llvm.org GIT mirror llvm / release_90 lib / Transforms / Scalar / EarlyCSE.cpp
release_90

Tree @release_90 (Download .tar.gz)

EarlyCSE.cpp @release_90raw · history · blame

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 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
//===- EarlyCSE.cpp - Simple and fast CSE 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 performs a simple dominator tree walk that eliminates trivially
// redundant instructions.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/EarlyCSE.h"
#include "llvm/ADT/DenseMapInfo.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/ScopedHashTable.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/GuardUtils.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/MemorySSAUpdater.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Use.h"
#include "llvm/IR/Value.h"
#include "llvm/Pass.h"
#include "llvm/Support/Allocator.h"
#include "llvm/Support/AtomicOrdering.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/DebugCounter.h"
#include "llvm/Support/RecyclingAllocator.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/GuardUtils.h"
#include <cassert>
#include <deque>
#include <memory>
#include <utility>

using namespace llvm;
using namespace llvm::PatternMatch;

#define DEBUG_TYPE "early-cse"

STATISTIC(NumSimplify, "Number of instructions simplified or DCE'd");
STATISTIC(NumCSE,      "Number of instructions CSE'd");
STATISTIC(NumCSECVP,   "Number of compare instructions CVP'd");
STATISTIC(NumCSELoad,  "Number of load instructions CSE'd");
STATISTIC(NumCSECall,  "Number of call instructions CSE'd");
STATISTIC(NumDSE,      "Number of trivial dead stores removed");

DEBUG_COUNTER(CSECounter, "early-cse",
              "Controls which instructions are removed");

static cl::opt<unsigned> EarlyCSEMssaOptCap(
    "earlycse-mssa-optimization-cap", cl::init(500), cl::Hidden,
    cl::desc("Enable imprecision in EarlyCSE in pathological cases, in exchange "
             "for faster compile. Caps the MemorySSA clobbering calls."));

static cl::opt<bool> EarlyCSEDebugHash(
    "earlycse-debug-hash", cl::init(false), cl::Hidden,
    cl::desc("Perform extra assertion checking to verify that SimpleValue's hash "
             "function is well-behaved w.r.t. its isEqual predicate"));

//===----------------------------------------------------------------------===//
// SimpleValue
//===----------------------------------------------------------------------===//

namespace {

/// Struct representing the available values in the scoped hash table.
struct SimpleValue {
  Instruction *Inst;

  SimpleValue(Instruction *I) : Inst(I) {
    assert((isSentinel() || canHandle(I)) && "Inst can't be handled!");
  }

  bool isSentinel() const {
    return Inst == DenseMapInfo<Instruction *>::getEmptyKey() ||
           Inst == DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static bool canHandle(Instruction *Inst) {
    // This can only handle non-void readnone functions.
    if (CallInst *CI = dyn_cast<CallInst>(Inst))
      return CI->doesNotAccessMemory() && !CI->getType()->isVoidTy();
    return isa<CastInst>(Inst) || isa<BinaryOperator>(Inst) ||
           isa<GetElementPtrInst>(Inst) || isa<CmpInst>(Inst) ||
           isa<SelectInst>(Inst) || isa<ExtractElementInst>(Inst) ||
           isa<InsertElementInst>(Inst) || isa<ShuffleVectorInst>(Inst) ||
           isa<ExtractValueInst>(Inst) || isa<InsertValueInst>(Inst);
  }
};

} // end anonymous namespace

namespace llvm {

template <> struct DenseMapInfo<SimpleValue> {
  static inline SimpleValue getEmptyKey() {
    return DenseMapInfo<Instruction *>::getEmptyKey();
  }

  static inline SimpleValue getTombstoneKey() {
    return DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static unsigned getHashValue(SimpleValue Val);
  static bool isEqual(SimpleValue LHS, SimpleValue RHS);
};

} // end namespace llvm

/// Match a 'select' including an optional 'not's of the condition.
static bool matchSelectWithOptionalNotCond(Value *V, Value *&Cond, Value *&A,
                                           Value *&B,
                                           SelectPatternFlavor &Flavor) {
  // Return false if V is not even a select.
  if (!match(V, m_Select(m_Value(Cond), m_Value(A), m_Value(B))))
    return false;

  // Look through a 'not' of the condition operand by swapping A/B.
  Value *CondNot;
  if (match(Cond, m_Not(m_Value(CondNot)))) {
    Cond = CondNot;
    std::swap(A, B);
  }

  // Set flavor if we find a match, or set it to unknown otherwise; in
  // either case, return true to indicate that this is a select we can
  // process.
  if (auto *CmpI = dyn_cast<ICmpInst>(Cond))
    Flavor = matchDecomposedSelectPattern(CmpI, A, B, A, B).Flavor;
  else
    Flavor = SPF_UNKNOWN;

  return true;
}

static unsigned getHashValueImpl(SimpleValue Val) {
  Instruction *Inst = Val.Inst;
  // Hash in all of the operands as pointers.
  if (BinaryOperator *BinOp = dyn_cast<BinaryOperator>(Inst)) {
    Value *LHS = BinOp->getOperand(0);
    Value *RHS = BinOp->getOperand(1);
    if (BinOp->isCommutative() && BinOp->getOperand(0) > BinOp->getOperand(1))
      std::swap(LHS, RHS);

    return hash_combine(BinOp->getOpcode(), LHS, RHS);
  }

  if (CmpInst *CI = dyn_cast<CmpInst>(Inst)) {
    // Compares can be commuted by swapping the comparands and
    // updating the predicate.  Choose the form that has the
    // comparands in sorted order, or in the case of a tie, the
    // one with the lower predicate.
    Value *LHS = CI->getOperand(0);
    Value *RHS = CI->getOperand(1);
    CmpInst::Predicate Pred = CI->getPredicate();
    CmpInst::Predicate SwappedPred = CI->getSwappedPredicate();
    if (std::tie(LHS, Pred) > std::tie(RHS, SwappedPred)) {
      std::swap(LHS, RHS);
      Pred = SwappedPred;
    }
    return hash_combine(Inst->getOpcode(), Pred, LHS, RHS);
  }

  // Hash general selects to allow matching commuted true/false operands.
  SelectPatternFlavor SPF;
  Value *Cond, *A, *B;
  if (matchSelectWithOptionalNotCond(Inst, Cond, A, B, SPF)) {
    // Hash min/max/abs (cmp + select) to allow for commuted operands.
    // Min/max may also have non-canonical compare predicate (eg, the compare for
    // smin may use 'sgt' rather than 'slt'), and non-canonical operands in the
    // compare.
    // TODO: We should also detect FP min/max.
    if (SPF == SPF_SMIN || SPF == SPF_SMAX ||
        SPF == SPF_UMIN || SPF == SPF_UMAX) {
      if (A > B)
        std::swap(A, B);
      return hash_combine(Inst->getOpcode(), SPF, A, B);
    }
    if (SPF == SPF_ABS || SPF == SPF_NABS) {
      // ABS/NABS always puts the input in A and its negation in B.
      return hash_combine(Inst->getOpcode(), SPF, A, B);
    }

    // Hash general selects to allow matching commuted true/false operands.

