llvm.org GIT mirror llvm / 045a03d lib / Transforms / Scalar / LICM.cpp
045a03d

Tree @045a03d (Download .tar.gz)

LICM.cpp @045a03draw · 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
//===-- LICM.cpp - Loop Invariant Code Motion Pass ------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass performs loop invariant code motion, attempting to remove as much
// code from the body of a loop as possible.  It does this by either hoisting
// code into the preheader block, or by sinking code to the exit blocks if it is
// safe.  This pass also promotes must-aliased memory locations in the loop to
// live in registers, thus hoisting and sinking "invariant" loads and stores.
//
// This pass uses alias analysis for two purposes:
//
//  1. Moving loop invariant loads and calls out of loops.  If we can determine
//     that a load or call inside of a loop never aliases anything stored to,
//     we can hoist it or sink it like any other instruction.
//  2. Scalar Promotion of Memory - If there is a store instruction inside of
//     the loop, we try to move the store to happen AFTER the loop instead of
//     inside of the loop.  This can only happen if a few conditions are true:
//       A. The pointer stored through is loop invariant
//       B. There are no stores or loads in the loop which _may_ alias the
//          pointer.  There are no calls in the loop which mod/ref the pointer.
//     If these conditions are true, we can promote the loads and stores in the
//     loop of the pointer to use a temporary alloca'd variable.  We then use
//     the SSAUpdater to construct the appropriate SSA form for the value.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AliasSetTracker.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/CaptureTracking.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/Loads.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionAliasAnalysis.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/PredIteratorCache.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/SSAUpdater.h"
#include <algorithm>
using namespace llvm;

#define DEBUG_TYPE "licm"

STATISTIC(NumSunk      , "Number of instructions sunk out of loop");
STATISTIC(NumHoisted   , "Number of instructions hoisted out of loop");
STATISTIC(NumMovedLoads, "Number of load insts hoisted or sunk");
STATISTIC(NumMovedCalls, "Number of call insts hoisted or sunk");
STATISTIC(NumPromoted  , "Number of memory locations promoted to registers");

static cl::opt<bool>
DisablePromotion("disable-licm-promotion", cl::Hidden,
                 cl::desc("Disable memory promotion in LICM pass"));

static bool inSubLoop(BasicBlock *BB, Loop *CurLoop, LoopInfo *LI);
static bool isNotUsedInLoop(const Instruction &I, const Loop *CurLoop,
                            const LICMSafetyInfo *SafetyInfo);
static bool hoist(Instruction &I, const DominatorTree *DT, const Loop *CurLoop,
                  const LICMSafetyInfo *SafetyInfo);
static bool sink(Instruction &I, const LoopInfo *LI, const DominatorTree *DT,
                 const Loop *CurLoop, AliasSetTracker *CurAST,
                 const LICMSafetyInfo *SafetyInfo);
static bool isGuaranteedToExecute(const Instruction &Inst,
                                  const DominatorTree *DT,
                                  const Loop *CurLoop,
                                  const LICMSafetyInfo *SafetyInfo);
static bool isSafeToExecuteUnconditionally(const Instruction &Inst,
                                           const DominatorTree *DT,
                                           const TargetLibraryInfo *TLI,
                                           const Loop *CurLoop,
                                           const LICMSafetyInfo *SafetyInfo,
                                           const Instruction *CtxI = nullptr);
static bool pointerInvalidatedByLoop(Value *V, uint64_t Size,
                                     const AAMDNodes &AAInfo, 
                                     AliasSetTracker *CurAST);
static Instruction *
CloneInstructionInExitBlock(Instruction &I, BasicBlock &ExitBlock, PHINode &PN,
                            const LoopInfo *LI,
                            const LICMSafetyInfo *SafetyInfo);
static bool canSinkOrHoistInst(Instruction &I, AliasAnalysis *AA,
                               DominatorTree *DT, TargetLibraryInfo *TLI,
                               Loop *CurLoop, AliasSetTracker *CurAST,
                               LICMSafetyInfo *SafetyInfo);

namespace {
  struct LICM : public LoopPass {
    static char ID; // Pass identification, replacement for typeid
    LICM() : LoopPass(ID) {
      initializeLICMPass(*PassRegistry::getPassRegistry());
    }

    bool runOnLoop(Loop *L, LPPassManager &LPM) override;

    /// This transformation requires natural loop information & requires that
    /// loop preheaders be inserted into the CFG...
    ///
    void getAnalysisUsage(AnalysisUsage &AU) const override {
      AU.setPreservesCFG();
      AU.addRequired<TargetLibraryInfoWrapperPass>();
      getLoopAnalysisUsage(AU);
    }

    using llvm::Pass::doFinalization;

    bool doFinalization() override {
      assert(LoopToAliasSetMap.empty() && "Didn't free loop alias sets");
      return false;
    }

  private:
    AliasAnalysis *AA;       // Current AliasAnalysis information
    LoopInfo      *LI;       // Current LoopInfo
    DominatorTree *DT;       // Dominator Tree for the current Loop.

    TargetLibraryInfo *TLI;  // TargetLibraryInfo for constant folding.

    // State that is updated as we process loops.
    bool Changed;            // Set to true when we change anything.
    BasicBlock *Preheader;   // The preheader block of the current loop...
    Loop *CurLoop;           // The current loop we are working on...
    AliasSetTracker *CurAST; // AliasSet information for the current loop...
    DenseMap<Loop*, AliasSetTracker*> LoopToAliasSetMap;

    /// cloneBasicBlockAnalysis - Simple Analysis hook. Clone alias set info.
    void cloneBasicBlockAnalysis(BasicBlock *From, BasicBlock *To,
                                 Loop *L) override;

    /// deleteAnalysisValue - Simple Analysis hook. Delete value V from alias
    /// set.
    void deleteAnalysisValue(Value *V, Loop *L) override;

    /// Simple Analysis hook. Delete loop L from alias set map.
    void deleteAnalysisLoop(Loop *L) override;

