X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=include%2Fllvm%2FAnalysis%2FTargetTransformInfo.h;h=eb29e3483d831077cc56e1c4e650ee853df12b70;hb=326ae27c4f744cc7fb43f5a413d042d54fc1ddc0;hp=4f6b9b2d26d398a2db5005a76bcf2d3a1be69839;hpb=674be02d525d4e24bc6943ed9274958c580bcfbc;p=oota-llvm.git diff --git a/include/llvm/Analysis/TargetTransformInfo.h b/include/llvm/Analysis/TargetTransformInfo.h index 4f6b9b2d26d..eb29e3483d8 100644 --- a/include/llvm/Analysis/TargetTransformInfo.h +++ b/include/llvm/Analysis/TargetTransformInfo.h @@ -22,14 +22,17 @@ #ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFO_H #define LLVM_ANALYSIS_TARGETTRANSFORMINFO_H -#include "llvm/IR/GlobalValue.h" #include "llvm/IR/Intrinsics.h" -#include "llvm/IR/Type.h" #include "llvm/Pass.h" #include "llvm/Support/DataTypes.h" namespace llvm { +class GlobalValue; +class Type; +class User; +class Value; + /// TargetTransformInfo - This pass provides access to the codegen /// interfaces that are needed for IR-level transformations. class TargetTransformInfo { @@ -67,6 +70,123 @@ public: /// This class is intended to be subclassed by real implementations. virtual ~TargetTransformInfo() = 0; + /// \name Generic Target Information + /// @{ + + /// \brief Underlying constants for 'cost' values in this interface. + /// + /// Many APIs in this interface return a cost. This enum defines the + /// fundamental values that should be used to interpret (and produce) those + /// costs. The costs are returned as an unsigned rather than a member of this + /// enumeration because it is expected that the cost of one IR instruction + /// may have a multiplicative factor to it or otherwise won't fit directly + /// into the enum. Moreover, it is common to sum or average costs which works + /// better as simple integral values. Thus this enum only provides constants. + /// + /// Note that these costs should usually reflect the intersection of code-size + /// cost and execution cost. A free instruction is typically one that folds + /// into another instruction. For example, reg-to-reg moves can often be + /// skipped by renaming the registers in the CPU, but they still are encoded + /// and thus wouldn't be considered 'free' here. + enum TargetCostConstants { + TCC_Free = 0, ///< Expected to fold away in lowering. + TCC_Basic = 1, ///< The cost of a typical 'add' instruction. + TCC_Expensive = 4 ///< The cost of a 'div' instruction on x86. + }; + + /// \brief Estimate the cost of a specific operation when lowered. + /// + /// Note that this is designed to work on an arbitrary synthetic opcode, and + /// thus work for hypothetical queries before an instruction has even been + /// formed. However, this does *not* work for GEPs, and must not be called + /// for a GEP instruction. Instead, use the dedicated getGEPCost interface as + /// analyzing a GEP's cost required more information. + /// + /// Typically only the result type is required, and the operand type can be + /// omitted. However, if the opcode is one of the cast instructions, the + /// operand type is required. + /// + /// The returned cost is defined in terms of \c TargetCostConstants, see its + /// comments for a detailed explanation of the cost values. + virtual unsigned getOperationCost(unsigned Opcode, Type *Ty, + Type *OpTy = 0) const; + + /// \brief Estimate the cost of a GEP operation when lowered. + /// + /// The contract for this function is the same as \c getOperationCost except + /// that it supports an interface that provides extra information specific to + /// the GEP operation. + virtual unsigned getGEPCost(const Value *Ptr, + ArrayRef Operands) const; + + /// \brief Estimate the cost of a function call when lowered. + /// + /// The contract for this is the same as \c getOperationCost except that it + /// supports an interface that provides extra information specific to call + /// instructions. + /// + /// This is the most basic query for estimating call cost: it only knows the + /// function type and (potentially) the number of arguments at the call site. + /// The latter is only interesting for varargs function types. + virtual unsigned getCallCost(FunctionType *FTy, int NumArgs = -1) const; + + /// \brief Estimate the cost of calling a specific function when lowered. + /// + /// This overload adds the ability to reason about the particular function + /// being called in the event it is a library call with special lowering. + virtual unsigned getCallCost(const Function *F, int NumArgs = -1) const; + + /// \brief Estimate the cost of calling a specific function when lowered. + /// + /// This overload allows specifying a set of candidate argument values. + virtual unsigned getCallCost(const Function *F, + ArrayRef Arguments) const; + + /// \brief Estimate the cost of an intrinsic when lowered. + /// + /// Mirrors the \c getCallCost method but uses an intrinsic identifier. + virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef ParamTys) const; + + /// \brief Estimate the cost of an intrinsic when lowered. + /// + /// Mirrors the \c getCallCost method but uses an intrinsic identifier. + virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef Arguments) const; + + /// \brief Estimate the cost of a given IR user when