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
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
|
//===-LTOBackend.cpp - LLVM Link Time Optimizer Backend -------------------===//
//
// 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 implements the "backend" phase of LTO, i.e. it performs
// optimization and code generation on a loaded module. It is generally used
// internally by the LTO class but can also be used independently, for example
// to implement a standalone ThinLTO backend.
//
//===----------------------------------------------------------------------===//
#include "llvm/LTO/LTOBackend.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CGSCCPassManager.h"
#include "llvm/Analysis/ModuleSummaryAnalysis.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Bitcode/BitcodeReader.h"
#include "llvm/Bitcode/BitcodeWriter.h"
#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/Verifier.h"
#include "llvm/LTO/LTO.h"
#include "llvm/MC/TargetRegistry.h"
#include "llvm/Object/ModuleSymbolTable.h"
#include "llvm/Passes/PassBuilder.h"
#include "llvm/Passes/PassPlugin.h"
#include "llvm/Passes/StandardInstrumentations.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/Program.h"
#include "llvm/Support/ThreadPool.h"
#include "llvm/Support/ToolOutputFile.h"
#include "llvm/Support/VirtualFileSystem.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/TargetParser/SubtargetFeature.h"
#include "llvm/Transforms/IPO/WholeProgramDevirt.h"
#include "llvm/Transforms/Scalar/LoopPassManager.h"
#include "llvm/Transforms/Utils/FunctionImportUtils.h"
#include "llvm/Transforms/Utils/SplitModule.h"
#include <optional>
using namespace llvm;
using namespace lto;
#define DEBUG_TYPE "lto-backend"
enum class LTOBitcodeEmbedding {
DoNotEmbed = 0,
EmbedOptimized = 1,
EmbedPostMergePreOptimized = 2
};
static cl::opt<LTOBitcodeEmbedding> EmbedBitcode(
"lto-embed-bitcode", cl::init(LTOBitcodeEmbedding::DoNotEmbed),
cl::values(clEnumValN(LTOBitcodeEmbedding::DoNotEmbed, "none",
"Do not embed"),
clEnumValN(LTOBitcodeEmbedding::EmbedOptimized, "optimized",
"Embed after all optimization passes"),
clEnumValN(LTOBitcodeEmbedding::EmbedPostMergePreOptimized,
"post-merge-pre-opt",
"Embed post merge, but before optimizations")),
cl::desc("Embed LLVM bitcode in object files produced by LTO"));
static cl::opt<bool> ThinLTOAssumeMerged(
"thinlto-assume-merged", cl::init(false),
cl::desc("Assume the input has already undergone ThinLTO function "
"importing and the other pre-optimization pipeline changes."));
namespace llvm {
extern cl::opt<bool> NoPGOWarnMismatch;
}
[[noreturn]] static void reportOpenError(StringRef Path, Twine Msg) {
errs() << "failed to open " << Path << ": " << Msg << '\n';
errs().flush();
exit(1);
}
Error Config::addSaveTemps(std::string OutputFileName, bool UseInputModulePath,
const DenseSet<StringRef> &SaveTempsArgs) {
ShouldDiscardValueNames = false;
std::error_code EC;
if (SaveTempsArgs.empty() || SaveTempsArgs.contains("resolution")) {
ResolutionFile =
std::make_unique<raw_fd_ostream>(OutputFileName + "resolution.txt", EC,
sys::fs::OpenFlags::OF_TextWithCRLF);
if (EC) {
ResolutionFile.reset();
return errorCodeToError(EC);
}
}
auto setHook = [&](std::string PathSuffix, ModuleHookFn &Hook) {
// Keep track of the hook provided by the linker, which also needs to run.
