This repository was archived by the owner on Nov 1, 2021. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 69
/
Copy pathCGAtomic.cpp
1638 lines (1483 loc) · 65.8 KB
/
CGAtomic.cpp
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
//===--- CGAtomic.cpp - Emit LLVM IR for atomic operations ----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains the code for emitting atomic operations.
//
//===----------------------------------------------------------------------===//
#include "CodeGenFunction.h"
#include "CGCall.h"
#include "CGRecordLayout.h"
#include "CodeGenModule.h"
#include "clang/AST/ASTContext.h"
#include "clang/CodeGen/CGFunctionInfo.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/Operator.h"
using namespace clang;
using namespace CodeGen;
namespace {
class AtomicInfo {
CodeGenFunction &CGF;
QualType AtomicTy;
QualType ValueTy;
uint64_t AtomicSizeInBits;
uint64_t ValueSizeInBits;
CharUnits AtomicAlign;
CharUnits ValueAlign;
CharUnits LValueAlign;
TypeEvaluationKind EvaluationKind;
bool UseLibcall;
LValue LVal;
CGBitFieldInfo BFI;
public:
AtomicInfo(CodeGenFunction &CGF, LValue &lvalue)
: CGF(CGF), AtomicSizeInBits(0), ValueSizeInBits(0),
EvaluationKind(TEK_Scalar), UseLibcall(true) {
assert(!lvalue.isGlobalReg());
ASTContext &C = CGF.getContext();
if (lvalue.isSimple()) {
AtomicTy = lvalue.getType();
if (auto *ATy = AtomicTy->getAs<AtomicType>())
ValueTy = ATy->getValueType();
else
ValueTy = AtomicTy;
EvaluationKind = CGF.getEvaluationKind(ValueTy);
uint64_t ValueAlignInBits;
uint64_t AtomicAlignInBits;
TypeInfo ValueTI = C.getTypeInfo(ValueTy);
ValueSizeInBits = ValueTI.Width;
ValueAlignInBits = ValueTI.Align;
TypeInfo AtomicTI = C.getTypeInfo(AtomicTy);
AtomicSizeInBits = AtomicTI.Width;
AtomicAlignInBits = AtomicTI.Align;
assert(ValueSizeInBits <= AtomicSizeInBits);
assert(ValueAlignInBits <= AtomicAlignInBits);
AtomicAlign = C.toCharUnitsFromBits(AtomicAlignInBits);
ValueAlign = C.toCharUnitsFromBits(ValueAlignInBits);
if (lvalue.getAlignment().isZero())
lvalue.setAlignment(AtomicAlign);
LVal = lvalue;
} else if (lvalue.isBitField()) {
ValueTy = lvalue.getType();
ValueSizeInBits = C.getTypeSize(ValueTy);
auto &OrigBFI = lvalue.getBitFieldInfo();
auto Offset = OrigBFI.Offset % C.toBits(lvalue.getAlignment());
AtomicSizeInBits = C.toBits(
C.toCharUnitsFromBits(Offset + OrigBFI.Size + C.getCharWidth() - 1)
.RoundUpToAlignment(lvalue.getAlignment()));
auto VoidPtrAddr = CGF.EmitCastToVoidPtr(lvalue.getBitFieldAddr());
auto OffsetInChars =
(C.toCharUnitsFromBits(OrigBFI.Offset) / lvalue.getAlignment()) *
lvalue.getAlignment();
VoidPtrAddr = CGF.Builder.CreateConstGEP1_64(
VoidPtrAddr, OffsetInChars.getQuantity());
auto Addr = CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
VoidPtrAddr,
CGF.Builder.getIntNTy(AtomicSizeInBits)->getPointerTo(),
"atomic_bitfield_base");
BFI = OrigBFI;
BFI.Offset = Offset;
BFI.StorageSize = AtomicSizeInBits;
LVal = LValue::MakeBitfield(Addr, BFI, lvalue.getType(),
lvalue.getAlignment());
LVal.setTBAAInfo(lvalue.getTBAAInfo());
AtomicTy = C.getIntTypeForBitwidth(AtomicSizeInBits, OrigBFI.IsSigned);
if (AtomicTy.isNull()) {
llvm::APInt Size(
/*numBits=*/32,
C.toCharUnitsFromBits(AtomicSizeInBits).getQuantity());
AtomicTy = C.getConstantArrayType(C.CharTy, Size, ArrayType::Normal,
/*IndexTypeQuals=*/0);
}
AtomicAlign = ValueAlign = lvalue.getAlignment();
} else if (lvalue.isVectorElt()) {
ValueTy = lvalue.getType()->getAs<VectorType>()->getElementType();
ValueSizeInBits = C.getTypeSize(ValueTy);
AtomicTy = lvalue.getType();
AtomicSizeInBits = C.getTypeSize(AtomicTy);
AtomicAlign = ValueAlign = lvalue.getAlignment();
LVal = lvalue;
} else {
assert(lvalue.isExtVectorElt());
ValueTy = lvalue.getType();
ValueSizeInBits = C.getTypeSize(ValueTy);
AtomicTy = ValueTy = CGF.getContext().getExtVectorType(
lvalue.getType(), lvalue.getExtVectorAddr()
->getType()
->getPointerElementType()
->getVectorNumElements());
AtomicSizeInBits = C.getTypeSize(AtomicTy);
AtomicAlign = ValueAlign = lvalue.getAlignment();
LVal = lvalue;
}
UseLibcall = !C.getTargetInfo().hasBuiltinAtomic(
AtomicSizeInBits, C.toBits(lvalue.getAlignment()));
}
QualType getAtomicType() const { return AtomicTy; }
QualType getValueType() const { return ValueTy; }
CharUnits getAtomicAlignment() const { return AtomicAlign; }
CharUnits getValueAlignment() const { return ValueAlign; }
uint64_t getAtomicSizeInBits() const { return AtomicSizeInBits; }
uint64_t getValueSizeInBits() const { return ValueSizeInBits; }
TypeEvaluationKind getEvaluationKind() const { return EvaluationKind; }
bool shouldUseLibcall() const { return UseLibcall; }
const LValue &getAtomicLValue() const { return LVal; }
llvm::Value *getAtomicAddress() const {
if (LVal.isSimple())
return LVal.getAddress();
else if (LVal.isBitField())
return LVal.getBitFieldAddr();
else if (LVal.isVectorElt())
return LVal.getVectorAddr();
assert(LVal.isExtVectorElt());
return LVal.getExtVectorAddr();
}
/// Is the atomic size larger than the underlying value type?
