[NFC] Introduce a helper in BasicTTIImpl.h to cast to T

[gchatelet]

Summary

This patch makes access to this as a T uniform accross the file.

llvm/include/llvm/CodeGen/BasicTTIImpl.h

 /// We need these methods implemented in the derived class so that this class
 /// doesn't have to duplicate storage for them.
 template <typename T>
 class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
 private:
   using BaseT = TargetTransformInfoImplCRTPBase<T>;
   using TTI = TargetTransformInfo;
 
+  /// Helper function to access this as a T.
+  T *thisT() { return static_cast<T *>(this); }
+
   /// Estimate a cost of Broadcast as an extract and sequence of insert
   /// operations.
   unsigned getBroadcastShuffleOverhead(FixedVectorType *VTy) {
     unsigned Cost = 0;
     // Broadcast cost is equal to the cost of extracting the zero'th element
     // plus the cost of inserting it into every element of the result vector.
-    Cost += static_cast<T *>(this)->getVectorInstrCost(
-        Instruction::ExtractElement, VTy, 0);
+    Cost += thisT()->getVectorInstrCost(Instruction::ExtractElement, VTy, 0);
 
     for (int i = 0, e = VTy->getNumElements(); i < e; ++i) {
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::InsertElement, VTy, i);
+      Cost += thisT()->getVectorInstrCost(Instruction::InsertElement, VTy, i);
     }
     return Cost;
   }
 
   /// Estimate a cost of shuffle as a sequence of extract and insert
   /// operations.
   unsigned getPermuteShuffleOverhead(FixedVectorType *VTy) {
     unsigned Cost = 0;
     // Shuffle cost is equal to the cost of extracting element from its argument
     // plus the cost of inserting them onto the result vector.
 
     // e.g. <4 x float> has a mask of <0,5,2,7> i.e we need to extract from
     // index 0 of first vector, index 1 of second vector,index 2 of first
     // vector and finally index 3 of second vector and insert them at index
     // <0,1,2,3> of result vector.
     for (int i = 0, e = VTy->getNumElements(); i < e; ++i) {
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::InsertElement, VTy, i);
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::ExtractElement, VTy, i);
+      Cost += thisT()->getVectorInstrCost(Instruction::InsertElement, VTy, i);
+      Cost += thisT()->getVectorInstrCost(Instruction::ExtractElement, VTy, i);
     }
     return Cost;
   }
 
   /// Estimate a cost of subvector extraction as a sequence of extract and
   /// insert operations.
   unsigned getExtractSubvectorOverhead(FixedVectorType *VTy, int Index,
                                        FixedVectorType *SubVTy) {
     assert(VTy && SubVTy &&
            "Can only extract subvectors from vectors");
     int NumSubElts = SubVTy->getNumElements();
     assert((Index + NumSubElts) <= (int)VTy->getNumElements() &&
            "SK_ExtractSubvector index out of range");
 
     unsigned Cost = 0;
     // Subvector extraction cost is equal to the cost of extracting element from
     // the source type plus the cost of inserting them into the result vector
     // type.
     for (int i = 0; i != NumSubElts; ++i) {
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::ExtractElement, VTy, i + Index);
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::InsertElement, SubVTy, i);
+      Cost += thisT()->getVectorInstrCost(Instruction::ExtractElement, VTy,
+                                          i + Index);
+      Cost +=
+          thisT()->getVectorInstrCost(Instruction::InsertElement, SubVTy, i);
     }
     return Cost;
   }
 
   /// Estimate a cost of subvector insertion as a sequence of extract and
   /// insert operations.
   unsigned getInsertSubvectorOverhead(FixedVectorType *VTy, int Index,
                                       FixedVectorType *SubVTy) {
     assert(VTy && SubVTy &&
            "Can only insert subvectors into vectors");
     int NumSubElts = SubVTy->getNumElements();
     assert((Index + NumSubElts) <= (int)VTy->getNumElements() &&
            "SK_InsertSubvector index out of range");
 
     unsigned Cost = 0;
     // Subvector insertion cost is equal to the cost of extracting element from
     // the source type plus the cost of inserting them into the result vector
     // type.
     for (int i = 0; i != NumSubElts; ++i) {
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::ExtractElement, SubVTy, i);
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::InsertElement, VTy, i + Index);
+      Cost +=
+          thisT()->getVectorInstrCost(Instruction::ExtractElement, SubVTy, i);
+      Cost += thisT()->getVectorInstrCost(Instruction::InsertElement, VTy,
+                                          i + Index);
     }
     return Cost;
   }
 
   /// Local query method delegates up to T which *must* implement this!
   const TargetSubtargetInfo *getST() const {
     return static_cast<const T *>(this)->getST();
   }
void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
     else
       return;
 
     // Scan the loop: don't unroll loops with calls.
     for (BasicBlock *BB : L->blocks()) {
       for (Instruction &I : *BB) {
         if (isa<CallInst>(I) || isa<InvokeInst>(I)) {
           if (const Function *F = cast<CallBase>(I).getCalledFunction()) {
-            if (!static_cast<T *>(this)->isLoweredToCall(F))
+            if (!thisT()->isLoweredToCall(F))
               continue;
           }
 
           return;
         }
       }
     }
 
assert(DemandedElts.getBitWidth() == Ty->getNumElements() &&
            "Vector size mismatch");
 
     unsigned Cost = 0;
 
     for (int i = 0, e = Ty->getNumElements(); i < e; ++i) {
       if (!DemandedElts[i])
         continue;
       if (Insert)
-        Cost += static_cast<T *>(this)->getVectorInstrCost(
-            Instruction::InsertElement, Ty, i);
+        Cost += thisT()->getVectorInstrCost(Instruction::InsertElement, Ty, i);
       if (Extract)
-        Cost += static_cast<T *>(this)->getVectorInstrCost(
-            Instruction::ExtractElement, Ty, i);
+        Cost += thisT()->getVectorInstrCost(Instruction::ExtractElement, Ty, i);
     }
 
     return Cost;
   }
 
   /// Helper wrapper for the DemandedElts variant of getScalarizationOverhead.
   unsigned getScalarizationOverhead(VectorType *InTy, bool Insert,
                                     bool Extract) {
     auto *Ty = cast<FixedVectorType>(InTy);
 