    AliasSetTracker *collectAliasInfoForLoop(Loop *L);
  };
}

char LICM::ID = 0;
INITIALIZE_PASS_BEGIN(LICM, "licm", "Loop Invariant Code Motion", false, false)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(LICM, "licm", "Loop Invariant Code Motion", false, false)

Pass *llvm::createLICMPass() { return new LICM(); }

/// Hoist expressions out of the specified loop. Note, alias info for inner
/// loop is not preserved so it is not a good idea to run LICM multiple
/// times on one loop.
///
bool LICM::runOnLoop(Loop *L, LPPassManager &LPM) {
  if (skipLoop(L))
    return false;

  Changed = false;

  // Get our Loop and Alias Analysis information...
  LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
  DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();

  TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();

  assert(L->isLCSSAForm(*DT) && "Loop is not in LCSSA form.");

  CurAST = collectAliasInfoForLoop(L);

  CurLoop = L;

  // Get the preheader block to move instructions into...
  Preheader = L->getLoopPreheader();

  // Compute loop safety information.
  LICMSafetyInfo SafetyInfo;
  computeLICMSafetyInfo(&SafetyInfo, CurLoop);

  // We want to visit all of the instructions in this loop... that are not parts
  // of our subloops (they have already had their invariants hoisted out of
  // their loop, into this loop, so there is no need to process the BODIES of
  // the subloops).
  //
  // Traverse the body of the loop in depth first order on the dominator tree so
  // that we are guaranteed to see definitions before we see uses.  This allows
  // us to sink instructions in one pass, without iteration.  After sinking
  // instructions, we perform another pass to hoist them out of the loop.
  //
  if (L->hasDedicatedExits())
    Changed |= sinkRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI, CurLoop,
                          CurAST, &SafetyInfo);
  if (Preheader)
    Changed |= hoistRegion(DT->getNode(L->getHeader()), AA, LI, DT, TLI,
                           CurLoop, CurAST, &SafetyInfo);

  // Now that all loop invariants have been removed from the loop, promote any
  // memory references to scalars that we can.
  if (!DisablePromotion && (Preheader || L->hasDedicatedExits())) {
    SmallVector<BasicBlock *, 8> ExitBlocks;
    SmallVector<Instruction *, 8> InsertPts;
    PredIteratorCache PIC;

    // Loop over all of the alias sets in the tracker object.
    for (AliasSet &AS : *CurAST)
      Changed |= promoteLoopAccessesToScalars(AS, ExitBlocks, InsertPts,
                                              PIC, LI, DT, TLI, CurLoop,
                                              CurAST, &SafetyInfo);

    // Once we have promoted values across the loop body we have to recursively
    // reform LCSSA as any nested loop may now have values defined within the
    // loop used in the outer loop.
    // FIXME: This is really heavy handed. It would be a bit better to use an
    // SSAUpdater strategy during promotion that was LCSSA aware and reformed
    // it as it went.
    if (Changed) {
      auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>();
      formLCSSARecursively(*L, *DT, LI, SEWP ? &SEWP->getSE() : nullptr);
    }
  }

  // Check that neither this loop nor its parent have had LCSSA broken. LICM is
  // specifically moving instructions across the loop boundary and so it is
  // especially in need of sanity checking here.
  assert(L->isLCSSAForm(*DT) && "Loop not left in LCSSA form after LICM!");
  assert((!L->getParentLoop() || L->getParentLoop()->isLCSSAForm(*DT)) &&
         "Parent loop not left in LCSSA form after LICM!");

  // Clear out loops state information for the next iteration
  CurLoop = nullptr;
  Preheader = nullptr;

  // If this loop is nested inside of another one, save the alias information
  // for when we process the outer loop.
  if (L->getParentLoop())
    LoopToAliasSetMap[L] = CurAST;
  else
    delete CurAST;
  return Changed;
}

/// Walk the specified region of the CFG (defined by all blocks dominated by
/// the specified block, and that are in the current loop) in reverse depth 
/// first order w.r.t the DominatorTree.  This allows us to visit uses before
/// definitions, allowing us to sink a loop body in one pass without iteration.
///
bool llvm::sinkRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
                      DominatorTree *DT, TargetLibraryInfo *TLI, Loop *CurLoop,
                      AliasSetTracker *CurAST, LICMSafetyInfo *SafetyInfo) {

  // Verify inputs.
  assert(N != nullptr && AA != nullptr && LI != nullptr && 
         DT != nullptr && CurLoop != nullptr && CurAST != nullptr && 
         SafetyInfo != nullptr && "Unexpected input to sinkRegion");

  BasicBlock *BB = N->getBlock();
  // If this subregion is not in the top level loop at all, exit.
  if (!CurLoop->contains(BB)) return false;

  // We are processing blocks in reverse dfo, so process children first.
  bool Changed = false;
  const std::vector<DomTreeNode*> &Children = N->getChildren();
  for (DomTreeNode *Child : Children)
    Changed |= sinkRegion(Child, AA, LI, DT, TLI, CurLoop, CurAST, SafetyInfo);

  // Only need to process the contents of this block if it is not part of a
  // subloop (which would already have been processed).
  if (inSubLoop(BB,CurLoop,LI)) return Changed;

  for (BasicBlock::iterator II = BB->end(); II != BB->begin(); ) {
    Instruction &I = *--II;

    // If the instruction is dead, we would try to sink it because it isn't used
    // in the loop, instead, just delete it.
    if (isInstructionTriviallyDead(&I, TLI)) {
      DEBUG(dbgs() << "LICM deleting dead inst: " << I << '\n');
      ++II;
      CurAST->deleteValue(&I);
      I.eraseFromParent();
      Changed = true;
      continue;
    }

    // Check to see if we can sink this instruction to the exit blocks
    // of the loop.  We can do this if the all users of the instruction are
    // outside of the loop.  In this case, it doesn't even matter if the
    // operands of the instruction are loop invariant.
    //
    if (isNotUsedInLoop(I, CurLoop, SafetyInfo) &&
        canSinkOrHoistInst(I, AA, DT, TLI, CurLoop, CurAST, SafetyInfo)) {
      ++II;
      Changed |= sink(I, LI, DT, CurLoop, CurAST, SafetyInfo);
    }
  }
  return Changed;
}

