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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
|
//===- AMDGPUInstructionSelector --------------------------------*- C++ -*-==//
//
// 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
//
//===----------------------------------------------------------------------===//
/// \file
/// This file declares the targeting of the InstructionSelector class for
/// AMDGPU.
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRUCTIONSELECTOR_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRUCTIONSELECTOR_H
#include "SIDefines.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/IR/InstrTypes.h"
namespace {
#define GET_GLOBALISEL_PREDICATE_BITSET
#define AMDGPUSubtarget GCNSubtarget
#include "AMDGPUGenGlobalISel.inc"
#undef GET_GLOBALISEL_PREDICATE_BITSET
#undef AMDGPUSubtarget
}
namespace llvm {
namespace AMDGPU {
struct ImageDimIntrinsicInfo;
}
class AMDGPURegisterBankInfo;
class AMDGPUTargetMachine;
class BlockFrequencyInfo;
class ProfileSummaryInfo;
class GCNSubtarget;
class MachineInstr;
class MachineIRBuilder;
class MachineOperand;
class MachineRegisterInfo;
class RegisterBank;
class SIInstrInfo;
class SIRegisterInfo;
class TargetRegisterClass;
class AMDGPUInstructionSelector final : public InstructionSelector {
private:
MachineRegisterInfo *MRI;
const GCNSubtarget *Subtarget;
public:
AMDGPUInstructionSelector(const GCNSubtarget &STI,
const AMDGPURegisterBankInfo &RBI,
const AMDGPUTargetMachine &TM);
bool select(MachineInstr &I) override;
static const char *getName();
void setupMF(MachineFunction &MF, GISelKnownBits *KB,
CodeGenCoverage *CoverageInfo, ProfileSummaryInfo *PSI,
BlockFrequencyInfo *BFI) override;
private:
struct GEPInfo {
SmallVector<unsigned, 2> SgprParts;
SmallVector<unsigned, 2> VgprParts;
int64_t Imm = 0;
};
bool isSGPR(Register Reg) const;
bool isInstrUniform(const MachineInstr &MI) const;
bool isVCC(Register Reg, const MachineRegisterInfo &MRI) const;
const RegisterBank *getArtifactRegBank(
Register Reg, const MachineRegisterInfo &MRI,
const TargetRegisterInfo &TRI) const;
/// tblgen-erated 'select' implementation.
bool selectImpl(MachineInstr &I, CodeGenCoverage &CoverageInfo) const;
MachineOperand getSubOperand64(MachineOperand &MO,
const TargetRegisterClass &SubRC,
unsigned SubIdx) const;
bool constrainCopyLikeIntrin(MachineInstr &MI, unsigned NewOpc) const;
bool selectCOPY(MachineInstr &I) const;
bool selectPHI(MachineInstr &I) const;
bool selectG_TRUNC(MachineInstr &I) const;
bool selectG_SZA_EXT(MachineInstr &I) const;
bool selectG_CONSTANT(MachineInstr &I) const;
bool selectG_FNEG(MachineInstr &I) const;
bool selectG_FABS(MachineInstr &I) const;
bool selectG_AND_OR_XOR(MachineInstr &I) const;
bool selectG_ADD_SUB(MachineInstr &I) const;
bool selectG_UADDO_USUBO_UADDE_USUBE(MachineInstr &I) const;
bool selectG_AMDGPU_MAD_64_32(MachineInstr &I) const;
bool selectG_EXTRACT(MachineInstr &I) const;
bool selectG_FMA_FMAD(MachineInstr &I) const;
bool selectG_MERGE_VALUES(MachineInstr &I) const;
bool selectG_UNMERGE_VALUES(MachineInstr &I) const;
bool selectG_BUILD_VECTOR(MachineInstr &I) const;
bool selectG_PTR_ADD(MachineInstr &I) const;
bool selectG_IMPLICIT_DEF(MachineInstr &I) const;
bool selectG_INSERT(MachineInstr &I) const;
bool selectG_SBFX_UBFX(MachineInstr &I) const;
bool selectInterpP1F16(MachineInstr &MI) const;
bool selectWritelane(MachineInstr &MI) const;
bool selectDivScale(MachineInstr &MI) const;
bool selectIntrinsicCmp(MachineInstr &MI) const;
bool selectBallot(MachineInstr &I) const;
bool selectInverseBallot(MachineInstr &I) const;
bool selectRelocConstant(MachineInstr &I) const;
bool selectGroupStaticSize(MachineInstr &I) const;
bool selectReturnAddress(MachineInstr &I) const;
bool selectG_INTRINSIC(MachineInstr &I) const;
bool selectEndCfIntrinsic(MachineInstr &MI) const;
bool selectDSOrderedIntrinsic(MachineInstr &MI, Intrinsic::ID IID) const;
bool selectDSGWSIntrinsic(MachineInstr &MI, Intrinsic::ID IID) const;
bool selectDSAppendConsume(MachineInstr &MI, bool IsAppend) const;
bool selectSBarrier(MachineInstr &MI) const;
bool selectDSBvhStackIntrinsic(MachineInstr &MI) const;
bool selectImageIntrinsic(MachineInstr &MI,
const AMDGPU::ImageDimIntrinsicInfo *Intr) const;
bool selectG_INTRINSIC_W_SIDE_EFFECTS(MachineInstr &I) const;
int getS_CMPOpcode(CmpInst::Predicate P, unsigned Size) const;
bool selectG_ICMP(MachineInstr &I) const;
