forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathHexagonISelLowering.cpp
3918 lines (3447 loc) · 149 KB
/
HexagonISelLowering.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
//===-- HexagonISelLowering.cpp - Hexagon DAG Lowering Implementation -----===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the interfaces that Hexagon uses to lower LLVM code
// into a selection DAG.
//
//===----------------------------------------------------------------------===//
#include "HexagonISelLowering.h"
#include "Hexagon.h"
#include "HexagonMachineFunctionInfo.h"
#include "HexagonRegisterInfo.h"
#include "HexagonSubtarget.h"
#include "HexagonTargetMachine.h"
#include "HexagonTargetObjectFile.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringSwitch.h"
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/TargetCallingConv.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsHexagon.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CodeGen.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <limits>
#include <utility>
using namespace llvm;
#define DEBUG_TYPE "hexagon-lowering"
static cl::opt<bool> EmitJumpTables("hexagon-emit-jump-tables",
cl::init(true), cl::Hidden,
cl::desc("Control jump table emission on Hexagon target"));
static cl::opt<bool>
EnableHexSDNodeSched("enable-hexagon-sdnode-sched", cl::Hidden,
cl::desc("Enable Hexagon SDNode scheduling"));
static cl::opt<bool> EnableFastMath("ffast-math", cl::Hidden,
cl::desc("Enable Fast Math processing"));
static cl::opt<int> MinimumJumpTables("minimum-jump-tables", cl::Hidden,
cl::init(5),
cl::desc("Set minimum jump tables"));
static cl::opt<int>
MaxStoresPerMemcpyCL("max-store-memcpy", cl::Hidden, cl::init(6),
cl::desc("Max #stores to inline memcpy"));
static cl::opt<int>
MaxStoresPerMemcpyOptSizeCL("max-store-memcpy-Os", cl::Hidden, cl::init(4),
cl::desc("Max #stores to inline memcpy"));
static cl::opt<int>
MaxStoresPerMemmoveCL("max-store-memmove", cl::Hidden, cl::init(6),
cl::desc("Max #stores to inline memmove"));
static cl::opt<int>
MaxStoresPerMemmoveOptSizeCL("max-store-memmove-Os", cl::Hidden,
cl::init(4),
cl::desc("Max #stores to inline memmove"));
static cl::opt<int>
MaxStoresPerMemsetCL("max-store-memset", cl::Hidden, cl::init(8),
cl::desc("Max #stores to inline memset"));
static cl::opt<int>
MaxStoresPerMemsetOptSizeCL("max-store-memset-Os", cl::Hidden, cl::init(4),
cl::desc("Max #stores to inline memset"));
static cl::opt<bool> AlignLoads("hexagon-align-loads",
cl::Hidden, cl::init(false),
cl::desc("Rewrite unaligned loads as a pair of aligned loads"));
static cl::opt<bool>
DisableArgsMinAlignment("hexagon-disable-args-min-alignment", cl::Hidden,
cl::init(false),
cl::desc("Disable minimum alignment of 1 for "
"arguments passed by value on stack"));
namespace {
class HexagonCCState : public CCState {
unsigned NumNamedVarArgParams = 0;
public:
HexagonCCState(CallingConv::ID CC, bool IsVarArg, MachineFunction &MF,
SmallVectorImpl<CCValAssign> &locs, LLVMContext &C,
unsigned NumNamedArgs)
: CCState(CC, IsVarArg, MF, locs, C),
NumNamedVarArgParams(NumNamedArgs) {}
unsigned getNumNamedVarArgParams() const { return NumNamedVarArgParams; }
};
} // end anonymous namespace
// Implement calling convention for Hexagon.
static bool CC_SkipOdd(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
CCValAssign::LocInfo &LocInfo,
ISD::ArgFlagsTy &ArgFlags, CCState &State) {
static const MCPhysReg ArgRegs[] = {
Hexagon::R0, Hexagon::R1, Hexagon::R2,
Hexagon::R3, Hexagon::R4, Hexagon::R5
};
const unsigned NumArgRegs = std::size(ArgRegs);
unsigned RegNum = State.getFirstUnallocated(ArgRegs);
// RegNum is an index into ArgRegs: skip a register if RegNum is odd.
if (RegNum != NumArgRegs && RegNum % 2 == 1)
State.AllocateReg(ArgRegs[RegNum]);
// Always return false here, as this function only makes sure that the first
// unallocated register has an even register number and does not actually
// allocate a register for the current argument.