/// Walk the specified region of the CFG (defined by all blocks dominated by
/// the specified block, and that are in the current loop) in depth first
/// order w.r.t the DominatorTree.  This allows us to visit definitions before
/// uses, allowing us to hoist a loop body in one pass without iteration.
///
bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
                       DominatorTree *DT, TargetLibraryInfo *TLI, Loop *CurLoop,
                       AliasSetTracker *CurAST, LICMSafetyInfo *SafetyInfo) {
  // Verify inputs.
  assert(N != nullptr && AA != nullptr && LI != nullptr && 
         DT != nullptr && CurLoop != nullptr && CurAST != nullptr && 
         SafetyInfo != nullptr && "Unexpected input to hoistRegion");

  BasicBlock *BB = N->getBlock();

  // If this subregion is not in the top level loop at all, exit.
  if (!CurLoop->contains(BB)) return false;

  // Only need to process the contents of this block if it is not part of a
  // subloop (which would already have been processed).
  bool Changed = false;
  if (!inSubLoop(BB, CurLoop, LI))
    for (BasicBlock::iterator II = BB->begin(), E = BB->end(); II != E; ) {
      Instruction &I = *II++;
      // Try constant folding this instruction.  If all the operands are
      // constants, it is technically hoistable, but it would be better to just
      // fold it.
      if (Constant *C = ConstantFoldInstruction(
              &I, I.getModule()->getDataLayout(), TLI)) {
        DEBUG(dbgs() << "LICM folding inst: " << I << "  --> " << *C << '\n');
        CurAST->copyValue(&I, C);
        CurAST->deleteValue(&I);
        I.replaceAllUsesWith(C);
        I.eraseFromParent();
        continue;
      }

      // Try hoisting the instruction out to the preheader.  We can only do this
      // if all of the operands of the instruction are loop invariant and if it
      // is safe to hoist the instruction.
      //
      if (CurLoop->hasLoopInvariantOperands(&I) &&
          canSinkOrHoistInst(I, AA, DT, TLI, CurLoop, CurAST, SafetyInfo) &&
          isSafeToExecuteUnconditionally(I, DT, TLI, CurLoop, SafetyInfo,
                                 CurLoop->getLoopPreheader()->getTerminator()))
        Changed |= hoist(I, DT, CurLoop, SafetyInfo);
    }

  const std::vector<DomTreeNode*> &Children = N->getChildren();
  for (DomTreeNode *Child : Children)
    Changed |= hoistRegion(Child, AA, LI, DT, TLI, CurLoop, CurAST, SafetyInfo);
  return Changed;
}

/// Computes loop safety information, checks loop body & header
/// for the possibility of may throw exception.
///
void llvm::computeLICMSafetyInfo(LICMSafetyInfo * SafetyInfo, Loop * CurLoop) {
  assert(CurLoop != nullptr && "CurLoop cant be null");
  BasicBlock *Header = CurLoop->getHeader();
  // Setting default safety values.
  SafetyInfo->MayThrow = false;
  SafetyInfo->HeaderMayThrow = false;
  // Iterate over header and compute safety info.
  for (BasicBlock::iterator I = Header->begin(), E = Header->end();
       (I != E) && !SafetyInfo->HeaderMayThrow; ++I)
    SafetyInfo->HeaderMayThrow |= I->mayThrow();
  
  SafetyInfo->MayThrow = SafetyInfo->HeaderMayThrow;
  // Iterate over loop instructions and compute safety info. 
  for (Loop::block_iterator BB = CurLoop->block_begin(), 
       BBE = CurLoop->block_end(); (BB != BBE) && !SafetyInfo->MayThrow ; ++BB)
    for (BasicBlock::iterator I = (*BB)->begin(), E = (*BB)->end();
         (I != E) && !SafetyInfo->MayThrow; ++I)
      SafetyInfo->MayThrow |= I->mayThrow();

  // Compute funclet colors if we might sink/hoist in a function with a funclet
  // personality routine.
  Function *Fn = CurLoop->getHeader()->getParent();
  if (Fn->hasPersonalityFn())
    if (Constant *PersonalityFn = Fn->getPersonalityFn())
      if (isFuncletEHPersonality(classifyEHPersonality(PersonalityFn)))
        SafetyInfo->BlockColors = colorEHFunclets(*Fn);
}

/// canSinkOrHoistInst - Return true if the hoister and sinker can handle this
/// instruction.
///
bool canSinkOrHoistInst(Instruction &I, AliasAnalysis *AA, DominatorTree *DT,
                        TargetLibraryInfo *TLI, Loop *CurLoop,
                        AliasSetTracker *CurAST, LICMSafetyInfo *SafetyInfo) {
  // Loads have extra constraints we have to verify before we can hoist them.
  if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
    if (!LI->isUnordered())
      return false;        // Don't hoist volatile/atomic loads!

    // Loads from constant memory are always safe to move, even if they end up
    // in the same alias set as something that ends up being modified.
    if (AA->pointsToConstantMemory(LI->getOperand(0)))
      return true;
    if (LI->getMetadata(LLVMContext::MD_invariant_load))
      return true;

    // Don't hoist loads which have may-aliased stores in loop.
    uint64_t Size = 0;
    if (LI->getType()->isSized())
      Size = I.getModule()->getDataLayout().getTypeStoreSize(LI->getType());

    AAMDNodes AAInfo;
    LI->getAAMetadata(AAInfo);

    return !pointerInvalidatedByLoop(LI->getOperand(0), Size, AAInfo, CurAST);
  } else if (CallInst *CI = dyn_cast<CallInst>(&I)) {
    // Don't sink or hoist dbg info; it's legal, but not useful.
    if (isa<DbgInfoIntrinsic>(I))
      return false;

    // Don't sink calls which can throw.
    if (CI->mayThrow())
      return false;