ModuleHookFn LinkerHook = Hook;
Hook = [=](unsigned Task, const Module &M) {
// If the linker's hook returned false, we need to pass that result
// through.
if (LinkerHook && !LinkerHook(Task, M))
return false;
std::string PathPrefix;
// If this is the combined module (not a ThinLTO backend compile) or the
// user hasn't requested using the input module's path, emit to a file
// named from the provided OutputFileName with the Task ID appended.
if (M.getModuleIdentifier() == "ld-temp.o" || !UseInputModulePath) {
PathPrefix = OutputFileName;
if (Task != (unsigned)-1)
PathPrefix += utostr(Task) + ".";
} else
PathPrefix = M.getModuleIdentifier() + ".";
std::string Path = PathPrefix + PathSuffix + ".bc";
std::error_code EC;
raw_fd_ostream OS(Path, EC, sys::fs::OpenFlags::OF_None);
// Because -save-temps is a debugging feature, we report the error
// directly and exit.
if (EC)
reportOpenError(Path, EC.message());
WriteBitcodeToFile(M, OS, /*ShouldPreserveUseListOrder=*/false);
return true;
};
};
auto SaveCombinedIndex =
[=](const ModuleSummaryIndex &Index,
const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) {
std::string Path = OutputFileName + "index.bc";
std::error_code EC;
raw_fd_ostream OS(Path, EC, sys::fs::OpenFlags::OF_None);
// Because -save-temps is a debugging feature, we report the error
// directly and exit.
if (EC)
reportOpenError(Path, EC.message());
writeIndexToFile(Index, OS);
Path = OutputFileName + "index.dot";
raw_fd_ostream OSDot(Path, EC, sys::fs::OpenFlags::OF_None);
if (EC)
reportOpenError(Path, EC.message());
Index.exportToDot(OSDot, GUIDPreservedSymbols);
return true;
};
if (SaveTempsArgs.empty()) {
setHook("0.preopt", PreOptModuleHook);
setHook("1.promote", PostPromoteModuleHook);
setHook("2.internalize", PostInternalizeModuleHook);
setHook("3.import", PostImportModuleHook);
setHook("4.opt", PostOptModuleHook);
setHook("5.precodegen", PreCodeGenModuleHook);
CombinedIndexHook = SaveCombinedIndex;
} else {
if (SaveTempsArgs.contains("preopt"))
setHook("0.preopt", PreOptModuleHook);
if (SaveTempsArgs.contains("promote"))
setHook("1.promote", PostPromoteModuleHook);
if (SaveTempsArgs.contains("internalize"))
setHook("2.internalize", PostInternalizeModuleHook);
if (SaveTempsArgs.contains("import"))
setHook("3.import", PostImportModuleHook);
if (SaveTempsArgs.contains("opt"))
setHook("4.opt", PostOptModuleHook);
if (SaveTempsArgs.contains("precodegen"))
setHook("5.precodegen", PreCodeGenModuleHook);
if (SaveTempsArgs.contains("combinedindex"))
CombinedIndexHook = SaveCombinedIndex;
}
return Error::success();
}
#define HANDLE_EXTENSION(Ext) \
llvm::PassPluginLibraryInfo get##Ext##PluginInfo();
#include "llvm/Support/Extension.def"
static void RegisterPassPlugins(ArrayRef<std::string> PassPlugins,
PassBuilder &PB) {
#define HANDLE_EXTENSION(Ext) \
get##Ext##PluginInfo().RegisterPassBuilderCallbacks(PB);
#include "llvm/Support/Extension.def"
// Load requested pass plugins and let them register pass builder callbacks
for (auto &PluginFN : PassPlugins) {
auto PassPlugin = PassPlugin::Load(PluginFN);
if (!PassPlugin) {
errs() << "Failed to load passes from '" << PluginFN
<< "'. Request ignored.\n";
continue;
}
PassPlugin->registerPassBuilderCallbacks(PB);