///
/// Note that the absence of padding does not mean that atomic
/// objects are completely interchangeable with non-atomic
/// objects: we might have promoted the alignment of a type
/// without making it bigger.
bool hasPadding() const {
return (ValueSizeInBits != AtomicSizeInBits);
}
bool emitMemSetZeroIfNecessary() const;
llvm::Value *getAtomicSizeValue() const {
CharUnits size = CGF.getContext().toCharUnitsFromBits(AtomicSizeInBits);
return CGF.CGM.getSize(size);
}
/// Cast the given pointer to an integer pointer suitable for
/// atomic operations.
llvm::Value *emitCastToAtomicIntPointer(llvm::Value *addr) const;
/// Turn an atomic-layout object into an r-value.
RValue convertTempToRValue(llvm::Value *addr, AggValueSlot resultSlot,
SourceLocation loc, bool AsValue) const;
/// \brief Converts a rvalue to integer value.
llvm::Value *convertRValueToInt(RValue RVal) const;
RValue ConvertIntToValueOrAtomic(llvm::Value *IntVal,
AggValueSlot ResultSlot,
SourceLocation Loc, bool AsValue) const;
/// Copy an atomic r-value into atomic-layout memory.
void emitCopyIntoMemory(RValue rvalue) const;
/// Project an l-value down to the value field.
LValue projectValue() const {
assert(LVal.isSimple());
llvm::Value *addr = getAtomicAddress();
if (hasPadding())
addr = CGF.Builder.CreateStructGEP(nullptr, addr, 0);
return LValue::MakeAddr(addr, getValueType(), LVal.getAlignment(),
CGF.getContext(), LVal.getTBAAInfo());
}
/// \brief Emits atomic load.
/// \returns Loaded value.
RValue EmitAtomicLoad(AggValueSlot ResultSlot, SourceLocation Loc,
bool AsValue, llvm::AtomicOrdering AO,
bool IsVolatile);
/// \brief Emits atomic compare-and-exchange sequence.
/// \param Expected Expected value.
/// \param Desired Desired value.
/// \param Success Atomic ordering for success operation.
/// \param Failure Atomic ordering for failed operation.
/// \param IsWeak true if atomic operation is weak, false otherwise.
/// \returns Pair of values: previous value from storage (value type) and
/// boolean flag (i1 type) with true if success and false otherwise.
std::pair<RValue, llvm::Value *> EmitAtomicCompareExchange(
RValue Expected, RValue Desired,
llvm::AtomicOrdering Success = llvm::SequentiallyConsistent,
llvm::AtomicOrdering Failure = llvm::SequentiallyConsistent,
bool IsWeak = false);
/// Materialize an atomic r-value in atomic-layout memory.
llvm::Value *materializeRValue(RValue rvalue) const;
/// \brief Translates LLVM atomic ordering to GNU atomic ordering for
/// libcalls.
static AtomicExpr::AtomicOrderingKind
translateAtomicOrdering(const llvm::AtomicOrdering AO);
private:
bool requiresMemSetZero(llvm::Type *type) const;
/// \brief Creates temp alloca for intermediate operations on atomic value.
llvm::Value *CreateTempAlloca() const;
/// \brief Emits atomic load as a libcall.
void EmitAtomicLoadLibcall(llvm::Value *AddForLoaded,
llvm::AtomicOrdering AO, bool IsVolatile);
/// \brief Emits atomic load as LLVM instruction.
llvm::Value *EmitAtomicLoadOp(llvm::AtomicOrdering AO, bool IsVolatile);
/// \brief Emits atomic compare-and-exchange op as a libcall.
std::pair<RValue, llvm::Value *> EmitAtomicCompareExchangeLibcall(
RValue Expected, RValue DesiredAddr,
llvm::AtomicOrdering Success = llvm::SequentiallyConsistent,
llvm::AtomicOrdering Failure = llvm::SequentiallyConsistent);
/// \brief Emits atomic compare-and-exchange op as LLVM instruction.
std::pair<RValue, llvm::Value *> EmitAtomicCompareExchangeOp(
RValue Expected, RValue Desired,
llvm::AtomicOrdering Success = llvm::SequentiallyConsistent,
llvm::AtomicOrdering Failure = llvm::SequentiallyConsistent,
bool IsWeak = false);
};
}
AtomicExpr::AtomicOrderingKind
AtomicInfo::translateAtomicOrdering(const llvm::AtomicOrdering AO) {
switch (AO) {
case llvm::Unordered:
case llvm::NotAtomic:
case llvm::Monotonic:
return AtomicExpr::AO_ABI_memory_order_relaxed;
case llvm::Acquire:
return AtomicExpr::AO_ABI_memory_order_acquire;
case llvm::Release:
return AtomicExpr::AO_ABI_memory_order_release;
case llvm::AcquireRelease:
return AtomicExpr::AO_ABI_memory_order_acq_rel;
case llvm::SequentiallyConsistent:
return AtomicExpr::AO_ABI_memory_order_seq_cst;
}
llvm_unreachable("Unhandled AtomicOrdering");
}
llvm::Value *AtomicInfo::CreateTempAlloca() const {
auto *TempAlloca = CGF.CreateMemTemp(
(LVal.isBitField() && ValueSizeInBits > AtomicSizeInBits) ? ValueTy
: AtomicTy,
"atomic-temp");
TempAlloca->setAlignment(getAtomicAlignment().getQuantity());
// Cast to pointer to value type for bitfields.