    // If we do not have a compare as the condition, just hash in the condition.
    CmpInst::Predicate Pred;
    Value *X, *Y;
    if (!match(Cond, m_Cmp(Pred, m_Value(X), m_Value(Y))))
      return hash_combine(Inst->getOpcode(), Cond, A, B);

    // Similar to cmp normalization (above) - canonicalize the predicate value:
    // select (icmp Pred, X, Y), A, B --> select (icmp InvPred, X, Y), B, A
    if (CmpInst::getInversePredicate(Pred) < Pred) {
      Pred = CmpInst::getInversePredicate(Pred);
      std::swap(A, B);
    }
    return hash_combine(Inst->getOpcode(), Pred, X, Y, A, B);
  }

  if (CastInst *CI = dyn_cast<CastInst>(Inst))
    return hash_combine(CI->getOpcode(), CI->getType(), CI->getOperand(0));

  if (const ExtractValueInst *EVI = dyn_cast<ExtractValueInst>(Inst))
    return hash_combine(EVI->getOpcode(), EVI->getOperand(0),
                        hash_combine_range(EVI->idx_begin(), EVI->idx_end()));

  if (const InsertValueInst *IVI = dyn_cast<InsertValueInst>(Inst))
    return hash_combine(IVI->getOpcode(), IVI->getOperand(0),
                        IVI->getOperand(1),
                        hash_combine_range(IVI->idx_begin(), IVI->idx_end()));

  assert((isa<CallInst>(Inst) || isa<GetElementPtrInst>(Inst) ||
          isa<ExtractElementInst>(Inst) || isa<InsertElementInst>(Inst) ||
          isa<ShuffleVectorInst>(Inst)) &&
         "Invalid/unknown instruction");

  // Mix in the opcode.
  return hash_combine(
      Inst->getOpcode(),
      hash_combine_range(Inst->value_op_begin(), Inst->value_op_end()));
}

unsigned DenseMapInfo<SimpleValue>::getHashValue(SimpleValue Val) {
#ifndef NDEBUG
  // If -earlycse-debug-hash was specified, return a constant -- this
  // will force all hashing to collide, so we'll exhaustively search
  // the table for a match, and the assertion in isEqual will fire if
  // there's a bug causing equal keys to hash differently.
  if (EarlyCSEDebugHash)
    return 0;
#endif
  return getHashValueImpl(Val);
}

static bool isEqualImpl(SimpleValue LHS, SimpleValue RHS) {
  Instruction *LHSI = LHS.Inst, *RHSI = RHS.Inst;

  if (LHS.isSentinel() || RHS.isSentinel())
    return LHSI == RHSI;

  if (LHSI->getOpcode() != RHSI->getOpcode())
    return false;
  if (LHSI->isIdenticalToWhenDefined(RHSI))
    return true;

  // If we're not strictly identical, we still might be a commutable instruction
  if (BinaryOperator *LHSBinOp = dyn_cast<BinaryOperator>(LHSI)) {
    if (!LHSBinOp->isCommutative())
      return false;

    assert(isa<BinaryOperator>(RHSI) &&
           "same opcode, but different instruction type?");
    BinaryOperator *RHSBinOp = cast<BinaryOperator>(RHSI);

    // Commuted equality
    return LHSBinOp->getOperand(0) == RHSBinOp->getOperand(1) &&
           LHSBinOp->getOperand(1) == RHSBinOp->getOperand(0);
  }
  if (CmpInst *LHSCmp = dyn_cast<CmpInst>(LHSI)) {
    assert(isa<CmpInst>(RHSI) &&
           "same opcode, but different instruction type?");
    CmpInst *RHSCmp = cast<CmpInst>(RHSI);
    // Commuted equality
    return LHSCmp->getOperand(0) == RHSCmp->getOperand(1) &&
           LHSCmp->getOperand(1) == RHSCmp->getOperand(0) &&
           LHSCmp->getSwappedPredicate() == RHSCmp->getPredicate();
  }

  // Min/max/abs can occur with commuted operands, non-canonical predicates,
  // and/or non-canonical operands.
  // Selects can be non-trivially equivalent via inverted conditions and swaps.
  SelectPatternFlavor LSPF, RSPF;
  Value *CondL, *CondR, *LHSA, *RHSA, *LHSB, *RHSB;
  if (matchSelectWithOptionalNotCond(LHSI, CondL, LHSA, LHSB, LSPF) &&
      matchSelectWithOptionalNotCond(RHSI, CondR, RHSA, RHSB, RSPF)) {
    if (LSPF == RSPF) {
      // TODO: We should also detect FP min/max.
      if (LSPF == SPF_SMIN || LSPF == SPF_SMAX ||
          LSPF == SPF_UMIN || LSPF == SPF_UMAX)
        return ((LHSA == RHSA && LHSB == RHSB) ||
                (LHSA == RHSB && LHSB == RHSA));

      if (LSPF == SPF_ABS || LSPF == SPF_NABS) {
        // Abs results are placed in a defined order by matchSelectPattern.
        return LHSA == RHSA && LHSB == RHSB;
      }

      // select Cond, A, B <--> select not(Cond), B, A
      if (CondL == CondR && LHSA == RHSA && LHSB == RHSB)
        return true;
    }

    // If the true/false operands are swapped and the conditions are compares
    // with inverted predicates, the selects are equal:
    // select (icmp Pred, X, Y), A, B <--> select (icmp InvPred, X, Y), B, A
    //
    // This also handles patterns with a double-negation in the sense of not +
    // inverse, because we looked through a 'not' in the matching function and
    // swapped A/B:
    // select (cmp Pred, X, Y), A, B <--> select (not (cmp InvPred, X, Y)), B, A
    //
    // This intentionally does NOT handle patterns with a double-negation in
    // the sense of not + not, because doing so could result in values
    // comparing
    // as equal that hash differently in the min/max/abs cases like:
    // select (cmp slt, X, Y), X, Y <--> select (not (not (cmp slt, X, Y))), X, Y
    //   ^ hashes as min                  ^ would not hash as min
    // In the context of the EarlyCSE pass, however, such cases never reach
    // this code, as we simplify the double-negation before hashing the second
    // select (and so still succeed at CSEing them).
    if (LHSA == RHSB && LHSB == RHSA) {
      CmpInst::Predicate PredL, PredR;
      Value *X, *Y;
      if (match(CondL, m_Cmp(PredL, m_Value(X), m_Value(Y))) &&
          match(CondR, m_Cmp(PredR, m_Specific(X), m_Specific(Y))) &&
          CmpInst::getInversePredicate(PredL) == PredR)
        return true;
    }
  }

  return false;
}

bool DenseMapInfo<SimpleValue>::isEqual(SimpleValue LHS, SimpleValue RHS) {
  // These comparisons are nontrivial, so assert that equality implies
  // hash equality (DenseMap demands this as an invariant).
  bool Result = isEqualImpl(LHS, RHS);
  assert(!Result || (LHS.isSentinel() && LHS.Inst == RHS.Inst) ||
         getHashValueImpl(LHS) == getHashValueImpl(RHS));
  return Result;
}

