[SVE] Eliminate calls to default-false VectorType::get() from Vectorize

[ctetreau]

rebase

[ctetreau]

rebase

llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp

bool Vectorizer::vectorizeStoreChain(
   // Check if it's legal to vectorize this chain. If not, split the chain and
   // try again.
   unsigned EltSzInBytes = Sz / 8;
   unsigned SzInBytes = EltSzInBytes * ChainSize;
 
   VectorType *VecTy;
   VectorType *VecStoreTy = dyn_cast<VectorType>(StoreTy);
   if (VecStoreTy)
-    VecTy = VectorType::get(StoreTy->getScalarType(),
+    VecTy = FixedVectorType::get(StoreTy->getScalarType(),
                                  Chain.size() * VecStoreTy->getNumElements());
   else
-    VecTy = VectorType::get(StoreTy, Chain.size());
+    VecTy = FixedVectorType::get(StoreTy, Chain.size());
 
   // If it's more than the max vector size or the target has a better
   // vector factor, break it into two pieces.
   unsigned TargetVF = TTI.getStoreVectorFactor(VF, Sz, SzInBytes, VecTy);
   if (ChainSize > VF || (VF != TargetVF && TargetVF < ChainSize)) {
     LLVM_DEBUG(dbgs() << "LSV: Chain doesn't match with the vector factor."
                          " Creating two separate arrays.\n");
     return vectorizeStoreChain(Chain.slice(0, TargetVF),
bool Vectorizer::vectorizeLoadChain(
 
   // Check if it's legal to vectorize this chain. If not, split the chain and
   // try again.
   unsigned EltSzInBytes = Sz / 8;
   unsigned SzInBytes = EltSzInBytes * ChainSize;
   VectorType *VecTy;
   VectorType *VecLoadTy = dyn_cast<VectorType>(LoadTy);
   if (VecLoadTy)
-    VecTy = VectorType::get(LoadTy->getScalarType(),
+    VecTy = FixedVectorType::get(LoadTy->getScalarType(),
                                  Chain.size() * VecLoadTy->getNumElements());
   else
-    VecTy = VectorType::get(LoadTy, Chain.size());
+    VecTy = FixedVectorType::get(LoadTy, Chain.size());
 
   // If it's more than the max vector size or the target has a better
   // vector factor, break it into two pieces.
   unsigned TargetVF = TTI.getLoadVectorFactor(VF, Sz, SzInBytes, VecTy);
   if (ChainSize > VF || (VF != TargetVF && TargetVF < ChainSize)) {
     LLVM_DEBUG(dbgs() << "LSV: Chain doesn't match with the vector factor."
                          " Creating two separate arrays.\n");
     return vectorizeLoadChain(Chain.slice(0, TargetVF), InstructionsProcessed) |

llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp

for (Instruction &I : *BB) {
                                      "CantVectorizeStore", ORE, TheLoop, ST);
           return false;
         }
 
         // For nontemporal stores, check that a nontemporal vector version is
         // supported on the target.
         if (ST->getMetadata(LLVMContext::MD_nontemporal)) {
           // Arbitrarily try a vector of 2 elements.
-          Type *VecTy = VectorType::get(T, /*NumElements=*/2);
+          auto *VecTy = FixedVectorType::get(T, /*NumElements=*/2);
           assert(VecTy && "did not find vectorized version of stored type");
           if (!TTI->isLegalNTStore(VecTy, ST->getAlign())) {
             reportVectorizationFailure(
                 "nontemporal store instruction cannot be vectorized",
                 "nontemporal store instruction cannot be vectorized",
                 "CantVectorizeNontemporalStore", ORE, TheLoop, ST);
             return false;
           }
         }
 
       } else if (auto *LD = dyn_cast<LoadInst>(&I)) {
         if (LD->getMetadata(LLVMContext::MD_nontemporal)) {
           // For nontemporal loads, check that a nontemporal vector version is
           // supported on the target (arbitrarily try a vector of 2 elements).
-          Type *VecTy = VectorType::get(I.getType(), /*NumElements=*/2);
+          auto *VecTy = FixedVectorType::get(I.getType(), /*NumElements=*/2);
           assert(VecTy && "did not find vectorized version of load type");
           if (!TTI->isLegalNTLoad(VecTy, LD->getAlign())) {
             reportVectorizationFailure(
                 "nontemporal load instruction cannot be vectorized",
                 "nontemporal load instruction cannot be vectorized",
                 "CantVectorizeNontemporalLoad", ORE, TheLoop, LD);
             return false;
           }

