#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetSubtargetInfo.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
namespace llvm {
extern cl::opt<unsigned> PartialUnrollingThreshold;
+/// \brief Base class which can be used to help build a TTI implementation.
+///
+/// This class provides as much implementation of the TTI interface as is
+/// possible using the target independent parts of the code generator.
+///
+/// In order to subclass it, your class must implement a getST() method to
+/// return the subtarget, and a getTLI() method to return the target lowering.
+/// 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:
return Cost;
}
+ /// \brief Local query method delegates up to T which *must* implement this!
+ const TargetSubtargetInfo *getST() const {
+ return static_cast<const T *>(this)->getST();
+ }
+
+ /// \brief Local query method delegates up to T which *must* implement this!
const TargetLoweringBase *getTLI() const {
- return TM->getSubtargetImpl()->getTargetLowering();
+ return static_cast<const T *>(this)->getTLI();
}
protected:
- const TargetMachine *TM;
-
- explicit BasicTTIImplBase(const TargetMachine *TM = nullptr)
- : BaseT(TM ? TM->getDataLayout() : nullptr), TM(TM) {}
+ explicit BasicTTIImplBase(const TargetMachine *TM)
+ : BaseT(TM->getDataLayout()) {}
public:
// Provide value semantics. MSVC requires that we spell all of these out.
BasicTTIImplBase(const BasicTTIImplBase &Arg)
- : BaseT(static_cast<const BaseT &>(Arg)), TM(Arg.TM) {}
+ : BaseT(static_cast<const BaseT &>(Arg)) {}
BasicTTIImplBase(BasicTTIImplBase &&Arg)
- : BaseT(std::move(static_cast<BaseT &>(Arg))), TM(std::move(Arg.TM)) {}
+ : BaseT(std::move(static_cast<BaseT &>(Arg))) {}
BasicTTIImplBase &operator=(const BasicTTIImplBase &RHS) {
BaseT::operator=(static_cast<const BaseT &>(RHS));
- TM = RHS.TM;
return *this;
}
BasicTTIImplBase &operator=(BasicTTIImplBase &&RHS) {
BaseT::operator=(std::move(static_cast<BaseT &>(RHS)));
- TM = std::move(RHS.TM);
return *this;
}
bool hasBranchDivergence() { return false; }
+ bool isSourceOfDivergence(const Value *V) { return false; }
+
bool isLegalAddImmediate(int64_t imm) {
return getTLI()->isLegalAddImmediate(imm);
}
return getTLI()->isTruncateFree(Ty1, Ty2);
}
+ bool isProfitableToHoist(Instruction *I) {
+ return getTLI()->isProfitableToHoist(I);
+ }
+
bool isTypeLegal(Type *Ty) {
EVT VT = getTLI()->getValueType(Ty);
return getTLI()->isTypeLegal(VT);
}
+ unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
+ ArrayRef<const Value *> Arguments) {
+ return BaseT::getIntrinsicCost(IID, RetTy, Arguments);
+ }
+
+ unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
+ ArrayRef<Type *> ParamTys) {
+ if (IID == Intrinsic::cttz) {
+ if (getTLI()->isCheapToSpeculateCttz())
+ return TargetTransformInfo::TCC_Basic;
+ return TargetTransformInfo::TCC_Expensive;
+ }
+
+ if (IID == Intrinsic::ctlz) {
+ if (getTLI()->isCheapToSpeculateCtlz())
+ return TargetTransformInfo::TCC_Basic;
+ return TargetTransformInfo::TCC_Expensive;
+ }
+
+ return BaseT::getIntrinsicCost(IID, RetTy, ParamTys);
+ }
+
unsigned getJumpBufAlignment() { return getTLI()->getJumpBufAlignment(); }
unsigned getJumpBufSize() { return getTLI()->getJumpBufSize(); }
TLI->isOperationLegalOrCustom(ISD::FSQRT, VT);
}
- void getUnrollingPreferences(const Function *F, Loop *L,
- TTI::UnrollingPreferences &UP) {
+ unsigned getFPOpCost(Type *Ty) {
+ // By default, FP instructions are no more expensive since they are
+ // implemented in HW. Target specific TTI can override this.
+ return TargetTransformInfo::TCC_Basic;
+ }
+
+ unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) {
+ const TargetLoweringBase *TLI = getTLI();
+ switch (Opcode) {
+ default: break;
+ case Instruction::Trunc: {
+ if (TLI->isTruncateFree(OpTy, Ty))
+ return TargetTransformInfo::TCC_Free;
+ return TargetTransformInfo::TCC_Basic;
+ }
+ case Instruction::ZExt: {
+ if (TLI->isZExtFree(OpTy, Ty))
+ return TargetTransformInfo::TCC_Free;
+ return TargetTransformInfo::TCC_Basic;
+ }
+ }
+
+ return BaseT::getOperationCost(Opcode, Ty, OpTy);
+ }
+
+ void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP) {
// This unrolling functionality is target independent, but to provide some
// motivation for its intended use, for x86:
// until someone finds a case where it matters in practice.
