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
| //===-- AMDGPU.h - MachineFunction passes hw codegen --------------*- 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
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
#include "llvm/Target/TargetMachine.h"
namespace llvm {
class AMDGPUTargetMachine;
class FunctionPass;
class GCNTargetMachine;
class ModulePass;
class Pass;
class Target;
class TargetMachine;
class TargetOptions;
class PassRegistry;
class Module;
// R600 Passes
FunctionPass *createR600VectorRegMerger();
FunctionPass *createR600ExpandSpecialInstrsPass();
FunctionPass *createR600EmitClauseMarkers();
FunctionPass *createR600ClauseMergePass();
FunctionPass *createR600Packetizer();
FunctionPass *createR600ControlFlowFinalizer();
FunctionPass *createAMDGPUCFGStructurizerPass();
FunctionPass *createR600ISelDag(TargetMachine *TM, CodeGenOpt::Level OptLevel);
// SI Passes
FunctionPass *createGCNDPPCombinePass();
FunctionPass *createSIAnnotateControlFlowPass();
FunctionPass *createSIFoldOperandsPass();
FunctionPass *createSIPeepholeSDWAPass();
FunctionPass *createSILowerI1CopiesPass();
FunctionPass *createSIFixupVectorISelPass();
FunctionPass *createSIAddIMGInitPass();
FunctionPass *createSIShrinkInstructionsPass();
FunctionPass *createSILoadStoreOptimizerPass();
FunctionPass *createSIWholeQuadModePass();
FunctionPass *createSIFixControlFlowLiveIntervalsPass();
FunctionPass *createSIOptimizeExecMaskingPreRAPass();
FunctionPass *createSIFixSGPRCopiesPass();
FunctionPass *createSIMemoryLegalizerPass();
FunctionPass *createSIInsertWaitcntsPass();
FunctionPass *createSIPreAllocateWWMRegsPass();
FunctionPass *createSIFormMemoryClausesPass();
FunctionPass *createAMDGPUSimplifyLibCallsPass(const TargetOptions &,
const TargetMachine *);
FunctionPass *createAMDGPUUseNativeCallsPass();
FunctionPass *createAMDGPUCodeGenPreparePass();
FunctionPass *createAMDGPUMachineCFGStructurizerPass();
FunctionPass *createAMDGPUPropagateAttributesEarlyPass(const TargetMachine *);
ModulePass *createAMDGPUPropagateAttributesLatePass(const TargetMachine *);
FunctionPass *createAMDGPURewriteOutArgumentsPass();
FunctionPass *createSIModeRegisterPass();
void initializeAMDGPUDAGToDAGISelPass(PassRegistry&);
void initializeAMDGPUMachineCFGStructurizerPass(PassRegistry&);
extern char &AMDGPUMachineCFGStructurizerID;
void initializeAMDGPUAlwaysInlinePass(PassRegistry&);
Pass *createAMDGPUAnnotateKernelFeaturesPass();
void initializeAMDGPUAnnotateKernelFeaturesPass(PassRegistry &);
extern char &AMDGPUAnnotateKernelFeaturesID;
FunctionPass *createAMDGPUAtomicOptimizerPass();
void initializeAMDGPUAtomicOptimizerPass(PassRegistry &);
extern char &AMDGPUAtomicOptimizerID;
ModulePass *createAMDGPULowerIntrinsicsPass();
void initializeAMDGPULowerIntrinsicsPass(PassRegistry &);
extern char &AMDGPULowerIntrinsicsID;
ModulePass *createAMDGPUFixFunctionBitcastsPass();
void initializeAMDGPUFixFunctionBitcastsPass(PassRegistry &);
extern char &AMDGPUFixFunctionBitcastsID;
FunctionPass *createAMDGPULowerKernelArgumentsPass();
void initializeAMDGPULowerKernelArgumentsPass(PassRegistry &);
extern char &AMDGPULowerKernelArgumentsID;
ModulePass *createAMDGPULowerKernelAttributesPass();
void initializeAMDGPULowerKernelAttributesPass(PassRegistry &);
extern char &AMDGPULowerKernelAttributesID;
void initializeAMDGPUPropagateAttributesEarlyPass(PassRegistry &);
