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
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
|
//===- PromoteMemoryToRegister.cpp - Convert allocas to registers ---------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file promotes memory references to be register references. It promotes
// alloca instructions which only have loads and stores as uses. An alloca is
// transformed by using iterated dominator frontiers to place PHI nodes, then
// traversing the function in depth-first order to rewrite loads and stores as
// appropriate.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasSetTracker.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/IteratedDominanceFrontier.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DIBuilder.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/PromoteMemToReg.h"
#include <algorithm>
using namespace llvm;
#define DEBUG_TYPE "mem2reg"
STATISTIC(NumLocalPromoted, "Number of alloca's promoted within one block");
STATISTIC(NumSingleStore, "Number of alloca's promoted with a single store");
STATISTIC(NumDeadAlloca, "Number of dead alloca's removed");
STATISTIC(NumPHIInsert, "Number of PHI nodes inserted");
bool llvm::isAllocaPromotable(const AllocaInst *AI) {
// FIXME: If the memory unit is of pointer or integer type, we can permit
// assignments to subsections of the memory unit.
unsigned AS = AI->getType()->getAddressSpace();
// Only allow direct and non-volatile loads and stores...
for (const User *U : AI->users()) {
if (const LoadInst *LI = dyn_cast<LoadInst>(U)) {
// Note that atomic loads can be transformed; atomic semantics do
// not have any meaning for a local alloca.
if (LI->isVolatile())
return false;
} else if (const StoreInst *SI = dyn_cast<StoreInst>(U)) {
if (SI->getOperand(0) == AI)
return false; // Don't allow a store OF the AI, only INTO the AI.
// Note that atomic stores can be transformed; atomic semantics do
// not have any meaning for a local alloca.
if (SI->isVolatile())
return false;
} else if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(U)) {
if (II->getIntrinsicID() != Intrinsic::lifetime_start &&
II->getIntrinsicID() != Intrinsic::lifetime_end)
return false;
} else if (const BitCastInst *BCI = dyn_cast<BitCastInst>(U)) {
if (BCI->getType() != Type::getInt8PtrTy(U->getContext(), AS))
return false;
if (!onlyUsedByLifetimeMarkers(BCI))
return false;
} else if (const GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(U)) {
if (GEPI->getType() != Type::getInt8PtrTy(U->getContext(), AS))
return false;
if (!GEPI->hasAllZeroIndices())
return false;
if (!onlyUsedByLifetimeMarkers(GEPI))
return false;
} else {
return false;
}
}
return true;
}
namespace {
struct AllocaInfo {
SmallVector<BasicBlock *, 32> DefiningBlocks;
SmallVector<BasicBlock *, 32> UsingBlocks;
StoreInst *OnlyStore;
BasicBlock *OnlyBlock;
bool OnlyUsedInOneBlock;
Value *AllocaPointerVal;
DbgDeclareInst *DbgDeclare;
void clear() {
DefiningBlocks.clear();
UsingBlocks.clear();
OnlyStore = nullptr;
OnlyBlock = nullptr;
OnlyUsedInOneBlock = true;
AllocaPointerVal = nullptr;
DbgDeclare = nullptr;
}
/// Scan the uses of the specified alloca, filling in the AllocaInfo used
/// by the rest of the pass to reason about the uses of this alloca.
void AnalyzeAlloca(AllocaInst *AI) {
clear();
// As we scan the uses of the alloca instruction, keep track of stores,
// and decide whether all of the loads and stores to the alloca are within
// the same basic block.
for (auto UI = AI->user_begin(), E = AI->user_end(); UI != E;) {
Instruction *User = cast<Instruction>(*UI++);
if (StoreInst *SI = dyn_cast<StoreInst>(User)) {
// Remember the basic blocks which define new values for the alloca
DefiningBlocks.push_back(SI->getParent());
AllocaPointerVal = SI->getOperand(0);
OnlyStore = SI;
} else {
LoadInst *LI = cast<LoadInst>(User);
// Otherwise it must be a load instruction, keep track of variable
// reads.
UsingBlocks.push_back(LI->getParent());
AllocaPointerVal = LI;
}
if (OnlyUsedInOneBlock) {
if (!OnlyBlock)
OnlyBlock = User->getParent();
else if (OnlyBlock != User->getParent())
OnlyUsedInOneBlock = false;
}
}
DbgDeclare = FindAllocaDbgDeclare(AI);
}
};
// Data package used by RenamePass()
class RenamePassData {
public:
typedef std::vector<Value *> ValVector;
RenamePassData() : BB(nullptr), Pred(nullptr), Values() {}
RenamePassData(BasicBlock *B, BasicBlock *P, const ValVector &V)
: BB(B), Pred(P), Values(V) {}
BasicBlock *BB;
BasicBlock *Pred;
ValVector Values;
void swap(RenamePassData &RHS) {
std::swap(BB, RHS.BB);
std::swap(Pred, RHS.Pred);
Values.swap(RHS.Values);
}
};
/// \brief This assigns and keeps a per-bb relative ordering of load/store
/// instructions in the block that directly load or store an alloca.
