#define DEBUG_TYPE "tti"
#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/Operator.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/Support/CallSite.h"
#include "llvm/Support/ErrorHandling.h"
using namespace llvm;
AU.addRequired<TargetTransformInfo>();
}
+unsigned TargetTransformInfo::getOperationCost(unsigned Opcode, Type *Ty,
+ Type *OpTy) const {
+ return PrevTTI->getOperationCost(Opcode, Ty, OpTy);
+}
+
+unsigned TargetTransformInfo::getGEPCost(
+ const Value *Ptr, ArrayRef<const Value *> Operands) const {
+ return PrevTTI->getGEPCost(Ptr, Operands);
+}
+
+unsigned TargetTransformInfo::getCallCost(FunctionType *FTy,
+ int NumArgs) const {
+ return PrevTTI->getCallCost(FTy, NumArgs);
+}
+
+unsigned TargetTransformInfo::getCallCost(const Function *F,
+ int NumArgs) const {
+ return PrevTTI->getCallCost(F, NumArgs);
+}
+
+unsigned TargetTransformInfo::getCallCost(
+ const Function *F, ArrayRef<const Value *> Arguments) const {
+ return PrevTTI->getCallCost(F, Arguments);
+}
+
+unsigned TargetTransformInfo::getIntrinsicCost(
+ Intrinsic::ID IID, Type *RetTy, ArrayRef<Type *> ParamTys) const {
+ return PrevTTI->getIntrinsicCost(IID, RetTy, ParamTys);
+}
+
+unsigned TargetTransformInfo::getIntrinsicCost(
+ Intrinsic::ID IID, Type *RetTy, ArrayRef<const Value *> Arguments) const {
+ return PrevTTI->getIntrinsicCost(IID, RetTy, Arguments);
+}
+
+unsigned TargetTransformInfo::getUserCost(const User *U) const {
+ return PrevTTI->getUserCost(U);
+}
+
+bool TargetTransformInfo::isLoweredToCall(const Function *F) const {
+ return PrevTTI->isLoweredToCall(F);
+}
+
bool TargetTransformInfo::isLegalAddImmediate(int64_t Imm) const {
return PrevTTI->isLegalAddImmediate(Imm);
}
return PrevTTI->getNumberOfRegisters(Vector);
}
+unsigned TargetTransformInfo::getRegisterBitWidth(bool Vector) const {
+ return PrevTTI->getRegisterBitWidth(Vector);
+}
+
+unsigned TargetTransformInfo::getMaximumUnrollFactor() const {
+ return PrevTTI->getMaximumUnrollFactor();
+}
+
unsigned TargetTransformInfo::getArithmeticInstrCost(unsigned Opcode,
Type *Ty) const {
return PrevTTI->getArithmeticInstrCost(Opcode, Ty);
return PrevTTI->getNumberOfParts(Tp);
}
+unsigned TargetTransformInfo::getAddressComputationCost(Type *Tp) const {
+ return PrevTTI->getAddressComputationCost(Tp);
+}
namespace {
struct NoTTI : ImmutablePass, TargetTransformInfo {
- NoTTI() : ImmutablePass(ID) {
+ const DataLayout *DL;
+
+ NoTTI() : ImmutablePass(ID), DL(0) {
initializeNoTTIPass(*PassRegistry::getPassRegistry());
}
virtual void initializePass() {
// Note that this subclass is special, and must *not* call initializeTTI as
// it does not chain.
+ TopTTI = this;
PrevTTI = 0;
+ DL = getAnalysisIfAvailable<DataLayout>();
}
virtual void getAnalysisUsage(AnalysisUsage &AU) const {
return this;
}
+ unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) const {
+ switch (Opcode) {
+ default:
+ // By default, just classify everything as 'basic'.
+ return 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 TCC_Free;
+
+ // Otherwise, the default basic cost is used.
+ return TCC_Basic;
+
+ case Instruction::IntToPtr:
+ // 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.
+ if (DL && DL->isLegalInteger(OpTy->getScalarSizeInBits()) &&
+ OpTy->getScalarSizeInBits() <= DL->getPointerSizeInBits())
+ return TCC_Free;
+
+ // Otherwise it's not a no-op.
