diff --git a/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h b/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h
--- a/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h
+++ b/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h
@@ -138,7 +138,7 @@
   bool vectorizeChainsInBlock(BasicBlock *BB, slpvectorizer::BoUpSLP &R);
 
   bool vectorizeStoreChain(ArrayRef<Value *> Chain, slpvectorizer::BoUpSLP &R,
-                           unsigned VecRegSize);
+                           unsigned Idx);
 
   bool vectorizeStores(ArrayRef<StoreInst *> Stores, slpvectorizer::BoUpSLP &R);
 
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -26,6 +26,7 @@
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallBitVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
@@ -5332,125 +5333,127 @@
 }
 
 bool SLPVectorizerPass::vectorizeStoreChain(ArrayRef<Value *> Chain, BoUpSLP &R,
-                                            unsigned VecRegSize) {
+                                            unsigned Idx) {
   const unsigned ChainLen = Chain.size();
   LLVM_DEBUG(dbgs() << "SLP: Analyzing a store chain of length " << ChainLen
                     << "\n");
   const unsigned Sz = R.getVectorElementSize(Chain[0]);
-  const unsigned VF = VecRegSize / Sz;
+  const unsigned MinVF = R.getMinVecRegSize() / Sz;
+  unsigned VF = Chain.size();
 
-  if (!isPowerOf2_32(Sz) || VF < 2)
+  if (!isPowerOf2_32(Sz) || !isPowerOf2_32(VF) || VF < 2 || VF < MinVF)
     return false;
 
-  bool Changed = false;
-  // Look for profitable vectorizable trees at all offsets, starting at zero.
-  for (unsigned i = 0, e = ChainLen; i + VF <= e; ++i) {
-
-    ArrayRef<Value *> Operands = Chain.slice(i, VF);
-    // Check that a previous iteration of this loop did not delete the Value.
-    if (llvm::any_of(Operands, [&R](Value *V) {
-          auto *I = dyn_cast<Instruction>(V);
-          return I && R.isDeleted(I);
-        }))
-      continue;
-
-    LLVM_DEBUG(dbgs() << "SLP: Analyzing " << VF << " stores at offset " << i
-                      << "\n");
-
-    R.buildTree(Operands);
-    if (R.isTreeTinyAndNotFullyVectorizable())
-      continue;
+  LLVM_DEBUG(dbgs() << "SLP: Analyzing " << VF << " stores at offset " << Idx
+                    << "\n");
 
-    R.computeMinimumValueSizes();
+  R.buildTree(Chain);
+  if (R.isTreeTinyAndNotFullyVectorizable())
+    return false;
 
-    int Cost = R.getTreeCost();
+  R.computeMinimumValueSizes();
 
-    LLVM_DEBUG(dbgs() << "SLP: Found cost=" << Cost << " for VF=" << VF
-                      << "\n");
-    if (Cost < -SLPCostThreshold) {
-      LLVM_DEBUG(dbgs() << "SLP: Decided to vectorize cost=" << Cost << "\n");
+  int Cost = R.getTreeCost();
 
-      using namespace ore;
+  LLVM_DEBUG(dbgs() << "SLP: Found cost=" << Cost << " for VF=" << VF << "\n");
+  if (Cost < -SLPCostThreshold) {
+    LLVM_DEBUG(dbgs() << "SLP: Decided to vectorize cost=" << Cost << "\n");
 
-      R.getORE()->emit(OptimizationRemark(SV_NAME, "StoresVectorized",
-                                          cast<StoreInst>(Chain[i]))
-                       << "Stores SLP vectorized with cost " << NV("Cost", Cost)
-                       << " and with tree size "
-                       << NV("TreeSize", R.getTreeSize()));
+    using namespace ore;
 
-      R.vectorizeTree();
+    R.getORE()->emit(OptimizationRemark(SV_NAME, "StoresVectorized",
+                                        cast<StoreInst>(Chain[0]))
+                     << "Stores SLP vectorized with cost " << NV("Cost", Cost)
+                     << " and with tree size "
+                     << NV("TreeSize", R.getTreeSize()));
 
-      // Move to the next bundle.
-      i += VF - 1;
-      Changed = true;
-    }
+    R.vectorizeTree();
+    return true;
   }
 
-  return Changed;
+  return false;
 }
 
 bool SLPVectorizerPass::vectorizeStores(ArrayRef<StoreInst *> Stores,
                                         BoUpSLP &R) {
-  SetVector<StoreInst *> Heads;
-  SmallDenseSet<StoreInst *> Tails;
-  SmallDenseMap<StoreInst *, StoreInst *> ConsecutiveChain;
-
   // We may run into multiple chains that merge into a single chain. We mark the
   // stores that we vectorized so that we don't visit the same store twice.
   BoUpSLP::ValueSet VectorizedStores;
   bool Changed = false;
 