///
/// This functionality is important because it avoids scanning large basic
/// blocks multiple times when promoting many allocas in the same block.
class LargeBlockInfo {
/// \brief For each instruction that we track, keep the index of the
/// instruction.
///
/// The index starts out as the number of the instruction from the start of
/// the block.
DenseMap<const Instruction *, unsigned> InstNumbers;
public:
/// This code only looks at accesses to allocas.
static bool isInterestingInstruction(const Instruction *I) {
return (isa<LoadInst>(I) && isa<AllocaInst>(I->getOperand(0))) ||
(isa<StoreInst>(I) && isa<AllocaInst>(I->getOperand(1)));
}
/// Get or calculate the index of the specified instruction.
unsigned getInstructionIndex(const Instruction *I) {
assert(isInterestingInstruction(I) &&
"Not a load/store to/from an alloca?");
// If we already have this instruction number, return it.
DenseMap<const Instruction *, unsigned>::iterator It = InstNumbers.find(I);
if (It != InstNumbers.end())
return It->second;
// Scan the whole block to get the instruction. This accumulates
// information for every interesting instruction in the block, in order to
// avoid gratuitus rescans.
const BasicBlock *BB = I->getParent();
unsigned InstNo = 0;
for (const Instruction &BBI : *BB)
if (isInterestingInstruction(&BBI))
InstNumbers[&BBI] = InstNo++;
It = InstNumbers.find(I);
assert(It != InstNumbers.end() && "Didn't insert instruction?");
return It->second;
}
void deleteValue(const Instruction *I) { InstNumbers.erase(I); }
void clear() { InstNumbers.clear(); }
};
struct PromoteMem2Reg {
/// The alloca instructions being promoted.
std::vector<AllocaInst *> Allocas;
DominatorTree &DT;
DIBuilder DIB;
/// A cache of @llvm.assume intrinsics used by SimplifyInstruction.
AssumptionCache *AC;
const SimplifyQuery SQ;
/// Reverse mapping of Allocas.
DenseMap<AllocaInst *, unsigned> AllocaLookup;
/// \brief The PhiNodes we're adding.
///
/// That map is used to simplify some Phi nodes as we iterate over it, so
/// it should have deterministic iterators. We could use a MapVector, but
/// since we already maintain a map from BasicBlock* to a stable numbering
/// (BBNumbers), the DenseMap is more efficient (also supports removal).
DenseMap<std::pair<unsigned, unsigned>, PHINode *> NewPhiNodes;
/// For each PHI node, keep track of which entry in Allocas it corresponds
/// to.
DenseMap<PHINode *, unsigned> PhiToAllocaMap;
/// If we are updating an AliasSetTracker, then for each alloca that is of
/// pointer type, we keep track of what to copyValue to the inserted PHI
/// nodes here.
std::vector<Value *> PointerAllocaValues;
/// For each alloca, we keep track of the dbg.declare intrinsic that
/// describes it, if any, so that we can convert it to a dbg.value
/// intrinsic if the alloca gets promoted.
SmallVector<DbgDeclareInst *, 8> AllocaDbgDeclares;
/// The set of basic blocks the renamer has already visited.
///
SmallPtrSet<BasicBlock *, 16> Visited;
/// Contains a stable numbering of basic blocks to avoid non-determinstic
/// behavior.
DenseMap<BasicBlock *, unsigned> BBNumbers;
/// Lazily compute the number of predecessors a block has.