}
}
static std::unique_ptr<TargetMachine>
createTargetMachine(const Config &Conf, const Target *TheTarget, Module &M) {
StringRef TheTriple = M.getTargetTriple();
SubtargetFeatures Features;
Features.getDefaultSubtargetFeatures(Triple(TheTriple));
for (const std::string &A : Conf.MAttrs)
Features.AddFeature(A);
std::optional<Reloc::Model> RelocModel;
if (Conf.RelocModel)
RelocModel = *Conf.RelocModel;
else if (M.getModuleFlag("PIC Level"))
RelocModel =
M.getPICLevel() == PICLevel::NotPIC ? Reloc::Static : Reloc::PIC_;
std::optional<CodeModel::Model> CodeModel;
if (Conf.CodeModel)
CodeModel = *Conf.CodeModel;
else
CodeModel = M.getCodeModel();
std::unique_ptr<TargetMachine> TM(TheTarget->createTargetMachine(
TheTriple, Conf.CPU, Features.getString(), Conf.Options, RelocModel,
CodeModel, Conf.CGOptLevel));
assert(TM && "Failed to create target machine");
if (std::optional<uint64_t> LargeDataThreshold = M.getLargeDataThreshold())
TM->setLargeDataThreshold(*LargeDataThreshold);
return TM;
}
static void runNewPMPasses(const Config &Conf, Module &Mod, TargetMachine *TM,
unsigned OptLevel, bool IsThinLTO,
ModuleSummaryIndex *ExportSummary,
const ModuleSummaryIndex *ImportSummary) {
auto FS = vfs::getRealFileSystem();
std::optional<PGOOptions> PGOOpt;
if (!Conf.SampleProfile.empty())
PGOOpt = PGOOptions(Conf.SampleProfile, "", Conf.ProfileRemapping,
/*MemoryProfile=*/"", FS, PGOOptions::SampleUse,
PGOOptions::NoCSAction,
PGOOptions::ColdFuncOpt::Default, true);
else if (Conf.RunCSIRInstr) {
PGOOpt = PGOOptions("", Conf.CSIRProfile, Conf.ProfileRemapping,
/*MemoryProfile=*/"", FS, PGOOptions::IRUse,
PGOOptions::CSIRInstr, PGOOptions::ColdFuncOpt::Default,
Conf.AddFSDiscriminator);
} else if (!Conf.CSIRProfile.empty()) {
PGOOpt = PGOOptions(Conf.CSIRProfile, "", Conf.ProfileRemapping,
/*MemoryProfile=*/"", FS, PGOOptions::IRUse,
PGOOptions::CSIRUse, PGOOptions::ColdFuncOpt::Default,
Conf.AddFSDiscriminator);
NoPGOWarnMismatch = !Conf.PGOWarnMismatch;
} else if (Conf.AddFSDiscriminator) {
PGOOpt = PGOOptions("", "", "", /*MemoryProfile=*/"", nullptr,
PGOOptions::NoAction, PGOOptions::NoCSAction,
PGOOptions::ColdFuncOpt::Default, true);
}
TM->setPGOOption(PGOOpt);
LoopAnalysisManager LAM;
FunctionAnalysisManager FAM;
CGSCCAnalysisManager CGAM;
ModuleAnalysisManager MAM;
PassInstrumentationCallbacks PIC;
StandardInstrumentations SI(Mod.getContext(), Conf.DebugPassManager,
Conf.VerifyEach);
SI.registerCallbacks(PIC, &MAM);
PassBuilder PB(TM, Conf.PTO, PGOOpt, &PIC);
RegisterPassPlugins(Conf.PassPlugins, PB);
std::unique_ptr<TargetLibraryInfoImpl> TLII(
new TargetLibraryInfoImpl(Triple(TM->getTargetTriple())));
if (Conf.Freestanding)
TLII->disableAllFunctions();
FAM.registerPass([&] { return TargetLibraryAnalysis(*TLII); });
// Parse a custom AA pipeline if asked to.
if (!Conf.AAPipeline.empty()) {
AAManager AA;
if (auto Err = PB.parseAAPipeline(AA, Conf.AAPipeline)) {
report_fatal_error(Twine("unable to parse AA pipeline description '") +
Conf.AAPipeline + "': " + toString(std::move(Err)));
}
// Register the AA manager first so that our version is the one used.
FAM.registerPass([&] { return std::move(AA); });
}
// Register all the basic analyses with the managers.