lowered. + /// + /// This can estimate the cost of either a ConstantExpr or Instruction when + /// lowered. It has two primary advantages over the \c getOperationCost and + /// \c getGEPCost above, and one significant disadvantage: it can only be + /// used when the IR construct has already been formed. + /// + /// The advantages are that it can inspect the SSA use graph to reason more + /// accurately about the cost. For example, all-constant-GEPs can often be + /// folded into a load or other instruction, but if they are used in some + /// other context they may not be folded. This routine can distinguish such + /// cases. + /// + /// The returned cost is defined in terms of \c TargetCostConstants, see its + /// comments for a detailed explanation of the cost values. + virtual unsigned getUserCost(const User *U) const; + + /// \brief Test whether calls to a function lower to actual program function + /// calls. + /// + /// The idea is to test whether the program is likely to require a 'call' + /// instruction or equivalent in order to call the given function. + /// + /// FIXME: It's not clear that this is a good or useful query API. Client's + /// should probably move to simpler cost metrics using the above. + /// Alternatively, we could split the cost interface into distinct code-size + /// and execution-speed costs. This would allow modelling the core of this + /// query more accurately as the a call is a single small instruction, but + /// incurs significant execution cost. + virtual bool isLoweredToCall(const Function *F) const; + + /// @} + /// \name Scalar Target Information /// @{ @@ -76,7 +196,7 @@ public: /// significantly boost the performance when the population is dense, and it /// may or may not degrade performance if the population is sparse. A HW /// support is considered as "Fast" if it can outperform, or is on a par - /// with, SW implementaion when the population is sparse; otherwise, it is + /// with, SW implementation when the population is sparse; otherwise, it is /// considered as "Slow". enum PopcntSupportKind { PSK_Software, @@ -105,6 +225,16 @@ public: int64_t BaseOffset, bool HasBaseReg, int64_t Scale) const; + /// \brief Return the cost of the scaling factor used in the addressing + /// mode represented by AM for this target, for a load/store + /// of the specified type. + /// If the AM is supported, the return value must be >= 0. + /// If the AM is not supported, it returns a negative value. + /// TODO: Handle pre/postinc as well. + virtual int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, + int64_t BaseOffset, bool HasBaseReg, + int64_t Scale) const; + /// isTruncateFree - Return true if it's free to truncate a value of /// type Ty1 to type Ty2. e.g. On x86 it's free to truncate a i32 value in /// register EAX to i16 by referencing its sub-register AX. @@ -143,6 +273,13 @@ public: SK_ExtractSubvector ///< ExtractSubvector Index indicates start offset. }; + /// \brief Additonal information about an operand's possible values. + enum OperandValueKind { + OK_AnyValue, // Operand can have any value. + OK_UniformValue, // Operand is uniform (splat of a value). + OK_UniformConstantValue // Operand is uniform constant. + }; + /// \return The number of scalar or vector registers that the target has. /// If 'Vectors' is true, it returns the number of vector registers. If it is /// set to false, it returns the number of scalar registers. @@ -157,7 +294,9 @@ public: virtual unsigned getMaximumUnrollFactor() const; /// \return The expected cost of arithmetic ops, such as mul, xor, fsub, etc. - virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const; + virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty, + OperandValueKind Opd1Info = OK_AnyValue, + OperandValueKind Opd2Info = OK_AnyValue) const; /// \return The cost of a shuffle instruction of kind Kind and of type Tp. /// The index and subtype parameters are used by the subvector insertion and @@ -170,7 +309,7 @@ public: virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const; - /// \return The expected cost of control-flow related instrutctions such as + /// \return The expected cost of control-flow related instructions such as /// Phi, Ret, Br. virtual unsigned getCFInstrCost(unsigned Opcode) const; @@ -196,6 +335,12 @@ public: /// split during legalization. Zero is returned when the answer is unknown. virtual unsigned getNumberOfParts(Type *Tp) const; + /// \returns The cost of the address computation. For most targets this can be + /// merged into the instruction indexing mode. Some targets might want to + /// distinguish between address computation for memory operations on vector + /// types and scalar types. Such targets should override this function. + virtual unsigned getAddressComputationCost(Type *Ty) const; + /// @} /// Analysis group identification. @@ -204,7 +349,7 @@ public: /// \brief Create the base case instance of a pass in the TTI analysis group. /// -/// This class provides the base case for the stack of TTI analyses. It doesn't +/// This class provides the base case for the stack of TTI analyzes. It doesn't /// delegate to anything and uses the STTI and VTTI objects passed in to /// satisfy the queries. ImmutablePass *createNoTargetTransformInfoPass();