Clean up usages of asserting vector getters in Type

[ctetreau]

Summary

Remove usages of asserting vector getters in Type in preparation for the
VectorType refactor. The existence of these functions complicates the
refactor while adding little value.

[ctetreau]

update to mention that this is NFC

[efriedma]

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

212

Please don't mix in semantic changes.

689

The assertion text isn't useful; just cast<>

907

The assertion text isn't useful; just cast<>

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

182–183

dyn_cast

[ctetreau]

address code review comments

[efriedma]

LGTM

[ctetreau]

rebase

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

bool AArch64TargetLowering::lowerInterleavedLoad(
   // the vector types are divisible by 128.
   if (!Subtarget->hasNEON() || !isLegalInterleavedAccessType(VecTy, DL))
     return false;
 
   unsigned NumLoads = getNumInterleavedAccesses(VecTy, DL);
 
   // A pointer vector can not be the return type of the ldN intrinsics. Need to
   // load integer vectors first and then convert to pointer vectors.
-  Type *EltTy = VecTy->getVectorElementType();
+  Type *EltTy = VecTy->getElementType();
   if (EltTy->isPointerTy())
-    VecTy =
-        VectorType::get(DL.getIntPtrType(EltTy), VecTy->getVectorNumElements());
+    VecTy = VectorType::get(DL.getIntPtrType(EltTy), VecTy->getNumElements());
 
   IRBuilder<> Builder(LI);
 
   // The base address of the load.
   Value *BaseAddr = LI->getPointerOperand();
 
   if (NumLoads > 1) {
     // If we're going to generate more than one load, reset the sub-vector type
     // to something legal.
-    VecTy = VectorType::get(VecTy->getVectorElementType(),
-                            VecTy->getVectorNumElements() / NumLoads);
+    VecTy = VectorType::get(VecTy->getElementType(),
+                            VecTy->getNumElements() / NumLoads);
 
     // We will compute the pointer operand of each load from the original base
     // address using GEPs. Cast the base address to a pointer to the scalar
     // element type.
     BaseAddr = Builder.CreateBitCast(
-        BaseAddr, VecTy->getVectorElementType()->getPointerTo(
-                      LI->getPointerAddressSpace()));
+        BaseAddr,
+        VecTy->getElementType()->getPointerTo(LI->getPointerAddressSpace()));
   }
 
   Type *PtrTy = VecTy->getPointerTo(LI->getPointerAddressSpace());
   Type *Tys[2] = {VecTy, PtrTy};
   static const Intrinsic::ID LoadInts[3] = {Intrinsic::aarch64_neon_ld2,
                                             Intrinsic::aarch64_neon_ld3,
                                             Intrinsic::aarch64_neon_ld4};
   Function *LdNFunc =
       Intrinsic::getDeclaration(LI->getModule(), LoadInts[Factor - 2], Tys);
 
   // Holds sub-vectors extracted from the load intrinsic return values. The
   // sub-vectors are associated with the shufflevector instructions they will
   // replace.
   DenseMap<ShuffleVectorInst *, SmallVector<Value *, 4>> SubVecs;
 
   for (unsigned LoadCount = 0; LoadCount < NumLoads; ++LoadCount) {
 
     // If we're generating more than one load, compute the base address of
     // subsequent loads as an offset from the previous.
     if (LoadCount > 0)
-      BaseAddr =
-          Builder.CreateConstGEP1_32(VecTy->getVectorElementType(), BaseAddr,
-                                     VecTy->getVectorNumElements() * Factor);
+      BaseAddr = Builder.CreateConstGEP1_32(VecTy->getElementType(), BaseAddr,
+                                            VecTy->getNumElements() * Factor);
 
     CallInst *LdN = Builder.CreateCall(
         LdNFunc, Builder.CreateBitCast(BaseAddr, PtrTy), "ldN");
 
     // Extract and store the sub-vectors returned by the load intrinsic.
     for (unsigned i = 0; i < Shuffles.size(); i++) {
       ShuffleVectorInst *SVI = Shuffles[i];
       unsigned Index = Indices[i];
 
       Value *SubVec = Builder.CreateExtractValue(LdN, Index);
 
       // Convert the integer vector to pointer vector if the element is pointer.
       if (EltTy->isPointerTy())
         SubVec = Builder.CreateIntToPtr(
-            SubVec, VectorType::get(SVI->getType()->getVectorElementType(),
-                                    VecTy->getVectorNumElements()));
+            SubVec, VectorType::get(SVI->getType()->getElementType(),
+                                    VecTy->getNumElements()));
       SubVecs[SVI].push_back(SubVec);
     }
   }
 
   // Replace uses of the shufflevector instructions with the sub-vectors
   // returned by the load intrinsic. If a shufflevector instruction is
   // associated with more than one sub-vector, those sub-vectors will be
   // concatenated into a single wide vector.