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

 
 /// A helper function that returns true if the given type is irregular. The
 /// type is irregular if its allocated size doesn't equal the store size of an
 /// element of the corresponding vector type at the given vectorization factor.
 static bool hasIrregularType(Type *Ty, const DataLayout &DL, unsigned VF) {
   // Determine if an array of VF elements of type Ty is "bitcast compatible"
   // with a <VF x Ty> vector.
   if (VF > 1) {
-    auto *VectorTy = VectorType::get(Ty, VF);
+    auto *VectorTy = FixedVectorType::get(Ty, VF);
     return VF * DL.getTypeAllocSize(Ty) != DL.getTypeStoreSize(VectorTy);
   }
 
   // If the vectorization factor is one, we just check if an array of type Ty
   // requires padding between elements.
   return DL.getTypeAllocSizeInBits(Ty) != DL.getTypeSizeInBits(Ty);
 }
 
if (VectorLoopValueMap.hasAnyScalarValue(V)) {
     // instructions. Since the resulting vectors are stored in
     // VectorLoopValueMap, we will only generate the insertelements once.
     Value *VectorValue = nullptr;
     if (Cost->isUniformAfterVectorization(I, VF)) {
       VectorValue = getBroadcastInstrs(ScalarValue);
       VectorLoopValueMap.setVectorValue(V, Part, VectorValue);
     } else {
       // Initialize packing with insertelements to start from undef.
-      Value *Undef = UndefValue::get(VectorType::get(V->getType(), VF));
+      Value *Undef = UndefValue::get(FixedVectorType::get(V->getType(), VF));
       VectorLoopValueMap.setVectorValue(V, Part, Undef);
       for (unsigned Lane = 0; Lane < VF; ++Lane)
         packScalarIntoVectorValue(V, {Part, Lane});
       VectorValue = VectorLoopValueMap.getVectorValue(V, Part);
     }
     Builder.restoreIP(OldIP);
     return VectorValue;
   }
void InnerLoopVectorizer::vectorizeInterleaveGroup(
     const InterleaveGroup<Instruction> *Group, VPTransformState &State,
     VPValue *Addr, VPValue *BlockInMask) {
   Instruction *Instr = Group->getInsertPos();
   const DataLayout &DL = Instr->getModule()->getDataLayout();
 
   // Prepare for the vector type of the interleaved load/store.
   Type *ScalarTy = getMemInstValueType(Instr);
   unsigned InterleaveFactor = Group->getFactor();
-  Type *VecTy = VectorType::get(ScalarTy, InterleaveFactor * VF);
+  auto *VecTy = FixedVectorType::get(ScalarTy, InterleaveFactor * VF);
 
   // Prepare for the new pointers.
   SmallVector<Value *, 2> AddrParts;
   unsigned Index = Group->getIndex(Instr);
 
   // TODO: extend the masked interleaved-group support to reversed access.
   assert((!BlockInMask || !Group->isReverse()) &&
          "Reversed masked interleave-group not supported.");
for (unsigned I = 0; I < InterleaveFactor; ++I) {
 
       auto StrideMask = createStrideMask(I, InterleaveFactor, VF);
       for (unsigned Part = 0; Part < UF; Part++) {
         Value *StridedVec = Builder.CreateShuffleVector(
             NewLoads[Part], UndefVec, StrideMask, "strided.vec");
 
         // If this member has different type, cast the result type.
         if (Member->getType() != ScalarTy) {
-          VectorType *OtherVTy = VectorType::get(Member->getType(), VF);
+          VectorType *OtherVTy = FixedVectorType::get(Member->getType(), VF);
           StridedVec = createBitOrPointerCast(StridedVec, OtherVTy, DL);
         }
 
         if (Group->isReverse())
           StridedVec = reverseVector(StridedVec);
 
         VectorLoopValueMap.setVectorValue(Member, Part, StridedVec);
       }
     }
     return;
   }
 