     APInt DemandedElts = APInt::getAllOnesValue(Ty->getNumElements());
-    return static_cast<T *>(this)->getScalarizationOverhead(Ty, DemandedElts,
-                                                            Insert, Extract);
+    return thisT()->getScalarizationOverhead(Ty, DemandedElts, Insert, Extract);
   }
 
   /// Estimate the overhead of scalarizing an instructions unique
   /// non-constant operands. The types of the arguments are ordinarily
   /// scalar, in which case the costs are multiplied with VF.
   unsigned getOperandsScalarizationOverhead(ArrayRef<const Value *> Args,
                                             unsigned VF) {
     unsigned Cost = 0;
if (!TLI->isOperationExpand(ISD, LT.second)) {
       return LT.first * 2 * OpCost;
     }
 
     // Else, assume that we need to scalarize this op.
     // TODO: If one of the types get legalized by splitting, handle this
     // similarly to what getCastInstrCost() does.
     if (auto *VTy = dyn_cast<VectorType>(Ty)) {
       unsigned Num = cast<FixedVectorType>(VTy)->getNumElements();
-      unsigned Cost = static_cast<T *>(this)->getArithmeticInstrCost(
+      unsigned Cost = thisT()->getArithmeticInstrCost(
           Opcode, VTy->getScalarType(), CostKind);
       // Return the cost of multiple scalar invocation plus the cost of
       // inserting and extracting the values.
       return getScalarizationOverhead(VTy, Args) + Num * Cost;
     }
 
     // We don't know anything about this scalar instruction.
     return OpCost;
if (DstVTy && SrcVTy) {
         return SplitCost +
                (2 * TTI->getCastInstrCost(Opcode, SplitDstTy, SplitSrcTy,
                                           CostKind, I));
       }
 
       // In other cases where the source or destination are illegal, assume
       // the operation will get scalarized.
       unsigned Num = cast<FixedVectorType>(DstVTy)->getNumElements();
-      unsigned Cost = static_cast<T *>(this)->getCastInstrCost(
-          Opcode, Dst->getScalarType(), Src->getScalarType(),
-          CostKind, I);
+      unsigned Cost = thisT()->getCastInstrCost(
+          Opcode, Dst->getScalarType(), Src->getScalarType(), CostKind, I);
 
       // Return the cost of multiple scalar invocation plus the cost of
       // inserting and extracting the values.
       return getScalarizationOverhead(DstVTy, true, true) + Num * Cost;
     }
 
     // We already handled vector-to-vector and scalar-to-scalar conversions.
     // This
     // is where we handle bitcast between vectors and scalars. We need to assume
     //  that the conversion is scalarized in one way or another.
     if (Opcode == Instruction::BitCast) {
       // Illegal bitcasts are done by storing and loading from a stack slot.
       return (SrcVTy ? getScalarizationOverhead(SrcVTy, false, true) : 0) +
              (DstVTy ? getScalarizationOverhead(DstVTy, true, false) : 0);
     }
 
     llvm_unreachable("Unhandled cast");
   }
 
   unsigned getExtractWithExtendCost(unsigned Opcode, Type *Dst,
                                     VectorType *VecTy, unsigned Index) {
-    return static_cast<T *>(this)->getVectorInstrCost(
-               Instruction::ExtractElement, VecTy, Index) +
-           static_cast<T *>(this)->getCastInstrCost(Opcode, Dst,
-                                                    VecTy->getElementType(),
-                                                    TTI::TCK_RecipThroughput);
+    return thisT()->getVectorInstrCost(Instruction::ExtractElement, VecTy,
+                                       Index) +
+           thisT()->getCastInstrCost(Opcode, Dst, VecTy->getElementType(),
   }
 
   unsigned getCFInstrCost(unsigned Opcode, TTI::TargetCostKind CostKind) {
     return BaseT::getCFInstrCost(Opcode, CostKind);
   }
 
   unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
                               TTI::TargetCostKind CostKind,
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
 
     // Otherwise, assume that the cast is scalarized.
     // TODO: If one of the types get legalized by splitting, handle this
     // similarly to what getCastInstrCost() does.
     if (auto *ValVTy = dyn_cast<VectorType>(ValTy)) {
       unsigned Num = cast<FixedVectorType>(ValVTy)->getNumElements();
       if (CondTy)
         CondTy = CondTy->getScalarType();
-      unsigned Cost = static_cast<T *>(this)->getCmpSelInstrCost(
+      unsigned Cost = thisT()->getCmpSelInstrCost(
           Opcode, ValVTy->getScalarType(), CondTy, CostKind, I);
 
       // Return the cost of multiple scalar invocation plus the cost of
       // inserting and extracting the values.
       return getScalarizationOverhead(ValVTy, true, false) + Num * Cost;
     }
 
     // Unknown scalar opcode.
unsigned getInterleavedMemoryOpCost(
     assert(Factor > 1 && NumElts % Factor == 0 && "Invalid interleave factor");
 
     unsigned NumSubElts = NumElts / Factor;
     auto *SubVT = FixedVectorType::get(VT->getElementType(), NumSubElts);
 
     // Firstly, the cost of load/store operation.
     unsigned Cost;
     if (UseMaskForCond || UseMaskForGaps)
-      Cost = static_cast<T *>(this)->getMaskedMemoryOpCost(
-          Opcode, VecTy, Alignment, AddressSpace, CostKind);
+      Cost = thisT()->getMaskedMemoryOpCost(Opcode, VecTy, Alignment,
+                                            AddressSpace, CostKind);
     else
-      Cost = static_cast<T *>(this)->getMemoryOpCost(
-          Opcode, VecTy, Alignment, AddressSpace, CostKind);
+      Cost = thisT()->getMemoryOpCost(Opcode, VecTy, Alignment, AddressSpace,
+                                      CostKind);
 