 ///        call void llvm.aarch64.neon.st3(%sub.v0, %sub.v1, %sub.v2, %ptr)
 bool AArch64TargetLowering::lowerInterleavedStore(StoreInst *SI,
                                                   ShuffleVectorInst *SVI,
                                                   unsigned Factor) const {
   assert(Factor >= 2 && Factor <= getMaxSupportedInterleaveFactor() &&
          "Invalid interleave factor");
 
   VectorType *VecTy = SVI->getType();
-  assert(VecTy->getVectorNumElements() % Factor == 0 &&
-         "Invalid interleaved store");
+  assert(VecTy->getNumElements() % Factor == 0 && "Invalid interleaved store");
 
-  unsigned LaneLen = VecTy->getVectorNumElements() / Factor;
-  Type *EltTy = VecTy->getVectorElementType();
+  unsigned LaneLen = VecTy->getNumElements() / Factor;
+  Type *EltTy = VecTy->getElementType();
   VectorType *SubVecTy = VectorType::get(EltTy, LaneLen);
 
   const DataLayout &DL = SI->getModule()->getDataLayout();
 
   // Skip if we do not have NEON and skip illegal vector types. We can
   // "legalize" wide vector types into multiple interleaved accesses as long as
   // the vector types are divisible by 128.
   if (!Subtarget->hasNEON() || !isLegalInterleavedAccessType(SubVecTy, DL))
     return false;
 
   unsigned NumStores = getNumInterleavedAccesses(SubVecTy, DL);
 
   Value *Op0 = SVI->getOperand(0);
   Value *Op1 = SVI->getOperand(1);
   IRBuilder<> Builder(SI);
 
   // StN intrinsics don't support pointer vectors as arguments. Convert pointer
   // vectors to integer vectors.
   if (EltTy->isPointerTy()) {
     Type *IntTy = DL.getIntPtrType(EltTy);
-    unsigned NumOpElts = Op0->getType()->getVectorNumElements();
+    unsigned NumOpElts = cast<VectorType>(Op0->getType())->getNumElements();
 
     // Convert to the corresponding integer vector.
     Type *IntVecTy = VectorType::get(IntTy, NumOpElts);
     Op0 = Builder.CreatePtrToInt(Op0, IntVecTy);
     Op1 = Builder.CreatePtrToInt(Op1, IntVecTy);
 
     SubVecTy = VectorType::get(IntTy, LaneLen);
   }
 
   // The base address of the store.
   Value *BaseAddr = SI->getPointerOperand();
 
   if (NumStores > 1) {
     // If we're going to generate more than one store, reset the lane length
     // and sub-vector type to something legal.
     LaneLen /= NumStores;
-    SubVecTy = VectorType::get(SubVecTy->getVectorElementType(), LaneLen);
+    SubVecTy = VectorType::get(SubVecTy->getElementType(), LaneLen);
 
     // We will compute the pointer operand of each store from the original base
     // address using GEPs. Cast the base address to a pointer to the scalar
     // element type.
     BaseAddr = Builder.CreateBitCast(
-        BaseAddr, SubVecTy->getVectorElementType()->getPointerTo(
-                      SI->getPointerAddressSpace()));
+        BaseAddr,
+        SubVecTy->getElementType()->getPointerTo(SI->getPointerAddressSpace()));
   }
 
   auto Mask = SVI->getShuffleMask();
 
   Type *PtrTy = SubVecTy->getPointerTo(SI->getPointerAddressSpace());
   Type *Tys[2] = {SubVecTy, PtrTy};
   static const Intrinsic::ID StoreInts[3] = {Intrinsic::aarch64_neon_st2,
                                              Intrinsic::aarch64_neon_st3,
for (unsigned i = 0; i < Factor; i++) {
         Ops.push_back(Builder.CreateShuffleVector(
             Op0, Op1, createSequentialMask(Builder, StartMask, LaneLen, 0)));
       }
     }
 
