llvm.org GIT mirror llvm / f5f73cd lib / Analysis / InlineCost.cpp
f5f73cd

Tree @f5f73cd (Download .tar.gz)

InlineCost.cpp @f5f73cdraw · history · blame

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
//===- InlineCost.cpp - Cost analysis for inliner -------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements inline cost analysis.
//
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/InlineCost.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/GetElementPtrTypeIterator.h"
#include "llvm/IR/GlobalAlias.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Operator.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"

using namespace llvm;

#define DEBUG_TYPE "inline-cost"

STATISTIC(NumCallsAnalyzed, "Number of call sites analyzed");

// Threshold to use when optsize is specified (and there is no
// -inline-threshold).
const int OptSizeThreshold = 75;

// Threshold to use when -Oz is specified (and there is no -inline-threshold).
const int OptMinSizeThreshold = 25;

// Threshold to use when -O[34] is specified (and there is no
// -inline-threshold).
const int OptAggressiveThreshold = 275;

static cl::opt<int> DefaultInlineThreshold(
    "inline-threshold", cl::Hidden, cl::init(225), cl::ZeroOrMore,
    cl::desc("Control the amount of inlining to perform (default = 225)"));

static cl::opt<int> HintThreshold(
    "inlinehint-threshold", cl::Hidden, cl::init(325),
    cl::desc("Threshold for inlining functions with inline hint"));

// We introduce this threshold to help performance of instrumentation based
// PGO before we actually hook up inliner with analysis passes such as BPI and
// BFI.
static cl::opt<int> ColdThreshold(
    "inlinecold-threshold", cl::Hidden, cl::init(225),
    cl::desc("Threshold for inlining functions with cold attribute"));

namespace {

class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
  typedef InstVisitor<CallAnalyzer, bool> Base;
  friend class InstVisitor<CallAnalyzer, bool>;

  /// The TargetTransformInfo available for this compilation.
  const TargetTransformInfo &TTI;

  /// The cache of @llvm.assume intrinsics.
  AssumptionCacheTracker *ACT;

  // The called function.
  Function &F;

  // The candidate callsite being analyzed. Please do not use this to do
  // analysis in the caller function; we want the inline cost query to be
  // easily cacheable. Instead, use the cover function paramHasAttr.
  CallSite CandidateCS;

  int Threshold;
  int Cost;

  bool IsCallerRecursive;
  bool IsRecursiveCall;
  bool ExposesReturnsTwice;
  bool HasDynamicAlloca;
  bool ContainsNoDuplicateCall;
  bool HasReturn;
  bool HasIndirectBr;
  bool HasFrameEscape;

  /// Number of bytes allocated statically by the callee.
  uint64_t AllocatedSize;
  unsigned NumInstructions, NumVectorInstructions;
  int FiftyPercentVectorBonus, TenPercentVectorBonus;
  int VectorBonus;

  // While we walk the potentially-inlined instructions, we build up and
  // maintain a mapping of simplified values specific to this callsite. The
  // idea is to propagate any special information we have about arguments to
  // this call through the inlinable section of the function, and account for
  // likely simplifications post-inlining. The most important aspect we track
  // is CFG altering simplifications -- when we prove a basic block dead, that
  // can cause dramatic shifts in the cost of inlining a function.
  DenseMap<Value *, Constant *> SimplifiedValues;

  // Keep track of the values which map back (through function arguments) to
  // allocas on the caller stack which could be simplified through SROA.
  DenseMap<Value *, Value *> SROAArgValues;

  // The mapping of caller Alloca values to their accumulated cost savings. If
  // we have to disable SROA for one of the allocas, this tells us how much
  // cost must be added.
  DenseMap<Value *, int> SROAArgCosts;

  // Keep track of values which map to a pointer base and constant offset.
  DenseMap<Value *, std::pair<Value *, APInt> > ConstantOffsetPtrs;

  // Custom simplification helper routines.
  bool isAllocaDerivedArg(Value *V);
  bool lookupSROAArgAndCost(Value *V, Value *&Arg,
                            DenseMap<Value *, int>::iterator &CostIt);
  void disableSROA(DenseMap<Value *, int>::iterator CostIt);
  void disableSROA(Value *V);
  void accumulateSROACost(DenseMap<Value *, int>::iterator CostIt,
                          int InstructionCost);
  bool isGEPOffsetConstant(GetElementPtrInst &GEP);
  bool accumulateGEPOffset(GEPOperator &GEP, APInt &Offset);
  bool simplifyCallSite(Function *F, CallSite CS);
  ConstantInt *stripAndComputeInBoundsConstantOffsets(Value *&V);

  /// Return true if the given argument to the function being considered for
  /// inlining has the given attribute set either at the call site or the
  /// function declaration.  Primarily used to inspect call site specific
  /// attributes since these can be more precise than the ones on the callee
  /// itself.
  bool paramHasAttr(Argument *A, Attribute::AttrKind Attr);
  
  /// Return true if the given value is known non null within the callee if
  /// inlined through this particular callsite.
  bool isKnownNonNullInCallee(Value *V);

  /// Update Threshold based on callsite properties such as callee
  /// attributes and callee hotness for PGO builds. The Callee is explicitly
  /// passed to support analyzing indirect calls whose target is inferred by
  /// analysis.
  void updateThreshold(CallSite CS, Function &Callee);

  // Custom analysis routines.
  bool analyzeBlock(BasicBlock *BB, SmallPtrSetImpl<const Value *> &EphValues);

  // Disable several entry points to the visitor so we don't accidentally use
  // them by declaring but not defining them here.
  void visit(Module *);     void visit(Module &);
  void visit(Function *);   void visit(Function &);
  void visit(BasicBlock *); void visit(BasicBlock &);

  // Provide base case for our instruction visit.
  bool visitInstruction(Instruction &I);

  // Our visit overrides.
  bool visitAlloca(AllocaInst &I);
  bool visitPHI(PHINode &I);
  bool visitGetElementPtr(GetElementPtrInst &I);
  bool visitBitCast(BitCastInst &I);
  bool visitPtrToInt(PtrToIntInst &I);
  bool visitIntToPtr(IntToPtrInst &I);
  bool visitCastInst(CastInst &I);
  bool visitUnaryInstruction(UnaryInstruction &I);
  bool visitCmpInst(CmpInst &I);
  bool visitSub(BinaryOperator &I);
  bool visitBinaryOperator(BinaryOperator &I);
  bool visitLoad(LoadInst &I);
  bool visitStore(StoreInst &I);
  bool visitExtractValue(ExtractValueInst &I);
  bool visitInsertValue(InsertValueInst &I);
  bool visitCallSite(CallSite CS);
  bool visitReturnInst(ReturnInst &RI);
  bool visitBranchInst(BranchInst &BI);
  bool visitSwitchInst(SwitchInst &SI);
  bool visitIndirectBrInst(IndirectBrInst &IBI);
  bool visitResumeInst(ResumeInst &RI);
  bool visitCleanupReturnInst(CleanupReturnInst &RI);
  bool visitCatchReturnInst(CatchReturnInst &RI);
  bool visitUnreachableInst(UnreachableInst &I);

