aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Analysis/LoopAccessAnalysis.cpp
blob: 7bedd40432b7aa9a1a05818741e5c6ddb55f71fd (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
//===- LoopAccessAnalysis.cpp - Loop Access Analysis Implementation --------==//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The implementation for the loop memory dependence that was originally
// developed for the loop vectorizer.
//
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/LoopAccessAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/ScalarEvolutionExpander.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/Support/Debug.h"
#include "llvm/Transforms/Utils/VectorUtils.h"
using namespace llvm;

#define DEBUG_TYPE "loop-accesses"

static cl::opt<unsigned, true>
VectorizationFactor("force-vector-width", cl::Hidden,
                    cl::desc("Sets the SIMD width. Zero is autoselect."),
                    cl::location(VectorizerParams::VectorizationFactor));
unsigned VectorizerParams::VectorizationFactor;

static cl::opt<unsigned, true>
VectorizationInterleave("force-vector-interleave", cl::Hidden,
                        cl::desc("Sets the vectorization interleave count. "
                                 "Zero is autoselect."),
                        cl::location(
                            VectorizerParams::VectorizationInterleave));
unsigned VectorizerParams::VectorizationInterleave;

static cl::opt<unsigned, true> RuntimeMemoryCheckThreshold(
    "runtime-memory-check-threshold", cl::Hidden,
    cl::desc("When performing memory disambiguation checks at runtime do not "
             "generate more than this number of comparisons (default = 8)."),
    cl::location(VectorizerParams::RuntimeMemoryCheckThreshold), cl::init(8));
unsigned VectorizerParams::RuntimeMemoryCheckThreshold;

/// Maximum SIMD width.
const unsigned VectorizerParams::MaxVectorWidth = 64;

bool VectorizerParams::isInterleaveForced() {
  return ::VectorizationInterleave.getNumOccurrences() > 0;
}

void LoopAccessReport::emitAnalysis(const LoopAccessReport &Message,
                                    const Function *TheFunction,
                                    const Loop *TheLoop,
                                    const char *PassName) {
  DebugLoc DL = TheLoop->getStartLoc();
  if (const Instruction *I = Message.getInstr())
    DL = I->getDebugLoc();
  emitOptimizationRemarkAnalysis(TheFunction->getContext(), PassName,
                                 *TheFunction, DL, Message.str());
}

Value *llvm::stripIntegerCast(Value *V) {
  if (CastInst *CI = dyn_cast<CastInst>(V))
    if (CI->getOperand(0)->getType()->isIntegerTy())
      return CI->getOperand(0);
  return V;
}

const SCEV *llvm::replaceSymbolicStrideSCEV(ScalarEvolution *SE,
                                            const ValueToValueMap &PtrToStride,
                                            Value *Ptr, Value *OrigPtr) {

  const SCEV *OrigSCEV = SE->getSCEV(Ptr);

  // If there is an entry in the map return the SCEV of the pointer with the
  // symbolic stride replaced by one.
  ValueToValueMap::const_iterator SI =
      PtrToStride.find(OrigPtr ? OrigPtr : Ptr);
  if (SI != PtrToStride.end()) {
    Value *StrideVal = SI->second;

    // Strip casts.
    StrideVal = stripIntegerCast(StrideVal);

    // Replace symbolic stride by one.
    Value *One = ConstantInt::get(StrideVal->getType(), 1);
    ValueToValueMap RewriteMap;
    RewriteMap[StrideVal] = One;

    const SCEV *ByOne =
        SCEVParameterRewriter::rewrite(OrigSCEV, *SE, RewriteMap, true);
    DEBUG(dbgs() << "LAA: Replacing SCEV: " << *OrigSCEV << " by: " << *ByOne
                 << "\n");
    return ByOne;
  }

  // Otherwise, just return the SCEV of the original pointer.
  return SE->getSCEV(Ptr);
}

void LoopAccessInfo::RuntimePointerCheck::insert(
    ScalarEvolution *SE, Loop *Lp, Value *Ptr, bool WritePtr, unsigned DepSetId,
    unsigned ASId, const ValueToValueMap &Strides) {
  // Get the stride replaced scev.
  const SCEV *Sc = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Sc);
  assert(AR && "Invalid addrec expression");
  const SCEV *Ex = SE->getBackedgeTakenCount(Lp);
  const SCEV *ScEnd = AR->evaluateAtIteration(Ex, *SE);
  Pointers.push_back(Ptr);
  Starts.push_back(AR->getStart());
  Ends.push_back(ScEnd);
  IsWritePtr.push_back(WritePtr);
  DependencySetId.push_back(DepSetId);
  AliasSetId.push_back(ASId);
}

bool LoopAccessInfo::RuntimePointerCheck::needsChecking(unsigned I,
                                                        unsigned J) const {
  // No need to check if two readonly pointers intersect.
  if (!IsWritePtr[I] && !IsWritePtr[J])
    return false;

  // Only need to check pointers between two different dependency sets.
  if (DependencySetId[I] == DependencySetId[J])
    return false;

  // Only need to check pointers in the same alias set.
  if (AliasSetId[I] != AliasSetId[J])
    return false;

  return true;
}

void LoopAccessInfo::RuntimePointerCheck::print(raw_ostream &OS,
                                                unsigned Depth) const {
  unsigned NumPointers = Pointers.size();
  if (NumPointers == 0)
    return;

  OS.indent(Depth) << "Run-time memory checks:\n";
  unsigned N = 0;
  for (unsigned I = 0; I < NumPointers; ++I)
    for (unsigned J = I + 1; J < NumPointers; ++J)
      if (needsChecking(I, J)) {
        OS.indent(Depth) << N++ << ":\n";
        OS.indent(Depth + 2) << *Pointers[I] << "\n";
        OS.indent(Depth + 2) << *Pointers[J] << "\n";
      }
}

namespace {
/// \brief Analyses memory accesses in a loop.
///
/// Checks whether run time pointer checks are needed and builds sets for data
/// dependence checking.
class AccessAnalysis {
public:
  /// \brief Read or write access location.
  typedef PointerIntPair<Value *, 1, bool> MemAccessInfo;
  typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;

  /// \brief Set of potential dependent memory accesses.
  typedef EquivalenceClasses<MemAccessInfo> DepCandidates;

  AccessAnalysis(const DataLayout *Dl, AliasAnalysis *AA, DepCandidates &DA) :
    DL(Dl), AST(*AA), DepCands(DA), IsRTCheckNeeded(false) {}

  /// \brief Register a load  and whether it is only read from.
  void addLoad(AliasAnalysis::Location &Loc, bool IsReadOnly) {
    Value *Ptr = const_cast<Value*>(Loc.Ptr);
    AST.add(Ptr, AliasAnalysis::UnknownSize, Loc.AATags);
    Accesses.insert(MemAccessInfo(Ptr, false));
    if (IsReadOnly)
      ReadOnlyPtr.insert(Ptr);
  }

