llvm.org GIT mirror llvm / 0392724 lib / Target / AMDGPU / MCTargetDesc / AMDGPUTargetStreamer.cpp
0392724

Tree @0392724 (Download .tar.gz)

AMDGPUTargetStreamer.cpp @0392724raw · history · blame

  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
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
//===-- AMDGPUTargetStreamer.cpp - Mips Target Streamer Methods -----------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file provides AMDGPU specific target streamer methods.
//
//===----------------------------------------------------------------------===//

#include "AMDGPUTargetStreamer.h"
#include "AMDGPU.h"
#include "SIDefines.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "Utils/AMDKernelCodeTUtils.h"
#include "llvm/ADT/Twine.h"
#include "llvm/BinaryFormat/AMDGPUMetadataVerifier.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCELFStreamer.h"
#include "llvm/MC/MCObjectFileInfo.h"
#include "llvm/MC/MCSectionELF.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/TargetParser.h"

namespace llvm {
#include "AMDGPUPTNote.h"
}

using namespace llvm;
using namespace llvm::AMDGPU;
using namespace llvm::AMDGPU::HSAMD;

//===----------------------------------------------------------------------===//
// AMDGPUTargetStreamer
//===----------------------------------------------------------------------===//

bool AMDGPUTargetStreamer::EmitHSAMetadataV2(StringRef HSAMetadataString) {
  HSAMD::Metadata HSAMetadata;
  if (HSAMD::fromString(HSAMetadataString, HSAMetadata))
    return false;

  return EmitHSAMetadata(HSAMetadata);
}

bool AMDGPUTargetStreamer::EmitHSAMetadataV3(StringRef HSAMetadataString) {
  msgpack::Document HSAMetadataDoc;
  if (!HSAMetadataDoc.fromYAML(HSAMetadataString))
    return false;
  return EmitHSAMetadata(HSAMetadataDoc, false);
}

StringRef AMDGPUTargetStreamer::getArchNameFromElfMach(unsigned ElfMach) {
  AMDGPU::GPUKind AK;

  switch (ElfMach) {
  case ELF::EF_AMDGPU_MACH_R600_R600:      AK = GK_R600;    break;
  case ELF::EF_AMDGPU_MACH_R600_R630:      AK = GK_R630;    break;
  case ELF::EF_AMDGPU_MACH_R600_RS880:     AK = GK_RS880;   break;
  case ELF::EF_AMDGPU_MACH_R600_RV670:     AK = GK_RV670;   break;
  case ELF::EF_AMDGPU_MACH_R600_RV710:     AK = GK_RV710;   break;
  case ELF::EF_AMDGPU_MACH_R600_RV730:     AK = GK_RV730;   break;
  case ELF::EF_AMDGPU_MACH_R600_RV770:     AK = GK_RV770;   break;
  case ELF::EF_AMDGPU_MACH_R600_CEDAR:     AK = GK_CEDAR;   break;
  case ELF::EF_AMDGPU_MACH_R600_CYPRESS:   AK = GK_CYPRESS; break;
  case ELF::EF_AMDGPU_MACH_R600_JUNIPER:   AK = GK_JUNIPER; break;
  case ELF::EF_AMDGPU_MACH_R600_REDWOOD:   AK = GK_REDWOOD; break;
  case ELF::EF_AMDGPU_MACH_R600_SUMO:      AK = GK_SUMO;    break;
  case ELF::EF_AMDGPU_MACH_R600_BARTS:     AK = GK_BARTS;   break;
  case ELF::EF_AMDGPU_MACH_R600_CAICOS:    AK = GK_CAICOS;  break;
  case ELF::EF_AMDGPU_MACH_R600_CAYMAN:    AK = GK_CAYMAN;  break;
  case ELF::EF_AMDGPU_MACH_R600_TURKS:     AK = GK_TURKS;   break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX600:  AK = GK_GFX600;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX601:  AK = GK_GFX601;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX700:  AK = GK_GFX700;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX701:  AK = GK_GFX701;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX702:  AK = GK_GFX702;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX703:  AK = GK_GFX703;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX704:  AK = GK_GFX704;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX801:  AK = GK_GFX801;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX802:  AK = GK_GFX802;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX803:  AK = GK_GFX803;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX810:  AK = GK_GFX810;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX900:  AK = GK_GFX900;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX902:  AK = GK_GFX902;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX904:  AK = GK_GFX904;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX906:  AK = GK_GFX906;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX908:  AK = GK_GFX908;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX909:  AK = GK_GFX909;  break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010: AK = GK_GFX1010; break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011: AK = GK_GFX1011; break;
  case ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012: AK = GK_GFX1012; break;
  case ELF::EF_AMDGPU_MACH_NONE:           AK = GK_NONE;    break;
  }

