maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

444 lines
16 KiB
C++
Raw Blame History

//===-- RISCVTargetTransformInfo.cpp - RISC-V specific TTI ----------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
#include "RISCVTargetTransformInfo.h"
#include "MCTargetDesc/RISCVMatInt.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/CodeGen/BasicTTIImpl.h"
#include "llvm/CodeGen/TargetLowering.h"
#include <cmath>
using namespace llvm;
#define DEBUG_TYPE "riscvtti"
static cl::opt<unsigned> RVVRegisterWidthLMUL(
"riscv-v-register-bit-width-lmul",
cl::desc(
"The LMUL to use for getRegisterBitWidth queries. Affects LMUL used "
"by autovectorized code. Fractional LMULs are not supported."),
cl::init(1), cl::Hidden);
InstructionCost RISCVTTIImpl::getIntImmCost(const APInt &Imm, Type *Ty,
TTI::TargetCostKind CostKind) {
assert(Ty->isIntegerTy() &&
"getIntImmCost can only estimate cost of materialising integers");
// We have a Zero register, so 0 is always free.
if (Imm == 0)
return TTI::TCC_Free;
// Otherwise, we check how many instructions it will take to materialise.
const DataLayout &DL = getDataLayout();
return RISCVMatInt::getIntMatCost(Imm, DL.getTypeSizeInBits(Ty),
getST()->getFeatureBits());
}
InstructionCost RISCVTTIImpl::getIntImmCostInst(unsigned Opcode, unsigned Idx,
const APInt &Imm, Type *Ty,
TTI::TargetCostKind CostKind,
Instruction *Inst) {
assert(Ty->isIntegerTy() &&
"getIntImmCost can only estimate cost of materialising integers");
// We have a Zero register, so 0 is always free.
if (Imm == 0)
return TTI::TCC_Free;
// Some instructions in RISC-V can take a 12-bit immediate. Some of these are
// commutative, in others the immediate comes from a specific argument index.
bool Takes12BitImm = false;
unsigned ImmArgIdx = ~0U;
switch (Opcode) {
case Instruction::GetElementPtr:
// Never hoist any arguments to a GetElementPtr. CodeGenPrepare will
// split up large offsets in GEP into better parts than ConstantHoisting
// can.
return TTI::TCC_Free;
case Instruction::And:
// zext.h
if (Imm == UINT64_C(0xffff) && ST->hasStdExtZbb())
return TTI::TCC_Free;
// zext.w
if (Imm == UINT64_C(0xffffffff) && ST->hasStdExtZbb())
return TTI::TCC_Free;
LLVM_FALLTHROUGH;
case Instruction::Add:
case Instruction::Or:
case Instruction::Xor:
case Instruction::Mul:
Takes12BitImm = true;
break;
case Instruction::Sub:
case Instruction::Shl:
case Instruction::LShr:
case Instruction::AShr:
Takes12BitImm = true;
ImmArgIdx = 1;
break;
default:
break;
}
if (Takes12BitImm) {
// Check immediate is the correct argument...
if (Instruction::isCommutative(Opcode) || Idx == ImmArgIdx) {
// ... and fits into the 12-bit immediate.
if (Imm.getMinSignedBits() <= 64 &&
getTLI()->isLegalAddImmediate(Imm.getSExtValue())) {
return TTI::TCC_Free;
}
}
// Otherwise, use the full materialisation cost.
return getIntImmCost(Imm, Ty, CostKind);
}
// By default, prevent hoisting.
return TTI::TCC_Free;
}
InstructionCost
RISCVTTIImpl::getIntImmCostIntrin(Intrinsic::ID IID, unsigned Idx,
const APInt &Imm, Type *Ty,
TTI::TargetCostKind CostKind) {
// Prevent hoisting in unknown cases.
return TTI::TCC_Free;
}
TargetTransformInfo::PopcntSupportKind
RISCVTTIImpl::getPopcntSupport(unsigned TyWidth) {
assert(isPowerOf2_32(TyWidth) && "Ty width must be power of 2");
return ST->hasStdExtZbb() ? TTI::PSK_FastHardware : TTI::PSK_Software;
}
bool RISCVTTIImpl::shouldExpandReduction(const IntrinsicInst *II) const {
// Currently, the ExpandReductions pass can't expand scalable-vector
// reductions, but we still request expansion as RVV doesn't support certain
// reductions and the SelectionDAG can't legalize them either.
switch (II->getIntrinsicID()) {
default:
return false;
// These reductions have no equivalent in RVV
case Intrinsic::vector_reduce_mul:
case Intrinsic::vector_reduce_fmul:
return true;
}
}
Optional<unsigned> RISCVTTIImpl::getMaxVScale() const {
// There is no assumption of the maximum vector length in V specification.
