summaryrefslogtreecommitdiff
path: root/lib/Transforms/Scalar/CodeGenPrepare.cpp
blob: 74b8447c64b2c0cd34f1dd3ec53606b04977d40a (plain)
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
//===- CodeGenPrepare.cpp - Prepare a function for code generation --------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass munges the code in the input function to better prepare it for
// SelectionDAG-based code generation. This works around limitations in it's
// basic-block-at-a-time approach. It should eventually be removed.
//
//===----------------------------------------------------------------------===//

#define DEBUG_TYPE "codegenprepare"
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/DominatorInternals.h"
#include "llvm/Analysis/Dominators.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/ProfileInfo.h"
#include "llvm/Assembly/Writer.h"
#include "llvm/Constants.h"
#include "llvm/DataLayout.h"
#include "llvm/DerivedTypes.h"
#include "llvm/Function.h"
#include "llvm/IRBuilder.h"
#include "llvm/InlineAsm.h"
#include "llvm/Instructions.h"
#include "llvm/IntrinsicInst.h"
#include "llvm/Pass.h"
#include "llvm/Support/CallSite.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/GetElementPtrTypeIterator.h"
#include "llvm/Support/PatternMatch.h"
#include "llvm/Support/ValueHandle.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetLibraryInfo.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Transforms/Utils/AddrModeMatcher.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/BuildLibCalls.h"
#include "llvm/Transforms/Utils/BypassSlowDivision.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
using namespace llvm::PatternMatch;

STATISTIC(NumBlocksElim, "Number of blocks eliminated");
STATISTIC(NumPHIsElim,   "Number of trivial PHIs eliminated");
STATISTIC(NumGEPsElim,   "Number of GEPs converted to casts");
STATISTIC(NumCmpUses, "Number of uses of Cmp expressions replaced with uses of "
                      "sunken Cmps");
STATISTIC(NumCastUses, "Number of uses of Cast expressions replaced with uses "
                       "of sunken Casts");
STATISTIC(NumMemoryInsts, "Number of memory instructions whose address "
                          "computations were sunk");
STATISTIC(NumExtsMoved,  "Number of [s|z]ext instructions combined with loads");
STATISTIC(NumExtUses,    "Number of uses of [s|z]ext instructions optimized");
STATISTIC(NumRetsDup,    "Number of return instructions duplicated");
STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved");
STATISTIC(NumSelectsExpanded, "Number of selects turned into branches");

static cl::opt<bool> DisableBranchOpts(
  "disable-cgp-branch-opts", cl::Hidden, cl::init(false),
  cl::desc("Disable branch optimizations in CodeGenPrepare"));

static cl::opt<bool> DisableSelectToBranch(
  "disable-cgp-select2branch", cl::Hidden, cl::init(false),
  cl::desc("Disable select to branch conversion."));

namespace {
  class CodeGenPrepare : public FunctionPass {
    /// TLI - Keep a pointer of a TargetLowering to consult for determining
    /// transformation profitability.
    const TargetLowering *TLI;
    const TargetLibraryInfo *TLInfo;
    DominatorTree *DT;
    ProfileInfo *PFI;

    /// CurInstIterator - As we scan instructions optimizing them, this is the
    /// next instruction to optimize.  Xforms that can invalidate this should
    /// update it.
    BasicBlock::iterator CurInstIterator;

    /// Keeps track of non-local addresses that have been sunk into a block.
    /// This allows us to avoid inserting duplicate code for blocks with
    /// multiple load/stores of the same address.
    DenseMap<Value*, Value*> SunkAddrs;

    /// ModifiedDT - If CFG is modified in anyway, dominator tree may need to
    /// be updated.
    bool ModifiedDT;

    /// OptSize - True if optimizing for size.
    bool OptSize;

  public:
    static char ID; // Pass identification, replacement for typeid
    explicit CodeGenPrepare(const TargetLowering *tli = 0)
      : FunctionPass(ID), TLI(tli) {
        initializeCodeGenPreparePass(*PassRegistry::getPassRegistry());
      }
    bool runOnFunction(Function &F);

    const char *getPassName() const { return "CodeGen Prepare"; }

    virtual void getAnalysisUsage(AnalysisUsage &AU) const {
      AU.addPreserved<DominatorTree>();
      AU.addPreserved<ProfileInfo>();
      AU.addRequired<TargetLibraryInfo>();
    }

  private:
    bool EliminateFallThrough(Function &F);
    bool EliminateMostlyEmptyBlocks(Function &F);
    bool CanMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
    void EliminateMostlyEmptyBlock(BasicBlock *BB);
    bool OptimizeBlock(BasicBlock &BB);
    bool OptimizeInst(Instruction *I);
    bool OptimizeMemoryInst(Instruction *I, Value *Addr, Type *AccessTy);
    bool OptimizeInlineAsmInst(CallInst *CS);
    bool OptimizeCallInst(CallInst *CI);
    bool MoveExtToFormExtLoad(Instruction *I);
    bool OptimizeExtUses(Instruction *I);
    bool OptimizeSelectInst(SelectInst *SI);
    bool DupRetToEnableTailCallOpts(BasicBlock *BB);
    bool PlaceDbgValues(Function &F);
  };
}

char CodeGenPrepare::ID = 0;
INITIALIZE_PASS_BEGIN(CodeGenPrepare, "codegenprepare",
                "Optimize for code generation", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfo)
INITIALIZE_PASS_END(CodeGenPrepare, "codegenprepare",
                "Optimize for code generation", false, false)

FunctionPass *llvm::createCodeGenPreparePass(const TargetLowering *TLI) {
  return new CodeGenPrepare(TLI);
}

bool CodeGenPrepare::runOnFunction(Function &F) {
  bool EverMadeChange = false;

  ModifiedDT = false;
  TLInfo = &getAnalysis<TargetLibraryInfo>();
  DT = getAnalysisIfAvailable<DominatorTree>();
  PFI = getAnalysisIfAvailable<ProfileInfo>();
  OptSize = F.getAttributes().hasAttribute(AttributeSet::FunctionIndex,
                                           Attribute::OptimizeForSize);

  /// This optimization identifies DIV instructions that can be
  /// profitably bypassed and carried out with a shorter, faster divide.
  if (TLI && TLI->isSlowDivBypassed()) {
    const DenseMap<unsigned int, unsigned int> &BypassWidths =
       TLI->getBypassSlowDivWidths();
    for (Function::iterator I = F.begin(); I != F.end(); I++)
      EverMadeChange |= bypassSlowDivision(F, I, BypassWidths);
  }