DenseMap<const BasicBlock *, unsigned> BBNumPreds;
public:
PromoteMem2Reg(ArrayRef<AllocaInst *> Allocas, DominatorTree &DT,
AssumptionCache *AC)
: Allocas(Allocas.begin(), Allocas.end()), DT(DT),
DIB(*DT.getRoot()->getParent()->getParent(), /*AllowUnresolved*/ false),
AC(AC), SQ(DT.getRoot()->getParent()->getParent()->getDataLayout(),
nullptr, &DT, AC) {}
void run();
private:
void RemoveFromAllocasList(unsigned &AllocaIdx) {
Allocas[AllocaIdx] = Allocas.back();
Allocas.pop_back();
--AllocaIdx;
}
unsigned getNumPreds(const BasicBlock *BB) {
unsigned &NP = BBNumPreds[BB];
if (NP == 0)
NP = std::distance(pred_begin(BB), pred_end(BB)) + 1;
return NP - 1;
}
void ComputeLiveInBlocks(AllocaInst *AI, AllocaInfo &Info,
const SmallPtrSetImpl<BasicBlock *> &DefBlocks,
SmallPtrSetImpl<BasicBlock *> &LiveInBlocks);
void RenamePass(BasicBlock *BB, BasicBlock *Pred,
RenamePassData::ValVector &IncVals,
std::vector<RenamePassData> &Worklist);
bool QueuePhiNode(BasicBlock *BB, unsigned AllocaIdx, unsigned &Version);
};
} // end of anonymous namespace
/// Given a LoadInst LI this adds assume(LI != null) after it.
static void addAssumeNonNull(AssumptionCache *AC, LoadInst *LI) {
Function *AssumeIntrinsic =
Intrinsic::getDeclaration(LI->getModule(), Intrinsic::assume);
ICmpInst *LoadNotNull = new ICmpInst(ICmpInst::ICMP_NE, LI,
Constant::getNullValue(LI->getType()));
LoadNotNull->insertAfter(LI);
CallInst *CI = CallInst::Create(AssumeIntrinsic, {LoadNotNull});
CI->insertAfter(LoadNotNull);
AC->registerAssumption(CI);
}
static void removeLifetimeIntrinsicUsers(AllocaInst *AI) {
// Knowing that this alloca is promotable, we know that it's safe to kill all
// instructions except for load and store.
for (auto UI = AI->user_begin(), UE = AI->user_end(); UI != UE;) {
Instruction *I = cast<Instruction>(*UI);
++UI;
if (isa<LoadInst>(I) || isa<StoreInst>(I))
continue;
if (!I->getType()->isVoidTy()) {
// The only users of this bitcast/GEP instruction are lifetime intrinsics.
// Follow the use/def chain to erase them now instead of leaving it for
// dead code elimination later.
for (auto UUI = I->user_begin(), UUE = I->user_end(); UUI != UUE;) {
Instruction *Inst = cast<Instruction>(*UUI);
++UUI;
Inst->eraseFromParent();
}
}
I->eraseFromParent();
}
}
/// \brief Rewrite as many loads as possible given a single store.
///
/// When there is only a single store, we can use the domtree to trivially
/// replace all of the dominated loads with the stored value. Do so, and return
/// true if this has successfully promoted the alloca entirely. If this returns
/// false there were some loads which were not dominated by the single store
/// and thus must be phi-ed with undef. We fall back to the standard alloca
/// promotion algorithm in that case.
static bool rewriteSingleStoreAlloca(AllocaInst *AI, AllocaInfo &Info,
LargeBlockInfo &LBI, DominatorTree &DT,
AssumptionCache *AC) {
StoreInst *OnlyStore = Info.OnlyStore;
bool StoringGlobalVal = !isa<Instruction>(OnlyStore->getOperand(0));
BasicBlock *StoreBB = OnlyStore->getParent();
int StoreIndex = -1;
// Clear out UsingBlocks. We will reconstruct it here if needed.
Info.UsingBlocks.clear();
for (auto UI = AI->user_begin(), E = AI->user_end(); UI != E;) {
Instruction *UserInst = cast<Instruction>(*UI++);
if (!isa<LoadInst>(UserInst)) {
assert(UserInst == OnlyStore && "Should only have load/stores");
continue;
}
LoadInst *LI = cast<LoadInst>(UserInst);
// Okay, if we have a load from the alloca, we want to replace it with the
// only value stored to the alloca. We can do this if the value is
// dominated by the store. If not, we use the rest of the mem2reg machinery
// to insert the phi nodes as needed.
if (!StoringGlobalVal) { // Non-instructions are always dominated.
if (LI->getParent() == StoreBB) {
// If we have a use that is in the same block as the store, compare the
// indices of the two instructions to see which one came first. If the
// load came before the store, we can't handle it.
if (StoreIndex == -1)
StoreIndex = LBI.getInstructionIndex(OnlyStore);
if (unsigned(StoreIndex) > LBI.getInstructionIndex(LI)) {
// Can't handle this load, bail out.
Info.UsingBlocks.push_back(StoreBB);
continue;
}
} else if (LI->getParent() != StoreBB &&
!DT.dominates(StoreBB, LI->getParent())) {
// If the load and store are in different blocks, use BB dominance to
// check their relationships. If the store doesn't dom the use, bail
// out.