   // The sub vector type for current instruction.
-  VectorType *SubVT = VectorType::get(ScalarTy, VF);
+  auto *SubVT = FixedVectorType::get(ScalarTy, VF);
 
   // Vectorize the interleaved store group.
   for (unsigned Part = 0; Part < UF; Part++) {
     // Collect the stored vector from each member.
     SmallVector<Value *, 4> StoredVecs;
     for (unsigned i = 0; i < InterleaveFactor; i++) {
       // Interleaved store group doesn't allow a gap, so each index has a member
       Instruction *Member = Group->getMember(i);
void InnerLoopVectorizer::vectorizeMemoryInstruction(Instruction *Instr,
   LoopVectorizationCostModel::InstWidening Decision =
       Cost->getWideningDecision(Instr, VF);
   assert((Decision == LoopVectorizationCostModel::CM_Widen ||
           Decision == LoopVectorizationCostModel::CM_Widen_Reverse ||
           Decision == LoopVectorizationCostModel::CM_GatherScatter) &&
          "CM decision is not to widen the memory instruction");
 
   Type *ScalarDataTy = getMemInstValueType(Instr);
-  Type *DataTy = VectorType::get(ScalarDataTy, VF);
+  auto *DataTy = FixedVectorType::get(ScalarDataTy, VF);
   const Align Alignment = getLoadStoreAlignment(Instr);
 
   // Determine if the pointer operand of the access is either consecutive or
   // reverse consecutive.
   bool Reverse = (Decision == LoopVectorizationCostModel::CM_Widen_Reverse);
   bool ConsecutiveStride =
       Reverse || (Decision == LoopVectorizationCostModel::CM_Widen);
   bool CreateGatherScatter =
Value *InnerLoopVectorizer::createBitOrPointerCast(Value *V, VectorType *DstVTy,
   // pointers or vice-versa. Handle this using a two-step bitcast using an
   // intermediate Integer type for the bitcast i.e. Ptr <-> Int <-> Float.
   assert((DstElemTy->isPointerTy() != SrcElemTy->isPointerTy()) &&
          "Only one type should be a pointer type");
   assert((DstElemTy->isFloatingPointTy() != SrcElemTy->isFloatingPointTy()) &&
          "Only one type should be a floating point type");
   Type *IntTy =
       IntegerType::getIntNTy(V->getContext(), DL.getTypeSizeInBits(SrcElemTy));
-  VectorType *VecIntTy = VectorType::get(IntTy, VF);
+  auto *VecIntTy = FixedVectorType::get(IntTy, VF);
   Value *CastVal = Builder.CreateBitOrPointerCast(V, VecIntTy);
   return Builder.CreateBitOrPointerCast(CastVal, DstVTy);
 }
 
 void InnerLoopVectorizer::emitMinimumIterationCountCheck(Loop *L,
                                                          BasicBlock *Bypass) {
   Value *Count = getOrCreateTripCount(L);
   // Reuse existing vector loop preheader for TC checks.
for (const auto &KV : Cost->getMinimalBitwidths()) {
     for (unsigned Part = 0; Part < UF; ++Part) {
       Value *I = getOrCreateVectorValue(KV.first, Part);
       if (Erased.find(I) != Erased.end() || I->use_empty() ||
           !isa<Instruction>(I))
         continue;
       Type *OriginalTy = I->getType();
       Type *ScalarTruncatedTy =
           IntegerType::get(OriginalTy->getContext(), KV.second);
-      Type *TruncatedTy = VectorType::get(
+      auto *TruncatedTy = FixedVectorType::get(
           ScalarTruncatedTy, cast<VectorType>(OriginalTy)->getNumElements());
       if (TruncatedTy == OriginalTy)
         continue;
 