PB.registerModuleAnalyses(MAM);
PB.registerCGSCCAnalyses(CGAM);
PB.registerFunctionAnalyses(FAM);
PB.registerLoopAnalyses(LAM);
PB.crossRegisterProxies(LAM, FAM, CGAM, MAM);
ModulePassManager MPM;
if (!Conf.DisableVerify)
MPM.addPass(VerifierPass());
OptimizationLevel OL;
switch (OptLevel) {
default:
llvm_unreachable("Invalid optimization level");
case 0:
OL = OptimizationLevel::O0;
break;
case 1:
OL = OptimizationLevel::O1;
break;
case 2:
OL = OptimizationLevel::O2;
break;
case 3:
OL = OptimizationLevel::O3;
break;
}
// Parse a custom pipeline if asked to.
if (!Conf.OptPipeline.empty()) {
if (auto Err = PB.parsePassPipeline(MPM, Conf.OptPipeline)) {
report_fatal_error(Twine("unable to parse pass pipeline description '") +
Conf.OptPipeline + "': " + toString(std::move(Err)));
}
} else if (IsThinLTO) {
MPM.addPass(PB.buildThinLTODefaultPipeline(OL, ImportSummary));
} else {
MPM.addPass(PB.buildLTODefaultPipeline(OL, ExportSummary));
}
if (!Conf.DisableVerify)
MPM.addPass(VerifierPass());
MPM.run(Mod, MAM);
}
bool lto::opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
bool IsThinLTO, ModuleSummaryIndex *ExportSummary,
const ModuleSummaryIndex *ImportSummary,
const std::vector<uint8_t> &CmdArgs) {
if (EmbedBitcode == LTOBitcodeEmbedding::EmbedPostMergePreOptimized) {
// FIXME: the motivation for capturing post-merge bitcode and command line
// is replicating the compilation environment from bitcode, without needing
// to understand the dependencies (the functions to be imported). This
// assumes a clang - based invocation, case in which we have the command
// line.
// It's not very clear how the above motivation would map in the
// linker-based case, so we currently don't plumb the command line args in
// that case.
if (CmdArgs.empty())
LLVM_DEBUG(
dbgs() << "Post-(Thin)LTO merge bitcode embedding was requested, but "
"command line arguments are not available");
llvm::embedBitcodeInModule(Mod, llvm::MemoryBufferRef(),
/*EmbedBitcode*/ true, /*EmbedCmdline*/ true,
/*Cmdline*/ CmdArgs);
}
// FIXME: Plumb the combined index into the new pass manager.
runNewPMPasses(Conf, Mod, TM, Conf.OptLevel, IsThinLTO, ExportSummary,
ImportSummary);
return !Conf.PostOptModuleHook || Conf.PostOptModuleHook(Task, Mod);
}
static void codegen(const Config &Conf, TargetMachine *TM,
AddStreamFn AddStream, unsigned Task, Module &Mod,
const ModuleSummaryIndex &CombinedIndex) {
if (Conf.PreCodeGenModuleHook && !Conf.PreCodeGenModuleHook(Task, Mod))
return;
if (EmbedBitcode == LTOBitcodeEmbedding::EmbedOptimized)
llvm::embedBitcodeInModule(Mod, llvm::MemoryBufferRef(),
/*EmbedBitcode*/ true,
/*EmbedCmdline*/ false,
/*CmdArgs*/ std::vector<uint8_t>());
std::unique_ptr<ToolOutputFile> DwoOut;
SmallString<1024> DwoFile(Conf.SplitDwarfOutput);
if (!Conf.DwoDir.empty()) {
std::error_code EC;
if (auto EC = llvm::sys::fs::create_directories(Conf.DwoDir))
report_fatal_error(Twine("Failed to create directory ") + Conf.DwoDir +
": " + EC.message());
DwoFile = Conf.DwoDir;
sys::path::append(DwoFile, std::to_string(Task) + ".dwo");
TM->Options.MCOptions.SplitDwarfFile = std::string(DwoFile);
} else
TM->Options.MCOptions.SplitDwarfFile = Conf.SplitDwarfFile;
if (!DwoFile.empty()) {
std::error_code EC;
DwoOut = std::make_unique<ToolOutputFile>(DwoFile, EC, sys::fs::OF_None);