     // Legalize the vector type, and get the legalized and unlegalized type
     // sizes.
     MVT VecTyLT = getTLI()->getTypeLegalizationCost(DL, VecTy).second;
-    unsigned VecTySize =
-        static_cast<T *>(this)->getDataLayout().getTypeStoreSize(VecTy);
+    unsigned VecTySize = thisT()->getDataLayout().getTypeStoreSize(VecTy);
     unsigned VecTyLTSize = VecTyLT.getStoreSize();
 
     // Return the ceiling of dividing A by B.
     auto ceil = [](unsigned A, unsigned B) { return (A + B - 1) / B; };
 
     // Scale the cost of the memory operation by the fraction of legalized
     // instructions that will actually be used. We shouldn't account for the
     // cost of dead instructions since they will be removed.
if (Opcode == Instruction::Load) {
       assert(Indices.size() <= Factor &&
              "Interleaved memory op has too many members");
 
       for (unsigned Index : Indices) {
         assert(Index < Factor && "Invalid index for interleaved memory op");
 
         // Extract elements from loaded vector for each sub vector.
         for (unsigned i = 0; i < NumSubElts; i++)
-          Cost += static_cast<T *>(this)->getVectorInstrCost(
-              Instruction::ExtractElement, VT, Index + i * Factor);
+          Cost += thisT()->getVectorInstrCost(Instruction::ExtractElement, VT,
+                                              Index + i * Factor);
       }
 
       unsigned InsSubCost = 0;
       for (unsigned i = 0; i < NumSubElts; i++)
-        InsSubCost += static_cast<T *>(this)->getVectorInstrCost(
-            Instruction::InsertElement, SubVT, i);
+        InsSubCost +=
+            thisT()->getVectorInstrCost(Instruction::InsertElement, SubVT, i);
 
       Cost += Indices.size() * InsSubCost;
     } else {
       // The interleave cost is extract all elements from sub vectors, and
       // insert them into the wide vector.
       //
       // E.g. An interleaved store of factor 2:
       //      %v0_v1 = shuffle %v0, %v1, <0, 4, 1, 5, 2, 6, 3, 7>
       //      store <8 x i32> %interleaved.vec, <8 x i32>* %ptr
       // The cost is estimated as extract all elements from both <4 x i32>
       // vectors and insert into the <8 x i32> vector.
 
       unsigned ExtSubCost = 0;
       for (unsigned i = 0; i < NumSubElts; i++)
-        ExtSubCost += static_cast<T *>(this)->getVectorInstrCost(
-            Instruction::ExtractElement, SubVT, i);
+        ExtSubCost +=
+            thisT()->getVectorInstrCost(Instruction::ExtractElement, SubVT, i);
       Cost += ExtSubCost * Factor;
 
       for (unsigned i = 0; i < NumElts; i++)
         Cost += static_cast<T *>(this)
                     ->getVectorInstrCost(Instruction::InsertElement, VT, i);
     }
 
     if (!UseMaskForCond)
unsigned getInterleavedMemoryOpCost(
     // E.g. an interleaved group with factor 3:
     //    %mask = icmp ult <8 x i32> %vec1, %vec2
     //    %interleaved.mask = shufflevector <8 x i1> %mask, <8 x i1> undef,
     //        <24 x i32> <0,0,0,1,1,1,2,2,2,3,3,3,4,4,4,5,5,5,6,6,6,7,7,7>
     // The cost is estimated as extract all mask elements from the <8xi1> mask
     // vector and insert them factor times into the <24xi1> shuffled mask
     // vector.
     for (unsigned i = 0; i < NumSubElts; i++)
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::ExtractElement, SubVT, i);
+      Cost +=
+          thisT()->getVectorInstrCost(Instruction::ExtractElement, SubVT, i);
 
     for (unsigned i = 0; i < NumElts; i++)
-      Cost += static_cast<T *>(this)->getVectorInstrCost(
-          Instruction::InsertElement, MaskVT, i);
+      Cost +=
+          thisT()->getVectorInstrCost(Instruction::InsertElement, MaskVT, i);
 
     // The Gaps mask is invariant and created outside the loop, therefore the
     // cost of creating it is not accounted for here. However if we have both
     // a MaskForGaps and some other mask that guards the execution of the
     // memory access, we need to account for the cost of And-ing the two masks
     // inside the loop.
     if (UseMaskForGaps)
-      Cost += static_cast<T *>(this)->getArithmeticInstrCost(
-          BinaryOperator::And, MaskVT, CostKind);
+      Cost += thisT()->getArithmeticInstrCost(BinaryOperator::And, MaskVT,
+                                              CostKind);
 
     return Cost;
   }
 
   /// Get intrinsic cost based on arguments.
   unsigned getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                  TTI::TargetCostKind CostKind) {
     Intrinsic::ID IID = ICA.getID();
-    auto *ConcreteTTI = static_cast<T *>(this);
 
     // Special case some scalar intrinsics.
     if (CostKind != TTI::TCK_RecipThroughput) {
       switch (IID) {
       default:
         break;
       case Intrinsic::cttz:
         if (getTLI()->isCheapToSpeculateCttz())
           return TargetTransformInfo::TCC_Basic;
         break;
       case Intrinsic::ctlz:
         if (getTLI()->isCheapToSpeculateCtlz())
           return TargetTransformInfo::TCC_Basic;
         break;
       case Intrinsic::memcpy:
-        return ConcreteTTI->getMemcpyCost(ICA.getInst());
+        return thisT()->getMemcpyCost(ICA.getInst());
         // TODO: other libc intrinsics.
       }
       return BaseT::getIntrinsicInstrCost(ICA, CostKind);
     }
 
     if (BaseT::getIntrinsicInstrCost(ICA, CostKind) == 0)
       return 0;
 
     // TODO: Combine these two logic paths.
default: {
         if (!RetTy->isVoidTy())
           ScalarizationCost +=
               getScalarizationOverhead(cast<VectorType>(RetTy), true, false);
         ScalarizationCost += getOperandsScalarizationOverhead(Args, VF);
       }
 