//===----------------------------------------------------------------------===//
// CallValue
//===----------------------------------------------------------------------===//

namespace {

/// Struct representing the available call values in the scoped hash
/// table.
struct CallValue {
  Instruction *Inst;

  CallValue(Instruction *I) : Inst(I) {
    assert((isSentinel() || canHandle(I)) && "Inst can't be handled!");
  }

  bool isSentinel() const {
    return Inst == DenseMapInfo<Instruction *>::getEmptyKey() ||
           Inst == DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static bool canHandle(Instruction *Inst) {
    // Don't value number anything that returns void.
    if (Inst->getType()->isVoidTy())
      return false;

    CallInst *CI = dyn_cast<CallInst>(Inst);
    if (!CI || !CI->onlyReadsMemory())
      return false;
    return true;
  }
};

} // end anonymous namespace

namespace llvm {

template <> struct DenseMapInfo<CallValue> {
  static inline CallValue getEmptyKey() {
    return DenseMapInfo<Instruction *>::getEmptyKey();
  }

  static inline CallValue getTombstoneKey() {
    return DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static unsigned getHashValue(CallValue Val);
  static bool isEqual(CallValue LHS, CallValue RHS);
};

} // end namespace llvm

unsigned DenseMapInfo<CallValue>::getHashValue(CallValue Val) {
  Instruction *Inst = Val.Inst;
  // Hash all of the operands as pointers and mix in the opcode.
  return hash_combine(
      Inst->getOpcode(),
      hash_combine_range(Inst->value_op_begin(), Inst->value_op_end()));
}

bool DenseMapInfo<CallValue>::isEqual(CallValue LHS, CallValue RHS) {
  Instruction *LHSI = LHS.Inst, *RHSI = RHS.Inst;
  if (LHS.isSentinel() || RHS.isSentinel())
    return LHSI == RHSI;
  return LHSI->isIdenticalTo(RHSI);
}

//===----------------------------------------------------------------------===//
// EarlyCSE implementation
//===----------------------------------------------------------------------===//

namespace {

/// A simple and fast domtree-based CSE pass.
///
/// This pass does a simple depth-first walk over the dominator tree,
/// eliminating trivially redundant instructions and using instsimplify to
/// canonicalize things as it goes. It is intended to be fast and catch obvious
/// cases so that instcombine and other passes are more effective. It is
/// expected that a later pass of GVN will catch the interesting/hard cases.
class EarlyCSE {
public:
  const TargetLibraryInfo &TLI;
  const TargetTransformInfo &TTI;
  DominatorTree &DT;
  AssumptionCache &AC;
  const SimplifyQuery SQ;
  MemorySSA *MSSA;
  std::unique_ptr<MemorySSAUpdater> MSSAUpdater;

  using AllocatorTy =
      RecyclingAllocator<BumpPtrAllocator,
                         ScopedHashTableVal<SimpleValue, Value *>>;
  using ScopedHTType =
      ScopedHashTable<SimpleValue, Value *, DenseMapInfo<SimpleValue>,
                      AllocatorTy>;

  /// A scoped hash table of the current values of all of our simple
  /// scalar expressions.
  ///
  /// As we walk down the domtree, we look to see if instructions are in this:
  /// if so, we replace them with what we find, otherwise we insert them so
  /// that dominated values can succeed in their lookup.
  ScopedHTType AvailableValues;

  /// A scoped hash table of the current values of previously encountered
  /// memory locations.
  ///
  /// This allows us to get efficient access to dominating loads or stores when
  /// we have a fully redundant load.  In addition to the most recent load, we
  /// keep track of a generation count of the read, which is compared against
  /// the current generation count.  The current generation count is incremented
  /// after every possibly writing memory operation, which ensures that we only
  /// CSE loads with other loads that have no intervening store.  Ordering
  /// events (such as fences or atomic instructions) increment the generation
  /// count as well; essentially, we model these as writes to all possible
  /// locations.  Note that atomic and/or volatile loads and stores can be
  /// present the table; it is the responsibility of the consumer to inspect
  /// the atomicity/volatility if needed.
  struct LoadValue {
    Instruction *DefInst = nullptr;
    unsigned Generation = 0;
    int MatchingId = -1;
    bool IsAtomic = false;

    LoadValue() = default;
    LoadValue(Instruction *Inst, unsigned Generation, unsigned MatchingId,
              bool IsAtomic)
        : DefInst(Inst), Generation(Generation), MatchingId(MatchingId),
          IsAtomic(IsAtomic) {}
  };

  using LoadMapAllocator =
      RecyclingAllocator<BumpPtrAllocator,
                         ScopedHashTableVal<Value *, LoadValue>>;
  using LoadHTType =
      ScopedHashTable<Value *, LoadValue, DenseMapInfo<Value *>,
                      LoadMapAllocator>;

  LoadHTType AvailableLoads;

  // A scoped hash table mapping memory locations (represented as typed
  // addresses) to generation numbers at which that memory location became
  // (henceforth indefinitely) invariant.
  using InvariantMapAllocator =
      RecyclingAllocator<BumpPtrAllocator,
                         ScopedHashTableVal<MemoryLocation, unsigned>>;
  using InvariantHTType =
      ScopedHashTable<MemoryLocation, unsigned, DenseMapInfo<MemoryLocation>,
                      InvariantMapAllocator>;
  InvariantHTType AvailableInvariants;

  /// A scoped hash table of the current values of read-only call
  /// values.
  ///
  /// It uses the same generation count as loads.
  using CallHTType =
      ScopedHashTable<CallValue, std::pair<Instruction *, unsigned>>;
  CallHTType AvailableCalls;

  /// This is the current generation of the memory value.
  unsigned CurrentGeneration = 0;