       IRBuilder<> B(cast<Instruction>(I));
       auto ShrinkOperand = [&](Value *V) -> Value * {
         if (auto *ZI = dyn_cast<ZExtInst>(V))
           if (ZI->getSrcTy() == TruncatedTy)
for (unsigned Part = 0; Part < UF; ++Part) {
               CI->getOperand(0),
               smallestIntegerVectorType(OriginalTy, TruncatedTy));
           break;
         }
       } else if (auto *SI = dyn_cast<ShuffleVectorInst>(I)) {
         auto Elements0 =
             cast<VectorType>(SI->getOperand(0)->getType())->getNumElements();
         auto *O0 = B.CreateZExtOrTrunc(
-            SI->getOperand(0), VectorType::get(ScalarTruncatedTy, Elements0));
+            SI->getOperand(0),
+            FixedVectorType::get(ScalarTruncatedTy, Elements0));
         auto Elements1 =
             cast<VectorType>(SI->getOperand(1)->getType())->getNumElements();
         auto *O1 = B.CreateZExtOrTrunc(
-            SI->getOperand(1), VectorType::get(ScalarTruncatedTy, Elements1));
+            SI->getOperand(1),
+            FixedVectorType::get(ScalarTruncatedTy, Elements1));
 
         NewI = B.CreateShuffleVector(O0, O1, SI->getShuffleMask());
       } else if (isa<LoadInst>(I) || isa<PHINode>(I)) {
         // Don't do anything with the operands, just extend the result.
         continue;
       } else if (auto *IE = dyn_cast<InsertElementInst>(I)) {
         auto Elements =
             cast<VectorType>(IE->getOperand(0)->getType())->getNumElements();
         auto *O0 = B.CreateZExtOrTrunc(
-            IE->getOperand(0), VectorType::get(ScalarTruncatedTy, Elements));
+            IE->getOperand(0),
+            FixedVectorType::get(ScalarTruncatedTy, Elements));
         auto *O1 = B.CreateZExtOrTrunc(IE->getOperand(1), ScalarTruncatedTy);
         NewI = B.CreateInsertElement(O0, O1, IE->getOperand(2));
       } else if (auto *EE = dyn_cast<ExtractElementInst>(I)) {
         auto Elements =
             cast<VectorType>(EE->getOperand(0)->getType())->getNumElements();
         auto *O0 = B.CreateZExtOrTrunc(
-            EE->getOperand(0), VectorType::get(ScalarTruncatedTy, Elements));
+            EE->getOperand(0),
+            FixedVectorType::get(ScalarTruncatedTy, Elements));
         NewI = B.CreateExtractElement(O0, EE->getOperand(2));
       } else {
         // If we don't know what to do, be conservative and don't do anything.
         continue;
       }
 
       // Lastly, extend the result.
       NewI->takeName(cast<Instruction>(I));
void InnerLoopVectorizer::fixFirstOrderRecurrence(PHINode *Phi) {
   auto *ScalarInit = Phi->getIncomingValueForBlock(Preheader);
   auto *Previous = Phi->getIncomingValueForBlock(Latch);
 
   // Create a vector from the initial value.
   auto *VectorInit = ScalarInit;
   if (VF > 1) {
     Builder.SetInsertPoint(LoopVectorPreHeader->getTerminator());
     VectorInit = Builder.CreateInsertElement(
-        UndefValue::get(VectorType::get(VectorInit->getType(), VF)), VectorInit,
-        Builder.getInt32(VF - 1), "vector.recur.init");
+        UndefValue::get(FixedVectorType::get(VectorInit->getType(), VF)),
+        VectorInit, Builder.getInt32(VF - 1), "vector.recur.init");
   }
 
   // We constructed a temporary phi node in the first phase of vectorization.
   // This phi node will eventually be deleted.
   Builder.SetInsertPoint(
       cast<Instruction>(VectorLoopValueMap.getVectorValue(Phi, 0)));
 
   // Create a phi node for the new recurrence. The current value will either be
for (unsigned Part = 0; Part < UF; ++Part) {
       VectorLoopValueMap.resetVectorValue(LoopExitInst, Part, Sel);
     }
   }
 