       IntrinsicCostAttributes Attrs(IID, RetTy, Types, FMF,
                                     ScalarizationCost, I);
-      return ConcreteTTI->getIntrinsicInstrCost(Attrs, CostKind);
+      return thisT()->getIntrinsicInstrCost(Attrs, CostKind);
     }
     case Intrinsic::masked_scatter: {
       assert(VF == 1 && "Can't vectorize types here.");
       const Value *Mask = Args[3];
       bool VarMask = !isa<Constant>(Mask);
       Align Alignment = cast<ConstantInt>(Args[2])->getAlignValue();
-      return ConcreteTTI->getGatherScatterOpCost(Instruction::Store,
-                                                 Args[0]->getType(), Args[1],
-                                                 VarMask, Alignment, CostKind,
-                                                 I);
+      return thisT()->getGatherScatterOpCost(Instruction::Store,
+                                             VarMask, Alignment, CostKind, I);
     }
     case Intrinsic::masked_gather: {
       assert(VF == 1 && "Can't vectorize types here.");
       const Value *Mask = Args[2];
       bool VarMask = !isa<Constant>(Mask);
       Align Alignment = cast<ConstantInt>(Args[1])->getAlignValue();
-      return ConcreteTTI->getGatherScatterOpCost(
-          Instruction::Load, RetTy, Args[0], VarMask, Alignment, CostKind, I);
+      return thisT()->getGatherScatterOpCost(Instruction::Load, RetTy, Args[0],
+                                             VarMask, Alignment, CostKind, I);
     }
     case Intrinsic::experimental_vector_reduce_add:
     case Intrinsic::experimental_vector_reduce_mul:
     case Intrinsic::experimental_vector_reduce_and:
     case Intrinsic::experimental_vector_reduce_or:
     case Intrinsic::experimental_vector_reduce_xor:
     case Intrinsic::experimental_vector_reduce_v2_fadd:
     case Intrinsic::experimental_vector_reduce_v2_fmul:
case Intrinsic::fshr: {
       TTI::OperandValueKind OpKindY = TTI::getOperandInfo(Y, OpPropsY);
       TTI::OperandValueKind OpKindZ = TTI::getOperandInfo(Z, OpPropsZ);
       TTI::OperandValueKind OpKindBW = TTI::OK_UniformConstantValue;
       OpPropsBW = isPowerOf2_32(RetTy->getScalarSizeInBits()) ? TTI::OP_PowerOf2
                                                               : TTI::OP_None;
       // fshl: (X << (Z % BW)) | (Y >> (BW - (Z % BW)))
       // fshr: (X << (BW - (Z % BW))) | (Y >> (Z % BW))
       unsigned Cost = 0;
-      Cost += ConcreteTTI->getArithmeticInstrCost(BinaryOperator::Or, RetTy,
-                                                  CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(BinaryOperator::Sub, RetTy,
-                                                  CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(BinaryOperator::Shl, RetTy,
-                                                  CostKind,
-                                                  OpKindX, OpKindZ, OpPropsX);
-      Cost += ConcreteTTI->getArithmeticInstrCost(BinaryOperator::LShr, RetTy,
-                                                  CostKind,
-                                                  OpKindY, OpKindZ, OpPropsY);
+      Cost +=
+          thisT()->getArithmeticInstrCost(BinaryOperator::Or, RetTy, CostKind);
+      Cost +=
+          thisT()->getArithmeticInstrCost(BinaryOperator::Sub, RetTy, CostKind);
+      Cost += thisT()->getArithmeticInstrCost(
+          BinaryOperator::Shl, RetTy, CostKind, OpKindX, OpKindZ, OpPropsX);
+      Cost += thisT()->getArithmeticInstrCost(
+          BinaryOperator::LShr, RetTy, CostKind, OpKindY, OpKindZ, OpPropsY);
       // Non-constant shift amounts requires a modulo.
       if (OpKindZ != TTI::OK_UniformConstantValue &&
           OpKindZ != TTI::OK_NonUniformConstantValue)
-        Cost += ConcreteTTI->getArithmeticInstrCost(BinaryOperator::URem, RetTy,
-                                                    CostKind,
-                                                    OpKindZ, OpKindBW, OpPropsZ,
-                                                    OpPropsBW);
+        Cost += thisT()->getArithmeticInstrCost(BinaryOperator::URem, RetTy,
+                                                CostKind, OpKindZ, OpKindBW,
+                                                OpPropsZ, OpPropsBW);
       // For non-rotates (X != Y) we must add shift-by-zero handling costs.
       if (X != Y) {
         Type *CondTy = RetTy->getWithNewBitWidth(1);
-        Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy,
-                                                CondTy, CostKind);
-        Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
-                                                CondTy, CostKind);
+        Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+                                            CostKind);
+        Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
       }
       return Cost;
     }
     }
   }
 
   /// Get intrinsic cost based on argument types.
   /// If ScalarizationCostPassed is std::numeric_limits<unsigned>::max(), the
   /// cost of scalarizing the arguments and the return value will be computed
   /// based on types.
   unsigned getTypeBasedIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                           TTI::TargetCostKind CostKind) {
-
-    auto *ConcreteTTI = static_cast<T *>(this);
-
     Intrinsic::ID IID = ICA.getID();
     Type *RetTy = ICA.getReturnType();
     const SmallVectorImpl<Type *> &Tys = ICA.getArgTypes();
     FastMathFlags FMF = ICA.getFlags();
     unsigned ScalarizationCostPassed = ICA.getScalarizationCost();
     bool SkipScalarizationCost = ICA.skipScalarizationCost();
 
     auto *VecOpTy = Tys.empty() ? nullptr : dyn_cast<VectorType>(Tys[0]);
default: {
         }
         ScalarTys.push_back(Ty);
       }
       if (ScalarCalls == 1)
         return 1; // Return cost of a scalar intrinsic. Assume it to be cheap.
 