  /// Set up the EarlyCSE runner for a particular function.
  EarlyCSE(const DataLayout &DL, const TargetLibraryInfo &TLI,
           const TargetTransformInfo &TTI, DominatorTree &DT,
           AssumptionCache &AC, MemorySSA *MSSA)
      : TLI(TLI), TTI(TTI), DT(DT), AC(AC), SQ(DL, &TLI, &DT, &AC), MSSA(MSSA),
        MSSAUpdater(llvm::make_unique<MemorySSAUpdater>(MSSA)) {}

  bool run();

private:
  unsigned ClobberCounter = 0;
  // Almost a POD, but needs to call the constructors for the scoped hash
  // tables so that a new scope gets pushed on. These are RAII so that the
  // scope gets popped when the NodeScope is destroyed.
  class NodeScope {
  public:
    NodeScope(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
              InvariantHTType &AvailableInvariants, CallHTType &AvailableCalls)
      : Scope(AvailableValues), LoadScope(AvailableLoads),
        InvariantScope(AvailableInvariants), CallScope(AvailableCalls) {}
    NodeScope(const NodeScope &) = delete;
    NodeScope &operator=(const NodeScope &) = delete;

  private:
    ScopedHTType::ScopeTy Scope;
    LoadHTType::ScopeTy LoadScope;
    InvariantHTType::ScopeTy InvariantScope;
    CallHTType::ScopeTy CallScope;
  };

  // Contains all the needed information to create a stack for doing a depth
  // first traversal of the tree. This includes scopes for values, loads, and
  // calls as well as the generation. There is a child iterator so that the
  // children do not need to be store separately.
  class StackNode {
  public:
    StackNode(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
              InvariantHTType &AvailableInvariants, CallHTType &AvailableCalls,
              unsigned cg, DomTreeNode *n, DomTreeNode::iterator child,
              DomTreeNode::iterator end)
        : CurrentGeneration(cg), ChildGeneration(cg), Node(n), ChildIter(child),
          EndIter(end),
          Scopes(AvailableValues, AvailableLoads, AvailableInvariants,
                 AvailableCalls)
          {}
    StackNode(const StackNode &) = delete;
    StackNode &operator=(const StackNode &) = delete;

    // Accessors.
    unsigned currentGeneration() { return CurrentGeneration; }
    unsigned childGeneration() { return ChildGeneration; }
    void childGeneration(unsigned generation) { ChildGeneration = generation; }
    DomTreeNode *node() { return Node; }
    DomTreeNode::iterator childIter() { return ChildIter; }

    DomTreeNode *nextChild() {
      DomTreeNode *child = *ChildIter;
      ++ChildIter;
      return child;
    }

    DomTreeNode::iterator end() { return EndIter; }
    bool isProcessed() { return Processed; }
    void process() { Processed = true; }

  private:
    unsigned CurrentGeneration;
    unsigned ChildGeneration;
    DomTreeNode *Node;
    DomTreeNode::iterator ChildIter;
    DomTreeNode::iterator EndIter;
    NodeScope Scopes;
    bool Processed = false;
  };

  /// Wrapper class to handle memory instructions, including loads,
  /// stores and intrinsic loads and stores defined by the target.
  class ParseMemoryInst {
  public:
    ParseMemoryInst(Instruction *Inst, const TargetTransformInfo &TTI)
      : Inst(Inst) {
      if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst))
        if (TTI.getTgtMemIntrinsic(II, Info))
          IsTargetMemInst = true;
    }

    bool isLoad() const {
      if (IsTargetMemInst) return Info.ReadMem;
      return isa<LoadInst>(Inst);
    }

    bool isStore() const {
      if (IsTargetMemInst) return Info.WriteMem;
      return isa<StoreInst>(Inst);
    }

    bool isAtomic() const {
      if (IsTargetMemInst)
        return Info.Ordering != AtomicOrdering::NotAtomic;
      return Inst->isAtomic();
    }

    bool isUnordered() const {
      if (IsTargetMemInst)
        return Info.isUnordered();

      if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        return LI->isUnordered();
      } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        return SI->isUnordered();
      }
      // Conservative answer
      return !Inst->isAtomic();
    }

    bool isVolatile() const {
      if (IsTargetMemInst)
        return Info.IsVolatile;

      if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        return LI->isVolatile();
      } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        return SI->isVolatile();
      }
      // Conservative answer
      return true;
    }

    bool isInvariantLoad() const {
      if (auto *LI = dyn_cast<LoadInst>(Inst))
        return LI->getMetadata(LLVMContext::MD_invariant_load) != nullptr;
      return false;
    }

    bool isMatchingMemLoc(const ParseMemoryInst &Inst) const {
      return (getPointerOperand() == Inst.getPointerOperand() &&
              getMatchingId() == Inst.getMatchingId());
    }

    bool isValid() const { return getPointerOperand() != nullptr; }

    // For regular (non-intrinsic) loads/stores, this is set to -1. For
    // intrinsic loads/stores, the id is retrieved from the corresponding
    // field in the MemIntrinsicInfo structure.  That field contains
    // non-negative values only.
    int getMatchingId() const {
      if (IsTargetMemInst) return Info.MatchingId;
      return -1;
    }

    Value *getPointerOperand() const {
      if (IsTargetMemInst) return Info.PtrVal;
      return getLoadStorePointerOperand(Inst);
    }

    bool mayReadFromMemory() const {
      if (IsTargetMemInst) return Info.ReadMem;
      return Inst->mayReadFromMemory();
    }

    bool mayWriteToMemory() const {
      if (IsTargetMemInst) return Info.WriteMem;
      return Inst->mayWriteToMemory();
    }

  private:
    bool IsTargetMemInst = false;
    MemIntrinsicInfo Info;
    Instruction *Inst;
  };

  bool processNode(DomTreeNode *Node);

  bool handleBranchCondition(Instruction *CondInst, const BranchInst *BI,
                             const BasicBlock *BB, const BasicBlock *Pred);

  Value *getOrCreateResult(Value *Inst, Type *ExpectedType) const {
    if (auto *LI = dyn_cast<LoadInst>(Inst))
      return LI;
    if (auto *SI = dyn_cast<StoreInst>(Inst))
      return SI->getValueOperand();
    assert(isa<IntrinsicInst>(Inst) && "Instruction not supported");
    return TTI.getOrCreateResultFromMemIntrinsic(cast<IntrinsicInst>(Inst),
                                                 ExpectedType);
  }

  /// Return true if the instruction is known to only operate on memory
  /// provably invariant in the given "generation".
  bool isOperatingOnInvariantMemAt(Instruction *I, unsigned GenAt);

  bool isSameMemGeneration(unsigned EarlierGeneration, unsigned LaterGeneration,
                           Instruction *EarlierInst, Instruction *LaterInst);

  void removeMSSA(Instruction *Inst) {
    if (!MSSA)
      return;
    if (VerifyMemorySSA)
      MSSA->verifyMemorySSA();
    // Removing a store here can leave MemorySSA in an unoptimized state by
    // creating MemoryPhis that have identical arguments and by creating
    // MemoryUses whose defining access is not an actual clobber. The phi case
    // is handled by MemorySSA when passing OptimizePhis = true to
    // removeMemoryAccess.  The non-optimized MemoryUse case is lazily updated
    // by MemorySSA's getClobberingMemoryAccess.
    MSSAUpdater->removeMemoryAccess(Inst, true);
  }
};