public:
  CallAnalyzer(const TargetTransformInfo &TTI, AssumptionCacheTracker *ACT,
               Function &Callee, int Threshold, CallSite CSArg)
    : TTI(TTI), ACT(ACT), F(Callee), CandidateCS(CSArg), Threshold(Threshold),
        Cost(0), IsCallerRecursive(false), IsRecursiveCall(false),
        ExposesReturnsTwice(false), HasDynamicAlloca(false),
        ContainsNoDuplicateCall(false), HasReturn(false), HasIndirectBr(false),
        HasFrameEscape(false), AllocatedSize(0), NumInstructions(0),
        NumVectorInstructions(0), FiftyPercentVectorBonus(0),
        TenPercentVectorBonus(0), VectorBonus(0), NumConstantArgs(0),
        NumConstantOffsetPtrArgs(0), NumAllocaArgs(0), NumConstantPtrCmps(0),
        NumConstantPtrDiffs(0), NumInstructionsSimplified(0),
        SROACostSavings(0), SROACostSavingsLost(0) {}

  bool analyzeCall(CallSite CS);

  int getThreshold() { return Threshold; }
  int getCost() { return Cost; }

  // Keep a bunch of stats about the cost savings found so we can print them
  // out when debugging.
  unsigned NumConstantArgs;
  unsigned NumConstantOffsetPtrArgs;
  unsigned NumAllocaArgs;
  unsigned NumConstantPtrCmps;
  unsigned NumConstantPtrDiffs;
  unsigned NumInstructionsSimplified;
  unsigned SROACostSavings;
  unsigned SROACostSavingsLost;

  void dump();
};

} // namespace

/// \brief Test whether the given value is an Alloca-derived function argument.
bool CallAnalyzer::isAllocaDerivedArg(Value *V) {
  return SROAArgValues.count(V);
}

/// \brief Lookup the SROA-candidate argument and cost iterator which V maps to.
/// Returns false if V does not map to a SROA-candidate.
bool CallAnalyzer::lookupSROAArgAndCost(
    Value *V, Value *&Arg, DenseMap<Value *, int>::iterator &CostIt) {
  if (SROAArgValues.empty() || SROAArgCosts.empty())
    return false;

  DenseMap<Value *, Value *>::iterator ArgIt = SROAArgValues.find(V);
  if (ArgIt == SROAArgValues.end())
    return false;

  Arg = ArgIt->second;
  CostIt = SROAArgCosts.find(Arg);
  return CostIt != SROAArgCosts.end();
}

/// \brief Disable SROA for the candidate marked by this cost iterator.
///
/// This marks the candidate as no longer viable for SROA, and adds the cost
/// savings associated with it back into the inline cost measurement.
void CallAnalyzer::disableSROA(DenseMap<Value *, int>::iterator CostIt) {
  // If we're no longer able to perform SROA we need to undo its cost savings
  // and prevent subsequent analysis.
  Cost += CostIt->second;
  SROACostSavings -= CostIt->second;
  SROACostSavingsLost += CostIt->second;
  SROAArgCosts.erase(CostIt);
}

/// \brief If 'V' maps to a SROA candidate, disable SROA for it.
void CallAnalyzer::disableSROA(Value *V) {
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(V, SROAArg, CostIt))
    disableSROA(CostIt);
}

/// \brief Accumulate the given cost for a particular SROA candidate.
void CallAnalyzer::accumulateSROACost(DenseMap<Value *, int>::iterator CostIt,
                                      int InstructionCost) {
  CostIt->second += InstructionCost;
  SROACostSavings += InstructionCost;
}

/// \brief Check whether a GEP's indices are all constant.
///
/// Respects any simplified values known during the analysis of this callsite.
bool CallAnalyzer::isGEPOffsetConstant(GetElementPtrInst &GEP) {
  for (User::op_iterator I = GEP.idx_begin(), E = GEP.idx_end(); I != E; ++I)
    if (!isa<Constant>(*I) && !SimplifiedValues.lookup(*I))
      return false;

  return true;
}

/// \brief Accumulate a constant GEP offset into an APInt if possible.
///
/// Returns false if unable to compute the offset for any reason. Respects any
/// simplified values known during the analysis of this callsite.
bool CallAnalyzer::accumulateGEPOffset(GEPOperator &GEP, APInt &Offset) {
  const DataLayout &DL = F.getParent()->getDataLayout();
  unsigned IntPtrWidth = DL.getPointerSizeInBits();
  assert(IntPtrWidth == Offset.getBitWidth());

  for (gep_type_iterator GTI = gep_type_begin(GEP), GTE = gep_type_end(GEP);
       GTI != GTE; ++GTI) {
    ConstantInt *OpC = dyn_cast<ConstantInt>(GTI.getOperand());
    if (!OpC)
      if (Constant *SimpleOp = SimplifiedValues.lookup(GTI.getOperand()))
        OpC = dyn_cast<ConstantInt>(SimpleOp);
    if (!OpC)
      return false;
    if (OpC->isZero()) continue;

    // Handle a struct index, which adds its field offset to the pointer.
    if (StructType *STy = dyn_cast<StructType>(*GTI)) {
      unsigned ElementIdx = OpC->getZExtValue();
      const StructLayout *SL = DL.getStructLayout(STy);
      Offset += APInt(IntPtrWidth, SL->getElementOffset(ElementIdx));
      continue;
    }

    APInt TypeSize(IntPtrWidth, DL.getTypeAllocSize(GTI.getIndexedType()));
    Offset += OpC->getValue().sextOrTrunc(IntPtrWidth) * TypeSize;
  }
  return true;
}

bool CallAnalyzer::visitAlloca(AllocaInst &I) {
  // Check whether inlining will turn a dynamic alloca into a static
  // alloca, and handle that case.
  if (I.isArrayAllocation()) {
    if (Constant *Size = SimplifiedValues.lookup(I.getArraySize())) {
      ConstantInt *AllocSize = dyn_cast<ConstantInt>(Size);
      assert(AllocSize && "Allocation size not a constant int?");
      Type *Ty = I.getAllocatedType();
      AllocatedSize += Ty->getPrimitiveSizeInBits() * AllocSize->getZExtValue();
      return Base::visitAlloca(I);
    }
  }

  // Accumulate the allocated size.
  if (I.isStaticAlloca()) {
    const DataLayout &DL = F.getParent()->getDataLayout();
    Type *Ty = I.getAllocatedType();
    AllocatedSize += DL.getTypeAllocSize(Ty);
  }

  // We will happily inline static alloca instructions.
  if (I.isStaticAlloca())
    return Base::visitAlloca(I);

  // FIXME: This is overly conservative. Dynamic allocas are inefficient for
  // a variety of reasons, and so we would like to not inline them into
  // functions which don't currently have a dynamic alloca. This simply
  // disables inlining altogether in the presence of a dynamic alloca.
  HasDynamicAlloca = true;
  return false;
}

bool CallAnalyzer::visitPHI(PHINode &I) {
  // FIXME: We should potentially be tracking values through phi nodes,
  // especially when they collapse to a single value due to deleted CFG edges
  // during inlining.

  // FIXME: We need to propagate SROA *disabling* through phi nodes, even
  // though we don't want to propagate it's bonuses. The idea is to disable
  // SROA if it *might* be used in an inappropriate manner.