       IntrinsicCostAttributes ScalarAttrs(IID, ScalarRetTy, ScalarTys, FMF);
       unsigned ScalarCost =
-          ConcreteTTI->getIntrinsicInstrCost(ScalarAttrs, CostKind);
+          thisT()->getIntrinsicInstrCost(ScalarAttrs, CostKind);
 
       return ScalarCalls * ScalarCost + ScalarizationCost;
     }
     // Look for intrinsics that can be lowered directly or turned into a scalar
     // intrinsic call.
     case Intrinsic::sqrt:
       ISDs.push_back(ISD::FSQRT);
       break;
case Intrinsic::experimental_constrained_fmuladd:
       break;
     // FIXME: We should return 0 whenever getIntrinsicCost == TCC_Free.
     case Intrinsic::lifetime_start:
     case Intrinsic::lifetime_end:
     case Intrinsic::sideeffect:
       return 0;
     case Intrinsic::masked_store: {
       Type *Ty = Tys[0];
-      Align TyAlign = ConcreteTTI->DL.getABITypeAlign(Ty);
-      return ConcreteTTI->getMaskedMemoryOpCost(Instruction::Store, Ty, TyAlign,
-                                                0, CostKind);
+      Align TyAlign = thisT()->DL.getABITypeAlign(Ty);
+      return thisT()->getMaskedMemoryOpCost(Instruction::Store, Ty, TyAlign, 0,
+                                            CostKind);
     }
     case Intrinsic::masked_load: {
       Type *Ty = RetTy;
-      Align TyAlign = ConcreteTTI->DL.getABITypeAlign(Ty);
-      return ConcreteTTI->getMaskedMemoryOpCost(Instruction::Load, Ty, TyAlign,
-                                                0, CostKind);
+      Align TyAlign = thisT()->DL.getABITypeAlign(Ty);
+      return thisT()->getMaskedMemoryOpCost(Instruction::Load, Ty, TyAlign, 0,
+                                            CostKind);
     }
     case Intrinsic::experimental_vector_reduce_add:
-      return ConcreteTTI->getArithmeticReductionCost(Instruction::Add, VecOpTy,
-                                                     /*IsPairwiseForm=*/false,
-                                                     CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::Add, VecOpTy,
     case Intrinsic::experimental_vector_reduce_mul:
-      return ConcreteTTI->getArithmeticReductionCost(Instruction::Mul, VecOpTy,
-                                                     /*IsPairwiseForm=*/false,
-                                                     CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::Mul, VecOpTy,
     case Intrinsic::experimental_vector_reduce_and:
-      return ConcreteTTI->getArithmeticReductionCost(Instruction::And, VecOpTy,
-                                                     /*IsPairwiseForm=*/false,
-                                                     CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::And, VecOpTy,
     case Intrinsic::experimental_vector_reduce_or:
-      return ConcreteTTI->getArithmeticReductionCost(Instruction::Or, VecOpTy,
-                                                     /*IsPairwiseForm=*/false,
-                                                     CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::Or, VecOpTy,
     case Intrinsic::experimental_vector_reduce_xor:
-      return ConcreteTTI->getArithmeticReductionCost(Instruction::Xor, VecOpTy,
-                                                     /*IsPairwiseForm=*/false,
-                                                     CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::Xor, VecOpTy,
     case Intrinsic::experimental_vector_reduce_v2_fadd:
       // FIXME: Add new flag for cost of strict reductions.
-      return ConcreteTTI->getArithmeticReductionCost(
-          Instruction::FAdd, VecOpTy,
-          /*IsPairwiseForm=*/false, CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::FAdd, VecOpTy,
+                                                 /*IsPairwiseForm=*/false,
+                                                 CostKind);
     case Intrinsic::experimental_vector_reduce_v2_fmul:
       // FIXME: Add new flag for cost of strict reductions.
-      return ConcreteTTI->getArithmeticReductionCost(
-          Instruction::FMul, VecOpTy,
-          /*IsPairwiseForm=*/false, CostKind);
+      return thisT()->getArithmeticReductionCost(Instruction::FMul, VecOpTy,
+                                                 /*IsPairwiseForm=*/false,
+                                                 CostKind);
     case Intrinsic::experimental_vector_reduce_smax:
     case Intrinsic::experimental_vector_reduce_smin:
     case Intrinsic::experimental_vector_reduce_fmax:
     case Intrinsic::experimental_vector_reduce_fmin:
-      return ConcreteTTI->getMinMaxReductionCost(
+      return thisT()->getMinMaxReductionCost(
           VecOpTy, cast<VectorType>(CmpInst::makeCmpResultType(VecOpTy)),
           /*IsPairwiseForm=*/false,
           /*IsUnsigned=*/false, CostKind);
     case Intrinsic::experimental_vector_reduce_umax:
     case Intrinsic::experimental_vector_reduce_umin:
-      return ConcreteTTI->getMinMaxReductionCost(
+      return thisT()->getMinMaxReductionCost(
           VecOpTy, cast<VectorType>(CmpInst::makeCmpResultType(VecOpTy)),
           /*IsPairwiseForm=*/false,
           /*IsUnsigned=*/true, CostKind);
     case Intrinsic::sadd_sat:
     case Intrinsic::ssub_sat: {
       Type *CondTy = RetTy->getWithNewBitWidth(1);
 
       Type *OpTy = StructType::create({RetTy, CondTy});
       Intrinsic::ID OverflowOp = IID == Intrinsic::sadd_sat
                                      ? Intrinsic::sadd_with_overflow
                                      : Intrinsic::ssub_with_overflow;
 
       // SatMax -> Overflow && SumDiff < 0
       // SatMin -> Overflow && SumDiff >= 0
       unsigned Cost = 0;
       IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
                                     ScalarizationCostPassed);
-      Cost += ConcreteTTI->getIntrinsicInstrCost(Attrs, CostKind);
-      Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy,
-                                              CondTy, CostKind);
-      Cost += 2 * ConcreteTTI->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
-                                                  CondTy, CostKind);
+      Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
+      Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, RetTy, CondTy,
+                                          CostKind);
+      Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
       return Cost;
     }
     case Intrinsic::uadd_sat:
     case Intrinsic::usub_sat: {
       Type *CondTy = RetTy->getWithNewBitWidth(1);
 