Info.UsingBlocks.push_back(LI->getParent());
continue;
}
}
// Otherwise, we *can* safely rewrite this load.
Value *ReplVal = OnlyStore->getOperand(0);
// If the replacement value is the load, this must occur in unreachable
// code.
if (ReplVal == LI)
ReplVal = UndefValue::get(LI->getType());
// If the load was marked as nonnull we don't want to lose
// that information when we erase this Load. So we preserve
// it with an assume.
if (AC && LI->getMetadata(LLVMContext::MD_nonnull) &&
!llvm::isKnownNonNullAt(ReplVal, LI, &DT))
addAssumeNonNull(AC, LI);
LI->replaceAllUsesWith(ReplVal);
LI->eraseFromParent();
LBI.deleteValue(LI);
}
// Finally, after the scan, check to see if the store is all that is left.
if (!Info.UsingBlocks.empty())
return false; // If not, we'll have to fall back for the remainder.
// Record debuginfo for the store and remove the declaration's
// debuginfo.
if (DbgDeclareInst *DDI = Info.DbgDeclare) {
DIBuilder DIB(*AI->getModule(), /*AllowUnresolved*/ false);
ConvertDebugDeclareToDebugValue(DDI, Info.OnlyStore, DIB);
DDI->eraseFromParent();
LBI.deleteValue(DDI);
}
// Remove the (now dead) store and alloca.
Info.OnlyStore->eraseFromParent();
LBI.deleteValue(Info.OnlyStore);
AI->eraseFromParent();
LBI.deleteValue(AI);
return true;
}
/// Many allocas are only used within a single basic block. If this is the
/// case, avoid traversing the CFG and inserting a lot of potentially useless
/// PHI nodes by just performing a single linear pass over the basic block
/// using the Alloca.
///
/// If we cannot promote this alloca (because it is read before it is written),
/// return false. This is necessary in cases where, due to control flow, the
/// alloca is undefined only on some control flow paths. e.g. code like
/// this is correct in LLVM IR:
/// // A is an alloca with no stores so far
/// for (...) {
/// int t = *A;
/// if (!first_iteration)
/// use(t);
/// *A = 42;
/// }
static bool promoteSingleBlockAlloca(AllocaInst *AI, const AllocaInfo &Info,
LargeBlockInfo &LBI,
DominatorTree &DT,
AssumptionCache *AC) {
// The trickiest case to handle is when we have large blocks. Because of this,
// this code is optimized assuming that large blocks happen. This does not
// significantly pessimize the small block case. This uses LargeBlockInfo to
// make it efficient to get the index of various operations in the block.
// Walk the use-def list of the alloca, getting the locations of all stores.
typedef SmallVector<std::pair<unsigned, StoreInst *>, 64> StoresByIndexTy;
StoresByIndexTy StoresByIndex;
for (User *U : AI->users())
if (StoreInst *SI = dyn_cast<StoreInst>(U))
StoresByIndex.push_back(std::make_pair(LBI.getInstructionIndex(SI), SI));
// Sort the stores by their index, making it efficient to do a lookup with a
// binary search.
std::sort(StoresByIndex.begin(), StoresByIndex.end(), less_first());
// Walk all of the loads from this alloca, replacing them with the nearest
// store above them, if any.
for (auto UI = AI->user_begin(), E = AI->user_end(); UI != E;) {
LoadInst *LI = dyn_cast<LoadInst>(*UI++);
if (!LI)
continue;
unsigned LoadIdx = LBI.getInstructionIndex(LI);
// Find the nearest store that has a lower index than this load.
StoresByIndexTy::iterator I =
std::lower_bound(StoresByIndex.begin(), StoresByIndex.end(),
std::make_pair(LoadIdx,
static_cast<StoreInst *>(nullptr)),
less_first());
if (I == StoresByIndex.begin()) {
if (StoresByIndex.empty())
// If there are no stores, the load takes the undef value.
LI->replaceAllUsesWith(UndefValue::get(LI->getType()));
else
// There is no store before this load, bail out (load may be affected
// by the following stores - see main comment).
return false;
} else {
// Otherwise, there was a store before this load, the load takes its value.
// Note, if the load was marked as nonnull we don't want to lose that
// information when we erase it. So we preserve it with an assume.
