llvm.org GIT mirror llvm / 9f998de lib / CodeGen / MachineBlockPlacement.cpp
9f998de

Tree @9f998de (Download .tar.gz)

MachineBlockPlacement.cpp @9f998deraw · 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
//===-- MachineBlockPlacement.cpp - Basic Block Code Layout optimization --===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements basic block placement transformations using the CFG
// structure and branch probability estimates.
//
// The pass strives to preserve the structure of the CFG (that is, retain
// a topological ordering of basic blocks) in the absence of a *strong* signal
// to the contrary from probabilities. However, within the CFG structure, it
// attempts to choose an ordering which favors placing more likely sequences of
// blocks adjacent to each other.
//
// The algorithm works from the inner-most loop within a function outward, and
// at each stage walks through the basic blocks, trying to coalesce them into
// sequential chains where allowed by the CFG (or demanded by heavy
// probabilities). Finally, it walks the blocks in topological order, and the
// first time it reaches a chain of basic blocks, it schedules them in the
// function in-order.
//
//===----------------------------------------------------------------------===//

#define DEBUG_TYPE "block-placement2"
#include "llvm/CodeGen/Passes.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
#include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineLoopInfo.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/Support/Allocator.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/TargetInstrInfo.h"
#include "llvm/Target/TargetLowering.h"
#include <algorithm>
using namespace llvm;

STATISTIC(NumCondBranches, "Number of conditional branches");
STATISTIC(NumUncondBranches, "Number of uncondittional branches");
STATISTIC(CondBranchTakenFreq,
          "Potential frequency of taking conditional branches");
STATISTIC(UncondBranchTakenFreq,
          "Potential frequency of taking unconditional branches");

static cl::opt<unsigned> AlignAllBlock("align-all-blocks",
                                       cl::desc("Force the alignment of all "
                                                "blocks in the function."),
                                       cl::init(0), cl::Hidden);

// FIXME: Find a good default for this flag and remove the flag.
static cl::opt<unsigned>
ExitBlockBias("block-placement-exit-block-bias",
              cl::desc("Block frequency percentage a loop exit block needs "
                       "over the original exit to be considered the new exit."),
              cl::init(0), cl::Hidden);

namespace {
class BlockChain;
/// \brief Type for our function-wide basic block -> block chain mapping.
typedef DenseMap<MachineBasicBlock *, BlockChain *> BlockToChainMapType;
}

namespace {
/// \brief A chain of blocks which will be laid out contiguously.
///
/// This is the datastructure representing a chain of consecutive blocks that
/// are profitable to layout together in order to maximize fallthrough
/// probabilities and code locality. We also can use a block chain to represent
/// a sequence of basic blocks which have some external (correctness)
/// requirement for sequential layout.
///
/// Chains can be built around a single basic block and can be merged to grow
/// them. They participate in a block-to-chain mapping, which is updated
/// automatically as chains are merged together.
class BlockChain {
  /// \brief The sequence of blocks belonging to this chain.
  ///
  /// This is the sequence of blocks for a particular chain. These will be laid
  /// out in-order within the function.
  SmallVector<MachineBasicBlock *, 4> Blocks;

  /// \brief A handle to the function-wide basic block to block chain mapping.
  ///
  /// This is retained in each block chain to simplify the computation of child
  /// block chains for SCC-formation and iteration. We store the edges to child
  /// basic blocks, and map them back to their associated chains using this
  /// structure.
  BlockToChainMapType &BlockToChain;

public:
  /// \brief Construct a new BlockChain.
  ///
  /// This builds a new block chain representing a single basic block in the
  /// function. It also registers itself as the chain that block participates
  /// in with the BlockToChain mapping.
  BlockChain(BlockToChainMapType &BlockToChain, MachineBasicBlock *BB)
    : Blocks(1, BB), BlockToChain(BlockToChain), LoopPredecessors(0) {
    assert(BB && "Cannot create a chain with a null basic block");
    BlockToChain[BB] = this;
  }

  /// \brief Iterator over blocks within the chain.
  typedef SmallVectorImpl<MachineBasicBlock *>::iterator iterator;

  /// \brief Beginning of blocks within the chain.
  iterator begin() { return Blocks.begin(); }

  /// \brief End of blocks within the chain.
  iterator end() { return Blocks.end(); }

  /// \brief Merge a block chain into this one.
  ///
  /// This routine merges a block chain into this one. It takes care of forming
  /// a contiguous sequence of basic blocks, updating the edge list, and
  /// updating the block -> chain mapping. It does not free or tear down the
  /// old chain, but the old chain's block list is no longer valid.
  void merge(MachineBasicBlock *BB, BlockChain *Chain) {
    assert(BB);
    assert(!Blocks.empty());

    // Fast path in case we don't have a chain already.
    if (!Chain) {
      assert(!BlockToChain[BB]);
      Blocks.push_back(BB);
      BlockToChain[BB] = this;
      return;
    }

    assert(BB == *Chain->begin());
    assert(Chain->begin() != Chain->end());

    // Update the incoming blocks to point to this chain, and add them to the
    // chain structure.
    for (BlockChain::iterator BI = Chain->begin(), BE = Chain->end();
         BI != BE; ++BI) {
      Blocks.push_back(*BI);
      assert(BlockToChain[*BI] == Chain && "Incoming blocks not in chain");
      BlockToChain[*BI] = this;
    }
  }

#ifndef NDEBUG
  /// \brief Dump the blocks in this chain.
  LLVM_DUMP_METHOD void dump() {
    for (iterator I = begin(), E = end(); I != E; ++I)
      (*I)->dump();
  }
#endif // NDEBUG

  /// \brief Count of predecessors within the loop currently being processed.
  ///
  /// This count is updated at each loop we process to represent the number of
  /// in-loop predecessors of this chain.
  unsigned LoopPredecessors;
};
}

namespace {
class MachineBlockPlacement : public MachineFunctionPass {
  /// \brief A typedef for a block filter set.
  typedef SmallPtrSet<MachineBasicBlock *, 16> BlockFilterSet;

  /// \brief A handle to the branch probability pass.
  const MachineBranchProbabilityInfo *MBPI;

  /// \brief A handle to the function-wide block frequency pass.
  const MachineBlockFrequencyInfo *MBFI;

  /// \brief A handle to the loop info.
  const MachineLoopInfo *MLI;