    // Handle simple cases by querying alias analysis.
    FunctionModRefBehavior Behavior = AA->getModRefBehavior(CI);
    if (Behavior == FMRB_DoesNotAccessMemory)
      return true;
    if (AliasAnalysis::onlyReadsMemory(Behavior)) {
      // A readonly argmemonly function only reads from memory pointed to by
      // it's arguments with arbitrary offsets.  If we can prove there are no
      // writes to this memory in the loop, we can hoist or sink.
      if (AliasAnalysis::onlyAccessesArgPointees(Behavior)) {
        for (Value *Op : CI->arg_operands())
          if (Op->getType()->isPointerTy() &&
              pointerInvalidatedByLoop(Op, MemoryLocation::UnknownSize,
                                       AAMDNodes(), CurAST))
            return false;
        return true;
      }
      // If this call only reads from memory and there are no writes to memory
      // in the loop, we can hoist or sink the call as appropriate.
      bool FoundMod = false;
      for (AliasSet &AS : *CurAST) {
        if (!AS.isForwardingAliasSet() && AS.isMod()) {
          FoundMod = true;
          break;
        }
      }
      if (!FoundMod) return true;
    }

    // FIXME: This should use mod/ref information to see if we can hoist or
    // sink the call.

    return false;
  }

  // Only these instructions are hoistable/sinkable.
  if (!isa<BinaryOperator>(I) && !isa<CastInst>(I) && !isa<SelectInst>(I) &&
      !isa<GetElementPtrInst>(I) && !isa<CmpInst>(I) &&
      !isa<InsertElementInst>(I) && !isa<ExtractElementInst>(I) &&
      !isa<ShuffleVectorInst>(I) && !isa<ExtractValueInst>(I) &&
      !isa<InsertValueInst>(I))
    return false;

  // TODO: Plumb the context instruction through to make hoisting and sinking
  // more powerful. Hoisting of loads already works due to the special casing
  // above. 
  return isSafeToExecuteUnconditionally(I, DT, TLI, CurLoop, SafetyInfo,
                                        nullptr);
}

/// Returns true if a PHINode is a trivially replaceable with an
/// Instruction.
/// This is true when all incoming values are that instruction.
/// This pattern occurs most often with LCSSA PHI nodes.
///
static bool isTriviallyReplacablePHI(const PHINode &PN, const Instruction &I) {
  for (const Value *IncValue : PN.incoming_values())
    if (IncValue != &I)
      return false;

  return true;
}

/// Return true if the only users of this instruction are outside of
/// the loop. If this is true, we can sink the instruction to the exit
/// blocks of the loop.
///
static bool isNotUsedInLoop(const Instruction &I, const Loop *CurLoop,
                            const LICMSafetyInfo *SafetyInfo) {
  const auto &BlockColors = SafetyInfo->BlockColors;
  for (const User *U : I.users()) {
    const Instruction *UI = cast<Instruction>(U);
    if (const PHINode *PN = dyn_cast<PHINode>(UI)) {
      const BasicBlock *BB = PN->getParent();
      // We cannot sink uses in catchswitches.
      if (isa<CatchSwitchInst>(BB->getTerminator()))
        return false;

      // We need to sink a callsite to a unique funclet.  Avoid sinking if the
      // phi use is too muddled.
      if (isa<CallInst>(I))
        if (!BlockColors.empty() &&
            BlockColors.find(const_cast<BasicBlock *>(BB))->second.size() != 1)
          return false;

      // A PHI node where all of the incoming values are this instruction are
      // special -- they can just be RAUW'ed with the instruction and thus
      // don't require a use in the predecessor. This is a particular important
      // special case because it is the pattern found in LCSSA form.
      if (isTriviallyReplacablePHI(*PN, I)) {
        if (CurLoop->contains(PN))
          return false;
        else
          continue;
      }

      // Otherwise, PHI node uses occur in predecessor blocks if the incoming
      // values. Check for such a use being inside the loop.
      for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i)
        if (PN->getIncomingValue(i) == &I)
          if (CurLoop->contains(PN->getIncomingBlock(i)))
            return false;

      continue;
    }

    if (CurLoop->contains(UI))
      return false;
  }
  return true;
}

static Instruction *
CloneInstructionInExitBlock(Instruction &I, BasicBlock &ExitBlock, PHINode &PN,
                            const LoopInfo *LI,
                            const LICMSafetyInfo *SafetyInfo) {
  Instruction *New;
  if (auto *CI = dyn_cast<CallInst>(&I)) {
    const auto &BlockColors = SafetyInfo->BlockColors;

    // Sinking call-sites need to be handled differently from other
    // instructions.  The cloned call-site needs a funclet bundle operand
    // appropriate for it's location in the CFG.
    SmallVector<OperandBundleDef, 1> OpBundles;
    for (unsigned BundleIdx = 0, BundleEnd = CI->getNumOperandBundles();
         BundleIdx != BundleEnd; ++BundleIdx) {
      OperandBundleUse Bundle = CI->getOperandBundleAt(BundleIdx);
      if (Bundle.getTagID() == LLVMContext::OB_funclet)
        continue;

      OpBundles.emplace_back(Bundle);
    }

    if (!BlockColors.empty()) {
      const ColorVector &CV = BlockColors.find(&ExitBlock)->second;
      assert(CV.size() == 1 && "non-unique color for exit block!");
      BasicBlock *BBColor = CV.front();
      Instruction *EHPad = BBColor->getFirstNonPHI();
      if (EHPad->isEHPad())
        OpBundles.emplace_back("funclet", EHPad);
    }

    New = CallInst::Create(CI, OpBundles);
  } else {
    New = I.clone();
  }

  ExitBlock.getInstList().insert(ExitBlock.getFirstInsertionPt(), New);
  if (!I.getName().empty()) New->setName(I.getName() + ".le");

