[PM] Change the core design of the TTI analysis to use a polymorphic
type erased interface and a single analysis pass rather than an
extremely complex analysis group.
The end result is that the TTI analysis can contain a type erased
implementation that supports the polymorphic TTI interface. We can build
one from a target-specific implementation or from a dummy one in the IR.
I've also factored all of the code into "mix-in"-able base classes,
including CRTP base classes to facilitate calling back up to the most
specialized form when delegating horizontally across the surface. These
aren't as clean as I would like and I'm planning to work on cleaning
some of this up, but I wanted to start by putting into the right form.
There are a number of reasons for this change, and this particular
design. The first and foremost reason is that an analysis group is
complete overkill, and the chaining delegation strategy was so opaque,
confusing, and high overhead that TTI was suffering greatly for it.
Several of the TTI functions had failed to be implemented in all places
because of the chaining-based delegation making there be no checking of
this. A few other functions were implemented with incorrect delegation.
The message to me was very clear working on this -- the delegation and
analysis group structure was too confusing to be useful here.
The other reason of course is that this is *much* more natural fit for
the new pass manager. This will lay the ground work for a type-erased
per-function info object that can look up the correct subtarget and even
cache it.
Yet another benefit is that this will significantly simplify the
interaction of the pass managers and the TargetMachine. See the future
work below.
The downside of this change is that it is very, very verbose. I'm going
to work to improve that, but it is somewhat an implementation necessity
in C++ to do type erasure. =/ I discussed this design really extensively
with Eric and Hal prior to going down this path, and afterward showed
them the result. No one was really thrilled with it, but there doesn't
seem to be a substantially better alternative. Using a base class and
virtual method dispatch would make the code much shorter, but as
discussed in the update to the programmer's manual and elsewhere,
a polymorphic interface feels like the more principled approach even if
this is perhaps the least compelling example of it. ;]
Ultimately, there is still a lot more to be done here, but this was the
huge chunk that I couldn't really split things out of because this was
the interface change to TTI. I've tried to minimize all the other parts
of this. The follow up work should include at least:
1) Improving the TargetMachine interface by having it directly return
a TTI object. Because we have a non-pass object with value semantics
and an internal type erasure mechanism, we can narrow the interface
of the TargetMachine to *just* do what we need: build and return
a TTI object that we can then insert into the pass pipeline.
2) Make the TTI object be fully specialized for a particular function.
This will include splitting off a minimal form of it which is
sufficient for the inliner and the old pass manager.
3) Add a new pass manager analysis which produces TTI objects from the
target machine for each function. This may actually be done as part
of #2 in order to use the new analysis to implement #2.
4) Work on narrowing the API between TTI and the targets so that it is
easier to understand and less verbose to type erase.
5) Work on narrowing the API between TTI and its clients so that it is
easier to understand and less verbose to forward.
6) Try to improve the CRTP-based delegation. I feel like this code is
just a bit messy and exacerbating the complexity of implementing
the TTI in each target.
Many thanks to Eric and Hal for their help here. I ended up blocked on
this somewhat more abruptly than I expected, and so I appreciate getting
it sorted out very quickly.
Differential Revision: http://reviews.llvm.org/D7293
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227669 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-31 03:43:40 +00:00
|
|
|
//===- TargetTransformInfoImpl.h --------------------------------*- C++ -*-===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/// \file
|
|
|
|
/// This file provides helpers for the implementation of
|
|
|
|
/// a TargetTransformInfo-conforming class.
|
|
|
|
///
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFOIMPL_H
|
|
|
|
#define LLVM_ANALYSIS_TARGETTRANSFORMINFOIMPL_H
|
|
|
|
|
|
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
|
|
#include "llvm/IR/CallSite.h"
|
|
|
|
#include "llvm/IR/DataLayout.h"
|
|
|
|
#include "llvm/IR/Operator.h"
|
|
|
|
#include "llvm/IR/Function.h"
|
|
|
|
#include "llvm/IR/Type.h"
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
/// \brief Base class for use as a mix-in that aids implementing
|
|
|
|
/// a TargetTransformInfo-compatible class.