if (LVal.isBitField())
return CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
TempAlloca, getAtomicAddress()->getType());
return TempAlloca;
}
static RValue emitAtomicLibcall(CodeGenFunction &CGF,
StringRef fnName,
QualType resultType,
CallArgList &args) {
const CGFunctionInfo &fnInfo =
CGF.CGM.getTypes().arrangeFreeFunctionCall(resultType, args,
FunctionType::ExtInfo(), RequiredArgs::All);
llvm::FunctionType *fnTy = CGF.CGM.getTypes().GetFunctionType(fnInfo);
llvm::Constant *fn = CGF.CGM.CreateRuntimeFunction(fnTy, fnName);
return CGF.EmitCall(fnInfo, fn, ReturnValueSlot(), args);
}
/// Does a store of the given IR type modify the full expected width?
static bool isFullSizeType(CodeGenModule &CGM, llvm::Type *type,
uint64_t expectedSize) {
return (CGM.getDataLayout().getTypeStoreSize(type) * 8 == expectedSize);
}
/// Does the atomic type require memsetting to zero before initialization?
///
/// The IR type is provided as a way of making certain queries faster.
bool AtomicInfo::requiresMemSetZero(llvm::Type *type) const {
// If the atomic type has size padding, we definitely need a memset.
if (hasPadding()) return true;
// Otherwise, do some simple heuristics to try to avoid it:
switch (getEvaluationKind()) {
// For scalars and complexes, check whether the store size of the
// type uses the full size.
case TEK_Scalar:
return !isFullSizeType(CGF.CGM, type, AtomicSizeInBits);
case TEK_Complex:
return !isFullSizeType(CGF.CGM, type->getStructElementType(0),
AtomicSizeInBits / 2);
// Padding in structs has an undefined bit pattern. User beware.
case TEK_Aggregate:
return false;
}
llvm_unreachable("bad evaluation kind");
}
bool AtomicInfo::emitMemSetZeroIfNecessary() const {
assert(LVal.isSimple());
llvm::Value *addr = LVal.getAddress();
if (!requiresMemSetZero(addr->getType()->getPointerElementType()))
return false;
CGF.Builder.CreateMemSet(
addr, llvm::ConstantInt::get(CGF.Int8Ty, 0),
CGF.getContext().toCharUnitsFromBits(AtomicSizeInBits).getQuantity(),
LVal.getAlignment().getQuantity());
return true;
}
static void emitAtomicCmpXchg(CodeGenFunction &CGF, AtomicExpr *E, bool IsWeak,
llvm::Value *Dest, llvm::Value *Ptr,
llvm::Value *Val1, llvm::Value *Val2,
uint64_t Size, unsigned Align,
llvm::AtomicOrdering SuccessOrder,
llvm::AtomicOrdering FailureOrder) {
// Note that cmpxchg doesn't support weak cmpxchg, at least at the moment.
llvm::LoadInst *Expected = CGF.Builder.CreateLoad(Val1);
Expected->setAlignment(Align);
llvm::LoadInst *Desired = CGF.Builder.CreateLoad(Val2);
Desired->setAlignment(Align);
llvm::AtomicCmpXchgInst *Pair = CGF.Builder.CreateAtomicCmpXchg(
Ptr, Expected, Desired, SuccessOrder, FailureOrder);
Pair->setVolatile(E->isVolatile());
Pair->setWeak(IsWeak);
// Cmp holds the result of the compare-exchange operation: true on success,
// false on failure.
llvm::Value *Old = CGF.Builder.CreateExtractValue(Pair, 0);
llvm::Value *Cmp = CGF.Builder.CreateExtractValue(Pair, 1);
// This basic block is used to hold the store instruction if the operation
// failed.
llvm::BasicBlock *StoreExpectedBB =
CGF.createBasicBlock("cmpxchg.store_expected", CGF.CurFn);
// This basic block is the exit point of the operation, we should end up
// here regardless of whether or not the operation succeeded.
llvm::BasicBlock *ContinueBB =
CGF.createBasicBlock("cmpxchg.continue", CGF.CurFn);
// Update Expected if Expected isn't equal to Old, otherwise branch to the
// exit point.
CGF.Builder.CreateCondBr(Cmp, ContinueBB, StoreExpectedBB);
CGF.Builder.SetInsertPoint(StoreExpectedBB);
// Update the memory at Expected with Old's value.
llvm::StoreInst *StoreExpected = CGF.Builder.CreateStore(Old, Val1);
StoreExpected->setAlignment(Align);
// Finally, branch to the exit point.
CGF.Builder.CreateBr(ContinueBB);
CGF.Builder.SetInsertPoint(ContinueBB);
// Update the memory at Dest with Cmp's value.