return false;
}
#include "HexagonGenCallingConv.inc"
SDValue
HexagonTargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op, SelectionDAG &DAG)
const {
return SDValue();
}
/// CreateCopyOfByValArgument - Make a copy of an aggregate at address specified
/// by "Src" to address "Dst" of size "Size". Alignment information is
/// specified by the specific parameter attribute. The copy will be passed as
/// a byval function parameter. Sometimes what we are copying is the end of a
/// larger object, the part that does not fit in registers.
static SDValue CreateCopyOfByValArgument(SDValue Src, SDValue Dst,
SDValue Chain, ISD::ArgFlagsTy Flags,
SelectionDAG &DAG, const SDLoc &dl) {
SDValue SizeNode = DAG.getConstant(Flags.getByValSize(), dl, MVT::i32);
return DAG.getMemcpy(
Chain, dl, Dst, Src, SizeNode, Flags.getNonZeroByValAlign(),
/*isVolatile=*/false, /*AlwaysInline=*/false,
/*CI=*/nullptr, std::nullopt, MachinePointerInfo(), MachinePointerInfo());
}
bool
HexagonTargetLowering::CanLowerReturn(
CallingConv::ID CallConv, MachineFunction &MF, bool IsVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
LLVMContext &Context, const Type *RetTy) const {
SmallVector<CCValAssign, 16> RVLocs;
CCState CCInfo(CallConv, IsVarArg, MF, RVLocs, Context);
if (MF.getSubtarget<HexagonSubtarget>().useHVXOps())
return CCInfo.CheckReturn(Outs, RetCC_Hexagon_HVX);
return CCInfo.CheckReturn(Outs, RetCC_Hexagon);
}
// LowerReturn - Lower ISD::RET. If a struct is larger than 8 bytes and is
// passed by value, the function prototype is modified to return void and
// the value is stored in memory pointed by a pointer passed by caller.
SDValue
HexagonTargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
bool IsVarArg,
const SmallVectorImpl<ISD::OutputArg> &Outs,
const SmallVectorImpl<SDValue> &OutVals,
const SDLoc &dl, SelectionDAG &DAG) const {
// CCValAssign - represent the assignment of the return value to locations.
SmallVector<CCValAssign, 16> RVLocs;
// CCState - Info about the registers and stack slot.
CCState CCInfo(CallConv, IsVarArg, DAG.getMachineFunction(), RVLocs,
*DAG.getContext());
// Analyze return values of ISD::RET
if (Subtarget.useHVXOps())
CCInfo.AnalyzeReturn(Outs, RetCC_Hexagon_HVX);
else
CCInfo.AnalyzeReturn(Outs, RetCC_Hexagon);
SDValue Glue;
SmallVector<SDValue, 4> RetOps(1, Chain);
// Copy the result values into the output registers.
for (unsigned i = 0; i != RVLocs.size(); ++i) {
CCValAssign &VA = RVLocs[i];
SDValue Val = OutVals[i];
switch (VA.getLocInfo()) {
default:
// Loc info must be one of Full, BCvt, SExt, ZExt, or AExt.
llvm_unreachable("Unknown loc info!");
case CCValAssign::Full:
break;
case CCValAssign::BCvt:
Val = DAG.getBitcast(VA.getLocVT(), Val);
break;
case CCValAssign::SExt:
Val = DAG.getNode(ISD::SIGN_EXTEND, dl, VA.getLocVT(), Val);
break;
case CCValAssign::ZExt:
Val = DAG.getNode(ISD::ZERO_EXTEND, dl, VA.getLocVT(), Val);
break;
case CCValAssign::AExt:
Val = DAG.getNode(ISD::ANY_EXTEND, dl, VA.getLocVT(), Val);
break;
}
Chain = DAG.getCopyToReg(Chain, dl, VA.getLocReg(), Val, Glue);
// Guarantee that all emitted copies are stuck together with flags.
Glue = Chain.getValue(1);
RetOps.push_back(DAG.getRegister(VA.getLocReg(), VA.getLocVT()));
}
RetOps[0] = Chain; // Update chain.
// Add the glue if we have it.
if (Glue.getNode())
RetOps.push_back(Glue);
return DAG.getNode(HexagonISD::RET_GLUE, dl, MVT::Other, RetOps);
}
bool HexagonTargetLowering::mayBeEmittedAsTailCall(const CallInst *CI) const {
// If either no tail call or told not to tail call at all, don't.
return CI->isTailCall();
}
Register HexagonTargetLowering::getRegisterByName(
const char* RegName, LLT VT, const MachineFunction &) const {
// Just support r19, the linux kernel uses it.