-  auto &&FindConsecutiveAccess =
-      [this, &Stores, &Heads, &Tails, &ConsecutiveChain] (int K, int Idx) {
-        if (!isConsecutiveAccess(Stores[K], Stores[Idx], *DL, *SE))
-          return false;
-
-        Tails.insert(Stores[Idx]);
-        Heads.insert(Stores[K]);
-        ConsecutiveChain[Stores[K]] = Stores[Idx];
-        return true;
-      };
+  int E = Stores.size();
+  SmallBitVector Tails(E, false);
+  SmallVector<int, 16> ConsecutiveChain(E, E + 1);
+  auto &&FindConsecutiveAccess = [this, &Stores, &Tails,
+                                  &ConsecutiveChain](int K, int Idx) {
+    if (!isConsecutiveAccess(Stores[K], Stores[Idx], *DL, *SE))
+      return false;
 
+    Tails.set(Idx);
+    ConsecutiveChain[K] = Idx;
+    return true;
+  };
   // Do a quadratic search on all of the given stores in reverse order and find
   // all of the pairs of stores that follow each other.
-  int E = Stores.size();
   for (int Idx = E - 1; Idx >= 0; --Idx) {
     // If a store has multiple consecutive store candidates, search according
     // to the sequence: Idx-1, Idx+1, Idx-2, Idx+2, ...
     // This is because usually pairing with immediate succeeding or preceding
     // candidate create the best chance to find slp vectorization opportunity.
-    for (int Offset = 1, F = std::max(E - Idx, Idx + 1); Offset < F; ++Offset)
+    const int MaxLookDepth = std::min(E - Idx, 16);
+    for (int Offset = 1, F = std::max(MaxLookDepth, Idx + 1); Offset < F;
+         ++Offset)
       if ((Idx >= Offset && FindConsecutiveAccess(Idx - Offset, Idx)) ||
           (Idx + Offset < E && FindConsecutiveAccess(Idx + Offset, Idx)))
         break;
   }
 
   // For stores that start but don't end a link in the chain:
-  for (auto *SI : llvm::reverse(Heads)) {
-    if (Tails.count(SI))
+  for (int Cnt = E; Cnt > 0; --Cnt) {
+    int I = Cnt - 1;
+    if (ConsecutiveChain[I] == E + 1 || Tails.test(I))
       continue;
-
     // We found a store instr that starts a chain. Now follow the chain and try
     // to vectorize it.
     BoUpSLP::ValueList Operands;
-    StoreInst *I = SI;
     // Collect the chain into a list.
-    while ((Tails.count(I) || Heads.count(I)) && !VectorizedStores.count(I)) {
-      Operands.push_back(I);
+    while (I != E + 1 && !VectorizedStores.count(Stores[I])) {
+      Operands.push_back(Stores[I]);
       // Move to the next value in the chain.
       I = ConsecutiveChain[I];
     }
 
+    // If a vector register can't hold 1 element, we are done.
+    unsigned MaxVecRegSize = R.getMaxVecRegSize();
+    unsigned EltSize = R.getVectorElementSize(Stores[0]);
+    if (MaxVecRegSize % EltSize != 0)
+      continue;
+
+    unsigned MaxElts = MaxVecRegSize / EltSize;
     // FIXME: Is division-by-2 the correct step? Should we assert that the
     // register size is a power-of-2?
-    for (unsigned Size = R.getMaxVecRegSize(); Size >= R.getMinVecRegSize();
-         Size /= 2) {
-      if (vectorizeStoreChain(Operands, R, Size)) {
-        // Mark the vectorized stores so that we don't vectorize them again.
-        VectorizedStores.insert(Operands.begin(), Operands.end());
-        Changed = true;
-        break;
+    unsigned StartIdx = 0;
+    for (unsigned Size = llvm::PowerOf2Ceil(MaxElts); Size >= 2; Size /= 2) {
+      for (unsigned Cnt = StartIdx, E = Operands.size(); Cnt + Size <= E;) {
+        ArrayRef<Value *> Slice = makeArrayRef(Operands).slice(Cnt, Size);
+        if (!VectorizedStores.count(Slice.front()) &&
+            !VectorizedStores.count(Slice.back()) &&
+            vectorizeStoreChain(Slice, R, Cnt)) {
+          // Mark the vectorized stores so that we don't vectorize them again.
+          VectorizedStores.insert(Slice.begin(), Slice.end());
+          Changed = true;
+          // If we vectorized initial block, no need to try to vectorize it
+          // again.
+          if (Cnt == StartIdx)
+            StartIdx += Size;
+          Cnt += Size;
+          continue;
+        }
+        ++Cnt;
       }
+      // Check if the whole array was vectorized already - exit.
+      if (StartIdx >= Operands.size())
+        break;
     }
   }
 
