+
+int ARMTTIImpl::getFPOpCost(Type *Ty) {
+ // Use similar logic that's in ARMISelLowering:
+ // Any ARM CPU with VFP2 has floating point, but Thumb1 didn't have access
+ // to VFP.
+
+ if (ST->hasVFP2() && !ST->isThumb1Only()) {
+ if (Ty->isFloatTy()) {
+ return TargetTransformInfo::TCC_Basic;
+ }
+
+ if (Ty->isDoubleTy()) {
+ return ST->isFPOnlySP() ? TargetTransformInfo::TCC_Expensive :
+ TargetTransformInfo::TCC_Basic;
+ }
+ }
+
+ return TargetTransformInfo::TCC_Expensive;
+}
+
+int ARMTTIImpl::getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
+ Type *SubTp) {
+ // We only handle costs of reverse and alternate shuffles for now.
+ if (Kind != TTI::SK_Reverse && Kind != TTI::SK_Alternate)
+ return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+
+ if (Kind == TTI::SK_Reverse) {
+ static const CostTblEntry NEONShuffleTbl[] = {
+ // Reverse shuffle cost one instruction if we are shuffling within a
+ // double word (vrev) or two if we shuffle a quad word (vrev, vext).
+ {ISD::VECTOR_SHUFFLE, MVT::v2i32, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2f32, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2i64, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2f64, 1},
+
+ {ISD::VECTOR_SHUFFLE, MVT::v4i32, 2},
+ {ISD::VECTOR_SHUFFLE, MVT::v4f32, 2},
+ {ISD::VECTOR_SHUFFLE, MVT::v8i16, 2},
+ {ISD::VECTOR_SHUFFLE, MVT::v16i8, 2}};
+
+ std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
+
+ if (const auto *Entry = CostTableLookup(NEONShuffleTbl, ISD::VECTOR_SHUFFLE,
+ LT.second))
+ return LT.first * Entry->Cost;
+
+ return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+ }
+ if (Kind == TTI::SK_Alternate) {
+ static const CostTblEntry NEONAltShuffleTbl[] = {
+ // Alt shuffle cost table for ARM. Cost is the number of instructions
+ // required to create the shuffled vector.
+
+ {ISD::VECTOR_SHUFFLE, MVT::v2f32, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2i64, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2f64, 1},
+ {ISD::VECTOR_SHUFFLE, MVT::v2i32, 1},
+
+ {ISD::VECTOR_SHUFFLE, MVT::v4i32, 2},
+ {ISD::VECTOR_SHUFFLE, MVT::v4f32, 2},
+ {ISD::VECTOR_SHUFFLE, MVT::v4i16, 2},
+
+ {ISD::VECTOR_SHUFFLE, MVT::v8i16, 16},
+
+ {ISD::VECTOR_SHUFFLE, MVT::v16i8, 32}};
+
+ std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
+ if (const auto *Entry = CostTableLookup(NEONAltShuffleTbl,
+ ISD::VECTOR_SHUFFLE, LT.second))
+ return LT.first * Entry->Cost;
+ return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+ }
+ return BaseT::getShuffleCost(Kind, Tp, Index, SubTp);
+}
+
+int ARMTTIImpl::getArithmeticInstrCost(
+ unsigned Opcode, Type *Ty, TTI::OperandValueKind Op1Info,
+ TTI::OperandValueKind Op2Info, TTI::OperandValueProperties Opd1PropInfo,
+ TTI::OperandValueProperties Opd2PropInfo) {
+
+ int ISDOpcode = TLI->InstructionOpcodeToISD(Opcode);
+ std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Ty);
+
+ const unsigned FunctionCallDivCost = 20;
+ const unsigned ReciprocalDivCost = 10;
+ static const CostTblEntry CostTbl[] = {
+ // Division.
+ // These costs are somewhat random. Choose a cost of 20 to indicate that
+ // vectorizing devision (added function call) is going to be very expensive.
+ // Double registers types.