if (EC)
report_fatal_error(Twine("Failed to open ") + DwoFile + ": " +
EC.message());
}
Expected<std::unique_ptr<CachedFileStream>> StreamOrErr =
AddStream(Task, Mod.getModuleIdentifier());
if (Error Err = StreamOrErr.takeError())
report_fatal_error(std::move(Err));
std::unique_ptr<CachedFileStream> &Stream = *StreamOrErr;
TM->Options.ObjectFilenameForDebug = Stream->ObjectPathName;
legacy::PassManager CodeGenPasses;
TargetLibraryInfoImpl TLII(Triple(Mod.getTargetTriple()));
CodeGenPasses.add(new TargetLibraryInfoWrapperPass(TLII));
CodeGenPasses.add(
createImmutableModuleSummaryIndexWrapperPass(&CombinedIndex));
if (Conf.PreCodeGenPassesHook)
Conf.PreCodeGenPassesHook(CodeGenPasses);
if (TM->addPassesToEmitFile(CodeGenPasses, *Stream->OS,
DwoOut ? &DwoOut->os() : nullptr,
Conf.CGFileType))
report_fatal_error("Failed to setup codegen");
CodeGenPasses.run(Mod);
if (DwoOut)
DwoOut->keep();
}
static void splitCodeGen(const Config &C, TargetMachine *TM,
AddStreamFn AddStream,
unsigned ParallelCodeGenParallelismLevel, Module &Mod,
const ModuleSummaryIndex &CombinedIndex) {
ThreadPool CodegenThreadPool(
heavyweight_hardware_concurrency(ParallelCodeGenParallelismLevel));
unsigned ThreadCount = 0;
const Target *T = &TM->getTarget();
SplitModule(
Mod, ParallelCodeGenParallelismLevel,
[&](std::unique_ptr<Module> MPart) {
// We want to clone the module in a new context to multi-thread the
// codegen. We do it by serializing partition modules to bitcode
// (while still on the main thread, in order to avoid data races) and
// spinning up new threads which deserialize the partitions into
// separate contexts.
// FIXME: Provide a more direct way to do this in LLVM.
SmallString<0> BC;
raw_svector_ostream BCOS(BC);
WriteBitcodeToFile(*MPart, BCOS);
// Enqueue the task
CodegenThreadPool.async(
[&](const SmallString<0> &BC, unsigned ThreadId) {
LTOLLVMContext Ctx(C);
Expected<std::unique_ptr<Module>> MOrErr = parseBitcodeFile(
MemoryBufferRef(StringRef(BC.data(), BC.size()), "ld-temp.o"),
Ctx);
if (!MOrErr)
report_fatal_error("Failed to read bitcode");
std::unique_ptr<Module> MPartInCtx = std::move(MOrErr.get());
std::unique_ptr<TargetMachine> TM =
createTargetMachine(C, T, *MPartInCtx);
codegen(C, TM.get(), AddStream, ThreadId, *MPartInCtx,
CombinedIndex);
},
// Pass BC using std::move to ensure that it get moved rather than
// copied into the thread's context.
std::move(BC), ThreadCount++);
},
false);
// Because the inner lambda (which runs in a worker thread) captures our local
// variables, we need to wait for the worker threads to terminate before we
// can leave the function scope.
CodegenThreadPool.wait();
}
static Expected<const Target *> initAndLookupTarget(const Config &C,
Module &Mod) {
if (!C.OverrideTriple.empty())
Mod.setTargetTriple(C.OverrideTriple);
else if (Mod.getTargetTriple().empty())
Mod.setTargetTriple(C.DefaultTriple);
std::string Msg;
const Target *T = TargetRegistry::lookupTarget(Mod.getTargetTriple(), Msg);
if (!T)
return make_error<StringError>(Msg, inconvertibleErrorCode());
return T;
}
Error lto::finalizeOptimizationRemarks(
std::unique_ptr<ToolOutputFile> DiagOutputFile) {
// Make sure we flush the diagnostic remarks file in case the linker doesn't
// call the global destructors before exiting.