bool hasVgprParts(ArrayRef<GEPInfo> AddrInfo) const;
void getAddrModeInfo(const MachineInstr &Load, const MachineRegisterInfo &MRI,
SmallVectorImpl<GEPInfo> &AddrInfo) const;
void initM0(MachineInstr &I) const;
bool selectG_LOAD_STORE_ATOMICRMW(MachineInstr &I) const;
bool selectG_SELECT(MachineInstr &I) const;
bool selectG_BRCOND(MachineInstr &I) const;
bool selectG_GLOBAL_VALUE(MachineInstr &I) const;
bool selectG_PTRMASK(MachineInstr &I) const;
bool selectG_EXTRACT_VECTOR_ELT(MachineInstr &I) const;
bool selectG_INSERT_VECTOR_ELT(MachineInstr &I) const;
bool selectBufferLoadLds(MachineInstr &MI) const;
bool selectGlobalLoadLds(MachineInstr &MI) const;
bool selectBVHIntrinsic(MachineInstr &I) const;
bool selectSMFMACIntrin(MachineInstr &I) const;
bool selectWaveAddress(MachineInstr &I) const;
std::pair<Register, unsigned> selectVOP3ModsImpl(MachineOperand &Root,
bool IsCanonicalizing = true,
bool AllowAbs = true,
bool OpSel = false) const;
Register copyToVGPRIfSrcFolded(Register Src, unsigned Mods,
MachineOperand Root, MachineInstr *InsertPt,
bool ForceVGPR = false) const;
InstructionSelector::ComplexRendererFns
selectVCSRC(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVSRC0(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3Mods0(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3BMods0(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3OMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3Mods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3ModsNonCanonicalizing(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3BMods(MachineOperand &Root) const;
ComplexRendererFns selectVOP3NoMods(MachineOperand &Root) const;
std::pair<Register, unsigned>
selectVOP3PModsImpl(Register Src, const MachineRegisterInfo &MRI,
bool IsDOT = false) const;
InstructionSelector::ComplexRendererFns
selectVOP3PMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3PModsDOT(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectDotIUVOP3PMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectWMMAOpSelVOP3PMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVOP3OpSelMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVINTERPMods(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectVINTERPModsHi(MachineOperand &Root) const;
bool selectSmrdOffset(MachineOperand &Root, Register &Base, Register *SOffset,
int64_t *Offset) const;
InstructionSelector::ComplexRendererFns
selectSmrdImm(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectSmrdImm32(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectSmrdSgpr(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectSmrdSgprImm(MachineOperand &Root) const;
std::pair<Register, int> selectFlatOffsetImpl(MachineOperand &Root,
uint64_t FlatVariant) const;
InstructionSelector::ComplexRendererFns
selectFlatOffset(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectGlobalOffset(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectScratchOffset(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectGlobalSAddr(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectScratchSAddr(MachineOperand &Root) const;
bool checkFlatScratchSVSSwizzleBug(Register VAddr, Register SAddr,
uint64_t ImmOffset) const;
InstructionSelector::ComplexRendererFns
selectScratchSVAddr(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectMUBUFScratchOffen(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectMUBUFScratchOffset(MachineOperand &Root) const;
bool isDSOffsetLegal(Register Base, int64_t Offset) const;
bool isDSOffset2Legal(Register Base, int64_t Offset0, int64_t Offset1,
unsigned Size) const;
bool isFlatScratchBaseLegal(
Register Base, uint64_t FlatVariant = SIInstrFlags::FlatScratch) const;
std::pair<Register, unsigned>
selectDS1Addr1OffsetImpl(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectDS1Addr1Offset(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectDS64Bit4ByteAligned(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectDS128Bit8ByteAligned(MachineOperand &Root) const;
std::pair<Register, unsigned> selectDSReadWrite2Impl(MachineOperand &Root,
unsigned size) const;
InstructionSelector::ComplexRendererFns
selectDSReadWrite2(MachineOperand &Root, unsigned size) const;
std::pair<Register, int64_t>
getPtrBaseWithConstantOffset(Register Root,
const MachineRegisterInfo &MRI) const;
// Parse out a chain of up to two g_ptr_add instructions.