Value *ReplVal = std::prev(I)->second->getOperand(0);
if (AC && LI->getMetadata(LLVMContext::MD_nonnull) &&
!llvm::isKnownNonNullAt(ReplVal, LI, &DT))
addAssumeNonNull(AC, LI);
LI->replaceAllUsesWith(ReplVal);
}
LI->eraseFromParent();
LBI.deleteValue(LI);
}
// Remove the (now dead) stores and alloca.
while (!AI->use_empty()) {
StoreInst *SI = cast<StoreInst>(AI->user_back());
// Record debuginfo for the store before removing it.
if (DbgDeclareInst *DDI = Info.DbgDeclare) {
DIBuilder DIB(*AI->getModule(), /*AllowUnresolved*/ false);
ConvertDebugDeclareToDebugValue(DDI, SI, DIB);
}
SI->eraseFromParent();
LBI.deleteValue(SI);
}
AI->eraseFromParent();
LBI.deleteValue(AI);
// The alloca's debuginfo can be removed as well.
if (DbgDeclareInst *DDI = Info.DbgDeclare) {
DDI->eraseFromParent();
LBI.deleteValue(DDI);
}
++NumLocalPromoted;
return true;
}
void PromoteMem2Reg::run() {
Function &F = *DT.getRoot()->getParent();
AllocaDbgDeclares.resize(Allocas.size());
AllocaInfo Info;
LargeBlockInfo LBI;
ForwardIDFCalculator IDF(DT);
for (unsigned AllocaNum = 0; AllocaNum != Allocas.size(); ++AllocaNum) {
AllocaInst *AI = Allocas[AllocaNum];
assert(isAllocaPromotable(AI) && "Cannot promote non-promotable alloca!");
assert(AI->getParent()->getParent() == &F &&
"All allocas should be in the same function, which is same as DF!");
removeLifetimeIntrinsicUsers(AI);
if (AI->use_empty()) {
// If there are no uses of the alloca, just delete it now.
AI->eraseFromParent();
// Remove the alloca from the Allocas list, since it has been processed
RemoveFromAllocasList(AllocaNum);
++NumDeadAlloca;
continue;
}
// Calculate the set of read and write-locations for each alloca. This is
// analogous to finding the 'uses' and 'definitions' of each variable.
Info.AnalyzeAlloca(AI);
// If there is only a single store to this value, replace any loads of
// it that are directly dominated by the definition with the value stored.
if (Info.DefiningBlocks.size() == 1) {
if (rewriteSingleStoreAlloca(AI, Info, LBI, DT, AC)) {
// The alloca has been processed, move on.
RemoveFromAllocasList(AllocaNum);
++NumSingleStore;
continue;
}
}
// If the alloca is only read and written in one basic block, just perform a
// linear sweep over the block to eliminate it.
if (Info.OnlyUsedInOneBlock &&
promoteSingleBlockAlloca(AI, Info, LBI, DT, AC)) {
// The alloca has been processed, move on.
RemoveFromAllocasList(AllocaNum);
continue;
}
// If we haven't computed a numbering for the BB's in the function, do so
// now.
if (BBNumbers.empty()) {
unsigned ID = 0;
for (auto &BB : F)
BBNumbers[&BB] = ID++;
}
// Remember the dbg.declare intrinsic describing this alloca, if any.
if (Info.DbgDeclare)
AllocaDbgDeclares[AllocaNum] = Info.DbgDeclare;
// Keep the reverse mapping of the 'Allocas' array for the rename pass.
AllocaLookup[Allocas[AllocaNum]] = AllocaNum;
// At this point, we're committed to promoting the alloca using IDF's, and
// the standard SSA construction algorithm. Determine which blocks need PHI
// nodes and see if we can optimize out some work by avoiding insertion of
// dead phi nodes.
// Unique the set of defining blocks for efficient lookup.
SmallPtrSet<BasicBlock *, 32> DefBlocks;
DefBlocks.insert(Info.DefiningBlocks.begin(), Info.DefiningBlocks.end());
// Determine which blocks the value is live in. These are blocks which lead
// to uses.
SmallPtrSet<BasicBlock *, 32> LiveInBlocks;
ComputeLiveInBlocks(AI, Info, DefBlocks, LiveInBlocks);
// At this point, we're committed to promoting the alloca using IDF's, and
// the standard SSA construction algorithm. Determine which blocks need phi
// nodes and see if we can optimize out some work by avoiding insertion of
// dead phi nodes.
IDF.setLiveInBlocks(LiveInBlocks);
IDF.setDefiningBlocks(DefBlocks);
SmallVector<BasicBlock *, 32> PHIBlocks;
IDF.calculate(PHIBlocks);
if (PHIBlocks.size() > 1)
std::sort(PHIBlocks.begin(), PHIBlocks.end(),
[this](BasicBlock *A, BasicBlock *B) {
return BBNumbers.lookup(A) < BBNumbers.lookup(B);
});
unsigned CurrentVersion = 0;
for (unsigned i = 0, e = PHIBlocks.size(); i != e; ++i)
QueuePhiNode(PHIBlocks[i], AllocaNum, CurrentVersion);
}
if (Allocas.empty())
return; // All of the allocas must have been trivial!
