+ for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
+ if (Tys[i]->isVectorTy()) {
+ ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
+ ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
+ }
+ }
+
+ return ScalarCalls + ScalarizationCost;
+ }
+ // Look for intrinsics that can be lowered directly or turned into a scalar
+ // intrinsic call.
+ case Intrinsic::sqrt: ISD = ISD::FSQRT; break;
+ case Intrinsic::sin: ISD = ISD::FSIN; break;
+ case Intrinsic::cos: ISD = ISD::FCOS; break;
+ case Intrinsic::exp: ISD = ISD::FEXP; break;
+ case Intrinsic::exp2: ISD = ISD::FEXP2; break;
+ case Intrinsic::log: ISD = ISD::FLOG; break;
+ case Intrinsic::log10: ISD = ISD::FLOG10; break;
+ case Intrinsic::log2: ISD = ISD::FLOG2; break;
+ case Intrinsic::fabs: ISD = ISD::FABS; break;
+ case Intrinsic::copysign: ISD = ISD::FCOPYSIGN; break;
+ case Intrinsic::floor: ISD = ISD::FFLOOR; break;
+ case Intrinsic::ceil: ISD = ISD::FCEIL; break;
+ case Intrinsic::trunc: ISD = ISD::FTRUNC; break;
+ case Intrinsic::nearbyint:
+ ISD = ISD::FNEARBYINT; break;
+ case Intrinsic::rint: ISD = ISD::FRINT; break;
+ case Intrinsic::round: ISD = ISD::FROUND; break;
+ case Intrinsic::pow: ISD = ISD::FPOW; break;
+ case Intrinsic::fma: ISD = ISD::FMA; break;
+ case Intrinsic::fmuladd: ISD = ISD::FMA; break;
+ case Intrinsic::lifetime_start:
+ case Intrinsic::lifetime_end:
+ return 0;
+ }
+
+ const TargetLoweringBase *TLI = getTLI();
+ std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(RetTy);
+
+ if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
+ // The operation is legal. Assume it costs 1.
+ // If the type is split to multiple registers, assume that thre is some
+ // overhead to this.
+ // TODO: Once we have extract/insert subvector cost we need to use them.
+ if (LT.first > 1)
+ return LT.first * 2;
+ return LT.first * 1;
+ }
+
+ if (!TLI->isOperationExpand(ISD, LT.second)) {
+ // If the operation is custom lowered then assume
+ // thare the code is twice as expensive.
+ return LT.first * 2;
+ }
+
+ // 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 TopTTI->getArithmeticInstrCost(BinaryOperator::FMul, RetTy) +
+ TopTTI->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy);
+
+ // 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 (RetTy->isVectorTy()) {
+ unsigned Num = RetTy->getVectorNumElements();
+ unsigned Cost = TopTTI->getIntrinsicInstrCost(IID, RetTy->getScalarType(),
+ Tys);
+ return 10 * Cost * Num;