// We use the value specified by users as the maximum vector length.
// This function will use the assumed maximum vector length to get the
// maximum vscale for LoopVectorizer.
// If users do not specify the maximum vector length, we have no way to
// know whether the LoopVectorizer is safe to do or not.
// We only consider to use single vector register (LMUL = 1) to vectorize.
unsigned MaxVectorSizeInBits = ST->getMaxRVVVectorSizeInBits();
if (ST->hasVInstructions() && MaxVectorSizeInBits != 0)
return MaxVectorSizeInBits / RISCV::RVVBitsPerBlock;
return BaseT::getMaxVScale();
}
TypeSize
RISCVTTIImpl::getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const {
unsigned LMUL = PowerOf2Floor(
std::max<unsigned>(std::min<unsigned>(RVVRegisterWidthLMUL, 8), 1));
switch (K) {
case TargetTransformInfo::RGK_Scalar:
return TypeSize::getFixed(ST->getXLen());
case TargetTransformInfo::RGK_FixedWidthVector:
return TypeSize::getFixed(
ST->hasVInstructions() ? LMUL * ST->getMinRVVVectorSizeInBits() : 0);
case TargetTransformInfo::RGK_ScalableVector:
return TypeSize::getScalable(
ST->hasVInstructions() ? LMUL * RISCV::RVVBitsPerBlock : 0);
}
llvm_unreachable("Unsupported register kind");
}
InstructionCost RISCVTTIImpl::getSpliceCost(VectorType *Tp, int Index) {
std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, Tp);
unsigned Cost = 2; // vslidedown+vslideup.
// TODO: LMUL should increase cost.
// TODO: Multiplying by LT.first implies this legalizes into multiple copies
// of similar code, but I think we expand through memory.
return Cost * LT.first;
}
InstructionCost RISCVTTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
VectorType *Tp, ArrayRef<int> Mask,
int Index, VectorType *SubTp,
ArrayRef<Value *> Args) {
if (Kind == TTI::SK_Splice && isa<ScalableVectorType>(Tp))
return getSpliceCost(Tp, Index);
return BaseT::getShuffleCost(Kind, Tp, Mask, Index, SubTp);
}
InstructionCost
RISCVTTIImpl::getMaskedMemoryOpCost(unsigned Opcode, Type *Src, Align Alignment,
unsigned AddressSpace,
TTI::TargetCostKind CostKind) {
if (!isa<ScalableVectorType>(Src))
return BaseT::getMaskedMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
CostKind);
return getMemoryOpCost(Opcode, Src, Alignment, AddressSpace, CostKind);
}
InstructionCost RISCVTTIImpl::getGatherScatterOpCost(
unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) {
if (CostKind != TTI::TCK_RecipThroughput)
return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
Alignment, CostKind, I);
if ((Opcode == Instruction::Load &&
!isLegalMaskedGather(DataTy, Align(Alignment))) ||
(Opcode == Instruction::Store &&
!isLegalMaskedScatter(DataTy, Align(Alignment))))
return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
Alignment, CostKind, I);
// FIXME: Only supporting fixed vectors for now.
if (!isa<FixedVectorType>(DataTy))
return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
Alignment, CostKind, I);
auto *VTy = cast<FixedVectorType>(DataTy);
unsigned NumLoads = VTy->getNumElements();
InstructionCost MemOpCost =
getMemoryOpCost(Opcode, VTy->getElementType(), Alignment, 0, CostKind, I);
return NumLoads * MemOpCost;
}
InstructionCost
RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
TTI::TargetCostKind CostKind) {
auto *RetTy = ICA.getReturnType();
switch (ICA.getID()) {
// TODO: add more intrinsic
case Intrinsic::experimental_stepvector: {
unsigned Cost = 1; // vid
auto LT = TLI->getTypeLegalizationCost(DL, RetTy);
return Cost + (LT.first - 1);
}
default:
break;
}
return BaseT::getIntrinsicInstrCost(ICA, CostKind);
}
InstructionCost RISCVTTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
Type *Src,
TTI::CastContextHint CCH,
TTI::TargetCostKind CostKind,
const Instruction *I) {
if (isa<VectorType>(Dst) && isa<VectorType>(Src)) {
// FIXME: Need to compute legalizing cost for illegal types.