Register Reg = StringSwitch<Register>(RegName)
.Case("r0", Hexagon::R0)
.Case("r1", Hexagon::R1)
.Case("r2", Hexagon::R2)
.Case("r3", Hexagon::R3)
.Case("r4", Hexagon::R4)
.Case("r5", Hexagon::R5)
.Case("r6", Hexagon::R6)
.Case("r7", Hexagon::R7)
.Case("r8", Hexagon::R8)
.Case("r9", Hexagon::R9)
.Case("r10", Hexagon::R10)
.Case("r11", Hexagon::R11)
.Case("r12", Hexagon::R12)
.Case("r13", Hexagon::R13)
.Case("r14", Hexagon::R14)
.Case("r15", Hexagon::R15)
.Case("r16", Hexagon::R16)
.Case("r17", Hexagon::R17)
.Case("r18", Hexagon::R18)
.Case("r19", Hexagon::R19)
.Case("r20", Hexagon::R20)
.Case("r21", Hexagon::R21)
.Case("r22", Hexagon::R22)
.Case("r23", Hexagon::R23)
.Case("r24", Hexagon::R24)
.Case("r25", Hexagon::R25)
.Case("r26", Hexagon::R26)
.Case("r27", Hexagon::R27)
.Case("r28", Hexagon::R28)
.Case("r29", Hexagon::R29)
.Case("r30", Hexagon::R30)
.Case("r31", Hexagon::R31)
.Case("r1:0", Hexagon::D0)
.Case("r3:2", Hexagon::D1)
.Case("r5:4", Hexagon::D2)
.Case("r7:6", Hexagon::D3)
.Case("r9:8", Hexagon::D4)
.Case("r11:10", Hexagon::D5)
.Case("r13:12", Hexagon::D6)
.Case("r15:14", Hexagon::D7)
.Case("r17:16", Hexagon::D8)
.Case("r19:18", Hexagon::D9)
.Case("r21:20", Hexagon::D10)
.Case("r23:22", Hexagon::D11)
.Case("r25:24", Hexagon::D12)
.Case("r27:26", Hexagon::D13)
.Case("r29:28", Hexagon::D14)
.Case("r31:30", Hexagon::D15)
.Case("sp", Hexagon::R29)
.Case("fp", Hexagon::R30)
.Case("lr", Hexagon::R31)
.Case("p0", Hexagon::P0)
.Case("p1", Hexagon::P1)
.Case("p2", Hexagon::P2)
.Case("p3", Hexagon::P3)
.Case("sa0", Hexagon::SA0)
.Case("lc0", Hexagon::LC0)
.Case("sa1", Hexagon::SA1)
.Case("lc1", Hexagon::LC1)
.Case("m0", Hexagon::M0)
.Case("m1", Hexagon::M1)
.Case("usr", Hexagon::USR)
.Case("ugp", Hexagon::UGP)
.Case("cs0", Hexagon::CS0)
.Case("cs1", Hexagon::CS1)
.Default(Register());
if (Reg)
return Reg;
report_fatal_error("Invalid register name global variable");
}
/// LowerCallResult - Lower the result values of an ISD::CALL into the
/// appropriate copies out of appropriate physical registers. This assumes that
/// Chain/Glue are the input chain/glue to use, and that TheCall is the call
/// being lowered. Returns a SDNode with the same number of values as the
/// ISD::CALL.
SDValue HexagonTargetLowering::LowerCallResult(
SDValue Chain, SDValue Glue, CallingConv::ID CallConv, bool IsVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals,
const SmallVectorImpl<SDValue> &OutVals, SDValue Callee) const {
// Assign locations to each value returned by this call.
SmallVector<CCValAssign, 16> RVLocs;
CCState CCInfo(CallConv, IsVarArg, DAG.getMachineFunction(), RVLocs,
*DAG.getContext());
if (Subtarget.useHVXOps())
CCInfo.AnalyzeCallResult(Ins, RetCC_Hexagon_HVX);
else
CCInfo.AnalyzeCallResult(Ins, RetCC_Hexagon);
// Copy all of the result registers out of their specified physreg.
for (unsigned i = 0; i != RVLocs.size(); ++i) {
SDValue RetVal;
if (RVLocs[i].getValVT() == MVT::i1) {
// Return values of type MVT::i1 require special handling. The reason
// is that MVT::i1 is associated with the PredRegs register class, but
// values of that type are still returned in R0. Generate an explicit
// copy into a predicate register from R0, and treat the value of the
// predicate register as the call result.