       Type *OpTy = StructType::create({RetTy, CondTy});
       Intrinsic::ID OverflowOp = IID == Intrinsic::uadd_sat
                                      ? Intrinsic::uadd_with_overflow
                                      : Intrinsic::usub_with_overflow;
 
       unsigned Cost = 0;
       IntrinsicCostAttributes Attrs(OverflowOp, OpTy, {RetTy, RetTy}, FMF,
                                     ScalarizationCostPassed);
-      Cost += ConcreteTTI->getIntrinsicInstrCost(Attrs, CostKind);
-      Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::Select, RetTy,
-                                              CondTy, CostKind);
+      Cost += thisT()->getIntrinsicInstrCost(Attrs, CostKind);
+      Cost += thisT()->getCmpSelInstrCost(BinaryOperator::Select, RetTy, CondTy,
+                                          CostKind);
       return Cost;
     }
     case Intrinsic::smul_fix:
     case Intrinsic::umul_fix: {
       unsigned ExtSize = RetTy->getScalarSizeInBits() * 2;
       Type *ExtTy = RetTy->getWithNewBitWidth(ExtSize);
 
       unsigned ExtOp =
           IID == Intrinsic::smul_fix ? Instruction::SExt : Instruction::ZExt;
 
       unsigned Cost = 0;
-      Cost += 2 * ConcreteTTI->getCastInstrCost(ExtOp, ExtTy, RetTy, CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Mul, ExtTy,
-                                                  CostKind);
+      Cost += 2 * thisT()->getCastInstrCost(ExtOp, ExtTy, RetTy, CostKind);
       Cost +=
-          2 * ConcreteTTI->getCastInstrCost(Instruction::Trunc, RetTy, ExtTy,
+          thisT()->getArithmeticInstrCost(Instruction::Mul, ExtTy, CostKind);
+      Cost += 2 * thisT()->getCastInstrCost(Instruction::Trunc, RetTy, ExtTy,
                                             CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::LShr, RetTy,
-                                                  CostKind,
-                                                  TTI::OK_AnyValue,
-                                                  TTI::OK_UniformConstantValue);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Shl, RetTy,
-                                                  CostKind,
-                                                  TTI::OK_AnyValue,
-                                                  TTI::OK_UniformConstantValue);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Or, RetTy,
-                                                  CostKind);
+      Cost += thisT()->getArithmeticInstrCost(Instruction::LShr, RetTy,
+                                              CostKind, TTI::OK_AnyValue,
+      Cost += thisT()->getArithmeticInstrCost(Instruction::Shl, RetTy, CostKind,
+      Cost += thisT()->getArithmeticInstrCost(Instruction::Or, RetTy, CostKind);
       return Cost;
     }
     case Intrinsic::sadd_with_overflow:
     case Intrinsic::ssub_with_overflow: {
       Type *SumTy = RetTy->getContainedType(0);
       Type *OverflowTy = RetTy->getContainedType(1);
       unsigned Opcode = IID == Intrinsic::sadd_with_overflow
                             ? BinaryOperator::Add
                             : BinaryOperator::Sub;
 
       //   LHSSign -> LHS >= 0
       //   RHSSign -> RHS >= 0
       //   SumSign -> Sum >= 0
       //
       //   Add:
       //   Overflow -> (LHSSign == RHSSign) && (LHSSign != SumSign)
       //   Sub:
       //   Overflow -> (LHSSign != RHSSign) && (LHSSign != SumSign)
       unsigned Cost = 0;
-      Cost += ConcreteTTI->getArithmeticInstrCost(Opcode, SumTy, CostKind);
-      Cost += 3 * ConcreteTTI->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
-                                                  OverflowTy, CostKind);
-      Cost += 2 * ConcreteTTI->getCmpSelInstrCost(
-                      BinaryOperator::ICmp, OverflowTy, OverflowTy, CostKind);
-      Cost +=
-          ConcreteTTI->getArithmeticInstrCost(BinaryOperator::And, OverflowTy,
+      Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind);
+      Cost += 3 * thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
+      Cost += 2 * thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, OverflowTy,
+                                              OverflowTy, CostKind);
+      Cost += thisT()->getArithmeticInstrCost(BinaryOperator::And, OverflowTy,
                                               CostKind);
       return Cost;
     }
     case Intrinsic::uadd_with_overflow:
     case Intrinsic::usub_with_overflow: {
       Type *SumTy = RetTy->getContainedType(0);
       Type *OverflowTy = RetTy->getContainedType(1);
       unsigned Opcode = IID == Intrinsic::uadd_with_overflow
                             ? BinaryOperator::Add
                             : BinaryOperator::Sub;
 
       unsigned Cost = 0;
-      Cost += ConcreteTTI->getArithmeticInstrCost(Opcode, SumTy, CostKind);
-      Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
-                                              OverflowTy, CostKind);
+      Cost += thisT()->getArithmeticInstrCost(Opcode, SumTy, CostKind);
+      Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, SumTy,
       return Cost;
     }
     case Intrinsic::smul_with_overflow:
     case Intrinsic::umul_with_overflow: {
       Type *MulTy = RetTy->getContainedType(0);
       Type *OverflowTy = RetTy->getContainedType(1);
       unsigned ExtSize = MulTy->getScalarSizeInBits() * 2;
       Type *ExtTy = MulTy->getWithNewBitWidth(ExtSize);
 
       unsigned ExtOp =
           IID == Intrinsic::smul_fix ? Instruction::SExt : Instruction::ZExt;
 
       unsigned Cost = 0;
-      Cost += 2 * ConcreteTTI->getCastInstrCost(ExtOp, ExtTy, MulTy, CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::Mul, ExtTy,
-                                                  CostKind);
+      Cost += 2 * thisT()->getCastInstrCost(ExtOp, ExtTy, MulTy, CostKind);
       Cost +=
-          2 * ConcreteTTI->getCastInstrCost(Instruction::Trunc, MulTy, ExtTy,
+          thisT()->getArithmeticInstrCost(Instruction::Mul, ExtTy, CostKind);
+      Cost += 2 * thisT()->getCastInstrCost(Instruction::Trunc, MulTy, ExtTy,
                                             CostKind);
-      Cost += ConcreteTTI->getArithmeticInstrCost(Instruction::LShr, MulTy,
-                                                  CostKind,
-                                                  TTI::OK_AnyValue,
-                                                  TTI::OK_UniformConstantValue);
+      Cost += thisT()->getArithmeticInstrCost(Instruction::LShr, MulTy,
+                                              CostKind, TTI::OK_AnyValue,
 