  StringRef GPUName = getArchNameAMDGCN(AK);
  if (GPUName != "")
    return GPUName;
  return getArchNameR600(AK);
}

unsigned AMDGPUTargetStreamer::getElfMach(StringRef GPU) {
  AMDGPU::GPUKind AK = parseArchAMDGCN(GPU);
  if (AK == AMDGPU::GPUKind::GK_NONE)
    AK = parseArchR600(GPU);

  switch (AK) {
  case GK_R600:    return ELF::EF_AMDGPU_MACH_R600_R600;
  case GK_R630:    return ELF::EF_AMDGPU_MACH_R600_R630;
  case GK_RS880:   return ELF::EF_AMDGPU_MACH_R600_RS880;
  case GK_RV670:   return ELF::EF_AMDGPU_MACH_R600_RV670;
  case GK_RV710:   return ELF::EF_AMDGPU_MACH_R600_RV710;
  case GK_RV730:   return ELF::EF_AMDGPU_MACH_R600_RV730;
  case GK_RV770:   return ELF::EF_AMDGPU_MACH_R600_RV770;
  case GK_CEDAR:   return ELF::EF_AMDGPU_MACH_R600_CEDAR;
  case GK_CYPRESS: return ELF::EF_AMDGPU_MACH_R600_CYPRESS;
  case GK_JUNIPER: return ELF::EF_AMDGPU_MACH_R600_JUNIPER;
  case GK_REDWOOD: return ELF::EF_AMDGPU_MACH_R600_REDWOOD;
  case GK_SUMO:    return ELF::EF_AMDGPU_MACH_R600_SUMO;
  case GK_BARTS:   return ELF::EF_AMDGPU_MACH_R600_BARTS;
  case GK_CAICOS:  return ELF::EF_AMDGPU_MACH_R600_CAICOS;
  case GK_CAYMAN:  return ELF::EF_AMDGPU_MACH_R600_CAYMAN;
  case GK_TURKS:   return ELF::EF_AMDGPU_MACH_R600_TURKS;
  case GK_GFX600:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX600;
  case GK_GFX601:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX601;
  case GK_GFX700:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX700;
  case GK_GFX701:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX701;
  case GK_GFX702:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX702;
  case GK_GFX703:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX703;
  case GK_GFX704:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX704;
  case GK_GFX801:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX801;
  case GK_GFX802:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX802;
  case GK_GFX803:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX803;
  case GK_GFX810:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX810;
  case GK_GFX900:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX900;
  case GK_GFX902:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX902;
  case GK_GFX904:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX904;
  case GK_GFX906:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX906;
  case GK_GFX908:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX908;
  case GK_GFX909:  return ELF::EF_AMDGPU_MACH_AMDGCN_GFX909;
  case GK_GFX1010: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1010;
  case GK_GFX1011: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1011;
  case GK_GFX1012: return ELF::EF_AMDGPU_MACH_AMDGCN_GFX1012;
  case GK_NONE:    return ELF::EF_AMDGPU_MACH_NONE;
  }

  llvm_unreachable("unknown GPU");
}

//===----------------------------------------------------------------------===//
// AMDGPUTargetAsmStreamer
//===----------------------------------------------------------------------===//