+ { ISD::SDIV, MVT::v1i64, 1 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v1i64, 1 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v1i64, 1 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v1i64, 1 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v2i32, 2 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v2i32, 2 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v2i32, 2 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v2i32, 2 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v4i16, ReciprocalDivCost},
+ { ISD::UDIV, MVT::v4i16, ReciprocalDivCost},
+ { ISD::SREM, MVT::v4i16, 4 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v4i16, 4 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v8i8, ReciprocalDivCost},
+ { ISD::UDIV, MVT::v8i8, ReciprocalDivCost},
+ { ISD::SREM, MVT::v8i8, 8 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v8i8, 8 * FunctionCallDivCost},
+ // Quad register types.
+ { ISD::SDIV, MVT::v2i64, 2 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v2i64, 2 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v2i64, 2 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v2i64, 2 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v4i32, 4 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v4i32, 4 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v4i32, 4 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v4i32, 4 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v8i16, 8 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v8i16, 8 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v8i16, 8 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v8i16, 8 * FunctionCallDivCost},
+ { ISD::SDIV, MVT::v16i8, 16 * FunctionCallDivCost},
+ { ISD::UDIV, MVT::v16i8, 16 * FunctionCallDivCost},
+ { ISD::SREM, MVT::v16i8, 16 * FunctionCallDivCost},
+ { ISD::UREM, MVT::v16i8, 16 * FunctionCallDivCost},
+ // Multiplication.
+ };
+
+ if (ST->hasNEON())
+ if (const auto *Entry = CostTableLookup(CostTbl, ISDOpcode, LT.second))
+ return LT.first * Entry->Cost;
+
+ int Cost = BaseT::getArithmeticInstrCost(Opcode, Ty, Op1Info, Op2Info,
+ Opd1PropInfo, Opd2PropInfo);
+
+ // This is somewhat of a hack. The problem that we are facing is that SROA
+ // creates a sequence of shift, and, or instructions to construct values.
+ // These sequences are recognized by the ISel and have zero-cost. Not so for
+ // the vectorized code. Because we have support for v2i64 but not i64 those
+ // sequences look particularly beneficial to vectorize.
+ // To work around this we increase the cost of v2i64 operations to make them
+ // seem less beneficial.
+ if (LT.second == MVT::v2i64 &&
+ Op2Info == TargetTransformInfo::OK_UniformConstantValue)
+ Cost += 4;
+
+ return Cost;
+}
+
+int ARMTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
+ unsigned AddressSpace) {
+ std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src);
+
+ if (Src->isVectorTy() && Alignment != 16 &&
+ Src->getVectorElementType()->isDoubleTy()) {
+ // Unaligned loads/stores are extremely inefficient.
+ // We need 4 uops for vst.1/vld.1 vs 1uop for vldr/vstr.
+ return LT.first * 4;
+ }
+ return LT.first;
+}
+
+int ARMTTIImpl::getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
+ unsigned Factor,
+ ArrayRef<unsigned> Indices,
+ unsigned Alignment,
+ unsigned AddressSpace) {
+ assert(Factor >= 2 && "Invalid interleave factor");
+ assert(isa<VectorType>(VecTy) && "Expect a vector type");
+
+ // vldN/vstN doesn't support vector types of i64/f64 element.
+ bool EltIs64Bits = DL.getTypeAllocSizeInBits(VecTy->getScalarType()) == 64;
+
+ if (Factor <= TLI->getMaxSupportedInterleaveFactor() && !EltIs64Bits) {
+ unsigned NumElts = VecTy->getVectorNumElements();
+ Type *SubVecTy = VectorType::get(VecTy->getScalarType(), NumElts / Factor);
+ unsigned SubVecSize = DL.getTypeAllocSizeInBits(SubVecTy);
+
+ // vldN/vstN only support legal vector types of size 64 or 128 in bits.
+ if (NumElts % Factor == 0 && (SubVecSize == 64 || SubVecSize == 128))
+ return Factor;
+ }
+
+ return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
+ Alignment, AddressSpace);
+}