CGF.EmitStoreOfScalar(Cmp, CGF.MakeAddrLValue(Dest, E->getType()));
return;
}
/// Given an ordering required on success, emit all possible cmpxchg
/// instructions to cope with the provided (but possibly only dynamically known)
/// FailureOrder.
static void emitAtomicCmpXchgFailureSet(CodeGenFunction &CGF, AtomicExpr *E,
bool IsWeak, llvm::Value *Dest,
llvm::Value *Ptr, llvm::Value *Val1,
llvm::Value *Val2,
llvm::Value *FailureOrderVal,
uint64_t Size, unsigned Align,
llvm::AtomicOrdering SuccessOrder) {
llvm::AtomicOrdering FailureOrder;
if (llvm::ConstantInt *FO = dyn_cast<llvm::ConstantInt>(FailureOrderVal)) {
switch (FO->getSExtValue()) {
default:
FailureOrder = llvm::Monotonic;
break;
case AtomicExpr::AO_ABI_memory_order_consume:
case AtomicExpr::AO_ABI_memory_order_acquire:
FailureOrder = llvm::Acquire;
break;
case AtomicExpr::AO_ABI_memory_order_seq_cst:
FailureOrder = llvm::SequentiallyConsistent;
break;
}
if (FailureOrder >= SuccessOrder) {
// Don't assert on undefined behaviour.
FailureOrder =
llvm::AtomicCmpXchgInst::getStrongestFailureOrdering(SuccessOrder);
}
emitAtomicCmpXchg(CGF, E, IsWeak, Dest, Ptr, Val1, Val2, Size, Align,
SuccessOrder, FailureOrder);
return;
}
// Create all the relevant BB's
llvm::BasicBlock *MonotonicBB = nullptr, *AcquireBB = nullptr,
*SeqCstBB = nullptr;
MonotonicBB = CGF.createBasicBlock("monotonic_fail", CGF.CurFn);
if (SuccessOrder != llvm::Monotonic && SuccessOrder != llvm::Release)
AcquireBB = CGF.createBasicBlock("acquire_fail", CGF.CurFn);
if (SuccessOrder == llvm::SequentiallyConsistent)
SeqCstBB = CGF.createBasicBlock("seqcst_fail", CGF.CurFn);
llvm::BasicBlock *ContBB = CGF.createBasicBlock("atomic.continue", CGF.CurFn);
llvm::SwitchInst *SI = CGF.Builder.CreateSwitch(FailureOrderVal, MonotonicBB);
// Emit all the different atomics
// MonotonicBB is arbitrarily chosen as the default case; in practice, this
// doesn't matter unless someone is crazy enough to use something that
// doesn't fold to a constant for the ordering.
CGF.Builder.SetInsertPoint(MonotonicBB);
emitAtomicCmpXchg(CGF, E, IsWeak, Dest, Ptr, Val1, Val2,
Size, Align, SuccessOrder, llvm::Monotonic);
CGF.Builder.CreateBr(ContBB);
if (AcquireBB) {
CGF.Builder.SetInsertPoint(AcquireBB);
emitAtomicCmpXchg(CGF, E, IsWeak, Dest, Ptr, Val1, Val2,
Size, Align, SuccessOrder, llvm::Acquire);
CGF.Builder.CreateBr(ContBB);
SI->addCase(CGF.Builder.getInt32(AtomicExpr::AO_ABI_memory_order_consume),
AcquireBB);
SI->addCase(CGF.Builder.getInt32(AtomicExpr::AO_ABI_memory_order_acquire),
AcquireBB);
}
if (SeqCstBB) {
CGF.Builder.SetInsertPoint(SeqCstBB);
emitAtomicCmpXchg(CGF, E, IsWeak, Dest, Ptr, Val1, Val2,
Size, Align, SuccessOrder, llvm::SequentiallyConsistent);
CGF.Builder.CreateBr(ContBB);
SI->addCase(CGF.Builder.getInt32(AtomicExpr::AO_ABI_memory_order_seq_cst),
SeqCstBB);
}
CGF.Builder.SetInsertPoint(ContBB);
}
static void EmitAtomicOp(CodeGenFunction &CGF, AtomicExpr *E, llvm::Value *Dest,
llvm::Value *Ptr, llvm::Value *Val1, llvm::Value *Val2,
llvm::Value *IsWeak, llvm::Value *FailureOrder,
uint64_t Size, unsigned Align,
llvm::AtomicOrdering Order) {
llvm::AtomicRMWInst::BinOp Op = llvm::AtomicRMWInst::Add;
llvm::Instruction::BinaryOps PostOp = (llvm::Instruction::BinaryOps)0;
switch (E->getOp()) {
case AtomicExpr::AO__c11_atomic_init:
llvm_unreachable("Already handled!");
case AtomicExpr::AO__c11_atomic_compare_exchange_strong:
emitAtomicCmpXchgFailureSet(CGF, E, false, Dest, Ptr, Val1, Val2,
FailureOrder, Size, Align, Order);
return;
case AtomicExpr::AO__c11_atomic_compare_exchange_weak:
emitAtomicCmpXchgFailureSet(CGF, E, true, Dest, Ptr, Val1, Val2,
FailureOrder, Size, Align, Order);
return;
case AtomicExpr::AO__atomic_compare_exchange:
case AtomicExpr::AO__atomic_compare_exchange_n: {
if (llvm::ConstantInt *IsWeakC = dyn_cast<llvm::ConstantInt>(IsWeak)) {
emitAtomicCmpXchgFailureSet(CGF, E, IsWeakC->getZExtValue(), Dest, Ptr,
Val1, Val2, FailureOrder, Size, Align, Order);
} else {
// Create all the relevant BB's
llvm::BasicBlock *StrongBB =
CGF.createBasicBlock("cmpxchg.strong", CGF.CurFn);
llvm::BasicBlock *WeakBB = CGF.createBasicBlock("cmxchg.weak", CGF.CurFn);
llvm::BasicBlock *ContBB =
CGF.createBasicBlock("cmpxchg.continue", CGF.CurFn);
llvm::SwitchInst *SI = CGF.Builder.CreateSwitch(IsWeak, WeakBB);