extern char &AMDGPUPropagateAttributesEarlyID;
void initializeAMDGPUPropagateAttributesLatePass(PassRegistry &);
extern char &AMDGPUPropagateAttributesLateID;
void initializeAMDGPURewriteOutArgumentsPass(PassRegistry &);
extern char &AMDGPURewriteOutArgumentsID;
void initializeGCNDPPCombinePass(PassRegistry &);
extern char &GCNDPPCombineID;
void initializeR600ClauseMergePassPass(PassRegistry &);
extern char &R600ClauseMergePassID;
void initializeR600ControlFlowFinalizerPass(PassRegistry &);
extern char &R600ControlFlowFinalizerID;
void initializeR600ExpandSpecialInstrsPassPass(PassRegistry &);
extern char &R600ExpandSpecialInstrsPassID;
void initializeR600VectorRegMergerPass(PassRegistry &);
extern char &R600VectorRegMergerID;
void initializeR600PacketizerPass(PassRegistry &);
extern char &R600PacketizerID;
void initializeSIFoldOperandsPass(PassRegistry &);
extern char &SIFoldOperandsID;
void initializeSIPeepholeSDWAPass(PassRegistry &);
extern char &SIPeepholeSDWAID;
void initializeSIShrinkInstructionsPass(PassRegistry&);
extern char &SIShrinkInstructionsID;
void initializeSIFixSGPRCopiesPass(PassRegistry &);
extern char &SIFixSGPRCopiesID;
void initializeSIFixVGPRCopiesPass(PassRegistry &);
extern char &SIFixVGPRCopiesID;
void initializeSIFixupVectorISelPass(PassRegistry &);
extern char &SIFixupVectorISelID;
void initializeSILowerI1CopiesPass(PassRegistry &);
extern char &SILowerI1CopiesID;
void initializeSILowerSGPRSpillsPass(PassRegistry &);
extern char &SILowerSGPRSpillsID;
void initializeSILoadStoreOptimizerPass(PassRegistry &);
extern char &SILoadStoreOptimizerID;
void initializeSIWholeQuadModePass(PassRegistry &);
extern char &SIWholeQuadModeID;
void initializeSILowerControlFlowPass(PassRegistry &);
extern char &SILowerControlFlowID;
void initializeSIInsertSkipsPass(PassRegistry &);
extern char &SIInsertSkipsPassID;
void initializeSIOptimizeExecMaskingPass(PassRegistry &);
extern char &SIOptimizeExecMaskingID;
void initializeSIPreAllocateWWMRegsPass(PassRegistry &);
extern char &SIPreAllocateWWMRegsID;
void initializeAMDGPUSimplifyLibCallsPass(PassRegistry &);
extern char &AMDGPUSimplifyLibCallsID;
void initializeAMDGPUUseNativeCallsPass(PassRegistry &);
extern char &AMDGPUUseNativeCallsID;
void initializeSIAddIMGInitPass(PassRegistry &);
extern char &SIAddIMGInitID;
void initializeAMDGPUPerfHintAnalysisPass(PassRegistry &);
extern char &AMDGPUPerfHintAnalysisID;
// Passes common to R600 and SI
FunctionPass *createAMDGPUPromoteAlloca();
void initializeAMDGPUPromoteAllocaPass(PassRegistry&);
extern char &AMDGPUPromoteAllocaID;
Pass *createAMDGPUStructurizeCFGPass();
FunctionPass *createAMDGPUISelDag(
TargetMachine *TM = nullptr,
CodeGenOpt::Level OptLevel = CodeGenOpt::Default);
ModulePass *createAMDGPUAlwaysInlinePass(bool GlobalOpt = true);
ModulePass *createR600OpenCLImageTypeLoweringPass();
FunctionPass *createAMDGPUAnnotateUniformValues();
ModulePass *createAMDGPUPrintfRuntimeBinding();
void initializeAMDGPUPrintfRuntimeBindingPass(PassRegistry&);
extern char &AMDGPUPrintfRuntimeBindingID;
ModulePass* createAMDGPUUnifyMetadataPass();
void initializeAMDGPUUnifyMetadataPass(PassRegistry&);
extern char &AMDGPUUnifyMetadataID;
void initializeSIOptimizeExecMaskingPreRAPass(PassRegistry&);
extern char &SIOptimizeExecMaskingPreRAID;
void initializeAMDGPUAnnotateUniformValuesPass(PassRegistry&);
extern char &AMDGPUAnnotateUniformValuesPassID;