if (!DiagOutputFile)
return Error::success();
DiagOutputFile->keep();
DiagOutputFile->os().flush();
return Error::success();
}
Error lto::backend(const Config &C, AddStreamFn AddStream,
unsigned ParallelCodeGenParallelismLevel, Module &Mod,
ModuleSummaryIndex &CombinedIndex) {
Expected<const Target *> TOrErr = initAndLookupTarget(C, Mod);
if (!TOrErr)
return TOrErr.takeError();
std::unique_ptr<TargetMachine> TM = createTargetMachine(C, *TOrErr, Mod);
LLVM_DEBUG(dbgs() << "Running regular LTO\n");
if (!C.CodeGenOnly) {
if (!opt(C, TM.get(), 0, Mod, /*IsThinLTO=*/false,
/*ExportSummary=*/&CombinedIndex, /*ImportSummary=*/nullptr,
/*CmdArgs*/ std::vector<uint8_t>()))
return Error::success();
}
if (ParallelCodeGenParallelismLevel == 1) {
codegen(C, TM.get(), AddStream, 0, Mod, CombinedIndex);
} else {
splitCodeGen(C, TM.get(), AddStream, ParallelCodeGenParallelismLevel, Mod,
CombinedIndex);
}
return Error::success();
}
static void dropDeadSymbols(Module &Mod, const GVSummaryMapTy &DefinedGlobals,
const ModuleSummaryIndex &Index) {
std::vector<GlobalValue*> DeadGVs;
for (auto &GV : Mod.global_values())
if (GlobalValueSummary *GVS = DefinedGlobals.lookup(GV.getGUID()))
if (!Index.isGlobalValueLive(GVS)) {
DeadGVs.push_back(&GV);
convertToDeclaration(GV);
}
// Now that all dead bodies have been dropped, delete the actual objects
// themselves when possible.
for (GlobalValue *GV : DeadGVs) {
GV->removeDeadConstantUsers();
// Might reference something defined in native object (i.e. dropped a
// non-prevailing IR def, but we need to keep the declaration).
if (GV->use_empty())
GV->eraseFromParent();
}
}
Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
Module &Mod, const ModuleSummaryIndex &CombinedIndex,
const FunctionImporter::ImportMapTy &ImportList,
const GVSummaryMapTy &DefinedGlobals,
MapVector<StringRef, BitcodeModule> *ModuleMap,
const std::vector<uint8_t> &CmdArgs) {
Expected<const Target *> TOrErr = initAndLookupTarget(Conf, Mod);
if (!TOrErr)
return TOrErr.takeError();
std::unique_ptr<TargetMachine> TM = createTargetMachine(Conf, *TOrErr, Mod);
// Setup optimization remarks.
auto DiagFileOrErr = lto::setupLLVMOptimizationRemarks(
Mod.getContext(), Conf.RemarksFilename, Conf.RemarksPasses,
Conf.RemarksFormat, Conf.RemarksWithHotness, Conf.RemarksHotnessThreshold,
Task);
if (!DiagFileOrErr)
return DiagFileOrErr.takeError();
auto DiagnosticOutputFile = std::move(*DiagFileOrErr);
// Set the partial sample profile ratio in the profile summary module flag of
// the module, if applicable.
Mod.setPartialSampleProfileRatio(CombinedIndex);
LLVM_DEBUG(dbgs() << "Running ThinLTO\n");
if (Conf.CodeGenOnly) {
codegen(Conf, TM.get(), AddStream, Task, Mod, CombinedIndex);
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
}
if (Conf.PreOptModuleHook && !Conf.PreOptModuleHook(Task, Mod))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
auto OptimizeAndCodegen =
[&](Module &Mod, TargetMachine *TM,
std::unique_ptr<ToolOutputFile> DiagnosticOutputFile) {
if (!opt(Conf, TM, Task, Mod, /*IsThinLTO=*/true,
/*ExportSummary=*/nullptr, /*ImportSummary=*/&CombinedIndex,
CmdArgs))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
codegen(Conf, TM, AddStream, Task, Mod, CombinedIndex);
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
};
if (ThinLTOAssumeMerged)
return OptimizeAndCodegen(Mod, TM.get(), std::move(DiagnosticOutputFile));
// When linking an ELF shared object, dso_local should be dropped. We
// conservatively do this for -fpic.
