#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetSubtargetInfo.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
namespace llvm {
bool hasBranchDivergence() { return false; }
+ bool isSourceOfDivergence(const Value *V) { return false; }
+
bool isLegalAddImmediate(int64_t imm) {
return getTLI()->isLegalAddImmediate(imm);
}
}
bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
- bool HasBaseReg, int64_t Scale) {
+ bool HasBaseReg, int64_t Scale,
+ unsigned AddrSpace) {
TargetLoweringBase::AddrMode AM;
AM.BaseGV = BaseGV;
AM.BaseOffs = BaseOffset;
AM.HasBaseReg = HasBaseReg;
AM.Scale = Scale;
- return getTLI()->isLegalAddressingMode(AM, Ty);
+ return getTLI()->isLegalAddressingMode(AM, Ty, AddrSpace);
}
int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset,
- bool HasBaseReg, int64_t Scale) {
+ bool HasBaseReg, int64_t Scale, unsigned AddrSpace) {
TargetLoweringBase::AddrMode AM;
AM.BaseGV = BaseGV;
AM.BaseOffs = BaseOffset;
AM.HasBaseReg = HasBaseReg;
AM.Scale = Scale;
- return getTLI()->getScalingFactorCost(AM, Ty);
+ return getTLI()->getScalingFactorCost(AM, Ty, AddrSpace);
}
bool isTruncateFree(Type *Ty1, Type *Ty2) {
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:
unsigned getRegisterBitWidth(bool Vector) { return 32; }
- unsigned getMaxInterleaveFactor() { return 1; }
+ unsigned getMaxInterleaveFactor(unsigned VF) { return 1; }
unsigned getArithmeticInstrCost(
unsigned Opcode, Type *Ty,
return Cost;
}
+ unsigned getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
+ unsigned Factor,
+ ArrayRef<unsigned> Indices,
+ unsigned Alignment,
+ unsigned AddressSpace) {
+ VectorType *VT = dyn_cast<VectorType>(VecTy);
+ assert(VT && "Expect a vector type for interleaved memory op");
+
+ unsigned NumElts = VT->getNumElements();
+ assert(Factor > 1 && NumElts % Factor == 0 && "Invalid interleave factor");
+
+ unsigned NumSubElts = NumElts / Factor;
+ VectorType *SubVT = VectorType::get(VT->getElementType(), NumSubElts);
+
+ // Firstly, the cost of load/store operation.
+ unsigned Cost = getMemoryOpCost(Opcode, VecTy, Alignment, AddressSpace);
+
+ // Then plus the cost of interleave operation.
+ if (Opcode == Instruction::Load) {
+ // The interleave cost is similar to extract sub vectors' elements
+ // from the wide vector, and insert them into sub vectors.
+ //
+ // E.g. An interleaved load of factor 2 (with one member of index 0):
+ // %vec = load <8 x i32>, <8 x i32>* %ptr
+ // %v0 = shuffle %vec, undef, <0, 2, 4, 6> ; Index 0
+ // The cost is estimated as extract elements at 0, 2, 4, 6 from the
+ // <8 x i32> vector and insert them into a <4 x i32> vector.
+
+ assert(Indices.size() <= Factor &&
+ "Interleaved memory op has too many members");
+ for (unsigned Index : Indices) {
+ assert(Index < Factor && "Invalid index for interleaved memory op");
+
+ // Extract elements from loaded vector for each sub vector.
+ for (unsigned i = 0; i < NumSubElts; i++)
+ Cost += getVectorInstrCost(Instruction::ExtractElement, VT,
+ Index + i * Factor);
+ }
+
+ unsigned InsSubCost = 0;
+ for (unsigned i = 0; i < NumSubElts; i++)
+ InsSubCost += getVectorInstrCost(Instruction::InsertElement, SubVT, i);
+
+ Cost += Indices.size() * InsSubCost;
+ } else {
+ // The interleave cost is extract all elements from sub vectors, and
+ // insert them into the wide vector.
+ //
+ // E.g. An interleaved store of factor 2:
+ // %v0_v1 = shuffle %v0, %v1, <0, 4, 1, 5, 2, 6, 3, 7>
+ // store <8 x i32> %interleaved.vec, <8 x i32>* %ptr
+ // The cost is estimated as extract all elements from both <4 x i32>
+ // vectors and insert into the <8 x i32> vector.
+
+ unsigned ExtSubCost = 0;
+ for (unsigned i = 0; i < NumSubElts; i++)
+ ExtSubCost += getVectorInstrCost(Instruction::ExtractElement, SubVT, i);
+
+ Cost += Factor * ExtSubCost;
+
+ for (unsigned i = 0; i < NumElts; i++)
+ Cost += getVectorInstrCost(Instruction::InsertElement, VT, i);
+ }
+
+ return Cost;
+ }
+
unsigned getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
ArrayRef<Type *> Tys) {
unsigned ISD = 0;
// 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;
projects / oota-llvm.git / blobdiff