  // Eliminate blocks that contain only PHI nodes and an
  // unconditional branch.
  EverMadeChange |= EliminateMostlyEmptyBlocks(F);

  // llvm.dbg.value is far away from the value then iSel may not be able
  // handle it properly. iSel will drop llvm.dbg.value if it can not
  // find a node corresponding to the value.
  EverMadeChange |= PlaceDbgValues(F);

  bool MadeChange = true;
  while (MadeChange) {
    MadeChange = false;
    for (Function::iterator I = F.begin(); I != F.end(); ) {
      BasicBlock *BB = I++;
      MadeChange |= OptimizeBlock(*BB);
    }
    EverMadeChange |= MadeChange;
  }

  SunkAddrs.clear();

  if (!DisableBranchOpts) {
    MadeChange = false;
    SmallPtrSet<BasicBlock*, 8> WorkList;
    for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB) {
      SmallVector<BasicBlock*, 2> Successors(succ_begin(BB), succ_end(BB));
      MadeChange |= ConstantFoldTerminator(BB, true);
      if (!MadeChange) continue;

      for (SmallVectorImpl<BasicBlock*>::iterator
             II = Successors.begin(), IE = Successors.end(); II != IE; ++II)
        if (pred_begin(*II) == pred_end(*II))
          WorkList.insert(*II);
    }

    // Delete the dead blocks and any of their dead successors.
    MadeChange |= !WorkList.empty();
    while (!WorkList.empty()) {
      BasicBlock *BB = *WorkList.begin();
      WorkList.erase(BB);
      SmallVector<BasicBlock*, 2> Successors(succ_begin(BB), succ_end(BB));

      DeleteDeadBlock(BB);
      
      for (SmallVectorImpl<BasicBlock*>::iterator
             II = Successors.begin(), IE = Successors.end(); II != IE; ++II)
        if (pred_begin(*II) == pred_end(*II))
          WorkList.insert(*II);
    }

    // Merge pairs of basic blocks with unconditional branches, connected by
    // a single edge.
    if (EverMadeChange || MadeChange)
      MadeChange |= EliminateFallThrough(F);

    if (MadeChange)
      ModifiedDT = true;
    EverMadeChange |= MadeChange;
  }

  if (ModifiedDT && DT)
    DT->DT->recalculate(F);

  return EverMadeChange;
}

/// EliminateFallThrough - Merge basic blocks which are connected
/// by a single edge, where one of the basic blocks has a single successor
/// pointing to the other basic block, which has a single predecessor.
bool CodeGenPrepare::EliminateFallThrough(Function &F) {
  bool Changed = false;
  // Scan all of the blocks in the function, except for the entry block.
  for (Function::iterator I = ++F.begin(), E = F.end(); I != E; ) {
    BasicBlock *BB = I++;
    // If the destination block has a single pred, then this is a trivial
    // edge, just collapse it.
    BasicBlock *SinglePred = BB->getSinglePredecessor();

    // Don't merge if BB's address is taken.
    if (!SinglePred || SinglePred == BB || BB->hasAddressTaken()) continue;

    BranchInst *Term = dyn_cast<BranchInst>(SinglePred->getTerminator());
    if (Term && !Term->isConditional()) {
      Changed = true;
      DEBUG(dbgs() << "To merge:\n"<< *SinglePred << "\n\n\n");
      // Remember if SinglePred was the entry block of the function.
      // If so, we will need to move BB back to the entry position.
      bool isEntry = SinglePred == &SinglePred->getParent()->getEntryBlock();
      MergeBasicBlockIntoOnlyPred(BB, this);

      if (isEntry && BB != &BB->getParent()->getEntryBlock())
        BB->moveBefore(&BB->getParent()->getEntryBlock());

      // We have erased a block. Update the iterator.
      I = BB;
    }
  }
  return Changed;
}

/// EliminateMostlyEmptyBlocks - eliminate blocks that contain only PHI nodes,
/// debug info directives, and an unconditional branch.  Passes before isel
/// (e.g. LSR/loopsimplify) often split edges in ways that are non-optimal for
/// isel.  Start by eliminating these blocks so we can split them the way we
/// want them.
bool CodeGenPrepare::EliminateMostlyEmptyBlocks(Function &F) {
  bool MadeChange = false;
  // Note that this intentionally skips the entry block.
  for (Function::iterator I = ++F.begin(), E = F.end(); I != E; ) {
    BasicBlock *BB = I++;

    // If this block doesn't end with an uncond branch, ignore it.
    BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator());
    if (!BI || !BI->isUnconditional())
      continue;

    // If the instruction before the branch (skipping debug info) isn't a phi
    // node, then other stuff is happening here.
    BasicBlock::iterator BBI = BI;
    if (BBI != BB->begin()) {
      --BBI;
      while (isa<DbgInfoIntrinsic>(BBI)) {
        if (BBI == BB->begin())
          break;
        --BBI;
      }
      if (!isa<DbgInfoIntrinsic>(BBI) && !isa<PHINode>(BBI))
        continue;
    }

    // Do not break infinite loops.
    BasicBlock *DestBB = BI->getSuccessor(0);
    if (DestBB == BB)
      continue;

    if (!CanMergeBlocks(BB, DestBB))
      continue;

    EliminateMostlyEmptyBlock(BB);
    MadeChange = true;
  }
  return MadeChange;
}

/// CanMergeBlocks - Return true if we can merge BB into DestBB if there is a
/// single uncond branch between them, and BB contains no other non-phi
/// instructions.
bool CodeGenPrepare::CanMergeBlocks(const BasicBlock *BB,
                                    const BasicBlock *DestBB) const {
  // We only want to eliminate blocks whose phi nodes are used by phi nodes in
  // the successor.  If there are more complex condition (e.g. preheaders),
  // don't mess around with them.
  BasicBlock::const_iterator BBI = BB->begin();
  while (const PHINode *PN = dyn_cast<PHINode>(BBI++)) {
    for (Value::const_use_iterator UI = PN->use_begin(), E = PN->use_end();
         UI != E; ++UI) {
      const Instruction *User = cast<Instruction>(*UI);
      if (User->getParent() != DestBB || !isa<PHINode>(User))
        return false;
      // If User is inside DestBB block and it is a PHINode then check
      // incoming value. If incoming value is not from BB then this is
      // a complex condition (e.g. preheaders) we want to avoid here.
      if (User->getParent() == DestBB) {
        if (const PHINode *UPN = dyn_cast<PHINode>(User))
          for (unsigned I = 0, E = UPN->getNumIncomingValues(); I != E; ++I) {
            Instruction *Insn = dyn_cast<Instruction>(UPN->getIncomingValue(I));
            if (Insn && Insn->getParent() == BB &&
                Insn->getParent() != UPN->getIncomingBlock(I))
              return false;
          }
      }
    }
  }

  // If BB and DestBB contain any common predecessors, then the phi nodes in BB
  // and DestBB may have conflicting incoming values for the block.  If so, we
  // can't merge the block.
  const PHINode *DestBBPN = dyn_cast<PHINode>(DestBB->begin());
  if (!DestBBPN) return true;  // no conflict.