} // end anonymous namespace

/// Determine if the memory referenced by LaterInst is from the same heap
/// version as EarlierInst.
/// This is currently called in two scenarios:
///
///   load p
///   ...
///   load p
///
/// and
///
///   x = load p
///   ...
///   store x, p
///
/// in both cases we want to verify that there are no possible writes to the
/// memory referenced by p between the earlier and later instruction.
bool EarlyCSE::isSameMemGeneration(unsigned EarlierGeneration,
                                   unsigned LaterGeneration,
                                   Instruction *EarlierInst,
                                   Instruction *LaterInst) {
  // Check the simple memory generation tracking first.
  if (EarlierGeneration == LaterGeneration)
    return true;

  if (!MSSA)
    return false;

  // If MemorySSA has determined that one of EarlierInst or LaterInst does not
  // read/write memory, then we can safely return true here.
  // FIXME: We could be more aggressive when checking doesNotAccessMemory(),
  // onlyReadsMemory(), mayReadFromMemory(), and mayWriteToMemory() in this pass
  // by also checking the MemorySSA MemoryAccess on the instruction.  Initial
  // experiments suggest this isn't worthwhile, at least for C/C++ code compiled
  // with the default optimization pipeline.
  auto *EarlierMA = MSSA->getMemoryAccess(EarlierInst);
  if (!EarlierMA)
    return true;
  auto *LaterMA = MSSA->getMemoryAccess(LaterInst);
  if (!LaterMA)
    return true;

  // Since we know LaterDef dominates LaterInst and EarlierInst dominates
  // LaterInst, if LaterDef dominates EarlierInst then it can't occur between
  // EarlierInst and LaterInst and neither can any other write that potentially
  // clobbers LaterInst.
  MemoryAccess *LaterDef;
  if (ClobberCounter < EarlyCSEMssaOptCap) {
    LaterDef = MSSA->getWalker()->getClobberingMemoryAccess(LaterInst);
    ClobberCounter++;
  } else
    LaterDef = LaterMA->getDefiningAccess();

  return MSSA->dominates(LaterDef, EarlierMA);
}

bool EarlyCSE::isOperatingOnInvariantMemAt(Instruction *I, unsigned GenAt) {
  // A location loaded from with an invariant_load is assumed to *never* change
  // within the visible scope of the compilation.
  if (auto *LI = dyn_cast<LoadInst>(I))
    if (LI->getMetadata(LLVMContext::MD_invariant_load))
      return true;

  auto MemLocOpt = MemoryLocation::getOrNone(I);
  if (!MemLocOpt)
    // "target" intrinsic forms of loads aren't currently known to
    // MemoryLocation::get.  TODO
    return false;
  MemoryLocation MemLoc = *MemLocOpt;
  if (!AvailableInvariants.count(MemLoc))
    return false;

  // Is the generation at which this became invariant older than the
  // current one?
  return AvailableInvariants.lookup(MemLoc) <= GenAt;
}

bool EarlyCSE::handleBranchCondition(Instruction *CondInst,
                                     const BranchInst *BI, const BasicBlock *BB,
                                     const BasicBlock *Pred) {
  assert(BI->isConditional() && "Should be a conditional branch!");
  assert(BI->getCondition() == CondInst && "Wrong condition?");
  assert(BI->getSuccessor(0) == BB || BI->getSuccessor(1) == BB);
  auto *TorF = (BI->getSuccessor(0) == BB)
                   ? ConstantInt::getTrue(BB->getContext())
                   : ConstantInt::getFalse(BB->getContext());
  auto MatchBinOp = [](Instruction *I, unsigned Opcode) {
    if (BinaryOperator *BOp = dyn_cast<BinaryOperator>(I))
      return BOp->getOpcode() == Opcode;
    return false;
  };
  // If the condition is AND operation, we can propagate its operands into the
  // true branch. If it is OR operation, we can propagate them into the false
  // branch.
  unsigned PropagateOpcode =
      (BI->getSuccessor(0) == BB) ? Instruction::And : Instruction::Or;

  bool MadeChanges = false;
  SmallVector<Instruction *, 4> WorkList;
  SmallPtrSet<Instruction *, 4> Visited;
  WorkList.push_back(CondInst);
  while (!WorkList.empty()) {
    Instruction *Curr = WorkList.pop_back_val();

    AvailableValues.insert(Curr, TorF);
    LLVM_DEBUG(dbgs() << "EarlyCSE CVP: Add conditional value for '"
                      << Curr->getName() << "' as " << *TorF << " in "
                      << BB->getName() << "\n");
    if (!DebugCounter::shouldExecute(CSECounter)) {
      LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
    } else {
      // Replace all dominated uses with the known value.
      if (unsigned Count = replaceDominatedUsesWith(Curr, TorF, DT,
                                                    BasicBlockEdge(Pred, BB))) {
        NumCSECVP += Count;
        MadeChanges = true;
      }
    }

    if (MatchBinOp(Curr, PropagateOpcode))
      for (auto &Op : cast<BinaryOperator>(Curr)->operands())
        if (Instruction *OPI = dyn_cast<Instruction>(Op))
          if (SimpleValue::canHandle(OPI) && Visited.insert(OPI).second)
            WorkList.push_back(OPI);
  }

  return MadeChanges;
}

bool EarlyCSE::processNode(DomTreeNode *Node) {
  bool Changed = false;
  BasicBlock *BB = Node->getBlock();

  // If this block has a single predecessor, then the predecessor is the parent
  // of the domtree node and all of the live out memory values are still current
  // in this block.  If this block has multiple predecessors, then they could
  // have invalidated the live-out memory values of our parent value.  For now,
  // just be conservative and invalidate memory if this block has multiple
  // predecessors.
  if (!BB->getSinglePredecessor())
    ++CurrentGeneration;

  // If this node has a single predecessor which ends in a conditional branch,
  // we can infer the value of the branch condition given that we took this
  // path.  We need the single predecessor to ensure there's not another path
  // which reaches this block where the condition might hold a different
  // value.  Since we're adding this to the scoped hash table (like any other
  // def), it will have been popped if we encounter a future merge block.
  if (BasicBlock *Pred = BB->getSinglePredecessor()) {
    auto *BI = dyn_cast<BranchInst>(Pred->getTerminator());
    if (BI && BI->isConditional()) {
      auto *CondInst = dyn_cast<Instruction>(BI->getCondition());
      if (CondInst && SimpleValue::canHandle(CondInst))
        Changed |= handleBranchCondition(CondInst, BI, BB, Pred);
    }
  }

  /// LastStore - Keep track of the last non-volatile store that we saw... for
  /// as long as there in no instruction that reads memory.  If we see a store
  /// to the same location, we delete the dead store.  This zaps trivial dead
  /// stores which can occur in bitfield code among other things.
  Instruction *LastStore = nullptr;

  // See if any instructions in the block can be eliminated.  If so, do it.  If
  // not, add them to AvailableValues.
  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) {
    Instruction *Inst = &*I++;

    // Dead instructions should just be removed.
    if (isInstructionTriviallyDead(Inst, &TLI)) {
      LLVM_DEBUG(dbgs() << "EarlyCSE DCE: " << *Inst << '\n');
      if (!DebugCounter::shouldExecute(CSECounter)) {
        LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
        continue;
      }
      if (!salvageDebugInfo(*Inst))
        replaceDbgUsesWithUndef(Inst);
      removeMSSA(Inst);
      Inst->eraseFromParent();
      Changed = true;
      ++NumSimplify;
      continue;
    }

    // Skip assume intrinsics, they don't really have side effects (although
    // they're marked as such to ensure preservation of control dependencies),
    // and this pass will not bother with its removal. However, we should mark
    // its condition as true for all dominated blocks.
    if (match(Inst, m_Intrinsic<Intrinsic::assume>())) {
      auto *CondI =
          dyn_cast<Instruction>(cast<CallInst>(Inst)->getArgOperand(0));
      if (CondI && SimpleValue::canHandle(CondI)) {
        LLVM_DEBUG(dbgs() << "EarlyCSE considering assumption: " << *Inst
                          << '\n');
        AvailableValues.insert(CondI, ConstantInt::getTrue(BB->getContext()));
      } else
        LLVM_DEBUG(dbgs() << "EarlyCSE skipping assumption: " << *Inst << '\n');
      continue;
    }

    // Skip sideeffect intrinsics, for the same reason as assume intrinsics.
    if (match(Inst, m_Intrinsic<Intrinsic::sideeffect>())) {
      LLVM_DEBUG(dbgs() << "EarlyCSE skipping sideeffect: " << *Inst << '\n');
      continue;
    }

    // We can skip all invariant.start intrinsics since they only read memory,
    // and we can forward values across it. For invariant starts without
    // invariant ends, we can use the fact that the invariantness never ends to
    // start a scope in the current generaton which is true for all future
    // generations.  Also, we dont need to consume the last store since the
    // semantics of invariant.start allow us to perform   DSE of the last
    // store, if there was a store following invariant.start. Consider:
    //
    // store 30, i8* p
    // invariant.start(p)
    // store 40, i8* p
    // We can DSE the store to 30, since the store 40 to invariant location p
    // causes undefined behaviour.
    if (match(Inst, m_Intrinsic<Intrinsic::invariant_start>())) {
      // If there are any uses, the scope might end.
      if (!Inst->use_empty())
        continue;
      auto *CI = cast<CallInst>(Inst);
      MemoryLocation MemLoc = MemoryLocation::getForArgument(CI, 1, TLI);
      // Don't start a scope if we already have a better one pushed
      if (!AvailableInvariants.count(MemLoc))
        AvailableInvariants.insert(MemLoc, CurrentGeneration);
      continue;
    }

    if (isGuard(Inst)) {
      if (auto *CondI =
              dyn_cast<Instruction>(cast<CallInst>(Inst)->getArgOperand(0))) {
        if (SimpleValue::canHandle(CondI)) {
          // Do we already know the actual value of this condition?
          if (auto *KnownCond = AvailableValues.lookup(CondI)) {
            // Is the condition known to be true?
            if (isa<ConstantInt>(KnownCond) &&
                cast<ConstantInt>(KnownCond)->isOne()) {
              LLVM_DEBUG(dbgs()
                         << "EarlyCSE removing guard: " << *Inst << '\n');
              removeMSSA(Inst);
              Inst->eraseFromParent();
              Changed = true;
              continue;
            } else
              // Use the known value if it wasn't true.
              cast<CallInst>(Inst)->setArgOperand(0, KnownCond);
          }
          // The condition we're on guarding here is true for all dominated
          // locations.
          AvailableValues.insert(CondI, ConstantInt::getTrue(BB->getContext()));
        }
      }

      // Guard intrinsics read all memory, but don't write any memory.
      // Accordingly, don't update the generation but consume the last store (to
      // avoid an incorrect DSE).
      LastStore = nullptr;
      continue;
    }

    // If the instruction can be simplified (e.g. X+0 = X) then replace it with
    // its simpler value.
    if (Value *V = SimplifyInstruction(Inst, SQ)) {
      LLVM_DEBUG(dbgs() << "EarlyCSE Simplify: " << *Inst << "  to: " << *V
                        << '\n');
      if (!DebugCounter::shouldExecute(CSECounter)) {
        LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
      } else {
        bool Killed = false;
        if (!Inst->use_empty()) {
          Inst->replaceAllUsesWith(V);
          Changed = true;
        }
        if (isInstructionTriviallyDead(Inst, &TLI)) {
          removeMSSA(Inst);
          Inst->eraseFromParent();
          Changed = true;
          Killed = true;
        }
        if (Changed)
          ++NumSimplify;
        if (Killed)
          continue;
      }
    }

    // If this is a simple instruction that we can value number, process it.
    if (SimpleValue::canHandle(Inst)) {
      // See if the instruction has an available value.  If so, use it.
      if (Value *V = AvailableValues.lookup(Inst)) {
        LLVM_DEBUG(dbgs() << "EarlyCSE CSE: " << *Inst << "  to: " << *V
                          << '\n');
        if (!DebugCounter::shouldExecute(CSECounter)) {
          LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
          continue;
        }
        if (auto *I = dyn_cast<Instruction>(V))
          I->andIRFlags(Inst);
        Inst->replaceAllUsesWith(V);
        removeMSSA(Inst);
        Inst->eraseFromParent();
        Changed = true;
        ++NumCSE;
        continue;
      }

      // Otherwise, just remember that this value is available.
      AvailableValues.insert(Inst, Inst);
      continue;
    }

    ParseMemoryInst MemInst(Inst, TTI);
    // If this is a non-volatile load, process it.
    if (MemInst.isValid() && MemInst.isLoad()) {
      // (conservatively) we can't peak past the ordering implied by this
      // operation, but we can add this load to our set of available values
      if (MemInst.isVolatile() || !MemInst.isUnordered()) {
        LastStore = nullptr;
        ++CurrentGeneration;
      }

      if (MemInst.isInvariantLoad()) {
        // If we pass an invariant load, we know that memory location is
        // indefinitely constant from the moment of first dereferenceability.
        // We conservatively treat the invariant_load as that moment.  If we
        // pass a invariant load after already establishing a scope, don't
        // restart it since we want to preserve the earliest point seen.
        auto MemLoc = MemoryLocation::get(Inst);
        if (!AvailableInvariants.count(MemLoc))
          AvailableInvariants.insert(MemLoc, CurrentGeneration);
      }

