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
|
//===-- SIISelLowering.h - SI DAG Lowering Interface ------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \file
/// SI DAG Lowering interface definition
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_SIISELLOWERING_H
#define LLVM_LIB_TARGET_AMDGPU_SIISELLOWERING_H
#include "AMDGPUISelLowering.h"
#include "AMDGPUArgumentUsageInfo.h"
#include "SIInstrInfo.h"
namespace llvm {
class SITargetLowering final : public AMDGPUTargetLowering {
private:
const GCNSubtarget *Subtarget;
public:
MVT getRegisterTypeForCallingConv(LLVMContext &Context,
CallingConv::ID CC,
EVT VT) const override;
unsigned getNumRegistersForCallingConv(LLVMContext &Context,
CallingConv::ID CC,
EVT VT) const override;
unsigned getVectorTypeBreakdownForCallingConv(
LLVMContext &Context, CallingConv::ID CC, EVT VT, EVT &IntermediateVT,
unsigned &NumIntermediates, MVT &RegisterVT) const override;
private:
SDValue lowerKernArgParameterPtr(SelectionDAG &DAG, const SDLoc &SL,
SDValue Chain, uint64_t Offset) const;
SDValue getImplicitArgPtr(SelectionDAG &DAG, const SDLoc &SL) const;
SDValue lowerKernargMemParameter(SelectionDAG &DAG, EVT VT, EVT MemVT,
const SDLoc &SL, SDValue Chain,
uint64_t Offset, unsigned Align, bool Signed,
const ISD::InputArg *Arg = nullptr) const;
SDValue lowerStackParameter(SelectionDAG &DAG, CCValAssign &VA,
const SDLoc &SL, SDValue Chain,
const ISD::InputArg &Arg) const;
SDValue getPreloadedValue(SelectionDAG &DAG,
const SIMachineFunctionInfo &MFI,
EVT VT,
AMDGPUFunctionArgInfo::PreloadedValue) const;
SDValue LowerGlobalAddress(AMDGPUMachineFunction *MFI, SDValue Op,
SelectionDAG &DAG) const override;
SDValue lowerImplicitZextParam(SelectionDAG &DAG, SDValue Op,
MVT VT, unsigned Offset) const;
SDValue lowerImage(SDValue Op, const AMDGPU::ImageDimIntrinsicInfo *Intr,
SelectionDAG &DAG) const;
SDValue LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINTRINSIC_W_CHAIN(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINTRINSIC_VOID(SDValue Op, SelectionDAG &DAG) const;
SDValue widenLoad(LoadSDNode *Ld, DAGCombinerInfo &DCI) const;
SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerFastUnsafeFDIV(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerFDIV_FAST(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFDIV16(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFDIV32(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFDIV64(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFDIV(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINT_TO_FP(SDValue Op, SelectionDAG &DAG, bool Signed) const;
SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerTrig(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBRCOND(SDValue Op, SelectionDAG &DAG) const;
SDValue adjustLoadValueType(unsigned Opcode, MemSDNode *M,
SelectionDAG &DAG,
bool IsIntrinsic = false) const;
SDValue handleD16VData(SDValue VData, SelectionDAG &DAG) const;
/// Converts \p Op, which must be of floating point type, to the
/// floating point type \p VT, by either extending or truncating it.
SDValue getFPExtOrFPTrunc(SelectionDAG &DAG,
SDValue Op,
const SDLoc &DL,
EVT VT) const;
SDValue convertArgType(
SelectionDAG &DAG, EVT VT, EVT MemVT, const SDLoc &SL, SDValue Val,
bool Signed, const ISD::InputArg *Arg = nullptr) const;
/// Custom lowering for ISD::FP_ROUND for MVT::f16.