AMDGPUTargetAsmStreamer::AMDGPUTargetAsmStreamer(MCStreamer &S,
                                                 formatted_raw_ostream &OS)
    : AMDGPUTargetStreamer(S), OS(OS) { }

// A hook for emitting stuff at the end.
// We use it for emitting the accumulated PAL metadata as directives.
void AMDGPUTargetAsmStreamer::finish() {
  std::string S;
  getPALMetadata()->toString(S);
  OS << S;
}

void AMDGPUTargetAsmStreamer::EmitDirectiveAMDGCNTarget(StringRef Target) {
  OS << "\t.amdgcn_target \"" << Target << "\"\n";
}

void AMDGPUTargetAsmStreamer::EmitDirectiveHSACodeObjectVersion(
    uint32_t Major, uint32_t Minor) {
  OS << "\t.hsa_code_object_version " <<
        Twine(Major) << "," << Twine(Minor) << '\n';
}

void
AMDGPUTargetAsmStreamer::EmitDirectiveHSACodeObjectISA(uint32_t Major,
                                                       uint32_t Minor,
                                                       uint32_t Stepping,
                                                       StringRef VendorName,
                                                       StringRef ArchName) {
  OS << "\t.hsa_code_object_isa " <<
        Twine(Major) << "," << Twine(Minor) << "," << Twine(Stepping) <<
        ",\"" << VendorName << "\",\"" << ArchName << "\"\n";

}

void
AMDGPUTargetAsmStreamer::EmitAMDKernelCodeT(const amd_kernel_code_t &Header) {
  OS << "\t.amd_kernel_code_t\n";
  dumpAmdKernelCode(&Header, OS, "\t\t");
  OS << "\t.end_amd_kernel_code_t\n";
}

void AMDGPUTargetAsmStreamer::EmitAMDGPUSymbolType(StringRef SymbolName,
                                                   unsigned Type) {
  switch (Type) {
    default: llvm_unreachable("Invalid AMDGPU symbol type");
    case ELF::STT_AMDGPU_HSA_KERNEL:
      OS << "\t.amdgpu_hsa_kernel " << SymbolName << '\n' ;
      break;
  }
}

void AMDGPUTargetAsmStreamer::emitAMDGPULDS(MCSymbol *Symbol, unsigned Size,
                                            unsigned Align) {
  OS << "\t.amdgpu_lds " << Symbol->getName() << ", " << Size << ", " << Align
     << '\n';
}

bool AMDGPUTargetAsmStreamer::EmitISAVersion(StringRef IsaVersionString) {
  OS << "\t.amd_amdgpu_isa \"" << IsaVersionString << "\"\n";
  return true;
}

bool AMDGPUTargetAsmStreamer::EmitHSAMetadata(
    const AMDGPU::HSAMD::Metadata &HSAMetadata) {
  std::string HSAMetadataString;
  if (HSAMD::toString(HSAMetadata, HSAMetadataString))
    return false;

  OS << '\t' << AssemblerDirectiveBegin << '\n';
  OS << HSAMetadataString << '\n';
  OS << '\t' << AssemblerDirectiveEnd << '\n';
  return true;
}

bool AMDGPUTargetAsmStreamer::EmitHSAMetadata(
    msgpack::Document &HSAMetadataDoc, bool Strict) {
  V3::MetadataVerifier Verifier(Strict);
  if (!Verifier.verify(HSAMetadataDoc.getRoot()))
    return false;

  std::string HSAMetadataString;
  raw_string_ostream StrOS(HSAMetadataString);
  HSAMetadataDoc.toYAML(StrOS);