unsigned MaxOps;
- const TargetSubtargetInfo *ST = TM->getSubtargetImpl(*F);
+ const TargetSubtargetInfo *ST = getST();
if (PartialUnrollingThreshold.getNumOccurrences() > 0)
MaxOps = PartialUnrollingThreshold;
else if (ST->getSchedModel().LoopMicroOpBufferSize > 0)
unsigned getRegisterBitWidth(bool Vector) { return 32; }
- unsigned getMaxInterleaveFactor() { return 1; }
+ unsigned getMaxInterleaveFactor(unsigned VF) { return 1; }
unsigned getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
// Assume that we need to scalarize this intrinsic.
unsigned ScalarizationCost = 0;
unsigned ScalarCalls = 1;
+ Type *ScalarRetTy = RetTy;
if (RetTy->isVectorTy()) {
ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
+ ScalarRetTy = RetTy->getScalarType();
}
+ SmallVector<Type *, 4> ScalarTys;
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());
+ Type *Ty = Tys[i];
+ if (Ty->isVectorTy()) {
+ ScalarizationCost += getScalarizationOverhead(Ty, false, true);
+ ScalarCalls = std::max(ScalarCalls, Ty->getVectorNumElements());
+ Ty = Ty->getScalarType();
}
+ ScalarTys.push_back(Ty);
}
+ if (ScalarCalls == 1)
+ return 1; // Return cost of a scalar intrinsic. Assume it to be cheap.
- return ScalarCalls + ScalarizationCost;
+ unsigned ScalarCost = static_cast<T *>(this)->getIntrinsicInstrCost(
+ IID, ScalarRetTy, ScalarTys);
+
+ return ScalarCalls * ScalarCost + ScalarizationCost;
}
// Look for intrinsics that can be lowered directly or turned into a scalar
// intrinsic call.
// this will emit a costly libcall, adding call overhead and spills. Make it
// very expensive.
if (RetTy->isVectorTy()) {
- unsigned Num = RetTy->getVectorNumElements();
- unsigned Cost = static_cast<T *>(this)->getIntrinsicInstrCost(
- IID, RetTy->getScalarType(), Tys);
- return 10 * Cost * Num;
+ unsigned ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
+ unsigned ScalarCalls = RetTy->getVectorNumElements();
+ 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);
+ }
+ unsigned ScalarCost = static_cast<T *>(this)->getIntrinsicInstrCost(
+ IID, RetTy->getScalarType(), ScalarTys);
+ for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
+ if (Tys[i]->isVectorTy()) {
+ ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
+ ScalarCalls = std::max(ScalarCalls, Tys[i]->getVectorNumElements());
+ }
+ }
+
+ return ScalarCalls * ScalarCost + ScalarizationCost;
}
// This is going to be turned into a library call, make it expensive.
return 10;
}
+ /// \brief Compute a cost of the given call instruction.
+ ///
+ /// Compute the cost of calling function F with return type RetTy and
+ /// argument types Tys. F might be nullptr, in this case the cost of an
+ /// arbitrary call with the specified signature will be returned.
+ /// This is used, for instance, when we estimate call of a vector
+ /// counterpart of the given function.
+ /// \param F Called function, might be nullptr.
+ /// \param RetTy Return value types.
+ /// \param Tys Argument types.
+ /// \returns The cost of Call instruction.
+ unsigned getCallInstrCost(Function *F, Type *RetTy, ArrayRef<Type *> Tys) {
+ return 10;
+ }
+
unsigned getNumberOfParts(Type *Tp) {
std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Tp);
return LT.first;
/// @}
};
+
+/// \brief Concrete BasicTTIImpl that can be used if no further customization
+/// is needed.
+class BasicTTIImpl : public BasicTTIImplBase<BasicTTIImpl> {
+ typedef BasicTTIImplBase<BasicTTIImpl> BaseT;
+ friend class BasicTTIImplBase<BasicTTIImpl>;
+
+ const TargetSubtargetInfo *ST;
+ const TargetLoweringBase *TLI;
+
+ const TargetSubtargetInfo *getST() const { return ST; }
+ const TargetLoweringBase *getTLI() const { return TLI; }
+
+public:
+ explicit BasicTTIImpl(const TargetMachine *ST, Function &F);
+
+ // Provide value semantics. MSVC requires that we spell all of these out.
+ BasicTTIImpl(const BasicTTIImpl &Arg)
+ : BaseT(static_cast<const BaseT &>(Arg)), ST(Arg.ST), TLI(Arg.TLI) {}
+ BasicTTIImpl(BasicTTIImpl &&Arg)
+ : BaseT(std::move(static_cast<BaseT &>(Arg))), ST(std::move(Arg.ST)),
+ TLI(std::move(Arg.TLI)) {}
+ BasicTTIImpl &operator=(const BasicTTIImpl &RHS) {
+ BaseT::operator=(static_cast<const BaseT &>(RHS));
+ ST = RHS.ST;
+ TLI = RHS.TLI;
+ return *this;
+ }
+ BasicTTIImpl &operator=(BasicTTIImpl &&RHS) {
+ BaseT::operator=(std::move(static_cast<BaseT &>(RHS)));
+ ST = std::move(RHS.ST);
+ TLI = std::move(RHS.TLI);
+ return *this;
+ }
+};
+
}
#endif
projects / oota-llvm.git / blobdiff