SDValue lowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const;
SDValue getSegmentAperture(unsigned AS, const SDLoc &DL,
SelectionDAG &DAG) const;
SDValue lowerADDRSPACECAST(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerINSERT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerTRAP(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerDEBUGTRAP(SDValue Op, SelectionDAG &DAG) const;
SDNode *adjustWritemask(MachineSDNode *&N, SelectionDAG &DAG) const;
SDValue performUCharToFloatCombine(SDNode *N,
DAGCombinerInfo &DCI) const;
SDValue performSHLPtrCombine(SDNode *N,
unsigned AS,
EVT MemVT,
DAGCombinerInfo &DCI) const;
SDValue performMemSDNodeCombine(MemSDNode *N, DAGCombinerInfo &DCI) const;
SDValue splitBinaryBitConstantOp(DAGCombinerInfo &DCI, const SDLoc &SL,
unsigned Opc, SDValue LHS,
const ConstantSDNode *CRHS) const;
SDValue performAndCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performOrCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performXorCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performZeroExtendCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performClassCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFCanonicalizeCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFPMed3ImmCombine(SelectionDAG &DAG, const SDLoc &SL,
SDValue Op0, SDValue Op1) const;
SDValue performIntMed3ImmCombine(SelectionDAG &DAG, const SDLoc &SL,
SDValue Op0, SDValue Op1, bool Signed) const;
SDValue performMinMaxCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFMed3Combine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performCvtPkRTZCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performExtractVectorEltCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performBuildVectorCombine(SDNode *N, DAGCombinerInfo &DCI) const;
unsigned getFusedOpcode(const SelectionDAG &DAG,
const SDNode *N0, const SDNode *N1) const;
SDValue performAddCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performAddCarrySubCarryCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performSubCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFAddCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFSubCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performFMACombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performSetCCCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performCvtF32UByteNCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performClampCombine(SDNode *N, DAGCombinerInfo &DCI) const;
SDValue performRcpCombine(SDNode *N, DAGCombinerInfo &DCI) const;
bool isLegalFlatAddressingMode(const AddrMode &AM) const;
bool isLegalGlobalAddressingMode(const AddrMode &AM) const;
bool isLegalMUBUFAddressingMode(const AddrMode &AM) const;
unsigned isCFIntrinsic(const SDNode *Intr) const;
void createDebuggerPrologueStackObjects(MachineFunction &MF) const;
/// \returns True if fixup needs to be emitted for given global value \p GV,
/// false otherwise.
bool shouldEmitFixup(const GlobalValue *GV) const;
/// \returns True if GOT relocation needs to be emitted for given global value
/// \p GV, false otherwise.
bool shouldEmitGOTReloc(const GlobalValue *GV) const;
/// \returns True if PC-relative relocation needs to be emitted for given
/// global value \p GV, false otherwise.
bool shouldEmitPCReloc(const GlobalValue *GV) const;
public:
SITargetLowering(const TargetMachine &tm, const GCNSubtarget &STI);
const GCNSubtarget *getSubtarget() const;
bool isFPExtFoldable(unsigned Opcode, EVT DestVT, EVT SrcVT) const override;
bool isShuffleMaskLegal(ArrayRef<int> /*Mask*/, EVT /*VT*/) const override;
bool getTgtMemIntrinsic(IntrinsicInfo &, const CallInst &,
MachineFunction &MF,
unsigned IntrinsicID) const override;
bool getAddrModeArguments(IntrinsicInst * /*I*/,
SmallVectorImpl<Value*> &/*Ops*/,
Type *&/*AccessTy*/) const override;
bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
unsigned AS,
Instruction *I = nullptr) const override;
bool canMergeStoresTo(unsigned AS, EVT MemVT,
const SelectionDAG &DAG) const override;
bool allowsMisalignedMemoryAccesses(EVT VT, unsigned AS,
unsigned Align,
bool *IsFast) const override;
EVT getOptimalMemOpType(uint64_t Size, unsigned DstAlign,
unsigned SrcAlign, bool IsMemset,