     // If we generating more than one store, we compute the base address of
     // subsequent stores as an offset from the previous.
     if (StoreCount > 0)
-      BaseAddr = Builder.CreateConstGEP1_32(SubVecTy->getVectorElementType(),
+      BaseAddr = Builder.CreateConstGEP1_32(SubVecTy->getElementType(),
                                             BaseAddr, LaneLen * Factor);
 
     Ops.push_back(Builder.CreateBitCast(BaseAddr, PtrTy));
     Builder.CreateCall(StNFunc, Ops);
   }
   return true;
 }
 
bool AArch64TargetLowering::isLegalAddressingMode(const DataLayout &DL,
   if (AM.BaseGV)
     return false;
 
   // No reg+reg+imm addressing.
   if (AM.HasBaseReg && AM.BaseOffs && AM.Scale)
     return false;
 
   // FIXME: Update this method to support scalable addressing modes.
-  if (Ty->isVectorTy() && Ty->getVectorIsScalable())
+  if (Ty->isVectorTy() && cast<VectorType>(Ty)->isScalable())
     return AM.HasBaseReg && !AM.BaseOffs && !AM.Scale;
 
   // check reg + imm case:
   // i.e., reg + 0, reg + imm9, reg + SIZE_IN_BYTES * uimm12
   uint64_t NumBytes = 0;
   if (Ty->isSized()) {
     uint64_t NumBits = DL.getTypeSizeInBits(Ty);
     NumBytes = NumBits / 8;

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
                                            Type *ExpectedType);
 
   bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info);
 
   bool isLegalMaskedLoadStore(Type *DataType, MaybeAlign Alignment) {
     if (!isa<VectorType>(DataType) || !ST->hasSVE())
       return false;
 
-    Type *Ty = DataType->getVectorElementType();
+    Type *Ty = cast<VectorType>(DataType)->getElementType();
     if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy())
       return true;
 
     if (Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
         Ty->isIntegerTy(32) || Ty->isIntegerTy(64))
       return true;
 
     return false;
public:
 
   bool isLegalNTStore(Type *DataType, Align Alignment) {
     // NOTE: The logic below is mostly geared towards LV, which calls it with
     //       vectors with 2 elements. We might want to improve that, if other
     //       users show up.
     // Nontemporal vector stores can be directly lowered to STNP, if the vector
     // can be halved so that each half fits into a register. That's the case if
     // the element type fits into a register and the number of elements is a
     // power of 2 > 1.
-    if (isa<VectorType>(DataType)) {
-      unsigned NumElements = DataType->getVectorNumElements();
-      unsigned EltSize =
-          DataType->getVectorElementType()->getScalarSizeInBits();
+    if (auto *DataTypeVTy = dyn_cast<VectorType>(DataType)) {
+      unsigned NumElements = DataTypeVTy->getNumElements();
+      unsigned EltSize = DataTypeVTy->getElementType()->getScalarSizeInBits();
       return NumElements > 1 && isPowerOf2_64(NumElements) && EltSize >= 8 &&
              EltSize <= 128 && isPowerOf2_64(EltSize);
     }
     return BaseT::isLegalNTStore(DataType, Alignment);
   }
 
   int getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy, unsigned Factor,
                                  ArrayRef<unsigned> Indices, unsigned Alignment,

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

 
 bool AArch64TTIImpl::isWideningInstruction(Type *DstTy, unsigned Opcode,
                                            ArrayRef<const Value *> Args) {
 
   // A helper that returns a vector type from the given type. The number of
   // elements in type Ty determine the vector width.
   auto toVectorTy = [&](Type *ArgTy) {
     return VectorType::get(ArgTy->getScalarType(),
-                           DstTy->getVectorNumElements());
+                           cast<VectorType>(DstTy)->getNumElements());
   };
 
   // Exit early if DstTy is not a vector type whose elements are at least
   // 16-bits wide.
   if (!DstTy->isVectorTy() || DstTy->getScalarSizeInBits() < 16)
     return false;
 
   // Determine if the operation has a widening variant. We consider both the
if (ST->isMisaligned128StoreSlow() && Opcode == Instruction::Store &&
     // practice on inlined block copy code.
     // We make such stores expensive so that we will only vectorize if there
     // are 6 other instructions getting vectorized.
     const int AmortizationCost = 6;
 
     return LT.first * 2 * AmortizationCost;
   }
 
-  if (Ty->isVectorTy() && Ty->getVectorElementType()->isIntegerTy(8)) {
+  if (Ty->isVectorTy() &&
+      cast<VectorType>(Ty)->getElementType()->isIntegerTy(8)) {
     unsigned ProfitableNumElements;
     if (Opcode == Instruction::Store)
       // We use a custom trunc store lowering so v.4b should be profitable.
       ProfitableNumElements = 4;
     else
       // We scalarize the loads because there is not v.4b register and we
       // have to promote the elements to v.2.
       ProfitableNumElements = 8;
 