  /// \brief Register a store.
  void addStore(AliasAnalysis::Location &Loc) {
    Value *Ptr = const_cast<Value*>(Loc.Ptr);
    AST.add(Ptr, AliasAnalysis::UnknownSize, Loc.AATags);
    Accesses.insert(MemAccessInfo(Ptr, true));
  }

  /// \brief Check whether we can check the pointers at runtime for
  /// non-intersection.
  bool canCheckPtrAtRT(LoopAccessInfo::RuntimePointerCheck &RtCheck,
                       unsigned &NumComparisons, ScalarEvolution *SE,
                       Loop *TheLoop, const ValueToValueMap &Strides,
                       bool ShouldCheckStride = false);

  /// \brief Goes over all memory accesses, checks whether a RT check is needed
  /// and builds sets of dependent accesses.
  void buildDependenceSets() {
    processMemAccesses();
  }

  bool isRTCheckNeeded() { return IsRTCheckNeeded; }

  bool isDependencyCheckNeeded() { return !CheckDeps.empty(); }
  void resetDepChecks() { CheckDeps.clear(); }

  MemAccessInfoSet &getDependenciesToCheck() { return CheckDeps; }

private:
  typedef SetVector<MemAccessInfo> PtrAccessSet;

  /// \brief Go over all memory access and check whether runtime pointer checks
  /// are needed /// and build sets of dependency check candidates.
  void processMemAccesses();

  /// Set of all accesses.
  PtrAccessSet Accesses;

  /// Set of accesses that need a further dependence check.
  MemAccessInfoSet CheckDeps;

  /// Set of pointers that are read only.
  SmallPtrSet<Value*, 16> ReadOnlyPtr;

  const DataLayout *DL;

  /// An alias set tracker to partition the access set by underlying object and
  //intrinsic property (such as TBAA metadata).
  AliasSetTracker AST;

  /// Sets of potentially dependent accesses - members of one set share an
  /// underlying pointer. The set "CheckDeps" identfies which sets really need a
  /// dependence check.
  DepCandidates &DepCands;

  bool IsRTCheckNeeded;
};

} // end anonymous namespace

/// \brief Check whether a pointer can participate in a runtime bounds check.
static bool hasComputableBounds(ScalarEvolution *SE,
                                const ValueToValueMap &Strides, Value *Ptr) {
  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
  if (!AR)
    return false;

  return AR->isAffine();
}

/// \brief Check the stride of the pointer and ensure that it does not wrap in
/// the address space.
static int isStridedPtr(ScalarEvolution *SE, const DataLayout *DL, Value *Ptr,
                        const Loop *Lp, const ValueToValueMap &StridesMap);

bool AccessAnalysis::canCheckPtrAtRT(
    LoopAccessInfo::RuntimePointerCheck &RtCheck, unsigned &NumComparisons,
    ScalarEvolution *SE, Loop *TheLoop, const ValueToValueMap &StridesMap,
    bool ShouldCheckStride) {
  // Find pointers with computable bounds. We are going to use this information
  // to place a runtime bound check.
  bool CanDoRT = true;

  bool IsDepCheckNeeded = isDependencyCheckNeeded();
  NumComparisons = 0;

  // We assign a consecutive id to access from different alias sets.
  // Accesses between different groups doesn't need to be checked.
  unsigned ASId = 1;
  for (auto &AS : AST) {
    unsigned NumReadPtrChecks = 0;
    unsigned NumWritePtrChecks = 0;

    // We assign consecutive id to access from different dependence sets.
    // Accesses within the same set don't need a runtime check.
    unsigned RunningDepId = 1;
    DenseMap<Value *, unsigned> DepSetId;

    for (auto A : AS) {
      Value *Ptr = A.getValue();
      bool IsWrite = Accesses.count(MemAccessInfo(Ptr, true));
      MemAccessInfo Access(Ptr, IsWrite);

      if (IsWrite)
        ++NumWritePtrChecks;
      else
        ++NumReadPtrChecks;

      if (hasComputableBounds(SE, StridesMap, Ptr) &&
          // When we run after a failing dependency check we have to make sure we
          // don't have wrapping pointers.
          (!ShouldCheckStride ||
           isStridedPtr(SE, DL, Ptr, TheLoop, StridesMap) == 1)) {
        // The id of the dependence set.
        unsigned DepId;

        if (IsDepCheckNeeded) {
          Value *Leader = DepCands.getLeaderValue(Access).getPointer();
          unsigned &LeaderId = DepSetId[Leader];
          if (!LeaderId)
            LeaderId = RunningDepId++;
          DepId = LeaderId;
        } else
          // Each access has its own dependence set.
          DepId = RunningDepId++;

        RtCheck.insert(SE, TheLoop, Ptr, IsWrite, DepId, ASId, StridesMap);

        DEBUG(dbgs() << "LAA: Found a runtime check ptr:" << *Ptr << '\n');
      } else {
        CanDoRT = false;
      }
    }

    if (IsDepCheckNeeded && CanDoRT && RunningDepId == 2)
      NumComparisons += 0; // Only one dependence set.
    else {
      NumComparisons += (NumWritePtrChecks * (NumReadPtrChecks +
                                              NumWritePtrChecks - 1));
    }

    ++ASId;
  }

  // If the pointers that we would use for the bounds comparison have different
  // address spaces, assume the values aren't directly comparable, so we can't
  // use them for the runtime check. We also have to assume they could
  // overlap. In the future there should be metadata for whether address spaces
  // are disjoint.
  unsigned NumPointers = RtCheck.Pointers.size();
  for (unsigned i = 0; i < NumPointers; ++i) {
    for (unsigned j = i + 1; j < NumPointers; ++j) {
      // Only need to check pointers between two different dependency sets.
      if (RtCheck.DependencySetId[i] == RtCheck.DependencySetId[j])
       continue;
      // Only need to check pointers in the same alias set.
      if (RtCheck.AliasSetId[i] != RtCheck.AliasSetId[j])
        continue;

      Value *PtrI = RtCheck.Pointers[i];
      Value *PtrJ = RtCheck.Pointers[j];

      unsigned ASi = PtrI->getType()->getPointerAddressSpace();
      unsigned ASj = PtrJ->getType()->getPointerAddressSpace();
      if (ASi != ASj) {
        DEBUG(dbgs() << "LAA: Runtime check would require comparison between"
                       " different address spaces\n");
        return false;
      }
    }
  }

  return CanDoRT;
}

void AccessAnalysis::processMemAccesses() {
  // We process the set twice: first we process read-write pointers, last we
  // process read-only pointers. This allows us to skip dependence tests for
  // read-only pointers.