  // Collect the preds of BB.
  SmallPtrSet<const BasicBlock*, 16> BBPreds;
  if (const PHINode *BBPN = dyn_cast<PHINode>(BB->begin())) {
    // It is faster to get preds from a PHI than with pred_iterator.
    for (unsigned i = 0, e = BBPN->getNumIncomingValues(); i != e; ++i)
      BBPreds.insert(BBPN->getIncomingBlock(i));
  } else {
    BBPreds.insert(pred_begin(BB), pred_end(BB));
  }

  // Walk the preds of DestBB.
  for (unsigned i = 0, e = DestBBPN->getNumIncomingValues(); i != e; ++i) {
    BasicBlock *Pred = DestBBPN->getIncomingBlock(i);
    if (BBPreds.count(Pred)) {   // Common predecessor?
      BBI = DestBB->begin();
      while (const PHINode *PN = dyn_cast<PHINode>(BBI++)) {
        const Value *V1 = PN->getIncomingValueForBlock(Pred);
        const Value *V2 = PN->getIncomingValueForBlock(BB);

        // If V2 is a phi node in BB, look up what the mapped value will be.
        if (const PHINode *V2PN = dyn_cast<PHINode>(V2))
          if (V2PN->getParent() == BB)
            V2 = V2PN->getIncomingValueForBlock(Pred);

        // If there is a conflict, bail out.
        if (V1 != V2) return false;
      }
    }
  }

  return true;
}


/// EliminateMostlyEmptyBlock - Eliminate a basic block that have only phi's and
/// an unconditional branch in it.
void CodeGenPrepare::EliminateMostlyEmptyBlock(BasicBlock *BB) {
  BranchInst *BI = cast<BranchInst>(BB->getTerminator());
  BasicBlock *DestBB = BI->getSuccessor(0);

  DEBUG(dbgs() << "MERGING MOSTLY EMPTY BLOCKS - BEFORE:\n" << *BB << *DestBB);

  // If the destination block has a single pred, then this is a trivial edge,
  // just collapse it.
  if (BasicBlock *SinglePred = DestBB->getSinglePredecessor()) {
    if (SinglePred != DestBB) {
      // Remember if SinglePred was the entry block of the function.  If so, we
      // will need to move BB back to the entry position.
      bool isEntry = SinglePred == &SinglePred->getParent()->getEntryBlock();
      MergeBasicBlockIntoOnlyPred(DestBB, this);

      if (isEntry && BB != &BB->getParent()->getEntryBlock())
        BB->moveBefore(&BB->getParent()->getEntryBlock());

      DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
      return;
    }
  }

  // Otherwise, we have multiple predecessors of BB.  Update the PHIs in DestBB
  // to handle the new incoming edges it is about to have.
  PHINode *PN;
  for (BasicBlock::iterator BBI = DestBB->begin();
       (PN = dyn_cast<PHINode>(BBI)); ++BBI) {
    // Remove the incoming value for BB, and remember it.
    Value *InVal = PN->removeIncomingValue(BB, false);

    // Two options: either the InVal is a phi node defined in BB or it is some
    // value that dominates BB.
    PHINode *InValPhi = dyn_cast<PHINode>(InVal);
    if (InValPhi && InValPhi->getParent() == BB) {
      // Add all of the input values of the input PHI as inputs of this phi.
      for (unsigned i = 0, e = InValPhi->getNumIncomingValues(); i != e; ++i)
        PN->addIncoming(InValPhi->getIncomingValue(i),
                        InValPhi->getIncomingBlock(i));
    } else {
      // Otherwise, add one instance of the dominating value for each edge that
      // we will be adding.
      if (PHINode *BBPN = dyn_cast<PHINode>(BB->begin())) {
        for (unsigned i = 0, e = BBPN->getNumIncomingValues(); i != e; ++i)
          PN->addIncoming(InVal, BBPN->getIncomingBlock(i));
      } else {
        for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI)
          PN->addIncoming(InVal, *PI);
      }
    }
  }

  // The PHIs are now updated, change everything that refers to BB to use
  // DestBB and remove BB.
  BB->replaceAllUsesWith(DestBB);
  if (DT && !ModifiedDT) {
    BasicBlock *BBIDom  = DT->getNode(BB)->getIDom()->getBlock();
    BasicBlock *DestBBIDom = DT->getNode(DestBB)->getIDom()->getBlock();
    BasicBlock *NewIDom = DT->findNearestCommonDominator(BBIDom, DestBBIDom);
    DT->changeImmediateDominator(DestBB, NewIDom);
    DT->eraseNode(BB);
  }
  if (PFI) {
    PFI->replaceAllUses(BB, DestBB);
    PFI->removeEdge(ProfileInfo::getEdge(BB, DestBB));
  }
  BB->eraseFromParent();
  ++NumBlocksElim;

  DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
}

/// OptimizeNoopCopyExpression - If the specified cast instruction is a noop
/// copy (e.g. it's casting from one pointer type to another, i32->i8 on PPC),
/// sink it into user blocks to reduce the number of virtual
/// registers that must be created and coalesced.
///
/// Return true if any changes are made.
///
static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI){
  // If this is a noop copy,
  EVT SrcVT = TLI.getValueType(CI->getOperand(0)->getType());
  EVT DstVT = TLI.getValueType(CI->getType());

  // This is an fp<->int conversion?
  if (SrcVT.isInteger() != DstVT.isInteger())
    return false;

  // If this is an extension, it will be a zero or sign extension, which
  // isn't a noop.
  if (SrcVT.bitsLT(DstVT)) return false;

  // If these values will be promoted, find out what they will be promoted
  // to.  This helps us consider truncates on PPC as noop copies when they
  // are.
  if (TLI.getTypeAction(CI->getContext(), SrcVT) ==
      TargetLowering::TypePromoteInteger)
    SrcVT = TLI.getTypeToTransformTo(CI->getContext(), SrcVT);
  if (TLI.getTypeAction(CI->getContext(), DstVT) ==
      TargetLowering::TypePromoteInteger)
    DstVT = TLI.getTypeToTransformTo(CI->getContext(), DstVT);

  // If, after promotion, these are the same types, this is a noop copy.
  if (SrcVT != DstVT)
    return false;