  // Build LCSSA PHI nodes for any in-loop operands. Note that this is
  // particularly cheap because we can rip off the PHI node that we're
  // replacing for the number and blocks of the predecessors.
  // OPT: If this shows up in a profile, we can instead finish sinking all
  // invariant instructions, and then walk their operands to re-establish
  // LCSSA. That will eliminate creating PHI nodes just to nuke them when
  // sinking bottom-up.
  for (User::op_iterator OI = New->op_begin(), OE = New->op_end(); OI != OE;
       ++OI)
    if (Instruction *OInst = dyn_cast<Instruction>(*OI))
      if (Loop *OLoop = LI->getLoopFor(OInst->getParent()))
        if (!OLoop->contains(&PN)) {
          PHINode *OpPN =
              PHINode::Create(OInst->getType(), PN.getNumIncomingValues(),
                              OInst->getName() + ".lcssa", &ExitBlock.front());
          for (unsigned i = 0, e = PN.getNumIncomingValues(); i != e; ++i)
            OpPN->addIncoming(OInst, PN.getIncomingBlock(i));
          *OI = OpPN;
        }
  return New;
}

/// When an instruction is found to only be used outside of the loop, this
/// function moves it to the exit blocks and patches up SSA form as needed.
/// This method is guaranteed to remove the original instruction from its
/// position, and may either delete it or move it to outside of the loop.
///
static bool sink(Instruction &I, const LoopInfo *LI, const DominatorTree *DT,
                 const Loop *CurLoop, AliasSetTracker *CurAST,
                 const LICMSafetyInfo *SafetyInfo) {
  DEBUG(dbgs() << "LICM sinking instruction: " << I << "\n");
  bool Changed = false;
  if (isa<LoadInst>(I)) ++NumMovedLoads;
  else if (isa<CallInst>(I)) ++NumMovedCalls;
  ++NumSunk;
  Changed = true;

#ifndef NDEBUG
  SmallVector<BasicBlock *, 32> ExitBlocks;
  CurLoop->getUniqueExitBlocks(ExitBlocks);
  SmallPtrSet<BasicBlock *, 32> ExitBlockSet(ExitBlocks.begin(), 
                                             ExitBlocks.end());
#endif

  // Clones of this instruction. Don't create more than one per exit block!
  SmallDenseMap<BasicBlock *, Instruction *, 32> SunkCopies;

  // If this instruction is only used outside of the loop, then all users are
  // PHI nodes in exit blocks due to LCSSA form. Just RAUW them with clones of
  // the instruction.
  while (!I.use_empty()) {
    Value::user_iterator UI = I.user_begin();
    auto *User = cast<Instruction>(*UI);
    if (!DT->isReachableFromEntry(User->getParent())) {
      User->replaceUsesOfWith(&I, UndefValue::get(I.getType()));
      continue;
    }
    // The user must be a PHI node.
    PHINode *PN = cast<PHINode>(User);

    // Surprisingly, instructions can be used outside of loops without any
    // exits.  This can only happen in PHI nodes if the incoming block is
    // unreachable.
    Use &U = UI.getUse();
    BasicBlock *BB = PN->getIncomingBlock(U);
    if (!DT->isReachableFromEntry(BB)) {
      U = UndefValue::get(I.getType());
      continue;
    }

    BasicBlock *ExitBlock = PN->getParent();
    assert(ExitBlockSet.count(ExitBlock) &&
           "The LCSSA PHI is not in an exit block!");

    Instruction *New;
    auto It = SunkCopies.find(ExitBlock);
    if (It != SunkCopies.end())
      New = It->second;
    else
      New = SunkCopies[ExitBlock] =
          CloneInstructionInExitBlock(I, *ExitBlock, *PN, LI, SafetyInfo);

    PN->replaceAllUsesWith(New);
    PN->eraseFromParent();
  }

  CurAST->deleteValue(&I);
  I.eraseFromParent();
  return Changed;
}

/// When an instruction is found to only use loop invariant operands that
/// is safe to hoist, this instruction is called to do the dirty work.
///
static bool hoist(Instruction &I, const DominatorTree *DT, const Loop *CurLoop,
                  const LICMSafetyInfo *SafetyInfo) {
  auto *Preheader = CurLoop->getLoopPreheader();
  DEBUG(dbgs() << "LICM hoisting to " << Preheader->getName() << ": "
        << I << "\n");

  // Metadata can be dependent on conditions we are hoisting above.
  // Conservatively strip all metadata on the instruction unless we were
  // guaranteed to execute I if we entered the loop, in which case the metadata
  // is valid in the loop preheader.
  if (I.hasMetadataOtherThanDebugLoc() &&
      // The check on hasMetadataOtherThanDebugLoc is to prevent us from burning
      // time in isGuaranteedToExecute if we don't actually have anything to
      // drop.  It is a compile time optimization, not required for correctness.
      !isGuaranteedToExecute(I, DT, CurLoop, SafetyInfo))
    I.dropUnknownNonDebugMetadata();

  // Move the new node to the Preheader, before its terminator.
  I.moveBefore(Preheader->getTerminator());

  if (isa<LoadInst>(I)) ++NumMovedLoads;
  else if (isa<CallInst>(I)) ++NumMovedCalls;
  ++NumHoisted;
  return true;
}

/// Only sink or hoist an instruction if it is not a trapping instruction,
/// or if the instruction is known not to trap when moved to the preheader.
/// or if it is a trapping instruction and is guaranteed to execute.
static bool isSafeToExecuteUnconditionally(const Instruction &Inst, 
                                           const DominatorTree *DT,
                                           const TargetLibraryInfo *TLI,
                                           const Loop *CurLoop,
                                           const LICMSafetyInfo *SafetyInfo,
                                           const Instruction *CtxI) {
  if (isSafeToSpeculativelyExecute(&Inst, CtxI, DT, TLI))
    return true;

  return isGuaranteedToExecute(Inst, DT, CurLoop, SafetyInfo);
}

static bool isGuaranteedToExecute(const Instruction &Inst,
                                  const DominatorTree *DT,
                                  const Loop *CurLoop,
                                  const LICMSafetyInfo * SafetyInfo) {

  // We have to check to make sure that the instruction dominates all
  // of the exit blocks.  If it doesn't, then there is a path out of the loop
  // which does not execute this instruction, so we can't hoist it.

