[AArch64][TTI][NFC] Overload method 'getVectorInstrCost' to provide vector instruction itself, as a context information for cost estimation.

[mingmingl]

Summary

1. Overloaded (instruction-based) method is a wrapper around the current (opcode-based) method.
2. This patch also changes a few callsites (VectorCombine.cpp, SLPVectorizer.cpp, CodeGenPrepare.cpp) to call the overloaded method.
3. This is a split of D128302.

[mingmingl]

undo the AArch64 custom overload

[davidxl]

llvm/include/llvm/Analysis/TargetTransformInfo.h

1181

Is the Type *val always from instruction? If yes, this parameter can be removed. Alternatively add an assert in the implementation that I->getType() == Val. The latter may be better as Type is readily available at callsite.

llvm/test/Analysis/CostModel/AArch64/kryo.ll

36

This test change belong to the follow up patch.

[mingmingl]

Resolve comments.

llvm/include/llvm/Analysis/TargetTransformInfo.h

1181

Type* val (representing vector type) could be retrieved from Instruction* I but not necessarily I->getType() (scalar for extract-element, and vector for insert-element)

For example, AArch64 TTI requires that Type* val is always vector type (code of asserts), while I->getType() for extract-element is the element type (code of EEI constructor)

For insert-element it should be true, since it's intentional that "there is only one instance of a particular type so that type comparison becomes pointer comparison" (class description of type)

[davidxl]

lgtm

llvm/include/llvm/Analysis/TargetTransformInfo.h

public:
   InstructionCost
   getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                      CmpInst::Predicate VecPred,
                      TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput,
                      const Instruction *I = nullptr) const;
 
   /// \return The expected cost of vector Insert and Extract.
   /// Use -1 to indicate that there is no information on the index value.
+  /// This is used when the instruction is not available; a typical use
+  /// case is to provision the cost of vectorization/scalarization in
+  /// vectorizer passes.
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index = -1) const;
 
+  /// \return The expected cost of vector Insert and Extract.
+  /// This is used when instruction is available, and implementation
+  /// asserts 'I' is not nullptr.
+  ///
+  /// A typical suitable use case is cost estimation when vector instruction
+  /// exists (e.g., from basic blocks during transformation).
+  InstructionCost getVectorInstrCost(const Instruction *I, Type *Val,
+                                     unsigned Index = -1) const;
+
   /// \return The cost of replication shuffle of \p VF elements typed \p EltTy
   /// \p ReplicationFactor times.
   ///
   /// For example, the mask for \p ReplicationFactor=3 and \p VF=4 is:
   ///   <0,0,0,1,1,1,2,2,2,3,3,3>
   InstructionCost getReplicationShuffleCost(Type *EltTy, int ReplicationFactor,
                                             int VF,
                                             const APInt &DemandedDstElts,
virtual InstructionCost getCFInstrCost(unsigned Opcode,
                                          const Instruction *I = nullptr) = 0;
   virtual InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
                                              Type *CondTy,
                                              CmpInst::Predicate VecPred,
                                              TTI::TargetCostKind CostKind,
                                              const Instruction *I) = 0;
   virtual InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                              unsigned Index) = 0;
+  virtual InstructionCost getVectorInstrCost(const Instruction *I, Type *Val,
+                                             unsigned Index) = 0;
 
   virtual InstructionCost
   getReplicationShuffleCost(Type *EltTy, int ReplicationFactor, int VF,
                             const APInt &DemandedDstElts,
                             TTI::TargetCostKind CostKind) = 0;
 
   virtual InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src,
                                           Align Alignment,
InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                      TTI::TargetCostKind CostKind,
                                      const Instruction *I) override {
     return Impl.getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
   }
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index) override {
     return Impl.getVectorInstrCost(Opcode, Val, Index);
   }
+  InstructionCost getVectorInstrCost(const Instruction *I, Type *Val,
+                                     unsigned Index) override {
+    return Impl.getVectorInstrCost(I, Val, Index);
+  }
   InstructionCost
   getReplicationShuffleCost(Type *EltTy, int ReplicationFactor, int VF,
                             const APInt &DemandedDstElts,
                             TTI::TargetCostKind CostKind) override {
     return Impl.getReplicationShuffleCost(EltTy, ReplicationFactor, VF,
                                           DemandedDstElts, CostKind);
   }
   InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
     return 1;
   }
 