@@ -7118,14 +7121,7 @@
     LLVM_DEBUG(dbgs() << "SLP: Analyzing a store chain of length "
                       << it->second.size() << ".\n");
 
-    // Process the stores in chunks of 16.
-    // TODO: The limit of 16 inhibits greater vectorization factors.
-    //       For example, AVX2 supports v32i8. Increasing this limit, however,
-    //       may cause a significant compile-time increase.
-    for (unsigned CI = 0, CE = it->second.size(); CI < CE; CI += 16) {
-      unsigned Len = std::min<unsigned>(CE - CI, 16);
-      Changed |= vectorizeStores(makeArrayRef(&it->second[CI], Len), R);
-    }
+    Changed |= vectorizeStores(it->second, R);
   }
   return Changed;
 }
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll
@@ -354,14 +354,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @add_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]])
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.sadd.sat.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]])
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.sadd.sat.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]])
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -496,24 +492,61 @@
 }
 
 define void @add_v64i8() {
-; CHECK-LABEL: @add_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @add_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @add_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SLM-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SLM-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SLM-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.sadd.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @add_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]])
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.sadd.sat.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]])
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @add_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.sadd.sat.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]])
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll
@@ -251,14 +251,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @add_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]])
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.uadd.sat.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]])
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.uadd.sat.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]])
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -393,24 +389,42 @@
 }
 
 define void @add_v64i8() {
-; CHECK-LABEL: @add_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @add_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.uadd.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @add_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]])
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.uadd.sat.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]])
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @add_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.uadd.sat.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]])
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-add.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-add.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-add.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-add.ll
@@ -289,14 +289,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @add_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = add <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = add <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = add <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -431,24 +427,61 @@
 }
 
 define void @add_v64i8() {
-; CHECK-LABEL: @add_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = add <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = add <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = add <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @add_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = add <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = add <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = add <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = add <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @add_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = add <16 x i8> [[TMP1]], [[TMP5]]
+; SLM-NEXT:    [[TMP10:%.*]] = add <16 x i8> [[TMP2]], [[TMP6]]
+; SLM-NEXT:    [[TMP11:%.*]] = add <16 x i8> [[TMP3]], [[TMP7]]
+; SLM-NEXT:    [[TMP12:%.*]] = add <16 x i8> [[TMP4]], [[TMP8]]
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @add_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = add <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = add <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @add_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = add <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-fix.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-fix.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-fix.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-fix.ll
@@ -496,14 +496,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @smul_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]], i32 3)
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.smul.fix.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]], i32 3)
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.smul.fix.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]], i32 3)
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -638,24 +634,61 @@
 }
 
 define void @smul_v64i8() {
-; CHECK-LABEL: @smul_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @smul_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @smul_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
+; SLM-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
+; SLM-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
+; SLM-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.smul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @smul_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]], i32 3)
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.smul.fix.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]], i32 3)
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @smul_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.smul.fix.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]], i32 3)
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
@@ -1392,14 +1425,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @umul_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]], i32 3)
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.umul.fix.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]], i32 3)
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.umul.fix.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]], i32 3)
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -1534,24 +1563,61 @@
 }
 
 define void @umul_v64i8() {
-; CHECK-LABEL: @umul_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @umul_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @umul_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]], i32 3)
+; SLM-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]], i32 3)
+; SLM-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]], i32 3)
+; SLM-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.umul.fix.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]], i32 3)
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @umul_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]], i32 3)
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.umul.fix.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]], i32 3)
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @umul_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.umul.fix.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]], i32 3)
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-mul.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-mul.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-mul.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-mul.ll
@@ -356,14 +356,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @mul_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = mul <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = mul <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = mul <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -498,24 +494,61 @@
 }
 
 define void @mul_v64i8() {
-; CHECK-LABEL: @mul_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @mul_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @mul_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = mul <16 x i8> [[TMP1]], [[TMP5]]
+; SLM-NEXT:    [[TMP10:%.*]] = mul <16 x i8> [[TMP2]], [[TMP6]]
+; SLM-NEXT:    [[TMP11:%.*]] = mul <16 x i8> [[TMP3]], [[TMP7]]
+; SLM-NEXT:    [[TMP12:%.*]] = mul <16 x i8> [[TMP4]], [[TMP8]]
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @mul_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = mul <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = mul <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @mul_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = mul <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-ssat.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-ssat.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-ssat.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-ssat.ll
@@ -354,14 +354,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @sub_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]])
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.ssub.sat.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]])
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.ssub.sat.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]])
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -496,24 +492,61 @@
 }
 