// g_ptr_add (n0, _)
// g_ptr_add (n0, (n1 = g_ptr_add n2, n3))
struct MUBUFAddressData {
Register N0, N2, N3;
int64_t Offset = 0;
};
bool shouldUseAddr64(MUBUFAddressData AddrData) const;
void splitIllegalMUBUFOffset(MachineIRBuilder &B,
Register &SOffset, int64_t &ImmOffset) const;
MUBUFAddressData parseMUBUFAddress(Register Src) const;
bool selectMUBUFAddr64Impl(MachineOperand &Root, Register &VAddr,
Register &RSrcReg, Register &SOffset,
int64_t &Offset) const;
bool selectMUBUFOffsetImpl(MachineOperand &Root, Register &RSrcReg,
Register &SOffset, int64_t &Offset) const;
InstructionSelector::ComplexRendererFns
selectMUBUFAddr64(MachineOperand &Root) const;
InstructionSelector::ComplexRendererFns
selectMUBUFOffset(MachineOperand &Root) const;
ComplexRendererFns selectSMRDBufferImm(MachineOperand &Root) const;
ComplexRendererFns selectSMRDBufferImm32(MachineOperand &Root) const;
ComplexRendererFns selectSMRDBufferSgprImm(MachineOperand &Root) const;
std::pair<Register, unsigned> selectVOP3PMadMixModsImpl(MachineOperand &Root,
bool &Matched) const;
ComplexRendererFns selectVOP3PMadMixModsExt(MachineOperand &Root) const;
ComplexRendererFns selectVOP3PMadMixMods(MachineOperand &Root) const;
void renderTruncImm32(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx = -1) const;
void renderTruncTImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderOpSelTImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderNegateImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderBitcastImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderPopcntImm(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderExtractCPol(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderExtractSWZ(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderSetGLC(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
void renderFrameIndex(MachineInstrBuilder &MIB, const MachineInstr &MI,
int OpIdx) const;
bool isInlineImmediate16(int64_t Imm) const;
bool isInlineImmediate32(int64_t Imm) const;
bool isInlineImmediate64(int64_t Imm) const;
bool isInlineImmediate(const APFloat &Imm) const;
// Returns true if TargetOpcode::G_AND MachineInstr `MI`'s masking of the
// shift amount operand's `ShAmtBits` bits is unneeded.
bool isUnneededShiftMask(const MachineInstr &MI, unsigned ShAmtBits) const;
const SIInstrInfo &TII;
const SIRegisterInfo &TRI;
const AMDGPURegisterBankInfo &RBI;
const AMDGPUTargetMachine &TM;
const GCNSubtarget &STI;
bool EnableLateStructurizeCFG;
#define GET_GLOBALISEL_PREDICATES_DECL
#define AMDGPUSubtarget GCNSubtarget
#include "AMDGPUGenGlobalISel.inc"
#undef GET_GLOBALISEL_PREDICATES_DECL
#undef AMDGPUSubtarget
#define GET_GLOBALISEL_TEMPORARIES_DECL
#include "AMDGPUGenGlobalISel.inc"
#undef GET_GLOBALISEL_TEMPORARIES_DECL
};
} // End llvm namespace.
#endif
|