SI->addCase(CGF.Builder.getInt1(false), StrongBB);
CGF.Builder.SetInsertPoint(StrongBB);
emitAtomicCmpXchgFailureSet(CGF, E, false, Dest, Ptr, Val1, Val2,
FailureOrder, Size, Align, Order);
CGF.Builder.CreateBr(ContBB);
CGF.Builder.SetInsertPoint(WeakBB);
emitAtomicCmpXchgFailureSet(CGF, E, true, Dest, Ptr, Val1, Val2,
FailureOrder, Size, Align, Order);
CGF.Builder.CreateBr(ContBB);
CGF.Builder.SetInsertPoint(ContBB);
}
return;
}
case AtomicExpr::AO__c11_atomic_load:
case AtomicExpr::AO__atomic_load_n:
case AtomicExpr::AO__atomic_load: {
llvm::LoadInst *Load = CGF.Builder.CreateLoad(Ptr);
Load->setAtomic(Order);
Load->setAlignment(Size);
Load->setVolatile(E->isVolatile());
llvm::StoreInst *StoreDest = CGF.Builder.CreateStore(Load, Dest);
StoreDest->setAlignment(Align);
return;
}
case AtomicExpr::AO__c11_atomic_store:
case AtomicExpr::AO__atomic_store:
case AtomicExpr::AO__atomic_store_n: {
assert(!Dest && "Store does not return a value");
llvm::LoadInst *LoadVal1 = CGF.Builder.CreateLoad(Val1);
LoadVal1->setAlignment(Align);
llvm::StoreInst *Store = CGF.Builder.CreateStore(LoadVal1, Ptr);
Store->setAtomic(Order);
Store->setAlignment(Size);
Store->setVolatile(E->isVolatile());
return;
}
case AtomicExpr::AO__c11_atomic_exchange:
case AtomicExpr::AO__atomic_exchange_n:
case AtomicExpr::AO__atomic_exchange:
Op = llvm::AtomicRMWInst::Xchg;
break;
case AtomicExpr::AO__atomic_add_fetch:
PostOp = llvm::Instruction::Add;
// Fall through.
case AtomicExpr::AO__c11_atomic_fetch_add:
case AtomicExpr::AO__atomic_fetch_add:
Op = llvm::AtomicRMWInst::Add;
break;
case AtomicExpr::AO__atomic_sub_fetch:
PostOp = llvm::Instruction::Sub;
// Fall through.
case AtomicExpr::AO__c11_atomic_fetch_sub:
case AtomicExpr::AO__atomic_fetch_sub:
Op = llvm::AtomicRMWInst::Sub;
break;
case AtomicExpr::AO__atomic_and_fetch:
PostOp = llvm::Instruction::And;
// Fall through.
case AtomicExpr::AO__c11_atomic_fetch_and:
case AtomicExpr::AO__atomic_fetch_and:
Op = llvm::AtomicRMWInst::And;
break;
case AtomicExpr::AO__atomic_or_fetch:
PostOp = llvm::Instruction::Or;
// Fall through.
case AtomicExpr::AO__c11_atomic_fetch_or:
case AtomicExpr::AO__atomic_fetch_or:
Op = llvm::AtomicRMWInst::Or;
break;
case AtomicExpr::AO__atomic_xor_fetch:
PostOp = llvm::Instruction::Xor;
// Fall through.
case AtomicExpr::AO__c11_atomic_fetch_xor:
case AtomicExpr::AO__atomic_fetch_xor:
Op = llvm::AtomicRMWInst::Xor;
break;
case AtomicExpr::AO__atomic_nand_fetch:
PostOp = llvm::Instruction::And;
// Fall through.
case AtomicExpr::AO__atomic_fetch_nand:
Op = llvm::AtomicRMWInst::Nand;
break;
}
llvm::LoadInst *LoadVal1 = CGF.Builder.CreateLoad(Val1);
LoadVal1->setAlignment(Align);
llvm::AtomicRMWInst *RMWI =
CGF.Builder.CreateAtomicRMW(Op, Ptr, LoadVal1, Order);
RMWI->setVolatile(E->isVolatile());
// For __atomic_*_fetch operations, perform the operation again to
// determine the value which was written.
llvm::Value *Result = RMWI;
if (PostOp)
Result = CGF.Builder.CreateBinOp(PostOp, RMWI, LoadVal1);
if (E->getOp() == AtomicExpr::AO__atomic_nand_fetch)
Result = CGF.Builder.CreateNot(Result);
llvm::StoreInst *StoreDest = CGF.Builder.CreateStore(Result, Dest);
StoreDest->setAlignment(Align);
}
// This function emits any expression (scalar, complex, or aggregate)
// into a temporary alloca.
static llvm::Value *
EmitValToTemp(CodeGenFunction &CGF, Expr *E) {
llvm::Value *DeclPtr = CGF.CreateMemTemp(E->getType(), ".atomictmp");
CGF.EmitAnyExprToMem(E, DeclPtr, E->getType().getQualifiers(),
/*Init*/ true);
return DeclPtr;
}
static void
AddDirectArgument(CodeGenFunction &CGF, CallArgList &Args,
bool UseOptimizedLibcall, llvm::Value *Val, QualType ValTy,
SourceLocation Loc, CharUnits SizeInChars) {
if (UseOptimizedLibcall) {
// Load value and pass it to the function directly.
unsigned Align = CGF.getContext().getTypeAlignInChars(ValTy).getQuantity();
int64_t SizeInBits = CGF.getContext().toBits(SizeInChars);
ValTy =
CGF.getContext().getIntTypeForBitwidth(SizeInBits, /*Signed=*/false);
llvm::Type *IPtrTy = llvm::IntegerType::get(CGF.getLLVMContext(),
SizeInBits)->getPointerTo();
Val = CGF.EmitLoadOfScalar(CGF.Builder.CreateBitCast(Val, IPtrTy), false,
Align, CGF.getContext().getPointerType(ValTy),
Loc);
// Coerce the value into an appropriately sized integer type.