|
|
|
|
class TargetTransformInfoImplBase {
|
|
|
|
protected:
|
|
|
|
typedef TargetTransformInfo TTI;
|
|
|
|
|
|
|
|
const DataLayout *DL;
|
|
|
|
|
|
|
|
explicit TargetTransformInfoImplBase(const DataLayout *DL)
|
|
|
|
: DL(DL) {}
|
|
|
|
|
|
|
|
public:
|
|
|
|
// Provide value semantics. MSVC requires that we spell all of these out.
|
|
|
|
TargetTransformInfoImplBase(const TargetTransformInfoImplBase &Arg)
|
|
|
|
: DL(Arg.DL) {}
|
|
|
|
TargetTransformInfoImplBase(TargetTransformInfoImplBase &&Arg)
|
|
|
|
: DL(std::move(Arg.DL)) {}
|
|
|
|
TargetTransformInfoImplBase &
|
|
|
|
operator=(const TargetTransformInfoImplBase &RHS) {
|
|
|
|
DL = RHS.DL;
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
TargetTransformInfoImplBase &operator=(TargetTransformInfoImplBase &&RHS) {
|
|
|
|
DL = std::move(RHS.DL);
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) {
|
|
|
|
switch (Opcode) {
|
|
|
|
default:
|
|
|
|
// By default, just classify everything as 'basic'.
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
case Instruction::GetElementPtr:
|
|
|
|
llvm_unreachable("Use getGEPCost for GEP operations!");
|
|
|
|
|
|
|
|
case Instruction::BitCast:
|
|
|
|
assert(OpTy && "Cast instructions must provide the operand type");
|
|
|
|
if (Ty == OpTy || (Ty->isPointerTy() && OpTy->isPointerTy()))
|
|
|
|
// Identity and pointer-to-pointer casts are free.
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
|
|
|
|
// Otherwise, the default basic cost is used.
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
case Instruction::IntToPtr: {
|
|
|
|
if (!DL)
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
// An inttoptr cast is free so long as the input is a legal integer type
|
|
|
|
// which doesn't contain values outside the range of a pointer.
|
|
|
|
unsigned OpSize = OpTy->getScalarSizeInBits();
|
|
|
|
if (DL->isLegalInteger(OpSize) &&
|
|
|
|
OpSize <= DL->getPointerTypeSizeInBits(Ty))
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
|
|
|
|
// Otherwise it's not a no-op.
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
}
|
|
|
|
case Instruction::PtrToInt: {
|
|
|
|
if (!DL)
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
// A ptrtoint cast is free so long as the result is large enough to store
|
|
|
|
// the pointer, and a legal integer type.
|
|
|
|
unsigned DestSize = Ty->getScalarSizeInBits();
|
|
|
|
if (DL->isLegalInteger(DestSize) &&
|
|
|
|
DestSize >= DL->getPointerTypeSizeInBits(OpTy))
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
|
|
|
|
// Otherwise it's not a no-op.
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
}
|
|
|
|
case Instruction::Trunc:
|
|
|
|
// trunc to a native type is free (assuming the target has compare and
|
|
|
|
// shift-right of the same width).
|
|
|
|
if (DL && DL->isLegalInteger(DL->getTypeSizeInBits(Ty)))
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getGEPCost(const Value *Ptr, ArrayRef<const Value *> Operands) {
|
|
|
|
// In the basic model, we just assume that all-constant GEPs will be folded
|
|
|
|
// into their uses via addressing modes.
|
|
|
|
for (unsigned Idx = 0, Size = Operands.size(); Idx != Size; ++Idx)
|
|
|
|
if (!isa<Constant>(Operands[Idx]))
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getCallCost(FunctionType *FTy, int NumArgs) {
|
|
|
|
assert(FTy && "FunctionType must be provided to this routine.");
|
|
|
|
|
|
|
|
// The target-independent implementation just measures the size of the
|
|
|
|
// function by approximating that each argument will take on average one
|
|
|
|
// instruction to prepare.
|
|
|
|
|
|
|
|
if (NumArgs < 0)
|
|
|
|
// Set the argument number to the number of explicit arguments in the
|
|
|
|
// function.