void initializeAMDGPUCodeGenPreparePass(PassRegistry&);
extern char &AMDGPUCodeGenPrepareID;
void initializeSIAnnotateControlFlowPass(PassRegistry&);
extern char &SIAnnotateControlFlowPassID;
void initializeSIMemoryLegalizerPass(PassRegistry&);
extern char &SIMemoryLegalizerID;
void initializeSIModeRegisterPass(PassRegistry&);
extern char &SIModeRegisterID;
void initializeSIInsertWaitcntsPass(PassRegistry&);
extern char &SIInsertWaitcntsID;
void initializeSIFormMemoryClausesPass(PassRegistry&);
extern char &SIFormMemoryClausesID;
void initializeAMDGPUUnifyDivergentExitNodesPass(PassRegistry&);
extern char &AMDGPUUnifyDivergentExitNodesID;
ImmutablePass *createAMDGPUAAWrapperPass();
void initializeAMDGPUAAWrapperPassPass(PassRegistry&);
ImmutablePass *createAMDGPUExternalAAWrapperPass();
void initializeAMDGPUExternalAAWrapperPass(PassRegistry&);
void initializeAMDGPUArgumentUsageInfoPass(PassRegistry &);
Pass *createAMDGPUFunctionInliningPass();
void initializeAMDGPUInlinerPass(PassRegistry&);
ModulePass *createAMDGPUOpenCLEnqueuedBlockLoweringPass();
void initializeAMDGPUOpenCLEnqueuedBlockLoweringPass(PassRegistry &);
extern char &AMDGPUOpenCLEnqueuedBlockLoweringID;
void initializeGCNRegBankReassignPass(PassRegistry &);
extern char &GCNRegBankReassignID;
void initializeGCNNSAReassignPass(PassRegistry &);
extern char &GCNNSAReassignID;
namespace AMDGPU {
enum TargetIndex {
TI_CONSTDATA_START,
TI_SCRATCH_RSRC_DWORD0,
TI_SCRATCH_RSRC_DWORD1,
TI_SCRATCH_RSRC_DWORD2,
TI_SCRATCH_RSRC_DWORD3
};
}
} // End namespace llvm
/// OpenCL uses address spaces to differentiate between
/// various memory regions on the hardware. On the CPU
/// all of the address spaces point to the same memory,
/// however on the GPU, each address space points to
/// a separate piece of memory that is unique from other
/// memory locations.
namespace AMDGPUAS {
enum : unsigned {
// The maximum value for flat, generic, local, private, constant and region.
MAX_AMDGPU_ADDRESS = 7,
FLAT_ADDRESS = 0, ///< Address space for flat memory.
GLOBAL_ADDRESS = 1, ///< Address space for global memory (RAT0, VTX0).
REGION_ADDRESS = 2, ///< Address space for region memory. (GDS)
CONSTANT_ADDRESS = 4, ///< Address space for constant memory (VTX2).
LOCAL_ADDRESS = 3, ///< Address space for local memory.
PRIVATE_ADDRESS = 5, ///< Address space for private memory.
CONSTANT_ADDRESS_32BIT = 6, ///< Address space for 32-bit constant memory.
BUFFER_FAT_POINTER = 7, ///< Address space for 160-bit buffer fat pointers.
/// Address space for direct addressible parameter memory (CONST0).
PARAM_D_ADDRESS = 6,
/// Address space for indirect addressible parameter memory (VTX1).
PARAM_I_ADDRESS = 7,
// Do not re-order the CONSTANT_BUFFER_* enums. Several places depend on
// this order to be able to dynamically index a constant buffer, for
// example:
//
// ConstantBufferAS = CONSTANT_BUFFER_0 + CBIdx
CONSTANT_BUFFER_0 = 8,
CONSTANT_BUFFER_1 = 9,
CONSTANT_BUFFER_2 = 10,
CONSTANT_BUFFER_3 = 11,
CONSTANT_BUFFER_4 = 12,
CONSTANT_BUFFER_5 = 13,
CONSTANT_BUFFER_6 = 14,
CONSTANT_BUFFER_7 = 15,
CONSTANT_BUFFER_8 = 16,
CONSTANT_BUFFER_9 = 17,
CONSTANT_BUFFER_10 = 18,
CONSTANT_BUFFER_11 = 19,
CONSTANT_BUFFER_12 = 20,
CONSTANT_BUFFER_13 = 21,
CONSTANT_BUFFER_14 = 22,
CONSTANT_BUFFER_15 = 23,
// Some places use this if the address space can't be determined.
UNKNOWN_ADDRESS_SPACE = ~0u,
};
}
#endif
|