  OS << '\t' << V3::AssemblerDirectiveBegin << '\n';
  OS << StrOS.str() << '\n';
  OS << '\t' << V3::AssemblerDirectiveEnd << '\n';
  return true;
}

bool AMDGPUTargetAsmStreamer::EmitCodeEnd() {
  const uint32_t Encoded_s_code_end = 0xbf9f0000;
  OS << "\t.p2alignl 6, " << Encoded_s_code_end << '\n';
  OS << "\t.fill 32, 4, " << Encoded_s_code_end << '\n';
  return true;
}

void AMDGPUTargetAsmStreamer::EmitAmdhsaKernelDescriptor(
    const MCSubtargetInfo &STI, StringRef KernelName,
    const amdhsa::kernel_descriptor_t &KD, uint64_t NextVGPR, uint64_t NextSGPR,
    bool ReserveVCC, bool ReserveFlatScr, bool ReserveXNACK) {
  IsaVersion IVersion = getIsaVersion(STI.getCPU());

  OS << "\t.amdhsa_kernel " << KernelName << '\n';

#define PRINT_FIELD(STREAM, DIRECTIVE, KERNEL_DESC, MEMBER_NAME, FIELD_NAME)   \
  STREAM << "\t\t" << DIRECTIVE << " "                                         \
         << AMDHSA_BITS_GET(KERNEL_DESC.MEMBER_NAME, FIELD_NAME) << '\n';

  OS << "\t\t.amdhsa_group_segment_fixed_size " << KD.group_segment_fixed_size
     << '\n';
  OS << "\t\t.amdhsa_private_segment_fixed_size "
     << KD.private_segment_fixed_size << '\n';

  PRINT_FIELD(OS, ".amdhsa_user_sgpr_private_segment_buffer", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_BUFFER);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_dispatch_ptr", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_PTR);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_queue_ptr", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_QUEUE_PTR);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_kernarg_segment_ptr", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_KERNARG_SEGMENT_PTR);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_dispatch_id", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_ID);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_flat_scratch_init", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_FLAT_SCRATCH_INIT);
  PRINT_FIELD(OS, ".amdhsa_user_sgpr_private_segment_size", KD,
              kernel_code_properties,
              amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_SIZE);
  if (IVersion.Major >= 10)
    PRINT_FIELD(OS, ".amdhsa_wavefront_size32", KD,
                kernel_code_properties,
                amdhsa::KERNEL_CODE_PROPERTY_ENABLE_WAVEFRONT_SIZE32);
  PRINT_FIELD(
      OS, ".amdhsa_system_sgpr_private_segment_wavefront_offset", KD,
      compute_pgm_rsrc2,
      amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_PRIVATE_SEGMENT_WAVEFRONT_OFFSET);
  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_x", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_X);
  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_y", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_Y);
  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_z", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_Z);
  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_info", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_INFO);
  PRINT_FIELD(OS, ".amdhsa_system_vgpr_workitem_id", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_VGPR_WORKITEM_ID);

  // These directives are required.
  OS << "\t\t.amdhsa_next_free_vgpr " << NextVGPR << '\n';
  OS << "\t\t.amdhsa_next_free_sgpr " << NextSGPR << '\n';

  if (!ReserveVCC)
    OS << "\t\t.amdhsa_reserve_vcc " << ReserveVCC << '\n';
  if (IVersion.Major >= 7 && !ReserveFlatScr)
    OS << "\t\t.amdhsa_reserve_flat_scratch " << ReserveFlatScr << '\n';
  if (IVersion.Major >= 8 && ReserveXNACK != hasXNACK(STI))
    OS << "\t\t.amdhsa_reserve_xnack_mask " << ReserveXNACK << '\n';