  // Phi nodes are always zero-cost.
  return true;
}

bool CallAnalyzer::visitGetElementPtr(GetElementPtrInst &I) {
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  bool SROACandidate = lookupSROAArgAndCost(I.getPointerOperand(),
                                            SROAArg, CostIt);

  // Try to fold GEPs of constant-offset call site argument pointers. This
  // requires target data and inbounds GEPs.
  if (I.isInBounds()) {
    // Check if we have a base + offset for the pointer.
    Value *Ptr = I.getPointerOperand();
    std::pair<Value *, APInt> BaseAndOffset = ConstantOffsetPtrs.lookup(Ptr);
    if (BaseAndOffset.first) {
      // Check if the offset of this GEP is constant, and if so accumulate it
      // into Offset.
      if (!accumulateGEPOffset(cast<GEPOperator>(I), BaseAndOffset.second)) {
        // Non-constant GEPs aren't folded, and disable SROA.
        if (SROACandidate)
          disableSROA(CostIt);
        return false;
      }

      // Add the result as a new mapping to Base + Offset.
      ConstantOffsetPtrs[&I] = BaseAndOffset;

      // Also handle SROA candidates here, we already know that the GEP is
      // all-constant indexed.
      if (SROACandidate)
        SROAArgValues[&I] = SROAArg;

      return true;
    }
  }

  if (isGEPOffsetConstant(I)) {
    if (SROACandidate)
      SROAArgValues[&I] = SROAArg;

    // Constant GEPs are modeled as free.
    return true;
  }

  // Variable GEPs will require math and will disable SROA.
  if (SROACandidate)
    disableSROA(CostIt);
  return false;
}

bool CallAnalyzer::visitBitCast(BitCastInst &I) {
  // Propagate constants through bitcasts.
  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
  if (!COp)
    COp = SimplifiedValues.lookup(I.getOperand(0));
  if (COp)
    if (Constant *C = ConstantExpr::getBitCast(COp, I.getType())) {
      SimplifiedValues[&I] = C;
      return true;
    }

  // Track base/offsets through casts
  std::pair<Value *, APInt> BaseAndOffset
    = ConstantOffsetPtrs.lookup(I.getOperand(0));
  // Casts don't change the offset, just wrap it up.
  if (BaseAndOffset.first)
    ConstantOffsetPtrs[&I] = BaseAndOffset;

  // Also look for SROA candidates here.
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(I.getOperand(0), SROAArg, CostIt))
    SROAArgValues[&I] = SROAArg;

  // Bitcasts are always zero cost.
  return true;
}

bool CallAnalyzer::visitPtrToInt(PtrToIntInst &I) {
  // Propagate constants through ptrtoint.
  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
  if (!COp)
    COp = SimplifiedValues.lookup(I.getOperand(0));
  if (COp)
    if (Constant *C = ConstantExpr::getPtrToInt(COp, I.getType())) {
      SimplifiedValues[&I] = C;
      return true;
    }

  // Track base/offset pairs when converted to a plain integer provided the
  // integer is large enough to represent the pointer.
  unsigned IntegerSize = I.getType()->getScalarSizeInBits();
  const DataLayout &DL = F.getParent()->getDataLayout();
  if (IntegerSize >= DL.getPointerSizeInBits()) {
    std::pair<Value *, APInt> BaseAndOffset
      = ConstantOffsetPtrs.lookup(I.getOperand(0));
    if (BaseAndOffset.first)
      ConstantOffsetPtrs[&I] = BaseAndOffset;
  }

  // This is really weird. Technically, ptrtoint will disable SROA. However,
  // unless that ptrtoint is *used* somewhere in the live basic blocks after
  // inlining, it will be nuked, and SROA should proceed. All of the uses which
  // would block SROA would also block SROA if applied directly to a pointer,
  // and so we can just add the integer in here. The only places where SROA is
  // preserved either cannot fire on an integer, or won't in-and-of themselves
  // disable SROA (ext) w/o some later use that we would see and disable.
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(I.getOperand(0), SROAArg, CostIt))
    SROAArgValues[&I] = SROAArg;

  return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
}

bool CallAnalyzer::visitIntToPtr(IntToPtrInst &I) {
  // Propagate constants through ptrtoint.
  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
  if (!COp)
    COp = SimplifiedValues.lookup(I.getOperand(0));
  if (COp)
    if (Constant *C = ConstantExpr::getIntToPtr(COp, I.getType())) {
      SimplifiedValues[&I] = C;
      return true;
    }

  // Track base/offset pairs when round-tripped through a pointer without
  // modifications provided the integer is not too large.
  Value *Op = I.getOperand(0);
  unsigned IntegerSize = Op->getType()->getScalarSizeInBits();
  const DataLayout &DL = F.getParent()->getDataLayout();
  if (IntegerSize <= DL.getPointerSizeInBits()) {
    std::pair<Value *, APInt> BaseAndOffset = ConstantOffsetPtrs.lookup(Op);
    if (BaseAndOffset.first)
      ConstantOffsetPtrs[&I] = BaseAndOffset;
  }

  // "Propagate" SROA here in the same manner as we do for ptrtoint above.
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(Op, SROAArg, CostIt))
    SROAArgValues[&I] = SROAArg;

  return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
}

bool CallAnalyzer::visitCastInst(CastInst &I) {
  // Propagate constants through ptrtoint.
  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
  if (!COp)
    COp = SimplifiedValues.lookup(I.getOperand(0));
  if (COp)
    if (Constant *C = ConstantExpr::getCast(I.getOpcode(), COp, I.getType())) {
      SimplifiedValues[&I] = C;
      return true;
    }

  // Disable SROA in the face of arbitrary casts we don't whitelist elsewhere.
  disableSROA(I.getOperand(0));

  return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
}

bool CallAnalyzer::visitUnaryInstruction(UnaryInstruction &I) {
  Value *Operand = I.getOperand(0);
  Constant *COp = dyn_cast<Constant>(Operand);
  if (!COp)
    COp = SimplifiedValues.lookup(Operand);
  if (COp) {
    const DataLayout &DL = F.getParent()->getDataLayout();
    if (Constant *C = ConstantFoldInstOperands(&I, COp, DL)) {
      SimplifiedValues[&I] = C;
      return true;
    }
  }

  // Disable any SROA on the argument to arbitrary unary operators.
  disableSROA(Operand);

  return false;
}

bool CallAnalyzer::paramHasAttr(Argument *A, Attribute::AttrKind Attr) {
  unsigned ArgNo = A->getArgNo();
  return CandidateCS.paramHasAttr(ArgNo+1, Attr);
}

bool CallAnalyzer::isKnownNonNullInCallee(Value *V) {
  // Does the *call site* have the NonNull attribute set on an argument?  We
  // use the attribute on the call site to memoize any analysis done in the
  // caller. This will also trip if the callee function has a non-null
  // parameter attribute, but that's a less interesting case because hopefully
  // the callee would already have been simplified based on that.
  if (Argument *A = dyn_cast<Argument>(V))
    if (paramHasAttr(A, Attribute::NonNull))
      return true;
  
  // Is this an alloca in the caller?  This is distinct from the attribute case
  // above because attributes aren't updated within the inliner itself and we
  // always want to catch the alloca derived case.
  if (isAllocaDerivedArg(V))
    // We can actually predict the result of comparisons between an
    // alloca-derived value and null. Note that this fires regardless of
    // SROA firing.
    return true;
  
  return false;
}

void CallAnalyzer::updateThreshold(CallSite CS, Function &Callee) {
  // If -inline-threshold is not given, listen to the optsize and minsize
  // attributes when they would decrease the threshold.
  Function *Caller = CS.getCaller();

  if (!(DefaultInlineThreshold.getNumOccurrences() > 0)) {
    if (Caller->optForMinSize() && OptMinSizeThreshold < Threshold)
      Threshold = OptMinSizeThreshold;
    else if (Caller->optForSize() && OptSizeThreshold < Threshold)
      Threshold = OptSizeThreshold;
  }