  DEBUG(dbgs() << "LAA: Processing memory accesses...\n");
  DEBUG(dbgs() << "  AST: "; AST.dump());
  DEBUG(dbgs() << "LAA:   Accesses:\n");
  DEBUG({
    for (auto A : Accesses)
      dbgs() << "\t" << *A.getPointer() << " (" <<
                (A.getInt() ? "write" : (ReadOnlyPtr.count(A.getPointer()) ?
                                         "read-only" : "read")) << ")\n";
  });

  // The AliasSetTracker has nicely partitioned our pointers by metadata
  // compatibility and potential for underlying-object overlap. As a result, we
  // only need to check for potential pointer dependencies within each alias
  // set.
  for (auto &AS : AST) {
    // Note that both the alias-set tracker and the alias sets themselves used
    // linked lists internally and so the iteration order here is deterministic
    // (matching the original instruction order within each set).

    bool SetHasWrite = false;

    // Map of pointers to last access encountered.
    typedef DenseMap<Value*, MemAccessInfo> UnderlyingObjToAccessMap;
    UnderlyingObjToAccessMap ObjToLastAccess;

    // Set of access to check after all writes have been processed.
    PtrAccessSet DeferredAccesses;

    // Iterate over each alias set twice, once to process read/write pointers,
    // and then to process read-only pointers.
    for (int SetIteration = 0; SetIteration < 2; ++SetIteration) {
      bool UseDeferred = SetIteration > 0;
      PtrAccessSet &S = UseDeferred ? DeferredAccesses : Accesses;

      for (auto AV : AS) {
        Value *Ptr = AV.getValue();

        // For a single memory access in AliasSetTracker, Accesses may contain
        // both read and write, and they both need to be handled for CheckDeps.
        for (auto AC : S) {
          if (AC.getPointer() != Ptr)
            continue;

          bool IsWrite = AC.getInt();

          // If we're using the deferred access set, then it contains only
          // reads.
          bool IsReadOnlyPtr = ReadOnlyPtr.count(Ptr) && !IsWrite;
          if (UseDeferred && !IsReadOnlyPtr)
            continue;
          // Otherwise, the pointer must be in the PtrAccessSet, either as a
          // read or a write.
          assert(((IsReadOnlyPtr && UseDeferred) || IsWrite ||
                  S.count(MemAccessInfo(Ptr, false))) &&
                 "Alias-set pointer not in the access set?");

          MemAccessInfo Access(Ptr, IsWrite);
          DepCands.insert(Access);

          // Memorize read-only pointers for later processing and skip them in
          // the first round (they need to be checked after we have seen all
          // write pointers). Note: we also mark pointer that are not
          // consecutive as "read-only" pointers (so that we check
          // "a[b[i]] +="). Hence, we need the second check for "!IsWrite".
          if (!UseDeferred && IsReadOnlyPtr) {
            DeferredAccesses.insert(Access);
            continue;
          }

          // If this is a write - check other reads and writes for conflicts. If
          // this is a read only check other writes for conflicts (but only if
          // there is no other write to the ptr - this is an optimization to
          // catch "a[i] = a[i] + " without having to do a dependence check).
          if ((IsWrite || IsReadOnlyPtr) && SetHasWrite) {
            CheckDeps.insert(Access);
            IsRTCheckNeeded = true;
          }

          if (IsWrite)
            SetHasWrite = true;

          // Create sets of pointers connected by a shared alias set and
          // underlying object.
          typedef SmallVector<Value *, 16> ValueVector;
          ValueVector TempObjects;
          GetUnderlyingObjects(Ptr, TempObjects, DL);
          for (Value *UnderlyingObj : TempObjects) {
            UnderlyingObjToAccessMap::iterator Prev =
                ObjToLastAccess.find(UnderlyingObj);
            if (Prev != ObjToLastAccess.end())
              DepCands.unionSets(Access, Prev->second);

            ObjToLastAccess[UnderlyingObj] = Access;
          }
        }
      }
    }
  }
}

namespace {
/// \brief Checks memory dependences among accesses to the same underlying
/// object to determine whether there vectorization is legal or not (and at
/// which vectorization factor).
///
/// This class works under the assumption that we already checked that memory
/// locations with different underlying pointers are "must-not alias".
/// We use the ScalarEvolution framework to symbolically evalutate access
/// functions pairs. Since we currently don't restructure the loop we can rely
/// on the program order of memory accesses to determine their safety.
/// At the moment we will only deem accesses as safe for:
///  * A negative constant distance assuming program order.
///
///      Safe: tmp = a[i + 1];     OR     a[i + 1] = x;
///            a[i] = tmp;                y = a[i];
///
///   The latter case is safe because later checks guarantuee that there can't
///   be a cycle through a phi node (that is, we check that "x" and "y" is not
///   the same variable: a header phi can only be an induction or a reduction, a
///   reduction can't have a memory sink, an induction can't have a memory
///   source). This is important and must not be violated (or we have to
///   resort to checking for cycles through memory).
///
///  * A positive constant distance assuming program order that is bigger
///    than the biggest memory access.
///
///     tmp = a[i]        OR              b[i] = x
///     a[i+2] = tmp                      y = b[i+2];
///
///     Safe distance: 2 x sizeof(a[0]), and 2 x sizeof(b[0]), respectively.
///
///  * Zero distances and all accesses have the same size.
///
class MemoryDepChecker {
public:
  typedef PointerIntPair<Value *, 1, bool> MemAccessInfo;
  typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;

  MemoryDepChecker(ScalarEvolution *Se, const DataLayout *Dl, const Loop *L)
      : SE(Se), DL(Dl), InnermostLoop(L), AccessIdx(0),
        ShouldRetryWithRuntimeCheck(false) {}

  /// \brief Register the location (instructions are given increasing numbers)
  /// of a write access.
  void addAccess(StoreInst *SI) {
    Value *Ptr = SI->getPointerOperand();
    Accesses[MemAccessInfo(Ptr, true)].push_back(AccessIdx);
    InstMap.push_back(SI);
    ++AccessIdx;
  }

  /// \brief Register the location (instructions are given increasing numbers)
  /// of a write access.
  void addAccess(LoadInst *LI) {
    Value *Ptr = LI->getPointerOperand();
    Accesses[MemAccessInfo(Ptr, false)].push_back(AccessIdx);
    InstMap.push_back(LI);
    ++AccessIdx;
  }

  /// \brief Check whether the dependencies between the accesses are safe.
  ///
  /// Only checks sets with elements in \p CheckDeps.
  bool areDepsSafe(AccessAnalysis::DepCandidates &AccessSets,
                   MemAccessInfoSet &CheckDeps, const ValueToValueMap &Strides);

  /// \brief The maximum number of bytes of a vector register we can vectorize
  /// the accesses safely with.
  unsigned getMaxSafeDepDistBytes() { return MaxSafeDepDistBytes; }

  /// \brief In same cases when the dependency check fails we can still
  /// vectorize the loop with a dynamic array access check.
  bool shouldRetryWithRuntimeCheck() { return ShouldRetryWithRuntimeCheck; }

private:
  ScalarEvolution *SE;
  const DataLayout *DL;
  const Loop *InnermostLoop;