  /// \brief A handle to the target's instruction info.
  const TargetInstrInfo *TII;

  /// \brief A handle to the target's lowering info.
  const TargetLoweringBase *TLI;

  /// \brief Allocator and owner of BlockChain structures.
  ///
  /// We build BlockChains lazily while processing the loop structure of
  /// a function. To reduce malloc traffic, we allocate them using this
  /// slab-like allocator, and destroy them after the pass completes. An
  /// important guarantee is that this allocator produces stable pointers to
  /// the chains.
  SpecificBumpPtrAllocator<BlockChain> ChainAllocator;

  /// \brief Function wide BasicBlock to BlockChain mapping.
  ///
  /// This mapping allows efficiently moving from any given basic block to the
  /// BlockChain it participates in, if any. We use it to, among other things,
  /// allow implicitly defining edges between chains as the existing edges
  /// between basic blocks.
  DenseMap<MachineBasicBlock *, BlockChain *> BlockToChain;

  void markChainSuccessors(BlockChain &Chain,
                           MachineBasicBlock *LoopHeaderBB,
                           SmallVectorImpl<MachineBasicBlock *> &BlockWorkList,
                           const BlockFilterSet *BlockFilter = 0);
  MachineBasicBlock *selectBestSuccessor(MachineBasicBlock *BB,
                                         BlockChain &Chain,
                                         const BlockFilterSet *BlockFilter);
  MachineBasicBlock *selectBestCandidateBlock(
      BlockChain &Chain, SmallVectorImpl<MachineBasicBlock *> &WorkList,
      const BlockFilterSet *BlockFilter);
  MachineBasicBlock *getFirstUnplacedBlock(
      MachineFunction &F,
      const BlockChain &PlacedChain,
      MachineFunction::iterator &PrevUnplacedBlockIt,
      const BlockFilterSet *BlockFilter);
  void buildChain(MachineBasicBlock *BB, BlockChain &Chain,
                  SmallVectorImpl<MachineBasicBlock *> &BlockWorkList,
                  const BlockFilterSet *BlockFilter = 0);
  MachineBasicBlock *findBestLoopTop(MachineLoop &L,
                                     const BlockFilterSet &LoopBlockSet);
  MachineBasicBlock *findBestLoopExit(MachineFunction &F,
                                      MachineLoop &L,
                                      const BlockFilterSet &LoopBlockSet);
  void buildLoopChains(MachineFunction &F, MachineLoop &L);
  void rotateLoop(BlockChain &LoopChain, MachineBasicBlock *ExitingBB,
                  const BlockFilterSet &LoopBlockSet);
  void buildCFGChains(MachineFunction &F);

public:
  static char ID; // Pass identification, replacement for typeid
  MachineBlockPlacement() : MachineFunctionPass(ID) {
    initializeMachineBlockPlacementPass(*PassRegistry::getPassRegistry());
  }

  bool runOnMachineFunction(MachineFunction &F) override;

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<MachineBranchProbabilityInfo>();
    AU.addRequired<MachineBlockFrequencyInfo>();
    AU.addRequired<MachineLoopInfo>();
    MachineFunctionPass::getAnalysisUsage(AU);
  }
};
}

char MachineBlockPlacement::ID = 0;
char &llvm::MachineBlockPlacementID = MachineBlockPlacement::ID;
INITIALIZE_PASS_BEGIN(MachineBlockPlacement, "block-placement2",
                      "Branch Probability Basic Block Placement", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
INITIALIZE_PASS_END(MachineBlockPlacement, "block-placement2",
                    "Branch Probability Basic Block Placement", false, false)

#ifndef NDEBUG
/// \brief Helper to print the name of a MBB.
///
/// Only used by debug logging.
static std::string getBlockName(MachineBasicBlock *BB) {
  std::string Result;
  raw_string_ostream OS(Result);
  OS << "BB#" << BB->getNumber()
     << " (derived from LLVM BB '" << BB->getName() << "')";
  OS.flush();
  return Result;
}

/// \brief Helper to print the number of a MBB.
///
/// Only used by debug logging.
static std::string getBlockNum(MachineBasicBlock *BB) {
  std::string Result;
  raw_string_ostream OS(Result);
  OS << "BB#" << BB->getNumber();
  OS.flush();
  return Result;
}
#endif

/// \brief Mark a chain's successors as having one fewer preds.
///
/// When a chain is being merged into the "placed" chain, this routine will
/// quickly walk the successors of each block in the chain and mark them as
/// having one fewer active predecessor. It also adds any successors of this
/// chain which reach the zero-predecessor state to the worklist passed in.
void MachineBlockPlacement::markChainSuccessors(
    BlockChain &Chain,
    MachineBasicBlock *LoopHeaderBB,
    SmallVectorImpl<MachineBasicBlock *> &BlockWorkList,
    const BlockFilterSet *BlockFilter) {
  // Walk all the blocks in this chain, marking their successors as having
  // a predecessor placed.
  for (BlockChain::iterator CBI = Chain.begin(), CBE = Chain.end();
       CBI != CBE; ++CBI) {
    // Add any successors for which this is the only un-placed in-loop
    // predecessor to the worklist as a viable candidate for CFG-neutral
    // placement. No subsequent placement of this block will violate the CFG
    // shape, so we get to use heuristics to choose a favorable placement.
    for (MachineBasicBlock::succ_iterator SI = (*CBI)->succ_begin(),
                                          SE = (*CBI)->succ_end();
         SI != SE; ++SI) {
      if (BlockFilter && !BlockFilter->count(*SI))
        continue;
      BlockChain &SuccChain = *BlockToChain[*SI];
      // Disregard edges within a fixed chain, or edges to the loop header.
      if (&Chain == &SuccChain || *SI == LoopHeaderBB)
        continue;

      // This is a cross-chain edge that is within the loop, so decrement the
      // loop predecessor count of the destination chain.
      if (SuccChain.LoopPredecessors > 0 && --SuccChain.LoopPredecessors == 0)
        BlockWorkList.push_back(*SuccChain.begin());
    }
  }
}