  // If profile information is available, use that to adjust threshold of hot
  // and cold functions.
  // FIXME: The heuristic used below for determining hotness and coldness are
  // based on preliminary SPEC tuning and may not be optimal. Replace this with
  // a well-tuned heuristic based on *callsite* hotness and not callee hotness.
  uint64_t FunctionCount = 0, MaxFunctionCount = 0;
  bool HasPGOCounts = false;
  if (Callee.getEntryCount() && Callee.getParent()->getMaximumFunctionCount()) {
    HasPGOCounts = true;
    FunctionCount = Callee.getEntryCount().getValue();
    MaxFunctionCount = Callee.getParent()->getMaximumFunctionCount().getValue();
  }

  // Listen to the inlinehint attribute or profile based hotness information
  // when it would increase the threshold and the caller does not need to
  // minimize its size.
  bool InlineHint =
      Callee.hasFnAttribute(Attribute::InlineHint) ||
      (HasPGOCounts &&
       FunctionCount >= (uint64_t)(0.3 * (double)MaxFunctionCount));
  if (InlineHint && HintThreshold > Threshold && !Caller->optForMinSize())
    Threshold = HintThreshold;

  // Listen to the cold attribute or profile based coldness information
  // when it would decrease the threshold.
  bool ColdCallee =
      Callee.hasFnAttribute(Attribute::Cold) ||
      (HasPGOCounts &&
       FunctionCount <= (uint64_t)(0.01 * (double)MaxFunctionCount));
  // Command line argument for DefaultInlineThreshold will override the default
  // ColdThreshold. If we have -inline-threshold but no -inlinecold-threshold,
  // do not use the default cold threshold even if it is smaller.
  if ((DefaultInlineThreshold.getNumOccurrences() == 0 ||
       ColdThreshold.getNumOccurrences() > 0) &&
      ColdCallee && ColdThreshold < Threshold)
    Threshold = ColdThreshold;
}

bool CallAnalyzer::visitCmpInst(CmpInst &I) {
  Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
  // First try to handle simplified comparisons.
  if (!isa<Constant>(LHS))
    if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
      LHS = SimpleLHS;
  if (!isa<Constant>(RHS))
    if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
      RHS = SimpleRHS;
  if (Constant *CLHS = dyn_cast<Constant>(LHS)) {
    if (Constant *CRHS = dyn_cast<Constant>(RHS))
      if (Constant *C = ConstantExpr::getCompare(I.getPredicate(), CLHS, CRHS)) {
        SimplifiedValues[&I] = C;
        return true;
      }
  }

  if (I.getOpcode() == Instruction::FCmp)
    return false;

  // Otherwise look for a comparison between constant offset pointers with
  // a common base.
  Value *LHSBase, *RHSBase;
  APInt LHSOffset, RHSOffset;
  std::tie(LHSBase, LHSOffset) = ConstantOffsetPtrs.lookup(LHS);
  if (LHSBase) {
    std::tie(RHSBase, RHSOffset) = ConstantOffsetPtrs.lookup(RHS);
    if (RHSBase && LHSBase == RHSBase) {
      // We have common bases, fold the icmp to a constant based on the
      // offsets.
      Constant *CLHS = ConstantInt::get(LHS->getContext(), LHSOffset);
      Constant *CRHS = ConstantInt::get(RHS->getContext(), RHSOffset);
      if (Constant *C = ConstantExpr::getICmp(I.getPredicate(), CLHS, CRHS)) {
        SimplifiedValues[&I] = C;
        ++NumConstantPtrCmps;
        return true;
      }
    }
  }

  // If the comparison is an equality comparison with null, we can simplify it
  // if we know the value (argument) can't be null
  if (I.isEquality() && isa<ConstantPointerNull>(I.getOperand(1)) &&
      isKnownNonNullInCallee(I.getOperand(0))) {
    bool IsNotEqual = I.getPredicate() == CmpInst::ICMP_NE;
    SimplifiedValues[&I] = IsNotEqual ? ConstantInt::getTrue(I.getType())
                                      : ConstantInt::getFalse(I.getType());
    return true;
  }
  // Finally check for SROA candidates in comparisons.
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(I.getOperand(0), SROAArg, CostIt)) {
    if (isa<ConstantPointerNull>(I.getOperand(1))) {
      accumulateSROACost(CostIt, InlineConstants::InstrCost);
      return true;
    }

    disableSROA(CostIt);
  }

  return false;
}

bool CallAnalyzer::visitSub(BinaryOperator &I) {
  // Try to handle a special case: we can fold computing the difference of two
  // constant-related pointers.
  Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
  Value *LHSBase, *RHSBase;
  APInt LHSOffset, RHSOffset;
  std::tie(LHSBase, LHSOffset) = ConstantOffsetPtrs.lookup(LHS);
  if (LHSBase) {
    std::tie(RHSBase, RHSOffset) = ConstantOffsetPtrs.lookup(RHS);
    if (RHSBase && LHSBase == RHSBase) {
      // We have common bases, fold the subtract to a constant based on the
      // offsets.
      Constant *CLHS = ConstantInt::get(LHS->getContext(), LHSOffset);
      Constant *CRHS = ConstantInt::get(RHS->getContext(), RHSOffset);
      if (Constant *C = ConstantExpr::getSub(CLHS, CRHS)) {
        SimplifiedValues[&I] = C;
        ++NumConstantPtrDiffs;
        return true;
      }
    }
  }

  // Otherwise, fall back to the generic logic for simplifying and handling
  // instructions.
  return Base::visitSub(I);
}

bool CallAnalyzer::visitBinaryOperator(BinaryOperator &I) {
  Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
  const DataLayout &DL = F.getParent()->getDataLayout();
  if (!isa<Constant>(LHS))
    if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
      LHS = SimpleLHS;
  if (!isa<Constant>(RHS))
    if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
      RHS = SimpleRHS;
  Value *SimpleV = nullptr;
  if (auto FI = dyn_cast<FPMathOperator>(&I))
    SimpleV =
        SimplifyFPBinOp(I.getOpcode(), LHS, RHS, FI->getFastMathFlags(), DL);
  else
    SimpleV = SimplifyBinOp(I.getOpcode(), LHS, RHS, DL);

  if (Constant *C = dyn_cast_or_null<Constant>(SimpleV)) {
    SimplifiedValues[&I] = C;
    return true;
  }

  // Disable any SROA on arguments to arbitrary, unsimplified binary operators.
  disableSROA(LHS);
  disableSROA(RHS);

  return false;
}

bool CallAnalyzer::visitLoad(LoadInst &I) {
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(I.getPointerOperand(), SROAArg, CostIt)) {
    if (I.isSimple()) {
      accumulateSROACost(CostIt, InlineConstants::InstrCost);
      return true;
    }

    disableSROA(CostIt);
  }

  return false;
}

bool CallAnalyzer::visitStore(StoreInst &I) {
  Value *SROAArg;
  DenseMap<Value *, int>::iterator CostIt;
  if (lookupSROAArgAndCost(I.getPointerOperand(), SROAArg, CostIt)) {
    if (I.isSimple()) {
      accumulateSROACost(CostIt, InlineConstants::InstrCost);
      return true;
    }

    disableSROA(CostIt);
  }

  return false;
}

bool CallAnalyzer::visitExtractValue(ExtractValueInst &I) {
  // Constant folding for extract value is trivial.
  Constant *C = dyn_cast<Constant>(I.getAggregateOperand());
  if (!C)
    C = SimplifiedValues.lookup(I.getAggregateOperand());
  if (C) {
    SimplifiedValues[&I] = ConstantExpr::getExtractValue(C, I.getIndices());
    return true;
  }