  /// \brief Maps access locations (ptr, read/write) to program order.
  DenseMap<MemAccessInfo, std::vector<unsigned> > Accesses;

  /// \brief Memory access instructions in program order.
  SmallVector<Instruction *, 16> InstMap;

  /// \brief The program order index to be used for the next instruction.
  unsigned AccessIdx;

  // We can access this many bytes in parallel safely.
  unsigned MaxSafeDepDistBytes;

  /// \brief If we see a non-constant dependence distance we can still try to
  /// vectorize this loop with runtime checks.
  bool ShouldRetryWithRuntimeCheck;

  /// \brief Check whether there is a plausible dependence between the two
  /// accesses.
  ///
  /// Access \p A must happen before \p B in program order. The two indices
  /// identify the index into the program order map.
  ///
  /// This function checks  whether there is a plausible dependence (or the
  /// absence of such can't be proved) between the two accesses. If there is a
  /// plausible dependence but the dependence distance is bigger than one
  /// element access it records this distance in \p MaxSafeDepDistBytes (if this
  /// distance is smaller than any other distance encountered so far).
  /// Otherwise, this function returns true signaling a possible dependence.
  bool isDependent(const MemAccessInfo &A, unsigned AIdx,
                   const MemAccessInfo &B, unsigned BIdx,
                   const ValueToValueMap &Strides);

  /// \brief Check whether the data dependence could prevent store-load
  /// forwarding.
  bool couldPreventStoreLoadForward(unsigned Distance, unsigned TypeByteSize);
};

} // end anonymous namespace

static bool isInBoundsGep(Value *Ptr) {
  if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Ptr))
    return GEP->isInBounds();
  return false;
}

/// \brief Check whether the access through \p Ptr has a constant stride.
static int isStridedPtr(ScalarEvolution *SE, const DataLayout *DL, Value *Ptr,
                        const Loop *Lp, const ValueToValueMap &StridesMap) {
  const Type *Ty = Ptr->getType();
  assert(Ty->isPointerTy() && "Unexpected non-ptr");

  // Make sure that the pointer does not point to aggregate types.
  const PointerType *PtrTy = cast<PointerType>(Ty);
  if (PtrTy->getElementType()->isAggregateType()) {
    DEBUG(dbgs() << "LAA: Bad stride - Not a pointer to a scalar type"
          << *Ptr << "\n");
    return 0;
  }

  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, StridesMap, Ptr);

  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
  if (!AR) {
    DEBUG(dbgs() << "LAA: Bad stride - Not an AddRecExpr pointer "
          << *Ptr << " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  // The accesss function must stride over the innermost loop.
  if (Lp != AR->getLoop()) {
    DEBUG(dbgs() << "LAA: Bad stride - Not striding over innermost loop " <<
          *Ptr << " SCEV: " << *PtrScev << "\n");
  }

  // The address calculation must not wrap. Otherwise, a dependence could be
  // inverted.
  // An inbounds getelementptr that is a AddRec with a unit stride
  // cannot wrap per definition. The unit stride requirement is checked later.
  // An getelementptr without an inbounds attribute and unit stride would have
  // to access the pointer value "0" which is undefined behavior in address
  // space 0, therefore we can also vectorize this case.
  bool IsInBoundsGEP = isInBoundsGep(Ptr);
  bool IsNoWrapAddRec = AR->getNoWrapFlags(SCEV::NoWrapMask);
  bool IsInAddressSpaceZero = PtrTy->getAddressSpace() == 0;
  if (!IsNoWrapAddRec && !IsInBoundsGEP && !IsInAddressSpaceZero) {
    DEBUG(dbgs() << "LAA: Bad stride - Pointer may wrap in the address space "
          << *Ptr << " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  // Check the step is constant.
  const SCEV *Step = AR->getStepRecurrence(*SE);

  // Calculate the pointer stride and check if it is consecutive.
  const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
  if (!C) {
    DEBUG(dbgs() << "LAA: Bad stride - Not a constant strided " << *Ptr <<
          " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  int64_t Size = DL->getTypeAllocSize(PtrTy->getElementType());
  const APInt &APStepVal = C->getValue()->getValue();

  // Huge step value - give up.
  if (APStepVal.getBitWidth() > 64)
    return 0;

  int64_t StepVal = APStepVal.getSExtValue();

  // Strided access.
  int64_t Stride = StepVal / Size;
  int64_t Rem = StepVal % Size;
  if (Rem)
    return 0;

  // If the SCEV could wrap but we have an inbounds gep with a unit stride we
  // know we can't "wrap around the address space". In case of address space
  // zero we know that this won't happen without triggering undefined behavior.
  if (!IsNoWrapAddRec && (IsInBoundsGEP || IsInAddressSpaceZero) &&
      Stride != 1 && Stride != -1)
    return 0;

  return Stride;
}

bool MemoryDepChecker::couldPreventStoreLoadForward(unsigned Distance,
                                                    unsigned TypeByteSize) {
  // If loads occur at a distance that is not a multiple of a feasible vector
  // factor store-load forwarding does not take place.
  // Positive dependences might cause troubles because vectorizing them might
  // prevent store-load forwarding making vectorized code run a lot slower.
  //   a[i] = a[i-3] ^ a[i-8];
  //   The stores to a[i:i+1] don't align with the stores to a[i-3:i-2] and
  //   hence on your typical architecture store-load forwarding does not take
  //   place. Vectorizing in such cases does not make sense.
  // Store-load forwarding distance.
  const unsigned NumCyclesForStoreLoadThroughMemory = 8*TypeByteSize;
  // Maximum vector factor.
  unsigned MaxVFWithoutSLForwardIssues =
    VectorizerParams::MaxVectorWidth * TypeByteSize;
  if(MaxSafeDepDistBytes < MaxVFWithoutSLForwardIssues)
    MaxVFWithoutSLForwardIssues = MaxSafeDepDistBytes;

  for (unsigned vf = 2*TypeByteSize; vf <= MaxVFWithoutSLForwardIssues;
       vf *= 2) {
    if (Distance % vf && Distance / vf < NumCyclesForStoreLoadThroughMemory) {
      MaxVFWithoutSLForwardIssues = (vf >>=1);
      break;
    }
  }

  if (MaxVFWithoutSLForwardIssues< 2*TypeByteSize) {
    DEBUG(dbgs() << "LAA: Distance " << Distance <<
          " that could cause a store-load forwarding conflict\n");
    return true;
  }

  if (MaxVFWithoutSLForwardIssues < MaxSafeDepDistBytes &&
      MaxVFWithoutSLForwardIssues !=
      VectorizerParams::MaxVectorWidth * TypeByteSize)
    MaxSafeDepDistBytes = MaxVFWithoutSLForwardIssues;
  return false;
}

bool MemoryDepChecker::isDependent(const MemAccessInfo &A, unsigned AIdx,
                                   const MemAccessInfo &B, unsigned BIdx,
                                   const ValueToValueMap &Strides) {
  assert (AIdx < BIdx && "Must pass arguments in program order");