 define void @sub_v64i8() {
-; CHECK-LABEL: @sub_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @sub_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @sub_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SLM-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SLM-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SLM-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.ssub.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @sub_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]])
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.ssub.sat.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]])
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @sub_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.ssub.sat.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]])
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-usat.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-usat.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-usat.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub-usat.ll
@@ -251,14 +251,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @sub_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> [[TMP1]], <16 x i16> [[TMP3]])
-; AVX512-NEXT:    [[TMP6:%.*]] = call <16 x i16> @llvm.usub.sat.v16i16(<16 x i16> [[TMP2]], <16 x i16> [[TMP4]])
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = call <32 x i16> @llvm.usub.sat.v32i16(<32 x i16> [[TMP1]], <32 x i16> [[TMP2]])
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -393,24 +389,42 @@
 }
 
 define void @sub_v64i8() {
-; CHECK-LABEL: @sub_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
-; CHECK-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
-; CHECK-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
-; CHECK-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @sub_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP1]], <16 x i8> [[TMP5]])
+; SSE-NEXT:    [[TMP10:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP2]], <16 x i8> [[TMP6]])
+; SSE-NEXT:    [[TMP11:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP3]], <16 x i8> [[TMP7]])
+; SSE-NEXT:    [[TMP12:%.*]] = call <16 x i8> @llvm.usub.sat.v16i8(<16 x i8> [[TMP4]], <16 x i8> [[TMP8]])
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @sub_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> [[TMP1]], <32 x i8> [[TMP3]])
+; AVX-NEXT:    [[TMP6:%.*]] = call <32 x i8> @llvm.usub.sat.v32i8(<32 x i8> [[TMP2]], <32 x i8> [[TMP4]])
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @sub_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = call <64 x i8> @llvm.usub.sat.v64i8(<64 x i8> [[TMP1]], <64 x i8> [[TMP2]])
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub.ll b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/arith-sub.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/arith-sub.ll
@@ -289,14 +289,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @sub_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = sub <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = sub <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = sub <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
   %a0  = load i16, i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 0 ), align 2
@@ -431,24 +427,61 @@
 }
 
 define void @sub_v64i8() {
-; CHECK-LABEL: @sub_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = sub <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = sub <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = sub <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = sub <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @sub_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = sub <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = sub <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = sub <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = sub <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; SLM-LABEL: @sub_v64i8(
+; SLM-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    [[TMP9:%.*]] = sub <16 x i8> [[TMP1]], [[TMP5]]
+; SLM-NEXT:    [[TMP10:%.*]] = sub <16 x i8> [[TMP2]], [[TMP6]]
+; SLM-NEXT:    [[TMP11:%.*]] = sub <16 x i8> [[TMP3]], [[TMP7]]
+; SLM-NEXT:    [[TMP12:%.*]] = sub <16 x i8> [[TMP4]], [[TMP8]]
+; SLM-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SLM-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SLM-NEXT:    ret void
+;
+; AVX-LABEL: @sub_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = sub <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = sub <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @sub_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = sub <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll b/llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll
@@ -311,14 +311,26 @@
 }
 
 define void @bitreverse_32i8() #0 {
-; CHECK-LABEL: @bitreverse_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP1]])
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP2]])
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @bitreverse_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP1]])
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> [[TMP2]])
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @bitreverse_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.bitreverse.v32i8(<32 x i8> [[TMP1]])
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; XOP-LABEL: @bitreverse_32i8(
+; XOP-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.bitreverse.v32i8(<32 x i8> [[TMP1]])
+; XOP-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; XOP-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/ctlz.ll b/llvm/test/Transforms/SLPVectorizer/X86/ctlz.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/ctlz.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/ctlz.ll
@@ -362,14 +362,20 @@
 }
 
 define void @ctlz_32i8() #0 {
-; CHECK-LABEL: @ctlz_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 false)
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 false)
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @ctlz_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 false)
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 false)
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @ctlz_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.ctlz.v32i8(<32 x i8> [[TMP1]], i1 false)
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
@@ -812,14 +818,20 @@
 }
 
 define void @ctlz_undef_32i8() #0 {
-; CHECK-LABEL: @ctlz_undef_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 true)
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 true)
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @ctlz_undef_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP1]], i1 true)
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctlz.v16i8(<16 x i8> [[TMP2]], i1 true)
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @ctlz_undef_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.ctlz.v32i8(<32 x i8> [[TMP1]], i1 true)
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/ctpop.ll b/llvm/test/Transforms/SLPVectorizer/X86/ctpop.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/ctpop.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/ctpop.ll
@@ -424,14 +424,20 @@
 }
 