/// \brief Select the best successor for a block.
///
/// This looks across all successors of a particular block and attempts to
/// select the "best" one to be the layout successor. It only considers direct
/// successors which also pass the block filter. It will attempt to avoid
/// breaking CFG structure, but cave and break such structures in the case of
/// very hot successor edges.
///
/// \returns The best successor block found, or null if none are viable.
MachineBasicBlock *MachineBlockPlacement::selectBestSuccessor(
    MachineBasicBlock *BB, BlockChain &Chain,
    const BlockFilterSet *BlockFilter) {
  const BranchProbability HotProb(4, 5); // 80%

  MachineBasicBlock *BestSucc = 0;
  // FIXME: Due to the performance of the probability and weight routines in
  // the MBPI analysis, we manually compute probabilities using the edge
  // weights. This is suboptimal as it means that the somewhat subtle
  // definition of edge weight semantics is encoded here as well. We should
  // improve the MBPI interface to efficiently support query patterns such as
  // this.
  uint32_t BestWeight = 0;
  uint32_t WeightScale = 0;
  uint32_t SumWeight = MBPI->getSumForBlock(BB, WeightScale);
  DEBUG(dbgs() << "Attempting merge from: " << getBlockName(BB) << "\n");
  for (MachineBasicBlock::succ_iterator SI = BB->succ_begin(),
                                        SE = BB->succ_end();
       SI != SE; ++SI) {
    if (BlockFilter && !BlockFilter->count(*SI))
      continue;
    BlockChain &SuccChain = *BlockToChain[*SI];
    if (&SuccChain == &Chain) {
      DEBUG(dbgs() << "    " << getBlockName(*SI) << " -> Already merged!\n");
      continue;
    }
    if (*SI != *SuccChain.begin()) {
      DEBUG(dbgs() << "    " << getBlockName(*SI) << " -> Mid chain!\n");
      continue;
    }

    uint32_t SuccWeight = MBPI->getEdgeWeight(BB, *SI);
    BranchProbability SuccProb(SuccWeight / WeightScale, SumWeight);

    // Only consider successors which are either "hot", or wouldn't violate
    // any CFG constraints.
    if (SuccChain.LoopPredecessors != 0) {
      if (SuccProb < HotProb) {
        DEBUG(dbgs() << "    " << getBlockName(*SI) << " -> " << SuccProb
                     << " (prob) (CFG conflict)\n");
        continue;
      }

      // Make sure that a hot successor doesn't have a globally more important
      // predecessor.
      BlockFrequency CandidateEdgeFreq
        = MBFI->getBlockFreq(BB) * SuccProb * HotProb.getCompl();
      bool BadCFGConflict = false;
      for (MachineBasicBlock::pred_iterator PI = (*SI)->pred_begin(),
                                            PE = (*SI)->pred_end();
           PI != PE; ++PI) {
        if (*PI == *SI || (BlockFilter && !BlockFilter->count(*PI)) ||
            BlockToChain[*PI] == &Chain)
          continue;
        BlockFrequency PredEdgeFreq
          = MBFI->getBlockFreq(*PI) * MBPI->getEdgeProbability(*PI, *SI);
        if (PredEdgeFreq >= CandidateEdgeFreq) {
          BadCFGConflict = true;
          break;
        }
      }
      if (BadCFGConflict) {
        DEBUG(dbgs() << "    " << getBlockName(*SI) << " -> " << SuccProb
                     << " (prob) (non-cold CFG conflict)\n");
        continue;
      }
    }

    DEBUG(dbgs() << "    " << getBlockName(*SI) << " -> " << SuccProb
                 << " (prob)"
                 << (SuccChain.LoopPredecessors != 0 ? " (CFG break)" : "")
                 << "\n");
    if (BestSucc && BestWeight >= SuccWeight)
      continue;
    BestSucc = *SI;
    BestWeight = SuccWeight;
  }
  return BestSucc;
}

/// \brief Select the best block from a worklist.
///
/// This looks through the provided worklist as a list of candidate basic
/// blocks and select the most profitable one to place. The definition of
/// profitable only really makes sense in the context of a loop. This returns
/// the most frequently visited block in the worklist, which in the case of
/// a loop, is the one most desirable to be physically close to the rest of the
/// loop body in order to improve icache behavior.
///
/// \returns The best block found, or null if none are viable.
MachineBasicBlock *MachineBlockPlacement::selectBestCandidateBlock(
    BlockChain &Chain, SmallVectorImpl<MachineBasicBlock *> &WorkList,
    const BlockFilterSet *BlockFilter) {
  // Once we need to walk the worklist looking for a candidate, cleanup the
  // worklist of already placed entries.
  // FIXME: If this shows up on profiles, it could be folded (at the cost of
  // some code complexity) into the loop below.
  WorkList.erase(std::remove_if(WorkList.begin(), WorkList.end(),
                                [&](MachineBasicBlock *BB) {
                   return BlockToChain.lookup(BB) == &Chain;
                 }),
                 WorkList.end());

  MachineBasicBlock *BestBlock = 0;
  BlockFrequency BestFreq;
  for (SmallVectorImpl<MachineBasicBlock *>::iterator WBI = WorkList.begin(),
                                                      WBE = WorkList.end();
       WBI != WBE; ++WBI) {
    BlockChain &SuccChain = *BlockToChain[*WBI];
    if (&SuccChain == &Chain) {
      DEBUG(dbgs() << "    " << getBlockName(*WBI)
                   << " -> Already merged!\n");
      continue;
    }
    assert(SuccChain.LoopPredecessors == 0 && "Found CFG-violating block");

    BlockFrequency CandidateFreq = MBFI->getBlockFreq(*WBI);
    DEBUG(dbgs() << "    " << getBlockName(*WBI) << " -> ";
                 MBFI->printBlockFreq(dbgs(), CandidateFreq) << " (freq)\n");
    if (BestBlock && BestFreq >= CandidateFreq)
      continue;
    BestBlock = *WBI;
    BestFreq = CandidateFreq;
  }
  return BestBlock;
}