LBI.clear();
// Set the incoming values for the basic block to be null values for all of
// the alloca's. We do this in case there is a load of a value that has not
// been stored yet. In this case, it will get this null value.
//
RenamePassData::ValVector Values(Allocas.size());
for (unsigned i = 0, e = Allocas.size(); i != e; ++i)
Values[i] = UndefValue::get(Allocas[i]->getAllocatedType());
// Walks all basic blocks in the function performing the SSA rename algorithm
// and inserting the phi nodes we marked as necessary
//
std::vector<RenamePassData> RenamePassWorkList;
RenamePassWorkList.emplace_back(&F.front(), nullptr, std::move(Values));
do {
RenamePassData RPD;
RPD.swap(RenamePassWorkList.back());
RenamePassWorkList.pop_back();
// RenamePass may add new worklist entries.
RenamePass(RPD.BB, RPD.Pred, RPD.Values, RenamePassWorkList);
} while (!RenamePassWorkList.empty());
// The renamer uses the Visited set to avoid infinite loops. Clear it now.
Visited.clear();
// Remove the allocas themselves from the function.
for (unsigned i = 0, e = Allocas.size(); i != e; ++i) {
Instruction *A = Allocas[i];
// If there are any uses of the alloca instructions left, they must be in
// unreachable basic blocks that were not processed by walking the dominator
// tree. Just delete the users now.
if (!A->use_empty())
A->replaceAllUsesWith(UndefValue::get(A->getType()));
A->eraseFromParent();
}
// Remove alloca's dbg.declare instrinsics from the function.
for (unsigned i = 0, e = AllocaDbgDeclares.size(); i != e; ++i)
if (DbgDeclareInst *DDI = AllocaDbgDeclares[i])
DDI->eraseFromParent();
// Loop over all of the PHI nodes and see if there are any that we can get
// rid of because they merge all of the same incoming values. This can
// happen due to undef values coming into the PHI nodes. This process is
// iterative, because eliminating one PHI node can cause others to be removed.
bool EliminatedAPHI = true;
while (EliminatedAPHI) {
EliminatedAPHI = false;
// Iterating over NewPhiNodes is deterministic, so it is safe to try to
// simplify and RAUW them as we go. If it was not, we could add uses to
// the values we replace with in a non-deterministic order, thus creating
// non-deterministic def->use chains.
for (DenseMap<std::pair<unsigned, unsigned>, PHINode *>::iterator
I = NewPhiNodes.begin(),
E = NewPhiNodes.end();
I != E;) {
PHINode *PN = I->second;
// If this PHI node merges one value and/or undefs, get the value.
if (Value *V = SimplifyInstruction(PN, SQ)) {
PN->replaceAllUsesWith(V);
PN->eraseFromParent();
NewPhiNodes.erase(I++);
EliminatedAPHI = true;
continue;
}
++I;
}
}
// At this point, the renamer has added entries to PHI nodes for all reachable
// code. Unfortunately, there may be unreachable blocks which the renamer
// hasn't traversed. If this is the case, the PHI nodes may not
// have incoming values for all predecessors. Loop over all PHI nodes we have
// created, inserting undef values if they are missing any incoming values.
//
for (DenseMap<std::pair<unsigned, unsigned>, PHINode *>::iterator
I = NewPhiNodes.begin(),
E = NewPhiNodes.end();
I != E; ++I) {
// We want to do this once per basic block. As such, only process a block
// when we find the PHI that is the first entry in the block.
PHINode *SomePHI = I->second;
BasicBlock *BB = SomePHI->getParent();
if (&BB->front() != SomePHI)
continue;
// Only do work here if there the PHI nodes are missing incoming values. We
// know that all PHI nodes that were inserted in a block will have the same
// number of incoming values, so we can just check any of them.
if (SomePHI->getNumIncomingValues() == getNumPreds(BB))
continue;
// Get the preds for BB.
SmallVector<BasicBlock *, 16> Preds(pred_begin(BB), pred_end(BB));
// Ok, now we know that all of the PHI nodes are missing entries for some
// basic blocks. Start by sorting the incoming predecessors for efficient
// access.
std::sort(Preds.begin(), Preds.end());
// Now we loop through all BB's which have entries in SomePHI and remove
// them from the Preds list.
for (unsigned i = 0, e = SomePHI->getNumIncomingValues(); i != e; ++i) {
// Do a log(n) search of the Preds list for the entry we want.