   // If the vector reduction can be performed in a smaller type, we truncate
   // then extend the loop exit value to enable InstCombine to evaluate the
   // entire expression in the smaller type.
   if (VF > 1 && Phi->getType() != RdxDesc.getRecurrenceType()) {
-    Type *RdxVecTy = VectorType::get(RdxDesc.getRecurrenceType(), VF);
+    Type *RdxVecTy = FixedVectorType::get(RdxDesc.getRecurrenceType(), VF);
     Builder.SetInsertPoint(
         LI->getLoopFor(LoopVectorBody)->getLoopLatch()->getTerminator());
     VectorParts RdxParts(UF);
     for (unsigned Part = 0; Part < UF; ++Part) {
       RdxParts[Part] = VectorLoopValueMap.getVectorValue(LoopExitInst, Part);
       Value *Trunc = Builder.CreateTrunc(RdxParts[Part], RdxVecTy);
       Value *Extnd = RdxDesc.isSigned() ? Builder.CreateSExt(Trunc, VecTy)
                                         : Builder.CreateZExt(Trunc, VecTy);
void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN, unsigned UF,
                                               unsigned VF) {
   PHINode *P = cast<PHINode>(PN);
   if (EnableVPlanNativePath) {
     // Currently we enter here in the VPlan-native path for non-induction
     // PHIs where all control flow is uniform. We simply widen these PHIs.
     // Create a vector phi with no operands - the vector phi operands will be
     // set at the end of vector code generation.
     Type *VecTy =
-        (VF == 1) ? PN->getType() : VectorType::get(PN->getType(), VF);
+        (VF == 1) ? PN->getType() : FixedVectorType::get(PN->getType(), VF);
     Value *VecPhi = Builder.CreatePHI(VecTy, PN->getNumOperands(), "vec.phi");
     VectorLoopValueMap.setVectorValue(P, 0, VecPhi);
     OrigPHIsToFix.push_back(P);
 
     return;
   }
 
   assert(PN->getParent() == OrigLoop->getHeader() &&
          "Non-header phis should have been handled elsewhere");
 
   // In order to support recurrences we need to be able to vectorize Phi nodes.
   // Phi nodes have cycles, so we need to vectorize them in two stages. This is
   // stage #1: We create a new vector PHI node with no incoming edges. We'll use
   // this value when we vectorize all of the instructions that use the PHI.
   if (Legal->isReductionVariable(P) || Legal->isFirstOrderRecurrence(P)) {
     for (unsigned Part = 0; Part < UF; ++Part) {
       // This is phase one of vectorizing PHIs.
       Type *VecTy =
-          (VF == 1) ? PN->getType() : VectorType::get(PN->getType(), VF);
+          (VF == 1) ? PN->getType() : FixedVectorType::get(PN->getType(), VF);
       Value *EntryPart = PHINode::Create(
           VecTy, 2, "vec.phi", &*LoopVectorBody->getFirstInsertionPt());
       VectorLoopValueMap.setVectorValue(P, Part, EntryPart);
     }
     return;
   }
 
   setDebugLocFromInst(Builder, P);
void InnerLoopVectorizer::widenInstruction(Instruction &I, VPUser &User,
   case Instruction::Trunc:
   case Instruction::FPTrunc:
   case Instruction::BitCast: {
     auto *CI = cast<CastInst>(&I);
     setDebugLocFromInst(Builder, CI);
 
     /// Vectorize casts.
     Type *DestTy =
-        (VF == 1) ? CI->getType() : VectorType::get(CI->getType(), VF);
+        (VF == 1) ? CI->getType() : FixedVectorType::get(CI->getType(), VF);
 
     for (unsigned Part = 0; Part < UF; ++Part) {
       Value *A = State.get(User.getOperand(0), Part);
       Value *Cast = Builder.CreateCast(CI->getOpcode(), A, DestTy);
       VectorLoopValueMap.setVectorValue(&I, Part, Cast);
       addMetadata(Cast, &I);
     }
     break;
for (auto &I : enumerate(ArgOperands.operands())) {
       Args.push_back(Arg);
     }
 
     Function *VectorF;
     if (UseVectorIntrinsic) {
       // Use vector version of the intrinsic.
       Type *TysForDecl[] = {CI->getType()};
       if (VF > 1)
-        TysForDecl[0] = VectorType::get(CI->getType()->getScalarType(), VF);
+        TysForDecl[0] =
+            FixedVectorType::get(CI->getType()->getScalarType(), VF);
       VectorF = Intrinsic::getDeclaration(M, ID, TysForDecl);
       assert(VectorF && "Can't retrieve vector intrinsic.");
     } else {
       // Use vector version of the function call.
       const VFShape Shape =
           VFShape::get(*CI, {VF, false} /*EC*/, false /*HasGlobalPred*/);
 #ifndef NDEBUG
       assert(VFDatabase(*CI).getVectorizedFunction(Shape) != nullptr &&
unsigned LoopVectorizationCostModel::getInterleaveGroupCost(Instruction *I,
   Type *ValTy = getMemInstValueType(I);
   auto *VectorTy = FixedVectorType::get(ValTy, VF);
   unsigned AS = getLoadStoreAddressSpace(I);
 