/// \brief Retrieve the first unplaced basic block.
///
/// This routine is called when we are unable to use the CFG to walk through
/// all of the basic blocks and form a chain due to unnatural loops in the CFG.
/// We walk through the function's blocks in order, starting from the
/// LastUnplacedBlockIt. We update this iterator on each call to avoid
/// re-scanning the entire sequence on repeated calls to this routine.
MachineBasicBlock *MachineBlockPlacement::getFirstUnplacedBlock(
    MachineFunction &F, const BlockChain &PlacedChain,
    MachineFunction::iterator &PrevUnplacedBlockIt,
    const BlockFilterSet *BlockFilter) {
  for (MachineFunction::iterator I = PrevUnplacedBlockIt, E = F.end(); I != E;
       ++I) {
    if (BlockFilter && !BlockFilter->count(I))
      continue;
    if (BlockToChain[I] != &PlacedChain) {
      PrevUnplacedBlockIt = I;
      // Now select the head of the chain to which the unplaced block belongs
      // as the block to place. This will force the entire chain to be placed,
      // and satisfies the requirements of merging chains.
      return *BlockToChain[I]->begin();
    }
  }
  return 0;
}

void MachineBlockPlacement::buildChain(
    MachineBasicBlock *BB,
    BlockChain &Chain,
    SmallVectorImpl<MachineBasicBlock *> &BlockWorkList,
    const BlockFilterSet *BlockFilter) {
  assert(BB);
  assert(BlockToChain[BB] == &Chain);
  MachineFunction &F = *BB->getParent();
  MachineFunction::iterator PrevUnplacedBlockIt = F.begin();

  MachineBasicBlock *LoopHeaderBB = BB;
  markChainSuccessors(Chain, LoopHeaderBB, BlockWorkList, BlockFilter);
  BB = *std::prev(Chain.end());
  for (;;) {
    assert(BB);
    assert(BlockToChain[BB] == &Chain);
    assert(*std::prev(Chain.end()) == BB);

    // Look for the best viable successor if there is one to place immediately
    // after this block.
    MachineBasicBlock *BestSucc = selectBestSuccessor(BB, Chain, BlockFilter);

    // If an immediate successor isn't available, look for the best viable
    // block among those we've identified as not violating the loop's CFG at
    // this point. This won't be a fallthrough, but it will increase locality.
    if (!BestSucc)
      BestSucc = selectBestCandidateBlock(Chain, BlockWorkList, BlockFilter);

    if (!BestSucc) {
      BestSucc = getFirstUnplacedBlock(F, Chain, PrevUnplacedBlockIt,
                                       BlockFilter);
      if (!BestSucc)
        break;

      DEBUG(dbgs() << "Unnatural loop CFG detected, forcibly merging the "
                      "layout successor until the CFG reduces\n");
    }

    // Place this block, updating the datastructures to reflect its placement.
    BlockChain &SuccChain = *BlockToChain[BestSucc];
    // Zero out LoopPredecessors for the successor we're about to merge in case
    // we selected a successor that didn't fit naturally into the CFG.
    SuccChain.LoopPredecessors = 0;
    DEBUG(dbgs() << "Merging from " << getBlockNum(BB)
                 << " to " << getBlockNum(BestSucc) << "\n");
    markChainSuccessors(SuccChain, LoopHeaderBB, BlockWorkList, BlockFilter);
    Chain.merge(BestSucc, &SuccChain);
    BB = *std::prev(Chain.end());
  }

  DEBUG(dbgs() << "Finished forming chain for header block "
               << getBlockNum(*Chain.begin()) << "\n");
}

/// \brief Find the best loop top block for layout.
///
/// Look for a block which is strictly better than the loop header for laying
/// out at the top of the loop. This looks for one and only one pattern:
/// a latch block with no conditional exit. This block will cause a conditional
/// jump around it or will be the bottom of the loop if we lay it out in place,
/// but if it it doesn't end up at the bottom of the loop for any reason,
/// rotation alone won't fix it. Because such a block will always result in an
/// unconditional jump (for the backedge) rotating it in front of the loop
/// header is always profitable.
MachineBasicBlock *
MachineBlockPlacement::findBestLoopTop(MachineLoop &L,
                                       const BlockFilterSet &LoopBlockSet) {
  // Check that the header hasn't been fused with a preheader block due to
  // crazy branches. If it has, we need to start with the header at the top to
  // prevent pulling the preheader into the loop body.
  BlockChain &HeaderChain = *BlockToChain[L.getHeader()];
  if (!LoopBlockSet.count(*HeaderChain.begin()))
    return L.getHeader();

  DEBUG(dbgs() << "Finding best loop top for: "
               << getBlockName(L.getHeader()) << "\n");

  BlockFrequency BestPredFreq;
  MachineBasicBlock *BestPred = 0;
  for (MachineBasicBlock::pred_iterator PI = L.getHeader()->pred_begin(),
                                        PE = L.getHeader()->pred_end();
       PI != PE; ++PI) {
    MachineBasicBlock *Pred = *PI;
    if (!LoopBlockSet.count(Pred))
      continue;
    DEBUG(dbgs() << "    header pred: " << getBlockName(Pred) << ", "
                 << Pred->succ_size() << " successors, ";
                 MBFI->printBlockFreq(dbgs(), Pred) << " freq\n");
    if (Pred->succ_size() > 1)
      continue;

    BlockFrequency PredFreq = MBFI->getBlockFreq(Pred);
    if (!BestPred || PredFreq > BestPredFreq ||
        (!(PredFreq < BestPredFreq) &&
         Pred->isLayoutSuccessor(L.getHeader()))) {
      BestPred = Pred;
      BestPredFreq = PredFreq;
    }
  }

  // If no direct predecessor is fine, just use the loop header.
  if (!BestPred)
    return L.getHeader();

  // Walk backwards through any straight line of predecessors.
  while (BestPred->pred_size() == 1 &&
         (*BestPred->pred_begin())->succ_size() == 1 &&
         *BestPred->pred_begin() != L.getHeader())
    BestPred = *BestPred->pred_begin();

  DEBUG(dbgs() << "    final top: " << getBlockName(BestPred) << "\n");
  return BestPred;
}


/// \brief Find the best loop exiting block for layout.
///
/// This routine implements the logic to analyze the loop looking for the best
/// block to layout at the top of the loop. Typically this is done to maximize
/// fallthrough opportunities.
MachineBasicBlock *
MachineBlockPlacement::findBestLoopExit(MachineFunction &F,
                                        MachineLoop &L,
                                        const BlockFilterSet &LoopBlockSet) {
  // We don't want to layout the loop linearly in all cases. If the loop header
  // is just a normal basic block in the loop, we want to look for what block
  // within the loop is the best one to layout at the top. However, if the loop
  // header has be pre-merged into a chain due to predecessors not having
  // analyzable branches, *and* the predecessor it is merged with is *not* part
  // of the loop, rotating the header into the middle of the loop will create
  // a non-contiguous range of blocks which is Very Bad. So start with the
  // header and only rotate if safe.
  BlockChain &HeaderChain = *BlockToChain[L.getHeader()];
  if (!LoopBlockSet.count(*HeaderChain.begin()))
    return 0;