auto &MRI = DAG.getMachineFunction().getRegInfo();
SDValue FR0 = DAG.getCopyFromReg(Chain, dl, RVLocs[i].getLocReg(),
MVT::i32, Glue);
// FR0 = (Value, Chain, Glue)
Register PredR = MRI.createVirtualRegister(&Hexagon::PredRegsRegClass);
SDValue TPR = DAG.getCopyToReg(FR0.getValue(1), dl, PredR,
FR0.getValue(0), FR0.getValue(2));
// TPR = (Chain, Glue)
// Don't glue this CopyFromReg, because it copies from a virtual
// register. If it is glued to the call, InstrEmitter will add it
// as an implicit def to the call (EmitMachineNode).
RetVal = DAG.getCopyFromReg(TPR.getValue(0), dl, PredR, MVT::i1);
Glue = TPR.getValue(1);
Chain = TPR.getValue(0);
} else {
RetVal = DAG.getCopyFromReg(Chain, dl, RVLocs[i].getLocReg(),
RVLocs[i].getValVT(), Glue);
Glue = RetVal.getValue(2);
Chain = RetVal.getValue(1);
}
InVals.push_back(RetVal.getValue(0));
}
return Chain;
}
/// LowerCall - Functions arguments are copied from virtual regs to
/// (physical regs)/(stack frame), CALLSEQ_START and CALLSEQ_END are emitted.
SDValue
HexagonTargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
SmallVectorImpl<SDValue> &InVals) const {
SelectionDAG &DAG = CLI.DAG;
SDLoc &dl = CLI.DL;
SmallVectorImpl<ISD::OutputArg> &Outs = CLI.Outs;
SmallVectorImpl<SDValue> &OutVals = CLI.OutVals;
SmallVectorImpl<ISD::InputArg> &Ins = CLI.Ins;
SDValue Chain = CLI.Chain;
SDValue Callee = CLI.Callee;
CallingConv::ID CallConv = CLI.CallConv;
bool IsVarArg = CLI.IsVarArg;
bool DoesNotReturn = CLI.DoesNotReturn;
bool IsStructRet = Outs.empty() ? false : Outs[0].Flags.isSRet();
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo &MFI = MF.getFrameInfo();
auto PtrVT = getPointerTy(MF.getDataLayout());
unsigned NumParams = CLI.CB ? CLI.CB->getFunctionType()->getNumParams() : 0;
if (GlobalAddressSDNode *GAN = dyn_cast<GlobalAddressSDNode>(Callee))
Callee = DAG.getTargetGlobalAddress(GAN->getGlobal(), dl, MVT::i32);
// Linux ABI treats var-arg calls the same way as regular ones.
bool TreatAsVarArg = !Subtarget.isEnvironmentMusl() && IsVarArg;
// Analyze operands of the call, assigning locations to each operand.
SmallVector<CCValAssign, 16> ArgLocs;
HexagonCCState CCInfo(CallConv, TreatAsVarArg, MF, ArgLocs, *DAG.getContext(),
NumParams);
if (Subtarget.useHVXOps())
CCInfo.AnalyzeCallOperands(Outs, CC_Hexagon_HVX);
else if (DisableArgsMinAlignment)
CCInfo.AnalyzeCallOperands(Outs, CC_Hexagon_Legacy);
else
CCInfo.AnalyzeCallOperands(Outs, CC_Hexagon);
if (CLI.IsTailCall) {
bool StructAttrFlag = MF.getFunction().hasStructRetAttr();
CLI.IsTailCall = IsEligibleForTailCallOptimization(Callee, CallConv,
IsVarArg, IsStructRet, StructAttrFlag, Outs,
OutVals, Ins, DAG);
for (const CCValAssign &VA : ArgLocs) {
if (VA.isMemLoc()) {
CLI.IsTailCall = false;
break;
}
}
LLVM_DEBUG(dbgs() << (CLI.IsTailCall ? "Eligible for Tail Call\n"
: "Argument must be passed on stack. "
"Not eligible for Tail Call\n"));
}
// Get a count of how many bytes are to be pushed on the stack.