  // SROA can look through these but give them a cost.
  return false;
}

bool CallAnalyzer::visitInsertValue(InsertValueInst &I) {
  // Constant folding for insert value is trivial.
  Constant *AggC = dyn_cast<Constant>(I.getAggregateOperand());
  if (!AggC)
    AggC = SimplifiedValues.lookup(I.getAggregateOperand());
  Constant *InsertedC = dyn_cast<Constant>(I.getInsertedValueOperand());
  if (!InsertedC)
    InsertedC = SimplifiedValues.lookup(I.getInsertedValueOperand());
  if (AggC && InsertedC) {
    SimplifiedValues[&I] = ConstantExpr::getInsertValue(AggC, InsertedC,
                                                        I.getIndices());
    return true;
  }

  // SROA can look through these but give them a cost.
  return false;
}

/// \brief Try to simplify a call site.
///
/// Takes a concrete function and callsite and tries to actually simplify it by
/// analyzing the arguments and call itself with instsimplify. Returns true if
/// it has simplified the callsite to some other entity (a constant), making it
/// free.
bool CallAnalyzer::simplifyCallSite(Function *F, CallSite CS) {
  // FIXME: Using the instsimplify logic directly for this is inefficient
  // because we have to continually rebuild the argument list even when no
  // simplifications can be performed. Until that is fixed with remapping
  // inside of instsimplify, directly constant fold calls here.
  if (!canConstantFoldCallTo(F))
    return false;

  // Try to re-map the arguments to constants.
  SmallVector<Constant *, 4> ConstantArgs;
  ConstantArgs.reserve(CS.arg_size());
  for (CallSite::arg_iterator I = CS.arg_begin(), E = CS.arg_end();
       I != E; ++I) {
    Constant *C = dyn_cast<Constant>(*I);
    if (!C)
      C = dyn_cast_or_null<Constant>(SimplifiedValues.lookup(*I));
    if (!C)
      return false; // This argument doesn't map to a constant.

    ConstantArgs.push_back(C);
  }
  if (Constant *C = ConstantFoldCall(F, ConstantArgs)) {
    SimplifiedValues[CS.getInstruction()] = C;
    return true;
  }

  return false;
}

bool CallAnalyzer::visitCallSite(CallSite CS) {
  if (CS.hasFnAttr(Attribute::ReturnsTwice) &&
      !F.hasFnAttribute(Attribute::ReturnsTwice)) {
    // This aborts the entire analysis.
    ExposesReturnsTwice = true;
    return false;
  }
  if (CS.isCall() &&
      cast<CallInst>(CS.getInstruction())->cannotDuplicate())
    ContainsNoDuplicateCall = true;

  if (Function *F = CS.getCalledFunction()) {
    // When we have a concrete function, first try to simplify it directly.
    if (simplifyCallSite(F, CS))
      return true;

    // Next check if it is an intrinsic we know about.
    // FIXME: Lift this into part of the InstVisitor.
    if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(CS.getInstruction())) {
      switch (II->getIntrinsicID()) {
      default:
        return Base::visitCallSite(CS);

      case Intrinsic::memset:
      case Intrinsic::memcpy:
      case Intrinsic::memmove:
        // SROA can usually chew through these intrinsics, but they aren't free.
        return false;
      case Intrinsic::localescape:
        HasFrameEscape = true;
        return false;
      }
    }

    if (F == CS.getInstruction()->getParent()->getParent()) {
      // This flag will fully abort the analysis, so don't bother with anything
      // else.
      IsRecursiveCall = true;
      return false;
    }

    if (TTI.isLoweredToCall(F)) {
      // We account for the average 1 instruction per call argument setup
      // here.
      Cost += CS.arg_size() * InlineConstants::InstrCost;

      // Everything other than inline ASM will also have a significant cost
      // merely from making the call.
      if (!isa<InlineAsm>(CS.getCalledValue()))
        Cost += InlineConstants::CallPenalty;
    }

    return Base::visitCallSite(CS);
  }

  // Otherwise we're in a very special case -- an indirect function call. See
  // if we can be particularly clever about this.
  Value *Callee = CS.getCalledValue();

  // First, pay the price of the argument setup. We account for the average
  // 1 instruction per call argument setup here.
  Cost += CS.arg_size() * InlineConstants::InstrCost;

  // Next, check if this happens to be an indirect function call to a known
  // function in this inline context. If not, we've done all we can.
  Function *F = dyn_cast_or_null<Function>(SimplifiedValues.lookup(Callee));
  if (!F)
    return Base::visitCallSite(CS);

  // If we have a constant that we are calling as a function, we can peer
  // through it and see the function target. This happens not infrequently
  // during devirtualization and so we want to give it a hefty bonus for
  // inlining, but cap that bonus in the event that inlining wouldn't pan
  // out. Pretend to inline the function, with a custom threshold.
  CallAnalyzer CA(TTI, ACT, *F, InlineConstants::IndirectCallThreshold, CS);
  if (CA.analyzeCall(CS)) {
    // We were able to inline the indirect call! Subtract the cost from the
    // threshold to get the bonus we want to apply, but don't go below zero.
    Cost -= std::max(0, CA.getThreshold() - CA.getCost());
  }

  return Base::visitCallSite(CS);
}

bool CallAnalyzer::visitReturnInst(ReturnInst &RI) {
  // At least one return instruction will be free after inlining.
  bool Free = !HasReturn;
  HasReturn = true;
  return Free;
}

bool CallAnalyzer::visitBranchInst(BranchInst &BI) {
  // We model unconditional branches as essentially free -- they really
  // shouldn't exist at all, but handling them makes the behavior of the
  // inliner more regular and predictable. Interestingly, conditional branches
  // which will fold away are also free.
  return BI.isUnconditional() || isa<ConstantInt>(BI.getCondition()) ||
         dyn_cast_or_null<ConstantInt>(
             SimplifiedValues.lookup(BI.getCondition()));
}

bool CallAnalyzer::visitSwitchInst(SwitchInst &SI) {
  // We model unconditional switches as free, see the comments on handling
  // branches.
  if (isa<ConstantInt>(SI.getCondition()))
    return true;
  if (Value *V = SimplifiedValues.lookup(SI.getCondition()))
    if (isa<ConstantInt>(V))
      return true;

  // Otherwise, we need to accumulate a cost proportional to the number of
  // distinct successor blocks. This fan-out in the CFG cannot be represented
  // for free even if we can represent the core switch as a jumptable that
  // takes a single instruction.
  //
  // NB: We convert large switches which are just used to initialize large phi
  // nodes to lookup tables instead in simplify-cfg, so this shouldn't prevent
  // inlining those. It will prevent inlining in cases where the optimization
  // does not (yet) fire.
  SmallPtrSet<BasicBlock *, 8> SuccessorBlocks;
  SuccessorBlocks.insert(SI.getDefaultDest());
  for (auto I = SI.case_begin(), E = SI.case_end(); I != E; ++I)
    SuccessorBlocks.insert(I.getCaseSuccessor());
  // Add cost corresponding to the number of distinct destinations. The first
  // we model as free because of fallthrough.
  Cost += (SuccessorBlocks.size() - 1) * InlineConstants::InstrCost;
  return false;
}

bool CallAnalyzer::visitIndirectBrInst(IndirectBrInst &IBI) {
  // We never want to inline functions that contain an indirectbr.  This is
  // incorrect because all the blockaddress's (in static global initializers
  // for example) would be referring to the original function, and this
  // indirect jump would jump from the inlined copy of the function into the
  // original function which is extremely undefined behavior.
  // FIXME: This logic isn't really right; we can safely inline functions with
  // indirectbr's as long as no other function or global references the
  // blockaddress of a block within the current function.
  HasIndirectBr = true;
  return false;
}