|
|
|
|
NumArgs = FTy->getNumParams();
|
|
|
|
|
|
|
|
return TTI::TCC_Basic * (NumArgs + 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
|
|
|
|
ArrayRef<Type *> ParamTys) {
|
|
|
|
switch (IID) {
|
|
|
|
default:
|
|
|
|
// Intrinsics rarely (if ever) have normal argument setup constraints.
|
|
|
|
// Model them as having a basic instruction cost.
|
|
|
|
// FIXME: This is wrong for libc intrinsics.
|
|
|
|
return TTI::TCC_Basic;
|
|
|
|
|
|
|
|
case Intrinsic::annotation:
|
|
|
|
case Intrinsic::assume:
|
|
|
|
case Intrinsic::dbg_declare:
|
|
|
|
case Intrinsic::dbg_value:
|
|
|
|
case Intrinsic::invariant_start:
|
|
|
|
case Intrinsic::invariant_end:
|
|
|
|
case Intrinsic::lifetime_start:
|
|
|
|
case Intrinsic::lifetime_end:
|
|
|
|
case Intrinsic::objectsize:
|
|
|
|
case Intrinsic::ptr_annotation:
|
|
|
|
case Intrinsic::var_annotation:
|
|
|
|
case Intrinsic::experimental_gc_result_int:
|
|
|
|
case Intrinsic::experimental_gc_result_float:
|
|
|
|
case Intrinsic::experimental_gc_result_ptr:
|
|
|
|
case Intrinsic::experimental_gc_result:
|
|
|
|
case Intrinsic::experimental_gc_relocate:
|
|
|
|
// These intrinsics don't actually represent code after lowering.
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
bool hasBranchDivergence() { return false; }
|
|
|
|
|
|
|
|
bool isLoweredToCall(const Function *F) {
|
|
|
|
// FIXME: These should almost certainly not be handled here, and instead
|
|
|
|
// handled with the help of TLI or the target itself. This was largely
|
|
|
|
// ported from existing analysis heuristics here so that such refactorings
|
|
|
|
// can take place in the future.
|
|
|
|
|
|
|
|
if (F->isIntrinsic())
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (F->hasLocalLinkage() || !F->hasName())
|
|
|
|
return true;
|
|
|
|
|
|
|
|
StringRef Name = F->getName();
|
|
|
|
|
|
|
|
// These will all likely lower to a single selection DAG node.
|
|
|
|
if (Name == "copysign" || Name == "copysignf" || Name == "copysignl" ||
|
|
|
|
Name == "fabs" || Name == "fabsf" || Name == "fabsl" || Name == "sin" ||
|
|
|
|
Name == "fmin" || Name == "fminf" || Name == "fminl" ||
|
|
|
|
Name == "fmax" || Name == "fmaxf" || Name == "fmaxl" ||
|
|
|
|
Name == "sinf" || Name == "sinl" || Name == "cos" || Name == "cosf" ||
|
|
|
|
Name == "cosl" || Name == "sqrt" || Name == "sqrtf" || Name == "sqrtl")
|
|
|
|
return false;
|
|
|
|
|
|
|
|
// These are all likely to be optimized into something smaller.
|
|
|
|
if (Name == "pow" || Name == "powf" || Name == "powl" || Name == "exp2" ||
|
|
|
|
Name == "exp2l" || Name == "exp2f" || Name == "floor" ||
|
|
|
|
Name == "floorf" || Name == "ceil" || Name == "round" ||
|
|
|
|
Name == "ffs" || Name == "ffsl" || Name == "abs" || Name == "labs" ||
|
|
|
|
Name == "llabs")
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2015-02-01 14:31:23 +00:00
|
|
|
void getUnrollingPreferences(Loop *, TTI::UnrollingPreferences &) {}
|
[PM] Change the core design of the TTI analysis to use a polymorphic
type erased interface and a single analysis pass rather than an
extremely complex analysis group.
The end result is that the TTI analysis can contain a type erased
implementation that supports the polymorphic TTI interface. We can build
one from a target-specific implementation or from a dummy one in the IR.
I've also factored all of the code into "mix-in"-able base classes,
including CRTP base classes to facilitate calling back up to the most
specialized form when delegating horizontally across the surface. These
aren't as clean as I would like and I'm planning to work on cleaning
some of this up, but I wanted to start by putting into the right form.