   auto Group = getInterleavedAccessGroup(I);
   assert(Group && "Fail to get an interleaved access group.");
 
   unsigned InterleaveFactor = Group->getFactor();
-  VectorType *WideVecTy = VectorType::get(ValTy, VF * InterleaveFactor);
+  auto *WideVecTy = FixedVectorType::get(ValTy, VF * InterleaveFactor);
 
   // Holds the indices of existing members in an interleaved load group.
   // An interleaved store group doesn't need this as it doesn't allow gaps.
   SmallVector<unsigned, 4> Indices;
   if (isa<LoadInst>(I)) {
     for (unsigned i = 0; i < InterleaveFactor; i++)
       if (Group->getMember(i))
         Indices.push_back(i);
return N * TTI.getArithmeticInstrCost(
                    I->getOperand(0), I);
   }
   case Instruction::Select: {
     SelectInst *SI = cast<SelectInst>(I);
     const SCEV *CondSCEV = SE->getSCEV(SI->getCondition());
     bool ScalarCond = (SE->isLoopInvariant(CondSCEV, TheLoop));
     Type *CondTy = SI->getCondition()->getType();
     if (!ScalarCond)
-      CondTy = VectorType::get(CondTy, VF);
+      CondTy = FixedVectorType::get(CondTy, VF);
 
     return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy, CondTy,
                                   CostKind, I);
   }
   case Instruction::ICmp:
   case Instruction::FCmp: {
     Type *ValTy = I->getOperand(0)->getType();
     Instruction *Op0AsInstruction = dyn_cast<Instruction>(I->getOperand(0));

 void VPReplicateRecipe::execute(VPTransformState &State) {
   if (State.Instance) { // Generate a single instance.
     State.ILV->scalarizeInstruction(Ingredient, User, *State.Instance,
                                     IsPredicated, State);
     // Insert scalar instance packing it into a vector.
     if (AlsoPack && State.VF > 1) {
       // If we're constructing lane 0, initialize to start from undef.
       if (State.Instance->Lane == 0) {
-        Value *Undef =
-            UndefValue::get(VectorType::get(Ingredient->getType(), State.VF));
+        Value *Undef = UndefValue::get(
+            FixedVectorType::get(Ingredient->getType(), State.VF));
         State.ValueMap.setVectorValue(Ingredient, State.Instance->Part, Undef);
       }
       State.ILV->packScalarIntoVectorValue(Ingredient, *State.Instance);
     }
     return;
   }
 
   // Generate scalar instances for all VF lanes of all UF parts, unless the

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

if (auto *ST = dyn_cast<StructType>(EltTy)) {
       auto *VT = cast<VectorType>(EltTy);
       N *= VT->getNumElements();
       EltTy = VT->getElementType();
     }
   }
 
   if (!isValidElementType(EltTy))
     return 0;
-  uint64_t VTSize = DL.getTypeStoreSizeInBits(VectorType::get(EltTy, N));
+  uint64_t VTSize = DL.getTypeStoreSizeInBits(FixedVectorType::get(EltTy, N));
   if (VTSize < MinVecRegSize || VTSize > MaxVecRegSize || VTSize != DL.getTypeStoreSizeInBits(T))
     return 0;
   return N;
 }
 
 bool BoUpSLP::canReuseExtract(ArrayRef<Value *> VL, Value *OpValue,
                               SmallVectorImpl<unsigned> &CurrentOrder) const {
   Instruction *E0 = cast<Instruction>(OpValue);
auto Shape =
                    false /*HasGlobalPred*/);
   Function *VecFunc = VFDatabase(*CI).getVectorizedFunction(Shape);
   int LibCost = IntrinsicCost;
   if (!CI->isNoBuiltin() && VecFunc) {
     // Calculate the cost of the vector library call.
     SmallVector<Type *, 4> VecTys;
     for (Use &Arg : CI->args())
       VecTys.push_back(
-          VectorType::get(Arg->getType(), VecTy->getNumElements()));
+          FixedVectorType::get(Arg->getType(), VecTy->getNumElements()));
 