       if (IID == Intrinsic::smul_with_overflow)
-        Cost += ConcreteTTI->getArithmeticInstrCost(
-            Instruction::AShr, MulTy, CostKind, TTI::OK_AnyValue,
+        Cost += thisT()->getArithmeticInstrCost(Instruction::AShr, MulTy,
+                                                CostKind, TTI::OK_AnyValue,
                                                 TTI::OK_UniformConstantValue);
 
-      Cost += ConcreteTTI->getCmpSelInstrCost(BinaryOperator::ICmp, MulTy,
-                                              OverflowTy, CostKind);
+      Cost += thisT()->getCmpSelInstrCost(BinaryOperator::ICmp, MulTy,
       return Cost;
     }
     case Intrinsic::ctpop:
       ISDs.push_back(ISD::CTPOP);
       // In case of legalization use TCC_Expensive. This is cheaper than a
       // library call but still not a cheap instruction.
       SingleCallCost = TargetTransformInfo::TCC_Expensive;
       break;
unsigned getTypeBasedIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
     auto MinCustomCostI =
         std::min_element(CustomCost.begin(), CustomCost.end());
     if (MinCustomCostI != CustomCost.end())
       return *MinCustomCostI;
 
     // If we can't lower fmuladd into an FMA estimate the cost as a floating
     // point mul followed by an add.
     if (IID == Intrinsic::fmuladd)
-      return ConcreteTTI->getArithmeticInstrCost(BinaryOperator::FMul, RetTy,
-                                                 CostKind) +
-             ConcreteTTI->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy,
-                                                 CostKind);
+      return thisT()->getArithmeticInstrCost(BinaryOperator::FMul, RetTy,
+             thisT()->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy,
     if (IID == Intrinsic::experimental_constrained_fmuladd) {
       IntrinsicCostAttributes FMulAttrs(
         Intrinsic::experimental_constrained_fmul, RetTy, Tys);
       IntrinsicCostAttributes FAddAttrs(
         Intrinsic::experimental_constrained_fadd, RetTy, Tys);
-      return ConcreteTTI->getIntrinsicInstrCost(FMulAttrs, CostKind) +
-             ConcreteTTI->getIntrinsicInstrCost(FAddAttrs, CostKind);
+      return thisT()->getIntrinsicInstrCost(FMulAttrs, CostKind) +
+             thisT()->getIntrinsicInstrCost(FAddAttrs, CostKind);
     }
 
     // Else, assume that we need to scalarize this intrinsic. For math builtins
     // this will emit a costly libcall, adding call overhead and spills. Make it
     // very expensive.
     if (auto *RetVTy = dyn_cast<VectorType>(RetTy)) {
       unsigned ScalarizationCost = SkipScalarizationCost ?
         ScalarizationCostPassed : getScalarizationOverhead(RetVTy, true, false);
 
       unsigned ScalarCalls = cast<FixedVectorType>(RetVTy)->getNumElements();
       SmallVector<Type *, 4> ScalarTys;
       for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
         Type *Ty = Tys[i];
         if (Ty->isVectorTy())
           Ty = Ty->getScalarType();
         ScalarTys.push_back(Ty);
       }
       IntrinsicCostAttributes Attrs(IID, RetTy->getScalarType(), ScalarTys, FMF);
-      unsigned ScalarCost = ConcreteTTI->getIntrinsicInstrCost(Attrs, CostKind);
+      unsigned ScalarCost = thisT()->getIntrinsicInstrCost(Attrs, CostKind);
       for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
         if (auto *VTy = dyn_cast<VectorType>(Tys[i])) {
           if (!ICA.skipScalarizationCost())
             ScalarizationCost += getScalarizationOverhead(VTy, false, true);
           ScalarCalls = std::max(ScalarCalls,
                                  cast<FixedVectorType>(VTy)->getNumElements());
         }
       }

   unsigned getArithmeticReductionCost(unsigned Opcode, VectorType *Ty,
                                       bool IsPairwise,
                                       TTI::TargetCostKind CostKind) {
     Type *ScalarTy = Ty->getElementType();
     unsigned NumVecElts = cast<FixedVectorType>(Ty)->getNumElements();
     unsigned NumReduxLevels = Log2_32(NumVecElts);
     unsigned ArithCost = 0;
     unsigned ShuffleCost = 0;
-    auto *ConcreteTTI = static_cast<T *>(this);
     std::pair<unsigned, MVT> LT =
-        ConcreteTTI->getTLI()->getTypeLegalizationCost(DL, Ty);
+        thisT()->getTLI()->getTypeLegalizationCost(DL, Ty);
     unsigned LongVectorCount = 0;
     unsigned MVTLen =
         LT.second.isVector() ? LT.second.getVectorNumElements() : 1;
     while (NumVecElts > MVTLen) {
       NumVecElts /= 2;
       VectorType *SubTy = FixedVectorType::get(ScalarTy, NumVecElts);
       // Assume the pairwise shuffles add a cost.
-      ShuffleCost += (IsPairwise + 1) *
-                     ConcreteTTI->getShuffleCost(TTI::SK_ExtractSubvector, Ty,
-                                                 NumVecElts, SubTy);
-      ArithCost += ConcreteTTI->getArithmeticInstrCost(Opcode, SubTy, CostKind);
+      ShuffleCost +=
+          (IsPairwise + 1) * thisT()->getShuffleCost(TTI::SK_ExtractSubvector,
+                                                     Ty, NumVecElts, SubTy);
+      ArithCost += thisT()->getArithmeticInstrCost(Opcode, SubTy, CostKind);
       Ty = SubTy;
       ++LongVectorCount;
     }
 
     NumReduxLevels -= LongVectorCount;
 
     // The minimal length of the vector is limited by the real length of vector
     // operations performed on the current platform. That's why several final
     // reduction operations are performed on the vectors with the same
     // architecture-dependent length.
 