  Value *APtr = A.getPointer();
  Value *BPtr = B.getPointer();
  bool AIsWrite = A.getInt();
  bool BIsWrite = B.getInt();

  // Two reads are independent.
  if (!AIsWrite && !BIsWrite)
    return false;

  // We cannot check pointers in different address spaces.
  if (APtr->getType()->getPointerAddressSpace() !=
      BPtr->getType()->getPointerAddressSpace())
    return true;

  const SCEV *AScev = replaceSymbolicStrideSCEV(SE, Strides, APtr);
  const SCEV *BScev = replaceSymbolicStrideSCEV(SE, Strides, BPtr);

  int StrideAPtr = isStridedPtr(SE, DL, APtr, InnermostLoop, Strides);
  int StrideBPtr = isStridedPtr(SE, DL, BPtr, InnermostLoop, Strides);

  const SCEV *Src = AScev;
  const SCEV *Sink = BScev;

  // If the induction step is negative we have to invert source and sink of the
  // dependence.
  if (StrideAPtr < 0) {
    //Src = BScev;
    //Sink = AScev;
    std::swap(APtr, BPtr);
    std::swap(Src, Sink);
    std::swap(AIsWrite, BIsWrite);
    std::swap(AIdx, BIdx);
    std::swap(StrideAPtr, StrideBPtr);
  }

  const SCEV *Dist = SE->getMinusSCEV(Sink, Src);

  DEBUG(dbgs() << "LAA: Src Scev: " << *Src << "Sink Scev: " << *Sink
        << "(Induction step: " << StrideAPtr <<  ")\n");
  DEBUG(dbgs() << "LAA: Distance for " << *InstMap[AIdx] << " to "
        << *InstMap[BIdx] << ": " << *Dist << "\n");

  // Need consecutive accesses. We don't want to vectorize
  // "A[B[i]] += ..." and similar code or pointer arithmetic that could wrap in
  // the address space.
  if (!StrideAPtr || !StrideBPtr || StrideAPtr != StrideBPtr){
    DEBUG(dbgs() << "Non-consecutive pointer access\n");
    return true;
  }

  const SCEVConstant *C = dyn_cast<SCEVConstant>(Dist);
  if (!C) {
    DEBUG(dbgs() << "LAA: Dependence because of non-constant distance\n");
    ShouldRetryWithRuntimeCheck = true;
    return true;
  }

  Type *ATy = APtr->getType()->getPointerElementType();
  Type *BTy = BPtr->getType()->getPointerElementType();
  unsigned TypeByteSize = DL->getTypeAllocSize(ATy);

  // Negative distances are not plausible dependencies.
  const APInt &Val = C->getValue()->getValue();
  if (Val.isNegative()) {
    bool IsTrueDataDependence = (AIsWrite && !BIsWrite);
    if (IsTrueDataDependence &&
        (couldPreventStoreLoadForward(Val.abs().getZExtValue(), TypeByteSize) ||
         ATy != BTy))
      return true;

    DEBUG(dbgs() << "LAA: Dependence is negative: NoDep\n");
    return false;
  }

  // Write to the same location with the same size.
  // Could be improved to assert type sizes are the same (i32 == float, etc).
  if (Val == 0) {
    if (ATy == BTy)
      return false;
    DEBUG(dbgs() << "LAA: Zero dependence difference but different types\n");
    return true;
  }

  assert(Val.isStrictlyPositive() && "Expect a positive value");

  if (ATy != BTy) {
    DEBUG(dbgs() <<
          "LAA: ReadWrite-Write positive dependency with different types\n");
    return true;
  }

  unsigned Distance = (unsigned) Val.getZExtValue();

  // Bail out early if passed-in parameters make vectorization not feasible.
  unsigned ForcedFactor = (VectorizerParams::VectorizationFactor ?
                           VectorizerParams::VectorizationFactor : 1);
  unsigned ForcedUnroll = (VectorizerParams::VectorizationInterleave ?
                           VectorizerParams::VectorizationInterleave : 1);

  // The distance must be bigger than the size needed for a vectorized version
  // of the operation and the size of the vectorized operation must not be
  // bigger than the currrent maximum size.
  if (Distance < 2*TypeByteSize ||
      2*TypeByteSize > MaxSafeDepDistBytes ||
      Distance < TypeByteSize * ForcedUnroll * ForcedFactor) {
    DEBUG(dbgs() << "LAA: Failure because of Positive distance "
        << Val.getSExtValue() << '\n');
    return true;
  }

  // Positive distance bigger than max vectorization factor.
  MaxSafeDepDistBytes = Distance < MaxSafeDepDistBytes ?
    Distance : MaxSafeDepDistBytes;

  bool IsTrueDataDependence = (!AIsWrite && BIsWrite);
  if (IsTrueDataDependence &&
      couldPreventStoreLoadForward(Distance, TypeByteSize))
     return true;

  DEBUG(dbgs() << "LAA: Positive distance " << Val.getSExtValue() <<
        " with max VF = " << MaxSafeDepDistBytes / TypeByteSize << '\n');

  return false;
}

bool MemoryDepChecker::areDepsSafe(AccessAnalysis::DepCandidates &AccessSets,
                                   MemAccessInfoSet &CheckDeps,
                                   const ValueToValueMap &Strides) {

  MaxSafeDepDistBytes = -1U;
  while (!CheckDeps.empty()) {
    MemAccessInfo CurAccess = *CheckDeps.begin();

    // Get the relevant memory access set.
    EquivalenceClasses<MemAccessInfo>::iterator I =
      AccessSets.findValue(AccessSets.getLeaderValue(CurAccess));

    // Check accesses within this set.
    EquivalenceClasses<MemAccessInfo>::member_iterator AI, AE;
    AI = AccessSets.member_begin(I), AE = AccessSets.member_end();

    // Check every access pair.
    while (AI != AE) {
      CheckDeps.erase(*AI);
      EquivalenceClasses<MemAccessInfo>::member_iterator OI = std::next(AI);
      while (OI != AE) {
        // Check every accessing instruction pair in program order.
        for (std::vector<unsigned>::iterator I1 = Accesses[*AI].begin(),
             I1E = Accesses[*AI].end(); I1 != I1E; ++I1)
          for (std::vector<unsigned>::iterator I2 = Accesses[*OI].begin(),
               I2E = Accesses[*OI].end(); I2 != I2E; ++I2) {
            if (*I1 < *I2 && isDependent(*AI, *I1, *OI, *I2, Strides))
              return false;
            if (*I2 < *I1 && isDependent(*OI, *I2, *AI, *I1, Strides))
              return false;
          }
        ++OI;
      }
      AI++;
    }
  }
  return true;
}

bool LoopAccessInfo::canAnalyzeLoop() {
    // We can only analyze innermost loops.
  if (!TheLoop->empty()) {
    emitAnalysis(LoopAccessReport() << "loop is not the innermost loop");
    return false;
  }