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index) const {
     return 1;
   }
 
+  InstructionCost getVectorInstrCost(const Instruction *I, Type *Val,
+                                     unsigned Index) const {
+    return 1;
+  }
+
   unsigned getReplicationShuffleCost(Type *EltTy, int ReplicationFactor, int VF,
                                      const APInt &DemandedDstElts,
                                      TTI::TargetCostKind CostKind) {
     return 1;
   }
 
   InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,
                                   unsigned AddressSpace,
InstructionCost getUserCost(const User *U, ArrayRef<const Value *> Operands,
     case Instruction::InsertElement: {
       auto *IE = dyn_cast<InsertElementInst>(U);
       if (!IE)
         return TTI::TCC_Basic; // FIXME
       unsigned Idx = -1;
       if (auto *CI = dyn_cast<ConstantInt>(IE->getOperand(2)))
         if (CI->getValue().getActiveBits() <= 32)
           Idx = CI->getZExtValue();
-      return TargetTTI->getVectorInstrCost(Opcode, Ty, Idx);
+      return TargetTTI->getVectorInstrCost(IE, Ty, Idx);
     }
     case Instruction::ShuffleVector: {
       auto *Shuffle = dyn_cast<ShuffleVectorInst>(U);
       if (!Shuffle)
         return TTI::TCC_Basic; // FIXME
 
       auto *VecTy = cast<VectorType>(U->getType());
       auto *VecSrcTy = cast<VectorType>(U->getOperand(0)->getType());
case Instruction::ExtractElement: {
       auto *EEI = dyn_cast<ExtractElementInst>(U);
       if (!EEI)
         return TTI::TCC_Basic; // FIXME
       unsigned Idx = -1;
       if (auto *CI = dyn_cast<ConstantInt>(EEI->getOperand(1)))
         if (CI->getValue().getActiveBits() <= 32)
           Idx = CI->getZExtValue();
       Type *DstTy = U->getOperand(0)->getType();
-      return TargetTTI->getVectorInstrCost(Opcode, DstTy, Idx);
+      return TargetTTI->getVectorInstrCost(EEI, DstTy, Idx);
     }
     }
     // By default, just classify everything as 'basic'.
     return TTI::TCC_Basic;
   }
 
   InstructionCost getInstructionLatency(const Instruction *I) {
     SmallVector<const Value *, 4> Operands(I->operand_values());

llvm/include/llvm/CodeGen/BasicTTIImpl.h

public:
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index) {
     std::pair<InstructionCost, MVT> LT =
         getTLI()->getTypeLegalizationCost(DL, Val->getScalarType());
 
     return LT.first;
   }
 
+  InstructionCost getVectorInstrCost(const Instruction *I, Type *Val,
+                                     unsigned Index) {
+    return thisT()->getVectorInstrCost(I->getOpcode(), Val, Index);
+  }
+
   InstructionCost getReplicationShuffleCost(Type *EltTy, int ReplicationFactor,
                                             int VF,
                                             const APInt &DemandedDstElts,
                                             TTI::TargetCostKind CostKind) {
     assert(DemandedDstElts.getBitWidth() == (unsigned)VF * ReplicationFactor &&
            "Unexpected size of DemandedDstElts.");
 
     InstructionCost Cost;

llvm/lib/Analysis/TargetTransformInfo.cpp

InstructionCost Cost =
       TTIImpl->getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
   assert(Cost >= 0 && "TTI should not produce negative costs!");
   return Cost;
 }
 
 InstructionCost TargetTransformInfo::getVectorInstrCost(unsigned Opcode,
                                                         Type *Val,
                                                         unsigned Index) const {
+  // FIXME: Assert that Opcode is either InsertElement or ExtractElement.
+  // This is mentioned in the interface description and respected by all
+  // callers, but never asserted upon.
   InstructionCost Cost = TTIImpl->getVectorInstrCost(Opcode, Val, Index);
   assert(Cost >= 0 && "TTI should not produce negative costs!");
   return Cost;
 }
 