     // Non pairwise reductions need one shuffle per reduction level. Pairwise
     // reductions need two shuffles on every level, but the last one. On that
     // level one of the shuffles is <0, u, u, ...> which is identity.
     unsigned NumShuffles = NumReduxLevels;
     if (IsPairwise && NumReduxLevels >= 1)
       NumShuffles += NumReduxLevels - 1;
     ShuffleCost += NumShuffles *
-                   ConcreteTTI->getShuffleCost(TTI::SK_PermuteSingleSrc, Ty,
-                                               0, Ty);
-    ArithCost += NumReduxLevels *
-                 ConcreteTTI->getArithmeticInstrCost(Opcode, Ty);
+                   thisT()->getShuffleCost(TTI::SK_PermuteSingleSrc, Ty, 0, Ty);
+    ArithCost += NumReduxLevels * thisT()->getArithmeticInstrCost(Opcode, Ty);
     return ShuffleCost + ArithCost +
-           ConcreteTTI->getVectorInstrCost(Instruction::ExtractElement, Ty, 0);
+           thisT()->getVectorInstrCost(Instruction::ExtractElement, Ty, 0);
   }
 
   /// Try to calculate op costs for min/max reduction operations.
   /// \param CondTy Conditional type for the Select instruction.
   unsigned getMinMaxReductionCost(VectorType *Ty, VectorType *CondTy,
                                   bool IsPairwise, bool IsUnsigned,
                                   TTI::TargetCostKind CostKind) {
     Type *ScalarTy = Ty->getElementType();
     Type *ScalarCondTy = CondTy->getElementType();
     unsigned NumVecElts = cast<FixedVectorType>(Ty)->getNumElements();
     unsigned NumReduxLevels = Log2_32(NumVecElts);
     unsigned CmpOpcode;
     if (Ty->isFPOrFPVectorTy()) {
       CmpOpcode = Instruction::FCmp;
     } else {
       assert(Ty->isIntOrIntVectorTy() &&
              "expecting floating point or integer type for min/max reduction");
       CmpOpcode = Instruction::ICmp;
     }
     unsigned MinMaxCost = 0;
     unsigned ShuffleCost = 0;
-    auto *ConcreteTTI = static_cast<T *>(this);
     std::pair<unsigned, MVT> LT =
-        ConcreteTTI->getTLI()->getTypeLegalizationCost(DL, Ty);
+        thisT()->getTLI()->getTypeLegalizationCost(DL, Ty);
     unsigned LongVectorCount = 0;
     unsigned MVTLen =
         LT.second.isVector() ? LT.second.getVectorNumElements() : 1;
     while (NumVecElts > MVTLen) {
       NumVecElts /= 2;
       auto *SubTy = FixedVectorType::get(ScalarTy, NumVecElts);
       CondTy = FixedVectorType::get(ScalarCondTy, NumVecElts);
 
       // Assume the pairwise shuffles add a cost.
-      ShuffleCost += (IsPairwise + 1) *
-                     ConcreteTTI->getShuffleCost(TTI::SK_ExtractSubvector, Ty,
-                                                 NumVecElts, SubTy);
+      ShuffleCost +=
+          (IsPairwise + 1) * thisT()->getShuffleCost(TTI::SK_ExtractSubvector,
+                                                     Ty, NumVecElts, SubTy);
       MinMaxCost +=
-          ConcreteTTI->getCmpSelInstrCost(CmpOpcode, SubTy, CondTy, CostKind) +
-          ConcreteTTI->getCmpSelInstrCost(Instruction::Select, SubTy, CondTy,
-                                          CostKind);
+          thisT()->getCmpSelInstrCost(CmpOpcode, SubTy, CondTy, CostKind) +
+          thisT()->getCmpSelInstrCost(Instruction::Select, SubTy, CondTy,
       Ty = SubTy;
       ++LongVectorCount;
     }
 
     NumReduxLevels -= LongVectorCount;
 
     // The minimal length of the vector is limited by the real length of vector
     // operations performed on the current platform. That's why several final
     // reduction opertions are perfomed on the vectors with the same
     // architecture-dependent length.
 
     // Non pairwise reductions need one shuffle per reduction level. Pairwise
     // reductions need two shuffles on every level, but the last one. On that
     // level one of the shuffles is <0, u, u, ...> which is identity.
     unsigned NumShuffles = NumReduxLevels;
     if (IsPairwise && NumReduxLevels >= 1)
       NumShuffles += NumReduxLevels - 1;
     ShuffleCost += NumShuffles *
-                   ConcreteTTI->getShuffleCost(TTI::SK_PermuteSingleSrc, Ty,
-                                               0, Ty);
+                   thisT()->getShuffleCost(TTI::SK_PermuteSingleSrc, Ty, 0, Ty);
     MinMaxCost +=
         NumReduxLevels *
-        (ConcreteTTI->getCmpSelInstrCost(CmpOpcode, Ty, CondTy, CostKind) +
-         ConcreteTTI->getCmpSelInstrCost(Instruction::Select, Ty, CondTy,
-                                         CostKind));
+        (thisT()->getCmpSelInstrCost(CmpOpcode, Ty, CondTy, CostKind) +
+         thisT()->getCmpSelInstrCost(Instruction::Select, Ty, CondTy,
     // The last min/max should be in vector registers and we counted it above.
     // So just need a single extractelement.
     return ShuffleCost + MinMaxCost +
-           ConcreteTTI->getVectorInstrCost(Instruction::ExtractElement, Ty, 0);
+           thisT()->getVectorInstrCost(Instruction::ExtractElement, Ty, 0);
   }
 
   unsigned getVectorSplitCost() { return 1; }
 
   /// @}
 };
 
 /// Concrete BasicTTIImpl that can be used if no further customization