bool ClearDSOLocalOnDeclarations =
TM->getTargetTriple().isOSBinFormatELF() &&
TM->getRelocationModel() != Reloc::Static &&
Mod.getPIELevel() == PIELevel::Default;
renameModuleForThinLTO(Mod, CombinedIndex, ClearDSOLocalOnDeclarations);
dropDeadSymbols(Mod, DefinedGlobals, CombinedIndex);
thinLTOFinalizeInModule(Mod, DefinedGlobals, /*PropagateAttrs=*/true);
if (Conf.PostPromoteModuleHook && !Conf.PostPromoteModuleHook(Task, Mod))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
if (!DefinedGlobals.empty())
thinLTOInternalizeModule(Mod, DefinedGlobals);
if (Conf.PostInternalizeModuleHook &&
!Conf.PostInternalizeModuleHook(Task, Mod))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
auto ModuleLoader = [&](StringRef Identifier) {
assert(Mod.getContext().isODRUniquingDebugTypes() &&
"ODR Type uniquing should be enabled on the context");
if (ModuleMap) {
auto I = ModuleMap->find(Identifier);
assert(I != ModuleMap->end());
return I->second.getLazyModule(Mod.getContext(),
/*ShouldLazyLoadMetadata=*/true,
/*IsImporting*/ true);
}
ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> MBOrErr =
llvm::MemoryBuffer::getFile(Identifier);
if (!MBOrErr)
return Expected<std::unique_ptr<llvm::Module>>(make_error<StringError>(
Twine("Error loading imported file ") + Identifier + " : ",
MBOrErr.getError()));
Expected<BitcodeModule> BMOrErr = findThinLTOModule(**MBOrErr);
if (!BMOrErr)
return Expected<std::unique_ptr<llvm::Module>>(make_error<StringError>(
Twine("Error loading imported file ") + Identifier + " : " +
toString(BMOrErr.takeError()),
inconvertibleErrorCode()));
Expected<std::unique_ptr<Module>> MOrErr =
BMOrErr->getLazyModule(Mod.getContext(),
/*ShouldLazyLoadMetadata=*/true,
/*IsImporting*/ true);
if (MOrErr)
(*MOrErr)->setOwnedMemoryBuffer(std::move(*MBOrErr));
return MOrErr;
};
FunctionImporter Importer(CombinedIndex, ModuleLoader,
ClearDSOLocalOnDeclarations);
if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
return Err;
// Do this after any importing so that imported code is updated.
updateMemProfAttributes(Mod, CombinedIndex);
updatePublicTypeTestCalls(Mod, CombinedIndex.withWholeProgramVisibility());
if (Conf.PostImportModuleHook && !Conf.PostImportModuleHook(Task, Mod))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
return OptimizeAndCodegen(Mod, TM.get(), std::move(DiagnosticOutputFile));
}
BitcodeModule *lto::findThinLTOModule(MutableArrayRef<BitcodeModule> BMs) {
if (ThinLTOAssumeMerged && BMs.size() == 1)
return BMs.begin();
for (BitcodeModule &BM : BMs) {
Expected<BitcodeLTOInfo> LTOInfo = BM.getLTOInfo();
if (LTOInfo && LTOInfo->IsThinLTO)
return &BM;
}
return nullptr;
}
Expected<BitcodeModule> lto::findThinLTOModule(MemoryBufferRef MBRef) {
Expected<std::vector<BitcodeModule>> BMsOrErr = getBitcodeModuleList(MBRef);
if (!BMsOrErr)
return BMsOrErr.takeError();
// The bitcode file may contain multiple modules, we want the one that is
// marked as being the ThinLTO module.
if (const BitcodeModule *Bm = lto::findThinLTOModule(*BMsOrErr))
return *Bm;
return make_error<StringError>("Could not find module summary",
inconvertibleErrorCode());
}
bool lto::initImportList(const Module &M,
const ModuleSummaryIndex &CombinedIndex,
FunctionImporter::ImportMapTy &ImportList) {
if (ThinLTOAssumeMerged)
return true;
// We can simply import the values mentioned in the combined index, since
// we should only invoke this using the individual indexes written out
// via a WriteIndexesThinBackend.
for (const auto &GlobalList : CombinedIndex) {
// Ignore entries for undefined references.
if (GlobalList.second.SummaryList.empty())
continue;
auto GUID = GlobalList.first;
for (const auto &Summary : GlobalList.second.SummaryList) {
// Skip the summaries for the importing module. These are included to
// e.g. record required linkage changes.
if (Summary->modulePath() == M.getModuleIdentifier())
continue;
// Add an entry to provoke importing by thinBackend.
ImportList[Summary->modulePath()].insert(GUID);
}
}
return true;
}
|