+InstructionCost TargetTransformInfo::getVectorInstrCost(const Instruction *I,
+                                                        Type *Val,
+                                                        unsigned Index) const {
+  assert((I != nullptr) && "Expect not-null instruction pointer");
+  // FIXME: Assert that Opcode is either InsertElement or ExtractElement.
+  // This is mentioned in the interface description and respected by all
+  // callers, but never asserted upon.
+  InstructionCost Cost = TTIImpl->getVectorInstrCost(I, Val, Index);
+  assert(Cost >= 0 && "TTI should not produce negative costs!");
+  return Cost;
+}
+
 InstructionCost TargetTransformInfo::getReplicationShuffleCost(
     Type *EltTy, int ReplicationFactor, int VF, const APInt &DemandedDstElts,
     TTI::TargetCostKind CostKind) {
   InstructionCost Cost = TTIImpl->getReplicationShuffleCost(
       EltTy, ReplicationFactor, VF, DemandedDstElts, CostKind);
   assert(Cost >= 0 && "TTI should not produce negative costs!");
   return Cost;
 }

llvm/lib/CodeGen/CodeGenPrepare.cpp

if (!TLI.allowsMisalignedMemoryAccesses(
       // the extract with the store.
       return false;
     }
 
     // The scalar chain of computation has to pay for the transition
     // scalar to vector.
     // The vector chain has to account for the combining cost.
     InstructionCost ScalarCost =
-        TTI.getVectorInstrCost(Transition->getOpcode(), PromotedType, Index);
+        TTI.getVectorInstrCost(Transition, PromotedType, Index);
     InstructionCost VectorCost = StoreExtractCombineCost;
     enum TargetTransformInfo::TargetCostKind CostKind =
       TargetTransformInfo::TCK_RecipThroughput;
     for (const auto &Inst : InstsToBePromoted) {
       // Compute the cost.
       // By construction, all instructions being promoted are arithmetic ones.
       // Moreover, one argument is a constant that can be viewed as a splat
       // constant.

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    const Instruction *I = nullptr);
 
   InstructionCost getExtractWithExtendCost(unsigned Opcode, Type *Dst,
                                            VectorType *VecTy, unsigned Index);
 
   InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr);
 
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
 
   InstructionCost getMinMaxReductionCost(VectorType *Ty, VectorType *CondTy,
                                          bool IsUnsigned,
                                          TTI::TargetCostKind CostKind);
 
   InstructionCost getArithmeticReductionCostSVE(unsigned Opcode,

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h

InstructionCost getArithmeticInstrCost(
       const Instruction *CxtI = nullptr);
 
   InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr);
 
   bool isInlineAsmSourceOfDivergence(const CallInst *CI,
                                      ArrayRef<unsigned> Indices = {}) const;
 
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *ValTy,
                                      unsigned Index);
   bool isSourceOfDivergence(const Value *V) const;
   bool isAlwaysUniform(const Value *V) const;
 
   unsigned getFlatAddressSpace() const {
     // Don't bother running InferAddressSpaces pass on graphics shaders which
     // don't use flat addressing.

llvm/lib/Target/AMDGPU/R600TargetTransformInfo.h

bool isLegalToVectorizeMemChain(unsigned ChainSizeInBytes, Align Alignment,
                                   unsigned AddrSpace) const;
   bool isLegalToVectorizeLoadChain(unsigned ChainSizeInBytes, Align Alignment,
                                    unsigned AddrSpace) const;
   bool isLegalToVectorizeStoreChain(unsigned ChainSizeInBytes, Align Alignment,
                                     unsigned AddrSpace) const;
   unsigned getMaxInterleaveFactor(unsigned VF);
   InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *ValTy,
                                      unsigned Index);
 };
 
 } // end namespace llvm
 
 #endif // LLVM_LIB_TARGET_AMDGPU_R600TARGETTRANSFORMINFO_H

llvm/lib/Target/ARM/ARMTargetTransformInfo.h

InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    TTI::TargetCostKind CostKind,
                                    const Instruction *I = nullptr);
 
   InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                      CmpInst::Predicate VecPred,
                                      TTI::TargetCostKind CostKind,
                                      const Instruction *I = nullptr);
 
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
 
   InstructionCost getAddressComputationCost(Type *Val, ScalarEvolution *SE,
                                             const SCEV *Ptr);
 
   InstructionCost getArithmeticInstrCost(
       unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,

llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h

InstructionCost getArithmeticInstrCost(
       TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
       TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
       ArrayRef<const Value *> Args = ArrayRef<const Value *>(),
       const Instruction *CxtI = nullptr);
   InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    TTI::CastContextHint CCH,
                                    TTI::TargetCostKind CostKind,
                                    const Instruction *I = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
 
   InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr) {
     return 1;
   }
 

llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h

InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    TTI::TargetCostKind CostKind,
                                    const Instruction *I = nullptr);
   InstructionCost getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind,
                                  const Instruction *I = nullptr);
   InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                      CmpInst::Predicate VecPred,
                                      TTI::TargetCostKind CostKind,
                                      const Instruction *I = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
   InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src,
                                   MaybeAlign Alignment, unsigned AddressSpace,
                                   TTI::TargetCostKind CostKind,
                                   const Instruction *I = nullptr);
   InstructionCost getInterleavedMemoryOpCost(
       unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,

llvm/lib/Target/SystemZ/SystemZTargetTransformInfo.h

public:
   InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    TTI::CastContextHint CCH,
                                    TTI::TargetCostKind CostKind,
                                    const Instruction *I = nullptr);
   InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                      CmpInst::Predicate VecPred,
                                      TTI::TargetCostKind CostKind,
                                      const Instruction *I = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
   bool isFoldableLoad(const LoadInst *Ld, const Instruction *&FoldedValue);
   InstructionCost getMemoryOpCost(unsigned Opcode, Type *Src,
                                   MaybeAlign Alignment, unsigned AddressSpace,
                                   TTI::TargetCostKind CostKind,
                                   const Instruction *I = nullptr);
 

llvm/lib/Target/WebAssembly/WebAssemblyTargetTransformInfo.h

public:
   InstructionCost getArithmeticInstrCost(
       unsigned Opcode, Type *Ty, TTI::TargetCostKind CostKind,
       TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
       TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
       TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
       TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None,
       ArrayRef<const Value *> Args = ArrayRef<const Value *>(),
       const Instruction *CxtI = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
 
   /// @}
 
   bool areInlineCompatible(const Function *Caller,
                            const Function *Callee) const;
 
   bool supportsTailCalls() const;
 };
 
 } // end namespace llvm
 
 #endif

llvm/lib/Target/X86/X86TargetTransformInfo.h

public:
   InstructionCost getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
                                    TTI::CastContextHint CCH,
                                    TTI::TargetCostKind CostKind,
                                    const Instruction *I = nullptr);
   InstructionCost getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                                      CmpInst::Predicate VecPred,
                                      TTI::TargetCostKind CostKind,
                                      const Instruction *I = nullptr);
+  using BaseT::getVectorInstrCost;
   InstructionCost getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index);
   InstructionCost getScalarizationOverhead(VectorType *Ty,
                                            const APInt &DemandedElts,
                                            bool Insert, bool Extract);
   InstructionCost getReplicationShuffleCost(Type *EltTy, int ReplicationFactor,
                                             int VF,
                                             const APInt &DemandedDstElts,

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

for (auto *V : VL) {
                                               EE->getVectorOperandType(), Idx);
           // Add back the cost of s|zext which is subtracted separately.
           Cost += TTIRef.getCastInstrCost(
               Ext->getOpcode(), Ext->getType(), EE->getType(),
               TTI::getCastContextHint(Ext), CostKind, Ext);
           continue;
         }
       }
-      Cost -= TTIRef.getVectorInstrCost(Instruction::ExtractElement,
-                                        EE->getVectorOperandType(), Idx);
+      Cost -= TTIRef.getVectorInstrCost(EE, EE->getVectorOperandType(), Idx);
     }
     // Add a cost for subvector extracts/inserts if required.
     for (const auto &Data : ExtractVectorsTys) {
       auto *EEVTy = cast<FixedVectorType>(Data.first->getType());
       unsigned NumElts = VecTy->getNumElements();
       if (Data.second % NumElts == 0)
         continue;
       if (TTIRef.getNumberOfParts(EEVTy) > TTIRef.getNumberOfParts(VecTy)) {
switch (ShuffleOrOp) {
     case Instruction::ExtractElement: {
       // The common cost of removal ExtractElement/ExtractValue instructions +
       // the cost of shuffles, if required to resuffle the original vector.
       if (NeedToShuffleReuses) {
         unsigned Idx = 0;
         for (unsigned I : E->ReuseShuffleIndices) {
           if (ShuffleOrOp == Instruction::ExtractElement) {
             auto *EE = cast<ExtractElementInst>(VL[I]);
-            CommonCost -= TTI->getVectorInstrCost(Instruction::ExtractElement,
-                                                  EE->getVectorOperandType(),
-                                                  *getExtractIndex(EE));
+            CommonCost -= TTI->getVectorInstrCost(
+                EE, EE->getVectorOperandType(), *getExtractIndex(EE));
           } else {
             CommonCost -= TTI->getVectorInstrCost(Instruction::ExtractElement,
                                                   VecTy, Idx);
             ++Idx;
           }
         }
         Idx = EntryVF;
         for (Value *V : VL) {
           if (ShuffleOrOp == Instruction::ExtractElement) {
             auto *EE = cast<ExtractElementInst>(V);
-            CommonCost += TTI->getVectorInstrCost(Instruction::ExtractElement,
-                                                  EE->getVectorOperandType(),
-                                                  *getExtractIndex(EE));
+            CommonCost += TTI->getVectorInstrCost(
+                EE, EE->getVectorOperandType(), *getExtractIndex(EE));
           } else {
             --Idx;
             CommonCost += TTI->getVectorInstrCost(Instruction::ExtractElement,
                                                   VecTy, Idx);
           }
         }
       }
       if (ShuffleOrOp == Instruction::ExtractValue) {