 define void @ctpop_32i8() #0 {
-; CHECK-LABEL: @ctpop_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP1]])
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP2]])
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @ctpop_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP1]])
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> [[TMP2]])
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @ctpop_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.ctpop.v32i8(<32 x i8> [[TMP1]])
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/cttz.ll b/llvm/test/Transforms/SLPVectorizer/X86/cttz.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/cttz.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/cttz.ll
@@ -353,14 +353,20 @@
 }
 
 define void @cttz_32i8() #0 {
-; CHECK-LABEL: @cttz_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 false)
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 false)
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @cttz_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 false)
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 false)
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @cttz_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.cttz.v32i8(<32 x i8> [[TMP1]], i1 false)
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
@@ -794,14 +800,20 @@
 }
 
 define void @cttz_undef_32i8() #0 {
-; CHECK-LABEL: @cttz_undef_32i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 true)
-; CHECK-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 true)
-; CHECK-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @cttz_undef_32i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([32 x i8]* @src8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP1]], i1 true)
+; SSE-NEXT:    [[TMP4:%.*]] = call <16 x i8> @llvm.cttz.v16i8(<16 x i8> [[TMP2]], i1 true)
+; SSE-NEXT:    store <16 x i8> [[TMP3]], <16 x i8>* bitcast ([32 x i8]* @dst8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP4]], <16 x i8>* bitcast (i8* getelementptr inbounds ([32 x i8], [32 x i8]* @dst8, i8 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @cttz_undef_32i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([32 x i8]* @src8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = call <32 x i8> @llvm.cttz.v32i8(<32 x i8> [[TMP1]], i1 true)
+; AVX-NEXT:    store <32 x i8> [[TMP2]], <32 x i8>* bitcast ([32 x i8]* @dst8 to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
 ;
   %ld0  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  0), align 1
   %ld1  = load i8, i8* getelementptr inbounds ([32 x i8], [32 x i8]* @src8, i8 0, i64  1), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/different-vec-widths.ll b/llvm/test/Transforms/SLPVectorizer/X86/different-vec-widths.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/different-vec-widths.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/different-vec-widths.ll
@@ -56,15 +56,14 @@
 ; AVX-NEXT:    [[Q5:%.*]] = getelementptr inbounds double, double* [[Q]], i64 5
 ; AVX-NEXT:    [[TMP1:%.*]] = bitcast double* [[P0]] to <4 x double>*
 ; AVX-NEXT:    [[TMP2:%.*]] = load <4 x double>, <4 x double>* [[TMP1]], align 8
-; AVX-NEXT:    [[D4:%.*]] = load double, double* [[P4]]
-; AVX-NEXT:    [[D5:%.*]] = load double, double* [[P5]]
-; AVX-NEXT:    [[TMP3:%.*]] = fadd <4 x double> [[TMP2]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
-; AVX-NEXT:    [[A4:%.*]] = fadd double [[D4]], 1.000000e+00
-; AVX-NEXT:    [[A5:%.*]] = fadd double [[D5]], 1.000000e+00
-; AVX-NEXT:    [[TMP4:%.*]] = bitcast double* [[Q0]] to <4 x double>*
-; AVX-NEXT:    store <4 x double> [[TMP3]], <4 x double>* [[TMP4]], align 8
-; AVX-NEXT:    store double [[A4]], double* [[Q4]]
-; AVX-NEXT:    store double [[A5]], double* [[Q5]]
+; AVX-NEXT:    [[TMP3:%.*]] = bitcast double* [[P4]] to <2 x double>*
+; AVX-NEXT:    [[TMP4:%.*]] = load <2 x double>, <2 x double>* [[TMP3]], align 8
+; AVX-NEXT:    [[TMP5:%.*]] = fadd <4 x double> [[TMP2]], <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>
+; AVX-NEXT:    [[TMP6:%.*]] = fadd <2 x double> [[TMP4]], <double 1.000000e+00, double 1.000000e+00>
+; AVX-NEXT:    [[TMP7:%.*]] = bitcast double* [[Q0]] to <4 x double>*
+; AVX-NEXT:    store <4 x double> [[TMP5]], <4 x double>* [[TMP7]], align 8
+; AVX-NEXT:    [[TMP8:%.*]] = bitcast double* [[Q4]] to <2 x double>*
+; AVX-NEXT:    store <2 x double> [[TMP6]], <2 x double>* [[TMP8]], align 8
 ; AVX-NEXT:    ret void
 ;
   %p0 = getelementptr inbounds double, double* %p, i64 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll b/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
+; RUN: opt -slp-vectorizer -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
 