      // If we have an available version of this load, and if it is the right
      // generation or the load is known to be from an invariant location,
      // replace this instruction.
      //
      // If either the dominating load or the current load are invariant, then
      // we can assume the current load loads the same value as the dominating
      // load.
      LoadValue InVal = AvailableLoads.lookup(MemInst.getPointerOperand());
      if (InVal.DefInst != nullptr &&
          InVal.MatchingId == MemInst.getMatchingId() &&
          // We don't yet handle removing loads with ordering of any kind.
          !MemInst.isVolatile() && MemInst.isUnordered() &&
          // We can't replace an atomic load with one which isn't also atomic.
          InVal.IsAtomic >= MemInst.isAtomic() &&
          (isOperatingOnInvariantMemAt(Inst, InVal.Generation) ||
           isSameMemGeneration(InVal.Generation, CurrentGeneration,
                               InVal.DefInst, Inst))) {
        Value *Op = getOrCreateResult(InVal.DefInst, Inst->getType());
        if (Op != nullptr) {
          LLVM_DEBUG(dbgs() << "EarlyCSE CSE LOAD: " << *Inst
                            << "  to: " << *InVal.DefInst << '\n');
          if (!DebugCounter::shouldExecute(CSECounter)) {
            LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
            continue;
          }
          if (!Inst->use_empty())
            Inst->replaceAllUsesWith(Op);
          removeMSSA(Inst);
          Inst->eraseFromParent();
          Changed = true;
          ++NumCSELoad;
          continue;
        }
      }

      // Otherwise, remember that we have this instruction.
      AvailableLoads.insert(
          MemInst.getPointerOperand(),
          LoadValue(Inst, CurrentGeneration, MemInst.getMatchingId(),
                    MemInst.isAtomic()));
      LastStore = nullptr;
      continue;
    }

    // If this instruction may read from memory or throw (and potentially read
    // from memory in the exception handler), forget LastStore.  Load/store
    // intrinsics will indicate both a read and a write to memory.  The target
    // may override this (e.g. so that a store intrinsic does not read from
    // memory, and thus will be treated the same as a regular store for
    // commoning purposes).
    if ((Inst->mayReadFromMemory() || Inst->mayThrow()) &&
        !(MemInst.isValid() && !MemInst.mayReadFromMemory()))
      LastStore = nullptr;

    // If this is a read-only call, process it.
    if (CallValue::canHandle(Inst)) {
      // If we have an available version of this call, and if it is the right
      // generation, replace this instruction.
      std::pair<Instruction *, unsigned> InVal = AvailableCalls.lookup(Inst);
      if (InVal.first != nullptr &&
          isSameMemGeneration(InVal.second, CurrentGeneration, InVal.first,
                              Inst)) {
        LLVM_DEBUG(dbgs() << "EarlyCSE CSE CALL: " << *Inst
                          << "  to: " << *InVal.first << '\n');
        if (!DebugCounter::shouldExecute(CSECounter)) {
          LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
          continue;
        }
        if (!Inst->use_empty())
          Inst->replaceAllUsesWith(InVal.first);
        removeMSSA(Inst);
        Inst->eraseFromParent();
        Changed = true;
        ++NumCSECall;
        continue;
      }

      // Otherwise, remember that we have this instruction.
      AvailableCalls.insert(
          Inst, std::pair<Instruction *, unsigned>(Inst, CurrentGeneration));
      continue;
    }

    // A release fence requires that all stores complete before it, but does
    // not prevent the reordering of following loads 'before' the fence.  As a
    // result, we don't need to consider it as writing to memory and don't need
    // to advance the generation.  We do need to prevent DSE across the fence,
    // but that's handled above.
    if (FenceInst *FI = dyn_cast<FenceInst>(Inst))
      if (FI->getOrdering() == AtomicOrdering::Release) {
        assert(Inst->mayReadFromMemory() && "relied on to prevent DSE above");
        continue;
      }

    // write back DSE - If we write back the same value we just loaded from
    // the same location and haven't passed any intervening writes or ordering
    // operations, we can remove the write.  The primary benefit is in allowing
    // the available load table to remain valid and value forward past where
    // the store originally was.
    if (MemInst.isValid() && MemInst.isStore()) {
      LoadValue InVal = AvailableLoads.lookup(MemInst.getPointerOperand());
      if (InVal.DefInst &&
          InVal.DefInst == getOrCreateResult(Inst, InVal.DefInst->getType()) &&
          InVal.MatchingId == MemInst.getMatchingId() &&
          // We don't yet handle removing stores with ordering of any kind.
          !MemInst.isVolatile() && MemInst.isUnordered() &&
          (isOperatingOnInvariantMemAt(Inst, InVal.Generation) ||
           isSameMemGeneration(InVal.Generation, CurrentGeneration,
                               InVal.DefInst, Inst))) {
        // It is okay to have a LastStore to a different pointer here if MemorySSA
        // tells us that the load and store are from the same memory generation.
        // In that case, LastStore should keep its present value since we're
        // removing the current store.
        assert((!LastStore ||
                ParseMemoryInst(LastStore, TTI).getPointerOperand() ==
                    MemInst.getPointerOperand() ||
                MSSA) &&
               "can't have an intervening store if not using MemorySSA!");
        LLVM_DEBUG(dbgs() << "EarlyCSE DSE (writeback): " << *Inst << '\n');
        if (!DebugCounter::shouldExecute(CSECounter)) {
          LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
          continue;
        }
        removeMSSA(Inst);
        Inst->eraseFromParent();
        Changed = true;
        ++NumDSE;
        // We can avoid incrementing the generation count since we were able
        // to eliminate this store.
        continue;
      }
    }

    // Okay, this isn't something we can CSE at all.  Check to see if it is
    // something that could modify memory.  If so, our available memory values
    // cannot be used so bump the generation count.
    if (Inst->mayWriteToMemory()) {
      ++CurrentGeneration;

      if (MemInst.isValid() && MemInst.isStore()) {
        // We do a trivial form of DSE if there are two stores to the same
        // location with no intervening loads.  Delete the earlier store.
        // At the moment, we don't remove ordered stores, but do remove
        // unordered atomic stores.  There's no special requirement (for
        // unordered atomics) about removing atomic stores only in favor of
        // other atomic stores since we were going to execute the non-atomic
        // one anyway and the atomic one might never have become visible.
        if (LastStore) {
          ParseMemoryInst LastStoreMemInst(LastStore, TTI);
          assert(LastStoreMemInst.isUnordered() &&
                 !LastStoreMemInst.isVolatile() &&
                 "Violated invariant");
          if (LastStoreMemInst.isMatchingMemLoc(MemInst)) {
            LLVM_DEBUG(dbgs() << "EarlyCSE DEAD STORE: " << *LastStore
                              << "  due to: " << *Inst << '\n');
            if (!DebugCounter::shouldExecute(CSECounter)) {
              LLVM_DEBUG(dbgs() << "Skipping due to debug counter\n");
            } else {
              removeMSSA(LastStore);
              LastStore->eraseFromParent();
              Changed = true;
              ++NumDSE;
              LastStore = nullptr;
            }
          }
          // fallthrough - we can exploit information about this store
        }