  BasicBlock *DefBB = CI->getParent();

  /// InsertedCasts - Only insert a cast in each block once.
  DenseMap<BasicBlock*, CastInst*> InsertedCasts;

  bool MadeChange = false;
  for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end();
       UI != E; ) {
    Use &TheUse = UI.getUse();
    Instruction *User = cast<Instruction>(*UI);

    // Figure out which BB this cast is used in.  For PHI's this is the
    // appropriate predecessor block.
    BasicBlock *UserBB = User->getParent();
    if (PHINode *PN = dyn_cast<PHINode>(User)) {
      UserBB = PN->getIncomingBlock(UI);
    }

    // Preincrement use iterator so we don't invalidate it.
    ++UI;

    // If this user is in the same block as the cast, don't change the cast.
    if (UserBB == DefBB) continue;

    // If we have already inserted a cast into this block, use it.
    CastInst *&InsertedCast = InsertedCasts[UserBB];

    if (!InsertedCast) {
      BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
      InsertedCast =
        CastInst::Create(CI->getOpcode(), CI->getOperand(0), CI->getType(), "",
                         InsertPt);
      MadeChange = true;
    }

    // Replace a use of the cast with a use of the new cast.
    TheUse = InsertedCast;
    ++NumCastUses;
  }

  // If we removed all uses, nuke the cast.
  if (CI->use_empty()) {
    CI->eraseFromParent();
    MadeChange = true;
  }

  return MadeChange;
}

/// OptimizeCmpExpression - sink the given CmpInst into user blocks to reduce
/// the number of virtual registers that must be created and coalesced.  This is
/// a clear win except on targets with multiple condition code registers
///  (PowerPC), where it might lose; some adjustment may be wanted there.
///
/// Return true if any changes are made.
static bool OptimizeCmpExpression(CmpInst *CI) {
  BasicBlock *DefBB = CI->getParent();

  /// InsertedCmp - Only insert a cmp in each block once.
  DenseMap<BasicBlock*, CmpInst*> InsertedCmps;

  bool MadeChange = false;
  for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end();
       UI != E; ) {
    Use &TheUse = UI.getUse();
    Instruction *User = cast<Instruction>(*UI);

    // Preincrement use iterator so we don't invalidate it.
    ++UI;

    // Don't bother for PHI nodes.
    if (isa<PHINode>(User))
      continue;

    // Figure out which BB this cmp is used in.
    BasicBlock *UserBB = User->getParent();

    // If this user is in the same block as the cmp, don't change the cmp.
    if (UserBB == DefBB) continue;

    // If we have already inserted a cmp into this block, use it.
    CmpInst *&InsertedCmp = InsertedCmps[UserBB];

    if (!InsertedCmp) {
      BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
      InsertedCmp =
        CmpInst::Create(CI->getOpcode(),
                        CI->getPredicate(),  CI->getOperand(0),
                        CI->getOperand(1), "", InsertPt);
      MadeChange = true;
    }

    // Replace a use of the cmp with a use of the new cmp.
    TheUse = InsertedCmp;
    ++NumCmpUses;
  }

  // If we removed all uses, nuke the cmp.
  if (CI->use_empty())
    CI->eraseFromParent();

  return MadeChange;
}

namespace {
class CodeGenPrepareFortifiedLibCalls : public SimplifyFortifiedLibCalls {
protected:
  void replaceCall(Value *With) {
    CI->replaceAllUsesWith(With);
    CI->eraseFromParent();
  }
  bool isFoldable(unsigned SizeCIOp, unsigned, bool) const {
      if (ConstantInt *SizeCI =
                             dyn_cast<ConstantInt>(CI->getArgOperand(SizeCIOp)))
        return SizeCI->isAllOnesValue();
    return false;
  }
};
} // end anonymous namespace

bool CodeGenPrepare::OptimizeCallInst(CallInst *CI) {
  BasicBlock *BB = CI->getParent();

  // Lower inline assembly if we can.
  // If we found an inline asm expession, and if the target knows how to
  // lower it to normal LLVM code, do so now.
  if (TLI && isa<InlineAsm>(CI->getCalledValue())) {
    if (TLI->ExpandInlineAsm(CI)) {
      // Avoid invalidating the iterator.
      CurInstIterator = BB->begin();
      // Avoid processing instructions out of order, which could cause
      // reuse before a value is defined.
      SunkAddrs.clear();
      return true;
    }
    // Sink address computing for memory operands into the block.
    if (OptimizeInlineAsmInst(CI))
      return true;
  }

  // Lower all uses of llvm.objectsize.*
  IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
  if (II && II->getIntrinsicID() == Intrinsic::objectsize) {
    bool Min = (cast<ConstantInt>(II->getArgOperand(1))->getZExtValue() == 1);
    Type *ReturnTy = CI->getType();
    Constant *RetVal = ConstantInt::get(ReturnTy, Min ? 0 : -1ULL);

    // Substituting this can cause recursive simplifications, which can
    // invalidate our iterator.  Use a WeakVH to hold onto it in case this
    // happens.
    WeakVH IterHandle(CurInstIterator);

    replaceAndRecursivelySimplify(CI, RetVal, TLI ? TLI->getDataLayout() : 0,
                                  TLInfo, ModifiedDT ? 0 : DT);

    // If the iterator instruction was recursively deleted, start over at the
    // start of the block.
    if (IterHandle != CurInstIterator) {
      CurInstIterator = BB->begin();
      SunkAddrs.clear();
    }
    return true;
  }

  if (II && TLI) {
    SmallVector<Value*, 2> PtrOps;
    Type *AccessTy;
    if (TLI->GetAddrModeArguments(II, PtrOps, AccessTy))
      while (!PtrOps.empty())
        if (OptimizeMemoryInst(II, PtrOps.pop_back_val(), AccessTy))
          return true;
  }

  // From here on out we're working with named functions.
  if (CI->getCalledFunction() == 0) return false;

  // We'll need DataLayout from here on out.
  const DataLayout *TD = TLI ? TLI->getDataLayout() : 0;
  if (!TD) return false;

  // Lower all default uses of _chk calls.  This is very similar
  // to what InstCombineCalls does, but here we are only lowering calls
  // that have the default "don't know" as the objectsize.  Anything else
  // should be left alone.
  CodeGenPrepareFortifiedLibCalls Simplifier;
  return Simplifier.fold(CI, TD, TLInfo);
}

