#ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
#define LLVM_ANALYSIS_TARGETTRANSFORMINFO_H
-#include "llvm/CodeGen/ValueTypes.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 {
/// 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 dircetly
+ /// 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.
///
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.
+ TCC_Expensive = 4 ///< The cost of a 'div' instruction on x86.
};
/// \brief Estimate the cost of a specific operation when lowered.
virtual unsigned getGEPCost(const Value *Ptr,
ArrayRef<const Value *> 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<const Value *> 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<Type *> 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<const Value *> 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
/// comments for a detailed explanation of the cost values.
virtual unsigned getUserCost(const User *U) const;
+ /// \brief hasBranchDivergence - Return true if branch divergence exists.
+ /// Branch divergence has a significantly negative impact on GPU performance
+ /// when threads in the same wavefront take different paths due to conditional
+ /// branches.
+ virtual bool hasBranchDivergence() 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;
+
+ /// Parameters that control the generic loop unrolling transformation.
+ struct UnrollingPreferences {
+ unsigned Threshold; ///< The cost threshold for the unrolled loop.
+ unsigned OptSizeThreshold; ///< The cost threshold for the unrolled loop
+ ///< when optimizing for size.
+ bool Partial; ///< Allow partial loop unrolling.
+ bool Runtime; ///< Perform runtime unrolling.
+ };
+
+ /// \brief Get target-customized preferences for the generic loop unrolling
+ /// transformation. Returns true if the UnrollingPreferences struct has been
+ /// initialized.
+ virtual bool getUnrollingPreferences(UnrollingPreferences &UP) const;
+
/// @}
/// \name Scalar Target Information
/// 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,
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.
/// getPopcntSupport - Return hardware support for population count.
virtual PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) const;
+ /// haveFastSqrt -- Return true if the hardware has a fast square-root
+ /// instruction.
+ virtual bool haveFastSqrt(Type *Ty) const;
+
/// getIntImmCost - Return the expected cost of materializing the given
/// integer immediate of the specified type.
virtual unsigned getIntImmCost(const APInt &Imm, Type *Ty) const;
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.
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
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;
/// 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.
+ /// The 'IsComplex' parameter is a hint that the address computation is likely
+ /// to involve multiple instructions and as such unlikely to be merged into
+ /// the address indexing mode.
+ virtual unsigned getAddressComputationCost(Type *Ty,
+ bool IsComplex = false) const;
+
/// @}
/// Analysis group identification.
/// \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();