+ return TCC_Basic;
+
+ case Instruction::PtrToInt:
+ // A ptrtoint cast is free so long as the result is large enough to store
+ // the pointer, and a legal integer type.
+ if (DL && DL->isLegalInteger(OpTy->getScalarSizeInBits()) &&
+ OpTy->getScalarSizeInBits() >= DL->getPointerSizeInBits())
+ return TCC_Free;
+
+ // Otherwise it's not a no-op.
+ return 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 TCC_Free;
+
+ return TCC_Basic;
+ }
+ }
+
+ unsigned getGEPCost(const Value *Ptr,
+ ArrayRef<const Value *> Operands) const {
+ // 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 TCC_Basic;
+
+ return TCC_Free;
+ }
+
+ unsigned getCallCost(FunctionType *FTy, int NumArgs = -1) const {
+ 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 TCC_Basic * (NumArgs + 1);
+ }
+
+ unsigned getCallCost(const Function *F, int NumArgs = -1) const {
+ 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 TopTTI->getIntrinsicCost(IID, FTy->getReturnType(), ParamTys);
+ }
+
+ if (!TopTTI->isLoweredToCall(F))
+ return TCC_Basic; // Give a basic cost if it will be lowered directly.
+
+ return TopTTI->getCallCost(F->getFunctionType(), NumArgs);
+ }
+
+ unsigned getCallCost(const Function *F,
+ ArrayRef<const Value *> Arguments) const {
+ // 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 TopTTI->getCallCost(F, Arguments.size());
+ }
+
+ unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
+ ArrayRef<Type *> ParamTys) const {
+ 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 TCC_Basic;
+
+ 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:
+ // These intrinsics don't actually represent code after lowering.
+ return TCC_Free;
+ }
+ }
+
+ unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
+ ArrayRef<const Value *> Arguments) const {
+ // 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 TopTTI->getIntrinsicCost(IID, RetTy, ParamTys);
+ }
+
+ unsigned getUserCost(const User *U) const {
+ if (isa<PHINode>(U))
+ return TCC_Free; // Model all PHI nodes as free.
+
+ if (const GEPOperator *GEP = dyn_cast<GEPOperator>(U))
+ // In the basic model we just assume that all-constant GEPs will be
+ // folded into their uses via addressing modes.
+ return GEP->hasAllConstantIndices() ? TCC_Free : TCC_Basic;
+
+ if (ImmutableCallSite CS = U) {
+ const Function *F = CS.getCalledFunction();
+ if (!F) {
+ // Just use the called value type.
+ Type *FTy = CS.getCalledValue()->getType()->getPointerElementType();
+ return TopTTI->getCallCost(cast<FunctionType>(FTy), CS.arg_size());
+ }
+
+ SmallVector<const Value *, 8> Arguments;
+ for (ImmutableCallSite::arg_iterator AI = CS.arg_begin(),
+ AE = CS.arg_end();
+ AI != AE; ++AI)
+ Arguments.push_back(*AI);
+
+ return TopTTI->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 TCC_Free;
+ }
+
+ // Otherwise delegate to the fully generic implementations.
+ return getOperationCost(Operator::getOpcode(U), U->getType(),
+ U->getNumOperands() == 1 ?
+ U->getOperand(0)->getType() : 0);
+ }
+
+ bool isLoweredToCall(const Function *F) const {
+ // 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 == "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;
+ }
bool isLegalAddImmediate(int64_t Imm) const {
return false;
bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
bool HasBaseReg, int64_t Scale) const {
- return false;
+ // Guess that reg+reg addressing is allowed. This heuristic is taken from
+ // the implementation of LSR.
+ return !BaseGV && BaseOffset == 0 && Scale <= 1;
}
bool isTruncateFree(Type *Ty1, Type *Ty2) const {
return 8;
}
+ unsigned getRegisterBitWidth(bool Vector) const {
+ return 32;
+ }
+
+ unsigned getMaximumUnrollFactor() const {
+ return 1;
+ }
+
unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const {
return 1;
}
unsigned getNumberOfParts(Type *Tp) const {
return 0;
}
+
+ unsigned getAddressComputationCost(Type *Tp) const {
+ return 0;
+ }
};
} // end anonymous namespace