  // We must have a single backedge.
  if (TheLoop->getNumBackEdges() != 1) {
    emitAnalysis(
        LoopAccessReport() <<
        "loop control flow is not understood by analyzer");
    return false;
  }

  // We must have a single exiting block.
  if (!TheLoop->getExitingBlock()) {
    emitAnalysis(
        LoopAccessReport() <<
        "loop control flow is not understood by analyzer");
    return false;
  }

  // We only handle bottom-tested loops, i.e. loop in which the condition is
  // checked at the end of each iteration. With that we can assume that all
  // instructions in the loop are executed the same number of times.
  if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch()) {
    emitAnalysis(
        LoopAccessReport() <<
        "loop control flow is not understood by analyzer");
    return false;
  }

  // We need to have a loop header.
  DEBUG(dbgs() << "LAA: Found a loop: " <<
        TheLoop->getHeader()->getName() << '\n');

  // ScalarEvolution needs to be able to find the exit count.
  const SCEV *ExitCount = SE->getBackedgeTakenCount(TheLoop);
  if (ExitCount == SE->getCouldNotCompute()) {
    emitAnalysis(LoopAccessReport() <<
                 "could not determine number of loop iterations");
    DEBUG(dbgs() << "LAA: SCEV could not compute the loop exit count.\n");
    return false;
  }

  return true;
}

void LoopAccessInfo::analyzeLoop(const ValueToValueMap &Strides) {

  typedef SmallVector<Value*, 16> ValueVector;
  typedef SmallPtrSet<Value*, 16> ValueSet;

  // Holds the Load and Store *instructions*.
  ValueVector Loads;
  ValueVector Stores;

  // Holds all the different accesses in the loop.
  unsigned NumReads = 0;
  unsigned NumReadWrites = 0;

  PtrRtCheck.Pointers.clear();
  PtrRtCheck.Need = false;

  const bool IsAnnotatedParallel = TheLoop->isAnnotatedParallel();
  MemoryDepChecker DepChecker(SE, DL, TheLoop);

  // For each block.
  for (Loop::block_iterator bb = TheLoop->block_begin(),
       be = TheLoop->block_end(); bb != be; ++bb) {

    // Scan the BB and collect legal loads and stores.
    for (BasicBlock::iterator it = (*bb)->begin(), e = (*bb)->end(); it != e;
         ++it) {

      // If this is a load, save it. If this instruction can read from memory
      // but is not a load, then we quit. Notice that we don't handle function
      // calls that read or write.
      if (it->mayReadFromMemory()) {
        // Many math library functions read the rounding mode. We will only
        // vectorize a loop if it contains known function calls that don't set
        // the flag. Therefore, it is safe to ignore this read from memory.
        CallInst *Call = dyn_cast<CallInst>(it);
        if (Call && getIntrinsicIDForCall(Call, TLI))
          continue;

        LoadInst *Ld = dyn_cast<LoadInst>(it);
        if (!Ld || (!Ld->isSimple() && !IsAnnotatedParallel)) {
          emitAnalysis(LoopAccessReport(Ld)
                       << "read with atomic ordering or volatile read");
          DEBUG(dbgs() << "LAA: Found a non-simple load.\n");
          CanVecMem = false;
          return;
        }
        NumLoads++;
        Loads.push_back(Ld);
        DepChecker.addAccess(Ld);
        continue;
      }

      // Save 'store' instructions. Abort if other instructions write to memory.
      if (it->mayWriteToMemory()) {
        StoreInst *St = dyn_cast<StoreInst>(it);
        if (!St) {
          emitAnalysis(LoopAccessReport(it) <<
                       "instruction cannot be vectorized");
          CanVecMem = false;
          return;
        }
        if (!St->isSimple() && !IsAnnotatedParallel) {
          emitAnalysis(LoopAccessReport(St)
                       << "write with atomic ordering or volatile write");
          DEBUG(dbgs() << "LAA: Found a non-simple store.\n");
          CanVecMem = false;
          return;
        }
        NumStores++;
        Stores.push_back(St);
        DepChecker.addAccess(St);
      }
    } // Next instr.
  } // Next block.

  // Now we have two lists that hold the loads and the stores.
  // Next, we find the pointers that they use.

  // Check if we see any stores. If there are no stores, then we don't
  // care if the pointers are *restrict*.
  if (!Stores.size()) {
    DEBUG(dbgs() << "LAA: Found a read-only loop!\n");
    CanVecMem = true;
    return;
  }

  AccessAnalysis::DepCandidates DependentAccesses;
  AccessAnalysis Accesses(DL, AA, DependentAccesses);

  // Holds the analyzed pointers. We don't want to call GetUnderlyingObjects
  // multiple times on the same object. If the ptr is accessed twice, once
  // for read and once for write, it will only appear once (on the write
  // list). This is okay, since we are going to check for conflicts between
  // writes and between reads and writes, but not between reads and reads.
  ValueSet Seen;

  ValueVector::iterator I, IE;
  for (I = Stores.begin(), IE = Stores.end(); I != IE; ++I) {
    StoreInst *ST = cast<StoreInst>(*I);
    Value* Ptr = ST->getPointerOperand();

    if (isUniform(Ptr)) {
      emitAnalysis(
          LoopAccessReport(ST)
          << "write to a loop invariant address could not be vectorized");
      DEBUG(dbgs() << "LAA: We don't allow storing to uniform addresses\n");
      CanVecMem = false;
      return;
    }

    // If we did *not* see this pointer before, insert it to  the read-write
    // list. At this phase it is only a 'write' list.
    if (Seen.insert(Ptr).second) {
      ++NumReadWrites;

      AliasAnalysis::Location Loc = AA->getLocation(ST);
      // The TBAA metadata could have a control dependency on the predication
      // condition, so we cannot rely on it when determining whether or not we
      // need runtime pointer checks.
      if (blockNeedsPredication(ST->getParent(), TheLoop, DT))
        Loc.AATags.TBAA = nullptr;

      Accesses.addStore(Loc);
    }
  }

  if (IsAnnotatedParallel) {
    DEBUG(dbgs()
          << "LAA: A loop annotated parallel, ignore memory dependency "
          << "checks.\n");
    CanVecMem = true;
    return;
  }

  for (I = Loads.begin(), IE = Loads.end(); I != IE; ++I) {
    LoadInst *LD = cast<LoadInst>(*I);
    Value* Ptr = LD->getPointerOperand();
    // If we did *not* see this pointer before, insert it to the
    // read list. If we *did* see it before, then it is already in
    // the read-write list. This allows us to vectorize expressions
    // such as A[i] += x;  Because the address of A[i] is a read-write
    // pointer. This only works if the index of A[i] is consecutive.
    // If the address of i is unknown (for example A[B[i]]) then we may
    // read a few words, modify, and write a few words, and some of the
    // words may be written to the same address.
    bool IsReadOnlyPtr = false;
    if (Seen.insert(Ptr).second ||
        !isStridedPtr(SE, DL, Ptr, TheLoop, Strides)) {
      ++NumReads;
      IsReadOnlyPtr = true;
    }