llvm/lib/Transforms/Vectorize/VectorCombine.cpp

ExtractElementInst *VectorCombine::getShuffleExtract(
   unsigned Index1 = Index1C->getZExtValue();
 
   // If the extract indexes are identical, no shuffle is needed.
   if (Index0 == Index1)
     return nullptr;
 
   Type *VecTy = Ext0->getVectorOperand()->getType();
   assert(VecTy == Ext1->getVectorOperand()->getType() && "Need matching types");
-  InstructionCost Cost0 =
-      TTI.getVectorInstrCost(Ext0->getOpcode(), VecTy, Index0);
-  InstructionCost Cost1 =
-      TTI.getVectorInstrCost(Ext1->getOpcode(), VecTy, Index1);
+  InstructionCost Cost0 = TTI.getVectorInstrCost(Ext0, VecTy, Index0);
+  InstructionCost Cost1 = TTI.getVectorInstrCost(Ext1, VecTy, Index1);
 
   // If both costs are invalid no shuffle is needed
   if (!Cost0.isValid() && !Cost1.isValid())
     return nullptr;
 
   // We are extracting from 2 different indexes, so one operand must be shuffled
   // before performing a vector operation and/or extract. The more expensive
   // extract will be replaced by a shuffle.
VectorOpCost = TTI.getCmpSelInstrCost(
         Opcode, VecTy, CmpInst::makeCmpResultType(VecTy), Pred);
   }
 
   // Get cost estimates for the extract elements. These costs will factor into
   // both sequences.
   unsigned Ext0Index = Ext0IndexC->getZExtValue();
   unsigned Ext1Index = Ext1IndexC->getZExtValue();
 
-  InstructionCost Extract0Cost =
-      TTI.getVectorInstrCost(Instruction::ExtractElement, VecTy, Ext0Index);
-  InstructionCost Extract1Cost =
-      TTI.getVectorInstrCost(Instruction::ExtractElement, VecTy, Ext1Index);
+  InstructionCost Extract0Cost = TTI.getVectorInstrCost(Ext0, VecTy, Ext0Index);
+  InstructionCost Extract1Cost = TTI.getVectorInstrCost(Ext1, VecTy, Ext1Index);
 
   // A more expensive extract will always be replaced by a splat shuffle.
   // For example, if Ext0 is more expensive:
   // opcode (extelt V0, Ext0), (ext V1, Ext1) -->
   // extelt (opcode (splat V0, Ext0), V1), Ext1
   // TODO: Evaluate whether that always results in lowest cost. Alternatively,
   //       check the cost of creating a broadcast shuffle and shuffling both
   //       operands to element 0.
bool VectorCombine::foldExtractedCmps(Instruction &I) {
   // binop i1 (cmp Pred (ext X, Index0), C0), (cmp Pred (ext X, Index1), C1)
   CmpInst::Predicate Pred = P0;
   unsigned CmpOpcode = CmpInst::isFPPredicate(Pred) ? Instruction::FCmp
                                                     : Instruction::ICmp;
   auto *VecTy = dyn_cast<FixedVectorType>(X->getType());
   if (!VecTy)
     return false;
 