SmallVectorImpl<BasicBlock *>::iterator EntIt = std::lower_bound(
Preds.begin(), Preds.end(), SomePHI->getIncomingBlock(i));
assert(EntIt != Preds.end() && *EntIt == SomePHI->getIncomingBlock(i) &&
"PHI node has entry for a block which is not a predecessor!");
// Remove the entry
Preds.erase(EntIt);
}
// At this point, the blocks left in the preds list must have dummy
// entries inserted into every PHI nodes for the block. Update all the phi
// nodes in this block that we are inserting (there could be phis before
// mem2reg runs).
unsigned NumBadPreds = SomePHI->getNumIncomingValues();
BasicBlock::iterator BBI = BB->begin();
while ((SomePHI = dyn_cast<PHINode>(BBI++)) &&
SomePHI->getNumIncomingValues() == NumBadPreds) {
Value *UndefVal = UndefValue::get(SomePHI->getType());
for (unsigned pred = 0, e = Preds.size(); pred != e; ++pred)
SomePHI->addIncoming(UndefVal, Preds[pred]);
}
}
NewPhiNodes.clear();
}
/// \brief Determine which blocks the value is live in.
///
/// These are blocks which lead to uses. Knowing this allows us to avoid
/// inserting PHI nodes into blocks which don't lead to uses (thus, the
/// inserted phi nodes would be dead).
void PromoteMem2Reg::ComputeLiveInBlocks(
AllocaInst *AI, AllocaInfo &Info,
const SmallPtrSetImpl<BasicBlock *> &DefBlocks,
SmallPtrSetImpl<BasicBlock *> &LiveInBlocks) {
// To determine liveness, we must iterate through the predecessors of blocks
// where the def is live. Blocks are added to the worklist if we need to
// check their predecessors. Start with all the using blocks.
SmallVector<BasicBlock *, 64> LiveInBlockWorklist(Info.UsingBlocks.begin(),
Info.UsingBlocks.end());
// If any of the using blocks is also a definition block, check to see if the
// definition occurs before or after the use. If it happens before the use,
// the value isn't really live-in.
for (unsigned i = 0, e = LiveInBlockWorklist.size(); i != e; ++i) {
BasicBlock *BB = LiveInBlockWorklist[i];
if (!DefBlocks.count(BB))
continue;
// Okay, this is a block that both uses and defines the value. If the first
// reference to the alloca is a def (store), then we know it isn't live-in.
for (BasicBlock::iterator I = BB->begin();; ++I) {
if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
if (SI->getOperand(1) != AI)
continue;
// We found a store to the alloca before a load. The alloca is not
// actually live-in here.
LiveInBlockWorklist[i] = LiveInBlockWorklist.back();
LiveInBlockWorklist.pop_back();
--i;
--e;
break;
}
if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
if (LI->getOperand(0) != AI)
continue;
// Okay, we found a load before a store to the alloca. It is actually
// live into this block.
break;
}
}
}
// Now that we have a set of blocks where the phi is live-in, recursively add
// their predecessors until we find the full region the value is live.
while (!LiveInBlockWorklist.empty()) {
BasicBlock *BB = LiveInBlockWorklist.pop_back_val();
// The block really is live in here, insert it into the set. If already in
// the set, then it has already been processed.
if (!LiveInBlocks.insert(BB).second)
continue;
// Since the value is live into BB, it is either defined in a predecessor or
// live into it to. Add the preds to the worklist unless they are a
// defining block.
for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
BasicBlock *P = *PI;
// The value is not live into a predecessor if it defines the value.
if (DefBlocks.count(P))
continue;
// Otherwise it is, add to the worklist.
LiveInBlockWorklist.push_back(P);
}
}
}
/// \brief Queue a phi-node to be added to a basic-block for a specific Alloca.
///
/// Returns true if there wasn't already a phi-node for that variable
bool PromoteMem2Reg::QueuePhiNode(BasicBlock *BB, unsigned AllocaNo,
unsigned &Version) {
// Look up the basic-block in question.
PHINode *&PN = NewPhiNodes[std::make_pair(BBNumbers[BB], AllocaNo)];
// If the BB already has a phi node added for the i'th alloca then we're done!
if (PN)
return false;
// Create a PhiNode using the dereferenced type... and add the phi-node to the
// BasicBlock.
PN = PHINode::Create(Allocas[AllocaNo]->getAllocatedType(), getNumPreds(BB),
Allocas[AllocaNo]->getName() + "." + Twine(Version++),
&BB->front());
++NumPHIInsert;
PhiToAllocaMap[PN] = AllocaNo;
return true;
}
/// \brief Recursively traverse the CFG of the function, renaming loads and
/// stores to the allocas which we are promoting.