unsigned NumBytes = CCInfo.getStackSize();
SmallVector<std::pair<unsigned, SDValue>, 16> RegsToPass;
SmallVector<SDValue, 8> MemOpChains;
const HexagonRegisterInfo &HRI = *Subtarget.getRegisterInfo();
SDValue StackPtr =
DAG.getCopyFromReg(Chain, dl, HRI.getStackRegister(), PtrVT);
bool NeedsArgAlign = false;
Align LargestAlignSeen;
// Walk the register/memloc assignments, inserting copies/loads.
for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
CCValAssign &VA = ArgLocs[i];
SDValue Arg = OutVals[i];
ISD::ArgFlagsTy Flags = Outs[i].Flags;
// Record if we need > 8 byte alignment on an argument.
bool ArgAlign = Subtarget.isHVXVectorType(VA.getValVT());
NeedsArgAlign |= ArgAlign;
// Promote the value if needed.
switch (VA.getLocInfo()) {
default:
// Loc info must be one of Full, BCvt, SExt, ZExt, or AExt.
llvm_unreachable("Unknown loc info!");
case CCValAssign::Full:
break;
case CCValAssign::BCvt:
Arg = DAG.getBitcast(VA.getLocVT(), Arg);
break;
case CCValAssign::SExt:
Arg = DAG.getNode(ISD::SIGN_EXTEND, dl, VA.getLocVT(), Arg);
break;
case CCValAssign::ZExt:
Arg = DAG.getNode(ISD::ZERO_EXTEND, dl, VA.getLocVT(), Arg);
break;
case CCValAssign::AExt:
Arg = DAG.getNode(ISD::ANY_EXTEND, dl, VA.getLocVT(), Arg);
break;
}
if (VA.isMemLoc()) {
unsigned LocMemOffset = VA.getLocMemOffset();
SDValue MemAddr = DAG.getConstant(LocMemOffset, dl,
StackPtr.getValueType());
MemAddr = DAG.getNode(ISD::ADD, dl, MVT::i32, StackPtr, MemAddr);
if (ArgAlign)
LargestAlignSeen = std::max(
LargestAlignSeen, Align(VA.getLocVT().getStoreSizeInBits() / 8));
if (Flags.isByVal()) {
// The argument is a struct passed by value. According to LLVM, "Arg"
// is a pointer.
MemOpChains.push_back(CreateCopyOfByValArgument(Arg, MemAddr, Chain,
Flags, DAG, dl));
} else {
MachinePointerInfo LocPI = MachinePointerInfo::getStack(
DAG.getMachineFunction(), LocMemOffset);
SDValue S = DAG.getStore(Chain, dl, Arg, MemAddr, LocPI);
MemOpChains.push_back(S);
}
continue;
}
// Arguments that can be passed on register must be kept at RegsToPass
// vector.
if (VA.isRegLoc())
RegsToPass.push_back(std::make_pair(VA.getLocReg(), Arg));
}
if (NeedsArgAlign && Subtarget.hasV60Ops()) {
LLVM_DEBUG(dbgs() << "Function needs byte stack align due to call args\n");
Align VecAlign = HRI.getSpillAlign(Hexagon::HvxVRRegClass);
LargestAlignSeen = std::max(LargestAlignSeen, VecAlign);
MFI.ensureMaxAlignment(LargestAlignSeen);
}
// Transform all store nodes into one single node because all store
// nodes are independent of each other.
if (!MemOpChains.empty())
Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, MemOpChains);
SDValue Glue;
if (!CLI.IsTailCall) {
Chain = DAG.getCALLSEQ_START(Chain, NumBytes, 0, dl);
Glue = Chain.getValue(1);
}
// Build a sequence of copy-to-reg nodes chained together with token
// chain and flag operands which copy the outgoing args into registers.
// The Glue is necessary since all emitted instructions must be
// stuck together.
if (!CLI.IsTailCall) {
for (const auto &R : RegsToPass) {
Chain = DAG.getCopyToReg(Chain, dl, R.first, R.second, Glue);
Glue = Chain.getValue(1);
}
} else {
// For tail calls lower the arguments to the 'real' stack slot.
//
// Force all the incoming stack arguments to be loaded from the stack
// before any new outgoing arguments are stored to the stack, because the
// outgoing stack slots may alias the incoming argument stack slots, and
// the alias isn't otherwise explicit. This is slightly more conservative
// than necessary, because it means that each store effectively depends
// on every argument instead of just those arguments it would clobber.
//
// Do not flag preceding copytoreg stuff together with the following stuff.