 %class.1 = type { %class.2 }
 %class.2 = type { %"class.3" }
@@ -67,10 +67,13 @@
 ; CHECK-NEXT:    [[ARRAYIDX2_6:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = bitcast i64* [[ARRAYIDX2_6]] to <2 x i64>*
 ; CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[TMP10]], align 1
-; CHECK-NEXT:    [[TMP11:%.*]] = lshr <2 x i64> [[TMP4]], <i64 6, i64 6>
-; CHECK-NEXT:    [[TMP12:%.*]] = add nuw nsw <2 x i64> [[TMP9]], [[TMP11]]
-; CHECK-NEXT:    [[TMP13:%.*]] = bitcast i64* [[ARRAYIDX2_2]] to <2 x i64>*
-; CHECK-NEXT:    store <2 x i64> [[TMP12]], <2 x i64>* [[TMP13]], align 1
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x i64> [[TMP4]], i32 0
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <2 x i64> undef, i64 [[TMP11]], i32 0
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <2 x i64> [[TMP12]], i64 [[TMP5]], i32 1
+; CHECK-NEXT:    [[TMP14:%.*]] = lshr <2 x i64> [[TMP13]], <i64 6, i64 6>
+; CHECK-NEXT:    [[TMP15:%.*]] = add nuw nsw <2 x i64> [[TMP9]], [[TMP14]]
+; CHECK-NEXT:    [[TMP16:%.*]] = bitcast i64* [[ARRAYIDX2_2]] to <2 x i64>*
+; CHECK-NEXT:    store <2 x i64> [[TMP15]], <2 x i64>* [[TMP16]], align 1
 ; CHECK-NEXT:    ret void
 ;
 entry:
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/shift-ashr.ll b/llvm/test/Transforms/SLPVectorizer/X86/shift-ashr.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/shift-ashr.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/shift-ashr.ll
@@ -482,14 +482,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @ashr_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = ashr <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = ashr <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = ashr <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
 ; XOP-LABEL: @ashr_v32i16(
@@ -635,24 +631,53 @@
 }
 
 define void @ashr_v64i8() {
-; CHECK-LABEL: @ashr_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = ashr <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = ashr <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = ashr <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = ashr <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @ashr_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = ashr <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = ashr <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = ashr <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = ashr <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @ashr_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = ashr <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = ashr <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @ashr_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = ashr <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
+;
+; XOP-LABEL: @ashr_v64i8(
+; XOP-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP5:%.*]] = ashr <32 x i8> [[TMP1]], [[TMP3]]
+; XOP-NEXT:    [[TMP6:%.*]] = ashr <32 x i8> [[TMP2]], [[TMP4]]
+; XOP-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; XOP-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/shift-lshr.ll b/llvm/test/Transforms/SLPVectorizer/X86/shift-lshr.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/shift-lshr.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/shift-lshr.ll
@@ -431,14 +431,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @lshr_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = lshr <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = lshr <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = lshr <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
 ; XOP-LABEL: @lshr_v32i16(
@@ -584,24 +580,53 @@
 }
 
 define void @lshr_v64i8() {
-; CHECK-LABEL: @lshr_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = lshr <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = lshr <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = lshr <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = lshr <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @lshr_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = lshr <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = lshr <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = lshr <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = lshr <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @lshr_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = lshr <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = lshr <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @lshr_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = lshr <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
+;
+; XOP-LABEL: @lshr_v64i8(
+; XOP-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP5:%.*]] = lshr <32 x i8> [[TMP1]], [[TMP3]]
+; XOP-NEXT:    [[TMP6:%.*]] = lshr <32 x i8> [[TMP2]], [[TMP4]]
+; XOP-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; XOP-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/shift-shl.ll b/llvm/test/Transforms/SLPVectorizer/X86/shift-shl.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/shift-shl.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/shift-shl.ll
@@ -383,14 +383,10 @@
 ; AVX-NEXT:    ret void
 ;
 ; AVX512-LABEL: @shl_v32i16(
-; AVX512-NEXT:    [[TMP1:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @a16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP2:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @a16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP3:%.*]] = load <16 x i16>, <16 x i16>* bitcast ([32 x i16]* @b16 to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP4:%.*]] = load <16 x i16>, <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @b16, i32 0, i64 16) to <16 x i16>*), align 2
-; AVX512-NEXT:    [[TMP5:%.*]] = shl <16 x i16> [[TMP1]], [[TMP3]]
-; AVX512-NEXT:    [[TMP6:%.*]] = shl <16 x i16> [[TMP2]], [[TMP4]]
-; AVX512-NEXT:    store <16 x i16> [[TMP5]], <16 x i16>* bitcast ([32 x i16]* @c16 to <16 x i16>*), align 2
-; AVX512-NEXT:    store <16 x i16> [[TMP6]], <16 x i16>* bitcast (i16* getelementptr inbounds ([32 x i16], [32 x i16]* @c16, i32 0, i64 16) to <16 x i16>*), align 2
+; AVX512-NEXT:    [[TMP1:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @a16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP2:%.*]] = load <32 x i16>, <32 x i16>* bitcast ([32 x i16]* @b16 to <32 x i16>*), align 2
+; AVX512-NEXT:    [[TMP3:%.*]] = shl <32 x i16> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <32 x i16> [[TMP3]], <32 x i16>* bitcast ([32 x i16]* @c16 to <32 x i16>*), align 2
 ; AVX512-NEXT:    ret void
 ;
 ; XOP-LABEL: @shl_v32i16(
@@ -536,24 +532,53 @@
 }
 