///
/// IncomingVals indicates what value each Alloca contains on exit from the
/// predecessor block Pred.
void PromoteMem2Reg::RenamePass(BasicBlock *BB, BasicBlock *Pred,
RenamePassData::ValVector &IncomingVals,
std::vector<RenamePassData> &Worklist) {
NextIteration:
// If we are inserting any phi nodes into this BB, they will already be in the
// block.
if (PHINode *APN = dyn_cast<PHINode>(BB->begin())) {
// If we have PHI nodes to update, compute the number of edges from Pred to
// BB.
if (PhiToAllocaMap.count(APN)) {
// We want to be able to distinguish between PHI nodes being inserted by
// this invocation of mem2reg from those phi nodes that already existed in
// the IR before mem2reg was run. We determine that APN is being inserted
// because it is missing incoming edges. All other PHI nodes being
// inserted by this pass of mem2reg will have the same number of incoming
// operands so far. Remember this count.
unsigned NewPHINumOperands = APN->getNumOperands();
unsigned NumEdges = std::count(succ_begin(Pred), succ_end(Pred), BB);
assert(NumEdges && "Must be at least one edge from Pred to BB!");
// Add entries for all the phis.
BasicBlock::iterator PNI = BB->begin();
do {
unsigned AllocaNo = PhiToAllocaMap[APN];
// Add N incoming values to the PHI node.
for (unsigned i = 0; i != NumEdges; ++i)
APN->addIncoming(IncomingVals[AllocaNo], Pred);
// The currently active variable for this block is now the PHI.
IncomingVals[AllocaNo] = APN;
if (DbgDeclareInst *DDI = AllocaDbgDeclares[AllocaNo])
ConvertDebugDeclareToDebugValue(DDI, APN, DIB);
// Get the next phi node.
++PNI;
APN = dyn_cast<PHINode>(PNI);
if (!APN)
break;
// Verify that it is missing entries. If not, it is not being inserted
// by this mem2reg invocation so we want to ignore it.
} while (APN->getNumOperands() == NewPHINumOperands);
}
}
// Don't revisit blocks.
if (!Visited.insert(BB).second)
return;
for (BasicBlock::iterator II = BB->begin(); !isa<TerminatorInst>(II);) {
Instruction *I = &*II++; // get the instruction, increment iterator
if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
AllocaInst *Src = dyn_cast<AllocaInst>(LI->getPointerOperand());
if (!Src)
continue;
DenseMap<AllocaInst *, unsigned>::iterator AI = AllocaLookup.find(Src);
if (AI == AllocaLookup.end())
continue;
Value *V = IncomingVals[AI->second];
// If the load was marked as nonnull we don't want to lose
// that information when we erase this Load. So we preserve
// it with an assume.
if (AC && LI->getMetadata(LLVMContext::MD_nonnull) &&
!llvm::isKnownNonNullAt(V, LI, &DT))
addAssumeNonNull(AC, LI);
// Anything using the load now uses the current value.
LI->replaceAllUsesWith(V);
BB->getInstList().erase(LI);
} else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
// Delete this instruction and mark the name as the current holder of the
// value
AllocaInst *Dest = dyn_cast<AllocaInst>(SI->getPointerOperand());
if (!Dest)
continue;
DenseMap<AllocaInst *, unsigned>::iterator ai = AllocaLookup.find(Dest);
if (ai == AllocaLookup.end())
continue;
// what value were we writing?
IncomingVals[ai->second] = SI->getOperand(0);
// Record debuginfo for the store before removing it.
if (DbgDeclareInst *DDI = AllocaDbgDeclares[ai->second])
ConvertDebugDeclareToDebugValue(DDI, SI, DIB);
BB->getInstList().erase(SI);
}
}
// 'Recurse' to our successors.
succ_iterator I = succ_begin(BB), E = succ_end(BB);
if (I == E)
return;
// Keep track of the successors so we don't visit the same successor twice
SmallPtrSet<BasicBlock *, 8> VisitedSuccs;
// Handle the first successor without using the worklist.
VisitedSuccs.insert(*I);
Pred = BB;
BB = *I;
++I;
for (; I != E; ++I)
if (VisitedSuccs.insert(*I).second)
Worklist.emplace_back(*I, Pred, IncomingVals);
goto NextIteration;
}
void llvm::PromoteMemToReg(ArrayRef<AllocaInst *> Allocas, DominatorTree &DT,
AssumptionCache *AC) {
// If there is nothing to do, bail out...
if (Allocas.empty())
return;
PromoteMem2Reg(Allocas, DT, AC).run();
}
|