There are a number of reasons for this change, and this particular
design. The first and foremost reason is that an analysis group is
complete overkill, and the chaining delegation strategy was so opaque,
confusing, and high overhead that TTI was suffering greatly for it.
Several of the TTI functions had failed to be implemented in all places
because of the chaining-based delegation making there be no checking of
this. A few other functions were implemented with incorrect delegation.
The message to me was very clear working on this -- the delegation and
analysis group structure was too confusing to be useful here.
The other reason of course is that this is *much* more natural fit for
the new pass manager. This will lay the ground work for a type-erased
per-function info object that can look up the correct subtarget and even
cache it.
Yet another benefit is that this will significantly simplify the
interaction of the pass managers and the TargetMachine. See the future
work below.
The downside of this change is that it is very, very verbose. I'm going
to work to improve that, but it is somewhat an implementation necessity
in C++ to do type erasure. =/ I discussed this design really extensively
with Eric and Hal prior to going down this path, and afterward showed
them the result. No one was really thrilled with it, but there doesn't
seem to be a substantially better alternative. Using a base class and
virtual method dispatch would make the code much shorter, but as
discussed in the update to the programmer's manual and elsewhere,
a polymorphic interface feels like the more principled approach even if
this is perhaps the least compelling example of it. ;]
Ultimately, there is still a lot more to be done here, but this was the
huge chunk that I couldn't really split things out of because this was
the interface change to TTI. I've tried to minimize all the other parts
of this. The follow up work should include at least:
1) Improving the TargetMachine interface by having it directly return
a TTI object. Because we have a non-pass object with value semantics
and an internal type erasure mechanism, we can narrow the interface
of the TargetMachine to *just* do what we need: build and return
a TTI object that we can then insert into the pass pipeline.
2) Make the TTI object be fully specialized for a particular function.
This will include splitting off a minimal form of it which is
sufficient for the inliner and the old pass manager.
3) Add a new pass manager analysis which produces TTI objects from the
target machine for each function. This may actually be done as part
of #2 in order to use the new analysis to implement #2.
4) Work on narrowing the API between TTI and the targets so that it is
easier to understand and less verbose to type erase.
5) Work on narrowing the API between TTI and its clients so that it is
easier to understand and less verbose to forward.
6) Try to improve the CRTP-based delegation. I feel like this code is
just a bit messy and exacerbating the complexity of implementing
the TTI in each target.
Many thanks to Eric and Hal for their help here. I ended up blocked on
this somewhat more abruptly than I expected, and so I appreciate getting
it sorted out very quickly.
Differential Revision: http://reviews.llvm.org/D7293
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227669 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-31 03:43:40 +00:00
|
|
|
|
|
|
|
bool isLegalAddImmediate(int64_t Imm) { return false; }
|
|
|
|
|
|
|
|
bool isLegalICmpImmediate(int64_t Imm) { return false; }
|
|
|
|
|
|
|
|
bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
|
|
|
|
bool HasBaseReg, int64_t Scale) {
|
|
|
|
// Guess that reg+reg addressing is allowed. This heuristic is taken from
|
|
|
|
// the implementation of LSR.
|
|
|
|
return !BaseGV && BaseOffset == 0 && Scale <= 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool isLegalMaskedStore(Type *DataType, int Consecutive) { return false; }
|
|
|
|
|
|
|
|
bool isLegalMaskedLoad(Type *DataType, int Consecutive) { return false; }
|
|
|
|
|
|
|
|
int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
|
|
|
|
bool HasBaseReg, int64_t Scale) {
|
|
|
|
// Guess that all legal addressing mode are free.