bool ZeroMemset,
bool MemcpyStrSrc,
MachineFunction &MF) const override;
bool isMemOpUniform(const SDNode *N) const;
bool isMemOpHasNoClobberedMemOperand(const SDNode *N) const;
bool isNoopAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override;
bool isCheapAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override;
TargetLoweringBase::LegalizeTypeAction
getPreferredVectorAction(EVT VT) const override;
bool shouldConvertConstantLoadToIntImm(const APInt &Imm,
Type *Ty) const override;
bool isTypeDesirableForOp(unsigned Op, EVT VT) const override;
bool isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const override;
bool supportSplitCSR(MachineFunction *MF) const override;
void initializeSplitCSR(MachineBasicBlock *Entry) const override;
void insertCopiesSplitCSR(
MachineBasicBlock *Entry,
const SmallVectorImpl<MachineBasicBlock *> &Exits) const override;
SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
const SDLoc &DL, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const override;
bool CanLowerReturn(CallingConv::ID CallConv,
MachineFunction &MF, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
LLVMContext &Context) const override;
SDValue LowerReturn(SDValue Chain, CallingConv::ID CallConv, bool IsVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals, const SDLoc &DL,
SelectionDAG &DAG) const override;
void passSpecialInputs(
CallLoweringInfo &CLI,
const SIMachineFunctionInfo &Info,
SmallVectorImpl<std::pair<unsigned, SDValue>> &RegsToPass,
SmallVectorImpl<SDValue> &MemOpChains,
SDValue Chain,
SDValue StackPtr) const;
SDValue LowerCallResult(SDValue Chain, SDValue InFlag,
CallingConv::ID CallConv, bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
const SDLoc &DL, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals, bool isThisReturn,
SDValue ThisVal) const;
bool mayBeEmittedAsTailCall(const CallInst *) const override;
bool isEligibleForTailCallOptimization(
SDValue Callee, CallingConv::ID CalleeCC, bool isVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SmallVectorImpl<ISD::InputArg> &Ins, SelectionDAG &DAG) const;
SDValue LowerCall(CallLoweringInfo &CLI,
SmallVectorImpl<SDValue> &InVals) const override;
unsigned getRegisterByName(const char* RegName, EVT VT,
SelectionDAG &DAG) const override;
MachineBasicBlock *splitKillBlock(MachineInstr &MI,
MachineBasicBlock *BB) const;
MachineBasicBlock *
EmitInstrWithCustomInserter(MachineInstr &MI,
MachineBasicBlock *BB) const override;
bool hasBitPreservingFPLogic(EVT VT) const override;
bool enableAggressiveFMAFusion(EVT VT) const override;
EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Context,
EVT VT) const override;
MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override;
bool isFMAFasterThanFMulAndFAdd(EVT VT) const override;
SDValue splitUnaryVectorOp(SDValue Op, SelectionDAG &DAG) const;
SDValue splitBinaryVectorOp(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;
void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue> &Results,
SelectionDAG &DAG) const override;
SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;
SDNode *PostISelFolding(MachineSDNode *N, SelectionDAG &DAG) const override;
void AdjustInstrPostInstrSelection(MachineInstr &MI,
SDNode *Node) const override;
SDNode *legalizeTargetIndependentNode(SDNode *Node, SelectionDAG &DAG) const;
MachineSDNode *wrapAddr64Rsrc(SelectionDAG &DAG, const SDLoc &DL,
SDValue Ptr) const;
MachineSDNode *buildRSRC(SelectionDAG &DAG, const SDLoc &DL, SDValue Ptr,
uint32_t RsrcDword1, uint64_t RsrcDword2And3) const;
std::pair<unsigned, const TargetRegisterClass *>
getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
StringRef Constraint, MVT VT) const override;
ConstraintType getConstraintType(StringRef Constraint) const override;
SDValue copyToM0(SelectionDAG &DAG, SDValue Chain, const SDLoc &DL,
SDValue V) const;
void finalizeLowering(MachineFunction &MF) const override;
void computeKnownBitsForFrameIndex(const SDValue Op,
KnownBits &Known,
const APInt &DemandedElts,
const SelectionDAG &DAG,
unsigned Depth = 0) const override;
bool isSDNodeSourceOfDivergence(const SDNode *N,
FunctionLoweringInfo *FLI, DivergenceAnalysis *DA) const override;
};
} // End namespace llvm
#endif
|
