1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
|
//===-- 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"
using namespace llvm;
#define DEBUG_TYPE "riscvtti"
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::Add:
case Instruction::And:
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->hasStdExtV() && MaxVectorSizeInBits != 0)
return MaxVectorSizeInBits / RISCV::RVVBitsPerBlock;
return BaseT::getMaxVScale();
}
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;
}
|