-    if (Ty->getVectorNumElements() < ProfitableNumElements) {
-      unsigned NumVecElts = Ty->getVectorNumElements();
+    if (cast<VectorType>(Ty)->getNumElements() < ProfitableNumElements) {
+      unsigned NumVecElts = cast<VectorType>(Ty)->getNumElements();
       unsigned NumVectorizableInstsToAmortize = NumVecElts * 2;
       // We generate 2 instructions per vector element.
       return NumVectorizableInstsToAmortize * NumVecElts * 2;
     }
   }
 
   return LT.first;
 }
 
 int AArch64TTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
                                                unsigned Factor,
                                                ArrayRef<unsigned> Indices,
                                                unsigned Alignment,
                                                unsigned AddressSpace,
                                                bool UseMaskForCond,
                                                bool UseMaskForGaps) {
   assert(Factor >= 2 && "Invalid interleave factor");
-  assert(isa<VectorType>(VecTy) && "Expect a vector type");
+  auto *VecVTy = cast<VectorType>(VecTy);
 
   if (!UseMaskForCond && !UseMaskForGaps &&
       Factor <= TLI->getMaxSupportedInterleaveFactor()) {
-    unsigned NumElts = VecTy->getVectorNumElements();
+    unsigned NumElts = VecVTy->getNumElements();
     auto *SubVecTy = VectorType::get(VecTy->getScalarType(), NumElts / Factor);
 
     // ldN/stN only support legal vector types of size 64 or 128 in bits.
     // Accesses having vector types that are a multiple of 128 bits can be
     // matched to more than one ldN/stN instruction.
     if (NumElts % Factor == 0 &&
         TLI->isLegalInterleavedAccessType(SubVecTy, DL))
       return Factor * TLI->getNumInterleavedAccesses(SubVecTy, DL);
   }
 
   return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
                                            Alignment, AddressSpace,
                                            UseMaskForCond, UseMaskForGaps);
 }
 
 int AArch64TTIImpl::getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys) {
   int Cost = 0;
   for (auto *I : Tys) {
     if (!I->isVectorTy())
       continue;
-    if (I->getScalarSizeInBits() * I->getVectorNumElements() == 128)
+    if (I->getScalarSizeInBits() * cast<VectorType>(I)->getNumElements() == 128)
       Cost += getMemoryOpCost(Instruction::Store, I, Align(128), 0) +
               getMemoryOpCost(Instruction::Load, I, Align(128), 0);
   }
   return Cost;
 }
 
 unsigned AArch64TTIImpl::getMaxInterleaveFactor(unsigned VF) {
   return ST->getMaxInterleaveFactor();
if (const GetElementPtrInst *GEPInst = dyn_cast<GetElementPtrInst>(U)) {
       }
     }
   }
   return Considerable;
 }
 
 bool AArch64TTIImpl::useReductionIntrinsic(unsigned Opcode, Type *Ty,
                                            TTI::ReductionFlags Flags) const {
-  assert(isa<VectorType>(Ty) && "Expected Ty to be a vector type");
+  auto *VTy = cast<VectorType>(Ty);
   unsigned ScalarBits = Ty->getScalarSizeInBits();
   switch (Opcode) {
   case Instruction::FAdd:
   case Instruction::FMul:
   case Instruction::And:
   case Instruction::Or:
   case Instruction::Xor:
   case Instruction::Mul:
     return false;
   case Instruction::Add:
-    return ScalarBits * Ty->getVectorNumElements() >= 128;
+    return ScalarBits * VTy->getNumElements() >= 128;
   case Instruction::ICmp:
-    return (ScalarBits < 64) &&
-           (ScalarBits * Ty->getVectorNumElements() >= 128);
+    return (ScalarBits < 64) && (ScalarBits * VTy->getNumElements() >= 128);
   case Instruction::FCmp:
     return Flags.NoNaN;
   default:
     llvm_unreachable("Unhandled reduction opcode");
   }
   return false;
 }