Index: lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -333,7 +333,7 @@
   case Instruction::Sub:
     return Instruction::Add;
   default:
-    return 0;
+    return Op;
   }
 }
 
@@ -346,6 +346,23 @@
   return Opcode == CheckedOpcode || AltOpcode == CheckedOpcode;
 }
 
+/// Checks if the \p Opcode can be considered as an operand of a (possibly)
+/// binary operation \p I.
+/// \returns The code of the binary operation of instruction \p I if the
+/// instruction with \p Opcode can be considered as an operand of \p I with the
+/// default value.
+static unsigned tryToRepresentAsInstArg(unsigned Opcode, Instruction *I) {
+  assert(!sameOpcodeOrAlt(Opcode, getAltOpcode(Opcode), I->getOpcode()) &&
+         "Invalid Opcode");
+  if (Opcode != Instruction::PHI && isa<BinaryOperator>(I) &&
+      I->getOpcode() != Instruction::SRem &&
+      I->getOpcode() != Instruction::URem &&
+      I->getOpcode() != Instruction::FRem &&
+      (I->getType()->isIntegerTy() || cast<FPMathOperator>(I)->isFast()))
+    return I->getOpcode();
+  return 0;
+}
+
 /// Chooses the correct key for scheduling data. If \p Op has the same (or
 /// alternate) opcode as \p OpValue, the key is \p Op. Otherwise the key is \p
 /// OpValue.
@@ -367,7 +384,12 @@
 struct RawInstructionsData {
   /// Main Opcode of the instructions going to be vectorized.
   unsigned Opcode = 0;
-
+  /// Position of the first instruction with the \a Opcode.
+  unsigned OpcodePos = 0;
+  /// Need an additional analysis (if at least one of the instruction is not
+  /// same instruction kind as an instruction at OpcodePos position in the
+  /// list).
+  bool NeedAnalysis = false;
   /// The list of instructions have some instructions with alternate opcodes.
   bool HasAltOpcodes = false;
 };
@@ -382,16 +404,39 @@
     return {};
   RawInstructionsData Res;
   unsigned Opcode = I0->getOpcode();
+  unsigned AltOpcode = getAltOpcode(Opcode);
+  unsigned NewOpcodePos = 0;
   // Walk through the list of the vectorized instructions
   // in order to check its structure described by RawInstructionsData.
   for (unsigned Cnt = 0, E = VL.size(); Cnt != E; ++Cnt) {
     auto *I = dyn_cast<Instruction>(VL[Cnt]);
     if (!I)
       return {};
-    if (Opcode != I->getOpcode())
-      Res.HasAltOpcodes = true;
+    if (sameOpcodeOrAlt(Opcode, AltOpcode, I->getOpcode())) {
+      if (Opcode != I->getOpcode()) {
+        Res.HasAltOpcodes = true;
+        if (Res.NeedAnalysis && isOdd(NewOpcodePos))
+          std::swap(Opcode, AltOpcode);
+      }
+      continue;
+    }
+    if (unsigned NewOpcode = tryToRepresentAsInstArg(Opcode, I)) {
+      if (!Instruction::isBinaryOp(Opcode) ||
+          !Instruction::isCommutative(Opcode)) {
+        NewOpcodePos = Cnt;
+        Opcode = NewOpcode;
+        AltOpcode = getAltOpcode(Opcode);
+        Res.NeedAnalysis = true;
+      }
+    } else if (tryToRepresentAsInstArg(I->getOpcode(),
+                                       cast<Instruction>(VL[NewOpcodePos]))) {
+      Res.NeedAnalysis = true;
+    } else {
+      return {};
+    }
   }
   Res.Opcode = Opcode;
+  Res.OpcodePos = NewOpcodePos;
   return Res;
 }
 
@@ -408,9 +453,14 @@
   /// Some of the instructions in the list have alternate opcodes.
   bool IsAltShuffle = false;
 
+  /// Some of the instructions in the list have non alternate opcodes.
+  bool IsNonAlt = false;
+
   InstructionsState() = default;
-  InstructionsState(Value *OpValue, unsigned Opcode, bool IsAltShuffle)
-      : OpValue(OpValue), Opcode(Opcode), IsAltShuffle(IsAltShuffle) {}
+  InstructionsState(Value *OpValue, unsigned Opcode, bool IsAltShuffle, 
+                    bool IsNonAlt)
+      : OpValue(OpValue), Opcode(Opcode), IsAltShuffle(IsAltShuffle),
+        IsNonAlt(IsNonAlt) {}
 };
 
 } // end anonymous namespace
@@ -421,23 +471,31 @@
 static InstructionsState getSameOpcode(ArrayRef<Value *> VL) {
   auto Res = getMainOpcode(VL);
   unsigned Opcode = Res.Opcode;
-  if (!Res.HasAltOpcodes)
-    return InstructionsState(VL[0], Opcode, false);
-  auto *OpInst = cast<Instruction>(VL[0]);
   unsigned AltOpcode = getAltOpcode(Opcode);
+  bool IsNonAlt = llvm::any_of(VL, [Opcode, AltOpcode](Value *V) {
+    return isa<Instruction>(V) &&
+           !sameOpcodeOrAlt(Opcode, AltOpcode,
+                            cast<Instruction>(V)->getOpcode());
+  });
+  if (!Res.NeedAnalysis && !Res.HasAltOpcodes)
+    return InstructionsState(VL[Res.OpcodePos], Opcode, false, IsNonAlt);
+  auto *OpInst = cast<Instruction>(VL[Res.OpcodePos]);
   // Examine each element in the list instructions VL to determine
   // if some operations there could be considered as an alternative
-  // (for example as subtraction relates to addition operation).
+  // (for example as subtraction relates to addition operation) or
+  // operation could be an operand of a (possibly) binary operation.
   for (int Cnt = 0, E = VL.size(); Cnt < E; Cnt++) {
     auto *I = cast<Instruction>(VL[Cnt]);
     unsigned InstOpcode = I->getOpcode();
+    if (Res.NeedAnalysis && !sameOpcodeOrAlt(Opcode, AltOpcode, InstOpcode))
+      if (tryToRepresentAsInstArg(InstOpcode, OpInst))
+        InstOpcode = (Res.HasAltOpcodes && isOdd(Cnt)) ? AltOpcode : Opcode;
     if ((Res.HasAltOpcodes &&
          InstOpcode != (isOdd(Cnt) ? AltOpcode : Opcode)) ||
-        (!Res.HasAltOpcodes && InstOpcode != Opcode)) {
-      return InstructionsState(OpInst, 0, false);
-    }
+        (!Res.HasAltOpcodes && InstOpcode != Opcode))
+      return InstructionsState(OpInst, 0, false, IsNonAlt);
   }
-  return InstructionsState(OpInst, Opcode, Res.HasAltOpcodes);
+  return InstructionsState(OpInst, Opcode, Res.HasAltOpcodes, IsNonAlt);
 }
 
 /// \returns true if all of the values in \p VL have the same type or false
@@ -588,6 +646,7 @@
   void deleteTree() {
     VectorizableTree.clear();
     ScalarToTreeEntry.clear();
+    ExtraScalarToTreeEntry.clear();
     MustGather.clear();
     ExternalUses.clear();
     NumOpsWantToKeepOrder.clear();
@@ -747,10 +806,14 @@
     /// The TreeEntry index containing the user of this entry.  We can actually
     /// have multiple users so the data structure is not truly a tree.
     SmallVector<int, 1> UserTreeIndices;
+
+    /// Info about instruction in this tree entry.
+    InstructionsState State;
   };
 
   /// Create a new VectorizableTree entry.
   void newTreeEntry(ArrayRef<Value *> VL, bool Vectorized, int &UserTreeIdx,
+                    const InstructionsState &S,
                     ArrayRef<unsigned> ReuseShuffleIndices = None,
                     ArrayRef<unsigned> ReorderIndices = None) {
     VectorizableTree.emplace_back(VectorizableTree);
@@ -762,11 +825,24 @@
                                      ReuseShuffleIndices.end());
     Last->ReorderIndices = ReorderIndices;
     if (Vectorized) {
+      Last->State = S;
+      unsigned AltOpcode = getAltOpcode(S.Opcode);
       for (int i = 0, e = VL.size(); i != e; ++i) {
-        assert(!getTreeEntry(VL[i]) && "Scalar already in tree!");
-        ScalarToTreeEntry[VL[i]] = idx;
+        unsigned RealOpcode =
+            (S.IsAltShuffle && isOdd(i)) ? AltOpcode : S.Opcode;
+        Value *Key = (cast<Instruction>(VL[i])->getOpcode() == RealOpcode)
+                         ? VL[i]
+                         : S.OpValue;
+        assert(!getTreeEntry(VL[i], Key) && "Scalar already in tree!");
+        if (VL[i] == Key)
+          ScalarToTreeEntry[Key] = idx;
+        else
+          ExtraScalarToTreeEntry[VL[i]][Key] = idx;
       }
     } else {
+      Last->State.Opcode = 0;
+      Last->State.OpValue = VL[0];
+      Last->State.IsAltShuffle = false;
       MustGather.insert(VL.begin(), VL.end());
     }
 
@@ -786,8 +862,24 @@
     return nullptr;
   }
 
+  TreeEntry *getTreeEntry(Value *V, Value *OpValue) {
+    if (V == OpValue)
+      return getTreeEntry(V);
+    auto I = ExtraScalarToTreeEntry.find(V);
+    if (I != ExtraScalarToTreeEntry.end()) {
+      auto &STT = I->second;
+      auto STTI = STT.find(OpValue);
+      if (STTI != STT.end())
+        return &VectorizableTree[STTI->second];
+    }
+    return nullptr;
+  }
+
   /// Maps a specific scalar to its tree entry.
-  SmallDenseMap<Value*, int> ScalarToTreeEntry;
+  SmallDenseMap<Value *, int> ScalarToTreeEntry;
+
+  /// Maps a specific scalar to its tree entry(s) with leading scalar.
+  SmallDenseMap<Value *, SmallDenseMap<Value *, int>> ExtraScalarToTreeEntry;
 
   /// A list of scalars that we found that we need to keep as scalars.
   ValueSet MustGather;
@@ -994,6 +1086,7 @@
 
     /// Opcode of the current instruction in the schedule data.
     Value *OpValue = nullptr;
+
   };
 
 #ifndef NDEBUG
@@ -1063,10 +1156,7 @@
 
       ScheduleData *BundleMember = SD;
       while (BundleMember) {
-        if (BundleMember->Inst != BundleMember->OpValue) {
-          BundleMember = BundleMember->NextInBundle;
-          continue;
-        }
+
         // Handle the def-use chain dependencies.
         for (Use &U : BundleMember->Inst->operands()) {
           auto *I = dyn_cast<Instruction>(U.get());
@@ -1106,13 +1196,23 @@
 
     void doForAllOpcodes(Value *V,
                          function_ref<void(ScheduleData *SD)> Action) {
-      if (ScheduleData *SD = getScheduleData(V))
-        Action(SD);
+      bool Found = false;
       auto I = ExtraScheduleDataMap.find(V);
-      if (I != ExtraScheduleDataMap.end())
-        for (auto &P : I->second)
-          if (P.second->SchedulingRegionID == SchedulingRegionID)
-            Action(P.second);
+      if (I != ExtraScheduleDataMap.end()) {
+        for (auto &P : I->second) {
+          ScheduleData *SD = P.second;
+          if (SD && !SD->isPartOfBundle())
+            continue;
+          if (SD && SD->SchedulingRegionID == SchedulingRegionID) {
+            Found = true;
+            Action(SD);
+          }
+        }
+      }
+      if (ScheduleData *SD = getScheduleData(V)) {
+        if (!Found || SD->isPartOfBundle())
+          Action(SD);
+      }
     }
 
     /// Put all instructions into the ReadyList which are ready for scheduling.
@@ -1132,7 +1232,8 @@
     /// Checks if a bundle of instructions can be scheduled, i.e. has no
     /// cyclic dependencies. This is only a dry-run, no instructions are
     /// actually moved at this stage.
-    bool tryScheduleBundle(ArrayRef<Value *> VL, BoUpSLP *SLP, Value *OpValue);
+    bool tryScheduleBundle(ArrayRef<Value *> VL, BoUpSLP *SLP,
+                           const InstructionsState &S);
 
     /// Un-bundles a group of instructions.
     void cancelScheduling(ArrayRef<Value *> VL, Value *OpValue);
@@ -1387,9 +1488,16 @@
       continue;
 
     // For each lane:
+    const unsigned Opcode = Entry->State.Opcode;
+    const unsigned AltOpcode = getAltOpcode(Opcode);
     for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
       Value *Scalar = Entry->Scalars[Lane];
       int FoundLane = Lane;
+
+      if (!sameOpcodeOrAlt(Opcode, AltOpcode,
+                           cast<Instruction>(Scalar)->getOpcode()))
+        continue;
+
       if (!Entry->ReuseShuffleIndices.empty()) {
         FoundLane =
             std::distance(Entry->ReuseShuffleIndices.begin(),
@@ -1425,6 +1533,11 @@
           }
         }
 
+        // Skip partially vectorized bundles with internal
+        // dependency and non alternative opcode.
+        if (!getTreeEntry(U) && getTreeEntry(U, Scalar) == Entry)
+          continue;
+
         // Ignore users in the user ignore list.
         if (is_contained(UserIgnoreList, UserInst))
           continue;
@@ -1437,6 +1550,34 @@
   }
 }
 
+static Value *getDefaultConstantForOpcode(unsigned Opcode, Type *Ty) {
+  switch(Opcode) {
+  case Instruction::Add:
+  case Instruction::Sub:
+  case Instruction::Or:
+  case Instruction::Xor:
+  case Instruction::Shl:
+  case Instruction::LShr:
+  case Instruction::AShr:
+    return ConstantInt::getNullValue(Ty);
+  case Instruction::Mul:
+  case Instruction::UDiv:
+  case Instruction::SDiv:
+    return ConstantInt::get(Ty, /*V=*/1);
+  case Instruction::FAdd:
+  case Instruction::FSub:
+    return ConstantFP::get(Ty, /*V=*/0.0);
+  case Instruction::FMul:
+  case Instruction::FDiv:
+    return ConstantFP::get(Ty, /*V=*/1.0);
+  case Instruction::And:
+    return ConstantInt::getAllOnesValue(Ty);
+  default:
+    break;
+  }
+  llvm_unreachable("unknown binop for default constant value");
+}
+
 void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
                             int UserTreeIdx) {
   assert((allConstant(VL) || allSameType(VL)) && "Invalid types!");
@@ -1444,31 +1585,48 @@
   InstructionsState S = getSameOpcode(VL);
   if (Depth == RecursionMaxDepth) {
     LLVM_DEBUG(dbgs() << "SLP: Gathering due to max recursion depth.\n");
-    newTreeEntry(VL, false, UserTreeIdx);
+    newTreeEntry(VL, false, UserTreeIdx, S);
     return;
   }
 
   // Don't handle vectors.
   if (S.OpValue->getType()->isVectorTy()) {
     LLVM_DEBUG(dbgs() << "SLP: Gathering due to vector type.\n");
-    newTreeEntry(VL, false, UserTreeIdx);
+    newTreeEntry(VL, false, UserTreeIdx, S);
     return;
   }
 
   if (StoreInst *SI = dyn_cast<StoreInst>(S.OpValue))
     if (SI->getValueOperand()->getType()->isVectorTy()) {
       LLVM_DEBUG(dbgs() << "SLP: Gathering due to store vector type.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
 
   // If all of the operands are identical or constant we have a simple solution.
   if (allConstant(VL) || isSplat(VL) || !allSameBlock(VL) || !S.Opcode) {
     LLVM_DEBUG(dbgs() << "SLP: Gathering due to C,S,B,O. \n");
-    newTreeEntry(VL, false, UserTreeIdx);
+    newTreeEntry(VL, false, UserTreeIdx, S);
     return;
   }
 
+  unsigned AltOpcode = getAltOpcode(S.Opcode);
+  if (S.IsNonAlt && VL.size() > 2) {
+    unsigned SameOrAlt = 0;
+    for (Value *V : VL) {
+      auto *Instr = cast<Instruction>(V);
+      if (sameOpcodeOrAlt(S.Opcode, AltOpcode, Instr->getOpcode()))
+        SameOrAlt++;
+    }
+    if (SameOrAlt <= (VL.size() / 2)) {
+      LLVM_DEBUG(
+          dbgs()
+          << "SLP: Number of pseudo instructions greater than others.\n");
+      newTreeEntry(VL, false, UserTreeIdx, S);
+      return;
+    }
+  }
+
   // We now know that this is a vector of instructions of the same type from
   // the same block.
 
@@ -1477,7 +1635,7 @@
     if (EphValues.count(VL[i])) {
       LLVM_DEBUG(dbgs() << "SLP: The instruction (" << *VL[i]
                         << ") is ephemeral.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
   }
@@ -1487,7 +1645,7 @@
     LLVM_DEBUG(dbgs() << "SLP: \tChecking bundle: " << *S.OpValue << ".\n");
     if (!E->isSame(VL)) {
       LLVM_DEBUG(dbgs() << "SLP: Gathering due to partial overlap.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
     // Record the reuse of the tree node.  FIXME, currently this is only used to
@@ -1506,7 +1664,7 @@
     if (getTreeEntry(I)) {
       LLVM_DEBUG(dbgs() << "SLP: The instruction (" << *VL[i]
                         << ") is already in tree.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
   }
@@ -1516,7 +1674,7 @@
   for (unsigned i = 0, e = VL.size(); i != e; ++i) {
     if (MustGather.count(VL[i])) {
       LLVM_DEBUG(dbgs() << "SLP: Gathering due to gathered scalar.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
   }
@@ -1530,7 +1688,7 @@
     // Don't go into unreachable blocks. They may contain instructions with
     // dependency cycles which confuse the final scheduling.
     LLVM_DEBUG(dbgs() << "SLP: bundle in unreachable block.\n");
-    newTreeEntry(VL, false, UserTreeIdx);
+    newTreeEntry(VL, false, UserTreeIdx, S);
     return;
   }
 
@@ -1550,7 +1708,7 @@
     LLVM_DEBUG(dbgs() << "SLP: Shuffle for reused scalars.\n");
     if (UniqueValues.size() <= 1 || !llvm::isPowerOf2_32(UniqueValues.size())) {
       LLVM_DEBUG(dbgs() << "SLP: Scalar used twice in bundle.\n");
-      newTreeEntry(VL, false, UserTreeIdx);
+      newTreeEntry(VL, false, UserTreeIdx, S);
       return;
     }
     VL = UniqueValues;
@@ -1562,12 +1720,12 @@
 
   BlockScheduling &BS = *BSRef.get();
 
-  if (!BS.tryScheduleBundle(VL, this, VL0)) {
+  if (!BS.tryScheduleBundle(VL, this, S)) {
     LLVM_DEBUG(dbgs() << "SLP: We are not able to schedule this bundle!\n");
     assert((!BS.getScheduleData(VL0) ||
             !BS.getScheduleData(VL0)->isPartOfBundle()) &&
            "tryScheduleBundle should cancelScheduling on failure");
-    newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+    newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
     return;
   }
   LLVM_DEBUG(dbgs() << "SLP: We are able to schedule this bundle.\n");
@@ -1588,12 +1746,12 @@
                 dbgs()
                 << "SLP: Need to swizzle PHINodes (TerminatorInst use).\n");
             BS.cancelScheduling(VL, VL0);
-            newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+            newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
             return;
           }
         }
 
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of PHINodes.\n");
 
       for (unsigned i = 0, e = PH->getNumIncomingValues(); i < e; ++i) {
@@ -1614,7 +1772,7 @@
       if (Reuse) {
         LLVM_DEBUG(dbgs() << "SLP: Reusing or shuffling extract sequence.\n");
         ++NumOpsWantToKeepOriginalOrder;
-        newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx,
+        newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx, S,
                      ReuseShuffleIndicies);
         return;
       }
@@ -1631,12 +1789,12 @@
         auto StoredCurrentOrderAndNum =
             NumOpsWantToKeepOrder.try_emplace(CurrentOrder).first;
         ++StoredCurrentOrderAndNum->getSecond();
-        newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx, ReuseShuffleIndicies,
+        newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx, S, ReuseShuffleIndicies,
                      StoredCurrentOrderAndNum->getFirst());
         return;
       }
       LLVM_DEBUG(dbgs() << "SLP: Gather extract sequence.\n");
-      newTreeEntry(VL, /*Vectorized=*/false, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, /*Vectorized=*/false, UserTreeIdx, S, ReuseShuffleIndicies);
       BS.cancelScheduling(VL, VL0);
       return;
     }
@@ -1652,7 +1810,7 @@
       if (DL->getTypeSizeInBits(ScalarTy) !=
           DL->getTypeAllocSizeInBits(ScalarTy)) {
         BS.cancelScheduling(VL, VL0);
-        newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+        newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
         LLVM_DEBUG(dbgs() << "SLP: Gathering loads of non-packed type.\n");
         return;
       }
@@ -1665,7 +1823,7 @@
         auto *L = cast<LoadInst>(V);
         if (!L->isSimple()) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs() << "SLP: Gathering non-simple loads.\n");
           return;
         }
@@ -1695,14 +1853,14 @@
           if (CurrentOrder.empty()) {
             // Original loads are consecutive and does not require reordering.
             ++NumOpsWantToKeepOriginalOrder;
-            newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx,
+            newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx, S,
                          ReuseShuffleIndicies);
             LLVM_DEBUG(dbgs() << "SLP: added a vector of loads.\n");
           } else {
             // Need to reorder.
             auto I = NumOpsWantToKeepOrder.try_emplace(CurrentOrder).first;
             ++I->getSecond();
-            newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx,
+            newTreeEntry(VL, /*Vectorized=*/true, UserTreeIdx, S,
                          ReuseShuffleIndicies, I->getFirst());
             LLVM_DEBUG(dbgs() << "SLP: added a vector of jumbled loads.\n");
           }
@@ -1712,7 +1870,7 @@
 
       LLVM_DEBUG(dbgs() << "SLP: Gathering non-consecutive loads.\n");
       BS.cancelScheduling(VL, VL0);
-      newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
       return;
     }
     case Instruction::ZExt:
@@ -1732,13 +1890,13 @@
         Type *Ty = cast<Instruction>(VL[i])->getOperand(0)->getType();
         if (Ty != SrcTy || !isValidElementType(Ty)) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs()
                      << "SLP: Gathering casts with different src types.\n");
           return;
         }
       }
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of casts.\n");
 
       for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
@@ -1761,14 +1919,14 @@
         if (Cmp->getPredicate() != P0 ||
             Cmp->getOperand(0)->getType() != ComparedTy) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs()
                      << "SLP: Gathering cmp with different predicate.\n");
           return;
         }
       }
 
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of compares.\n");
 
       for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
@@ -1800,7 +1958,7 @@
     case Instruction::And:
     case Instruction::Or:
     case Instruction::Xor:
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of bin op.\n");
 
       // Sort operands of the instructions so that each side is more likely to
@@ -1816,10 +1974,21 @@
       for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
         ValueList Operands;
         // Prepare the operand vector.
-        for (Value *j : VL)
-          Operands.push_back(cast<Instruction>(j)->getOperand(i));
-
-        buildTree_rec(Operands, Depth + 1, UserTreeIdx);
+        for (Value *VecOp : VL) {
+          auto *I = cast<Instruction>(VecOp);
+          if (I->getOpcode() == S.Opcode) {
+             Operands.push_back(I->getOperand(i));
+             continue;
+          }
+          assert(Instruction::isBinaryOp(S.Opcode) &&
+                  "Expected a binary operation.");
+          Value *Operand = isOdd(i)
+                        ? getDefaultConstantForOpcode(S.Opcode, I->getType())
+                        : VecOp;
+          Operands.push_back(Operand);
+        }
+        if (allSameType(Operands))
+          buildTree_rec(Operands, Depth + 1, UserTreeIdx);
       }
       return;
 
@@ -1829,7 +1998,7 @@
         if (cast<Instruction>(VL[j])->getNumOperands() != 2) {
           LLVM_DEBUG(dbgs() << "SLP: not-vectorizable GEP (nested indexes).\n");
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           return;
         }
       }
@@ -1843,7 +2012,7 @@
           LLVM_DEBUG(dbgs()
                      << "SLP: not-vectorizable GEP (different types).\n");
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           return;
         }
       }
@@ -1855,12 +2024,12 @@
           LLVM_DEBUG(dbgs()
                      << "SLP: not-vectorizable GEP (non-constant indexes).\n");
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           return;
         }
       }
 
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of GEPs.\n");
       for (unsigned i = 0, e = 2; i < e; ++i) {
         ValueList Operands;
@@ -1877,12 +2046,12 @@
       for (unsigned i = 0, e = VL.size() - 1; i < e; ++i)
         if (!isConsecutiveAccess(VL[i], VL[i + 1], *DL, *SE)) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs() << "SLP: Non-consecutive store.\n");
           return;
         }
 
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a vector of stores.\n");
 
       ValueList Operands;
@@ -1900,7 +2069,7 @@
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
       if (!isTriviallyVectorizable(ID)) {
         BS.cancelScheduling(VL, VL0);
-        newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+        newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
         LLVM_DEBUG(dbgs() << "SLP: Non-vectorizable call.\n");
         return;
       }
@@ -1914,7 +2083,7 @@
             getVectorIntrinsicIDForCall(CI2, TLI) != ID ||
             !CI->hasIdenticalOperandBundleSchema(*CI2)) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs() << "SLP: mismatched calls:" << *CI << "!=" << *VL[i]
                             << "\n");
           return;
@@ -1925,7 +2094,7 @@
           Value *A1J = CI2->getArgOperand(1);
           if (A1I != A1J) {
             BS.cancelScheduling(VL, VL0);
-            newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+            newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
             LLVM_DEBUG(dbgs() << "SLP: mismatched arguments in call:" << *CI
                               << " argument " << A1I << "!=" << A1J << "\n");
             return;
@@ -1937,22 +2106,32 @@
                         CI->op_begin() + CI->getBundleOperandsEndIndex(),
                         CI2->op_begin() + CI2->getBundleOperandsStartIndex())) {
           BS.cancelScheduling(VL, VL0);
-          newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+          newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
           LLVM_DEBUG(dbgs() << "SLP: mismatched bundle operands in calls:"
                             << *CI << "!=" << *VL[i] << '\n');
           return;
         }
       }
 
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       for (unsigned i = 0, e = CI->getNumArgOperands(); i != e; ++i) {
         ValueList Operands;
         // Prepare the operand vector.
-        for (Value *j : VL) {
-          CallInst *CI2 = dyn_cast<CallInst>(j);
-          Operands.push_back(CI2->getArgOperand(i));
+        for (Value *VecOp : VL) {
+          auto *I = cast<Instruction>(VecOp);
+          if (I->getOpcode() == S.Opcode) {
+             Operands.push_back(I->getOperand(i));
+             continue;
+          }
+          assert(Instruction::isBinaryOp(S.Opcode) &&
+                  "Expected a binary operation.");
+          Value *Operand = isOdd(i)
+                        ? getDefaultConstantForOpcode(S.Opcode, I->getType())
+                        : VecOp;
+          Operands.push_back(Operand);
         }
-        buildTree_rec(Operands, Depth + 1, UserTreeIdx);
+        if (allSameType(Operands))
+          buildTree_rec(Operands, Depth + 1, UserTreeIdx);
       }
       return;
     }
@@ -1961,11 +2140,11 @@
       // then do not vectorize this instruction.
       if (!S.IsAltShuffle) {
         BS.cancelScheduling(VL, VL0);
-        newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+        newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
         LLVM_DEBUG(dbgs() << "SLP: ShuffleVector are not vectorized.\n");
         return;
       }
-      newTreeEntry(VL, true, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, true, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: added a ShuffleVector op.\n");
 
       // Reorder operands if reordering would enable vectorization.
@@ -1980,8 +2159,19 @@
       for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
         ValueList Operands;
         // Prepare the operand vector.
-        for (Value *j : VL)
-          Operands.push_back(cast<Instruction>(j)->getOperand(i));
+        for (Value *VecOp : VL) {
+          auto *I = cast<Instruction>(VecOp);
+          if (sameOpcodeOrAlt(S.Opcode, AltOpcode, I->getOpcode())) {
+            Operands.push_back(I->getOperand(i));
+            continue;
+          }
+          assert(Instruction::isBinaryOp(S.Opcode) &&
+                  "Expected a binary operation.");
+          Value *Operand = isOdd(i)
+                        ? getDefaultConstantForOpcode(S.Opcode, I->getType())
+                        : VecOp;
+          Operands.push_back(Operand);
+        }
 
         buildTree_rec(Operands, Depth + 1, UserTreeIdx);
       }
@@ -1989,7 +2179,7 @@
 
     default:
       BS.cancelScheduling(VL, VL0);
-      newTreeEntry(VL, false, UserTreeIdx, ReuseShuffleIndicies);
+      newTreeEntry(VL, false, UserTreeIdx, S, ReuseShuffleIndicies);
       LLVM_DEBUG(dbgs() << "SLP: Gathering unknown instruction.\n");
       return;
   }
@@ -2147,11 +2337,10 @@
     }
     return ReuseShuffleCost + getGatherCost(VL);
   }
-  InstructionsState S = getSameOpcode(VL);
-  assert(S.Opcode && allSameType(VL) && allSameBlock(VL) && "Invalid VL");
-  Instruction *VL0 = cast<Instruction>(S.OpValue);
-  unsigned ShuffleOrOp = S.IsAltShuffle ?
-               (unsigned) Instruction::ShuffleVector : S.Opcode;
+  assert(E->State.Opcode && allSameType(VL) && allSameBlock(VL) && "Invalid VL");
+  auto *VL0 = cast<Instruction>(E->State.OpValue);
+  unsigned ShuffleOrOp = E->State.IsAltShuffle ?
+               (unsigned) Instruction::ShuffleVector : E->State.Opcode;
   switch (ShuffleOrOp) {
     case Instruction::PHI:
       return 0;
@@ -2239,7 +2428,7 @@
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -=
             (ReuseShuffleNumbers - VL.size()) *
-            TTI->getCastInstrCost(S.Opcode, ScalarTy, SrcTy, VL0);
+            TTI->getCastInstrCost(VL0->getOpcode(), VL0->getType(), SrcTy, VL0);
       }
 
       // Calculate the cost of this instruction.
@@ -2261,13 +2450,13 @@
       // Calculate the cost of this instruction.
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) *
-                            TTI->getCmpSelInstrCost(S.Opcode, ScalarTy,
+                            TTI->getCmpSelInstrCost(VL0->getOpcode(), VL0->getType(),
                                                     Builder.getInt1Ty(), VL0);
       }
       VectorType *MaskTy = VectorType::get(Builder.getInt1Ty(), VL.size());
       int ScalarCost = VecTy->getNumElements() *
-          TTI->getCmpSelInstrCost(S.Opcode, ScalarTy, Builder.getInt1Ty(), VL0);
-      int VecCost = TTI->getCmpSelInstrCost(S.Opcode, VecTy, MaskTy, VL0);
+          TTI->getCmpSelInstrCost(ShuffleOrOp, ScalarTy, Builder.getInt1Ty(), VL0);
+      int VecCost = TTI->getCmpSelInstrCost(ShuffleOrOp, VecTy, MaskTy, VL0);
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::Add:
@@ -2293,7 +2482,7 @@
       TargetTransformInfo::OperandValueKind Op1VK =
           TargetTransformInfo::OK_AnyValue;
       TargetTransformInfo::OperandValueKind Op2VK =
-          TargetTransformInfo::OK_UniformConstantValue;
+          TargetTransformInfo::OK_AnyValue;
       TargetTransformInfo::OperandValueProperties Op1VP =
           TargetTransformInfo::OP_None;
       TargetTransformInfo::OperandValueProperties Op2VP =
@@ -2304,40 +2493,40 @@
       // If instead not all operands are constants, then set the operand kind
       // to OK_AnyValue. If all operands are constants but not the same,
       // then set the operand kind to OK_NonUniformConstantValue.
-      ConstantInt *CInt = nullptr;
-      for (unsigned i = 0; i < VL.size(); ++i) {
-        const Instruction *I = cast<Instruction>(VL[i]);
-        if (!isa<ConstantInt>(I->getOperand(1))) {
-          Op2VK = TargetTransformInfo::OK_AnyValue;
-          break;
-        }
-        if (i == 0) {
-          CInt = cast<ConstantInt>(I->getOperand(1));
-          continue;
+      if (auto *CInt = dyn_cast<ConstantInt>(VL0->getOperand(1))) {
+        Op2VK = TargetTransformInfo::OK_UniformConstantValue;
+        const unsigned Opcode = E->State.Opcode;
+        for (auto *V : VL) {
+          auto *I = cast<Instruction>(V);
+          if (I == VL0 || Opcode != I->getOpcode())
+            continue;
+          if (!isa<ConstantInt>(I->getOperand(1))) {
+            Op2VK = TargetTransformInfo::OK_AnyValue;
+            break;
+          }
+          if (Op2VK == TargetTransformInfo::OK_UniformConstantValue &&
+              CInt != cast<ConstantInt>(I->getOperand(1)))
+            Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
         }
+        // FIXME: Currently cost of model modification for division by power of
+        // 2 is handled for X86 and AArch64. Add support for other targets.
         if (Op2VK == TargetTransformInfo::OK_UniformConstantValue &&
-            CInt != cast<ConstantInt>(I->getOperand(1)))
-          Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
+            CInt->getValue().isPowerOf2())
+          Op2VP = TargetTransformInfo::OP_PowerOf2;
       }
-      // FIXME: Currently cost of model modification for division by power of
-      // 2 is handled for X86 and AArch64. Add support for other targets.
-      if (Op2VK == TargetTransformInfo::OK_UniformConstantValue && CInt &&
-          CInt->getValue().isPowerOf2())
-        Op2VP = TargetTransformInfo::OP_PowerOf2;
 
       SmallVector<const Value *, 4> Operands(VL0->operand_values());
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -=
             (ReuseShuffleNumbers - VL.size()) *
-            TTI->getArithmeticInstrCost(S.Opcode, ScalarTy, Op1VK, Op2VK, Op1VP,
+            TTI->getArithmeticInstrCost(VL0->getOpcode(), VL0->getType(), Op1VK, Op2VK, Op1VP,
                                         Op2VP, Operands);
       }
-      int ScalarCost =
-          VecTy->getNumElements() *
-          TTI->getArithmeticInstrCost(S.Opcode, ScalarTy, Op1VK, Op2VK, Op1VP,
-                                      Op2VP, Operands);
-      int VecCost = TTI->getArithmeticInstrCost(S.Opcode, VecTy, Op1VK, Op2VK,
-                                                Op1VP, Op2VP, Operands);
+      int ScalarCost = VecTy->getNumElements() *
+                       TTI->getArithmeticInstrCost(E->State.Opcode, ScalarTy,
+                                                   Op1VK, Op2VK, Op1VP, Op2VP);
+      int VecCost = TTI->getArithmeticInstrCost(E->State.Opcode, VecTy, Op1VK,
+                                                Op2VK, Op1VP, Op2VP);
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::GetElementPtr: {
@@ -2526,7 +2715,7 @@
   Instruction *PrevInst = nullptr;
 
   for (const auto &N : VectorizableTree) {
-    Instruction *Inst = dyn_cast<Instruction>(N.Scalars[0]);
+    auto *Inst = dyn_cast<Instruction>(N.State.OpValue);
     if (!Inst)
       continue;
 
@@ -2610,7 +2799,7 @@
 
     int C = getEntryCost(&TE);
     LLVM_DEBUG(dbgs() << "SLP: Adding cost " << C
-                      << " for bundle that starts with " << *TE.Scalars[0]
+                      << " for bundle that starts with " << *TE.State.OpValue
                       << ".\n");
     Cost += C;
   }
@@ -2632,7 +2821,7 @@
     // extend the extracted value back to the original type. Here, we account
     // for the extract and the added cost of the sign extend if needed.
     auto *VecTy = VectorType::get(EU.Scalar->getType(), BundleWidth);
-    auto *ScalarRoot = VectorizableTree[0].Scalars[0];
+    auto *ScalarRoot = VectorizableTree[0].State.OpValue;
     if (MinBWs.count(ScalarRoot)) {
       auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
       auto Extend =
@@ -2709,13 +2898,15 @@
                                         SmallVectorImpl<Value *> &Right) {
   // Push left and right operands of binary operation into Left and Right
   unsigned AltOpcode = getAltOpcode(Opcode);
-  (void)AltOpcode;
   for (Value *V : VL) {
     auto *I = cast<Instruction>(V);
-    assert(sameOpcodeOrAlt(Opcode, AltOpcode, I->getOpcode()) &&
-           "Incorrect instruction in vector");
-    Left.push_back(I->getOperand(0));
-    Right.push_back(I->getOperand(1));
+    if (sameOpcodeOrAlt(Opcode, AltOpcode, I->getOpcode())) {
+      Left.push_back(I->getOperand(0));
+      Right.push_back(I->getOperand(1));
+    } else {
+      Left.push_back(I);
+      Right.push_back(getDefaultConstantForOpcode(Opcode, I->getType()));
+    }
   }
 
   // Reorder if we have a commutative operation and consecutive access
@@ -2764,8 +2955,13 @@
     int i, unsigned Opcode, Instruction &I, ArrayRef<Value *> Left,
     ArrayRef<Value *> Right, bool AllSameOpcodeLeft, bool AllSameOpcodeRight,
     bool SplatLeft, bool SplatRight, Value *&VLeft, Value *&VRight) {
-  VLeft = I.getOperand(0);
-  VRight = I.getOperand(1);
+  if (I.getOpcode() == Opcode) {
+    VLeft = I.getOperand(0);
+    VRight = I.getOperand(1);
+  } else {
+    VLeft = &I;
+    VRight = getDefaultConstantForOpcode(Opcode, I.getType());
+  }
   // If we have "SplatRight", try to see if commuting is needed to preserve it.
   if (SplatRight) {
     if (VRight == Right[i - 1])
@@ -2829,8 +3025,15 @@
     // Peel the first iteration out of the loop since there's nothing
     // interesting to do anyway and it simplifies the checks in the loop.
     auto *I = cast<Instruction>(VL[0]);
-    Value *VLeft = I->getOperand(0);
-    Value *VRight = I->getOperand(1);
+    Value *VLeft;
+    Value *VRight;
+    if (I->getOpcode() == Opcode) {
+      VLeft = I->getOperand(0);
+      VRight = I->getOperand(1);
+    } else {
+      VLeft = I;
+      VRight = getDefaultConstantForOpcode(Opcode, I->getType());
+    }
     if (!isa<Instruction>(VRight) && isa<Instruction>(VLeft))
       // Favor having instruction to the right. FIXME: why?
       std::swap(VLeft, VRight);
@@ -2935,13 +3138,22 @@
   // VL.back() and iterate over schedule data until we reach the end of the
   // bundle. The end of the bundle is marked by null ScheduleData.
   if (BlocksSchedules.count(BB)) {
-    auto *Bundle =
+    ScheduleData *Bundle =
         BlocksSchedules[BB]->getScheduleData(isOneOf(OpValue, VL.back()));
-    if (Bundle && Bundle->isPartOfBundle())
-      for (; Bundle; Bundle = Bundle->NextInBundle)
-        if (Bundle->OpValue == Bundle->Inst)
+    if (Bundle && Bundle->isPartOfBundle()) {
+      Bundle = Bundle->FirstInBundle;
+      int MaxDist = 0;
+      while (Bundle) {
+        int Dist = std::distance(BB->begin(), Bundle->Inst->getIterator());
+        if (Dist > MaxDist) {
           LastInst = Bundle->Inst;
+          MaxDist = Dist;
+        }
+        Bundle = Bundle->NextInBundle;
+      }
+    }
   }
+  
 
   // LastInst can still be null at this point if there's either not an entry
   // for BB in BlocksSchedules or there's no ScheduleData available for
@@ -3087,12 +3299,12 @@
   IRBuilder<>::InsertPointGuard Guard(Builder);
 
   if (E->VectorizedValue) {
-    LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n");
+    LLVM_DEBUG(dbgs() << "SLP: Diamond merged for "
+                      << *E->State.OpValue << ".\n");
     return E->VectorizedValue;
   }
 
-  InstructionsState S = getSameOpcode(E->Scalars);
-  Instruction *VL0 = cast<Instruction>(E->Scalars[0]);
+  auto *VL0 = cast<Instruction>(E->State.OpValue);
   Type *ScalarTy = VL0->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL0))
     ScalarTy = SI->getValueOperand()->getType();
@@ -3115,8 +3327,8 @@
     return V;
   }
 
-  unsigned ShuffleOrOp = S.IsAltShuffle ?
-           (unsigned) Instruction::ShuffleVector : S.Opcode;
+  unsigned ShuffleOrOp = E->State.IsAltShuffle ?
+           (unsigned) Instruction::ShuffleVector : E->State.Opcode;
   switch (ShuffleOrOp) {
     case Instruction::PHI: {
       PHINode *PH = dyn_cast<PHINode>(VL0);
@@ -3281,7 +3493,7 @@
 
       CmpInst::Predicate P0 = cast<CmpInst>(VL0)->getPredicate();
       Value *V;
-      if (S.Opcode == Instruction::FCmp)
+      if (E->State.Opcode == Instruction::FCmp)
         V = Builder.CreateFCmp(P0, L, R);
       else
         V = Builder.CreateICmp(P0, L, R);
@@ -3343,13 +3555,19 @@
     case Instruction::Xor: {
       ValueList LHSVL, RHSVL;
       if (isa<BinaryOperator>(VL0) && VL0->isCommutative())
-        reorderInputsAccordingToOpcode(S.Opcode, E->Scalars, LHSVL,
+        reorderInputsAccordingToOpcode(E->State.Opcode, E->Scalars, LHSVL,
                                        RHSVL);
       else
         for (Value *V : E->Scalars) {
           auto *I = cast<Instruction>(V);
-          LHSVL.push_back(I->getOperand(0));
-          RHSVL.push_back(I->getOperand(1));
+          if (I->getOpcode() == E->State.Opcode) {
+            LHSVL.push_back(I->getOperand(0));
+            RHSVL.push_back(I->getOperand(1));
+          } else {
+            LHSVL.push_back(V);
+            RHSVL.push_back(
+                getDefaultConstantForOpcode(E->State.Opcode, I->getType()));
+          }
         }
 
       setInsertPointAfterBundle(E->Scalars, VL0);
@@ -3363,7 +3581,7 @@
       }
 
       Value *V = Builder.CreateBinOp(
-          static_cast<Instruction::BinaryOps>(S.Opcode), LHS, RHS);
+          static_cast<Instruction::BinaryOps>(VL0->getOpcode()), LHS, RHS);
       propagateIRFlags(V, E->Scalars, VL0);
       if (auto *I = dyn_cast<Instruction>(V))
         V = propagateMetadata(I, E->Scalars);
@@ -3545,9 +3763,9 @@
     }
     case Instruction::ShuffleVector: {
       ValueList LHSVL, RHSVL;
-      assert(Instruction::isBinaryOp(S.Opcode) &&
+      assert(Instruction::isBinaryOp(E->State.Opcode) &&
              "Invalid Shuffle Vector Operand");
-      reorderAltShuffleOperands(S.Opcode, E->Scalars, LHSVL, RHSVL);
+      reorderAltShuffleOperands(E->State.Opcode, E->Scalars, LHSVL, RHSVL);
       setInsertPointAfterBundle(E->Scalars, VL0);
 
       Value *LHS = vectorizeTree(LHSVL);
@@ -3560,9 +3778,9 @@
 
       // Create a vector of LHS op1 RHS
       Value *V0 = Builder.CreateBinOp(
-          static_cast<Instruction::BinaryOps>(S.Opcode), LHS, RHS);
+          static_cast<Instruction::BinaryOps>(E->State.Opcode), LHS, RHS);
 
-      unsigned AltOpcode = getAltOpcode(S.Opcode);
+      unsigned AltOpcode = getAltOpcode(E->State.Opcode);
       // Create a vector of LHS op2 RHS
       Value *V1 = Builder.CreateBinOp(
           static_cast<Instruction::BinaryOps>(AltOpcode), LHS, RHS);
@@ -3584,8 +3802,13 @@
       }
 
       Value *ShuffleMask = ConstantVector::get(Mask);
-      propagateIRFlags(V0, EvenScalars);
-      propagateIRFlags(V1, OddScalars);
+      InstructionsState S = getSameOpcode(EvenScalars);
+      assert(!S.IsAltShuffle && "Unexpected alternate opcode");
+      propagateIRFlags(V0, EvenScalars, S.OpValue);
+
+      S = getSameOpcode(OddScalars);
+      assert(!S.IsAltShuffle && "Unexpected alternate opcode");
+      propagateIRFlags(V1, OddScalars, S.OpValue);
 
       Value *V = Builder.CreateShuffleVector(V0, V1, ShuffleMask);
       if (Instruction *I = dyn_cast<Instruction>(V))
@@ -3623,7 +3846,7 @@
   // If the vectorized tree can be rewritten in a smaller type, we truncate the
   // vectorized root. InstCombine will then rewrite the entire expression. We
   // sign extend the extracted values below.
-  auto *ScalarRoot = VectorizableTree[0].Scalars[0];
+  auto *ScalarRoot = VectorizableTree[0].State.OpValue;
   if (MinBWs.count(ScalarRoot)) {
     if (auto *I = dyn_cast<Instruction>(VectorRoot))
       Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
@@ -3656,6 +3879,7 @@
     // has multiple uses of the same value.
     if (User && !is_contained(Scalar->users(), User))
       continue;
+
     TreeEntry *E = getTreeEntry(Scalar);
     assert(E && "Invalid scalar");
     assert(!E->NeedToGather && "Extracting from a gather list");
@@ -3735,9 +3959,22 @@
     assert(Entry->VectorizedValue && "Can't find vectorizable value");
 
     // For each lane:
+    const unsigned Opcode = Entry->State.Opcode;
+    const unsigned AltOpcode = getAltOpcode(Opcode);
     for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
       Value *Scalar = Entry->Scalars[Lane];
 
+      if (!sameOpcodeOrAlt(Opcode, AltOpcode,
+                           cast<Instruction>(Scalar)->getOpcode()))
+        continue;
+
+      // Skip partially vectorized bundles with internal
+      // dependency and non alternative opcode.
+      if (llvm::any_of(Scalar->users(), [this, Entry, Scalar](User *U) {
+            return !getTreeEntry(U) && getTreeEntry(U, Scalar) == Entry;
+          }))
+        continue;
+
       Type *Ty = Scalar->getType();
       if (!Ty->isVoidTy()) {
 #ifndef NDEBUG
@@ -3848,8 +4085,9 @@
 // Groups the instructions to a bundle (which is then a single scheduling entity)
 // and schedules instructions until the bundle gets ready.
 bool BoUpSLP::BlockScheduling::tryScheduleBundle(ArrayRef<Value *> VL,
-                                                 BoUpSLP *SLP, Value *OpValue) {
-  if (isa<PHINode>(OpValue))
+                                                 BoUpSLP *SLP,
+                                                 const InstructionsState &S) {
+  if (isa<PHINode>(S.OpValue))
     return true;
 
   // Initialize the instruction bundle.
@@ -3857,17 +4095,17 @@
   ScheduleData *PrevInBundle = nullptr;
   ScheduleData *Bundle = nullptr;
   bool ReSchedule = false;
-  LLVM_DEBUG(dbgs() << "SLP:  bundle: " << *OpValue << "\n");
+  LLVM_DEBUG(dbgs() << "SLP:  bundle: " << *S.OpValue << "\n");
 
   // Make sure that the scheduling region contains all
   // instructions of the bundle.
   for (Value *V : VL) {
-    if (!extendSchedulingRegion(V, OpValue))
+    if (!extendSchedulingRegion(V, S.OpValue))
       return false;
   }
 
   for (Value *V : VL) {
-    ScheduleData *BundleMember = getScheduleData(V);
+    ScheduleData *BundleMember = getScheduleData(V, isOneOf(S.OpValue, V));
     assert(BundleMember &&
            "no ScheduleData for bundle member (maybe not in same basic block)");
     if (BundleMember->IsScheduled) {
@@ -3929,9 +4167,10 @@
     }
   }
   if (!Bundle->isReady()) {
-    cancelScheduling(VL, OpValue);
+    cancelScheduling(VL, S.OpValue);
     return false;
   }
+
   return true;
 }
 
@@ -3940,7 +4179,7 @@
   if (isa<PHINode>(OpValue))
     return;
 
-  ScheduleData *Bundle = getScheduleData(OpValue);
+  ScheduleData *Bundle = getScheduleData(OpValue)->FirstInBundle;
   LLVM_DEBUG(dbgs() << "SLP:  cancel scheduling of " << *Bundle << "\n");
   assert(!Bundle->IsScheduled &&
          "Can't cancel bundle which is already scheduled");
@@ -3984,10 +4223,15 @@
       return false;
     assert(isInSchedulingRegion(ISD) &&
            "ScheduleData not in scheduling region");
-    ScheduleData *SD = allocateScheduleDataChunks();
-    SD->Inst = I;
-    SD->init(SchedulingRegionID, OpValue);
-    ExtraScheduleDataMap[I][OpValue] = SD;
+    if (I == OpValue) {
+      ExtraScheduleDataMap[I][OpValue] = ISD;
+    } else
+    {
+      ScheduleData *SD = allocateScheduleDataChunks();
+      SD->Inst = I;
+      SD->init(SchedulingRegionID, OpValue);
+      ExtraScheduleDataMap[I][OpValue] = SD;
+    }
     return true;
   };
   if (CheckSheduleForI(I))
@@ -4059,6 +4303,7 @@
       SD = allocateScheduleDataChunks();
       ScheduleDataMap[I] = SD;
       SD->Inst = I;
+      SD->OpValue = I;
     }
     assert(!isInSchedulingRegion(SD) &&
            "new ScheduleData already in scheduling region");
@@ -4105,19 +4350,40 @@
                           << "\n");
         BundleMember->Dependencies = 0;
         BundleMember->resetUnscheduledDeps();
-
-        // Handle def-use chain dependencies.
         if (BundleMember->OpValue != BundleMember->Inst) {
-          ScheduleData *UseSD = getScheduleData(BundleMember->Inst);
-          if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle)) {
-            BundleMember->Dependencies++;
-            ScheduleData *DestBundle = UseSD->FirstInBundle;
-            if (!DestBundle->IsScheduled)
-              BundleMember->incrementUnscheduledDeps(1);
-            if (!DestBundle->hasValidDependencies())
-              WorkList.push_back(DestBundle);
+          for (Use &U : BundleMember->Inst->operands()) {
+            auto *I = dyn_cast<Instruction>(U.get());
+            if (!I)
+              continue;
+            ScheduleData *UseSD = getScheduleData(I);
+            if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle) &&
+                UseSD->FirstInBundle == BundleMember->FirstInBundle) {
+              BundleMember->Dependencies++;
+              ScheduleData *DestBundle = UseSD->FirstInBundle;
+              if (!DestBundle->IsScheduled) {
+                BundleMember->incrementUnscheduledDeps(1);
+              }
+              if (!DestBundle->hasValidDependencies())
+                WorkList.push_back(DestBundle);
+            }
+          }
+          for (User *U : BundleMember->Inst->users()) {
+            if (isa<Instruction>(U)) {
+              ScheduleData *UseSD = getScheduleData(U);
+              if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle) &&
+                  UseSD->FirstInBundle != BundleMember->FirstInBundle) {
+                BundleMember->Dependencies++;
+                ScheduleData *DestBundle = UseSD->FirstInBundle;
+                if (!DestBundle->IsScheduled) {
+                  BundleMember->incrementUnscheduledDeps(1);
+                }
+                if (!DestBundle->hasValidDependencies())
+                  WorkList.push_back(DestBundle);
+              }
+            }
           }
         } else {
+          // Handle def-use chain dependencies.
           for (User *U : BundleMember->Inst->users()) {
             if (isa<Instruction>(U)) {
               ScheduleData *UseSD = getScheduleData(U);
@@ -4249,7 +4515,7 @@
        I = I->getNextNode()) {
     BS->doForAllOpcodes(I, [this, &Idx, &NumToSchedule, BS](ScheduleData *SD) {
       assert(SD->isPartOfBundle() ==
-                 (getTreeEntry(SD->Inst) != nullptr) &&
+                 (getTreeEntry(SD->Inst, SD->OpValue) != nullptr) &&
              "scheduler and vectorizer bundle mismatch");
       SD->FirstInBundle->SchedulingPriority = Idx++;
       if (SD->isSchedulingEntity()) {
@@ -4258,6 +4524,7 @@
       }
     });
   }
+
   BS->initialFillReadyList(ReadyInsts);
 
   Instruction *LastScheduledInst = BS->ScheduleEnd;
@@ -4271,13 +4538,13 @@
     // there yet.
     ScheduleData *BundleMember = picked;
     while (BundleMember) {
-      Instruction *pickedInst = BundleMember->Inst;
-      if (LastScheduledInst->getNextNode() != pickedInst) {
-        BS->BB->getInstList().remove(pickedInst);
+      Instruction *PickedInst = BundleMember->Inst;
+      if (LastScheduledInst != PickedInst) {
+        BS->BB->getInstList().remove(PickedInst);
         BS->BB->getInstList().insert(LastScheduledInst->getIterator(),
-                                     pickedInst);
+                                     PickedInst);
       }
-      LastScheduledInst = pickedInst;
+      LastScheduledInst = PickedInst;
       BundleMember = BundleMember->NextInBundle;
     }
 
Index: test/Transforms/SLPVectorizer/AArch64/transpose.ll
===================================================================
--- test/Transforms/SLPVectorizer/AArch64/transpose.ll
+++ test/Transforms/SLPVectorizer/AArch64/transpose.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -slp-vectorizer -instcombine -S | FileCheck %s
 
 target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
@@ -5,10 +6,10 @@
 
 define <2 x i64> @build_vec_v2i64(<2 x i64> %v0, <2 x i64> %v1) {
 ; CHECK-LABEL: @build_vec_v2i64(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i64> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i64> %v0, i32 1
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i64> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i64> %v1, i32 1
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i64> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i64> [[V0]], i32 1
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i64> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i64> [[V1]], i32 1
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i64 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i64 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP1_0:%.*]] = sub i64 [[V0_0]], [[V1_0]]
@@ -36,12 +37,12 @@
 
 define void @store_chain_v2i64(i64* %a, i64* %b, i64* %c) {
 ; CHECK-LABEL: @store_chain_v2i64(
-; CHECK-NEXT:    [[A_1:%.*]] = getelementptr i64, i64* %a, i64 1
-; CHECK-NEXT:    [[B_1:%.*]] = getelementptr i64, i64* %b, i64 1
-; CHECK-NEXT:    [[C_1:%.*]] = getelementptr i64, i64* %c, i64 1
-; CHECK-NEXT:    [[V0_0:%.*]] = load i64, i64* %a, align 8
+; CHECK-NEXT:    [[A_1:%.*]] = getelementptr i64, i64* [[A:%.*]], i64 1
+; CHECK-NEXT:    [[B_1:%.*]] = getelementptr i64, i64* [[B:%.*]], i64 1
+; CHECK-NEXT:    [[C_1:%.*]] = getelementptr i64, i64* [[C:%.*]], i64 1
+; CHECK-NEXT:    [[V0_0:%.*]] = load i64, i64* [[A]], align 8
 ; CHECK-NEXT:    [[V0_1:%.*]] = load i64, i64* [[A_1]], align 8
-; CHECK-NEXT:    [[V1_0:%.*]] = load i64, i64* %b, align 8
+; CHECK-NEXT:    [[V1_0:%.*]] = load i64, i64* [[B]], align 8
 ; CHECK-NEXT:    [[V1_1:%.*]] = load i64, i64* [[B_1]], align 8
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i64 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i64 [[V0_1]], [[V1_1]]
@@ -49,7 +50,7 @@
 ; CHECK-NEXT:    [[TMP1_1:%.*]] = sub i64 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP2_0:%.*]] = add i64 [[TMP0_0]], [[TMP0_1]]
 ; CHECK-NEXT:    [[TMP2_1:%.*]] = add i64 [[TMP1_0]], [[TMP1_1]]
-; CHECK-NEXT:    store i64 [[TMP2_0]], i64* %c, align 8
+; CHECK-NEXT:    store i64 [[TMP2_0]], i64* [[C]], align 8
 ; CHECK-NEXT:    store i64 [[TMP2_1]], i64* [[C_1]], align 8
 ; CHECK-NEXT:    ret void
 ;
@@ -76,14 +77,14 @@
 
 define <4 x i32> @build_vec_v4i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: @build_vec_v4i32(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <4 x i32> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <4 x i32> %v0, i32 1
-; CHECK-NEXT:    [[V0_2:%.*]] = extractelement <4 x i32> %v0, i32 2
-; CHECK-NEXT:    [[V0_3:%.*]] = extractelement <4 x i32> %v0, i32 3
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <4 x i32> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <4 x i32> %v1, i32 1
-; CHECK-NEXT:    [[V1_2:%.*]] = extractelement <4 x i32> %v1, i32 2
-; CHECK-NEXT:    [[V1_3:%.*]] = extractelement <4 x i32> %v1, i32 3
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <4 x i32> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <4 x i32> [[V0]], i32 1
+; CHECK-NEXT:    [[V0_2:%.*]] = extractelement <4 x i32> [[V0]], i32 2
+; CHECK-NEXT:    [[V0_3:%.*]] = extractelement <4 x i32> [[V0]], i32 3
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <4 x i32> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <4 x i32> [[V1]], i32 1
+; CHECK-NEXT:    [[V1_2:%.*]] = extractelement <4 x i32> [[V1]], i32 2
+; CHECK-NEXT:    [[V1_3:%.*]] = extractelement <4 x i32> [[V1]], i32 3
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP0_2:%.*]] = add i32 [[V0_2]], [[V1_2]]
@@ -131,10 +132,10 @@
 
 define <4 x i32> @build_vec_v4i32_reuse_0(<2 x i32> %v0, <2 x i32> %v1) {
 ; CHECK-LABEL: @build_vec_v4i32_reuse_0(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> %v0, i32 1
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> %v1, i32 1
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> [[V0]], i32 1
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> [[V1]], i32 1
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP1_0:%.*]] = sub i32 [[V0_0]], [[V1_0]]
@@ -166,10 +167,10 @@
 
 define <4 x i32> @build_vec_v4i32_reuse_1(<2 x i32> %v0, <2 x i32> %v1) {
 ; CHECK-LABEL: @build_vec_v4i32_reuse_1(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> %v0, i32 1
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> %v1, i32 1
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> [[V0]], i32 1
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> [[V1]], i32 1
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP0_2:%.*]] = xor i32 [[V0_0]], [[V1_0]]
@@ -208,25 +209,25 @@
 
 define <4 x i32> @build_vec_v4i32_3_binops(<2 x i32> %v0, <2 x i32> %v1) {
 ; CHECK-LABEL: @build_vec_v4i32_3_binops(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> %v0, i32 1
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> %v1, i32 1
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <2 x i32> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <2 x i32> [[V0]], i32 1
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <2 x i32> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <2 x i32> [[V1]], i32 1
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP1_0:%.*]] = mul i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP1_1:%.*]] = mul i32 [[V0_1]], [[V1_1]]
-; CHECK-NEXT:    [[TMP1:%.*]] = xor <2 x i32> %v0, %v1
+; CHECK-NEXT:    [[TMP1:%.*]] = xor <2 x i32> [[V0]], [[V1]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP3:%.*]] = xor <2 x i32> %v0, %v1
+; CHECK-NEXT:    [[TMP3:%.*]] = xor <2 x i32> [[V0]], [[V1]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> undef, <2 x i32> <i32 1, i32 1>
-; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <2 x i32> undef, i32 [[TMP0_0]], i32 0
-; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP1_0]], i32 1
-; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x i32> undef, i32 [[TMP0_1]], i32 0
-; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP1_1]], i32 1
-; CHECK-NEXT:    [[TMP9:%.*]] = add <2 x i32> [[TMP6]], [[TMP8]]
-; CHECK-NEXT:    [[TMP10:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[TMP3_3:%.*]] = shufflevector <2 x i32> [[TMP9]], <2 x i32> [[TMP10]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP2_0:%.*]] = add i32 [[TMP0_0]], [[TMP0_1]]
+; CHECK-NEXT:    [[TMP2_1:%.*]] = add i32 [[TMP1_0]], [[TMP1_1]]
+; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i32> [[TMP2]], [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; CHECK-NEXT:    [[TMP3_0:%.*]] = insertelement <4 x i32> undef, i32 [[TMP2_0]], i32 0
+; CHECK-NEXT:    [[TMP3_1:%.*]] = insertelement <4 x i32> [[TMP3_0]], i32 [[TMP2_1]], i32 1
+; CHECK-NEXT:    [[TMP3_3:%.*]] = shufflevector <4 x i32> [[TMP3_1]], <4 x i32> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
 ; CHECK-NEXT:    ret <4 x i32> [[TMP3_3]]
 ;
   %v0.0 = extractelement <2 x i32> %v0, i32 0
@@ -254,14 +255,14 @@
 
 define i32 @reduction_v4i32(<4 x i32> %v0, <4 x i32> %v1) {
 ; CHECK-LABEL: @reduction_v4i32(
-; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <4 x i32> %v0, i32 0
-; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <4 x i32> %v0, i32 1
-; CHECK-NEXT:    [[V0_2:%.*]] = extractelement <4 x i32> %v0, i32 2
-; CHECK-NEXT:    [[V0_3:%.*]] = extractelement <4 x i32> %v0, i32 3
-; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <4 x i32> %v1, i32 0
-; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <4 x i32> %v1, i32 1
-; CHECK-NEXT:    [[V1_2:%.*]] = extractelement <4 x i32> %v1, i32 2
-; CHECK-NEXT:    [[V1_3:%.*]] = extractelement <4 x i32> %v1, i32 3
+; CHECK-NEXT:    [[V0_0:%.*]] = extractelement <4 x i32> [[V0:%.*]], i32 0
+; CHECK-NEXT:    [[V0_1:%.*]] = extractelement <4 x i32> [[V0]], i32 1
+; CHECK-NEXT:    [[V0_2:%.*]] = extractelement <4 x i32> [[V0]], i32 2
+; CHECK-NEXT:    [[V0_3:%.*]] = extractelement <4 x i32> [[V0]], i32 3
+; CHECK-NEXT:    [[V1_0:%.*]] = extractelement <4 x i32> [[V1:%.*]], i32 0
+; CHECK-NEXT:    [[V1_1:%.*]] = extractelement <4 x i32> [[V1]], i32 1
+; CHECK-NEXT:    [[V1_2:%.*]] = extractelement <4 x i32> [[V1]], i32 2
+; CHECK-NEXT:    [[V1_3:%.*]] = extractelement <4 x i32> [[V1]], i32 3
 ; CHECK-NEXT:    [[TMP0_0:%.*]] = add i32 [[V0_0]], [[V1_0]]
 ; CHECK-NEXT:    [[TMP0_1:%.*]] = add i32 [[V0_1]], [[V1_1]]
 ; CHECK-NEXT:    [[TMP0_2:%.*]] = add i32 [[V0_2]], [[V1_2]]
Index: test/Transforms/SLPVectorizer/X86/pr35497.ll
===================================================================
--- test/Transforms/SLPVectorizer/X86/pr35497.ll
+++ test/Transforms/SLPVectorizer/X86/pr35497.ll
@@ -12,20 +12,20 @@
 define void @_ZN1C10SwitchModeEv() local_unnamed_addr #0 comdat align 2 {
 ; CHECK-LABEL: @_ZN1C10SwitchModeEv(
 ; CHECK-NEXT:  for.body.lr.ph.i:
-; CHECK-NEXT:    [[OR_1:%.*]] = or i64 undef, 1
-; CHECK-NEXT:    store i64 [[OR_1]], i64* undef, align 8
+; CHECK-NEXT:    [[BAR5:%.*]] = load i64, i64* undef, align 8
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x i64> undef, i64 [[BAR5]], i32 1
+; CHECK-NEXT:    [[TMP1:%.*]] = or <2 x i64> [[TMP0]], <i64 1, i64 0>
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x i64> [[TMP1]], i32 0
+; CHECK-NEXT:    store i64 [[TMP2]], i64* undef, align 8
 ; CHECK-NEXT:    [[FOO_1:%.*]] = getelementptr inbounds [[CLASS_1:%.*]], %class.1* undef, i64 0, i32 0, i32 0, i32 0, i32 0, i64 0
 ; CHECK-NEXT:    [[FOO_2:%.*]] = getelementptr inbounds [[CLASS_1]], %class.1* undef, i64 0, i32 0, i32 0, i32 0, i32 0, i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i64* [[FOO_1]] to <2 x i64>*
-; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x i64>, <2 x i64>* [[TMP0]], align 8
-; CHECK-NEXT:    [[BAR5:%.*]] = load i64, i64* undef, align 8
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i64> undef, i64 [[OR_1]], i32 0
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x i64> [[TMP2]], i64 [[BAR5]], i32 1
-; CHECK-NEXT:    [[TMP4:%.*]] = and <2 x i64> [[TMP3]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i64* [[FOO_1]] to <2 x i64>*
+; CHECK-NEXT:    [[TMP4:%.*]] = load <2 x i64>, <2 x i64>* [[TMP3]], align 8
+; CHECK-NEXT:    [[TMP5:%.*]] = and <2 x i64> [[TMP1]], [[TMP4]]
 ; CHECK-NEXT:    [[BAR3:%.*]] = getelementptr inbounds [[CLASS_2:%.*]], %class.2* undef, i64 0, i32 0, i32 0, i32 0, i64 0
 ; CHECK-NEXT:    [[BAR4:%.*]] = getelementptr inbounds [[CLASS_2]], %class.2* undef, i64 0, i32 0, i32 0, i32 0, i64 1
-; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i64* [[BAR3]] to <2 x i64>*
-; CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[TMP5]], align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i64* [[BAR3]] to <2 x i64>*
+; CHECK-NEXT:    store <2 x i64> [[TMP5]], <2 x i64>* [[TMP6]], align 8
 ; CHECK-NEXT:    ret void
 ;
 for.body.lr.ph.i:
@@ -50,27 +50,28 @@
 ; CHECK-LABEL: @pr35497(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = load i64, i64* undef, align 1
-; CHECK-NEXT:    [[ADD:%.*]] = add i64 undef, undef
-; CHECK-NEXT:    store i64 [[ADD]], i64* undef, align 1
-; CHECK-NEXT:    [[ARRAYIDX2_1:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 5
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i64> undef, i64 [[TMP0]], i32 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = shl <2 x i64> [[TMP1]], <i64 2, i64 2>
 ; CHECK-NEXT:    [[TMP3:%.*]] = and <2 x i64> <i64 20, i64 20>, [[TMP2]]
-; CHECK-NEXT:    [[ARRAYIDX2_2:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = add nuw nsw <2 x i64> [[TMP3]], zeroinitializer
-; CHECK-NEXT:    [[ARRAYIDX2_5:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 1
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i64> [[TMP4]], i32 1
 ; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <2 x i64> undef, i64 [[TMP5]], i32 0
-; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x i64> [[TMP6]], i64 [[ADD]], i32 1
-; CHECK-NEXT:    [[TMP8:%.*]] = shl <2 x i64> [[TMP7]], <i64 2, i64 2>
-; CHECK-NEXT:    [[TMP9:%.*]] = and <2 x i64> <i64 20, i64 20>, [[TMP8]]
+; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <2 x i64> [[TMP6]], i64 undef, i32 1
+; CHECK-NEXT:    [[TMP8:%.*]] = add <2 x i64> <i64 0, i64 undef>, [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <2 x i64> [[TMP8]], i32 1
+; CHECK-NEXT:    store i64 [[TMP9]], i64* undef, align 1
+; CHECK-NEXT:    [[ARRAYIDX2_1:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 5
+; CHECK-NEXT:    [[ARRAYIDX2_2:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 4
+; CHECK-NEXT:    [[ARRAYIDX2_5:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 1
+; CHECK-NEXT:    [[TMP10:%.*]] = shl <2 x i64> [[TMP8]], <i64 2, i64 2>
+; CHECK-NEXT:    [[TMP11:%.*]] = and <2 x i64> <i64 20, i64 20>, [[TMP10]]
 ; 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:    [[TMP12:%.*]] = bitcast i64* [[ARRAYIDX2_6]] to <2 x i64>*
+; CHECK-NEXT:    store <2 x i64> [[TMP4]], <2 x i64>* [[TMP12]], align 1
+; CHECK-NEXT:    [[TMP13:%.*]] = lshr <2 x i64> [[TMP4]], <i64 6, i64 6>
+; CHECK-NEXT:    [[TMP14:%.*]] = add nuw nsw <2 x i64> [[TMP11]], [[TMP13]]
+; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i64* [[ARRAYIDX2_2]] to <2 x i64>*
+; CHECK-NEXT:    store <2 x i64> [[TMP14]], <2 x i64>* [[TMP15]], align 1
 ; CHECK-NEXT:    ret void
 ;
 entry:
Index: test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll
===================================================================
--- test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll
+++ test/Transforms/SLPVectorizer/X86/vect_copyable_in_binops.ll
@@ -43,22 +43,16 @@
 ; CHECK-LABEL: @add1(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[TMP0]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[ADD3:%.*]] = add nsw i32 [[TMP1]], 1
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[ADD3]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[ADD6:%.*]] = add nsw i32 [[TMP2]], 2
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[ADD6]], i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[ADD9:%.*]] = add nsw i32 [[TMP3]], 3
-; CHECK-NEXT:    store i32 [[ADD9]], i32* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> <i32 0, i32 1, i32 2, i32 3>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -86,22 +80,16 @@
 ; CHECK-LABEL: @sub0(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[SUB5:%.*]] = add nsw i32 [[TMP2]], -2
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[SUB5]], i32* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SUB8:%.*]] = add nsw i32 [[TMP3]], -3
-; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> <i32 -1, i32 0, i32 -2, i32 -3>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -205,22 +193,18 @@
 ; CHECK-LABEL: @addsub0(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[SUB5:%.*]] = add nsw i32 [[TMP2]], -2
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[SUB5]], i32* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SUB8:%.*]] = sub nsw i32 [[TMP3]], -3
-; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> [[TMP1]], <i32 -1, i32 0, i32 -2, i32 -3>
+; CHECK-NEXT:    [[TMP3:%.*]] = sub nsw <4 x i32> [[TMP1]], <i32 -1, i32 0, i32 -2, i32 -3>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP4]], <4 x i32>* [[TMP5]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -248,22 +232,18 @@
 ; CHECK-LABEL: @addsub1(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = add nsw i32 [[TMP0]], -1
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[SUB]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[SUB1:%.*]] = sub nsw i32 [[TMP1]], -1
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[SUB1]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SUB8:%.*]] = sub nsw i32 [[TMP3]], -3
-; CHECK-NEXT:    store i32 [[SUB8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <4 x i32> [[TMP1]], <i32 -1, i32 -1, i32 0, i32 -3>
+; CHECK-NEXT:    [[TMP3:%.*]] = sub nsw <4 x i32> [[TMP1]], <i32 -1, i32 -1, i32 0, i32 -3>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP3]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP4]], <4 x i32>* [[TMP5]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -291,22 +271,16 @@
 ; CHECK-LABEL: @mul(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
-; CHECK-NEXT:    [[MUL:%.*]] = mul nsw i32 [[TMP0]], 257
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[MUL]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[MUL3:%.*]] = mul nsw i32 [[TMP1]], -3
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[MUL3]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[MUL9:%.*]] = mul nsw i32 [[TMP3]], -9
-; CHECK-NEXT:    store i32 [[MUL9]], i32* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = mul nsw <4 x i32> <i32 257, i32 -3, i32 1, i32 -9>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -334,22 +308,16 @@
 ; CHECK-LABEL: @shl0(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load i32, i32* [[SRC]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store i32 [[TMP0]], i32* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[SHL:%.*]] = shl i32 [[TMP1]], 1
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 2
-; CHECK-NEXT:    store i32 [[SHL]], i32* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[SHL5:%.*]] = shl i32 [[TMP2]], 2
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 3
-; CHECK-NEXT:    store i32 [[SHL5]], i32* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load i32, i32* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SHL8:%.*]] = shl i32 [[TMP3]], 3
-; CHECK-NEXT:    store i32 [[SHL8]], i32* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i32* [[SRC]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = shl <4 x i32> [[TMP1]], <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[DST]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -453,22 +421,16 @@
 ; CHECK-LABEL: @add1f(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[TMP0]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[ADD3:%.*]] = fadd fast float [[TMP1]], 1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[ADD3]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[ADD6:%.*]] = fadd fast float [[TMP2]], 2.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[ADD9:%.*]] = fadd fast float [[TMP3]], 3.000000e+00
-; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> <float 0.000000e+00, float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -496,22 +458,16 @@
 ; CHECK-LABEL: @sub0f(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
-; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[ADD]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[ADD6:%.*]] = fadd fast float [[TMP2]], -2.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[ADD9:%.*]] = fadd fast float [[TMP3]], -3.000000e+00
-; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> <float -1.000000e+00, float 0.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -615,22 +571,18 @@
 ; CHECK-LABEL: @addsub0f(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[SUB5:%.*]] = fadd fast float [[TMP2]], -2.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[SUB5]], float* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SUB8:%.*]] = fsub fast float [[TMP3]], -3.000000e+00
-; CHECK-NEXT:    store float [[SUB8]], float* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> [[TMP1]], <float -1.000000e+00, float 0.000000e+00, float -2.000000e+00, float -3.000000e+00>
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast <4 x float> [[TMP1]], <float -1.000000e+00, float 0.000000e+00, float -2.000000e+00, float -3.000000e+00>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> [[TMP3]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP4]], <4 x float>* [[TMP5]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -658,22 +610,18 @@
 ; CHECK-LABEL: @addsub1f(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[SUB1:%.*]] = fsub fast float [[TMP1]], -1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR3:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[SUB1]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR6:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[TMP2]], float* [[INCDEC_PTR3]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[SUB8:%.*]] = fsub fast float [[TMP3]], -3.000000e+00
-; CHECK-NEXT:    store float [[SUB8]], float* [[INCDEC_PTR6]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast <4 x float> [[TMP1]], <float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -3.000000e+00>
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast <4 x float> [[TMP1]], <float -1.000000e+00, float -1.000000e+00, float 0.000000e+00, float -3.000000e+00>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> [[TMP3]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP4]], <4 x float>* [[TMP5]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -701,22 +649,16 @@
 ; CHECK-LABEL: @mulf(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
-; CHECK-NEXT:    [[SUB:%.*]] = fmul fast float [[TMP0]], 2.570000e+02
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[SUB]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
-; CHECK-NEXT:    [[SUB3:%.*]] = fmul fast float [[TMP1]], -3.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[SUB3]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[TMP2]], float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[SUB9:%.*]] = fmul fast float [[TMP3]], -9.000000e+00
-; CHECK-NEXT:    store float [[SUB9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul fast <4 x float> <float 2.570000e+02, float -3.000000e+00, float 1.000000e+00, float -9.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -825,22 +767,16 @@
 ; CHECK-LABEL: @sub0fn(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INCDEC_PTR:%.*]] = getelementptr inbounds float, float* [[SRC:%.*]], i64 1
-; CHECK-NEXT:    [[TMP0:%.*]] = load float, float* [[SRC]], align 4
-; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP0]], -1.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR1:%.*]] = getelementptr inbounds float, float* [[DST:%.*]], i64 1
-; CHECK-NEXT:    store float [[ADD]], float* [[DST]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR2:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 2
-; CHECK-NEXT:    [[TMP1:%.*]] = load float, float* [[INCDEC_PTR]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR4:%.*]] = getelementptr inbounds float, float* [[DST]], i64 2
-; CHECK-NEXT:    store float [[TMP1]], float* [[INCDEC_PTR1]], align 4
 ; CHECK-NEXT:    [[INCDEC_PTR5:%.*]] = getelementptr inbounds float, float* [[SRC]], i64 3
-; CHECK-NEXT:    [[TMP2:%.*]] = load float, float* [[INCDEC_PTR2]], align 4
-; CHECK-NEXT:    [[ADD6:%.*]] = fadd float [[TMP2]], -2.000000e+00
 ; CHECK-NEXT:    [[INCDEC_PTR7:%.*]] = getelementptr inbounds float, float* [[DST]], i64 3
-; CHECK-NEXT:    store float [[ADD6]], float* [[INCDEC_PTR4]], align 4
-; CHECK-NEXT:    [[TMP3:%.*]] = load float, float* [[INCDEC_PTR5]], align 4
-; CHECK-NEXT:    [[ADD9:%.*]] = fadd float [[TMP3]], -3.000000e+00
-; CHECK-NEXT:    store float [[ADD9]], float* [[INCDEC_PTR7]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast float* [[SRC]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd <4 x float> <float -1.000000e+00, float 0.000000e+00, float -2.000000e+00, float -3.000000e+00>, [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = bitcast float* [[DST]] to <4 x float>*
+; CHECK-NEXT:    store <4 x float> [[TMP2]], <4 x float>* [[TMP3]], align 4
 ; CHECK-NEXT:    ret void
 ;
 entry: