aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Transforms/Scalar/LoopInterchange.cpp
blob: c2b065c4eb3140c3255bdb6f3811de00af31b8ef (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
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
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
//===- LoopInterchange.cpp - Loop interchange pass-------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This Pass handles loop interchange transform.
// This pass interchanges loops to provide a more cache-friendly memory access
// patterns.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/LoopInterchange.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Analysis/DependenceAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopNestAnalysis.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/User.h"
#include "llvm/IR/Value.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include <cassert>
#include <utility>
#include <vector>

using namespace llvm;

#define DEBUG_TYPE "loop-interchange"

STATISTIC(LoopsInterchanged, "Number of loops interchanged");

static cl::opt<int> LoopInterchangeCostThreshold(
    "loop-interchange-threshold", cl::init(0), cl::Hidden,
    cl::desc("Interchange if you gain more than this number"));

namespace {

using LoopVector = SmallVector<Loop *, 8>;

// TODO: Check if we can use a sparse matrix here.
using CharMatrix = std::vector<std::vector<char>>;

} // end anonymous namespace

// Maximum number of dependencies that can be handled in the dependency matrix.
static const unsigned MaxMemInstrCount = 100;

// Maximum loop depth supported.
static const unsigned MaxLoopNestDepth = 10;

#ifdef DUMP_DEP_MATRICIES
static void printDepMatrix(CharMatrix &DepMatrix) {
  for (auto &Row : DepMatrix) {
    for (auto D : Row)
      LLVM_DEBUG(dbgs() << D << " ");
    LLVM_DEBUG(dbgs() << "\n");
  }
}
#endif

static bool populateDependencyMatrix(CharMatrix &DepMatrix, unsigned Level,
                                     Loop *L, DependenceInfo *DI) {
  using ValueVector = SmallVector<Value *, 16>;

  ValueVector MemInstr;

  // For each block.
  for (BasicBlock *BB : L->blocks()) {
    // Scan the BB and collect legal loads and stores.
    for (Instruction &I : *BB) {
      if (!isa<Instruction>(I))
        return false;
      if (auto *Ld = dyn_cast<LoadInst>(&I)) {
        if (!Ld->isSimple())
          return false;
        MemInstr.push_back(&I);
      } else if (auto *St = dyn_cast<StoreInst>(&I)) {
        if (!St->isSimple())
          return false;
        MemInstr.push_back(&I);
      }
    }
  }

  LLVM_DEBUG(dbgs() << "Found " << MemInstr.size()
                    << " Loads and Stores to analyze\n");

  ValueVector::iterator I, IE, J, JE;

  for (I = MemInstr.begin(), IE = MemInstr.end(); I != IE; ++I) {
    for (J = I, JE = MemInstr.end(); J != JE; ++J) {
      std::vector<char> Dep;
      Instruction *Src = cast<Instruction>(*I);
      Instruction *Dst = cast<Instruction>(*J);
      if (Src == Dst)
        continue;
      // Ignore Input dependencies.
      if (isa<LoadInst>(Src) && isa<LoadInst>(Dst))
        continue;
      // Track Output, Flow, and Anti dependencies.
      if (auto D = DI->depends(Src, Dst, true)) {
        assert(D->isOrdered() && "Expected an output, flow or anti dep.");
        LLVM_DEBUG(StringRef DepType =
                       D->isFlow() ? "flow" : D->isAnti() ? "anti" : "output";
                   dbgs() << "Found " << DepType
                          << " dependency between Src and Dst\n"
                          << " Src:" << *Src << "\n Dst:" << *Dst << '\n');
        unsigned Levels = D->getLevels();
        char Direction;
        for (unsigned II = 1; II <= Levels; ++II) {
          const SCEV *Distance = D->getDistance(II);
          const SCEVConstant *SCEVConst =
              dyn_cast_or_null<SCEVConstant>(Distance);
          if (SCEVConst) {
            const ConstantInt *CI = SCEVConst->getValue();
            if (CI->isNegative())
              Direction = '<';
            else if (CI->isZero())
              Direction = '=';
            else
              Direction = '>';
            Dep.push_back(Direction);
          } else if (D->isScalar(II)) {
            Direction = 'S';
            Dep.push_back(Direction);
          } else {
            unsigned Dir = D->getDirection(II);
            if (Dir == Dependence::DVEntry::LT ||
                Dir == Dependence::DVEntry::LE)
              Direction = '<';
            else if (Dir == Dependence::DVEntry::GT ||
                     Dir == Dependence::DVEntry::GE)
              Direction = '>';
            else if (Dir == Dependence::DVEntry::EQ)
              Direction = '=';
            else
              Direction = '*';
            Dep.push_back(Direction);
          }
        }
        while (Dep.size() != Level) {
          Dep.push_back('I');
        }

        DepMatrix.push_back(Dep);
        if (DepMatrix.size() > MaxMemInstrCount) {
          LLVM_DEBUG(dbgs() << "Cannot handle more than " << MaxMemInstrCount
                            << " dependencies inside loop\n");
          return false;
        }
      }
    }
  }

  return true;
}

// A loop is moved from index 'from' to an index 'to'. Update the Dependence
// matrix by exchanging the two columns.
static void interChangeDependencies(CharMatrix &DepMatrix, unsigned FromIndx,
                                    unsigned ToIndx) {
  for (unsigned I = 0, E = DepMatrix.size(); I < E; ++I)
    std::swap(DepMatrix[I][ToIndx], DepMatrix[I][FromIndx]);
}

// Checks if outermost non '=','S'or'I' dependence in the dependence matrix is
// '>'
static bool isOuterMostDepPositive(CharMatrix &DepMatrix, unsigned Row,
                                   unsigned Column) {
  for (unsigned i = 0; i <= Column; ++i) {
    if (DepMatrix[Row][i] == '<')
      return false;
    if (DepMatrix[Row][i] == '>')
      return true;
  }
  // All dependencies were '=','S' or 'I'
  return false;
}

// Checks if no dependence exist in the dependency matrix in Row before Column.
static bool containsNoDependence(CharMatrix &DepMatrix, unsigned Row,
                                 unsigned Column) {
  for (unsigned i = 0; i < Column; ++i) {
    if (DepMatrix[Row][i] != '=' && DepMatrix[Row][i] != 'S' &&
        DepMatrix[Row][i] != 'I')
      return false;
  }
  return true;
}

static bool validDepInterchange(CharMatrix &DepMatrix, unsigned Row,
                                unsigned OuterLoopId, char InnerDep,
                                char OuterDep) {
  if (isOuterMostDepPositive(DepMatrix, Row, OuterLoopId))
    return false;

  if (InnerDep == OuterDep)
    return true;

  // It is legal to interchange if and only if after interchange no row has a
  // '>' direction as the leftmost non-'='.

  if (InnerDep == '=' || InnerDep == 'S' || InnerDep == 'I')
    return true;

  if (InnerDep == '<')
    return true;

  if (InnerDep == '>') {
    // If OuterLoopId represents outermost loop then interchanging will make the
    // 1st dependency as '>'
    if (OuterLoopId == 0)
      return false;

    // If all dependencies before OuterloopId are '=','S'or 'I'. Then
    // interchanging will result in this row having an outermost non '='
    // dependency of '>'
    if (!containsNoDependence(DepMatrix, Row, OuterLoopId))
      return true;
  }

  return false;
}

// Checks if it is legal to interchange 2 loops.
// [Theorem] A permutation of the loops in a perfect nest is legal if and only
// if the direction matrix, after the same permutation is applied to its
// columns, has no ">" direction as the leftmost non-"=" direction in any row.
static bool isLegalToInterChangeLoops(CharMatrix &DepMatrix,
                                      unsigned InnerLoopId,
                                      unsigned OuterLoopId) {
  unsigned NumRows = DepMatrix.size();
  // For each row check if it is valid to interchange.
  for (unsigned Row = 0; Row < NumRows; ++Row) {
    char InnerDep = DepMatrix[Row][InnerLoopId];
    char OuterDep = DepMatrix[Row][OuterLoopId];
    if (InnerDep == '*' || OuterDep == '*')
      return false;
    if (!validDepInterchange(DepMatrix, Row, OuterLoopId, InnerDep, OuterDep))
      return false;
  }
  return true;
}

static LoopVector populateWorklist(Loop &L) {
  LLVM_DEBUG(dbgs() << "Calling populateWorklist on Func: "
                    << L.getHeader()->getParent()->getName() << " Loop: %"
                    << L.getHeader()->getName() << '\n');
  LoopVector LoopList;
  Loop *CurrentLoop = &L;
  const std::vector<Loop *> *Vec = &CurrentLoop->getSubLoops();
  while (!Vec->empty()) {
    // The current loop has multiple subloops in it hence it is not tightly
    // nested.
    // Discard all loops above it added into Worklist.
    if (Vec->size() != 1)
      return {};

    LoopList.push_back(CurrentLoop);
    CurrentLoop = Vec->front();
    Vec = &CurrentLoop->getSubLoops();
  }
  LoopList.push_back(CurrentLoop);
  return LoopList;
}

namespace {

/// LoopInterchangeLegality checks if it is legal to interchange the loop.
class LoopInterchangeLegality {
public:
  LoopInterchangeLegality(Loop *Outer, Loop *Inner, ScalarEvolution *SE,
                          OptimizationRemarkEmitter *ORE)
      : OuterLoop(Outer), InnerLoop(Inner), SE(SE), ORE(ORE) {}

  /// Check if the loops can be interchanged.
  bool canInterchangeLoops(unsigned InnerLoopId, unsigned OuterLoopId,
                           CharMatrix &DepMatrix);

  /// Discover induction PHIs in the header of \p L. Induction
  /// PHIs are added to \p Inductions.
  bool findInductions(Loop *L, SmallVectorImpl<PHINode *> &Inductions);

  /// Check if the loop structure is understood. We do not handle triangular
  /// loops for now.
  bool isLoopStructureUnderstood();

  bool currentLimitations();

  const SmallPtrSetImpl<PHINode *> &getOuterInnerReductions() const {
    return OuterInnerReductions;
  }

  const SmallVectorImpl<PHINode *> &getInnerLoopInductions() const {
    return InnerLoopInductions;
  }

private:
  bool tightlyNested(Loop *Outer, Loop *Inner);
  bool containsUnsafeInstructions(BasicBlock *BB);

  /// Discover induction and reduction PHIs in the header of \p L. Induction
  /// PHIs are added to \p Inductions, reductions are added to
  /// OuterInnerReductions. When the outer loop is passed, the inner loop needs
  /// to be passed as \p InnerLoop.
  bool findInductionAndReductions(Loop *L,
                                  SmallVector<PHINode *, 8> &Inductions,
                                  Loop *InnerLoop);

  Loop *OuterLoop;
  Loop *InnerLoop;

  ScalarEvolution *SE;

  /// Interface to emit optimization remarks.
  OptimizationRemarkEmitter *ORE;

  /// Set of reduction PHIs taking part of a reduction across the inner and
  /// outer loop.
  SmallPtrSet<PHINode *, 4> OuterInnerReductions;

  /// Set of inner loop induction PHIs
  SmallVector<PHINode *, 8> InnerLoopInductions;
};

/// LoopInterchangeProfitability checks if it is profitable to interchange the
/// loop.
class LoopInterchangeProfitability {
public:
  LoopInterchangeProfitability(Loop *Outer, Loop *Inner, ScalarEvolution *SE,
                               OptimizationRemarkEmitter *ORE)
      : OuterLoop(Outer), InnerLoop(Inner), SE(SE), ORE(ORE) {}

  /// Check if the loop interchange is profitable.
  bool isProfitable(unsigned InnerLoopId, unsigned OuterLoopId,
                    CharMatrix &DepMatrix);

private:
  int getInstrOrderCost();

  Loop *OuterLoop;
  Loop *InnerLoop;

  /// Scev analysis.
  ScalarEvolution *SE;

  /// Interface to emit optimization remarks.
  OptimizationRemarkEmitter *ORE;
};

/// LoopInterchangeTransform interchanges the loop.
class LoopInterchangeTransform {
public:
  LoopInterchangeTransform(Loop *Outer, Loop *Inner, ScalarEvolution *SE,
                           LoopInfo *LI, DominatorTree *DT,
                           const LoopInterchangeLegality &LIL)
      : OuterLoop(Outer), InnerLoop(Inner), SE(SE), LI(LI), DT(DT), LIL(LIL) {}

  /// Interchange OuterLoop and InnerLoop.
  bool transform();
  void restructureLoops(Loop *NewInner, Loop *NewOuter,
                        BasicBlock *OrigInnerPreHeader,
                        BasicBlock *OrigOuterPreHeader);
  void removeChildLoop(Loop *OuterLoop, Loop *InnerLoop);

private:
  bool adjustLoopLinks();
  bool adjustLoopBranches();

  Loop *OuterLoop;
  Loop *InnerLoop;

  /// Scev analysis.
  ScalarEvolution *SE;

  LoopInfo *LI;
  DominatorTree *DT;

  const LoopInterchangeLegality &LIL;
};

struct LoopInterchange {
  ScalarEvolution *SE = nullptr;
  LoopInfo *LI = nullptr;
  DependenceInfo *DI = nullptr;
  DominatorTree *DT = nullptr;

  /// Interface to emit optimization remarks.
  OptimizationRemarkEmitter *ORE;

  LoopInterchange(ScalarEvolution *SE, LoopInfo *LI, DependenceInfo *DI,
                  DominatorTree *DT, OptimizationRemarkEmitter *ORE)
      : SE(SE), LI(LI), DI(DI), DT(DT), ORE(ORE) {}

  bool run(Loop *L) {
    if (L->getParentLoop())
      return false;

    return processLoopList(populateWorklist(*L));
  }

  bool run(LoopNest &LN) {
    const auto &LoopList = LN.getLoops();
    for (unsigned I = 1; I < LoopList.size(); ++I)
      if (LoopList[I]->getParentLoop() != LoopList[I - 1])
        return false;
    return processLoopList(LoopList);
  }

  bool isComputableLoopNest(ArrayRef<Loop *> LoopList) {
    for (Loop *L : LoopList) {
      const SCEV *ExitCountOuter = SE->getBackedgeTakenCount(L);
      if (isa<SCEVCouldNotCompute>(ExitCountOuter)) {
        LLVM_DEBUG(dbgs() << "Couldn't compute backedge count\n");
        return false;
      }
      if (L->getNumBackEdges() != 1) {
        LLVM_DEBUG(dbgs() << "NumBackEdges is not equal to 1\n");
        return false;
      }
      if (!L->getExitingBlock()) {
        LLVM_DEBUG(dbgs() << "Loop doesn't have unique exit block\n");
        return false;
      }
    }
    return true;
  }

  unsigned selectLoopForInterchange(ArrayRef<Loop *> LoopList) {
    // TODO: Add a better heuristic to select the loop to be interchanged based
    // on the dependence matrix. Currently we select the innermost loop.
    return LoopList.size() - 1;
  }

  bool processLoopList(ArrayRef<Loop *> LoopList) {
    bool Changed = false;
    unsigned LoopNestDepth = LoopList.size();
    if (LoopNestDepth < 2) {
      LLVM_DEBUG(dbgs() << "Loop doesn't contain minimum nesting level.\n");
      return false;
    }
    if (LoopNestDepth > MaxLoopNestDepth) {
      LLVM_DEBUG(dbgs() << "Cannot handle loops of depth greater than "
                        << MaxLoopNestDepth << "\n");
      return false;
    }
    if (!isComputableLoopNest(LoopList)) {
      LLVM_DEBUG(dbgs() << "Not valid loop candidate for interchange\n");
      return false;
    }

    LLVM_DEBUG(dbgs() << "Processing LoopList of size = " << LoopNestDepth
                      << "\n");

    CharMatrix DependencyMatrix;
    Loop *OuterMostLoop = *(LoopList.begin());
    if (!populateDependencyMatrix(DependencyMatrix, LoopNestDepth,
                                  OuterMostLoop, DI)) {
      LLVM_DEBUG(dbgs() << "Populating dependency matrix failed\n");
      return false;
    }
#ifdef DUMP_DEP_MATRICIES
    LLVM_DEBUG(dbgs() << "Dependence before interchange\n");
    printDepMatrix(DependencyMatrix);
#endif

    // Get the Outermost loop exit.
    BasicBlock *LoopNestExit = OuterMostLoop->getExitBlock();
    if (!LoopNestExit) {
      LLVM_DEBUG(dbgs() << "OuterMostLoop needs an unique exit block");
      return false;
    }

    unsigned SelecLoopId = selectLoopForInterchange(LoopList);
    // Move the selected loop outwards to the best possible position.
    Loop *LoopToBeInterchanged = LoopList[SelecLoopId];
    for (unsigned i = SelecLoopId; i > 0; i--) {
      bool Interchanged = processLoop(LoopToBeInterchanged, LoopList[i - 1], i,
                                      i - 1, DependencyMatrix);
      if (!Interchanged)
        return Changed;
      // Update the DependencyMatrix
      interChangeDependencies(DependencyMatrix, i, i - 1);
#ifdef DUMP_DEP_MATRICIES
      LLVM_DEBUG(dbgs() << "Dependence after interchange\n");
      printDepMatrix(DependencyMatrix);
#endif
      Changed |= Interchanged;
    }
    return Changed;
  }

  bool processLoop(Loop *InnerLoop, Loop *OuterLoop, unsigned InnerLoopId,
                   unsigned OuterLoopId,
                   std::vector<std::vector<char>> &DependencyMatrix) {
    LLVM_DEBUG(dbgs() << "Processing InnerLoopId = " << InnerLoopId
                      << " and OuterLoopId = " << OuterLoopId << "\n");
    LoopInterchangeLegality LIL(OuterLoop, InnerLoop, SE, ORE);
    if (!LIL.canInterchangeLoops(InnerLoopId, OuterLoopId, DependencyMatrix)) {
      LLVM_DEBUG(dbgs() << "Not interchanging loops. Cannot prove legality.\n");
      return false;
    }
    LLVM_DEBUG(dbgs() << "Loops are legal to interchange\n");
    LoopInterchangeProfitability LIP(OuterLoop, InnerLoop, SE, ORE);
    if (!LIP.isProfitable(InnerLoopId, OuterLoopId, DependencyMatrix)) {
      LLVM_DEBUG(dbgs() << "Interchanging loops not profitable.\n");
      return false;
    }

    ORE->emit([&]() {
      return OptimizationRemark(DEBUG_TYPE, "Interchanged",
                                InnerLoop->getStartLoc(),
                                InnerLoop->getHeader())
             << "Loop interchanged with enclosing loop.";
    });

    LoopInterchangeTransform LIT(OuterLoop, InnerLoop, SE, LI, DT, LIL);
    LIT.transform();
    LLVM_DEBUG(dbgs() << "Loops interchanged.\n");
    LoopsInterchanged++;

    assert(InnerLoop->isLCSSAForm(*DT) &&
           "Inner loop not left in LCSSA form after loop interchange!");
    assert(OuterLoop->isLCSSAForm(*DT) &&
           "Outer loop not left in LCSSA form after loop interchange!");

    return true;
  }
};

} // end anonymous namespace

bool LoopInterchangeLegality::containsUnsafeInstructions(BasicBlock *BB) {
  return any_of(*BB, [](const Instruction &I) {
    return I.mayHaveSideEffects() || I.mayReadFromMemory();
  });
}

bool LoopInterchangeLegality::tightlyNested(Loop *OuterLoop, Loop *InnerLoop) {
  BasicBlock *OuterLoopHeader = OuterLoop->getHeader();
  BasicBlock *InnerLoopPreHeader = InnerLoop->getLoopPreheader();
  BasicBlock *OuterLoopLatch = OuterLoop->getLoopLatch();

  LLVM_DEBUG(dbgs() << "Checking if loops are tightly nested\n");

  // A perfectly nested loop will not have any branch in between the outer and
  // inner block i.e. outer header will branch to either inner preheader and
  // outerloop latch.
  BranchInst *OuterLoopHeaderBI =
      dyn_cast<BranchInst>(OuterLoopHeader->getTerminator());
  if (!OuterLoopHeaderBI)
    return false;

  for (BasicBlock *Succ : successors(OuterLoopHeaderBI))
    if (Succ != InnerLoopPreHeader && Succ != InnerLoop->getHeader() &&
        Succ != OuterLoopLatch)
      return false;

  LLVM_DEBUG(dbgs() << "Checking instructions in Loop header and Loop latch\n");
  // We do not have any basic block in between now make sure the outer header
  // and outer loop latch doesn't contain any unsafe instructions.
  if (containsUnsafeInstructions(OuterLoopHeader) ||
      containsUnsafeInstructions(OuterLoopLatch))
    return false;

  // Also make sure the inner loop preheader does not contain any unsafe
  // instructions. Note that all instructions in the preheader will be moved to
  // the outer loop header when interchanging.
  if (InnerLoopPreHeader != OuterLoopHeader &&
      containsUnsafeInstructions(InnerLoopPreHeader))
    return false;

  BasicBlock *InnerLoopExit = InnerLoop->getExitBlock();
  // Ensure the inner loop exit block flows to the outer loop latch possibly
  // through empty blocks.
  const BasicBlock &SuccInner =
      LoopNest::skipEmptyBlockUntil(InnerLoopExit, OuterLoopLatch);
  if (&SuccInner != OuterLoopLatch) {
    LLVM_DEBUG(dbgs() << "Inner loop exit block " << *InnerLoopExit
                      << " does not lead to the outer loop latch.\n";);
    return false;
  }
  // The inner loop exit block does flow to the outer loop latch and not some
  // other BBs, now make sure it contains safe instructions, since it will be
  // moved into the (new) inner loop after interchange.
  if (containsUnsafeInstructions(InnerLoopExit))
    return false;

  LLVM_DEBUG(dbgs() << "Loops are perfectly nested\n");
  // We have a perfect loop nest.
  return true;
}

bool LoopInterchangeLegality::isLoopStructureUnderstood() {
  BasicBlock *InnerLoopPreheader = InnerLoop->getLoopPreheader();
  for (PHINode *InnerInduction : InnerLoopInductions) {
    unsigned Num = InnerInduction->getNumOperands();
    for (unsigned i = 0; i < Num; ++i) {
      Value *Val = InnerInduction->getOperand(i);
      if (isa<Constant>(Val))
        continue;
      Instruction *I = dyn_cast<Instruction>(Val);
      if (!I)
        return false;
      // TODO: Handle triangular loops.
      // e.g. for(int i=0;i<N;i++)
      //        for(int j=i;j<N;j++)
      unsigned IncomBlockIndx = PHINode::getIncomingValueNumForOperand(i);
      if (InnerInduction->getIncomingBlock(IncomBlockIndx) ==
              InnerLoopPreheader &&
          !OuterLoop->isLoopInvariant(I)) {
        return false;
      }
    }
  }

  // TODO: Handle triangular loops of another form.
  // e.g. for(int i=0;i<N;i++)
  //        for(int j=0;j<i;j++)
  // or,
  //      for(int i=0;i<N;i++)
  //        for(int j=0;j*i<N;j++)
  BasicBlock *InnerLoopLatch = InnerLoop->getLoopLatch();
  BranchInst *InnerLoopLatchBI =
      dyn_cast<BranchInst>(InnerLoopLatch->getTerminator());
  if (!InnerLoopLatchBI->isConditional())
    return false;
  if (CmpInst *InnerLoopCmp =
          dyn_cast<CmpInst>(InnerLoopLatchBI->getCondition())) {
    Value *Op0 = InnerLoopCmp->getOperand(0);
    Value *Op1 = InnerLoopCmp->getOperand(1);

    // LHS and RHS of the inner loop exit condition, e.g.,
    // in "for(int j=0;j<i;j++)", LHS is j and RHS is i.
    Value *Left = nullptr;
    Value *Right = nullptr;

    // Check if V only involves inner loop induction variable.
    // Return true if V is InnerInduction, or a cast from
    // InnerInduction, or a binary operator that involves
    // InnerInduction and a constant.
    std::function<bool(Value *)> IsPathToInnerIndVar;
    IsPathToInnerIndVar = [this, &IsPathToInnerIndVar](const Value *V) -> bool {
      if (llvm::is_contained(InnerLoopInductions, V))
        return true;
      if (isa<Constant>(V))
        return true;
      const Instruction *I = dyn_cast<Instruction>(V);
      if (!I)
        return false;
      if (isa<CastInst>(I))
        return IsPathToInnerIndVar(I->getOperand(0));
      if (isa<BinaryOperator>(I))
        return IsPathToInnerIndVar(I->getOperand(0)) &&
               IsPathToInnerIndVar(I->getOperand(1));
      return false;
    };

    // In case of multiple inner loop indvars, it is okay if LHS and RHS
    // are both inner indvar related variables.
    if (IsPathToInnerIndVar(Op0) && IsPathToInnerIndVar(Op1))
      return true;

    // Otherwise we check if the cmp instruction compares an inner indvar
    // related variable (Left) with a outer loop invariant (Right).
    if (IsPathToInnerIndVar(Op0) && !isa<Constant>(Op0)) {
      Left = Op0;
      Right = Op1;
    } else if (IsPathToInnerIndVar(Op1) && !isa<Constant>(Op1)) {
      Left = Op1;
      Right = Op0;
    }

    if (Left == nullptr)
      return false;

    const SCEV *S = SE->getSCEV(Right);
    if (!SE->isLoopInvariant(S, OuterLoop))
      return false;
  }

  return true;
}

// If SV is a LCSSA PHI node with a single incoming value, return the incoming
// value.
static Value *followLCSSA(Value *SV) {
  PHINode *PHI = dyn_cast<PHINode>(SV);
  if (!PHI)
    return SV;

  if (PHI->getNumIncomingValues() != 1)
    return SV;
  return followLCSSA(PHI->getIncomingValue(0));
}