 define void @shl_v64i8() {
-; CHECK-LABEL: @shl_v64i8(
-; CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    [[TMP9:%.*]] = shl <16 x i8> [[TMP1]], [[TMP5]]
-; CHECK-NEXT:    [[TMP10:%.*]] = shl <16 x i8> [[TMP2]], [[TMP6]]
-; CHECK-NEXT:    [[TMP11:%.*]] = shl <16 x i8> [[TMP3]], [[TMP7]]
-; CHECK-NEXT:    [[TMP12:%.*]] = shl <16 x i8> [[TMP4]], [[TMP8]]
-; CHECK-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
-; CHECK-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
-; CHECK-NEXT:    ret void
+; SSE-LABEL: @shl_v64i8(
+; SSE-NEXT:    [[TMP1:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @a8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP2:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP3:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP5:%.*]] = load <16 x i8>, <16 x i8>* bitcast ([64 x i8]* @b8 to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP6:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP7:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP8:%.*]] = load <16 x i8>, <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    [[TMP9:%.*]] = shl <16 x i8> [[TMP1]], [[TMP5]]
+; SSE-NEXT:    [[TMP10:%.*]] = shl <16 x i8> [[TMP2]], [[TMP6]]
+; SSE-NEXT:    [[TMP11:%.*]] = shl <16 x i8> [[TMP3]], [[TMP7]]
+; SSE-NEXT:    [[TMP12:%.*]] = shl <16 x i8> [[TMP4]], [[TMP8]]
+; SSE-NEXT:    store <16 x i8> [[TMP9]], <16 x i8>* bitcast ([64 x i8]* @c8 to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP10]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 16) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP11]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <16 x i8>*), align 1
+; SSE-NEXT:    store <16 x i8> [[TMP12]], <16 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 48) to <16 x i8>*), align 1
+; SSE-NEXT:    ret void
+;
+; AVX-LABEL: @shl_v64i8(
+; AVX-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    [[TMP5:%.*]] = shl <32 x i8> [[TMP1]], [[TMP3]]
+; AVX-NEXT:    [[TMP6:%.*]] = shl <32 x i8> [[TMP2]], [[TMP4]]
+; AVX-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; AVX-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; AVX-NEXT:    ret void
+;
+; AVX512-LABEL: @shl_v64i8(
+; AVX512-NEXT:    [[TMP1:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @a8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP2:%.*]] = load <64 x i8>, <64 x i8>* bitcast ([64 x i8]* @b8 to <64 x i8>*), align 1
+; AVX512-NEXT:    [[TMP3:%.*]] = shl <64 x i8> [[TMP1]], [[TMP2]]
+; AVX512-NEXT:    store <64 x i8> [[TMP3]], <64 x i8>* bitcast ([64 x i8]* @c8 to <64 x i8>*), align 1
+; AVX512-NEXT:    ret void
+;
+; XOP-LABEL: @shl_v64i8(
+; XOP-NEXT:    [[TMP1:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @a8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP2:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP3:%.*]] = load <32 x i8>, <32 x i8>* bitcast ([64 x i8]* @b8 to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP4:%.*]] = load <32 x i8>, <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @b8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    [[TMP5:%.*]] = shl <32 x i8> [[TMP1]], [[TMP3]]
+; XOP-NEXT:    [[TMP6:%.*]] = shl <32 x i8> [[TMP2]], [[TMP4]]
+; XOP-NEXT:    store <32 x i8> [[TMP5]], <32 x i8>* bitcast ([64 x i8]* @c8 to <32 x i8>*), align 1
+; XOP-NEXT:    store <32 x i8> [[TMP6]], <32 x i8>* bitcast (i8* getelementptr inbounds ([64 x i8], [64 x i8]* @c8, i32 0, i64 32) to <32 x i8>*), align 1
+; XOP-NEXT:    ret void
 ;
   %a0  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 0 ), align 1
   %a1  = load i8, i8* getelementptr inbounds ([64 x i8], [64 x i8]* @a8, i32 0, i64 1 ), align 1
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll b/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/stores_vectorize.ll
@@ -92,15 +92,15 @@
 ; CHECK-NEXT:    [[ARRAYIDX11:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 3
 ; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i64>, <4 x i64>* [[TMP0]], align 8
-; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT:    [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
 ; CHECK-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 11
-; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i64* [[ARRAYIDX1]] to <4 x i64>*