if (!isTypeLegal(Src) || !isTypeLegal(Dst))
return BaseT::getCastInstrCost(Opcode, Dst, Src, CCH, CostKind, I);
// Skip if element size of Dst or Src is bigger than ELEN.
if (Src->getScalarSizeInBits() > ST->getELEN() ||
Dst->getScalarSizeInBits() > ST->getELEN())
return BaseT::getCastInstrCost(Opcode, Dst, Src, CCH, CostKind, I);
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
// FIXME: Need to consider vsetvli and lmul.
int PowDiff = (int)Log2_32(Dst->getScalarSizeInBits()) -
(int)Log2_32(Src->getScalarSizeInBits());
switch (ISD) {
case ISD::SIGN_EXTEND:
case ISD::ZERO_EXTEND:
return 1;
case ISD::TRUNCATE:
case ISD::FP_EXTEND:
case ISD::FP_ROUND:
// Counts of narrow/widen instructions.
return std::abs(PowDiff);
case ISD::FP_TO_SINT:
case ISD::FP_TO_UINT:
case ISD::SINT_TO_FP:
case ISD::UINT_TO_FP:
if (std::abs(PowDiff) <= 1)
return 1;
// Backend could lower (v[sz]ext i8 to double) to vfcvt(v[sz]ext.f8 i8),
// so it only need two conversion.
if (Src->isIntOrIntVectorTy())
return 2;
// Counts of narrow/widen instructions.
return std::abs(PowDiff);
}
}
return BaseT::getCastInstrCost(Opcode, Dst, Src, CCH, CostKind, I);
}
InstructionCost
RISCVTTIImpl::getMinMaxReductionCost(VectorType *Ty, VectorType *CondTy,
bool IsUnsigned,
TTI::TargetCostKind CostKind) {
// FIXME: Only supporting fixed vectors for now.
if (!isa<FixedVectorType>(Ty))
return BaseT::getMinMaxReductionCost(Ty, CondTy, IsUnsigned, CostKind);
if (!ST->useRVVForFixedLengthVectors())
return BaseT::getMinMaxReductionCost(Ty, CondTy, IsUnsigned, CostKind);
// Skip if scalar size of Ty is bigger than ELEN.
if (Ty->getScalarSizeInBits() > ST->getELEN())
return BaseT::getMinMaxReductionCost(Ty, CondTy, IsUnsigned, CostKind);
// IR Reduction is composed by two vmv and one rvv reduction instruction.
InstructionCost BaseCost = 2;
unsigned VL = cast<FixedVectorType>(Ty)->getNumElements();
std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, Ty);
return (LT.first - 1) + BaseCost + Log2_32_Ceil(VL);
}
InstructionCost
RISCVTTIImpl::getArithmeticReductionCost(unsigned Opcode, VectorType *VTy,
Optional<FastMathFlags> FMF,
TTI::TargetCostKind CostKind) {
// FIXME: Only supporting fixed vectors for now.
if (!isa<FixedVectorType>(VTy))
return BaseT::getArithmeticReductionCost(Opcode, VTy, FMF, CostKind);
// FIXME: Do not support i1 and/or reduction now.
if (VTy->getElementType()->isIntegerTy(1))
return BaseT::getArithmeticReductionCost(Opcode, VTy, FMF, CostKind);
if (!ST->useRVVForFixedLengthVectors())
return BaseT::getArithmeticReductionCost(Opcode, VTy, FMF, CostKind);
// Skip if scalar size of VTy is bigger than ELEN.
if (VTy->getScalarSizeInBits() > ST->getELEN())
return BaseT::getArithmeticReductionCost(Opcode, VTy, FMF, CostKind);
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
if (ISD != ISD::ADD && ISD != ISD::OR && ISD != ISD::XOR && ISD != ISD::AND &&
ISD != ISD::FADD)
return BaseT::getArithmeticReductionCost(Opcode, VTy, FMF, CostKind);
// IR Reduction is composed by two vmv and one rvv reduction instruction.