  // If the instruction is in the header block for the loop (which is very
  // common), it is always guaranteed to dominate the exit blocks.  Since this
  // is a common case, and can save some work, check it now.
  if (Inst.getParent() == CurLoop->getHeader())
    // If there's a throw in the header block, we can't guarantee we'll reach
    // Inst.
    return !SafetyInfo->HeaderMayThrow;

  // Somewhere in this loop there is an instruction which may throw and make us
  // exit the loop.
  if (SafetyInfo->MayThrow)
    return false;

  // Get the exit blocks for the current loop.
  SmallVector<BasicBlock*, 8> ExitBlocks;
  CurLoop->getExitBlocks(ExitBlocks);

  // Verify that the block dominates each of the exit blocks of the loop.
  for (BasicBlock *ExitBlock : ExitBlocks)
    if (!DT->dominates(Inst.getParent(), ExitBlock))
      return false;

  // As a degenerate case, if the loop is statically infinite then we haven't
  // proven anything since there are no exit blocks.
  if (ExitBlocks.empty())
    return false;

  return true;
}

namespace {
  class LoopPromoter : public LoadAndStorePromoter {
    Value *SomePtr;  // Designated pointer to store to.
    SmallPtrSetImpl<Value*> &PointerMustAliases;
    SmallVectorImpl<BasicBlock*> &LoopExitBlocks;
    SmallVectorImpl<Instruction*> &LoopInsertPts;
    PredIteratorCache &PredCache;
    AliasSetTracker &AST;
    LoopInfo &LI;
    DebugLoc DL;
    int Alignment;
    AAMDNodes AATags;

    Value *maybeInsertLCSSAPHI(Value *V, BasicBlock *BB) const {
      if (Instruction *I = dyn_cast<Instruction>(V))
        if (Loop *L = LI.getLoopFor(I->getParent()))
          if (!L->contains(BB)) {
            // We need to create an LCSSA PHI node for the incoming value and
            // store that.
            PHINode *PN =
                PHINode::Create(I->getType(), PredCache.size(BB),
                                I->getName() + ".lcssa", &BB->front());
            for (BasicBlock *Pred : PredCache.get(BB))
              PN->addIncoming(I, Pred);
            return PN;
          }
      return V;
    }

  public:
    LoopPromoter(Value *SP,
                 ArrayRef<const Instruction *> Insts,
                 SSAUpdater &S, SmallPtrSetImpl<Value *> &PMA,
                 SmallVectorImpl<BasicBlock *> &LEB,
                 SmallVectorImpl<Instruction *> &LIP, PredIteratorCache &PIC,
                 AliasSetTracker &ast, LoopInfo &li, DebugLoc dl, int alignment,
                 const AAMDNodes &AATags)
        : LoadAndStorePromoter(Insts, S), SomePtr(SP), PointerMustAliases(PMA),
          LoopExitBlocks(LEB), LoopInsertPts(LIP), PredCache(PIC), AST(ast),
          LI(li), DL(dl), Alignment(alignment), AATags(AATags) {}

    bool isInstInList(Instruction *I,
                      const SmallVectorImpl<Instruction*> &) const override {
      Value *Ptr;
      if (LoadInst *LI = dyn_cast<LoadInst>(I))
        Ptr = LI->getOperand(0);
      else
        Ptr = cast<StoreInst>(I)->getPointerOperand();
      return PointerMustAliases.count(Ptr);
    }

    void doExtraRewritesBeforeFinalDeletion() const override {
      // Insert stores after in the loop exit blocks.  Each exit block gets a
      // store of the live-out values that feed them.  Since we've already told
      // the SSA updater about the defs in the loop and the preheader
      // definition, it is all set and we can start using it.
      for (unsigned i = 0, e = LoopExitBlocks.size(); i != e; ++i) {
        BasicBlock *ExitBlock = LoopExitBlocks[i];
        Value *LiveInValue = SSA.GetValueInMiddleOfBlock(ExitBlock);
        LiveInValue = maybeInsertLCSSAPHI(LiveInValue, ExitBlock);
        Value *Ptr = maybeInsertLCSSAPHI(SomePtr, ExitBlock);
        Instruction *InsertPos = LoopInsertPts[i];
        StoreInst *NewSI = new StoreInst(LiveInValue, Ptr, InsertPos);
        NewSI->setAlignment(Alignment);
        NewSI->setDebugLoc(DL);
        if (AATags) NewSI->setAAMetadata(AATags);
      }
    }

    void replaceLoadWithValue(LoadInst *LI, Value *V) const override {
      // Update alias analysis.
      AST.copyValue(LI, V);
    }
    void instructionDeleted(Instruction *I) const override {
      AST.deleteValue(I);
    }
  };
} // end anon namespace

/// Try to promote memory values to scalars by sinking stores out of the
/// loop and moving loads to before the loop.  We do this by looping over
/// the stores in the loop, looking for stores to Must pointers which are
/// loop invariant.
///
bool llvm::promoteLoopAccessesToScalars(AliasSet &AS,
                                        SmallVectorImpl<BasicBlock*>&ExitBlocks,
                                        SmallVectorImpl<Instruction*>&InsertPts,
                                        PredIteratorCache &PIC, LoopInfo *LI, 
                                        DominatorTree *DT,
                                        const TargetLibraryInfo *TLI,
                                        Loop *CurLoop,
                                        AliasSetTracker *CurAST, 
                                        LICMSafetyInfo * SafetyInfo) { 
  // Verify inputs.
  assert(LI != nullptr && DT != nullptr && 
         CurLoop != nullptr && CurAST != nullptr && 
         SafetyInfo != nullptr && 
         "Unexpected Input to promoteLoopAccessesToScalars");