Glue = SDValue();
for (const auto &R : RegsToPass) {
Chain = DAG.getCopyToReg(Chain, dl, R.first, R.second, Glue);
Glue = Chain.getValue(1);
}
Glue = SDValue();
}
bool LongCalls = MF.getSubtarget<HexagonSubtarget>().useLongCalls();
unsigned Flags = LongCalls ? HexagonII::HMOTF_ConstExtended : 0;
// If the callee is a GlobalAddress/ExternalSymbol node (quite common, every
// direct call is) turn it into a TargetGlobalAddress/TargetExternalSymbol
// node so that legalize doesn't hack it.
if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee)) {
Callee = DAG.getTargetGlobalAddress(G->getGlobal(), dl, PtrVT, 0, Flags);
} else if (ExternalSymbolSDNode *S =
dyn_cast<ExternalSymbolSDNode>(Callee)) {
Callee = DAG.getTargetExternalSymbol(S->getSymbol(), PtrVT, Flags);
}
// Returns a chain & a flag for retval copy to use.
SmallVector<SDValue, 8> Ops;
Ops.push_back(Chain);
Ops.push_back(Callee);
// Add argument registers to the end of the list so that they are
// known live into the call.
for (const auto &R : RegsToPass)
Ops.push_back(DAG.getRegister(R.first, R.second.getValueType()));
const uint32_t *Mask = HRI.getCallPreservedMask(MF, CallConv);
assert(Mask && "Missing call preserved mask for calling convention");
Ops.push_back(DAG.getRegisterMask(Mask));
if (Glue.getNode())
Ops.push_back(Glue);
if (CLI.IsTailCall) {
MFI.setHasTailCall();
return DAG.getNode(HexagonISD::TC_RETURN, dl, MVT::Other, Ops);
}
// Set this here because we need to know this for "hasFP" in frame lowering.
// The target-independent code calls getFrameRegister before setting it, and
// getFrameRegister uses hasFP to determine whether the function has FP.
MFI.setHasCalls(true);
unsigned OpCode = DoesNotReturn ? HexagonISD::CALLnr : HexagonISD::CALL;
Chain = DAG.getNode(OpCode, dl, {MVT::Other, MVT::Glue}, Ops);
Glue = Chain.getValue(1);
// Create the CALLSEQ_END node.
Chain = DAG.getCALLSEQ_END(Chain, NumBytes, 0, Glue, dl);
Glue = Chain.getValue(1);
// Handle result values, copying them out of physregs into vregs that we
// return.
return LowerCallResult(Chain, Glue, CallConv, IsVarArg, Ins, dl, DAG,
InVals, OutVals, Callee);
}
/// Returns true by value, base pointer and offset pointer and addressing
/// mode by reference if this node can be combined with a load / store to
/// form a post-indexed load / store.
bool HexagonTargetLowering::getPostIndexedAddressParts(SDNode *N, SDNode *Op,
SDValue &Base, SDValue &Offset, ISD::MemIndexedMode &AM,
SelectionDAG &DAG) const {
LSBaseSDNode *LSN = dyn_cast<LSBaseSDNode>(N);
if (!LSN)
return false;
EVT VT = LSN->getMemoryVT();
if (!VT.isSimple())
return false;
bool IsLegalType = VT == MVT::i8 || VT == MVT::i16 || VT == MVT::i32 ||
VT == MVT::i64 || VT == MVT::f32 || VT == MVT::f64 ||
VT == MVT::v2i16 || VT == MVT::v2i32 || VT == MVT::v4i8 ||
VT == MVT::v4i16 || VT == MVT::v8i8 ||
Subtarget.isHVXVectorType(VT.getSimpleVT());
if (!IsLegalType)
return false;
if (Op->getOpcode() != ISD::ADD)
return false;
Base = Op->getOperand(0);
Offset = Op->getOperand(1);
if (!isa<ConstantSDNode>(Offset.getNode()))
return false;
AM = ISD::POST_INC;
int32_t V = cast<ConstantSDNode>(Offset.getNode())->getSExtValue();
return Subtarget.getInstrInfo()->isValidAutoIncImm(VT, V);
}
SDValue HexagonTargetLowering::LowerFDIV(SDValue Op, SelectionDAG &DAG) const {
if (DAG.getMachineFunction().getFunction().hasOptSize())
return SDValue();
else
return Op;
}
SDValue
HexagonTargetLowering::LowerINLINEASM(SDValue Op, SelectionDAG &DAG) const {
MachineFunction &MF = DAG.getMachineFunction();
auto &HMFI = *MF.getInfo<HexagonMachineFunctionInfo>();
const HexagonRegisterInfo &HRI = *Subtarget.getRegisterInfo();
unsigned LR = HRI.getRARegister();
if ((Op.getOpcode() != ISD::INLINEASM &&
Op.getOpcode() != ISD::INLINEASM_BR) || HMFI.hasClobberLR())
return Op;
unsigned NumOps = Op.getNumOperands();
if (Op.getOperand(NumOps-1).getValueType() == MVT::Glue)
--NumOps; // Ignore the flag operand.