InstructionCost BaseCost = 2;
unsigned VL = cast<FixedVectorType>(VTy)->getNumElements();
std::pair<InstructionCost, MVT> LT = TLI->getTypeLegalizationCost(DL, VTy);
if (TTI::requiresOrderedReduction(FMF))
return (LT.first - 1) + BaseCost + VL;
return (LT.first - 1) + BaseCost + Log2_32_Ceil(VL);
}
void RISCVTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
TTI::UnrollingPreferences &UP,
OptimizationRemarkEmitter *ORE) {
// TODO: More tuning on benchmarks and metrics with changes as needed
// would apply to all settings below to enable performance.
// Support explicit targets enabled for SiFive with the unrolling preferences
// below
bool UseDefaultPreferences = true;
if (ST->getProcFamily() == RISCVSubtarget::SiFive7)
UseDefaultPreferences = false;
if (UseDefaultPreferences)
return BasicTTIImplBase::getUnrollingPreferences(L, SE, UP, ORE);
// Enable Upper bound unrolling universally, not dependant upon the conditions
// below.
UP.UpperBound = true;
// Disable loop unrolling for Oz and Os.
UP.OptSizeThreshold = 0;
UP.PartialOptSizeThreshold = 0;
if (L->getHeader()->getParent()->hasOptSize())
return;
SmallVector<BasicBlock *, 4> ExitingBlocks;
L->getExitingBlocks(ExitingBlocks);
LLVM_DEBUG(dbgs() << "Loop has:\n"
<< "Blocks: " << L->getNumBlocks() << "\n"
<< "Exit blocks: " << ExitingBlocks.size() << "\n");
// Only allow another exit other than the latch. This acts as an early exit
// as it mirrors the profitability calculation of the runtime unroller.
if (ExitingBlocks.size() > 2)
return;
// Limit the CFG of the loop body for targets with a branch predictor.
// Allowing 4 blocks permits if-then-else diamonds in the body.
if (L->getNumBlocks() > 4)
return;
// Don't unroll vectorized loops, including the remainder loop
if (getBooleanLoopAttribute(L, "llvm.loop.isvectorized"))
return;
// Scan the loop: don't unroll loops with calls as this could prevent
// inlining.
InstructionCost Cost = 0;
for (auto *BB : L->getBlocks()) {
for (auto &I : *BB) {
// Initial setting - Don't unroll loops containing vectorized
// instructions.
if (I.getType()->isVectorTy())
return;
if (isa<CallInst>(I) || isa<InvokeInst>(I)) {
if (const Function *F = cast<CallBase>(I).getCalledFunction()) {
if (!isLoweredToCall(F))
continue;
}
return;
}
SmallVector<const Value *> Operands(I.operand_values());
Cost +=
getUserCost(&I, Operands, TargetTransformInfo::TCK_SizeAndLatency);
}
}
LLVM_DEBUG(dbgs() << "Cost of loop: " << Cost << "\n");
UP.Partial = true;
UP.Runtime = true;
UP.UnrollRemainder = true;
UP.UnrollAndJam = true;
UP.UnrollAndJamInnerLoopThreshold = 60;
// Force unrolling small loops can be very useful because of the branch
// taken cost of the backedge.
if (Cost < 12)
UP.Force = true;
}
void RISCVTTIImpl::getPeelingPreferences(Loop *L, ScalarEvolution &SE,
TTI::PeelingPreferences &PP) {
BaseT::getPeelingPreferences(L, SE, PP);
}
InstructionCost RISCVTTIImpl::getRegUsageForType(Type *Ty) {
TypeSize Size = Ty->getPrimitiveSizeInBits();
if (Ty->isVectorTy()) {
if (Size.isScalable() && ST->hasVInstructions())
return divideCeil(Size.getKnownMinValue(), RISCV::RVVBitsPerBlock);
if (ST->useRVVForFixedLengthVectors())
return divideCeil(Size, ST->getMinRVVVectorSizeInBits());
}
return BaseT::getRegUsageForType(Ty);
}
Reference in New Issue View Git Blame Copy Permalink