     // If the corresponding vector call is cheaper, return its cost.
     LibCost = TTI->getCallInstrCost(nullptr, VecTy, VecTys,
                                     TTI::TCK_RecipThroughput);
   }
   return {IntrinsicCost, LibCost};
 }
 
case Instruction::BitCast: {
                                 VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
 
       // Calculate the cost of this instruction.
       int ScalarCost = VL.size() * ScalarEltCost;
 
-      VectorType *SrcVecTy = VectorType::get(SrcTy, VL.size());
+      auto *SrcVecTy = FixedVectorType::get(SrcTy, VL.size());
       int VecCost = 0;
       // Check if the values are candidates to demote.
       if (!MinBWs.count(VL0) || VecTy != SrcVecTy) {
         VecCost = ReuseShuffleCost +
                   TTI->getCastInstrCost(E->getOpcode(), VecTy, SrcVecTy,
                                         CostKind, VL0);
       }
       return VecCost - ScalarCost;
     }
     case Instruction::FCmp:
     case Instruction::ICmp:
     case Instruction::Select: {
       // Calculate the cost of this instruction.
       int ScalarEltCost = TTI->getCmpSelInstrCost(E->getOpcode(), ScalarTy,
                                                   Builder.getInt1Ty(),
                                                   CostKind, VL0);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;
       }
-      VectorType *MaskTy = VectorType::get(Builder.getInt1Ty(), VL.size());
+      auto *MaskTy = FixedVectorType::get(Builder.getInt1Ty(), VL.size());
       int ScalarCost = VecTy->getNumElements() * ScalarEltCost;
       int VecCost = TTI->getCmpSelInstrCost(E->getOpcode(), VecTy, MaskTy,
                                             CostKind, VL0);
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
     case Instruction::FNeg:
     case Instruction::Add:
     case Instruction::FAdd:
case Instruction::ShuffleVector: {
       int VecCost = 0;
       if (Instruction::isBinaryOp(E->getOpcode())) {
         VecCost = TTI->getArithmeticInstrCost(E->getOpcode(), VecTy, CostKind);
         VecCost += TTI->getArithmeticInstrCost(E->getAltOpcode(), VecTy,
                                                CostKind);
       } else {
         Type *Src0SclTy = E->getMainOp()->getOperand(0)->getType();
         Type *Src1SclTy = E->getAltOp()->getOperand(0)->getType();
-        VectorType *Src0Ty = VectorType::get(Src0SclTy, VL.size());
-        VectorType *Src1Ty = VectorType::get(Src1SclTy, VL.size());
+        auto *Src0Ty = FixedVectorType::get(Src0SclTy, VL.size());
+        auto *Src1Ty = FixedVectorType::get(Src1SclTy, VL.size());
         VecCost = TTI->getCastInstrCost(E->getOpcode(), VecTy, Src0Ty,
                                         CostKind);
         VecCost += TTI->getCastInstrCost(E->getAltOpcode(), VecTy, Src1Ty,
                                          CostKind);
       }
       VecCost += TTI->getShuffleCost(TargetTransformInfo::SK_Select, VecTy, 0);
       return ReuseShuffleCost + VecCost - ScalarCost;
     }
while (InstIt != PrevInstIt) {
         NumCalls++;
 
       ++PrevInstIt;
     }
 
     if (NumCalls) {
       SmallVector<Type*, 4> V;
       for (auto *II : LiveValues)
-        V.push_back(VectorType::get(II->getType(), BundleWidth));
+        V.push_back(FixedVectorType::get(II->getType(), BundleWidth));
       Cost += NumCalls * TTI->getCostOfKeepingLiveOverCall(V);
     }
 