Args.add(RValue::get(Val), ValTy);
} else {
// Non-optimized functions always take a reference.
Args.add(RValue::get(CGF.EmitCastToVoidPtr(Val)),
CGF.getContext().VoidPtrTy);
}
}
RValue CodeGenFunction::EmitAtomicExpr(AtomicExpr *E, llvm::Value *Dest) {
QualType AtomicTy = E->getPtr()->getType()->getPointeeType();
QualType MemTy = AtomicTy;
if (const AtomicType *AT = AtomicTy->getAs<AtomicType>())
MemTy = AT->getValueType();
CharUnits sizeChars = getContext().getTypeSizeInChars(AtomicTy);
uint64_t Size = sizeChars.getQuantity();
CharUnits alignChars = getContext().getTypeAlignInChars(AtomicTy);
unsigned Align = alignChars.getQuantity();
unsigned MaxInlineWidthInBits =
getTarget().getMaxAtomicInlineWidth();
bool UseLibcall = (Size != Align ||
getContext().toBits(sizeChars) > MaxInlineWidthInBits);
llvm::Value *IsWeak = nullptr, *OrderFail = nullptr, *Val1 = nullptr,
*Val2 = nullptr;
llvm::Value *Ptr = EmitScalarExpr(E->getPtr());
if (E->getOp() == AtomicExpr::AO__c11_atomic_init) {
assert(!Dest && "Init does not return a value");
LValue lvalue = LValue::MakeAddr(Ptr, AtomicTy, alignChars, getContext());
EmitAtomicInit(E->getVal1(), lvalue);
return RValue::get(nullptr);
}
llvm::Value *Order = EmitScalarExpr(E->getOrder());
switch (E->getOp()) {
case AtomicExpr::AO__c11_atomic_init:
llvm_unreachable("Already handled!");
case AtomicExpr::AO__c11_atomic_load:
case AtomicExpr::AO__atomic_load_n:
break;
case AtomicExpr::AO__atomic_load:
Dest = EmitScalarExpr(E->getVal1());
break;
case AtomicExpr::AO__atomic_store:
Val1 = EmitScalarExpr(E->getVal1());
break;
case AtomicExpr::AO__atomic_exchange:
Val1 = EmitScalarExpr(E->getVal1());
Dest = EmitScalarExpr(E->getVal2());
break;
case AtomicExpr::AO__c11_atomic_compare_exchange_strong:
case AtomicExpr::AO__c11_atomic_compare_exchange_weak:
case AtomicExpr::AO__atomic_compare_exchange_n:
case AtomicExpr::AO__atomic_compare_exchange:
Val1 = EmitScalarExpr(E->getVal1());
if (E->getOp() == AtomicExpr::AO__atomic_compare_exchange)
Val2 = EmitScalarExpr(E->getVal2());
else
Val2 = EmitValToTemp(*this, E->getVal2());
OrderFail = EmitScalarExpr(E->getOrderFail());
if (E->getNumSubExprs() == 6)
IsWeak = EmitScalarExpr(E->getWeak());
break;
case AtomicExpr::AO__c11_atomic_fetch_add:
case AtomicExpr::AO__c11_atomic_fetch_sub:
if (MemTy->isPointerType()) {
// For pointer arithmetic, we're required to do a bit of math:
// adding 1 to an int* is not the same as adding 1 to a uintptr_t.
// ... but only for the C11 builtins. The GNU builtins expect the
// user to multiply by sizeof(T).
QualType Val1Ty = E->getVal1()->getType();
llvm::Value *Val1Scalar = EmitScalarExpr(E->getVal1());
CharUnits PointeeIncAmt =
getContext().getTypeSizeInChars(MemTy->getPointeeType());
Val1Scalar = Builder.CreateMul(Val1Scalar, CGM.getSize(PointeeIncAmt));
Val1 = CreateMemTemp(Val1Ty, ".atomictmp");
EmitStoreOfScalar(Val1Scalar, MakeAddrLValue(Val1, Val1Ty));
break;
}
// Fall through.
case AtomicExpr::AO__atomic_fetch_add:
case AtomicExpr::AO__atomic_fetch_sub:
case AtomicExpr::AO__atomic_add_fetch:
case AtomicExpr::AO__atomic_sub_fetch:
case AtomicExpr::AO__c11_atomic_store:
case AtomicExpr::AO__c11_atomic_exchange:
case AtomicExpr::AO__atomic_store_n:
case AtomicExpr::AO__atomic_exchange_n:
case AtomicExpr::AO__c11_atomic_fetch_and:
case AtomicExpr::AO__c11_atomic_fetch_or:
case AtomicExpr::AO__c11_atomic_fetch_xor:
case AtomicExpr::AO__atomic_fetch_and:
case AtomicExpr::AO__atomic_fetch_or:
case AtomicExpr::AO__atomic_fetch_xor:
case AtomicExpr::AO__atomic_fetch_nand:
case AtomicExpr::AO__atomic_and_fetch:
case AtomicExpr::AO__atomic_or_fetch:
case AtomicExpr::AO__atomic_xor_fetch:
case AtomicExpr::AO__atomic_nand_fetch:
Val1 = EmitValToTemp(*this, E->getVal1());
break;
}
QualType RValTy = E->getType().getUnqualifiedType();
auto GetDest = [&] {
if (!RValTy->isVoidType() && !Dest) {
Dest = CreateMemTemp(RValTy, ".atomicdst");
}
return Dest;
};
// Use a library call. See: http://gcc.gnu.org/wiki/Atomic/GCCMM/LIbrary .
if (UseLibcall) {
bool UseOptimizedLibcall = false;
switch (E->getOp()) {
case AtomicExpr::AO__c11_atomic_fetch_add:
case AtomicExpr::AO__atomic_fetch_add:
case AtomicExpr::AO__c11_atomic_fetch_and:
case AtomicExpr::AO__atomic_fetch_and:
case AtomicExpr::AO__c11_atomic_fetch_or:
case AtomicExpr::AO__atomic_fetch_or:
case AtomicExpr::AO__c11_atomic_fetch_sub:
case AtomicExpr::AO__atomic_fetch_sub:
case AtomicExpr::AO__c11_atomic_fetch_xor:
case AtomicExpr::AO__atomic_fetch_xor:
// For these, only library calls for certain sizes exist.
UseOptimizedLibcall = true;
break;
default:
// Only use optimized library calls for sizes for which they exist.
if (Size == 1 || Size == 2 || Size == 4 || Size == 8)
UseOptimizedLibcall = true;
break;
}
CallArgList Args;
if (!UseOptimizedLibcall) {
// For non-optimized library calls, the size is the first parameter
Args.add(RValue::get(llvm::ConstantInt::get(SizeTy, Size)),
getContext().getSizeType());
}
// Atomic address is the first or second parameter
Args.add(RValue::get(EmitCastToVoidPtr(Ptr)), getContext().VoidPtrTy);
std::string LibCallName;
QualType LoweredMemTy =
MemTy->isPointerType() ? getContext().getIntPtrType() : MemTy;
QualType RetTy;
bool HaveRetTy = false;
switch (E->getOp()) {
// There is only one libcall for compare an exchange, because there is no
// optimisation benefit possible from a libcall version of a weak compare
// and exchange.
// bool __atomic_compare_exchange(size_t size, void *mem, void *expected,
// void *desired, int success, int failure)
// bool __atomic_compare_exchange_N(T *mem, T *expected, T desired,
// int success, int failure)
case AtomicExpr::AO__c11_atomic_compare_exchange_weak:
case AtomicExpr::AO__c11_atomic_compare_exchange_strong:
case AtomicExpr::AO__atomic_compare_exchange:
case AtomicExpr::AO__atomic_compare_exchange_n:
LibCallName = "__atomic_compare_exchange";
RetTy = getContext().BoolTy;
HaveRetTy = true;
Args.add(RValue::get(EmitCastToVoidPtr(Val1)), getContext().VoidPtrTy);
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val2, MemTy,
E->getExprLoc(), sizeChars);
Args.add(RValue::get(Order), getContext().IntTy);
Order = OrderFail;
break;
// void __atomic_exchange(size_t size, void *mem, void *val, void *return,
// int order)
// T __atomic_exchange_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_exchange:
case AtomicExpr::AO__atomic_exchange_n:
case AtomicExpr::AO__atomic_exchange:
LibCallName = "__atomic_exchange";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, MemTy,
E->getExprLoc(), sizeChars);
break;
// void __atomic_store(size_t size, void *mem, void *val, int order)
// void __atomic_store_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_store:
case AtomicExpr::AO__atomic_store:
case AtomicExpr::AO__atomic_store_n:
LibCallName = "__atomic_store";
RetTy = getContext().VoidTy;
HaveRetTy = true;
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, MemTy,
E->getExprLoc(), sizeChars);
break;
// void __atomic_load(size_t size, void *mem, void *return, int order)
// T __atomic_load_N(T *mem, int order)
case AtomicExpr::AO__c11_atomic_load:
case AtomicExpr::AO__atomic_load:
case AtomicExpr::AO__atomic_load_n:
LibCallName = "__atomic_load";
break;
// T __atomic_fetch_add_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_fetch_add:
case AtomicExpr::AO__atomic_fetch_add:
LibCallName = "__atomic_fetch_add";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, LoweredMemTy,
E->getExprLoc(), sizeChars);
break;
// T __atomic_fetch_and_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_fetch_and:
case AtomicExpr::AO__atomic_fetch_and:
LibCallName = "__atomic_fetch_and";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, MemTy,
E->getExprLoc(), sizeChars);
break;
// T __atomic_fetch_or_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_fetch_or:
case AtomicExpr::AO__atomic_fetch_or:
LibCallName = "__atomic_fetch_or";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, MemTy,
E->getExprLoc(), sizeChars);
break;
// T __atomic_fetch_sub_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_fetch_sub:
case AtomicExpr::AO__atomic_fetch_sub:
LibCallName = "__atomic_fetch_sub";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, LoweredMemTy,
E->getExprLoc(), sizeChars);
break;
// T __atomic_fetch_xor_N(T *mem, T val, int order)
case AtomicExpr::AO__c11_atomic_fetch_xor:
case AtomicExpr::AO__atomic_fetch_xor:
LibCallName = "__atomic_fetch_xor";
AddDirectArgument(*this, Args, UseOptimizedLibcall, Val1, MemTy,
E->getExprLoc(), sizeChars);
break;
default: return EmitUnsupportedRValue(E, "atomic library call");
}
// Optimized functions have the size in their name.
if (UseOptimizedLibcall)
LibCallName += "_" + llvm::utostr(Size);
// By default, assume we return a value of the atomic type.
if (!HaveRetTy) {
if (UseOptimizedLibcall) {
// Value is returned directly.
// The function returns an appropriately sized integer type.
RetTy = getContext().getIntTypeForBitwidth(
getContext().toBits(sizeChars), /*Signed=*/false);
} else {
// Value is returned through parameter before the order.
RetTy = getContext().VoidTy;
Args.add(RValue::get(EmitCastToVoidPtr(Dest)), getContext().VoidPtrTy);
}
}
// order is always the last parameter
Args.add(RValue::get(Order),
getContext().IntTy);
RValue Res = emitAtomicLibcall(*this, LibCallName, RetTy, Args);
// The value is returned directly from the libcall.
if (HaveRetTy && !RetTy->isVoidType())
return Res;
// The value is returned via an explicit out param.
if (RetTy->isVoidType())
return RValue::get(nullptr);
// The value is returned directly for optimized libcalls but the caller is
// expected an out-param.
if (UseOptimizedLibcall) {
llvm::Value *ResVal = Res.getScalarVal();
llvm::StoreInst *StoreDest = Builder.CreateStore(
ResVal,
Builder.CreateBitCast(GetDest(), ResVal->getType()->getPointerTo()));
StoreDest->setAlignment(Align);
}
return convertTempToRValue(Dest, RValTy, E->getExprLoc());
}
bool IsStore = E->getOp() == AtomicExpr::AO__c11_atomic_store ||
E->getOp() == AtomicExpr::AO__atomic_store ||
E->getOp() == AtomicExpr::AO__atomic_store_n;
bool IsLoad = E->getOp() == AtomicExpr::AO__c11_atomic_load ||
E->getOp() == AtomicExpr::AO__atomic_load ||
E->getOp() == AtomicExpr::AO__atomic_load_n;
llvm::Type *ITy =
llvm::IntegerType::get(getLLVMContext(), Size * 8);
llvm::Value *OrigDest = GetDest();
Ptr = Builder.CreateBitCast(
Ptr, ITy->getPointerTo(Ptr->getType()->getPointerAddressSpace()));
if (Val1) Val1 = Builder.CreateBitCast(Val1, ITy->getPointerTo());
if (Val2) Val2 = Builder.CreateBitCast(Val2, ITy->getPointerTo());
if (Dest && !E->isCmpXChg())
Dest = Builder.CreateBitCast(Dest, ITy->getPointerTo());
if (isa<llvm::ConstantInt>(Order)) {
int ord = cast<llvm::ConstantInt>(Order)->getZExtValue();
switch (ord) {
case AtomicExpr::AO_ABI_memory_order_relaxed:
EmitAtomicOp(*this, E, Dest, Ptr, Val1, Val2, IsWeak, OrderFail,
Size, Align, llvm::Monotonic);
break;
case AtomicExpr::AO_ABI_memory_order_consume:
case AtomicExpr::AO_ABI_memory_order_acquire:
if (IsStore)
break; // Avoid crashing on code with undefined behavior
EmitAtomicOp(*this, E, Dest, Ptr, Val1, Val2, IsWeak, OrderFail,
Size, Align, llvm::Acquire);
break;
case AtomicExpr::AO_ABI_memory_order_release:
if (IsLoad)
break; // Avoid crashing on code with undefined behavior
EmitAtomicOp(*this, E, Dest, Ptr, Val1, Val2, IsWeak, OrderFail,
Size, Align, llvm::Release);
break;
case AtomicExpr::AO_ABI_memory_order_acq_rel:
if (IsLoad || IsStore)
break; // Avoid crashing on code with undefined behavior
EmitAtomicOp(*this, E, Dest, Ptr, Val1, Val2, IsWeak, OrderFail,
Size, Align, llvm::AcquireRelease);
break;
case AtomicExpr::AO_ABI_memory_order_seq_cst:
EmitAtomicOp(*this, E, Dest, Ptr, Val1, Val2, IsWeak, OrderFail,
Size, Align, llvm::SequentiallyConsistent);
break;
default: // invalid order
// We should not ever get here normally, but it's hard to
// enforce that in general.
break;
}
if (RValTy->isVoidType())
return RValue::get(nullptr);
return convertTempToRValue(OrigDest, RValTy, E->getExprLoc());
}
// Long case, when Order isn't obviously constant.
// Create all the relevant BB's
llvm::BasicBlock *MonotonicBB = nullptr, *AcquireBB = nullptr,
*ReleaseBB = nullptr, *AcqRelBB = nullptr,
*SeqCstBB = nullptr;
MonotonicBB = createBasicBlock("monotonic", CurFn);
if (!IsStore)
AcquireBB = createBasicBlock("acquire", CurFn);
if (!IsLoad)
ReleaseBB = createBasicBlock("release", CurFn);
if (!IsLoad && !IsStore)
AcqRelBB = createBasicBlock("acqrel", CurFn);
SeqCstBB = createBasicBlock("seqcst", CurFn);
llvm::BasicBlock *ContBB = createBasicBlock("atomic.continue", CurFn);
// Create the switch for the split
// MonotonicBB is arbitrarily chosen as the default case; in practice, this
// doesn't matter unless someone is crazy enough to use something that
// doesn't fold to a constant for the ordering.
Order = Builder.CreateIntCast(Order, Builder.getInt32Ty(), false);
llvm::SwitchInst *SI = Builder.CreateSwitch(Order, MonotonicBB);