/// DupRetToEnableTailCallOpts - Look for opportunities to duplicate return
/// instructions to the predecessor to enable tail call optimizations. The
/// case it is currently looking for is:
/// @code
/// bb0:
///   %tmp0 = tail call i32 @f0()
///   br label %return
/// bb1:
///   %tmp1 = tail call i32 @f1()
///   br label %return
/// bb2:
///   %tmp2 = tail call i32 @f2()
///   br label %return
/// return:
///   %retval = phi i32 [ %tmp0, %bb0 ], [ %tmp1, %bb1 ], [ %tmp2, %bb2 ]
///   ret i32 %retval
/// @endcode
///
/// =>
///
/// @code
/// bb0:
///   %tmp0 = tail call i32 @f0()
///   ret i32 %tmp0
/// bb1:
///   %tmp1 = tail call i32 @f1()
///   ret i32 %tmp1
/// bb2:
///   %tmp2 = tail call i32 @f2()
///   ret i32 %tmp2
/// @endcode
bool CodeGenPrepare::DupRetToEnableTailCallOpts(BasicBlock *BB) {
  if (!TLI)
    return false;

  ReturnInst *RI = dyn_cast<ReturnInst>(BB->getTerminator());
  if (!RI)
    return false;

  PHINode *PN = 0;
  BitCastInst *BCI = 0;
  Value *V = RI->getReturnValue();
  if (V) {
    BCI = dyn_cast<BitCastInst>(V);
    if (BCI)
      V = BCI->getOperand(0);

    PN = dyn_cast<PHINode>(V);
    if (!PN)
      return false;
  }

  if (PN && PN->getParent() != BB)
    return false;

  // It's not safe to eliminate the sign / zero extension of the return value.
  // See llvm::isInTailCallPosition().
  const Function *F = BB->getParent();
  Attribute CallerRetAttr = F->getAttributes().getRetAttributes();
  if (CallerRetAttr.hasAttribute(Attribute::ZExt) ||
      CallerRetAttr.hasAttribute(Attribute::SExt))
    return false;

  // Make sure there are no instructions between the PHI and return, or that the
  // return is the first instruction in the block.
  if (PN) {
    BasicBlock::iterator BI = BB->begin();
    do { ++BI; } while (isa<DbgInfoIntrinsic>(BI));
    if (&*BI == BCI)
      // Also skip over the bitcast.
      ++BI;
    if (&*BI != RI)
      return false;
  } else {
    BasicBlock::iterator BI = BB->begin();
    while (isa<DbgInfoIntrinsic>(BI)) ++BI;
    if (&*BI != RI)
      return false;
  }

  /// Only dup the ReturnInst if the CallInst is likely to be emitted as a tail
  /// call.
  SmallVector<CallInst*, 4> TailCalls;
  if (PN) {
    for (unsigned I = 0, E = PN->getNumIncomingValues(); I != E; ++I) {
      CallInst *CI = dyn_cast<CallInst>(PN->getIncomingValue(I));
      // Make sure the phi value is indeed produced by the tail call.
      if (CI && CI->hasOneUse() && CI->getParent() == PN->getIncomingBlock(I) &&
          TLI->mayBeEmittedAsTailCall(CI))
        TailCalls.push_back(CI);
    }
  } else {
    SmallPtrSet<BasicBlock*, 4> VisitedBBs;
    for (pred_iterator PI = pred_begin(BB), PE = pred_end(BB); PI != PE; ++PI) {
      if (!VisitedBBs.insert(*PI))
        continue;

      BasicBlock::InstListType &InstList = (*PI)->getInstList();
      BasicBlock::InstListType::reverse_iterator RI = InstList.rbegin();
      BasicBlock::InstListType::reverse_iterator RE = InstList.rend();
      do { ++RI; } while (RI != RE && isa<DbgInfoIntrinsic>(&*RI));
      if (RI == RE)
        continue;

      CallInst *CI = dyn_cast<CallInst>(&*RI);
      if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI))
        TailCalls.push_back(CI);
    }
  }

  bool Changed = false;
  for (unsigned i = 0, e = TailCalls.size(); i != e; ++i) {
    CallInst *CI = TailCalls[i];
    CallSite CS(CI);

    // Conservatively require the attributes of the call to match those of the
    // return. Ignore noalias because it doesn't affect the call sequence.
    Attribute CalleeRetAttr = CS.getAttributes().getRetAttributes();
    if (AttrBuilder(CalleeRetAttr).
          removeAttribute(Attribute::NoAlias) !=
        AttrBuilder(CallerRetAttr).
          removeAttribute(Attribute::NoAlias))
      continue;

    // Make sure the call instruction is followed by an unconditional branch to
    // the return block.
    BasicBlock *CallBB = CI->getParent();
    BranchInst *BI = dyn_cast<BranchInst>(CallBB->getTerminator());
    if (!BI || !BI->isUnconditional() || BI->getSuccessor(0) != BB)
      continue;

    // Duplicate the return into CallBB.
    (void)FoldReturnIntoUncondBranch(RI, BB, CallBB);
    ModifiedDT = Changed = true;
    ++NumRetsDup;
  }

  // If we eliminated all predecessors of the block, delete the block now.
  if (Changed && !BB->hasAddressTaken() && pred_begin(BB) == pred_end(BB))
    BB->eraseFromParent();

  return Changed;
}

//===----------------------------------------------------------------------===//
// Memory Optimization
//===----------------------------------------------------------------------===//

/// IsNonLocalValue - Return true if the specified values are defined in a
/// different basic block than BB.
static bool IsNonLocalValue(Value *V, BasicBlock *BB) {
  if (Instruction *I = dyn_cast<Instruction>(V))
    return I->getParent() != BB;
  return false;
}

/// OptimizeMemoryInst - Load and Store Instructions often have
/// addressing modes that can do significant amounts of computation.  As such,
/// instruction selection will try to get the load or store to do as much
/// computation as possible for the program.  The problem is that isel can only
/// see within a single block.  As such, we sink as much legal addressing mode
/// stuff into the block as possible.
///
/// This method is used to optimize both load/store and inline asms with memory
/// operands.
bool CodeGenPrepare::OptimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
                                        Type *AccessTy) {
  Value *Repl = Addr;

  // Try to collapse single-value PHI nodes.  This is necessary to undo
  // unprofitable PRE transformations.
  SmallVector<Value*, 8> worklist;
  SmallPtrSet<Value*, 16> Visited;
  worklist.push_back(Addr);

  // Use a worklist to iteratively look through PHI nodes, and ensure that
  // the addressing mode obtained from the non-PHI roots of the graph
  // are equivalent.
  Value *Consensus = 0;
  unsigned NumUsesConsensus = 0;
  bool IsNumUsesConsensusValid = false;
  SmallVector<Instruction*, 16> AddrModeInsts;
  ExtAddrMode AddrMode;
  while (!worklist.empty()) {
    Value *V = worklist.back();
    worklist.pop_back();