  BlockFrequency BestExitEdgeFreq;
  unsigned BestExitLoopDepth = 0;
  MachineBasicBlock *ExitingBB = 0;
  // If there are exits to outer loops, loop rotation can severely limit
  // fallthrough opportunites unless it selects such an exit. Keep a set of
  // blocks where rotating to exit with that block will reach an outer loop.
  SmallPtrSet<MachineBasicBlock *, 4> BlocksExitingToOuterLoop;

  DEBUG(dbgs() << "Finding best loop exit for: "
               << getBlockName(L.getHeader()) << "\n");
  for (MachineLoop::block_iterator I = L.block_begin(),
                                   E = L.block_end();
       I != E; ++I) {
    BlockChain &Chain = *BlockToChain[*I];
    // Ensure that this block is at the end of a chain; otherwise it could be
    // mid-way through an inner loop or a successor of an analyzable branch.
    if (*I != *std::prev(Chain.end()))
      continue;

    // Now walk the successors. We need to establish whether this has a viable
    // exiting successor and whether it has a viable non-exiting successor.
    // We store the old exiting state and restore it if a viable looping
    // successor isn't found.
    MachineBasicBlock *OldExitingBB = ExitingBB;
    BlockFrequency OldBestExitEdgeFreq = BestExitEdgeFreq;
    bool HasLoopingSucc = false;
    // FIXME: Due to the performance of the probability and weight routines in
    // the MBPI analysis, we use the internal weights and manually compute the
    // probabilities to avoid quadratic behavior.
    uint32_t WeightScale = 0;
    uint32_t SumWeight = MBPI->getSumForBlock(*I, WeightScale);
    for (MachineBasicBlock::succ_iterator SI = (*I)->succ_begin(),
                                          SE = (*I)->succ_end();
         SI != SE; ++SI) {
      if ((*SI)->isLandingPad())
        continue;
      if (*SI == *I)
        continue;
      BlockChain &SuccChain = *BlockToChain[*SI];
      // Don't split chains, either this chain or the successor's chain.
      if (&Chain == &SuccChain) {
        DEBUG(dbgs() << "    exiting: " << getBlockName(*I) << " -> "
                     << getBlockName(*SI) << " (chain conflict)\n");
        continue;
      }

      uint32_t SuccWeight = MBPI->getEdgeWeight(*I, *SI);
      if (LoopBlockSet.count(*SI)) {
        DEBUG(dbgs() << "    looping: " << getBlockName(*I) << " -> "
                     << getBlockName(*SI) << " (" << SuccWeight << ")\n");
        HasLoopingSucc = true;
        continue;
      }

      unsigned SuccLoopDepth = 0;
      if (MachineLoop *ExitLoop = MLI->getLoopFor(*SI)) {
        SuccLoopDepth = ExitLoop->getLoopDepth();
        if (ExitLoop->contains(&L))
          BlocksExitingToOuterLoop.insert(*I);
      }

      BranchProbability SuccProb(SuccWeight / WeightScale, SumWeight);
      BlockFrequency ExitEdgeFreq = MBFI->getBlockFreq(*I) * SuccProb;
      DEBUG(dbgs() << "    exiting: " << getBlockName(*I) << " -> "
                   << getBlockName(*SI) << " [L:" << SuccLoopDepth
                   << "] (";
                   MBFI->printBlockFreq(dbgs(), ExitEdgeFreq) << ")\n");
      // Note that we bias this toward an existing layout successor to retain
      // incoming order in the absence of better information. The exit must have
      // a frequency higher than the current exit before we consider breaking
      // the layout.
      BranchProbability Bias(100 - ExitBlockBias, 100);
      if (!ExitingBB || BestExitLoopDepth < SuccLoopDepth ||
          ExitEdgeFreq > BestExitEdgeFreq ||
          ((*I)->isLayoutSuccessor(*SI) &&
           !(ExitEdgeFreq < BestExitEdgeFreq * Bias))) {
        BestExitEdgeFreq = ExitEdgeFreq;
        ExitingBB = *I;
      }
    }

    // Restore the old exiting state, no viable looping successor was found.
    if (!HasLoopingSucc) {
      ExitingBB = OldExitingBB;
      BestExitEdgeFreq = OldBestExitEdgeFreq;
      continue;
    }
  }
  // Without a candidate exiting block or with only a single block in the
  // loop, just use the loop header to layout the loop.
  if (!ExitingBB || L.getNumBlocks() == 1)
    return 0;

  // Also, if we have exit blocks which lead to outer loops but didn't select
  // one of them as the exiting block we are rotating toward, disable loop
  // rotation altogether.
  if (!BlocksExitingToOuterLoop.empty() &&
      !BlocksExitingToOuterLoop.count(ExitingBB))
    return 0;

  DEBUG(dbgs() << "  Best exiting block: " << getBlockName(ExitingBB) << "\n");
  return ExitingBB;
}

/// \brief Attempt to rotate an exiting block to the bottom of the loop.
///
/// Once we have built a chain, try to rotate it to line up the hot exit block
/// with fallthrough out of the loop if doing so doesn't introduce unnecessary
/// branches. For example, if the loop has fallthrough into its header and out
/// of its bottom already, don't rotate it.
void MachineBlockPlacement::rotateLoop(BlockChain &LoopChain,
                                       MachineBasicBlock *ExitingBB,
                                       const BlockFilterSet &LoopBlockSet) {
  if (!ExitingBB)
    return;

  MachineBasicBlock *Top = *LoopChain.begin();
  bool ViableTopFallthrough = false;
  for (MachineBasicBlock::pred_iterator PI = Top->pred_begin(),
                                        PE = Top->pred_end();
       PI != PE; ++PI) {
    BlockChain *PredChain = BlockToChain[*PI];
    if (!LoopBlockSet.count(*PI) &&
        (!PredChain || *PI == *std::prev(PredChain->end()))) {
      ViableTopFallthrough = true;
      break;
    }
  }