  PRINT_FIELD(OS, ".amdhsa_float_round_mode_32", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_FLOAT_ROUND_MODE_32);
  PRINT_FIELD(OS, ".amdhsa_float_round_mode_16_64", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_FLOAT_ROUND_MODE_16_64);
  PRINT_FIELD(OS, ".amdhsa_float_denorm_mode_32", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_FLOAT_DENORM_MODE_32);
  PRINT_FIELD(OS, ".amdhsa_float_denorm_mode_16_64", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_FLOAT_DENORM_MODE_16_64);
  PRINT_FIELD(OS, ".amdhsa_dx10_clamp", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_ENABLE_DX10_CLAMP);
  PRINT_FIELD(OS, ".amdhsa_ieee_mode", KD,
              compute_pgm_rsrc1,
              amdhsa::COMPUTE_PGM_RSRC1_ENABLE_IEEE_MODE);
  if (IVersion.Major >= 9)
    PRINT_FIELD(OS, ".amdhsa_fp16_overflow", KD,
                compute_pgm_rsrc1,
                amdhsa::COMPUTE_PGM_RSRC1_FP16_OVFL);
  if (IVersion.Major >= 10) {
    PRINT_FIELD(OS, ".amdhsa_workgroup_processor_mode", KD,
                compute_pgm_rsrc1,
                amdhsa::COMPUTE_PGM_RSRC1_WGP_MODE);
    PRINT_FIELD(OS, ".amdhsa_memory_ordered", KD,
                compute_pgm_rsrc1,
                amdhsa::COMPUTE_PGM_RSRC1_MEM_ORDERED);
    PRINT_FIELD(OS, ".amdhsa_forward_progress", KD,
                compute_pgm_rsrc1,
                amdhsa::COMPUTE_PGM_RSRC1_FWD_PROGRESS);
  }
  PRINT_FIELD(
      OS, ".amdhsa_exception_fp_ieee_invalid_op", KD,
      compute_pgm_rsrc2,
      amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_INVALID_OPERATION);
  PRINT_FIELD(OS, ".amdhsa_exception_fp_denorm_src", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_FP_DENORMAL_SOURCE);
  PRINT_FIELD(
      OS, ".amdhsa_exception_fp_ieee_div_zero", KD,
      compute_pgm_rsrc2,
      amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_DIVISION_BY_ZERO);
  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_overflow", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_OVERFLOW);
  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_underflow", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_UNDERFLOW);
  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_inexact", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_INEXACT);
  PRINT_FIELD(OS, ".amdhsa_exception_int_div_zero", KD,
              compute_pgm_rsrc2,
              amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_INT_DIVIDE_BY_ZERO);
#undef PRINT_FIELD

  OS << "\t.end_amdhsa_kernel\n";
}

//===----------------------------------------------------------------------===//
// AMDGPUTargetELFStreamer
//===----------------------------------------------------------------------===//

AMDGPUTargetELFStreamer::AMDGPUTargetELFStreamer(
    MCStreamer &S, const MCSubtargetInfo &STI)
    : AMDGPUTargetStreamer(S), Streamer(S) {
  MCAssembler &MCA = getStreamer().getAssembler();
  unsigned EFlags = MCA.getELFHeaderEFlags();

  EFlags &= ~ELF::EF_AMDGPU_MACH;
  EFlags |= getElfMach(STI.getCPU());

  EFlags &= ~ELF::EF_AMDGPU_XNACK;
  if (AMDGPU::hasXNACK(STI))
    EFlags |= ELF::EF_AMDGPU_XNACK;

  EFlags &= ~ELF::EF_AMDGPU_SRAM_ECC;
  if (AMDGPU::hasSRAMECC(STI))
    EFlags |= ELF::EF_AMDGPU_SRAM_ECC;

  MCA.setELFHeaderEFlags(EFlags);
}

MCELFStreamer &AMDGPUTargetELFStreamer::getStreamer() {
  return static_cast<MCELFStreamer &>(Streamer);
}