    // Break use-def graph loops.
    if (!Visited.insert(V)) {
      Consensus = 0;
      break;
    }

    // For a PHI node, push all of its incoming values.
    if (PHINode *P = dyn_cast<PHINode>(V)) {
      for (unsigned i = 0, e = P->getNumIncomingValues(); i != e; ++i)
        worklist.push_back(P->getIncomingValue(i));
      continue;
    }

    // For non-PHIs, determine the addressing mode being computed.
    SmallVector<Instruction*, 16> NewAddrModeInsts;
    ExtAddrMode NewAddrMode =
      AddressingModeMatcher::Match(V, AccessTy, MemoryInst,
                                   NewAddrModeInsts, *TLI);

    // This check is broken into two cases with very similar code to avoid using
    // getNumUses() as much as possible. Some values have a lot of uses, so
    // calling getNumUses() unconditionally caused a significant compile-time
    // regression.
    if (!Consensus) {
      Consensus = V;
      AddrMode = NewAddrMode;
      AddrModeInsts = NewAddrModeInsts;
      continue;
    } else if (NewAddrMode == AddrMode) {
      if (!IsNumUsesConsensusValid) {
        NumUsesConsensus = Consensus->getNumUses();
        IsNumUsesConsensusValid = true;
      }

      // Ensure that the obtained addressing mode is equivalent to that obtained
      // for all other roots of the PHI traversal.  Also, when choosing one
      // such root as representative, select the one with the most uses in order
      // to keep the cost modeling heuristics in AddressingModeMatcher
      // applicable.
      unsigned NumUses = V->getNumUses();
      if (NumUses > NumUsesConsensus) {
        Consensus = V;
        NumUsesConsensus = NumUses;
        AddrModeInsts = NewAddrModeInsts;
      }
      continue;
    }

    Consensus = 0;
    break;
  }

  // If the addressing mode couldn't be determined, or if multiple different
  // ones were determined, bail out now.
  if (!Consensus) return false;

  // Check to see if any of the instructions supersumed by this addr mode are
  // non-local to I's BB.
  bool AnyNonLocal = false;
  for (unsigned i = 0, e = AddrModeInsts.size(); i != e; ++i) {
    if (IsNonLocalValue(AddrModeInsts[i], MemoryInst->getParent())) {
      AnyNonLocal = true;
      break;
    }
  }

  // If all the instructions matched are already in this BB, don't do anything.
  if (!AnyNonLocal) {
    DEBUG(dbgs() << "CGP: Found      local addrmode: " << AddrMode << "\n");
    return false;
  }

  // Insert this computation right after this user.  Since our caller is
  // scanning from the top of the BB to the bottom, reuse of the expr are
  // guaranteed to happen later.
  IRBuilder<> Builder(MemoryInst);

  // Now that we determined the addressing expression we want to use and know
  // that we have to sink it into this block.  Check to see if we have already
  // done this for some other load/store instr in this block.  If so, reuse the
  // computation.
  Value *&SunkAddr = SunkAddrs[Addr];
  if (SunkAddr) {
    DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode << " for "
                 << *MemoryInst);
    if (SunkAddr->getType() != Addr->getType())
      SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
  } else {
    DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
                 << *MemoryInst);
    Type *IntPtrTy =
          TLI->getDataLayout()->getIntPtrType(AccessTy->getContext());

    Value *Result = 0;

    // Start with the base register. Do this first so that subsequent address
    // matching finds it last, which will prevent it from trying to match it
    // as the scaled value in case it happens to be a mul. That would be
    // problematic if we've sunk a different mul for the scale, because then
    // we'd end up sinking both muls.
    if (AddrMode.BaseReg) {
      Value *V = AddrMode.BaseReg;
      if (V->getType()->isPointerTy())
        V = Builder.CreatePtrToInt(V, IntPtrTy, "sunkaddr");
      if (V->getType() != IntPtrTy)
        V = Builder.CreateIntCast(V, IntPtrTy, /*isSigned=*/true, "sunkaddr");
      Result = V;
    }

    // Add the scale value.
    if (AddrMode.Scale) {
      Value *V = AddrMode.ScaledReg;
      if (V->getType() == IntPtrTy) {
        // done.
      } else if (V->getType()->isPointerTy()) {
        V = Builder.CreatePtrToInt(V, IntPtrTy, "sunkaddr");
      } else if (cast<IntegerType>(IntPtrTy)->getBitWidth() <
                 cast<IntegerType>(V->getType())->getBitWidth()) {
        V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
      } else {
        V = Builder.CreateSExt(V, IntPtrTy, "sunkaddr");
      }
      if (AddrMode.Scale != 1)
        V = Builder.CreateMul(V, ConstantInt::get(IntPtrTy, AddrMode.Scale),
                              "sunkaddr");
      if (Result)
        Result = Builder.CreateAdd(Result, V, "sunkaddr");
      else
        Result = V;
    }

    // Add in the BaseGV if present.
    if (AddrMode.BaseGV) {
      Value *V = Builder.CreatePtrToInt(AddrMode.BaseGV, IntPtrTy, "sunkaddr");
      if (Result)
        Result = Builder.CreateAdd(Result, V, "sunkaddr");
      else
        Result = V;
    }

    // Add in the Base Offset if present.
    if (AddrMode.BaseOffs) {
      Value *V = ConstantInt::get(IntPtrTy, AddrMode.BaseOffs);
      if (Result)
        Result = Builder.CreateAdd(Result, V, "sunkaddr");
      else
        Result = V;
    }

    if (Result == 0)
      SunkAddr = Constant::getNullValue(Addr->getType());
    else
      SunkAddr = Builder.CreateIntToPtr(Result, Addr->getType(), "sunkaddr");
  }

  MemoryInst->replaceUsesOfWith(Repl, SunkAddr);

  // If we have no uses, recursively delete the value and all dead instructions
  // using it.
  if (Repl->use_empty()) {
    // This can cause recursive deletion, which can invalidate our iterator.
    // Use a WeakVH to hold onto it in case this happens.
    WeakVH IterHandle(CurInstIterator);
    BasicBlock *BB = CurInstIterator->getParent();

    RecursivelyDeleteTriviallyDeadInstructions(Repl, TLInfo);

    if (IterHandle != CurInstIterator) {
      // If the iterator instruction was recursively deleted, start over at the
      // start of the block.
      CurInstIterator = BB->begin();
      SunkAddrs.clear();
    } else {
      // This address is now available for reassignment, so erase the table
      // entry; we don't want to match some completely different instruction.
      SunkAddrs[Addr] = 0;
    }
  }
  ++NumMemoryInsts;
  return true;
}