bool CallAnalyzer::visitResumeInst(ResumeInst &RI) {
  // FIXME: It's not clear that a single instruction is an accurate model for
  // the inline cost of a resume instruction.
  return false;
}

bool CallAnalyzer::visitCleanupReturnInst(CleanupReturnInst &CRI) {
  // FIXME: It's not clear that a single instruction is an accurate model for
  // the inline cost of a cleanupret instruction.
  return false;
}

bool CallAnalyzer::visitCatchReturnInst(CatchReturnInst &CRI) {
  // FIXME: It's not clear that a single instruction is an accurate model for
  // the inline cost of a catchret instruction.
  return false;
}

bool CallAnalyzer::visitUnreachableInst(UnreachableInst &I) {
  // FIXME: It might be reasonably to discount the cost of instructions leading
  // to unreachable as they have the lowest possible impact on both runtime and
  // code size.
  return true; // No actual code is needed for unreachable.
}

bool CallAnalyzer::visitInstruction(Instruction &I) {
  // Some instructions are free. All of the free intrinsics can also be
  // handled by SROA, etc.
  if (TargetTransformInfo::TCC_Free == TTI.getUserCost(&I))
    return true;

  // We found something we don't understand or can't handle. Mark any SROA-able
  // values in the operand list as no longer viable.
  for (User::op_iterator OI = I.op_begin(), OE = I.op_end(); OI != OE; ++OI)
    disableSROA(*OI);

  return false;
}


/// \brief Analyze a basic block for its contribution to the inline cost.
///
/// This method walks the analyzer over every instruction in the given basic
/// block and accounts for their cost during inlining at this callsite. It
/// aborts early if the threshold has been exceeded or an impossible to inline
/// construct has been detected. It returns false if inlining is no longer
/// viable, and true if inlining remains viable.
bool CallAnalyzer::analyzeBlock(BasicBlock *BB,
                                SmallPtrSetImpl<const Value *> &EphValues) {
  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
    // FIXME: Currently, the number of instructions in a function regardless of
    // our ability to simplify them during inline to constants or dead code,
    // are actually used by the vector bonus heuristic. As long as that's true,
    // we have to special case debug intrinsics here to prevent differences in
    // inlining due to debug symbols. Eventually, the number of unsimplified
    // instructions shouldn't factor into the cost computation, but until then,
    // hack around it here.
    if (isa<DbgInfoIntrinsic>(I))
      continue;

    // Skip ephemeral values.
    if (EphValues.count(&*I))
      continue;

    ++NumInstructions;
    if (isa<ExtractElementInst>(I) || I->getType()->isVectorTy())
      ++NumVectorInstructions;

    // If the instruction is floating point, and the target says this operation
    // is expensive or the function has the "use-soft-float" attribute, this may
    // eventually become a library call. Treat the cost as such.
    if (I->getType()->isFloatingPointTy()) {
      bool hasSoftFloatAttr = false;

      // If the function has the "use-soft-float" attribute, mark it as
      // expensive.
      if (F.hasFnAttribute("use-soft-float")) {
        Attribute Attr = F.getFnAttribute("use-soft-float");
        StringRef Val = Attr.getValueAsString();
        if (Val == "true")
          hasSoftFloatAttr = true;
      }

      if (TTI.getFPOpCost(I->getType()) == TargetTransformInfo::TCC_Expensive ||
          hasSoftFloatAttr)
        Cost += InlineConstants::CallPenalty;
    }

    // If the instruction simplified to a constant, there is no cost to this
    // instruction. Visit the instructions using our InstVisitor to account for
    // all of the per-instruction logic. The visit tree returns true if we
    // consumed the instruction in any way, and false if the instruction's base
    // cost should count against inlining.
    if (Base::visit(&*I))
      ++NumInstructionsSimplified;
    else
      Cost += InlineConstants::InstrCost;

    // If the visit this instruction detected an uninlinable pattern, abort.
    if (IsRecursiveCall || ExposesReturnsTwice || HasDynamicAlloca ||
        HasIndirectBr || HasFrameEscape)
      return false;

    // If the caller is a recursive function then we don't want to inline
    // functions which allocate a lot of stack space because it would increase
    // the caller stack usage dramatically.
    if (IsCallerRecursive &&
        AllocatedSize > InlineConstants::TotalAllocaSizeRecursiveCaller)
      return false;

    // Check if we've past the maximum possible threshold so we don't spin in
    // huge basic blocks that will never inline.
    if (Cost > Threshold)
      return false;
  }

  return true;
}

/// \brief Compute the base pointer and cumulative constant offsets for V.
///
/// This strips all constant offsets off of V, leaving it the base pointer, and
/// accumulates the total constant offset applied in the returned constant. It
/// returns 0 if V is not a pointer, and returns the constant '0' if there are
/// no constant offsets applied.
ConstantInt *CallAnalyzer::stripAndComputeInBoundsConstantOffsets(Value *&V) {
  if (!V->getType()->isPointerTy())
    return nullptr;

  const DataLayout &DL = F.getParent()->getDataLayout();
  unsigned IntPtrWidth = DL.getPointerSizeInBits();
  APInt Offset = APInt::getNullValue(IntPtrWidth);

  // Even though we don't look through PHI nodes, we could be called on an
  // instruction in an unreachable block, which may be on a cycle.
  SmallPtrSet<Value *, 4> Visited;
  Visited.insert(V);
  do {
    if (GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
      if (!GEP->isInBounds() || !accumulateGEPOffset(*GEP, Offset))
        return nullptr;
      V = GEP->getPointerOperand();
    } else if (Operator::getOpcode(V) == Instruction::BitCast) {
      V = cast<Operator>(V)->getOperand(0);
    } else if (GlobalAlias *GA = dyn_cast<GlobalAlias>(V)) {
      if (GA->mayBeOverridden())
        break;
      V = GA->getAliasee();
    } else {
      break;
    }
    assert(V->getType()->isPointerTy() && "Unexpected operand type!");
  } while (Visited.insert(V).second);

  Type *IntPtrTy = DL.getIntPtrType(V->getContext());
  return cast<ConstantInt>(ConstantInt::get(IntPtrTy, Offset));
}

/// \brief Analyze a call site for potential inlining.
///
/// Returns true if inlining this call is viable, and false if it is not
/// viable. It computes the cost and adjusts the threshold based on numerous
/// factors and heuristics. If this method returns false but the computed cost
/// is below the computed threshold, then inlining was forcibly disabled by
/// some artifact of the routine.
bool CallAnalyzer::analyzeCall(CallSite CS) {
  ++NumCallsAnalyzed;

  // Perform some tweaks to the cost and threshold based on the direct
  // callsite information.