for (unsigned i = InlineAsm::Op_FirstOperand; i != NumOps;) {
const InlineAsm::Flag Flags(Op.getConstantOperandVal(i));
unsigned NumVals = Flags.getNumOperandRegisters();
++i; // Skip the ID value.
switch (Flags.getKind()) {
default:
llvm_unreachable("Bad flags!");
case InlineAsm::Kind::RegUse:
case InlineAsm::Kind::Imm:
case InlineAsm::Kind::Mem:
i += NumVals;
break;
case InlineAsm::Kind::Clobber:
case InlineAsm::Kind::RegDef:
case InlineAsm::Kind::RegDefEarlyClobber: {
for (; NumVals; --NumVals, ++i) {
Register Reg = cast<RegisterSDNode>(Op.getOperand(i))->getReg();
if (Reg != LR)
continue;
HMFI.setHasClobberLR(true);
return Op;
}
break;
}
}
}
return Op;
}
// Need to transform ISD::PREFETCH into something that doesn't inherit
// all of the properties of ISD::PREFETCH, specifically SDNPMayLoad and
// SDNPMayStore.
SDValue HexagonTargetLowering::LowerPREFETCH(SDValue Op,
SelectionDAG &DAG) const {
SDValue Chain = Op.getOperand(0);
SDValue Addr = Op.getOperand(1);
// Lower it to DCFETCH($reg, #0). A "pat" will try to merge the offset in,
// if the "reg" is fed by an "add".
SDLoc DL(Op);
SDValue Zero = DAG.getConstant(0, DL, MVT::i32);
return DAG.getNode(HexagonISD::DCFETCH, DL, MVT::Other, Chain, Addr, Zero);
}
// Custom-handle ISD::READCYCLECOUNTER because the target-independent SDNode
// is marked as having side-effects, while the register read on Hexagon does
// not have any. TableGen refuses to accept the direct pattern from that node
// to the A4_tfrcpp.
SDValue HexagonTargetLowering::LowerREADCYCLECOUNTER(SDValue Op,
SelectionDAG &DAG) const {
SDValue Chain = Op.getOperand(0);
SDLoc dl(Op);
SDVTList VTs = DAG.getVTList(MVT::i64, MVT::Other);
return DAG.getNode(HexagonISD::READCYCLE, dl, VTs, Chain);
}
// Custom-handle ISD::READSTEADYCOUNTER because the target-independent SDNode
// is marked as having side-effects, while the register read on Hexagon does
// not have any. TableGen refuses to accept the direct pattern from that node
// to the A4_tfrcpp.
SDValue HexagonTargetLowering::LowerREADSTEADYCOUNTER(SDValue Op,
SelectionDAG &DAG) const {
SDValue Chain = Op.getOperand(0);
SDLoc dl(Op);
SDVTList VTs = DAG.getVTList(MVT::i64, MVT::Other);
return DAG.getNode(HexagonISD::READTIMER, dl, VTs, Chain);
}
SDValue HexagonTargetLowering::LowerINTRINSIC_VOID(SDValue Op,
SelectionDAG &DAG) const {
SDValue Chain = Op.getOperand(0);
unsigned IntNo = Op.getConstantOperandVal(1);
// Lower the hexagon_prefetch builtin to DCFETCH, as above.
if (IntNo == Intrinsic::hexagon_prefetch) {
SDValue Addr = Op.getOperand(2);
SDLoc DL(Op);
SDValue Zero = DAG.getConstant(0, DL, MVT::i32);
return DAG.getNode(HexagonISD::DCFETCH, DL, MVT::Other, Chain, Addr, Zero);
}
return SDValue();
}
SDValue
HexagonTargetLowering::LowerDYNAMIC_STACKALLOC(SDValue Op,
SelectionDAG &DAG) const {
SDValue Chain = Op.getOperand(0);
SDValue Size = Op.getOperand(1);
SDValue Align = Op.getOperand(2);
SDLoc dl(Op);
ConstantSDNode *AlignConst = dyn_cast<ConstantSDNode>(Align);
assert(AlignConst && "Non-constant Align in LowerDYNAMIC_STACKALLOC");
unsigned A = AlignConst->getSExtValue();
auto &HFI = *Subtarget.getFrameLowering();
// "Zero" means natural stack alignment.