/// OptimizeInlineAsmInst - If there are any memory operands, use
/// OptimizeMemoryInst to sink their address computing into the block when
/// possible / profitable.
bool CodeGenPrepare::OptimizeInlineAsmInst(CallInst *CS) {
  bool MadeChange = false;

  TargetLowering::AsmOperandInfoVector
    TargetConstraints = TLI->ParseConstraints(CS);
  unsigned ArgNo = 0;
  for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
    TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];

    // Compute the constraint code and ConstraintType to use.
    TLI->ComputeConstraintToUse(OpInfo, SDValue());

    if (OpInfo.ConstraintType == TargetLowering::C_Memory &&
        OpInfo.isIndirect) {
      Value *OpVal = CS->getArgOperand(ArgNo++);
      MadeChange |= OptimizeMemoryInst(CS, OpVal, OpVal->getType());
    } else if (OpInfo.Type == InlineAsm::isInput)
      ArgNo++;
  }

  return MadeChange;
}

/// MoveExtToFormExtLoad - Move a zext or sext fed by a load into the same
/// basic block as the load, unless conditions are unfavorable. This allows
/// SelectionDAG to fold the extend into the load.
///
bool CodeGenPrepare::MoveExtToFormExtLoad(Instruction *I) {
  // Look for a load being extended.
  LoadInst *LI = dyn_cast<LoadInst>(I->getOperand(0));
  if (!LI) return false;

  // If they're already in the same block, there's nothing to do.
  if (LI->getParent() == I->getParent())
    return false;

  // If the load has other users and the truncate is not free, this probably
  // isn't worthwhile.
  if (!LI->hasOneUse() &&
      TLI && (TLI->isTypeLegal(TLI->getValueType(LI->getType())) ||
              !TLI->isTypeLegal(TLI->getValueType(I->getType()))) &&
      !TLI->isTruncateFree(I->getType(), LI->getType()))
    return false;

  // Check whether the target supports casts folded into loads.
  unsigned LType;
  if (isa<ZExtInst>(I))
    LType = ISD::ZEXTLOAD;
  else {
    assert(isa<SExtInst>(I) && "Unexpected ext type!");
    LType = ISD::SEXTLOAD;
  }
  if (TLI && !TLI->isLoadExtLegal(LType, TLI->getValueType(LI->getType())))
    return false;

  // Move the extend into the same block as the load, so that SelectionDAG
  // can fold it.
  I->removeFromParent();
  I->insertAfter(LI);
  ++NumExtsMoved;
  return true;
}

bool CodeGenPrepare::OptimizeExtUses(Instruction *I) {
  BasicBlock *DefBB = I->getParent();

  // If the result of a {s|z}ext and its source are both live out, rewrite all
  // other uses of the source with result of extension.
  Value *Src = I->getOperand(0);
  if (Src->hasOneUse())
    return false;

  // Only do this xform if truncating is free.
  if (TLI && !TLI->isTruncateFree(I->getType(), Src->getType()))
    return false;

  // Only safe to perform the optimization if the source is also defined in
  // this block.
  if (!isa<Instruction>(Src) || DefBB != cast<Instruction>(Src)->getParent())
    return false;

  bool DefIsLiveOut = false;
  for (Value::use_iterator UI = I->use_begin(), E = I->use_end();
       UI != E; ++UI) {
    Instruction *User = cast<Instruction>(*UI);

    // Figure out which BB this ext is used in.
    BasicBlock *UserBB = User->getParent();
    if (UserBB == DefBB) continue;
    DefIsLiveOut = true;
    break;
  }
  if (!DefIsLiveOut)
    return false;

  // Make sure non of the uses are PHI nodes.
  for (Value::use_iterator UI = Src->use_begin(), E = Src->use_end();
       UI != E; ++UI) {
    Instruction *User = cast<Instruction>(*UI);
    BasicBlock *UserBB = User->getParent();
    if (UserBB == DefBB) continue;
    // Be conservative. We don't want this xform to end up introducing
    // reloads just before load / store instructions.
    if (isa<PHINode>(User) || isa<LoadInst>(User) || isa<StoreInst>(User))
      return false;
  }

  // InsertedTruncs - Only insert one trunc in each block once.
  DenseMap<BasicBlock*, Instruction*> InsertedTruncs;

  bool MadeChange = false;
  for (Value::use_iterator UI = Src->use_begin(), E = Src->use_end();
       UI != E; ++UI) {
    Use &TheUse = UI.getUse();
    Instruction *User = cast<Instruction>(*UI);

    // Figure out which BB this ext is used in.
    BasicBlock *UserBB = User->getParent();
    if (UserBB == DefBB) continue;

    // Both src and def are live in this block. Rewrite the use.
    Instruction *&InsertedTrunc = InsertedTruncs[UserBB];

    if (!InsertedTrunc) {
      BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
      InsertedTrunc = new TruncInst(I, Src->getType(), "", InsertPt);
    }

    // Replace a use of the {s|z}ext source with a use of the result.
    TheUse = InsertedTrunc;
    ++NumExtUses;
    MadeChange = true;
  }

  return MadeChange;
}

/// isFormingBranchFromSelectProfitable - Returns true if a SelectInst should be
/// turned into an explicit branch.
static bool isFormingBranchFromSelectProfitable(SelectInst *SI) {
  // FIXME: This should use the same heuristics as IfConversion to determine
  // whether a select is better represented as a branch.  This requires that
  // branch probability metadata is preserved for the select, which is not the
  // case currently.

  CmpInst *Cmp = dyn_cast<CmpInst>(SI->getCondition());

  // If the branch is predicted right, an out of order CPU can avoid blocking on
  // the compare.  Emit cmovs on compares with a memory operand as branches to
  // avoid stalls on the load from memory.  If the compare has more than one use
  // there's probably another cmov or setcc around so it's not worth emitting a
  // branch.
  if (!Cmp)
    return false;

  Value *CmpOp0 = Cmp->getOperand(0);
  Value *CmpOp1 = Cmp->getOperand(1);

  // We check that the memory operand has one use to avoid uses of the loaded
  // value directly after the compare, making branches unprofitable.
  return Cmp->hasOneUse() &&
         ((isa<LoadInst>(CmpOp0) && CmpOp0->hasOneUse()) ||
          (isa<LoadInst>(CmpOp1) && CmpOp1->hasOneUse()));
}


/// If we have a SelectInst that will likely profit from branch prediction,
/// turn it into a branch.
bool CodeGenPrepare::OptimizeSelectInst(SelectInst *SI) {
  bool VectorCond = !SI->getCondition()->getType()->isIntegerTy(1);