|
|
|
|
if (isLegalAddressingMode(Ty, BaseGV, BaseOffset, HasBaseReg, Scale))
|
|
|
|
return 0;
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool isTruncateFree(Type *Ty1, Type *Ty2) { return false; }
|
|
|
|
|
|
|
|
bool isTypeLegal(Type *Ty) { return false; }
|
|
|
|
|
|
|
|
unsigned getJumpBufAlignment() { return 0; }
|
|
|
|
|
|
|
|
unsigned getJumpBufSize() { return 0; }
|
|
|
|
|
|
|
|
bool shouldBuildLookupTables() { return true; }
|
|
|
|
|
|
|
|
TTI::PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) {
|
|
|
|
return TTI::PSK_Software;
|
|
|
|
}
|
|
|
|
|
|
|
|
bool haveFastSqrt(Type *Ty) { return false; }
|
|
|
|
|
|
|
|
unsigned getIntImmCost(const APInt &Imm, Type *Ty) { return TTI::TCC_Basic; }
|
|
|
|
|
|
|
|
unsigned getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm,
|
|
|
|
Type *Ty) {
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
|
|
|
|
Type *Ty) {
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getNumberOfRegisters(bool Vector) { return 8; }
|
|
|
|
|
|
|
|
unsigned getRegisterBitWidth(bool Vector) { return 32; }
|
|
|
|
|
|
|
|
unsigned getMaxInterleaveFactor() { return 1; }
|
|
|
|
|
|
|
|
unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty,
|
|
|
|
TTI::OperandValueKind Opd1Info,
|
|
|
|
TTI::OperandValueKind Opd2Info,
|
|
|
|
TTI::OperandValueProperties Opd1PropInfo,
|
|
|
|
TTI::OperandValueProperties Opd2PropInfo) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getShuffleCost(TTI::ShuffleKind Kind, Type *Ty, int Index,
|
|
|
|
Type *SubTp) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) { return 1; }
|
|
|
|
|
|
|
|
unsigned getCFInstrCost(unsigned Opcode) { return 1; }
|
|
|
|
|
|
|
|
unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
|
|
|
|
unsigned AddressSpace) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getMaskedMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
|
|
|
|
unsigned AddressSpace) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
|
|
|
|
ArrayRef<Type *> Tys) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getNumberOfParts(Type *Tp) { return 0; }
|
|
|
|
|
|
|
|
unsigned getAddressComputationCost(Type *Tp, bool) { return 0; }
|
|
|
|
|
|
|
|
unsigned getReductionCost(unsigned, Type *, bool) { return 1; }
|
|
|
|
|
|
|
|
unsigned getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys) { return 0; }
|
|
|
|
|
|
|
|
bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info) {
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst,
|
|
|
|
Type *ExpectedType) {
|
|
|
|
return nullptr;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
|
|
|
|
/// \brief CRTP base class for use as a mix-in that aids implementing
|
|
|
|
/// a TargetTransformInfo-compatible class.
|
|
|
|
template <typename T>
|
|
|
|
class TargetTransformInfoImplCRTPBase : public TargetTransformInfoImplBase {
|
|
|
|
private:
|
|
|
|
typedef TargetTransformInfoImplBase BaseT;
|
|
|
|
|
|
|
|
protected:
|
|
|
|
explicit TargetTransformInfoImplCRTPBase(const DataLayout *DL)
|
|
|
|
: BaseT(DL) {}
|
|
|
|
|
|
|
|
public:
|
|
|
|
// Provide value semantics. MSVC requires that we spell all of these out.
|
|
|
|
TargetTransformInfoImplCRTPBase(const TargetTransformInfoImplCRTPBase &Arg)
|
|
|
|
: BaseT(static_cast<const BaseT &>(Arg)) {}
|
|
|
|
TargetTransformInfoImplCRTPBase(TargetTransformInfoImplCRTPBase &&Arg)
|
|
|
|
: BaseT(std::move(static_cast<BaseT &>(Arg))) {}
|
|
|
|
TargetTransformInfoImplCRTPBase &
|
|
|
|
operator=(const TargetTransformInfoImplCRTPBase &RHS) {
|
|
|
|
BaseT::operator=(static_cast<const BaseT &>(RHS));
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
TargetTransformInfoImplCRTPBase &
|
|
|
|
operator=(TargetTransformInfoImplCRTPBase &&RHS) {
|
|
|
|
BaseT::operator=(std::move(static_cast<BaseT &>(RHS)));
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
|
|
|
|
using BaseT::getCallCost;
|
|
|
|
|
|
|
|
unsigned getCallCost(const Function *F, int NumArgs) {
|
|
|
|
assert(F && "A concrete function must be provided to this routine.");
|
|
|
|
|
|
|
|
if (NumArgs < 0)
|
|
|
|
// Set the argument number to the number of explicit arguments in the
|
|
|
|
// function.