// A hook for emitting stuff at the end.
// We use it for emitting the accumulated PAL metadata as a .note record.
void AMDGPUTargetELFStreamer::finish() {
  std::string Blob;
  const char *Vendor = getPALMetadata()->getVendor();
  unsigned Type = getPALMetadata()->getType();
  getPALMetadata()->toBlob(Type, Blob);
  if (Blob.empty())
    return;
  EmitNote(Vendor, MCConstantExpr::create(Blob.size(), getContext()), Type,
           [&](MCELFStreamer &OS) { OS.EmitBytes(Blob); });
}

void AMDGPUTargetELFStreamer::EmitNote(
    StringRef Name, const MCExpr *DescSZ, unsigned NoteType,
    function_ref<void(MCELFStreamer &)> EmitDesc) {
  auto &S = getStreamer();
  auto &Context = S.getContext();

  auto NameSZ = Name.size() + 1;

  S.PushSection();
  S.SwitchSection(Context.getELFSection(
    ElfNote::SectionName, ELF::SHT_NOTE, ELF::SHF_ALLOC));
  S.EmitIntValue(NameSZ, 4);                                  // namesz
  S.EmitValue(DescSZ, 4);                                     // descz
  S.EmitIntValue(NoteType, 4);                                // type
  S.EmitBytes(Name);                                          // name
  S.EmitValueToAlignment(4, 0, 1, 0);                         // padding 0
  EmitDesc(S);                                                // desc
  S.EmitValueToAlignment(4, 0, 1, 0);                         // padding 0
  S.PopSection();
}

void AMDGPUTargetELFStreamer::EmitDirectiveAMDGCNTarget(StringRef Target) {}

void AMDGPUTargetELFStreamer::EmitDirectiveHSACodeObjectVersion(
    uint32_t Major, uint32_t Minor) {

  EmitNote(ElfNote::NoteNameV2, MCConstantExpr::create(8, getContext()),
           ElfNote::NT_AMDGPU_HSA_CODE_OBJECT_VERSION, [&](MCELFStreamer &OS) {
             OS.EmitIntValue(Major, 4);
             OS.EmitIntValue(Minor, 4);
           });
}

void
AMDGPUTargetELFStreamer::EmitDirectiveHSACodeObjectISA(uint32_t Major,
                                                       uint32_t Minor,
                                                       uint32_t Stepping,
                                                       StringRef VendorName,
                                                       StringRef ArchName) {
  uint16_t VendorNameSize = VendorName.size() + 1;
  uint16_t ArchNameSize = ArchName.size() + 1;

  unsigned DescSZ = sizeof(VendorNameSize) + sizeof(ArchNameSize) +
    sizeof(Major) + sizeof(Minor) + sizeof(Stepping) +
    VendorNameSize + ArchNameSize;

  EmitNote(ElfNote::NoteNameV2, MCConstantExpr::create(DescSZ, getContext()),
           ElfNote::NT_AMDGPU_HSA_ISA, [&](MCELFStreamer &OS) {
             OS.EmitIntValue(VendorNameSize, 2);
             OS.EmitIntValue(ArchNameSize, 2);
             OS.EmitIntValue(Major, 4);
             OS.EmitIntValue(Minor, 4);
             OS.EmitIntValue(Stepping, 4);
             OS.EmitBytes(VendorName);
             OS.EmitIntValue(0, 1); // NULL terminate VendorName
             OS.EmitBytes(ArchName);
             OS.EmitIntValue(0, 1); // NULL terminte ArchName
           });
}

void
AMDGPUTargetELFStreamer::EmitAMDKernelCodeT(const amd_kernel_code_t &Header) {

  MCStreamer &OS = getStreamer();
  OS.PushSection();
  OS.EmitBytes(StringRef((const char*)&Header, sizeof(Header)));
  OS.PopSection();
}

void AMDGPUTargetELFStreamer::EmitAMDGPUSymbolType(StringRef SymbolName,
                                                   unsigned Type) {
  MCSymbolELF *Symbol = cast<MCSymbolELF>(
      getStreamer().getContext().getOrCreateSymbol(SymbolName));
  Symbol->setType(Type);
}

void AMDGPUTargetELFStreamer::emitAMDGPULDS(MCSymbol *Symbol, unsigned Size,
                                            unsigned Align) {
  assert(isPowerOf2_32(Align));