    AliasAnalysis::Location Loc = AA->getLocation(LD);
    // The TBAA metadata could have a control dependency on the predication
    // condition, so we cannot rely on it when determining whether or not we
    // need runtime pointer checks.
    if (blockNeedsPredication(LD->getParent(), TheLoop, DT))
      Loc.AATags.TBAA = nullptr;

    Accesses.addLoad(Loc, IsReadOnlyPtr);
  }

  // If we write (or read-write) to a single destination and there are no
  // other reads in this loop then is it safe to vectorize.
  if (NumReadWrites == 1 && NumReads == 0) {
    DEBUG(dbgs() << "LAA: Found a write-only loop!\n");
    CanVecMem = true;
    return;
  }

  // Build dependence sets and check whether we need a runtime pointer bounds
  // check.
  Accesses.buildDependenceSets();
  bool NeedRTCheck = Accesses.isRTCheckNeeded();

  // Find pointers with computable bounds. We are going to use this information
  // to place a runtime bound check.
  unsigned NumComparisons = 0;
  bool CanDoRT = false;
  if (NeedRTCheck)
    CanDoRT = Accesses.canCheckPtrAtRT(PtrRtCheck, NumComparisons, SE, TheLoop,
                                       Strides);

  DEBUG(dbgs() << "LAA: We need to do " << NumComparisons <<
        " pointer comparisons.\n");

  // If we only have one set of dependences to check pointers among we don't
  // need a runtime check.
  if (NumComparisons == 0 && NeedRTCheck)
    NeedRTCheck = false;

  // Check that we did not collect too many pointers or found an unsizeable
  // pointer.
  if (!CanDoRT || NumComparisons > RuntimeMemoryCheckThreshold) {
    PtrRtCheck.reset();
    CanDoRT = false;
  }

  if (CanDoRT) {
    DEBUG(dbgs() << "LAA: We can perform a memory runtime check if needed.\n");
  }

  if (NeedRTCheck && !CanDoRT) {
    emitAnalysis(LoopAccessReport() << "cannot identify array bounds");
    DEBUG(dbgs() << "LAA: We can't vectorize because we can't find " <<
          "the array bounds.\n");
    PtrRtCheck.reset();
    CanVecMem = false;
    return;
  }

  PtrRtCheck.Need = NeedRTCheck;

  CanVecMem = true;
  if (Accesses.isDependencyCheckNeeded()) {
    DEBUG(dbgs() << "LAA: Checking memory dependencies\n");
    CanVecMem = DepChecker.areDepsSafe(
        DependentAccesses, Accesses.getDependenciesToCheck(), Strides);
    MaxSafeDepDistBytes = DepChecker.getMaxSafeDepDistBytes();

    if (!CanVecMem && DepChecker.shouldRetryWithRuntimeCheck()) {
      DEBUG(dbgs() << "LAA: Retrying with memory checks\n");
      NeedRTCheck = true;

      // Clear the dependency checks. We assume they are not needed.
      Accesses.resetDepChecks();

      PtrRtCheck.reset();
      PtrRtCheck.Need = true;

      CanDoRT = Accesses.canCheckPtrAtRT(PtrRtCheck, NumComparisons, SE,
                                         TheLoop, Strides, true);
      // Check that we did not collect too many pointers or found an unsizeable
      // pointer.
      if (!CanDoRT || NumComparisons > RuntimeMemoryCheckThreshold) {
        if (!CanDoRT && NumComparisons > 0)
          emitAnalysis(LoopAccessReport()
                       << "cannot check memory dependencies at runtime");
        else
          emitAnalysis(LoopAccessReport()
                       << NumComparisons << " exceeds limit of "
                       << RuntimeMemoryCheckThreshold
                       << " dependent memory operations checked at runtime");
        DEBUG(dbgs() << "LAA: Can't vectorize with memory checks\n");
        PtrRtCheck.reset();
        CanVecMem = false;
        return;
      }

      CanVecMem = true;
    }
  }

  if (!CanVecMem)
    emitAnalysis(LoopAccessReport() <<
                 "unsafe dependent memory operations in loop");

  DEBUG(dbgs() << "LAA: We" << (NeedRTCheck ? "" : " don't") <<
        " need a runtime memory check.\n");
}

bool LoopAccessInfo::blockNeedsPredication(BasicBlock *BB, Loop *TheLoop,
                                           DominatorTree *DT)  {
  assert(TheLoop->contains(BB) && "Unknown block used");

  // Blocks that do not dominate the latch need predication.
  BasicBlock* Latch = TheLoop->getLoopLatch();
  return !DT->dominates(BB, Latch);
}

void LoopAccessInfo::emitAnalysis(LoopAccessReport &Message) {
  assert(!Report && "Multiple reports generated");
  Report = Message;
}

bool LoopAccessInfo::isUniform(Value *V) const {
  return (SE->isLoopInvariant(SE->getSCEV(V), TheLoop));
}

// FIXME: this function is currently a duplicate of the one in
// LoopVectorize.cpp.
static Instruction *getFirstInst(Instruction *FirstInst, Value *V,
                                 Instruction *Loc) {
  if (FirstInst)
    return FirstInst;
  if (Instruction *I = dyn_cast<Instruction>(V))
    return I->getParent() == Loc->getParent() ? I : nullptr;
  return nullptr;
}

std::pair<Instruction *, Instruction *>
LoopAccessInfo::addRuntimeCheck(Instruction *Loc) const {
  Instruction *tnullptr = nullptr;
  if (!PtrRtCheck.Need)
    return std::pair<Instruction *, Instruction *>(tnullptr, tnullptr);

  unsigned NumPointers = PtrRtCheck.Pointers.size();
  SmallVector<TrackingVH<Value> , 2> Starts;
  SmallVector<TrackingVH<Value> , 2> Ends;

  LLVMContext &Ctx = Loc->getContext();
  SCEVExpander Exp(*SE, "induction");
  Instruction *FirstInst = nullptr;

  for (unsigned i = 0; i < NumPointers; ++i) {
    Value *Ptr = PtrRtCheck.Pointers[i];
    const SCEV *Sc = SE->getSCEV(Ptr);

    if (SE->isLoopInvariant(Sc, TheLoop)) {
      DEBUG(dbgs() << "LAA: Adding RT check for a loop invariant ptr:" <<
            *Ptr <<"\n");
      Starts.push_back(Ptr);
      Ends.push_back(Ptr);
    } else {
      DEBUG(dbgs() << "LAA: Adding RT check for range:" << *Ptr << '\n');
      unsigned AS = Ptr->getType()->getPointerAddressSpace();