  // We want to more aggressively inline vector-dense kernels, so up the
  // threshold, and we'll lower it if the % of vector instructions gets too
  // low. Note that these bonuses are some what arbitrary and evolved over time
  // by accident as much as because they are principled bonuses.
  //
  // FIXME: It would be nice to remove all such bonuses. At least it would be
  // nice to base the bonus values on something more scientific.
  assert(NumInstructions == 0);
  assert(NumVectorInstructions == 0);

  // Update the threshold based on callsite properties
  updateThreshold(CS, F);

  FiftyPercentVectorBonus = 3 * Threshold / 2;
  TenPercentVectorBonus = 3 * Threshold / 4;
  const DataLayout &DL = F.getParent()->getDataLayout();

  // Track whether the post-inlining function would have more than one basic
  // block. A single basic block is often intended for inlining. Balloon the
  // threshold by 50% until we pass the single-BB phase.
  bool SingleBB = true;
  int SingleBBBonus = Threshold / 2;

  // Speculatively apply all possible bonuses to Threshold. If cost exceeds
  // this Threshold any time, and cost cannot decrease, we can stop processing
  // the rest of the function body.
  Threshold += (SingleBBBonus + FiftyPercentVectorBonus);

  // Give out bonuses per argument, as the instructions setting them up will
  // be gone after inlining.
  for (unsigned I = 0, E = CS.arg_size(); I != E; ++I) {
    if (CS.isByValArgument(I)) {
      // We approximate the number of loads and stores needed by dividing the
      // size of the byval type by the target's pointer size.
      PointerType *PTy = cast<PointerType>(CS.getArgument(I)->getType());
      unsigned TypeSize = DL.getTypeSizeInBits(PTy->getElementType());
      unsigned PointerSize = DL.getPointerSizeInBits();
      // Ceiling division.
      unsigned NumStores = (TypeSize + PointerSize - 1) / PointerSize;

      // If it generates more than 8 stores it is likely to be expanded as an
      // inline memcpy so we take that as an upper bound. Otherwise we assume
      // one load and one store per word copied.
      // FIXME: The maxStoresPerMemcpy setting from the target should be used
      // here instead of a magic number of 8, but it's not available via
      // DataLayout.
      NumStores = std::min(NumStores, 8U);

      Cost -= 2 * NumStores * InlineConstants::InstrCost;
    } else {
      // For non-byval arguments subtract off one instruction per call
      // argument.
      Cost -= InlineConstants::InstrCost;
    }
  }

  // If there is only one call of the function, and it has internal linkage,
  // the cost of inlining it drops dramatically.
  bool OnlyOneCallAndLocalLinkage = F.hasLocalLinkage() && F.hasOneUse() &&
    &F == CS.getCalledFunction();
  if (OnlyOneCallAndLocalLinkage)
    Cost += InlineConstants::LastCallToStaticBonus;

  // If the normal destination of the invoke or the parent block of the call
  // site is unreachable-terminated, there is little point in inlining this
  // unless there is literally zero cost.
  // FIXME: Note that it is possible that an unreachable-terminated block has a
  // hot entry. For example, in below scenario inlining hot_call_X() may be
  // beneficial :
  // main() {
  //   hot_call_1();
  //   ...
  //   hot_call_N()
  //   exit(0);
  // }
  // For now, we are not handling this corner case here as it is rare in real
  // code. In future, we should elaborate this based on BPI and BFI in more
  // general threshold adjusting heuristics in updateThreshold().
  Instruction *Instr = CS.getInstruction();
  if (InvokeInst *II = dyn_cast<InvokeInst>(Instr)) {
    if (isa<UnreachableInst>(II->getNormalDest()->getTerminator()))
      Threshold = 0;
  } else if (isa<UnreachableInst>(Instr->getParent()->getTerminator()))
    Threshold = 0;

  // If this function uses the coldcc calling convention, prefer not to inline
  // it.
  if (F.getCallingConv() == CallingConv::Cold)
    Cost += InlineConstants::ColdccPenalty;

  // Check if we're done. This can happen due to bonuses and penalties.
  if (Cost > Threshold)
    return false;

  if (F.empty())
    return true;

  Function *Caller = CS.getInstruction()->getParent()->getParent();
  // Check if the caller function is recursive itself.
  for (User *U : Caller->users()) {
    CallSite Site(U);
    if (!Site)
      continue;
    Instruction *I = Site.getInstruction();
    if (I->getParent()->getParent() == Caller) {
      IsCallerRecursive = true;
      break;
    }
  }

  // Populate our simplified values by mapping from function arguments to call
  // arguments with known important simplifications.
  CallSite::arg_iterator CAI = CS.arg_begin();
  for (Function::arg_iterator FAI = F.arg_begin(), FAE = F.arg_end();
       FAI != FAE; ++FAI, ++CAI) {
    assert(CAI != CS.arg_end());
    if (Constant *C = dyn_cast<Constant>(CAI))
      SimplifiedValues[&*FAI] = C;

    Value *PtrArg = *CAI;
    if (ConstantInt *C = stripAndComputeInBoundsConstantOffsets(PtrArg)) {
      ConstantOffsetPtrs[&*FAI] = std::make_pair(PtrArg, C->getValue());

      // We can SROA any pointer arguments derived from alloca instructions.
      if (isa<AllocaInst>(PtrArg)) {
        SROAArgValues[&*FAI] = PtrArg;
        SROAArgCosts[PtrArg] = 0;
      }
    }
  }
  NumConstantArgs = SimplifiedValues.size();
  NumConstantOffsetPtrArgs = ConstantOffsetPtrs.size();
  NumAllocaArgs = SROAArgValues.size();

  // FIXME: If a caller has multiple calls to a callee, we end up recomputing
  // the ephemeral values multiple times (and they're completely determined by
  // the callee, so this is purely duplicate work).
  SmallPtrSet<const Value *, 32> EphValues;
  CodeMetrics::collectEphemeralValues(&F, &ACT->getAssumptionCache(F), EphValues);

  // The worklist of live basic blocks in the callee *after* inlining. We avoid
  // adding basic blocks of the callee which can be proven to be dead for this
  // particular call site in order to get more accurate cost estimates. This
  // requires a somewhat heavyweight iteration pattern: we need to walk the
  // basic blocks in a breadth-first order as we insert live successors. To
  // accomplish this, prioritizing for small iterations because we exit after
  // crossing our threshold, we use a small-size optimized SetVector.
  typedef SetVector<BasicBlock *, SmallVector<BasicBlock *, 16>,
                                  SmallPtrSet<BasicBlock *, 16> > BBSetVector;
  BBSetVector BBWorklist;
  BBWorklist.insert(&F.getEntryBlock());
  // Note that we *must not* cache the size, this loop grows the worklist.
  for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
    // Bail out the moment we cross the threshold. This means we'll under-count
    // the cost, but only when undercounting doesn't matter.
    if (Cost > Threshold)
      break;

    BasicBlock *BB = BBWorklist[Idx];
    if (BB->empty())
      continue;

    // Disallow inlining a blockaddress. A blockaddress only has defined
    // behavior for an indirect branch in the same function, and we do not
    // currently support inlining indirect branches. But, the inliner may not
    // see an indirect branch that ends up being dead code at a particular call
    // site. If the blockaddress escapes the function, e.g., via a global
    // variable, inlining may lead to an invalid cross-function reference.
    if (BB->hasAddressTaken())
      return false;

    // Analyze the cost of this block. If we blow through the threshold, this
    // returns false, and we can bail on out.
    if (!analyzeBlock(BB, EphValues)) {
      if (IsRecursiveCall || ExposesReturnsTwice || HasDynamicAlloca ||
          HasIndirectBr || HasFrameEscape)
        return false;

      // If the caller is a recursive function then we don't want to inline
      // functions which allocate a lot of stack space because it would increase
      // the caller stack usage dramatically.
      if (IsCallerRecursive &&
          AllocatedSize > InlineConstants::TotalAllocaSizeRecursiveCaller)
        return false;

      break;
    }

    TerminatorInst *TI = BB->getTerminator();