  // If the header has viable fallthrough, check whether the current loop
  // bottom is a viable exiting block. If so, bail out as rotating will
  // introduce an unnecessary branch.
  if (ViableTopFallthrough) {
    MachineBasicBlock *Bottom = *std::prev(LoopChain.end());
    for (MachineBasicBlock::succ_iterator SI = Bottom->succ_begin(),
                                          SE = Bottom->succ_end();
         SI != SE; ++SI) {
      BlockChain *SuccChain = BlockToChain[*SI];
      if (!LoopBlockSet.count(*SI) &&
          (!SuccChain || *SI == *SuccChain->begin()))
        return;
    }
  }

  BlockChain::iterator ExitIt = std::find(LoopChain.begin(), LoopChain.end(),
                                          ExitingBB);
  if (ExitIt == LoopChain.end())
    return;

  std::rotate(LoopChain.begin(), std::next(ExitIt), LoopChain.end());
}

/// \brief Forms basic block chains from the natural loop structures.
///
/// These chains are designed to preserve the existing *structure* of the code
/// as much as possible. We can then stitch the chains together in a way which
/// both preserves the topological structure and minimizes taken conditional
/// branches.
void MachineBlockPlacement::buildLoopChains(MachineFunction &F,
                                            MachineLoop &L) {
  // First recurse through any nested loops, building chains for those inner
  // loops.
  for (MachineLoop::iterator LI = L.begin(), LE = L.end(); LI != LE; ++LI)
    buildLoopChains(F, **LI);

  SmallVector<MachineBasicBlock *, 16> BlockWorkList;
  BlockFilterSet LoopBlockSet(L.block_begin(), L.block_end());

  // First check to see if there is an obviously preferable top block for the
  // loop. This will default to the header, but may end up as one of the
  // predecessors to the header if there is one which will result in strictly
  // fewer branches in the loop body.
  MachineBasicBlock *LoopTop = findBestLoopTop(L, LoopBlockSet);

  // If we selected just the header for the loop top, look for a potentially
  // profitable exit block in the event that rotating the loop can eliminate
  // branches by placing an exit edge at the bottom.
  MachineBasicBlock *ExitingBB = 0;
  if (LoopTop == L.getHeader())
    ExitingBB = findBestLoopExit(F, L, LoopBlockSet);

  BlockChain &LoopChain = *BlockToChain[LoopTop];

  // FIXME: This is a really lame way of walking the chains in the loop: we
  // walk the blocks, and use a set to prevent visiting a particular chain
  // twice.
  SmallPtrSet<BlockChain *, 4> UpdatedPreds;
  assert(LoopChain.LoopPredecessors == 0);
  UpdatedPreds.insert(&LoopChain);
  for (MachineLoop::block_iterator BI = L.block_begin(),
                                   BE = L.block_end();
       BI != BE; ++BI) {
    BlockChain &Chain = *BlockToChain[*BI];
    if (!UpdatedPreds.insert(&Chain))
      continue;

    assert(Chain.LoopPredecessors == 0);
    for (BlockChain::iterator BCI = Chain.begin(), BCE = Chain.end();
         BCI != BCE; ++BCI) {
      assert(BlockToChain[*BCI] == &Chain);
      for (MachineBasicBlock::pred_iterator PI = (*BCI)->pred_begin(),
                                            PE = (*BCI)->pred_end();
           PI != PE; ++PI) {
        if (BlockToChain[*PI] == &Chain || !LoopBlockSet.count(*PI))
          continue;
        ++Chain.LoopPredecessors;
      }
    }

    if (Chain.LoopPredecessors == 0)
      BlockWorkList.push_back(*Chain.begin());
  }

  buildChain(LoopTop, LoopChain, BlockWorkList, &LoopBlockSet);
  rotateLoop(LoopChain, ExitingBB, LoopBlockSet);

  DEBUG({
    // Crash at the end so we get all of the debugging output first.
    bool BadLoop = false;
    if (LoopChain.LoopPredecessors) {
      BadLoop = true;
      dbgs() << "Loop chain contains a block without its preds placed!\n"
             << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
             << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n";
    }
    for (BlockChain::iterator BCI = LoopChain.begin(), BCE = LoopChain.end();
         BCI != BCE; ++BCI) {
      dbgs() << "          ... " << getBlockName(*BCI) << "\n";
      if (!LoopBlockSet.erase(*BCI)) {
        // We don't mark the loop as bad here because there are real situations
        // where this can occur. For example, with an unanalyzable fallthrough
        // from a loop block to a non-loop block or vice versa.
        dbgs() << "Loop chain contains a block not contained by the loop!\n"
               << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
               << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n"
               << "  Bad block:    " << getBlockName(*BCI) << "\n";
      }
    }

    if (!LoopBlockSet.empty()) {
      BadLoop = true;
      for (BlockFilterSet::iterator LBI = LoopBlockSet.begin(),
                                    LBE = LoopBlockSet.end();
           LBI != LBE; ++LBI)
        dbgs() << "Loop contains blocks never placed into a chain!\n"
               << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
               << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n"
               << "  Bad block:    " << getBlockName(*LBI) << "\n";
    }
    assert(!BadLoop && "Detected problems with the placement of this loop.");
  });
}

void MachineBlockPlacement::buildCFGChains(MachineFunction &F) {
  // Ensure that every BB in the function has an associated chain to simplify
  // the assumptions of the remaining algorithm.
  SmallVector<MachineOperand, 4> Cond; // For AnalyzeBranch.
  for (MachineFunction::iterator FI = F.begin(), FE = F.end(); FI != FE; ++FI) {
    MachineBasicBlock *BB = FI;
    BlockChain *Chain
      = new (ChainAllocator.Allocate()) BlockChain(BlockToChain, BB);
    // Also, merge any blocks which we cannot reason about and must preserve
    // the exact fallthrough behavior for.
    for (;;) {
      Cond.clear();
      MachineBasicBlock *TBB = 0, *FBB = 0; // For AnalyzeBranch.
      if (!TII->AnalyzeBranch(*BB, TBB, FBB, Cond) || !FI->canFallThrough())
        break;