  MCSymbolELF *SymbolELF = cast<MCSymbolELF>(Symbol);
  SymbolELF->setType(ELF::STT_OBJECT);

  if (!SymbolELF->isBindingSet()) {
    SymbolELF->setBinding(ELF::STB_GLOBAL);
    SymbolELF->setExternal(true);
  }

  if (SymbolELF->declareCommon(Size, Align, true)) {
    report_fatal_error("Symbol: " + Symbol->getName() +
                       " redeclared as different type");
  }

  SymbolELF->setIndex(ELF::SHN_AMDGPU_LDS);
  SymbolELF->setSize(MCConstantExpr::create(Size, getContext()));
}

bool AMDGPUTargetELFStreamer::EmitISAVersion(StringRef IsaVersionString) {
  // Create two labels to mark the beginning and end of the desc field
  // and a MCExpr to calculate the size of the desc field.
  auto &Context = getContext();
  auto *DescBegin = Context.createTempSymbol();
  auto *DescEnd = Context.createTempSymbol();
  auto *DescSZ = MCBinaryExpr::createSub(
    MCSymbolRefExpr::create(DescEnd, Context),
    MCSymbolRefExpr::create(DescBegin, Context), Context);

  EmitNote(ElfNote::NoteNameV2, DescSZ, ELF::NT_AMD_AMDGPU_ISA,
           [&](MCELFStreamer &OS) {
             OS.EmitLabel(DescBegin);
             OS.EmitBytes(IsaVersionString);
             OS.EmitLabel(DescEnd);
           });
  return true;
}

bool AMDGPUTargetELFStreamer::EmitHSAMetadata(msgpack::Document &HSAMetadataDoc,
                                              bool Strict) {
  V3::MetadataVerifier Verifier(Strict);
  if (!Verifier.verify(HSAMetadataDoc.getRoot()))
    return false;

  std::string HSAMetadataString;
  HSAMetadataDoc.writeToBlob(HSAMetadataString);

  // Create two labels to mark the beginning and end of the desc field
  // and a MCExpr to calculate the size of the desc field.
  auto &Context = getContext();
  auto *DescBegin = Context.createTempSymbol();
  auto *DescEnd = Context.createTempSymbol();
  auto *DescSZ = MCBinaryExpr::createSub(
      MCSymbolRefExpr::create(DescEnd, Context),
      MCSymbolRefExpr::create(DescBegin, Context), Context);

  EmitNote(ElfNote::NoteNameV3, DescSZ, ELF::NT_AMDGPU_METADATA,
           [&](MCELFStreamer &OS) {
             OS.EmitLabel(DescBegin);
             OS.EmitBytes(HSAMetadataString);
             OS.EmitLabel(DescEnd);
           });
  return true;
}

bool AMDGPUTargetELFStreamer::EmitHSAMetadata(
    const AMDGPU::HSAMD::Metadata &HSAMetadata) {
  std::string HSAMetadataString;
  if (HSAMD::toString(HSAMetadata, HSAMetadataString))
    return false;

  // Create two labels to mark the beginning and end of the desc field
  // and a MCExpr to calculate the size of the desc field.
  auto &Context = getContext();
  auto *DescBegin = Context.createTempSymbol();
  auto *DescEnd = Context.createTempSymbol();
  auto *DescSZ = MCBinaryExpr::createSub(
    MCSymbolRefExpr::create(DescEnd, Context),
    MCSymbolRefExpr::create(DescBegin, Context), Context);