     PrevInst = Inst;
   }
 
   return Cost;
 }
if (VL.size() > 2) {
     // Do not shuffle single element or if number of unique values is not power
     // of 2.
     if (UniqueValues.size() == VL.size() || UniqueValues.size() <= 1 ||
         !llvm::isPowerOf2_32(UniqueValues.size()))
       ReuseShuffleIndicies.clear();
     else
       VL = UniqueValues;
   }
-  VectorType *VecTy = VectorType::get(ScalarTy, VL.size());
+  auto *VecTy = FixedVectorType::get(ScalarTy, VL.size());
 
   Value *V = Gather(VL, VecTy);
   if (!ReuseShuffleIndicies.empty()) {
     V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                     ReuseShuffleIndicies, "shuffle");
     if (auto *I = dyn_cast<Instruction>(V)) {
       GatherSeq.insert(I);
       CSEBlocks.insert(I->getParent());
if (E->VectorizedValue) {
     LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n");
     return E->VectorizedValue;
   }
 
   Instruction *VL0 = E->getMainOp();
   Type *ScalarTy = VL0->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL0))
     ScalarTy = SI->getValueOperand()->getType();
-  VectorType *VecTy = VectorType::get(ScalarTy, E->Scalars.size());
+  auto *VecTy = FixedVectorType::get(ScalarTy, E->Scalars.size());
 
   bool NeedToShuffleReuses = !E->ReuseShuffleIndices.empty();
 
   if (E->State == TreeEntry::NeedToGather) {
     setInsertPointAfterBundle(E);
     auto *V = Gather(E->Scalars, VecTy);
     if (NeedToShuffleReuses) {
       V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
case Instruction::Call: {
         }
 
         Value *OpVec = vectorizeTree(E->getOperand(j));
         LLVM_DEBUG(dbgs() << "SLP: OpVec[" << j << "]: " << *OpVec << "\n");
         OpVecs.push_back(OpVec);
       }
 
       Module *M = F->getParent();
-      Type *Tys[] = { VectorType::get(CI->getType(), E->Scalars.size()) };
+      Type *Tys[] = {FixedVectorType::get(CI->getType(), E->Scalars.size())};
       Function *CF = Intrinsic::getDeclaration(M, ID, Tys);
 
       if (!UseIntrinsic) {
         VFShape Shape = VFShape::get(
             *CI, {static_cast<unsigned>(VecTy->getNumElements()), false},
             false /*HasGlobalPred*/);
         CF = VFDatabase(*CI).getVectorizedFunction(Shape);
       }
BoUpSLP::vectorizeTree(ExtraValueToDebugLocsMap &ExternallyUsedValues) {
   // vectorized root. InstCombine will then rewrite the entire expression. We
   // sign extend the extracted values below.
   auto *ScalarRoot = VectorizableTree[0]->Scalars[0];
   if (MinBWs.count(ScalarRoot)) {
     if (auto *I = dyn_cast<Instruction>(VectorRoot))
       Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
     auto BundleWidth = VectorizableTree[0]->Scalars.size();
     auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
-    auto *VecTy = VectorType::get(MinTy, BundleWidth);
+    auto *VecTy = FixedVectorType::get(MinTy, BundleWidth);
     auto *Trunc = Builder.CreateTrunc(VectorRoot, VecTy);
     VectorizableTree[0]->VectorizedValue = Trunc;
   }
 
   LLVM_DEBUG(dbgs() << "SLP: Extracting " << ExternalUses.size()
                     << " values .\n");
 
   // If necessary, sign-extend or zero-extend ScalarRoot to the larger type
bool SLPVectorizerPass::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R,
   bool CandidateFound = false;
   int MinCost = SLPCostThreshold;
 
   unsigned NextInst = 0, MaxInst = VL.size();
   for (unsigned VF = MaxVF; NextInst + 1 < MaxInst && VF >= MinVF; VF /= 2) {
     // No actual vectorization should happen, if number of parts is the same as
     // provided vectorization factor (i.e. the scalar type is used for vector
     // code during codegen).
-    auto *VecTy = VectorType::get(VL[0]->getType(), VF);
+    auto *VecTy = FixedVectorType::get(VL[0]->getType(), VF);
     if (TTI->getNumberOfParts(VecTy) == VF)
       continue;
     for (unsigned I = NextInst; I < MaxInst; ++I) {
       unsigned OpsWidth = 0;
 
       if (I + VF > MaxInst)
         OpsWidth = MaxInst - I;
       else