// Check V's users to see if it is involved in a reduction in L.
static PHINode *findInnerReductionPhi(Loop *L, Value *V) {
  // Reduction variables cannot be constants.
  if (isa<Constant>(V))
    return nullptr;

  for (Value *User : V->users()) {
    if (PHINode *PHI = dyn_cast<PHINode>(User)) {
      if (PHI->getNumIncomingValues() == 1)
        continue;
      RecurrenceDescriptor RD;
      if (RecurrenceDescriptor::isReductionPHI(PHI, L, RD))
        return PHI;
      return nullptr;
    }
  }

  return nullptr;
}

bool LoopInterchangeLegality::findInductionAndReductions(
    Loop *L, SmallVector<PHINode *, 8> &Inductions, Loop *InnerLoop) {
  if (!L->getLoopLatch() || !L->getLoopPredecessor())
    return false;
  for (PHINode &PHI : L->getHeader()->phis()) {
    RecurrenceDescriptor RD;
    InductionDescriptor ID;
    if (InductionDescriptor::isInductionPHI(&PHI, L, SE, ID))
      Inductions.push_back(&PHI);
    else {
      // PHIs in inner loops need to be part of a reduction in the outer loop,
      // discovered when checking the PHIs of the outer loop earlier.
      if (!InnerLoop) {
        if (!OuterInnerReductions.count(&PHI)) {
          LLVM_DEBUG(dbgs() << "Inner loop PHI is not part of reductions "
                               "across the outer loop.\n");
          return false;
        }
      } else {
        assert(PHI.getNumIncomingValues() == 2 &&
               "Phis in loop header should have exactly 2 incoming values");
        // Check if we have a PHI node in the outer loop that has a reduction
        // result from the inner loop as an incoming value.
        Value *V = followLCSSA(PHI.getIncomingValueForBlock(L->getLoopLatch()));
        PHINode *InnerRedPhi = findInnerReductionPhi(InnerLoop, V);
        if (!InnerRedPhi ||
            !llvm::is_contained(InnerRedPhi->incoming_values(), &PHI)) {
          LLVM_DEBUG(
              dbgs()
              << "Failed to recognize PHI as an induction or reduction.\n");
          return false;
        }
        OuterInnerReductions.insert(&PHI);
        OuterInnerReductions.insert(InnerRedPhi);
      }
    }
  }
  return true;
}

// This function indicates the current limitations in the transform as a result
// of which we do not proceed.
bool LoopInterchangeLegality::currentLimitations() {
  BasicBlock *InnerLoopLatch = InnerLoop->getLoopLatch();

  // transform currently expects the loop latches to also be the exiting
  // blocks.
  if (InnerLoop->getExitingBlock() != InnerLoopLatch ||
      OuterLoop->getExitingBlock() != OuterLoop->getLoopLatch() ||
      !isa<BranchInst>(InnerLoopLatch->getTerminator()) ||
      !isa<BranchInst>(OuterLoop->getLoopLatch()->getTerminator())) {
    LLVM_DEBUG(
        dbgs() << "Loops where the latch is not the exiting block are not"
               << " supported currently.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "ExitingNotLatch",
                                      OuterLoop->getStartLoc(),
                                      OuterLoop->getHeader())
             << "Loops where the latch is not the exiting block cannot be"
                " interchange currently.";
    });
    return true;
  }

  SmallVector<PHINode *, 8> Inductions;
  if (!findInductionAndReductions(OuterLoop, Inductions, InnerLoop)) {
    LLVM_DEBUG(
        dbgs() << "Only outer loops with induction or reduction PHI nodes "
               << "are supported currently.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedPHIOuter",
                                      OuterLoop->getStartLoc(),
                                      OuterLoop->getHeader())
             << "Only outer loops with induction or reduction PHI nodes can be"
                " interchanged currently.";
    });
    return true;
  }

  Inductions.clear();
  if (!findInductionAndReductions(InnerLoop, Inductions, nullptr)) {
    LLVM_DEBUG(
        dbgs() << "Only inner loops with induction or reduction PHI nodes "
               << "are supported currently.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedPHIInner",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Only inner loops with induction or reduction PHI nodes can be"
                " interchange currently.";
    });
    return true;
  }

  // TODO: Triangular loops are not handled for now.
  if (!isLoopStructureUnderstood()) {
    LLVM_DEBUG(dbgs() << "Loop structure not understood by pass\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedStructureInner",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Inner loop structure not understood currently.";
    });
    return true;
  }

  return false;
}

bool LoopInterchangeLegality::findInductions(
    Loop *L, SmallVectorImpl<PHINode *> &Inductions) {
  for (PHINode &PHI : L->getHeader()->phis()) {
    InductionDescriptor ID;
    if (InductionDescriptor::isInductionPHI(&PHI, L, SE, ID))
      Inductions.push_back(&PHI);
  }
  return !Inductions.empty();
}

// We currently only support LCSSA PHI nodes in the inner loop exit, if their
// users are either reduction PHIs or PHIs outside the outer loop (which means
// the we are only interested in the final value after the loop).
static bool
areInnerLoopExitPHIsSupported(Loop *InnerL, Loop *OuterL,
                              SmallPtrSetImpl<PHINode *> &Reductions) {
  BasicBlock *InnerExit = OuterL->getUniqueExitBlock();
  for (PHINode &PHI : InnerExit->phis()) {
    // Reduction lcssa phi will have only 1 incoming block that from loop latch.
    if (PHI.getNumIncomingValues() > 1)
      return false;
    if (any_of(PHI.users(), [&Reductions, OuterL](User *U) {
          PHINode *PN = dyn_cast<PHINode>(U);
          return !PN ||
                 (!Reductions.count(PN) && OuterL->contains(PN->getParent()));
        })) {
      return false;
    }
  }
  return true;
}

// We currently support LCSSA PHI nodes in the outer loop exit, if their
// incoming values do not come from the outer loop latch or if the
// outer loop latch has a single predecessor. In that case, the value will
// be available if both the inner and outer loop conditions are true, which
// will still be true after interchanging. If we have multiple predecessor,
// that may not be the case, e.g. because the outer loop latch may be executed
// if the inner loop is not executed.
static bool areOuterLoopExitPHIsSupported(Loop *OuterLoop, Loop *InnerLoop) {
  BasicBlock *LoopNestExit = OuterLoop->getUniqueExitBlock();
  for (PHINode &PHI : LoopNestExit->phis()) {
    //  FIXME: We currently are not able to detect floating point reductions
    //         and have to use floating point PHIs as a proxy to prevent
    //         interchanging in the presence of floating point reductions.
    if (PHI.getType()->isFloatingPointTy())
      return false;
    for (unsigned i = 0; i < PHI.getNumIncomingValues(); i++) {
     Instruction *IncomingI = dyn_cast<Instruction>(PHI.getIncomingValue(i));
     if (!IncomingI || IncomingI->getParent() != OuterLoop->getLoopLatch())
       continue;

     // The incoming value is defined in the outer loop latch. Currently we
     // only support that in case the outer loop latch has a single predecessor.
     // This guarantees that the outer loop latch is executed if and only if
     // the inner loop is executed (because tightlyNested() guarantees that the
     // outer loop header only branches to the inner loop or the outer loop
     // latch).
     // FIXME: We could weaken this logic and allow multiple predecessors,
     //        if the values are produced outside the loop latch. We would need
     //        additional logic to update the PHI nodes in the exit block as
     //        well.
     if (OuterLoop->getLoopLatch()->getUniquePredecessor() == nullptr)
       return false;
    }
  }
  return true;
}

// In case of multi-level nested loops, it may occur that lcssa phis exist in
// the latch of InnerLoop, i.e., when defs of the incoming values are further
// inside the loopnest. Sometimes those incoming values are not available
// after interchange, since the original inner latch will become the new outer
// latch which may have predecessor paths that do not include those incoming
// values.
// TODO: Handle transformation of lcssa phis in the InnerLoop latch in case of
// multi-level loop nests.
static bool areInnerLoopLatchPHIsSupported(Loop *OuterLoop, Loop *InnerLoop) {
  if (InnerLoop->getSubLoops().empty())
    return true;
  // If the original outer latch has only one predecessor, then values defined
  // further inside the looploop, e.g., in the innermost loop, will be available
  // at the new outer latch after interchange.
  if (OuterLoop->getLoopLatch()->getUniquePredecessor() != nullptr)
    return true;