      MachineFunction::iterator NextFI(std::next(FI));
      MachineBasicBlock *NextBB = NextFI;
      // Ensure that the layout successor is a viable block, as we know that
      // fallthrough is a possibility.
      assert(NextFI != FE && "Can't fallthrough past the last block.");
      DEBUG(dbgs() << "Pre-merging due to unanalyzable fallthrough: "
                   << getBlockName(BB) << " -> " << getBlockName(NextBB)
                   << "\n");
      Chain->merge(NextBB, 0);
      FI = NextFI;
      BB = NextBB;
    }
  }

  // Build any loop-based chains.
  for (MachineLoopInfo::iterator LI = MLI->begin(), LE = MLI->end(); LI != LE;
       ++LI)
    buildLoopChains(F, **LI);

  SmallVector<MachineBasicBlock *, 16> BlockWorkList;

  SmallPtrSet<BlockChain *, 4> UpdatedPreds;
  for (MachineFunction::iterator FI = F.begin(), FE = F.end(); FI != FE; ++FI) {
    MachineBasicBlock *BB = &*FI;
    BlockChain &Chain = *BlockToChain[BB];
    if (!UpdatedPreds.insert(&Chain))
      continue;

    assert(Chain.LoopPredecessors == 0);
    for (BlockChain::iterator BCI = Chain.begin(), BCE = Chain.end();
         BCI != BCE; ++BCI) {
      assert(BlockToChain[*BCI] == &Chain);
      for (MachineBasicBlock::pred_iterator PI = (*BCI)->pred_begin(),
                                            PE = (*BCI)->pred_end();
           PI != PE; ++PI) {
        if (BlockToChain[*PI] == &Chain)
          continue;
        ++Chain.LoopPredecessors;
      }
    }

    if (Chain.LoopPredecessors == 0)
      BlockWorkList.push_back(*Chain.begin());
  }

  BlockChain &FunctionChain = *BlockToChain[&F.front()];
  buildChain(&F.front(), FunctionChain, BlockWorkList);

#ifndef NDEBUG
  typedef SmallPtrSet<MachineBasicBlock *, 16> FunctionBlockSetType;
#endif
  DEBUG({
    // Crash at the end so we get all of the debugging output first.
    bool BadFunc = false;
    FunctionBlockSetType FunctionBlockSet;
    for (MachineFunction::iterator FI = F.begin(), FE = F.end(); FI != FE; ++FI)
      FunctionBlockSet.insert(FI);

    for (BlockChain::iterator BCI = FunctionChain.begin(),
                              BCE = FunctionChain.end();
         BCI != BCE; ++BCI)
      if (!FunctionBlockSet.erase(*BCI)) {
        BadFunc = true;
        dbgs() << "Function chain contains a block not in the function!\n"
               << "  Bad block:    " << getBlockName(*BCI) << "\n";
      }

    if (!FunctionBlockSet.empty()) {
      BadFunc = true;
      for (FunctionBlockSetType::iterator FBI = FunctionBlockSet.begin(),
                                          FBE = FunctionBlockSet.end();
           FBI != FBE; ++FBI)
        dbgs() << "Function contains blocks never placed into a chain!\n"
               << "  Bad block:    " << getBlockName(*FBI) << "\n";
    }
    assert(!BadFunc && "Detected problems with the block placement.");
  });

  // Splice the blocks into place.
  MachineFunction::iterator InsertPos = F.begin();
  for (BlockChain::iterator BI = FunctionChain.begin(),
                            BE = FunctionChain.end();
       BI != BE; ++BI) {
    DEBUG(dbgs() << (BI == FunctionChain.begin() ? "Placing chain "
                                                  : "          ... ")
          << getBlockName(*BI) << "\n");
    if (InsertPos != MachineFunction::iterator(*BI))
      F.splice(InsertPos, *BI);
    else
      ++InsertPos;

    // Update the terminator of the previous block.
    if (BI == FunctionChain.begin())
      continue;
    MachineBasicBlock *PrevBB = std::prev(MachineFunction::iterator(*BI));

    // FIXME: It would be awesome of updateTerminator would just return rather
    // than assert when the branch cannot be analyzed in order to remove this
    // boiler plate.
    Cond.clear();
    MachineBasicBlock *TBB = 0, *FBB = 0; // For AnalyzeBranch.
    if (!TII->AnalyzeBranch(*PrevBB, TBB, FBB, Cond)) {
      // The "PrevBB" is not yet updated to reflect current code layout, so,
      //   o. it may fall-through to a block without explict "goto" instruction
      //      before layout, and no longer fall-through it after layout; or 
      //   o. just opposite.
      // 
      // AnalyzeBranch() may return erroneous value for FBB when these two
      // situations take place. For the first scenario FBB is mistakenly set
      // NULL; for the 2nd scenario, the FBB, which is expected to be NULL,
      // is mistakenly pointing to "*BI".
      //
      bool needUpdateBr = true;
      if (!Cond.empty() && (!FBB || FBB == *BI)) {
        PrevBB->updateTerminator();
        needUpdateBr = false;
        Cond.clear();
        TBB = FBB = 0;
        if (TII->AnalyzeBranch(*PrevBB, TBB, FBB, Cond)) {
          // FIXME: This should never take place.
          TBB = FBB = 0;
        }
      }

      // If PrevBB has a two-way branch, try to re-order the branches
      // such that we branch to the successor with higher weight first.
      if (TBB && !Cond.empty() && FBB &&
          MBPI->getEdgeWeight(PrevBB, FBB) > MBPI->getEdgeWeight(PrevBB, TBB) &&
          !TII->ReverseBranchCondition(Cond)) {
        DEBUG(dbgs() << "Reverse order of the two branches: "
                     << getBlockName(PrevBB) << "\n");
        DEBUG(dbgs() << "    Edge weight: " << MBPI->getEdgeWeight(PrevBB, FBB)
                     << " vs " << MBPI->getEdgeWeight(PrevBB, TBB) << "\n");
        DebugLoc dl;  // FIXME: this is nowhere
        TII->RemoveBranch(*PrevBB);
        TII->InsertBranch(*PrevBB, FBB, TBB, Cond, dl);
        needUpdateBr = true;
      }
      if (needUpdateBr)
        PrevBB->updateTerminator();
    }
  }

  // Fixup the last block.
  Cond.clear();
  MachineBasicBlock *TBB = 0, *FBB = 0; // For AnalyzeBranch.
  if (!TII->AnalyzeBranch(F.back(), TBB, FBB, Cond))
    F.back().updateTerminator();