|
|
|
|
NumArgs = F->arg_size();
|
|
|
|
|
|
|
|
if (Intrinsic::ID IID = (Intrinsic::ID)F->getIntrinsicID()) {
|
|
|
|
FunctionType *FTy = F->getFunctionType();
|
|
|
|
SmallVector<Type *, 8> ParamTys(FTy->param_begin(), FTy->param_end());
|
|
|
|
return static_cast<T *>(this)
|
|
|
|
->getIntrinsicCost(IID, FTy->getReturnType(), ParamTys);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!static_cast<T *>(this)->isLoweredToCall(F))
|
|
|
|
return TTI::TCC_Basic; // Give a basic cost if it will be lowered
|
|
|
|
// directly.
|
|
|
|
|
|
|
|
return static_cast<T *>(this)->getCallCost(F->getFunctionType(), NumArgs);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getCallCost(const Function *F, ArrayRef<const Value *> Arguments) {
|
|
|
|
// Simply delegate to generic handling of the call.
|
|
|
|
// FIXME: We should use instsimplify or something else to catch calls which
|
|
|
|
// will constant fold with these arguments.
|
|
|
|
return static_cast<T *>(this)->getCallCost(F, Arguments.size());
|
|
|
|
}
|
|
|
|
|
|
|
|
using BaseT::getIntrinsicCost;
|
|
|
|
|
|
|
|
unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
|
|
|
|
ArrayRef<const Value *> Arguments) {
|
|
|
|
// Delegate to the generic intrinsic handling code. This mostly provides an
|
|
|
|
// opportunity for targets to (for example) special case the cost of
|
|
|
|
// certain intrinsics based on constants used as arguments.
|
|
|
|
SmallVector<Type *, 8> ParamTys;
|
|
|
|
ParamTys.reserve(Arguments.size());
|
|
|
|
for (unsigned Idx = 0, Size = Arguments.size(); Idx != Size; ++Idx)
|
|
|
|
ParamTys.push_back(Arguments[Idx]->getType());
|
|
|
|
return static_cast<T *>(this)->getIntrinsicCost(IID, RetTy, ParamTys);
|
|
|
|
}
|
|
|
|
|
|
|
|
unsigned getUserCost(const User *U) {
|
|
|
|
if (isa<PHINode>(U))
|
|
|
|
return TTI::TCC_Free; // Model all PHI nodes as free.
|
|
|
|
|
|
|
|
if (const GEPOperator *GEP = dyn_cast<GEPOperator>(U)) {
|
|
|
|
SmallVector<const Value *, 4> Indices(GEP->idx_begin(), GEP->idx_end());
|
|
|
|
return static_cast<T *>(this)
|
|
|
|
->getGEPCost(GEP->getPointerOperand(), Indices);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ImmutableCallSite CS = U) {
|
|
|
|
const Function *F = CS.getCalledFunction();
|
|
|
|
if (!F) {
|
|
|
|
// Just use the called value type.
|
|
|
|
Type *FTy = CS.getCalledValue()->getType()->getPointerElementType();
|
|
|
|
return static_cast<T *>(this)
|
|
|
|
->getCallCost(cast<FunctionType>(FTy), CS.arg_size());
|
|
|
|
}
|
|
|
|
|
|
|
|
SmallVector<const Value *, 8> Arguments(CS.arg_begin(), CS.arg_end());
|
|
|
|
return static_cast<T *>(this)->getCallCost(F, Arguments);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (const CastInst *CI = dyn_cast<CastInst>(U)) {
|
|
|
|
// Result of a cmp instruction is often extended (to be used by other
|
|
|
|
// cmp instructions, logical or return instructions). These are usually
|
|
|
|
// nop on most sane targets.
|
|
|
|
if (isa<CmpInst>(CI->getOperand(0)))
|
|
|
|
return TTI::TCC_Free;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Otherwise delegate to the fully generic implementations.
|
|
|
|
return getOperationCost(
|
|
|
|
Operator::getOpcode(U), U->getType(),
|
|
|
|
U->getNumOperands() == 1 ? U->getOperand(0)->getType() : nullptr);
|
|
|
|
}
|
|
|
|
};
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|