  // Can we convert the 'select' to CF ?
  if (DisableSelectToBranch || OptSize || !TLI || VectorCond)
    return false;

  TargetLowering::SelectSupportKind SelectKind;
  if (VectorCond)
    SelectKind = TargetLowering::VectorMaskSelect;
  else if (SI->getType()->isVectorTy())
    SelectKind = TargetLowering::ScalarCondVectorVal;
  else
    SelectKind = TargetLowering::ScalarValSelect;

  // Do we have efficient codegen support for this kind of 'selects' ?
  if (TLI->isSelectSupported(SelectKind)) {
    // We have efficient codegen support for the select instruction.
    // Check if it is profitable to keep this 'select'.
    if (!TLI->isPredictableSelectExpensive() ||
        !isFormingBranchFromSelectProfitable(SI))
      return false;
  }

  ModifiedDT = true;

  // First, we split the block containing the select into 2 blocks.
  BasicBlock *StartBlock = SI->getParent();
  BasicBlock::iterator SplitPt = ++(BasicBlock::iterator(SI));
  BasicBlock *NextBlock = StartBlock->splitBasicBlock(SplitPt, "select.end");

  // Create a new block serving as the landing pad for the branch.
  BasicBlock *SmallBlock = BasicBlock::Create(SI->getContext(), "select.mid",
                                             NextBlock->getParent(), NextBlock);

  // Move the unconditional branch from the block with the select in it into our
  // landing pad block.
  StartBlock->getTerminator()->eraseFromParent();
  BranchInst::Create(NextBlock, SmallBlock);

  // Insert the real conditional branch based on the original condition.
  BranchInst::Create(NextBlock, SmallBlock, SI->getCondition(), SI);

  // The select itself is replaced with a PHI Node.
  PHINode *PN = PHINode::Create(SI->getType(), 2, "", NextBlock->begin());
  PN->takeName(SI);
  PN->addIncoming(SI->getTrueValue(), StartBlock);
  PN->addIncoming(SI->getFalseValue(), SmallBlock);
  SI->replaceAllUsesWith(PN);
  SI->eraseFromParent();

  // Instruct OptimizeBlock to skip to the next block.
  CurInstIterator = StartBlock->end();
  ++NumSelectsExpanded;
  return true;
}

bool CodeGenPrepare::OptimizeInst(Instruction *I) {
  if (PHINode *P = dyn_cast<PHINode>(I)) {
    // It is possible for very late stage optimizations (such as SimplifyCFG)
    // to introduce PHI nodes too late to be cleaned up.  If we detect such a
    // trivial PHI, go ahead and zap it here.
    if (Value *V = SimplifyInstruction(P)) {
      P->replaceAllUsesWith(V);
      P->eraseFromParent();
      ++NumPHIsElim;
      return true;
    }
    return false;
  }

  if (CastInst *CI = dyn_cast<CastInst>(I)) {
    // If the source of the cast is a constant, then this should have
    // already been constant folded.  The only reason NOT to constant fold
    // it is if something (e.g. LSR) was careful to place the constant
    // evaluation in a block other than then one that uses it (e.g. to hoist
    // the address of globals out of a loop).  If this is the case, we don't
    // want to forward-subst the cast.
    if (isa<Constant>(CI->getOperand(0)))
      return false;

    if (TLI && OptimizeNoopCopyExpression(CI, *TLI))
      return true;

    if (isa<ZExtInst>(I) || isa<SExtInst>(I)) {
      bool MadeChange = MoveExtToFormExtLoad(I);
      return MadeChange | OptimizeExtUses(I);
    }
    return false;
  }

  if (CmpInst *CI = dyn_cast<CmpInst>(I))
    return OptimizeCmpExpression(CI);

  if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
    if (TLI)
      return OptimizeMemoryInst(I, I->getOperand(0), LI->getType());
    return false;
  }

  if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
    if (TLI)
      return OptimizeMemoryInst(I, SI->getOperand(1),
                                SI->getOperand(0)->getType());
    return false;
  }

  if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(I)) {
    if (GEPI->hasAllZeroIndices()) {
      /// The GEP operand must be a pointer, so must its result -> BitCast
      Instruction *NC = new BitCastInst(GEPI->getOperand(0), GEPI->getType(),
                                        GEPI->getName(), GEPI);
      GEPI->replaceAllUsesWith(NC);
      GEPI->eraseFromParent();
      ++NumGEPsElim;
      OptimizeInst(NC);
      return true;
    }
    return false;
  }

  if (CallInst *CI = dyn_cast<CallInst>(I))
    return OptimizeCallInst(CI);

  if (SelectInst *SI = dyn_cast<SelectInst>(I))
    return OptimizeSelectInst(SI);

  return false;
}

// In this pass we look for GEP and cast instructions that are used
// across basic blocks and rewrite them to improve basic-block-at-a-time
// selection.
bool CodeGenPrepare::OptimizeBlock(BasicBlock &BB) {
  SunkAddrs.clear();
  bool MadeChange = false;

  CurInstIterator = BB.begin();
  while (CurInstIterator != BB.end())
    MadeChange |= OptimizeInst(CurInstIterator++);

  MadeChange |= DupRetToEnableTailCallOpts(&BB);

  return MadeChange;
}

// llvm.dbg.value is far away from the value then iSel may not be able
// handle it properly. iSel will drop llvm.dbg.value if it can not
// find a node corresponding to the value.
bool CodeGenPrepare::PlaceDbgValues(Function &F) {
  bool MadeChange = false;
  for (Function::iterator I = F.begin(), E = F.end(); I != E; ++I) {
    Instruction *PrevNonDbgInst = NULL;
    for (BasicBlock::iterator BI = I->begin(), BE = I->end(); BI != BE;) {
      Instruction *Insn = BI; ++BI;
      DbgValueInst *DVI = dyn_cast<DbgValueInst>(Insn);
      if (!DVI) {
        PrevNonDbgInst = Insn;
        continue;
      }

      Instruction *VI = dyn_cast_or_null<Instruction>(DVI->getValue());
      if (VI && VI != PrevNonDbgInst && !VI->isTerminator()) {
        DEBUG(dbgs() << "Moving Debug Value before :\n" << *DVI << ' ' << *VI);
        DVI->removeFromParent();
        if (isa<PHINode>(VI))
          DVI->insertBefore(VI->getParent()->getFirstInsertionPt());
        else
          DVI->insertAfter(VI);
        MadeChange = true;
        ++NumDbgValueMoved;
      }
    }
  }
  return MadeChange;
}