  // Walk through the backedges of the function now that we have fully laid out
  // the basic blocks and align the destination of each backedge. We don't rely
  // exclusively on the loop info here so that we can align backedges in
  // unnatural CFGs and backedges that were introduced purely because of the
  // loop rotations done during this layout pass.
  if (F.getFunction()->getAttributes().
        hasAttribute(AttributeSet::FunctionIndex, Attribute::OptimizeForSize))
    return;
  unsigned Align = TLI->getPrefLoopAlignment();
  if (!Align)
    return;  // Don't care about loop alignment.
  if (FunctionChain.begin() == FunctionChain.end())
    return;  // Empty chain.

  const BranchProbability ColdProb(1, 5); // 20%
  BlockFrequency EntryFreq = MBFI->getBlockFreq(F.begin());
  BlockFrequency WeightedEntryFreq = EntryFreq * ColdProb;
  for (BlockChain::iterator BI = std::next(FunctionChain.begin()),
                            BE = FunctionChain.end();
       BI != BE; ++BI) {
    // Don't align non-looping basic blocks. These are unlikely to execute
    // enough times to matter in practice. Note that we'll still handle
    // unnatural CFGs inside of a natural outer loop (the common case) and
    // rotated loops.
    MachineLoop *L = MLI->getLoopFor(*BI);
    if (!L)
      continue;

    // If the block is cold relative to the function entry don't waste space
    // aligning it.
    BlockFrequency Freq = MBFI->getBlockFreq(*BI);
    if (Freq < WeightedEntryFreq)
      continue;

    // If the block is cold relative to its loop header, don't align it
    // regardless of what edges into the block exist.
    MachineBasicBlock *LoopHeader = L->getHeader();
    BlockFrequency LoopHeaderFreq = MBFI->getBlockFreq(LoopHeader);
    if (Freq < (LoopHeaderFreq * ColdProb))
      continue;

    // Check for the existence of a non-layout predecessor which would benefit
    // from aligning this block.
    MachineBasicBlock *LayoutPred = *std::prev(BI);

    // Force alignment if all the predecessors are jumps. We already checked
    // that the block isn't cold above.
    if (!LayoutPred->isSuccessor(*BI)) {
      (*BI)->setAlignment(Align);
      continue;
    }

    // Align this block if the layout predecessor's edge into this block is
    // cold relative to the block. When this is true, other predecessors make up
    // all of the hot entries into the block and thus alignment is likely to be
    // important.
    BranchProbability LayoutProb = MBPI->getEdgeProbability(LayoutPred, *BI);
    BlockFrequency LayoutEdgeFreq = MBFI->getBlockFreq(LayoutPred) * LayoutProb;
    if (LayoutEdgeFreq <= (Freq * ColdProb))
      (*BI)->setAlignment(Align);
  }
}

bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &F) {
  // Check for single-block functions and skip them.
  if (std::next(F.begin()) == F.end())
    return false;

  MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
  MBFI = &getAnalysis<MachineBlockFrequencyInfo>();
  MLI = &getAnalysis<MachineLoopInfo>();
  TII = F.getTarget().getInstrInfo();
  TLI = F.getTarget().getTargetLowering();
  assert(BlockToChain.empty());

  buildCFGChains(F);

  BlockToChain.clear();
  ChainAllocator.DestroyAll();

  if (AlignAllBlock)
    // Align all of the blocks in the function to a specific alignment.
    for (MachineFunction::iterator FI = F.begin(), FE = F.end();
         FI != FE; ++FI)
      FI->setAlignment(AlignAllBlock);

  // We always return true as we have no way to track whether the final order
  // differs from the original order.
  return true;
}

namespace {
/// \brief A pass to compute block placement statistics.
///
/// A separate pass to compute interesting statistics for evaluating block
/// placement. This is separate from the actual placement pass so that they can
/// be computed in the absence of any placement transformations or when using
/// alternative placement strategies.
class MachineBlockPlacementStats : public MachineFunctionPass {
  /// \brief A handle to the branch probability pass.
  const MachineBranchProbabilityInfo *MBPI;

  /// \brief A handle to the function-wide block frequency pass.
  const MachineBlockFrequencyInfo *MBFI;

public:
  static char ID; // Pass identification, replacement for typeid
  MachineBlockPlacementStats() : MachineFunctionPass(ID) {
    initializeMachineBlockPlacementStatsPass(*PassRegistry::getPassRegistry());
  }

  bool runOnMachineFunction(MachineFunction &F) override;

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<MachineBranchProbabilityInfo>();
    AU.addRequired<MachineBlockFrequencyInfo>();
    AU.setPreservesAll();
    MachineFunctionPass::getAnalysisUsage(AU);
  }
};
}

char MachineBlockPlacementStats::ID = 0;
char &llvm::MachineBlockPlacementStatsID = MachineBlockPlacementStats::ID;
INITIALIZE_PASS_BEGIN(MachineBlockPlacementStats, "block-placement-stats",
                      "Basic Block Placement Stats", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
INITIALIZE_PASS_END(MachineBlockPlacementStats, "block-placement-stats",
                    "Basic Block Placement Stats", false, false)

bool MachineBlockPlacementStats::runOnMachineFunction(MachineFunction &F) {
  // Check for single-block functions and skip them.
  if (std::next(F.begin()) == F.end())
    return false;

  MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
  MBFI = &getAnalysis<MachineBlockFrequencyInfo>();

  for (MachineFunction::iterator I = F.begin(), E = F.end(); I != E; ++I) {
    BlockFrequency BlockFreq = MBFI->getBlockFreq(I);
    Statistic &NumBranches = (I->succ_size() > 1) ? NumCondBranches
                                                  : NumUncondBranches;
    Statistic &BranchTakenFreq = (I->succ_size() > 1) ? CondBranchTakenFreq
                                                      : UncondBranchTakenFreq;
    for (MachineBasicBlock::succ_iterator SI = I->succ_begin(),
                                          SE = I->succ_end();
         SI != SE; ++SI) {
      // Skip if this successor is a fallthrough.
      if (I->isLayoutSuccessor(*SI))
        continue;

      BlockFrequency EdgeFreq = BlockFreq * MBPI->getEdgeProbability(I, *SI);
      ++NumBranches;
      BranchTakenFreq += EdgeFreq.getFrequency();
    }
  }

  return false;
}