  // The outer latch has more than one predecessors, i.e., the inner
  // exit and the inner header.
  // PHI nodes in the inner latch are lcssa phis where the incoming values
  // are defined further inside the loopnest. Check if those phis are used
  // in the original inner latch. If that is the case then bail out since
  // those incoming values may not be available at the new outer latch.
  BasicBlock *InnerLoopLatch = InnerLoop->getLoopLatch();
  for (PHINode &PHI : InnerLoopLatch->phis()) {
    for (auto *U : PHI.users()) {
      Instruction *UI = cast<Instruction>(U);
      if (InnerLoopLatch == UI->getParent())
        return false;
    }
  }
  return true;
}

bool LoopInterchangeLegality::canInterchangeLoops(unsigned InnerLoopId,
                                                  unsigned OuterLoopId,
                                                  CharMatrix &DepMatrix) {
  if (!isLegalToInterChangeLoops(DepMatrix, InnerLoopId, OuterLoopId)) {
    LLVM_DEBUG(dbgs() << "Failed interchange InnerLoopId = " << InnerLoopId
                      << " and OuterLoopId = " << OuterLoopId
                      << " due to dependence\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "Dependence",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Cannot interchange loops due to dependences.";
    });
    return false;
  }
  // Check if outer and inner loop contain legal instructions only.
  for (auto *BB : OuterLoop->blocks())
    for (Instruction &I : BB->instructionsWithoutDebug())
      if (CallInst *CI = dyn_cast<CallInst>(&I)) {
        // readnone functions do not prevent interchanging.
        if (CI->onlyWritesMemory())
          continue;
        LLVM_DEBUG(
            dbgs() << "Loops with call instructions cannot be interchanged "
                   << "safely.");
        ORE->emit([&]() {
          return OptimizationRemarkMissed(DEBUG_TYPE, "CallInst",
                                          CI->getDebugLoc(),
                                          CI->getParent())
                 << "Cannot interchange loops due to call instruction.";
        });

        return false;
      }

  if (!findInductions(InnerLoop, InnerLoopInductions)) {
    LLVM_DEBUG(dbgs() << "Cound not find inner loop induction variables.\n");
    return false;
  }

  if (!areInnerLoopLatchPHIsSupported(OuterLoop, InnerLoop)) {
    LLVM_DEBUG(dbgs() << "Found unsupported PHI nodes in inner loop latch.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedInnerLatchPHI",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Cannot interchange loops because unsupported PHI nodes found "
                "in inner loop latch.";
    });
    return false;
  }

  // TODO: The loops could not be interchanged due to current limitations in the
  // transform module.
  if (currentLimitations()) {
    LLVM_DEBUG(dbgs() << "Not legal because of current transform limitation\n");
    return false;
  }

  // Check if the loops are tightly nested.
  if (!tightlyNested(OuterLoop, InnerLoop)) {
    LLVM_DEBUG(dbgs() << "Loops not tightly nested\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "NotTightlyNested",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Cannot interchange loops because they are not tightly "
                "nested.";
    });
    return false;
  }

  if (!areInnerLoopExitPHIsSupported(OuterLoop, InnerLoop,
                                     OuterInnerReductions)) {
    LLVM_DEBUG(dbgs() << "Found unsupported PHI nodes in inner loop exit.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedExitPHI",
                                      InnerLoop->getStartLoc(),
                                      InnerLoop->getHeader())
             << "Found unsupported PHI node in loop exit.";
    });
    return false;
  }

  if (!areOuterLoopExitPHIsSupported(OuterLoop, InnerLoop)) {
    LLVM_DEBUG(dbgs() << "Found unsupported PHI nodes in outer loop exit.\n");
    ORE->emit([&]() {
      return OptimizationRemarkMissed(DEBUG_TYPE, "UnsupportedExitPHI",
                                      OuterLoop->getStartLoc(),
                                      OuterLoop->getHeader())
             << "Found unsupported PHI node in loop exit.";
    });
    return false;
  }

  return true;
}

int LoopInterchangeProfitability::getInstrOrderCost() {
  unsigned GoodOrder, BadOrder;
  BadOrder = GoodOrder = 0;
  for (BasicBlock *BB : InnerLoop->blocks()) {
    for (Instruction &Ins : *BB) {
      if (const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(&Ins)) {
        unsigned NumOp = GEP->getNumOperands();
        bool FoundInnerInduction = false;
        bool FoundOuterInduction = false;
        for (unsigned i = 0; i < NumOp; ++i) {
          // Skip operands that are not SCEV-able.
          if (!SE->isSCEVable(GEP->getOperand(i)->getType()))
            continue;

          const SCEV *OperandVal = SE->getSCEV(GEP->getOperand(i));
          const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(OperandVal);
          if (!AR)
            continue;

          // If we find the inner induction after an outer induction e.g.
          // for(int i=0;i<N;i++)
          //   for(int j=0;j<N;j++)
          //     A[i][j] = A[i-1][j-1]+k;
          // then it is a good order.
          if (AR->getLoop() == InnerLoop) {
            // We found an InnerLoop induction after OuterLoop induction. It is
            // a good order.
            FoundInnerInduction = true;
            if (FoundOuterInduction) {
              GoodOrder++;
              break;
            }
          }
          // If we find the outer induction after an inner induction e.g.
          // for(int i=0;i<N;i++)
          //   for(int j=0;j<N;j++)
          //     A[j][i] = A[j-1][i-1]+k;
          // then it is a bad order.
          if (AR->getLoop() == OuterLoop) {
            // We found an OuterLoop induction after InnerLoop induction. It is
            // a bad order.
            FoundOuterInduction = true;
            if (FoundInnerInduction) {
              BadOrder++;
              break;
            }
          }
        }
      }
    }
  }
  return GoodOrder - BadOrder;
}

static bool isProfitableForVectorization(unsigned InnerLoopId,
                                         unsigned OuterLoopId,
                                         CharMatrix &DepMatrix) {
  // TODO: Improve this heuristic to catch more cases.
  // If the inner loop is loop independent or doesn't carry any dependency it is
  // profitable to move this to outer position.
  for (auto &Row : DepMatrix) {
    if (Row[InnerLoopId] != 'S' && Row[InnerLoopId] != 'I')
      return false;
    // TODO: We need to improve this heuristic.
    if (Row[OuterLoopId] != '=')
      return false;
  }
  // If outer loop has dependence and inner loop is loop independent then it is
  // profitable to interchange to enable parallelism.
  // If there are no dependences, interchanging will not improve anything.
  return !DepMatrix.empty();
}

bool LoopInterchangeProfitability::isProfitable(unsigned InnerLoopId,
                                                unsigned OuterLoopId,
                                                CharMatrix &DepMatrix) {
  // TODO: Add better profitability checks.
  // e.g
  // 1) Construct dependency matrix and move the one with no loop carried dep
  //    inside to enable vectorization.

  // This is rough cost estimation algorithm. It counts the good and bad order
  // of induction variables in the instruction and allows reordering if number
  // of bad orders is more than good.
  int Cost = getInstrOrderCost();
  LLVM_DEBUG(dbgs() << "Cost = " << Cost << "\n");
  if (Cost < -LoopInterchangeCostThreshold)
    return true;

  // It is not profitable as per current cache profitability model. But check if
  // we can move this loop outside to improve parallelism.
  if (isProfitableForVectorization(InnerLoopId, OuterLoopId, DepMatrix))
    return true;

  ORE->emit([&]() {
    return OptimizationRemarkMissed(DEBUG_TYPE, "InterchangeNotProfitable",
                                    InnerLoop->getStartLoc(),
                                    InnerLoop->getHeader())
           << "Interchanging loops is too costly (cost="
           << ore::NV("Cost", Cost) << ", threshold="
           << ore::NV("Threshold", LoopInterchangeCostThreshold)
           << ") and it does not improve parallelism.";
  });
  return false;
}

void LoopInterchangeTransform::removeChildLoop(Loop *OuterLoop,
                                               Loop *InnerLoop) {
  for (Loop *L : *OuterLoop)
    if (L == InnerLoop) {
      OuterLoop->removeChildLoop(L);
      return;
    }
  llvm_unreachable("Couldn't find loop");
}

/// Update LoopInfo, after interchanging. NewInner and NewOuter refer to the
/// new inner and outer loop after interchanging: NewInner is the original
/// outer loop and NewOuter is the original inner loop.
///
/// Before interchanging, we have the following structure
/// Outer preheader
//  Outer header
//    Inner preheader
//    Inner header
//      Inner body
//      Inner latch
//   outer bbs
//   Outer latch
//
// After interchanging:
// Inner preheader
// Inner header
//   Outer preheader
//   Outer header
//     Inner body
//     outer bbs
//     Outer latch
//   Inner latch
void LoopInterchangeTransform::restructureLoops(
    Loop *NewInner, Loop *NewOuter, BasicBlock *OrigInnerPreHeader,
    BasicBlock *OrigOuterPreHeader) {
  Loop *OuterLoopParent = OuterLoop->getParentLoop();
  // The original inner loop preheader moves from the new inner loop to
  // the parent loop, if there is one.
  NewInner->removeBlockFromLoop(OrigInnerPreHeader);
  LI->changeLoopFor(OrigInnerPreHeader, OuterLoopParent);

  // Switch the loop levels.
  if (OuterLoopParent) {
    // Remove the loop from its parent loop.
    removeChildLoop(OuterLoopParent, NewInner);
    removeChildLoop(NewInner, NewOuter);
    OuterLoopParent->addChildLoop(NewOuter);
  } else {
    removeChildLoop(NewInner, NewOuter);
    LI->changeTopLevelLoop(NewInner, NewOuter);
  }
  while (!NewOuter->isInnermost())
    NewInner->addChildLoop(NewOuter->removeChildLoop(NewOuter->begin()));
  NewOuter->addChildLoop(NewInner);

  // BBs from the original inner loop.
  SmallVector<BasicBlock *, 8> OrigInnerBBs(NewOuter->blocks());

  // Add BBs from the original outer loop to the original inner loop (excluding
  // BBs already in inner loop)
  for (BasicBlock *BB : NewInner->blocks())
    if (LI->getLoopFor(BB) == NewInner)
      NewOuter->addBlockEntry(BB);

  // Now remove inner loop header and latch from the new inner loop and move
  // other BBs (the loop body) to the new inner loop.
  BasicBlock *OuterHeader = NewOuter->getHeader();
  BasicBlock *OuterLatch = NewOuter->getLoopLatch();
  for (BasicBlock *BB : OrigInnerBBs) {
    // Nothing will change for BBs in child loops.
    if (LI->getLoopFor(BB) != NewOuter)
      continue;
    // Remove the new outer loop header and latch from the new inner loop.
    if (BB == OuterHeader || BB == OuterLatch)
      NewInner->removeBlockFromLoop(BB);
    else
      LI->changeLoopFor(BB, NewInner);
  }

  // The preheader of the original outer loop becomes part of the new
  // outer loop.
  NewOuter->addBlockEntry(OrigOuterPreHeader);
  LI->changeLoopFor(OrigOuterPreHeader, NewOuter);

  // Tell SE that we move the loops around.
  SE->forgetLoop(NewOuter);
  SE->forgetLoop(NewInner);
}

bool LoopInterchangeTransform::transform() {
  bool Transformed = false;

  if (InnerLoop->getSubLoops().empty()) {
    BasicBlock *InnerLoopPreHeader = InnerLoop->getLoopPreheader();
    LLVM_DEBUG(dbgs() << "Splitting the inner loop latch\n");
    auto &InductionPHIs = LIL.getInnerLoopInductions();
    if (InductionPHIs.empty()) {
      LLVM_DEBUG(dbgs() << "Failed to find the point to split loop latch \n");
      return false;
    }

    SmallVector<Instruction *, 8> InnerIndexVarList;
    for (PHINode *CurInductionPHI : InductionPHIs) {
      if (CurInductionPHI->getIncomingBlock(0) == InnerLoopPreHeader)
        InnerIndexVarList.push_back(
            dyn_cast<Instruction>(CurInductionPHI->getIncomingValue(1)));
      else
        InnerIndexVarList.push_back(
            dyn_cast<Instruction>(CurInductionPHI->getIncomingValue(0)));
    }

    // Create a new latch block for the inner loop. We split at the
    // current latch's terminator and then move the condition and all
    // operands that are not either loop-invariant or the induction PHI into the
    // new latch block.
    BasicBlock *NewLatch =
        SplitBlock(InnerLoop->getLoopLatch(),
                   InnerLoop->getLoopLatch()->getTerminator(), DT, LI);

    SmallSetVector<Instruction *, 4> WorkList;
    unsigned i = 0;
    auto MoveInstructions = [&i, &WorkList, this, &InductionPHIs, NewLatch]() {
      for (; i < WorkList.size(); i++) {
        // Duplicate instruction and move it the new latch. Update uses that
        // have been moved.
        Instruction *NewI = WorkList[i]->clone();
        NewI->insertBefore(NewLatch->getFirstNonPHI());
        assert(!NewI->mayHaveSideEffects() &&
               "Moving instructions with side-effects may change behavior of "
               "the loop nest!");
        for (Use &U : llvm::make_early_inc_range(WorkList[i]->uses())) {
          Instruction *UserI = cast<Instruction>(U.getUser());
          if (!InnerLoop->contains(UserI->getParent()) ||
              UserI->getParent() == NewLatch ||
              llvm::is_contained(InductionPHIs, UserI))
            U.set(NewI);
        }
        // Add operands of moved instruction to the worklist, except if they are
        // outside the inner loop or are the induction PHI.
        for (Value *Op : WorkList[i]->operands()) {
          Instruction *OpI = dyn_cast<Instruction>(Op);
          if (!OpI ||
              this->LI->getLoopFor(OpI->getParent()) != this->InnerLoop ||
              llvm::is_contained(InductionPHIs, OpI))
            continue;
          WorkList.insert(OpI);
        }
      }
    };

    // FIXME: Should we interchange when we have a constant condition?
    Instruction *CondI = dyn_cast<Instruction>(
        cast<BranchInst>(InnerLoop->getLoopLatch()->getTerminator())
            ->getCondition());
    if (CondI)
      WorkList.insert(CondI);
    MoveInstructions();
    for (Instruction *InnerIndexVar : InnerIndexVarList)
      WorkList.insert(cast<Instruction>(InnerIndexVar));
    MoveInstructions();

    // Splits the inner loops phi nodes out into a separate basic block.
    BasicBlock *InnerLoopHeader = InnerLoop->getHeader();
    SplitBlock(InnerLoopHeader, InnerLoopHeader->getFirstNonPHI(), DT, LI);
    LLVM_DEBUG(dbgs() << "splitting InnerLoopHeader done\n");
  }

  // Instructions in the original inner loop preheader may depend on values
  // defined in the outer loop header. Move them there, because the original
  // inner loop preheader will become the entry into the interchanged loop nest.
  // Currently we move all instructions and rely on LICM to move invariant
  // instructions outside the loop nest.
  BasicBlock *InnerLoopPreHeader = InnerLoop->getLoopPreheader();
  BasicBlock *OuterLoopHeader = OuterLoop->getHeader();
  if (InnerLoopPreHeader != OuterLoopHeader) {
    SmallPtrSet<Instruction *, 4> NeedsMoving;
    for (Instruction &I :
         make_early_inc_range(make_range(InnerLoopPreHeader->begin(),
                                         std::prev(InnerLoopPreHeader->end()))))
      I.moveBefore(OuterLoopHeader->getTerminator());
  }

  Transformed |= adjustLoopLinks();
  if (!Transformed) {
    LLVM_DEBUG(dbgs() << "adjustLoopLinks failed\n");
    return false;
  }

  return true;
}

/// \brief Move all instructions except the terminator from FromBB right before
/// InsertBefore
static void moveBBContents(BasicBlock *FromBB, Instruction *InsertBefore) {
  auto &ToList = InsertBefore->getParent()->getInstList();
  auto &FromList = FromBB->getInstList();

  ToList.splice(InsertBefore->getIterator(), FromList, FromList.begin(),
                FromBB->getTerminator()->getIterator());
}

/// Swap instructions between \p BB1 and \p BB2 but keep terminators intact.
static void swapBBContents(BasicBlock *BB1, BasicBlock *BB2) {
  // Save all non-terminator instructions of BB1 into TempInstrs and unlink them
  // from BB1 afterwards.
  auto Iter = map_range(*BB1, [](Instruction &I) { return &I; });
  SmallVector<Instruction *, 4> TempInstrs(Iter.begin(), std::prev(Iter.end()));
  for (Instruction *I : TempInstrs)
    I->removeFromParent();

  // Move instructions from BB2 to BB1.
  moveBBContents(BB2, BB1->getTerminator());

  // Move instructions from TempInstrs to BB2.
  for (Instruction *I : TempInstrs)
    I->insertBefore(BB2->getTerminator());
}

// Update BI to jump to NewBB instead of OldBB. Records updates to the
// dominator tree in DTUpdates. If \p MustUpdateOnce is true, assert that
// \p OldBB  is exactly once in BI's successor list.
static void updateSuccessor(BranchInst *BI, BasicBlock *OldBB,
                            BasicBlock *NewBB,
                            std::vector<DominatorTree::UpdateType> &DTUpdates,
                            bool MustUpdateOnce = true) {
  assert((!MustUpdateOnce ||
          llvm::count_if(successors(BI),
                         [OldBB](BasicBlock *BB) {
                           return BB == OldBB;
                         }) == 1) && "BI must jump to OldBB exactly once.");
  bool Changed = false;
  for (Use &Op : BI->operands())
    if (Op == OldBB) {
      Op.set(NewBB);
      Changed = true;
    }

  if (Changed) {
    DTUpdates.push_back(
        {DominatorTree::UpdateKind::Insert, BI->getParent(), NewBB});
    DTUpdates.push_back(
        {DominatorTree::UpdateKind::Delete, BI->getParent(), OldBB});
  }
  assert(Changed && "Expected a successor to be updated");
}

// Move Lcssa PHIs to the right place.
static void moveLCSSAPhis(BasicBlock *InnerExit, BasicBlock *InnerHeader,
                          BasicBlock *InnerLatch, BasicBlock *OuterHeader,
                          BasicBlock *OuterLatch, BasicBlock *OuterExit,
                          Loop *InnerLoop, LoopInfo *LI) {

  // Deal with LCSSA PHI nodes in the exit block of the inner loop, that are
  // defined either in the header or latch. Those blocks will become header and
  // latch of the new outer loop, and the only possible users can PHI nodes
  // in the exit block of the loop nest or the outer loop header (reduction
  // PHIs, in that case, the incoming value must be defined in the inner loop
  // header). We can just substitute the user with the incoming value and remove
  // the PHI.
  for (PHINode &P : make_early_inc_range(InnerExit->phis())) {
    assert(P.getNumIncomingValues() == 1 &&
           "Only loops with a single exit are supported!");

    // Incoming values are guaranteed be instructions currently.
    auto IncI = cast<Instruction>(P.getIncomingValueForBlock(InnerLatch));
    // Skip phis with incoming values from the inner loop body, excluding the
    // header and latch.
    if (IncI->getParent() != InnerLatch && IncI->getParent() != InnerHeader)
      continue;

    assert(all_of(P.users(),
                  [OuterHeader, OuterExit, IncI, InnerHeader](User *U) {
                    return (cast<PHINode>(U)->getParent() == OuterHeader &&
                            IncI->getParent() == InnerHeader) ||
                           cast<PHINode>(U)->getParent() == OuterExit;
                  }) &&
           "Can only replace phis iff the uses are in the loop nest exit or "
           "the incoming value is defined in the inner header (it will "
           "dominate all loop blocks after interchanging)");
    P.replaceAllUsesWith(IncI);
    P.eraseFromParent();
  }

  SmallVector<PHINode *, 8> LcssaInnerExit;
  for (PHINode &P : InnerExit->phis())
    LcssaInnerExit.push_back(&P);

  SmallVector<PHINode *, 8> LcssaInnerLatch;
  for (PHINode &P : InnerLatch->phis())
    LcssaInnerLatch.push_back(&P);

  // Lcssa PHIs for values used outside the inner loop are in InnerExit.
  // If a PHI node has users outside of InnerExit, it has a use outside the
  // interchanged loop and we have to preserve it. We move these to
  // InnerLatch, which will become the new exit block for the innermost
  // loop after interchanging.
  for (PHINode *P : LcssaInnerExit)
    P->moveBefore(InnerLatch->getFirstNonPHI());

  // If the inner loop latch contains LCSSA PHIs, those come from a child loop
  // and we have to move them to the new inner latch.
  for (PHINode *P : LcssaInnerLatch)
    P->moveBefore(InnerExit->getFirstNonPHI());

  // Deal with LCSSA PHI nodes in the loop nest exit block. For PHIs that have
  // incoming values defined in the outer loop, we have to add a new PHI
  // in the inner loop latch, which became the exit block of the outer loop,
  // after interchanging.
  if (OuterExit) {
    for (PHINode &P : OuterExit->phis()) {
      if (P.getNumIncomingValues() != 1)
        continue;
      // Skip Phis with incoming values defined in the inner loop. Those should
      // already have been updated.
      auto I = dyn_cast<Instruction>(P.getIncomingValue(0));
      if (!I || LI->getLoopFor(I->getParent()) == InnerLoop)
        continue;

      PHINode *NewPhi = dyn_cast<PHINode>(P.clone());
      NewPhi->setIncomingValue(0, P.getIncomingValue(0));
      NewPhi->setIncomingBlock(0, OuterLatch);
      // We might have incoming edges from other BBs, i.e., the original outer
      // header.
      for (auto *Pred : predecessors(InnerLatch)) {
        if (Pred == OuterLatch)
          continue;
        NewPhi->addIncoming(P.getIncomingValue(0), Pred);
      }
      NewPhi->insertBefore(InnerLatch->getFirstNonPHI());
      P.setIncomingValue(0, NewPhi);
    }
  }

  // Now adjust the incoming blocks for the LCSSA PHIs.
  // For PHIs moved from Inner's exit block, we need to replace Inner's latch
  // with the new latch.
  InnerLatch->replacePhiUsesWith(InnerLatch, OuterLatch);
}

bool LoopInterchangeTransform::adjustLoopBranches() {
  LLVM_DEBUG(dbgs() << "adjustLoopBranches called\n");
  std::vector<DominatorTree::UpdateType> DTUpdates;

  BasicBlock *OuterLoopPreHeader = OuterLoop->getLoopPreheader();
  BasicBlock *InnerLoopPreHeader = InnerLoop->getLoopPreheader();

  assert(OuterLoopPreHeader != OuterLoop->getHeader() &&
         InnerLoopPreHeader != InnerLoop->getHeader() && OuterLoopPreHeader &&
         InnerLoopPreHeader && "Guaranteed by loop-simplify form");
  // Ensure that both preheaders do not contain PHI nodes and have single
  // predecessors. This allows us to move them easily. We use
  // InsertPreHeaderForLoop to create an 'extra' preheader, if the existing
  // preheaders do not satisfy those conditions.
  if (isa<PHINode>(OuterLoopPreHeader->begin()) ||
      !OuterLoopPreHeader->getUniquePredecessor())
    OuterLoopPreHeader =
        InsertPreheaderForLoop(OuterLoop, DT, LI, nullptr, true);
  if (InnerLoopPreHeader == OuterLoop->getHeader())
    InnerLoopPreHeader =
        InsertPreheaderForLoop(InnerLoop, DT, LI, nullptr, true);

  // Adjust the loop preheader
  BasicBlock *InnerLoopHeader = InnerLoop->getHeader();
  BasicBlock *OuterLoopHeader = OuterLoop->getHeader();
  BasicBlock *InnerLoopLatch = InnerLoop->getLoopLatch();
  BasicBlock *OuterLoopLatch = OuterLoop->getLoopLatch();
  BasicBlock *OuterLoopPredecessor = OuterLoopPreHeader->getUniquePredecessor();
  BasicBlock *InnerLoopLatchPredecessor =
      InnerLoopLatch->getUniquePredecessor();
  BasicBlock *InnerLoopLatchSuccessor;
  BasicBlock *OuterLoopLatchSuccessor;

  BranchInst *OuterLoopLatchBI =
      dyn_cast<BranchInst>(OuterLoopLatch->getTerminator());
  BranchInst *InnerLoopLatchBI =
      dyn_cast<BranchInst>(InnerLoopLatch->getTerminator());
  BranchInst *OuterLoopHeaderBI =
      dyn_cast<BranchInst>(OuterLoopHeader->getTerminator());
  BranchInst *InnerLoopHeaderBI =
      dyn_cast<BranchInst>(InnerLoopHeader->getTerminator());

  if (!OuterLoopPredecessor || !InnerLoopLatchPredecessor ||
      !OuterLoopLatchBI || !InnerLoopLatchBI || !OuterLoopHeaderBI ||
      !InnerLoopHeaderBI)
    return false;