      // Use this type for pointer arithmetic.
      Type *PtrArithTy = Type::getInt8PtrTy(Ctx, AS);

      Value *Start = Exp.expandCodeFor(PtrRtCheck.Starts[i], PtrArithTy, Loc);
      Value *End = Exp.expandCodeFor(PtrRtCheck.Ends[i], PtrArithTy, Loc);
      Starts.push_back(Start);
      Ends.push_back(End);
    }
  }

  IRBuilder<> ChkBuilder(Loc);
  // Our instructions might fold to a constant.
  Value *MemoryRuntimeCheck = nullptr;
  for (unsigned i = 0; i < NumPointers; ++i) {
    for (unsigned j = i+1; j < NumPointers; ++j) {
      if (!PtrRtCheck.needsChecking(i, j))
        continue;

      unsigned AS0 = Starts[i]->getType()->getPointerAddressSpace();
      unsigned AS1 = Starts[j]->getType()->getPointerAddressSpace();

      assert((AS0 == Ends[j]->getType()->getPointerAddressSpace()) &&
             (AS1 == Ends[i]->getType()->getPointerAddressSpace()) &&
             "Trying to bounds check pointers with different address spaces");

      Type *PtrArithTy0 = Type::getInt8PtrTy(Ctx, AS0);
      Type *PtrArithTy1 = Type::getInt8PtrTy(Ctx, AS1);

      Value *Start0 = ChkBuilder.CreateBitCast(Starts[i], PtrArithTy0, "bc");
      Value *Start1 = ChkBuilder.CreateBitCast(Starts[j], PtrArithTy1, "bc");
      Value *End0 =   ChkBuilder.CreateBitCast(Ends[i],   PtrArithTy1, "bc");
      Value *End1 =   ChkBuilder.CreateBitCast(Ends[j],   PtrArithTy0, "bc");

      Value *Cmp0 = ChkBuilder.CreateICmpULE(Start0, End1, "bound0");
      FirstInst = getFirstInst(FirstInst, Cmp0, Loc);
      Value *Cmp1 = ChkBuilder.CreateICmpULE(Start1, End0, "bound1");
      FirstInst = getFirstInst(FirstInst, Cmp1, Loc);
      Value *IsConflict = ChkBuilder.CreateAnd(Cmp0, Cmp1, "found.conflict");
      FirstInst = getFirstInst(FirstInst, IsConflict, Loc);
      if (MemoryRuntimeCheck) {
        IsConflict = ChkBuilder.CreateOr(MemoryRuntimeCheck, IsConflict,
                                         "conflict.rdx");
        FirstInst = getFirstInst(FirstInst, IsConflict, Loc);
      }
      MemoryRuntimeCheck = IsConflict;
    }
  }

  // We have to do this trickery because the IRBuilder might fold the check to a
  // constant expression in which case there is no Instruction anchored in a
  // the block.
  Instruction *Check = BinaryOperator::CreateAnd(MemoryRuntimeCheck,
                                                 ConstantInt::getTrue(Ctx));
  ChkBuilder.Insert(Check, "memcheck.conflict");
  FirstInst = getFirstInst(FirstInst, Check, Loc);
  return std::make_pair(FirstInst, Check);
}

LoopAccessInfo::LoopAccessInfo(Loop *L, ScalarEvolution *SE,
                               const DataLayout *DL,
                               const TargetLibraryInfo *TLI, AliasAnalysis *AA,
                               DominatorTree *DT,
                               const ValueToValueMap &Strides)
    : TheLoop(L), SE(SE), DL(DL), TLI(TLI), AA(AA), DT(DT), NumLoads(0),
      NumStores(0), MaxSafeDepDistBytes(-1U), CanVecMem(false) {
  if (canAnalyzeLoop())
    analyzeLoop(Strides);
}

void LoopAccessInfo::print(raw_ostream &OS, unsigned Depth) const {
  if (CanVecMem) {
    if (PtrRtCheck.empty())
      OS.indent(Depth) << "Memory dependences are safe\n";
    else
      OS.indent(Depth) << "Memory dependences are safe with run-time checks\n";
  }

  if (Report)
    OS.indent(Depth) << "Report: " << Report->str() << "\n";

  // FIXME: Print unsafe dependences

  // List the pair of accesses need run-time checks to prove independence.
  PtrRtCheck.print(OS, Depth);
  OS << "\n";
}

const LoopAccessInfo &
LoopAccessAnalysis::getInfo(Loop *L, const ValueToValueMap &Strides) {
  auto &LAI = LoopAccessInfoMap[L];

#ifndef NDEBUG
  assert((!LAI || LAI->NumSymbolicStrides == Strides.size()) &&
         "Symbolic strides changed for loop");
#endif

  if (!LAI) {
    LAI = llvm::make_unique<LoopAccessInfo>(L, SE, DL, TLI, AA, DT, Strides);
#ifndef NDEBUG
    LAI->NumSymbolicStrides = Strides.size();
#endif
  }
  return *LAI.get();
}

void LoopAccessAnalysis::print(raw_ostream &OS, const Module *M) const {
  LoopAccessAnalysis &LAA = *const_cast<LoopAccessAnalysis *>(this);

  LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  ValueToValueMap NoSymbolicStrides;

  for (Loop *TopLevelLoop : *LI)
    for (Loop *L : depth_first(TopLevelLoop)) {
      OS.indent(2) << L->getHeader()->getName() << ":\n";
      auto &LAI = LAA.getInfo(L, NoSymbolicStrides);
      LAI.print(OS, 4);
    }
}

bool LoopAccessAnalysis::runOnFunction(Function &F) {
  SE = &getAnalysis<ScalarEvolution>();
  DL = F.getParent()->getDataLayout();
  auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
  TLI = TLIP ? &TLIP->getTLI() : nullptr;
  AA = &getAnalysis<AliasAnalysis>();
  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();

  return false;
}

void LoopAccessAnalysis::getAnalysisUsage(AnalysisUsage &AU) const {
    AU.addRequired<ScalarEvolution>();
    AU.addRequired<AliasAnalysis>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<LoopInfoWrapperPass>();

    AU.setPreservesAll();
}

char LoopAccessAnalysis::ID = 0;
static const char laa_name[] = "Loop Access Analysis";
#define LAA_NAME "loop-accesses"

INITIALIZE_PASS_BEGIN(LoopAccessAnalysis, LAA_NAME, laa_name, false, true)
INITIALIZE_AG_DEPENDENCY(AliasAnalysis)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_END(LoopAccessAnalysis, LAA_NAME, laa_name, false, true)

namespace llvm {
  Pass *createLAAPass() {
    return new LoopAccessAnalysis();
  }
}