  // We can promote this alias set if it has a store, if it is a "Must" alias
  // set, if the pointer is loop invariant, and if we are not eliminating any
  // volatile loads or stores.
  if (AS.isForwardingAliasSet() || !AS.isMod() || !AS.isMustAlias() ||
      AS.isVolatile() || !CurLoop->isLoopInvariant(AS.begin()->getValue()))
    return false;

  assert(!AS.empty() &&
         "Must alias set should have at least one pointer element in it!");

  Value *SomePtr = AS.begin()->getValue();
  BasicBlock * Preheader = CurLoop->getLoopPreheader();

  // It isn't safe to promote a load/store from the loop if the load/store is
  // conditional.  For example, turning:
  //
  //    for () { if (c) *P += 1; }
  //
  // into:
  //
  //    tmp = *P;  for () { if (c) tmp +=1; } *P = tmp;
  //
  // is not safe, because *P may only be valid to access if 'c' is true.
  //
  // The safety property divides into two parts:
  // 1) The memory may not be dereferenceable on entry to the loop.  In this
  //    case, we can't insert the required load in the preheader.
  // 2) The memory model does not allow us to insert a store along any dynamic
  //    path which did not originally have one.
  //
  // It is safe to promote P if all uses are direct load/stores and if at
  // least one is guaranteed to be executed.
  bool GuaranteedToExecute = false;

  // It is also safe to promote P if we can prove that speculating a load into
  // the preheader is safe (i.e. proving dereferenceability on all
  // paths through the loop), and that the memory can be proven thread local
  // (so that the memory model requirement doesn't apply.)  We first establish
  // the former, and then run a capture analysis below to establish the later.
  // We can use any access within the alias set to prove dereferenceability
  // since they're all must alias.
  bool CanSpeculateLoad = false;

  SmallVector<Instruction*, 64> LoopUses;
  SmallPtrSet<Value*, 4> PointerMustAliases;

  // We start with an alignment of one and try to find instructions that allow
  // us to prove better alignment.
  unsigned Alignment = 1;
  AAMDNodes AATags;
  bool HasDedicatedExits = CurLoop->hasDedicatedExits();

  // Don't sink stores from loops without dedicated block exits. Exits
  // containing indirect branches are not transformed by loop simplify,
  // make sure we catch that. An additional load may be generated in the
  // preheader for SSA updater, so also avoid sinking when no preheader
  // is available.
  if (!HasDedicatedExits || !Preheader)
    return false;
  
  const DataLayout &MDL = Preheader->getModule()->getDataLayout();

  // Check that all of the pointers in the alias set have the same type.  We
  // cannot (yet) promote a memory location that is loaded and stored in
  // different sizes.  While we are at it, collect alignment and AA info.
  bool Changed = false;
  for (AliasSet::iterator ASI = AS.begin(), E = AS.end(); ASI != E; ++ASI) {
    Value *ASIV = ASI->getValue();
    PointerMustAliases.insert(ASIV);

    // Check that all of the pointers in the alias set have the same type.  We
    // cannot (yet) promote a memory location that is loaded and stored in
    // different sizes.
    if (SomePtr->getType() != ASIV->getType())
      return Changed;

    for (User *U : ASIV->users()) {
      // Ignore instructions that are outside the loop.
      Instruction *UI = dyn_cast<Instruction>(U);
      if (!UI || !CurLoop->contains(UI))
        continue;

      // If there is an non-load/store instruction in the loop, we can't promote
      // it.
      if (const LoadInst *Load = dyn_cast<LoadInst>(UI)) {
        assert(!Load->isVolatile() && "AST broken");
        if (!Load->isSimple())
          return Changed;

        if (!GuaranteedToExecute && !CanSpeculateLoad)
          CanSpeculateLoad =
            isSafeToExecuteUnconditionally(*Load, DT, TLI, CurLoop,
                                           SafetyInfo,
                                           Preheader->getTerminator());
      } else if (const StoreInst *Store = dyn_cast<StoreInst>(UI)) {
        // Stores *of* the pointer are not interesting, only stores *to* the
        // pointer.
        if (UI->getOperand(1) != ASIV)
          continue;
        assert(!Store->isVolatile() && "AST broken");
        if (!Store->isSimple())
          return Changed;

        // Note that we only check GuaranteedToExecute inside the store case
        // so that we do not introduce stores where they did not exist before
        // (which would break the LLVM concurrency model).

        // If the alignment of this instruction allows us to specify a more
        // restrictive (and performant) alignment and if we are sure this
        // instruction will be executed, update the alignment.
        // Larger is better, with the exception of 0 being the best alignment.
        unsigned InstAlignment = Store->getAlignment();
        if ((InstAlignment > Alignment || InstAlignment == 0) && Alignment != 0)
          if (isGuaranteedToExecute(*UI, DT, CurLoop, SafetyInfo)) {
            GuaranteedToExecute = true;
            Alignment = InstAlignment;
          }

        if (!GuaranteedToExecute)
          GuaranteedToExecute = isGuaranteedToExecute(*UI, DT, 
                                                      CurLoop, SafetyInfo);


        if (!GuaranteedToExecute && !CanSpeculateLoad) {
          CanSpeculateLoad =
            isDereferenceableAndAlignedPointer(Store->getPointerOperand(),
                                               Store->getAlignment(), MDL,
                                               Preheader->getTerminator(),
                                               DT, TLI);
        }
      } else
        return Changed; // Not a load or store.