  BranchInst *InnerLoopLatchPredecessorBI =
      dyn_cast<BranchInst>(InnerLoopLatchPredecessor->getTerminator());
  BranchInst *OuterLoopPredecessorBI =
      dyn_cast<BranchInst>(OuterLoopPredecessor->getTerminator());

  if (!OuterLoopPredecessorBI || !InnerLoopLatchPredecessorBI)
    return false;
  BasicBlock *InnerLoopHeaderSuccessor = InnerLoopHeader->getUniqueSuccessor();
  if (!InnerLoopHeaderSuccessor)
    return false;

  // Adjust Loop Preheader and headers.
  // The branches in the outer loop predecessor and the outer loop header can
  // be unconditional branches or conditional branches with duplicates. Consider
  // this when updating the successors.
  updateSuccessor(OuterLoopPredecessorBI, OuterLoopPreHeader,
                  InnerLoopPreHeader, DTUpdates, /*MustUpdateOnce=*/false);
  // The outer loop header might or might not branch to the outer latch.
  // We are guaranteed to branch to the inner loop preheader.
  if (llvm::is_contained(OuterLoopHeaderBI->successors(), OuterLoopLatch)) {
    // In this case the outerLoopHeader should branch to the InnerLoopLatch.
    updateSuccessor(OuterLoopHeaderBI, OuterLoopLatch, InnerLoopLatch,
                    DTUpdates,
                    /*MustUpdateOnce=*/false);
  }
  updateSuccessor(OuterLoopHeaderBI, InnerLoopPreHeader,
                  InnerLoopHeaderSuccessor, DTUpdates,
                  /*MustUpdateOnce=*/false);

  // Adjust reduction PHI's now that the incoming block has changed.
  InnerLoopHeaderSuccessor->replacePhiUsesWith(InnerLoopHeader,
                                               OuterLoopHeader);

  updateSuccessor(InnerLoopHeaderBI, InnerLoopHeaderSuccessor,
                  OuterLoopPreHeader, DTUpdates);

  // -------------Adjust loop latches-----------
  if (InnerLoopLatchBI->getSuccessor(0) == InnerLoopHeader)
    InnerLoopLatchSuccessor = InnerLoopLatchBI->getSuccessor(1);
  else
    InnerLoopLatchSuccessor = InnerLoopLatchBI->getSuccessor(0);

  updateSuccessor(InnerLoopLatchPredecessorBI, InnerLoopLatch,
                  InnerLoopLatchSuccessor, DTUpdates);

  if (OuterLoopLatchBI->getSuccessor(0) == OuterLoopHeader)
    OuterLoopLatchSuccessor = OuterLoopLatchBI->getSuccessor(1);
  else
    OuterLoopLatchSuccessor = OuterLoopLatchBI->getSuccessor(0);

  updateSuccessor(InnerLoopLatchBI, InnerLoopLatchSuccessor,
                  OuterLoopLatchSuccessor, DTUpdates);
  updateSuccessor(OuterLoopLatchBI, OuterLoopLatchSuccessor, InnerLoopLatch,
                  DTUpdates);

  DT->applyUpdates(DTUpdates);
  restructureLoops(OuterLoop, InnerLoop, InnerLoopPreHeader,
                   OuterLoopPreHeader);

  moveLCSSAPhis(InnerLoopLatchSuccessor, InnerLoopHeader, InnerLoopLatch,
                OuterLoopHeader, OuterLoopLatch, InnerLoop->getExitBlock(),
                InnerLoop, LI);
  // For PHIs in the exit block of the outer loop, outer's latch has been
  // replaced by Inners'.
  OuterLoopLatchSuccessor->replacePhiUsesWith(OuterLoopLatch, InnerLoopLatch);

  auto &OuterInnerReductions = LIL.getOuterInnerReductions();
  // Now update the reduction PHIs in the inner and outer loop headers.
  SmallVector<PHINode *, 4> InnerLoopPHIs, OuterLoopPHIs;
  for (PHINode &PHI : InnerLoopHeader->phis())
    if (OuterInnerReductions.contains(&PHI))
      InnerLoopPHIs.push_back(&PHI);

  for (PHINode &PHI : OuterLoopHeader->phis())
    if (OuterInnerReductions.contains(&PHI))
      OuterLoopPHIs.push_back(&PHI);

  // Now move the remaining reduction PHIs from outer to inner loop header and
  // vice versa. The PHI nodes must be part of a reduction across the inner and
  // outer loop and all the remains to do is and updating the incoming blocks.
  for (PHINode *PHI : OuterLoopPHIs) {
    LLVM_DEBUG(dbgs() << "Outer loop reduction PHIs:\n"; PHI->dump(););
    PHI->moveBefore(InnerLoopHeader->getFirstNonPHI());
    assert(OuterInnerReductions.count(PHI) && "Expected a reduction PHI node");
  }
  for (PHINode *PHI : InnerLoopPHIs) {
    LLVM_DEBUG(dbgs() << "Inner loop reduction PHIs:\n"; PHI->dump(););
    PHI->moveBefore(OuterLoopHeader->getFirstNonPHI());
    assert(OuterInnerReductions.count(PHI) && "Expected a reduction PHI node");
  }

  // Update the incoming blocks for moved PHI nodes.
  OuterLoopHeader->replacePhiUsesWith(InnerLoopPreHeader, OuterLoopPreHeader);
  OuterLoopHeader->replacePhiUsesWith(InnerLoopLatch, OuterLoopLatch);
  InnerLoopHeader->replacePhiUsesWith(OuterLoopPreHeader, InnerLoopPreHeader);
  InnerLoopHeader->replacePhiUsesWith(OuterLoopLatch, InnerLoopLatch);

  // Values defined in the outer loop header could be used in the inner loop
  // latch. In that case, we need to create LCSSA phis for them, because after
  // interchanging they will be defined in the new inner loop and used in the
  // new outer loop.
  IRBuilder<> Builder(OuterLoopHeader->getContext());
  SmallVector<Instruction *, 4> MayNeedLCSSAPhis;
  for (Instruction &I :
       make_range(OuterLoopHeader->begin(), std::prev(OuterLoopHeader->end())))
    MayNeedLCSSAPhis.push_back(&I);
  formLCSSAForInstructions(MayNeedLCSSAPhis, *DT, *LI, SE, Builder);

  return true;
}

bool LoopInterchangeTransform::adjustLoopLinks() {
  // Adjust all branches in the inner and outer loop.
  bool Changed = adjustLoopBranches();
  if (Changed) {
    // We have interchanged the preheaders so we need to interchange the data in
    // the preheaders as well. This is because the content of the inner
    // preheader was previously executed inside the outer loop.
    BasicBlock *OuterLoopPreHeader = OuterLoop->getLoopPreheader();
    BasicBlock *InnerLoopPreHeader = InnerLoop->getLoopPreheader();
    swapBBContents(OuterLoopPreHeader, InnerLoopPreHeader);
  }
  return Changed;
}

namespace {
/// Main LoopInterchange Pass.
struct LoopInterchangeLegacyPass : public LoopPass {
  static char ID;

  LoopInterchangeLegacyPass() : LoopPass(ID) {
    initializeLoopInterchangeLegacyPassPass(*PassRegistry::getPassRegistry());
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<DependenceAnalysisWrapperPass>();
    AU.addRequired<OptimizationRemarkEmitterWrapperPass>();

    getLoopAnalysisUsage(AU);
  }

  bool runOnLoop(Loop *L, LPPassManager &LPM) override {
    if (skipLoop(L))
      return false;

    auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
    auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
    auto *DI = &getAnalysis<DependenceAnalysisWrapperPass>().getDI();
    auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    auto *ORE = &getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE();

    return LoopInterchange(SE, LI, DI, DT, ORE).run(L);
  }
};
} // namespace

char LoopInterchangeLegacyPass::ID = 0;

INITIALIZE_PASS_BEGIN(LoopInterchangeLegacyPass, "loop-interchange",
                      "Interchanges loops for cache reuse", false, false)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(DependenceAnalysisWrapperPass)
INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)

INITIALIZE_PASS_END(LoopInterchangeLegacyPass, "loop-interchange",
                    "Interchanges loops for cache reuse", false, false)

Pass *llvm::createLoopInterchangePass() {
  return new LoopInterchangeLegacyPass();
}

PreservedAnalyses LoopInterchangePass::run(LoopNest &LN,
                                           LoopAnalysisManager &AM,
                                           LoopStandardAnalysisResults &AR,
                                           LPMUpdater &U) {
  Function &F = *LN.getParent();

  DependenceInfo DI(&F, &AR.AA, &AR.SE, &AR.LI);
  OptimizationRemarkEmitter ORE(&F);
  if (!LoopInterchange(&AR.SE, &AR.LI, &DI, &AR.DT, &ORE).run(LN))
    return PreservedAnalyses::all();
  return getLoopPassPreservedAnalyses();
}