        // Okay, we just invalidated anything we knew about loaded values.  Try
        // to salvage *something* by remembering that the stored value is a live
        // version of the pointer.  It is safe to forward from volatile stores
        // to non-volatile loads, so we don't have to check for volatility of
        // the store.
        AvailableLoads.insert(
            MemInst.getPointerOperand(),
            LoadValue(Inst, CurrentGeneration, MemInst.getMatchingId(),
                      MemInst.isAtomic()));

        // Remember that this was the last unordered store we saw for DSE. We
        // don't yet handle DSE on ordered or volatile stores since we don't
        // have a good way to model the ordering requirement for following
        // passes  once the store is removed.  We could insert a fence, but
        // since fences are slightly stronger than stores in their ordering,
        // it's not clear this is a profitable transform. Another option would
        // be to merge the ordering with that of the post dominating store.
        if (MemInst.isUnordered() && !MemInst.isVolatile())
          LastStore = Inst;
        else
          LastStore = nullptr;
      }
    }
  }

  return Changed;
}

bool EarlyCSE::run() {
  // Note, deque is being used here because there is significant performance
  // gains over vector when the container becomes very large due to the
  // specific access patterns. For more information see the mailing list
  // discussion on this:
  // http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20120116/135228.html
  std::deque<StackNode *> nodesToProcess;

  bool Changed = false;

  // Process the root node.
  nodesToProcess.push_back(new StackNode(
      AvailableValues, AvailableLoads, AvailableInvariants, AvailableCalls,
      CurrentGeneration, DT.getRootNode(),
      DT.getRootNode()->begin(), DT.getRootNode()->end()));

  assert(!CurrentGeneration && "Create a new EarlyCSE instance to rerun it.");

  // Process the stack.
  while (!nodesToProcess.empty()) {
    // Grab the first item off the stack. Set the current generation, remove
    // the node from the stack, and process it.
    StackNode *NodeToProcess = nodesToProcess.back();

    // Initialize class members.
    CurrentGeneration = NodeToProcess->currentGeneration();

    // Check if the node needs to be processed.
    if (!NodeToProcess->isProcessed()) {
      // Process the node.
      Changed |= processNode(NodeToProcess->node());
      NodeToProcess->childGeneration(CurrentGeneration);
      NodeToProcess->process();
    } else if (NodeToProcess->childIter() != NodeToProcess->end()) {
      // Push the next child onto the stack.
      DomTreeNode *child = NodeToProcess->nextChild();
      nodesToProcess.push_back(
          new StackNode(AvailableValues, AvailableLoads, AvailableInvariants,
                        AvailableCalls, NodeToProcess->childGeneration(),
                        child, child->begin(), child->end()));
    } else {
      // It has been processed, and there are no more children to process,
      // so delete it and pop it off the stack.
      delete NodeToProcess;
      nodesToProcess.pop_back();
    }
  } // while (!nodes...)

  return Changed;
}

PreservedAnalyses EarlyCSEPass::run(Function &F,
                                    FunctionAnalysisManager &AM) {
  auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
  auto &TTI = AM.getResult<TargetIRAnalysis>(F);
  auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
  auto &AC = AM.getResult<AssumptionAnalysis>(F);
  auto *MSSA =
      UseMemorySSA ? &AM.getResult<MemorySSAAnalysis>(F).getMSSA() : nullptr;

  EarlyCSE CSE(F.getParent()->getDataLayout(), TLI, TTI, DT, AC, MSSA);

  if (!CSE.run())
    return PreservedAnalyses::all();

  PreservedAnalyses PA;
  PA.preserveSet<CFGAnalyses>();
  PA.preserve<GlobalsAA>();
  if (UseMemorySSA)
    PA.preserve<MemorySSAAnalysis>();
  return PA;
}

namespace {

/// A simple and fast domtree-based CSE pass.
///
/// This pass does a simple depth-first walk over the dominator tree,
/// eliminating trivially redundant instructions and using instsimplify to
/// canonicalize things as it goes. It is intended to be fast and catch obvious
/// cases so that instcombine and other passes are more effective. It is
/// expected that a later pass of GVN will catch the interesting/hard cases.
template<bool UseMemorySSA>
class EarlyCSELegacyCommonPass : public FunctionPass {
public:
  static char ID;

  EarlyCSELegacyCommonPass() : FunctionPass(ID) {
    if (UseMemorySSA)
      initializeEarlyCSEMemSSALegacyPassPass(*PassRegistry::getPassRegistry());
    else
      initializeEarlyCSELegacyPassPass(*PassRegistry::getPassRegistry());
  }

  bool runOnFunction(Function &F) override {
    if (skipFunction(F))
      return false;

    auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
    auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
    auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
    auto *MSSA =
        UseMemorySSA ? &getAnalysis<MemorySSAWrapperPass>().getMSSA() : nullptr;

    EarlyCSE CSE(F.getParent()->getDataLayout(), TLI, TTI, DT, AC, MSSA);

    return CSE.run();
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<AssumptionCacheTracker>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<TargetLibraryInfoWrapperPass>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    if (UseMemorySSA) {
      AU.addRequired<MemorySSAWrapperPass>();
      AU.addPreserved<MemorySSAWrapperPass>();
    }
    AU.addPreserved<GlobalsAAWrapperPass>();
    AU.setPreservesCFG();
  }
};

} // end anonymous namespace

using EarlyCSELegacyPass = EarlyCSELegacyCommonPass</*UseMemorySSA=*/false>;

template<>
char EarlyCSELegacyPass::ID = 0;

INITIALIZE_PASS_BEGIN(EarlyCSELegacyPass, "early-cse", "Early CSE", false,
                      false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(EarlyCSELegacyPass, "early-cse", "Early CSE", false, false)

using EarlyCSEMemSSALegacyPass =
    EarlyCSELegacyCommonPass</*UseMemorySSA=*/true>;

template<>
char EarlyCSEMemSSALegacyPass::ID = 0;

FunctionPass *llvm::createEarlyCSEPass(bool UseMemorySSA) {
  if (UseMemorySSA)
    return new EarlyCSEMemSSALegacyPass();
  else
    return new EarlyCSELegacyPass();
}

INITIALIZE_PASS_BEGIN(EarlyCSEMemSSALegacyPass, "early-cse-memssa",
                      "Early CSE w/ MemorySSA", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
INITIALIZE_PASS_END(EarlyCSEMemSSALegacyPass, "early-cse-memssa",
                    "Early CSE w/ MemorySSA", false, false)