    // Add in the live successors by first checking whether we have terminator
    // that may be simplified based on the values simplified by this call.
    if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
      if (BI->isConditional()) {
        Value *Cond = BI->getCondition();
        if (ConstantInt *SimpleCond
              = dyn_cast_or_null<ConstantInt>(SimplifiedValues.lookup(Cond))) {
          BBWorklist.insert(BI->getSuccessor(SimpleCond->isZero() ? 1 : 0));
          continue;
        }
      }
    } else if (SwitchInst *SI = dyn_cast<SwitchInst>(TI)) {
      Value *Cond = SI->getCondition();
      if (ConstantInt *SimpleCond
            = dyn_cast_or_null<ConstantInt>(SimplifiedValues.lookup(Cond))) {
        BBWorklist.insert(SI->findCaseValue(SimpleCond).getCaseSuccessor());
        continue;
      }
    }

    // If we're unable to select a particular successor, just count all of
    // them.
    for (unsigned TIdx = 0, TSize = TI->getNumSuccessors(); TIdx != TSize;
         ++TIdx)
      BBWorklist.insert(TI->getSuccessor(TIdx));

    // If we had any successors at this point, than post-inlining is likely to
    // have them as well. Note that we assume any basic blocks which existed
    // due to branches or switches which folded above will also fold after
    // inlining.
    if (SingleBB && TI->getNumSuccessors() > 1) {
      // Take off the bonus we applied to the threshold.
      Threshold -= SingleBBBonus;
      SingleBB = false;
    }
  }

  // If this is a noduplicate call, we can still inline as long as
  // inlining this would cause the removal of the caller (so the instruction
  // is not actually duplicated, just moved).
  if (!OnlyOneCallAndLocalLinkage && ContainsNoDuplicateCall)
    return false;

  // We applied the maximum possible vector bonus at the beginning. Now,
  // subtract the excess bonus, if any, from the Threshold before
  // comparing against Cost.
  if (NumVectorInstructions <= NumInstructions / 10)
    Threshold -= FiftyPercentVectorBonus;
  else if (NumVectorInstructions <= NumInstructions / 2)
    Threshold -= (FiftyPercentVectorBonus - TenPercentVectorBonus);

  return Cost < std::max(1, Threshold);
}

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
/// \brief Dump stats about this call's analysis.
LLVM_DUMP_METHOD void CallAnalyzer::dump() {
#define DEBUG_PRINT_STAT(x) dbgs() << "      " #x ": " << x << "\n"
  DEBUG_PRINT_STAT(NumConstantArgs);
  DEBUG_PRINT_STAT(NumConstantOffsetPtrArgs);
  DEBUG_PRINT_STAT(NumAllocaArgs);
  DEBUG_PRINT_STAT(NumConstantPtrCmps);
  DEBUG_PRINT_STAT(NumConstantPtrDiffs);
  DEBUG_PRINT_STAT(NumInstructionsSimplified);
  DEBUG_PRINT_STAT(NumInstructions);
  DEBUG_PRINT_STAT(SROACostSavings);
  DEBUG_PRINT_STAT(SROACostSavingsLost);
  DEBUG_PRINT_STAT(ContainsNoDuplicateCall);
  DEBUG_PRINT_STAT(Cost);
  DEBUG_PRINT_STAT(Threshold);
#undef DEBUG_PRINT_STAT
}
#endif

/// \brief Test that two functions either have or have not the given attribute
///        at the same time.
template<typename AttrKind>
static bool attributeMatches(Function *F1, Function *F2, AttrKind Attr) {
  return F1->getFnAttribute(Attr) == F2->getFnAttribute(Attr);
}

/// \brief Test that there are no attribute conflicts between Caller and Callee
///        that prevent inlining.
static bool functionsHaveCompatibleAttributes(Function *Caller,
                                              Function *Callee,
                                              TargetTransformInfo &TTI) {
  return TTI.areInlineCompatible(Caller, Callee) &&
         AttributeFuncs::areInlineCompatible(*Caller, *Callee);
}

InlineCost llvm::getInlineCost(CallSite CS, int DefaultThreshold,
                               TargetTransformInfo &CalleeTTI,
                               AssumptionCacheTracker *ACT) {
  return getInlineCost(CS, CS.getCalledFunction(), DefaultThreshold, CalleeTTI,
                       ACT);
}

int llvm::computeThresholdFromOptLevels(unsigned OptLevel,
                                        unsigned SizeOptLevel) {
  if (OptLevel > 2)
    return OptAggressiveThreshold;
  if (SizeOptLevel == 1) // -Os
    return OptSizeThreshold;
  if (SizeOptLevel == 2) // -Oz
    return OptMinSizeThreshold;
  return DefaultInlineThreshold;
}

int llvm::getDefaultInlineThreshold() { return DefaultInlineThreshold; }

InlineCost llvm::getInlineCost(CallSite CS, Function *Callee,
                               int DefaultThreshold,
                               TargetTransformInfo &CalleeTTI,
                               AssumptionCacheTracker *ACT) {

  // Cannot inline indirect calls.
  if (!Callee)
    return llvm::InlineCost::getNever();

  // Calls to functions with always-inline attributes should be inlined
  // whenever possible.
  if (CS.hasFnAttr(Attribute::AlwaysInline)) {
    if (isInlineViable(*Callee))
      return llvm::InlineCost::getAlways();
    return llvm::InlineCost::getNever();
  }

  // Never inline functions with conflicting attributes (unless callee has
  // always-inline attribute).
  if (!functionsHaveCompatibleAttributes(CS.getCaller(), Callee, CalleeTTI))
    return llvm::InlineCost::getNever();

  // Don't inline this call if the caller has the optnone attribute.
  if (CS.getCaller()->hasFnAttribute(Attribute::OptimizeNone))
    return llvm::InlineCost::getNever();

  // Don't inline functions which can be redefined at link-time to mean
  // something else.  Don't inline functions marked noinline or call sites
  // marked noinline.
  if (Callee->mayBeOverridden() ||
      Callee->hasFnAttribute(Attribute::NoInline) || CS.isNoInline())
    return llvm::InlineCost::getNever();

  DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
        << "...\n");

  CallAnalyzer CA(CalleeTTI, ACT, *Callee, DefaultThreshold, CS);
  bool ShouldInline = CA.analyzeCall(CS);

  DEBUG(CA.dump());

  // Check if there was a reason to force inlining or no inlining.
  if (!ShouldInline && CA.getCost() < CA.getThreshold())
    return InlineCost::getNever();
  if (ShouldInline && CA.getCost() >= CA.getThreshold())
    return InlineCost::getAlways();

  return llvm::InlineCost::get(CA.getCost(), CA.getThreshold());
}

bool llvm::isInlineViable(Function &F) {
  bool ReturnsTwice = F.hasFnAttribute(Attribute::ReturnsTwice);
  for (Function::iterator BI = F.begin(), BE = F.end(); BI != BE; ++BI) {
    // Disallow inlining of functions which contain indirect branches or
    // blockaddresses.
    if (isa<IndirectBrInst>(BI->getTerminator()) || BI->hasAddressTaken())
      return false;

    for (auto &II : *BI) {
      CallSite CS(&II);
      if (!CS)
        continue;

      // Disallow recursive calls.
      if (&F == CS.getCalledFunction())
        return false;

      // Disallow calls which expose returns-twice to a function not previously
      // attributed as such.
      if (!ReturnsTwice && CS.isCall() &&
          cast<CallInst>(CS.getInstruction())->canReturnTwice())
        return false;

      // Disallow inlining functions that call @llvm.localescape. Doing this
      // correctly would require major changes to the inliner.
      if (CS.getCalledFunction() &&
          CS.getCalledFunction()->getIntrinsicID() ==
              llvm::Intrinsic::localescape)
        return false;
    }
  }

  return true;
}