-; CHECK-NEXT:    [[TMP4:%.*]] = load <4 x i64>, <4 x i64>* [[TMP3]], align 8
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
-; CHECK-NEXT:    [[TMP6:%.*]] = shl <4 x i64> [[TMP2]], [[TMP5]]
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[ARRAYIDX1]] to <4 x i64>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x i64>, <4 x i64>* [[TMP2]], align 8
+; CHECK-NEXT:    [[REORDER_SHUFFLE1:%.*]] = shufflevector <4 x i64> [[TMP3]], <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+; CHECK-NEXT:    [[TMP4:%.*]] = shl <4 x i64> [[REORDER_SHUFFLE]], [[REORDER_SHUFFLE1]]
 ; CHECK-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 4
-; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i64* [[ARRAYIDX14]] to <4 x i64>*
-; CHECK-NEXT:    store <4 x i64> [[TMP6]], <4 x i64>* [[TMP7]], align 8
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[ARRAYIDX14]] to <4 x i64>*
+; CHECK-NEXT:    store <4 x i64> [[TMP4]], <4 x i64>* [[TMP5]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -147,18 +147,11 @@
 ; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[TMP0]], [[TMP1]]
 ; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 1
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P3]] to <2 x i64>*
-; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* [[TMP2]], align 8
-; CHECK-NEXT:    [[TMP4:%.*]] = lshr <2 x i64> [[TMP3]], <i64 5, i64 5>
-; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[P3]] to <2 x i64>*
-; CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[TMP5]], align 8
 ; CHECK-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 2
-; CHECK-NEXT:    [[TMP6:%.*]] = load i64, i64* [[ARRAYIDX6]], align 8
-; CHECK-NEXT:    [[SHR7:%.*]] = lshr i64 [[TMP6]], 5
-; CHECK-NEXT:    store i64 [[SHR7]], i64* [[ARRAYIDX6]], align 8
 ; CHECK-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 3
-; CHECK-NEXT:    [[TMP7:%.*]] = load i64, i64* [[ARRAYIDX8]], align 8
-; CHECK-NEXT:    [[SHR9:%.*]] = lshr i64 [[TMP7]], 5
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x i64>, <4 x i64>* [[TMP2]], align 8
+; CHECK-NEXT:    [[TMP4:%.*]] = lshr <4 x i64> [[TMP3]], <i64 5, i64 5, i64 5, i64 5>
 ; CHECK-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 5
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
@@ -175,7 +168,8 @@
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
-; CHECK-NEXT:    store i64 [[SHR9]], i64* [[ARRAYIDX8]], align 8
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
+; CHECK-NEXT:    store <4 x i64> [[TMP4]], <4 x i64>* [[TMP5]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -235,18 +229,11 @@
 ; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[TMP0]], [[TMP1]]
 ; CHECK-NEXT:    store float [[ADD]], float* [[ARRAYIDX2]], align 4
 ; CHECK-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 1
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P3]] to <2 x i64>*
-; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x i64>, <2 x i64>* [[TMP2]], align 8
-; CHECK-NEXT:    [[TMP4:%.*]] = lshr <2 x i64> [[TMP3]], <i64 5, i64 5>
-; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[P3]] to <2 x i64>*
-; CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[TMP5]], align 8
 ; CHECK-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 2
-; CHECK-NEXT:    [[TMP6:%.*]] = load i64, i64* [[ARRAYIDX6]], align 8
-; CHECK-NEXT:    [[SHR7:%.*]] = lshr i64 [[TMP6]], 5
-; CHECK-NEXT:    store i64 [[SHR7]], i64* [[ARRAYIDX6]], align 8
 ; CHECK-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 3
-; CHECK-NEXT:    [[TMP7:%.*]] = load i64, i64* [[ARRAYIDX8]], align 8
-; CHECK-NEXT:    [[SHR9:%.*]] = lshr i64 [[TMP7]], 5
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x i64>, <4 x i64>* [[TMP2]], align 8
+; CHECK-NEXT:    [[TMP4:%.*]] = lshr <4 x i64> [[TMP3]], <i64 5, i64 5, i64 5, i64 5>
 ; CHECK-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i64, i64* [[P3]], i64 5
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
@@ -264,7 +251,8 @@
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
 ; CHECK-NEXT:    store i64 5, i64* [[ARRAYIDX9]], align 8
-; CHECK-NEXT:    store i64 [[SHR9]], i64* [[ARRAYIDX8]], align 8
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[P3]] to <4 x i64>*
+; CHECK-NEXT:    store <4 x i64> [[TMP4]], <4 x i64>* [[TMP5]], align 8
 ; CHECK-NEXT:    ret void
 ;
 entry: