[SLPVectorizer] Provide InstructionsState down the BoUpSLP vectorization call tree.

[RKSimon]

Summary

As described in D48359, this patch pushes InstructionsState down the BoUpSLP call hierarchy instead of the corresponding raw OpValue. This makes it easier to track the alternate opcode etc. and avoids us having to call getAltOpcode which makes it difficult to support more than one alternate opcode.

[ABataev]

LG

lib/Transforms/Vectorize/SLPVectorizer.cpp

InstructionsState(Value *OpValue, unsigned Opcode, unsigned AltOpcode)
       : OpValue(OpValue), Opcode(Opcode), AltOpcode(AltOpcode) {}
 };
 
 } // end anonymous namespace
 
 /// 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.
-static Value *isOneOf(Value *OpValue, Value *Op) {
+static Value *isOneOf(const InstructionsState &S, Value *Op) {
   auto *I = dyn_cast<Instruction>(Op);
-  if (!I)
-    return OpValue;
-  auto *OpInst = cast<Instruction>(OpValue);
-  unsigned OpInstOpcode = OpInst->getOpcode();
-  unsigned IOpcode = I->getOpcode();
-  if (sameOpcodeOrAlt(OpInstOpcode, getAltOpcode(OpInstOpcode), IOpcode))
+  if (I && sameOpcodeOrAlt(S.Opcode, S.AltOpcode, I->getOpcode()))
     return Op;
-  return OpValue;
+  return S.OpValue;
 }
 
 /// \returns analysis of the Instructions in \p VL described in
 /// InstructionsState, the Opcode that we suppose the whole list 
 /// could be vectorized even if its structure is diverse.
-static InstructionsState getSameOpcode(ArrayRef<Value *> VL) {
+static InstructionsState getSameOpcode(ArrayRef<Value *> VL,
+                                       unsigned BaseIndex = 0) {
   // Make sure these are all Instructions.
   if (llvm::any_of(VL, [](Value *V) { return !isa<Instruction>(V); }))
-    return InstructionsState(VL[0], 0, 0);
+    return InstructionsState(VL[BaseIndex], 0, 0);
 
-  unsigned Opcode = cast<Instruction>(VL[0])->getOpcode();
+  unsigned Opcode = cast<Instruction>(VL[BaseIndex])->getOpcode();
   unsigned AltOpcode = Opcode;
   bool HasAltOpcodes = llvm::any_of(VL, [Opcode](Value *V) {
     return Opcode != cast<Instruction>(V)->getOpcode();
   });
 
   // Check for an alternate opcode pattern.
   if (HasAltOpcodes) {
     AltOpcode = getAltOpcode(Opcode);
     for (int Cnt = 0, E = VL.size(); Cnt < E; Cnt++) {
       unsigned InstOpcode = cast<Instruction>(VL[Cnt])->getOpcode();
       if (!sameOpcodeOrAlt(Opcode, AltOpcode, InstOpcode))
-        return InstructionsState(VL[0], 0, 0);
+        return InstructionsState(VL[BaseIndex], 0, 0);
     }
   }
 
-  return InstructionsState(VL[0], Opcode, AltOpcode);
+  return InstructionsState(VL[BaseIndex], Opcode, AltOpcode);
 }
 
 /// \returns true if all of the values in \p VL have the same type or false
 /// otherwise.
 static bool allSameType(ArrayRef<Value *> VL) {
   Type *Ty = VL[0]->getType();
   for (int i = 1, e = VL.size(); i < e; i++)
     if (VL[i]->getType() != Ty)
private:
 
   /// \returns the scalarization cost for this list of values. Assuming that
   /// this subtree gets vectorized, we may need to extract the values from the
   /// roots. This method calculates the cost of extracting the values.
   int getGatherCost(ArrayRef<Value *> VL);
 
   /// Set the Builder insert point to one after the last instruction in
   /// the bundle
-  void setInsertPointAfterBundle(ArrayRef<Value *> VL, Value *OpValue);
+  void setInsertPointAfterBundle(ArrayRef<Value *> VL,
+                                 const InstructionsState &S);
 
   /// \returns a vector from a collection of scalars in \p VL.
   Value *Gather(ArrayRef<Value *> VL, VectorType *Ty);
 
   /// \returns whether the VectorizableTree is fully vectorizable and will
   /// be beneficial even the tree height is tiny.
   bool isFullyVectorizableTinyTree();
 
void initialFillReadyList(ReadyListType &ReadyList) {
           }
         });
       }
     }
 
     /// 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);
 
     /// Allocates schedule data chunk.
     ScheduleData *allocateScheduleDataChunks();
 
     /// Extends the scheduling region so that V is inside the region.
     /// \returns true if the region size is within the limit.
-    bool extendSchedulingRegion(Value *V, Value *OpValue);
+    bool extendSchedulingRegion(Value *V, const InstructionsState &S);
 
     /// Initialize the ScheduleData structures for new instructions in the
     /// scheduling region.
     void initScheduleData(Instruction *FromI, Instruction *ToI,
                           ScheduleData *PrevLoadStore,
                           ScheduleData *NextLoadStore);
 
     /// Updates the dependency information of a bundle and of all instructions/
void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
   }
 
   auto &BSRef = BlocksSchedules[BB];
   if (!BSRef)
     BSRef = llvm::make_unique<BlockScheduling>(BB);
 
   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);
     return;
   }
   LLVM_DEBUG(dbgs() << "SLP: We are able to schedule this bundle.\n");
if (LoadInst *L = dyn_cast<LoadInst>(Right[j])) {
           continue;
         }
       }
     }
     // else unchanged
   }
 }
 
-void BoUpSLP::setInsertPointAfterBundle(ArrayRef<Value *> VL, Value *OpValue) {
+void BoUpSLP::setInsertPointAfterBundle(ArrayRef<Value *> VL,
+                                        const InstructionsState &S) {
   // Get the basic block this bundle is in. All instructions in the bundle
   // should be in this block.
-  auto *Front = cast<Instruction>(OpValue);
+  auto *Front = cast<Instruction>(S.OpValue);
   auto *BB = Front->getParent();
-  const unsigned Opcode = cast<Instruction>(OpValue)->getOpcode();
-  const unsigned AltOpcode = getAltOpcode(Opcode);
+  const unsigned Opcode = S.Opcode;
+  const unsigned AltOpcode = S.AltOpcode;
   assert(llvm::all_of(make_range(VL.begin(), VL.end()), [=](Value *V) -> bool {
     return !sameOpcodeOrAlt(Opcode, AltOpcode,
                             cast<Instruction>(V)->getOpcode()) ||
            cast<Instruction>(V)->getParent() == BB;
   }));
 
   // The last instruction in the bundle in program order.
   Instruction *LastInst = nullptr;
 
   // Find the last instruction. The common case should be that BB has been
   // scheduled, and the last instruction is VL.back(). So we start with
   // 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 =
-        BlocksSchedules[BB]->getScheduleData(isOneOf(OpValue, VL.back()));
+        BlocksSchedules[BB]->getScheduleData(isOneOf(S, VL.back()));
     if (Bundle && Bundle->isPartOfBundle())
       for (; Bundle; Bundle = Bundle->NextInBundle)
         if (Bundle->OpValue == Bundle->Inst)
           LastInst = Bundle->Inst;
   }
 
   // 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
Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
   IRBuilder<>::InsertPointGuard Guard(Builder);
 
   if (E->VectorizedValue) {
     LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n");
     return E->VectorizedValue;
   }
 
   InstructionsState S = getSameOpcode(E->Scalars);
-  Instruction *VL0 = cast<Instruction>(E->Scalars[0]);
+  Instruction *VL0 = cast<Instruction>(S.OpValue);
   Type *ScalarTy = VL0->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL0))
     ScalarTy = SI->getValueOperand()->getType();
   VectorType *VecTy = VectorType::get(ScalarTy, E->Scalars.size());
 
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
 
   if (E->NeedToGather) {
-    setInsertPointAfterBundle(E->Scalars, VL0);
+    setInsertPointAfterBundle(E->Scalars, S);
     auto *V = Gather(E->Scalars, VecTy);
     if (NeedToShuffleReuses) {
       V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                       E->ReuseShuffleIndices, "shuffle");
       if (auto *I = dyn_cast<Instruction>(V)) {
         GatherSeq.insert(I);
         CSEBlocks.insert(I->getParent());
       }
case Instruction::ExtractElement: {
           if (!E->ReorderIndices.empty())
             Builder.SetInsertPoint(VL0);
           V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                           E->ReuseShuffleIndices, "shuffle");
         }
         E->VectorizedValue = V;
         return V;
       }
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
       auto *V = Gather(E->Scalars, VecTy);
       if (NeedToShuffleReuses) {
         V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                         E->ReuseShuffleIndices, "shuffle");
         if (auto *I = dyn_cast<Instruction>(V)) {
           GatherSeq.insert(I);
           CSEBlocks.insert(I->getParent());
         }
case Instruction::ExtractValue: {
         if (NeedToShuffleReuses) {
           // TODO: Merge this shuffle with the ReorderShuffleMask.
           NewV = Builder.CreateShuffleVector(
               NewV, UndefValue::get(VecTy), E->ReuseShuffleIndices, "shuffle");
         }
         E->VectorizedValue = NewV;
         return NewV;
       }
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
       auto *V = Gather(E->Scalars, VecTy);
       if (NeedToShuffleReuses) {
         V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                         E->ReuseShuffleIndices, "shuffle");
         if (auto *I = dyn_cast<Instruction>(V)) {
           GatherSeq.insert(I);
           CSEBlocks.insert(I->getParent());
         }
switch (ShuffleOrOp) {
     case Instruction::UIToFP:
     case Instruction::Trunc:
     case Instruction::FPTrunc:
     case Instruction::BitCast: {
       ValueList INVL;
       for (Value *V : E->Scalars)
         INVL.push_back(cast<Instruction>(V)->getOperand(0));
 
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *InVec = vectorizeTree(INVL);
 
       if (E->VectorizedValue) {
         LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
         return E->VectorizedValue;
       }
 
switch (ShuffleOrOp) {
     case Instruction::FCmp:
     case Instruction::ICmp: {
       ValueList LHSV, RHSV;
       for (Value *V : E->Scalars) {
         LHSV.push_back(cast<Instruction>(V)->getOperand(0));
         RHSV.push_back(cast<Instruction>(V)->getOperand(1));
       }
 
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *L = vectorizeTree(LHSV);
       Value *R = vectorizeTree(RHSV);
 
       if (E->VectorizedValue) {
         LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
         return E->VectorizedValue;
       }
switch (ShuffleOrOp) {
     case Instruction::Select: {
       ValueList TrueVec, FalseVec, CondVec;
       for (Value *V : E->Scalars) {
         CondVec.push_back(cast<Instruction>(V)->getOperand(0));
         TrueVec.push_back(cast<Instruction>(V)->getOperand(1));
         FalseVec.push_back(cast<Instruction>(V)->getOperand(2));
       }
 
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *Cond = vectorizeTree(CondVec);
       Value *True = vectorizeTree(TrueVec);
       Value *False = vectorizeTree(FalseVec);
 
       if (E->VectorizedValue) {
         LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
         return E->VectorizedValue;
case Instruction::Xor: {
                                        RHSVL);
       else
         for (Value *V : E->Scalars) {
           auto *I = cast<Instruction>(V);
           LHSVL.push_back(I->getOperand(0));
           RHSVL.push_back(I->getOperand(1));
         }
 
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *LHS = vectorizeTree(LHSVL);
       Value *RHS = vectorizeTree(RHSVL);
 
       if (E->VectorizedValue) {
         LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
         return E->VectorizedValue;
       }
case Instruction::Xor: {
       ++NumVectorInstructions;
 
       return V;
     }
     case Instruction::Load: {
       // Loads are inserted at the head of the tree because we don't want to
       // sink them all the way down past store instructions.
       bool IsReorder = !E->ReorderIndices.empty();
-      if (IsReorder)
-        VL0 = cast<Instruction>(E->Scalars[E->ReorderIndices.front()]);
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      if (IsReorder) {
+        S = getSameOpcode(E->Scalars, E->ReorderIndices.front());
+        VL0 = cast<Instruction>(S.OpValue);
+      }
+      setInsertPointAfterBundle(E->Scalars, S);
 
       LoadInst *LI = cast<LoadInst>(VL0);
       Type *ScalarLoadTy = LI->getType();
       unsigned AS = LI->getPointerAddressSpace();
 
       Value *VecPtr = Builder.CreateBitCast(LI->getPointerOperand(),
                                             VecTy->getPointerTo(AS));
 
case Instruction::Store: {
       StoreInst *SI = cast<StoreInst>(VL0);
       unsigned Alignment = SI->getAlignment();
       unsigned AS = SI->getPointerAddressSpace();
 
       ValueList ScalarStoreValues;
       for (Value *V : E->Scalars)
         ScalarStoreValues.push_back(cast<StoreInst>(V)->getValueOperand());
 
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *VecValue = vectorizeTree(ScalarStoreValues);
       Value *ScalarPtr = SI->getPointerOperand();
       Value *VecPtr = Builder.CreateBitCast(ScalarPtr, VecTy->getPointerTo(AS));
-      StoreInst *S = Builder.CreateStore(VecValue, VecPtr);
+      StoreInst *ST = Builder.CreateStore(VecValue, VecPtr);
 
       // The pointer operand uses an in-tree scalar, so add the new BitCast to
       // ExternalUses to make sure that an extract will be generated in the
       // future.
       if (getTreeEntry(ScalarPtr))
         ExternalUses.push_back(ExternalUser(ScalarPtr, cast<User>(VecPtr), 0));
 
       if (!Alignment)
         Alignment = DL->getABITypeAlignment(SI->getValueOperand()->getType());
 
-      S->setAlignment(Alignment);
-      Value *V = propagateMetadata(S, E->Scalars);
+      ST->setAlignment(Alignment);
+      Value *V = propagateMetadata(ST, E->Scalars);
       if (NeedToShuffleReuses) {
         V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                         E->ReuseShuffleIndices, "shuffle");
       }
       E->VectorizedValue = V;
       ++NumVectorInstructions;
       return V;
     }
     case Instruction::GetElementPtr: {
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       ValueList Op0VL;
       for (Value *V : E->Scalars)
         Op0VL.push_back(cast<GetElementPtrInst>(V)->getOperand(0));
 
       Value *Op0 = vectorizeTree(Op0VL);
 
       std::vector<Value *> OpVecs;
case Instruction::GetElementPtr: {
       }
       E->VectorizedValue = V;
       ++NumVectorInstructions;
 
       return V;
     }
     case Instruction::Call: {
       CallInst *CI = cast<CallInst>(VL0);
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
       Function *FI;
       Intrinsic::ID IID  = Intrinsic::not_intrinsic;
       Value *ScalarArg = nullptr;
       if (CI && (FI = CI->getCalledFunction())) {
         IID = FI->getIntrinsicID();
       }
       std::vector<Value *> OpVecs;
       for (int j = 0, e = CI->getNumArgOperands(); j < e; ++j) {
case Instruction::Call: {
       return V;
     }
     case Instruction::ShuffleVector: {
       ValueList LHSVL, RHSVL;
       assert(Instruction::isBinaryOp(S.Opcode) &&
              "Invalid Shuffle Vector Operand");
       reorderAltShuffleOperands(S.Opcode, S.AltOpcode, E->Scalars, LHSVL,
                                 RHSVL);
-      setInsertPointAfterBundle(E->Scalars, VL0);
+      setInsertPointAfterBundle(E->Scalars, S);
 
       Value *LHS = vectorizeTree(LHSVL);
       Value *RHS = vectorizeTree(RHSVL);
 
       if (E->VectorizedValue) {
         LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
         return E->VectorizedValue;
       }
void BoUpSLP::optimizeGatherSequence() {
   }
   CSEBlocks.clear();
   GatherSeq.clear();
 }
 
 // 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.
   Instruction *OldScheduleEnd = ScheduleEnd;
   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))
       return false;
   }
 
   for (Value *V : VL) {
     ScheduleData *BundleMember = getScheduleData(V);
     assert(BundleMember &&
            "no ScheduleData for bundle member (maybe not in same basic block)");
     if (BundleMember->IsScheduled) {
while (!Bundle->isReady() && !ReadyInsts.empty()) {
     ScheduleData *pickedSD = ReadyInsts.back();
     ReadyInsts.pop_back();
 
     if (pickedSD->isSchedulingEntity() && pickedSD->isReady()) {
       schedule(pickedSD, ReadyInsts);
     }
   }
   if (!Bundle->isReady()) {
-    cancelScheduling(VL, OpValue);
+    cancelScheduling(VL, S.OpValue);
     return false;
   }
   return true;
 }
 
 void BoUpSLP::BlockScheduling::cancelScheduling(ArrayRef<Value *> VL,
                                                 Value *OpValue) {
   if (isa<PHINode>(OpValue))
BoUpSLP::ScheduleData *BoUpSLP::BlockScheduling::allocateScheduleDataChunks() {
   if (ChunkPos >= ChunkSize) {
     ScheduleDataChunks.push_back(llvm::make_unique<ScheduleData[]>(ChunkSize));
     ChunkPos = 0;
   }
   return &(ScheduleDataChunks.back()[ChunkPos++]);
 }
 
 bool BoUpSLP::BlockScheduling::extendSchedulingRegion(Value *V,
-                                                      Value *OpValue) {
-  if (getScheduleData(V, isOneOf(OpValue, V)))
+                                                      const InstructionsState &S) {
+  if (getScheduleData(V, isOneOf(S, V)))
     return true;
   Instruction *I = dyn_cast<Instruction>(V);
   assert(I && "bundle member must be an instruction");
   assert(!isa<PHINode>(I) && "phi nodes don't need to be scheduled");
-  auto &&CheckSheduleForI = [this, OpValue](Instruction *I) -> bool {
+  auto &&CheckSheduleForI = [this, &S](Instruction *I) -> bool {
     ScheduleData *ISD = getScheduleData(I);
     if (!ISD)
       return false;
     assert(isInSchedulingRegion(ISD) &&
            "ScheduleData not in scheduling region");
     ScheduleData *SD = allocateScheduleDataChunks();
     SD->Inst = I;
-    SD->init(SchedulingRegionID, OpValue);
-    ExtraScheduleDataMap[I][OpValue] = SD;
+    SD->init(SchedulingRegionID, S.OpValue);
+    ExtraScheduleDataMap[I][S.OpValue] = SD;
     return true;
   };
   if (CheckSheduleForI(I))
     return true;
   if (!ScheduleStart) {
     // It's the first instruction in the new region.
     initScheduleData(I, I->getNextNode(), nullptr, nullptr);
     ScheduleStart = I;
     ScheduleEnd = I->getNextNode();
-    if (isOneOf(OpValue, I) != I)
+    if (isOneOf(S, I) != I)
       CheckSheduleForI(I);
     assert(ScheduleEnd && "tried to vectorize a TerminatorInst?");
     LLVM_DEBUG(dbgs() << "SLP:  initialize schedule region to " << *I << "\n");
     return true;
   }
   // Search up and down at the same time, because we don't know if the new
   // instruction is above or below the existing scheduling region.
   BasicBlock::reverse_iterator UpIter =
       ++ScheduleStart->getIterator().getReverse();
   BasicBlock::reverse_iterator UpperEnd = BB->rend();
   BasicBlock::iterator DownIter = ScheduleEnd->getIterator();
   BasicBlock::iterator LowerEnd = BB->end();
   while (true) {
     if (++ScheduleRegionSize > ScheduleRegionSizeLimit) {
       LLVM_DEBUG(dbgs() << "SLP:  exceeded schedule region size limit\n");
       return false;
     }
 
     if (UpIter != UpperEnd) {
       if (&*UpIter == I) {
         initScheduleData(I, ScheduleStart, nullptr, FirstLoadStoreInRegion);
         ScheduleStart = I;
-        if (isOneOf(OpValue, I) != I)
+        if (isOneOf(S, I) != I)
           CheckSheduleForI(I);
         LLVM_DEBUG(dbgs() << "SLP:  extend schedule region start to " << *I
                           << "\n");
         return true;
       }
       UpIter++;
     }
     if (DownIter != LowerEnd) {
       if (&*DownIter == I) {
         initScheduleData(ScheduleEnd, I->getNextNode(), LastLoadStoreInRegion,
                          nullptr);
         ScheduleEnd = I->getNextNode();
-        if (isOneOf(OpValue, I) != I)
+        if (isOneOf(S, I) != I)
           CheckSheduleForI(I);
         assert(ScheduleEnd && "tried to vectorize a TerminatorInst?");
         LLVM_DEBUG(dbgs() << "SLP:  extend schedule region end to " << *I
                           << "\n");
         return true;
       }
       DownIter++;
     }