = <255,0,u,u,255,0,u,u,255,0,u,u,255,0,u,u,0,255,u,u,0,255,u,u,0,255,u,u,0,255,u,u>
-; AVX2-NEXT:    vpblendvb %ymm8, %ymm4, %ymm7, %ymm4
-; AVX2-NEXT:    vpblendw {{.*#+}} ymm2 = ymm4[0],ymm2[1],ymm4[2],ymm2[3],ymm4[4],ymm2[5],ymm4[6],ymm2[7],ymm4[8],ymm2[9],ymm4[10],ymm2[11],ymm4[12],ymm2[13],ymm4[14],ymm2[15]
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31]
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm3 = ymm3[u,u,u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u]
-; AVX2-NEXT:    vpblendvb %ymm5, %ymm1, %ymm3, %ymm1
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u,u]
-; AVX2-NEXT:    vpshufb {{.*#+}} ymm3 = ymm6[u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u,u,u]
-; AVX2-NEXT:    vpblendvb %ymm8, %ymm0, %ymm3, %ymm0
-; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
+; 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:    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 %ymm2, (%rdi)
+; AVX2-NEXT:    vmovdqa %ymm1, (%rdi)
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
 ;
 ; AVX512-LABEL: interleaved_store_vf16_i8_stride4:
 ; AVX512:       # BB#0:
-; AVX512-NEXT:    # kill: %XMM2<def> %XMM2<kill> %YMM2<def>
-; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<def>
-; AVX512-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
-; AVX512-NEXT:    vinserti128 $1, %xmm3, %ymm2, %ymm1
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm2 = ymm1[u,u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31]
-; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm3 = ymm1[2,3,0,1]
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm4 = ymm3[u,u,u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u]
-; AVX512-NEXT:    vmovdqa {{.*#+}} ymm5 = <u,u,255,0,u,u,255,0,u,u,255,0,u,u,255,0,u,u,0,255,u,u,0,255,u,u,0,255,u,u,0,255>
-; AVX512-NEXT:    vpblendvb %ymm5, %ymm2, %ymm4, %ymm2
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm4 = ymm0[8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u,u]
-; AVX512-NEXT:    vperm2i128 {{.*#+}} ymm6 = ymm0[2,3,0,1]
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm7 = ymm6[u,8,u,u,u,9,u,u,u,10,u,u,u,11,u,u,28,u,u,u,29,u,u,u,30,u,u,u,31,u,u,u]
-; AVX512-NEXT:    vmovdqa {{.*#+}} ymm8 = <255,0,u,u,255,0,u,u,255,0,u,u,255,0,u,u,0,255,u,u,0,255,u,u,0,255,u,u,0,255,u,u>
-; AVX512-NEXT:    vpblendvb %ymm8, %ymm4, %ymm7, %ymm4
-; AVX512-NEXT:    vpblendw {{.*#+}} ymm2 = ymm4[0],ymm2[1],ymm4[2],ymm2[3],ymm4[4],ymm2[5],ymm4[6],ymm2[7],ymm4[8],ymm2[9],ymm4[10],ymm2[11],ymm4[12],ymm2[13],ymm4[14],ymm2[15]
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23]
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm3 = ymm3[u,u,u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u]
-; AVX512-NEXT:    vpblendvb %ymm5, %ymm1, %ymm3, %ymm1
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u,u]
-; AVX512-NEXT:    vpshufb {{.*#+}} ymm3 = ymm6[u,0,u,u,u,1,u,u,u,2,u,u,u,3,u,u,20,u,u,u,21,u,u,u,22,u,u,u,23,u,u,u]
-; AVX512-NEXT:    vpblendvb %ymm8, %ymm0, %ymm3, %ymm0
-; AVX512-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
-; AVX512-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
+; 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:    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:    vmovdqu8 %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

test/Transforms/InterleavedAccess/X86/interleavedStore.ll

;
   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:    [[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>
-; CHECK-NEXT:    store <64 x i8> [[INTERLEAVED_VEC]], <64 x i8>* [[P:%.*]]
+; 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:    [[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
 }