-  InstructionCost OldCost =
-      TTI.getVectorInstrCost(Ext0->getOpcode(), VecTy, Index0);
-  OldCost += TTI.getVectorInstrCost(Ext1->getOpcode(), VecTy, Index1);
+  InstructionCost OldCost = TTI.getVectorInstrCost(Ext0, VecTy, Index0);
+  OldCost += TTI.getVectorInstrCost(Ext1, VecTy, Index1);
   OldCost +=
       TTI.getCmpSelInstrCost(CmpOpcode, I0->getType(),
                              CmpInst::makeCmpResultType(I0->getType()), Pred) *
       2;
   OldCost += TTI.getArithmeticInstrCost(I.getOpcode(), I.getType());
 
   // The proposed vector pattern is:
   // vcmp = cmp Pred X, VecC
   // ext (binop vNi1 vcmp, (shuffle vcmp, Index1)), Index0
   int CheapIndex = ConvertToShuf == Ext0 ? Index1 : Index0;
   int ExpensiveIndex = ConvertToShuf == Ext0 ? Index0 : Index1;
   auto *CmpTy = cast<FixedVectorType>(CmpInst::makeCmpResultType(X->getType()));
   InstructionCost NewCost = TTI.getCmpSelInstrCost(
       CmpOpcode, X->getType(), CmpInst::makeCmpResultType(X->getType()), Pred);
   SmallVector<int, 32> ShufMask(VecTy->getNumElements(), UndefMaskElem);
   ShufMask[CheapIndex] = ExpensiveIndex;
   NewCost += TTI.getShuffleCost(TargetTransformInfo::SK_PermuteSingleSrc, CmpTy,
                                 ShufMask);
   NewCost += TTI.getArithmeticInstrCost(I.getOpcode(), CmpTy);
-  NewCost += TTI.getVectorInstrCost(Ext0->getOpcode(), CmpTy, CheapIndex);
+  NewCost += TTI.getVectorInstrCost(Ext0, CmpTy, CheapIndex);
 
   // Aggressively form vector ops if the cost is equal because the transform
   // may enable further optimization.
   // Codegen can reverse this transform (scalarize) if it was not profitable.
   if (OldCost < NewCost || !NewCost.isValid())
     return false;
 
   // Create a vector constant from the 2 scalar constants.

llvm/test/Analysis/CostModel/AArch64/kryo.ll

define void @vectorInstrCost() {
 
     ; Vector inserts - inserting the first element should have a zero cost; all
     ; other elements should have a cost of two.
     ;
     ; CHECK: cost of 0 {{.*}} insertelement <2 x i64> undef, i64 undef, i32 0
     ; CHECK: cost of 2 {{.*}} insertelement <2 x i64> undef, i64 undef, i32 1
     %t3 = insertelement <2 x i64> undef, i64 undef, i32 0
     %t4 = insertelement <2 x i64> undef, i64 undef, i32 1
-
     ret void
 }
 
 ; CHECK-LABEL: vectorInstrExtractCost
 define i64 @vectorInstrExtractCost(<4 x i64> %vecreg) {
-    
-    ; Vector extracts - extracting each element at index 0 is considered
-    ; free in the current implementation. When extracting element at index
-    ; 2, 2 is rounded to 0, so extracting element at index 2 has cost 0 as 
-    ; well.
-    ;
     ; CHECK: cost of 2 {{.*}} extractelement <4 x i64> %vecreg, i32 1
     ; CHECK: cost of 0 {{.*}} extractelement <4 x i64> %vecreg, i32 2
     %t1 = extractelement <4 x i64> %vecreg, i32 1
     %t2 = extractelement <4 x i64> %vecreg, i32 2
     %ele = add i64 %t2, 1
     %cond = icmp eq i64 %t1, %ele
 
+    ; Vector extracts - extracting each element should have a cost
+    ; if they are used as integers.
+    ;
     ; CHECK: cost of 0 {{.*}} extractelement <4 x i64> %vecreg, i32 0
     ; CHECK: cost of 2 {{.*}} extractelement <4 x i64> %vecreg, i32 3
     %t0 = extractelement <4 x i64> %vecreg, i32 0
     %t3 = extractelement <4 x i64> %vecreg, i32 3
     %val = select i1 %cond, i64 %t0 , i64 %t3
 
     ret i64 %val
 }