      // Merge the AA tags.
      if (LoopUses.empty()) {
        // On the first load/store, just take its AA tags.
        UI->getAAMetadata(AATags);
      } else if (AATags) {
        UI->getAAMetadata(AATags, /* Merge = */ true);
      }

      LoopUses.push_back(UI);
    }
  }

  // Check legality per comment above. Otherwise, we can't promote.
  bool PromotionIsLegal = GuaranteedToExecute;
  if (!PromotionIsLegal && CanSpeculateLoad) {
    // If this is a thread local location, then we can insert stores along
    // paths which originally didn't have them without violating the memory
    // model. 
    Value *Object = GetUnderlyingObject(SomePtr, MDL);
    PromotionIsLegal = isAllocLikeFn(Object, TLI) &&
      !PointerMayBeCaptured(Object, true, true);
  }
  if (!PromotionIsLegal)
    return Changed;

  // Figure out the loop exits and their insertion points, if this is the
  // first promotion.
  if (ExitBlocks.empty()) {
    CurLoop->getUniqueExitBlocks(ExitBlocks);
    InsertPts.clear();
    InsertPts.reserve(ExitBlocks.size());
    for (BasicBlock *ExitBlock : ExitBlocks)
      InsertPts.push_back(&*ExitBlock->getFirstInsertionPt());
  }

  // Can't insert into a catchswitch.
  for (BasicBlock *ExitBlock : ExitBlocks)
    if (isa<CatchSwitchInst>(ExitBlock->getTerminator()))
      return Changed;

  // Otherwise, this is safe to promote, lets do it!
  DEBUG(dbgs() << "LICM: Promoting value stored to in loop: " <<*SomePtr<<'\n');
  Changed = true;
  ++NumPromoted;

  // Grab a debug location for the inserted loads/stores; given that the
  // inserted loads/stores have little relation to the original loads/stores,
  // this code just arbitrarily picks a location from one, since any debug
  // location is better than none.
  DebugLoc DL = LoopUses[0]->getDebugLoc();

  // We use the SSAUpdater interface to insert phi nodes as required.
  SmallVector<PHINode*, 16> NewPHIs;
  SSAUpdater SSA(&NewPHIs);
  LoopPromoter Promoter(SomePtr, LoopUses, SSA,
                        PointerMustAliases, ExitBlocks,
                        InsertPts, PIC, *CurAST, *LI, DL, Alignment, AATags);

  // Set up the preheader to have a definition of the value.  It is the live-out
  // value from the preheader that uses in the loop will use.
  LoadInst *PreheaderLoad =
    new LoadInst(SomePtr, SomePtr->getName()+".promoted",
                 Preheader->getTerminator());
  PreheaderLoad->setAlignment(Alignment);
  PreheaderLoad->setDebugLoc(DL);
  if (AATags) PreheaderLoad->setAAMetadata(AATags);
  SSA.AddAvailableValue(Preheader, PreheaderLoad);

  // Rewrite all the loads in the loop and remember all the definitions from
  // stores in the loop.
  Promoter.run(LoopUses);

  // If the SSAUpdater didn't use the load in the preheader, just zap it now.
  if (PreheaderLoad->use_empty())
    PreheaderLoad->eraseFromParent();

  return Changed;
}

/// Returns an owning pointer to an alias set which incorporates aliasing info
/// from L and all subloops of L.
AliasSetTracker *LICM::collectAliasInfoForLoop(Loop *L) {
  AliasSetTracker *CurAST = nullptr;
  SmallVector<Loop *, 4> RecomputeLoops;
  for (Loop *InnerL : L->getSubLoops()) {
    auto MapI = LoopToAliasSetMap.find(InnerL);
    // If the AST for this inner loop is missing it may have been merged into
    // some other loop's AST and then that loop unrolled, and so we need to
    // recompute it.
    if (MapI == LoopToAliasSetMap.end()) {
      RecomputeLoops.push_back(InnerL);
      continue;
    }
    AliasSetTracker *InnerAST = MapI->second;

    if (CurAST != nullptr) {
      // What if InnerLoop was modified by other passes ?
      CurAST->add(*InnerAST);

      // Once we've incorporated the inner loop's AST into ours, we don't need
      // the subloop's anymore.
      delete InnerAST;
    } else {
      CurAST = InnerAST;
    }
    LoopToAliasSetMap.erase(MapI);
  }
  if (CurAST == nullptr)
    CurAST = new AliasSetTracker(*AA);

  auto mergeLoop = [&](Loop *L) {
    // Loop over the body of this loop, looking for calls, invokes, and stores.
    // Because subloops have already been incorporated into AST, we skip blocks
    // in subloops.
    for (BasicBlock *BB : L->blocks())
      if (LI->getLoopFor(BB) == L) // Ignore blocks in subloops.
        CurAST->add(*BB);          // Incorporate the specified basic block
  };

  // Add everything from the sub loops that are no longer directly available.
  for (Loop *InnerL : RecomputeLoops)
    mergeLoop(InnerL);

  // And merge in this loop.
  mergeLoop(L);

  return CurAST;
}

/// Simple analysis hook. Clone alias set info.
///
void LICM::cloneBasicBlockAnalysis(BasicBlock *From, BasicBlock *To, Loop *L) {
  AliasSetTracker *AST = LoopToAliasSetMap.lookup(L);
  if (!AST)
    return;

  AST->copyValue(From, To);
}

/// Simple Analysis hook. Delete value V from alias set
///
void LICM::deleteAnalysisValue(Value *V, Loop *L) {
  AliasSetTracker *AST = LoopToAliasSetMap.lookup(L);
  if (!AST)
    return;

  AST->deleteValue(V);
}

/// Simple Analysis hook. Delete value L from alias set map.
///
void LICM::deleteAnalysisLoop(Loop *L) {
  AliasSetTracker *AST = LoopToAliasSetMap.lookup(L);
  if (!AST)
    return;

  delete AST;
  LoopToAliasSetMap.erase(L);
}


/// Return true if the body of this loop may store into the memory
/// location pointed to by V.
///
static bool pointerInvalidatedByLoop(Value *V, uint64_t Size,
                                     const AAMDNodes &AAInfo, 
                                     AliasSetTracker *CurAST) {
  // Check to see if any of the basic blocks in CurLoop invalidate *V.
  return CurAST->getAliasSetForPointer(V, Size, AAInfo).isMod();
}

/// Little predicate that returns true if the specified basic block is in
/// a subloop of the current one, not the current one itself.
///
static bool inSubLoop(BasicBlock *BB, Loop *CurLoop, LoopInfo *LI) {
  assert(CurLoop->contains(BB) && "Only valid if BB is IN the loop");
  return LI->getLoopFor(BB) != CurLoop;
}