  EmitNote(ElfNote::NoteNameV2, DescSZ, ELF::NT_AMD_AMDGPU_HSA_METADATA,
           [&](MCELFStreamer &OS) {
             OS.EmitLabel(DescBegin);
             OS.EmitBytes(HSAMetadataString);
             OS.EmitLabel(DescEnd);
           });
  return true;
}

bool AMDGPUTargetELFStreamer::EmitCodeEnd() {
  const uint32_t Encoded_s_code_end = 0xbf9f0000;

  MCStreamer &OS = getStreamer();
  OS.PushSection();
  OS.EmitValueToAlignment(64, Encoded_s_code_end, 4);
  for (unsigned I = 0; I < 32; ++I)
    OS.EmitIntValue(Encoded_s_code_end, 4);
  OS.PopSection();
  return true;
}

void AMDGPUTargetELFStreamer::EmitAmdhsaKernelDescriptor(
    const MCSubtargetInfo &STI, StringRef KernelName,
    const amdhsa::kernel_descriptor_t &KernelDescriptor, uint64_t NextVGPR,
    uint64_t NextSGPR, bool ReserveVCC, bool ReserveFlatScr,
    bool ReserveXNACK) {
  auto &Streamer = getStreamer();
  auto &Context = Streamer.getContext();

  MCSymbolELF *KernelCodeSymbol = cast<MCSymbolELF>(
      Context.getOrCreateSymbol(Twine(KernelName)));
  MCSymbolELF *KernelDescriptorSymbol = cast<MCSymbolELF>(
      Context.getOrCreateSymbol(Twine(KernelName) + Twine(".kd")));

  // Copy kernel descriptor symbol's binding, other and visibility from the
  // kernel code symbol.
  KernelDescriptorSymbol->setBinding(KernelCodeSymbol->getBinding());
  KernelDescriptorSymbol->setOther(KernelCodeSymbol->getOther());
  KernelDescriptorSymbol->setVisibility(KernelCodeSymbol->getVisibility());
  // Kernel descriptor symbol's type and size are fixed.
  KernelDescriptorSymbol->setType(ELF::STT_OBJECT);
  KernelDescriptorSymbol->setSize(
      MCConstantExpr::create(sizeof(KernelDescriptor), Context));

  // The visibility of the kernel code symbol must be protected or less to allow
  // static relocations from the kernel descriptor to be used.
  if (KernelCodeSymbol->getVisibility() == ELF::STV_DEFAULT)
    KernelCodeSymbol->setVisibility(ELF::STV_PROTECTED);

  Streamer.EmitLabel(KernelDescriptorSymbol);
  Streamer.EmitBytes(StringRef(
      (const char*)&(KernelDescriptor),
      offsetof(amdhsa::kernel_descriptor_t, kernel_code_entry_byte_offset)));
  // FIXME: Remove the use of VK_AMDGPU_REL64 in the expression below. The
  // expression being created is:
  //   (start of kernel code) - (start of kernel descriptor)
  // It implies R_AMDGPU_REL64, but ends up being R_AMDGPU_ABS64.
  Streamer.EmitValue(MCBinaryExpr::createSub(
      MCSymbolRefExpr::create(
          KernelCodeSymbol, MCSymbolRefExpr::VK_AMDGPU_REL64, Context),
      MCSymbolRefExpr::create(
          KernelDescriptorSymbol, MCSymbolRefExpr::VK_None, Context),
      Context),
      sizeof(KernelDescriptor.kernel_code_entry_byte_offset));
  Streamer.EmitBytes(StringRef(
      (const char*)&(KernelDescriptor) +
          offsetof(amdhsa::kernel_descriptor_t, kernel_code_entry_byte_offset) +
          sizeof(KernelDescriptor.kernel_code_entry_byte_offset),
      sizeof(KernelDescriptor) -
          offsetof(amdhsa::kernel_descriptor_t, kernel_code_entry_byte_offset) -
          sizeof(KernelDescriptor.kernel_code_entry_byte_offset)));
}