if (A == 0)
A = HFI.getStackAlign().value();
LLVM_DEBUG({
dbgs () << __func__ << " Align: " << A << " Size: ";
Size.getNode()->dump(&DAG);
dbgs() << "\n";
});
SDValue AC = DAG.getConstant(A, dl, MVT::i32);
SDVTList VTs = DAG.getVTList(MVT::i32, MVT::Other);
SDValue AA = DAG.getNode(HexagonISD::ALLOCA, dl, VTs, Chain, Size, AC);
DAG.ReplaceAllUsesOfValueWith(Op, AA);
return AA;
}
SDValue HexagonTargetLowering::LowerFormalArguments(
SDValue Chain, CallingConv::ID CallConv, bool IsVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &dl,
SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const {
MachineFunction &MF = DAG.getMachineFunction();
MachineFrameInfo &MFI = MF.getFrameInfo();
MachineRegisterInfo &MRI = MF.getRegInfo();
// Linux ABI treats var-arg calls the same way as regular ones.
bool TreatAsVarArg = !Subtarget.isEnvironmentMusl() && IsVarArg;
// Assign locations to all of the incoming arguments.
SmallVector<CCValAssign, 16> ArgLocs;
HexagonCCState CCInfo(CallConv, TreatAsVarArg, MF, ArgLocs,
*DAG.getContext(),
MF.getFunction().getFunctionType()->getNumParams());
if (Subtarget.useHVXOps())
CCInfo.AnalyzeFormalArguments(Ins, CC_Hexagon_HVX);
else if (DisableArgsMinAlignment)
CCInfo.AnalyzeFormalArguments(Ins, CC_Hexagon_Legacy);
else
CCInfo.AnalyzeFormalArguments(Ins, CC_Hexagon);
// For LLVM, in the case when returning a struct by value (>8byte),
// the first argument is a pointer that points to the location on caller's
// stack where the return value will be stored. For Hexagon, the location on
// caller's stack is passed only when the struct size is smaller than (and
// equal to) 8 bytes. If not, no address will be passed into callee and
// callee return the result direclty through R0/R1.
auto NextSingleReg = [] (const TargetRegisterClass &RC, unsigned Reg) {
switch (RC.getID()) {
case Hexagon::IntRegsRegClassID:
return Reg - Hexagon::R0 + 1;
case Hexagon::DoubleRegsRegClassID:
return (Reg - Hexagon::D0 + 1) * 2;
case Hexagon::HvxVRRegClassID:
return Reg - Hexagon::V0 + 1;
case Hexagon::HvxWRRegClassID:
return (Reg - Hexagon::W0 + 1) * 2;
}
llvm_unreachable("Unexpected register class");
};
auto &HFL = const_cast<HexagonFrameLowering&>(*Subtarget.getFrameLowering());
auto &HMFI = *MF.getInfo<HexagonMachineFunctionInfo>();
HFL.FirstVarArgSavedReg = 0;
HMFI.setFirstNamedArgFrameIndex(-int(MFI.getNumFixedObjects()));
for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
CCValAssign &VA = ArgLocs[i];
ISD::ArgFlagsTy Flags = Ins[i].Flags;
bool ByVal = Flags.isByVal();
// Arguments passed in registers:
// 1. 32- and 64-bit values and HVX vectors are passed directly,
// 2. Large structs are passed via an address, and the address is
// passed in a register.
if (VA.isRegLoc() && ByVal && Flags.getByValSize() <= 8)
llvm_unreachable("ByValSize must be bigger than 8 bytes");
bool InReg = VA.isRegLoc() &&
(!ByVal || (ByVal && Flags.getByValSize() > 8));
if (InReg) {
MVT RegVT = VA.getLocVT();
if (VA.getLocInfo() == CCValAssign::BCvt)
RegVT = VA.getValVT();
const TargetRegisterClass *RC = getRegClassFor(RegVT);
Register VReg = MRI.createVirtualRegister(RC);
SDValue Copy = DAG.getCopyFromReg(Chain, dl, VReg, RegVT);
// Treat values of type MVT::i1 specially: they are passed in
// registers of type i32, but they need to remain as values of
// type i1 for consistency of the argument lowering.
if (VA.getValVT() == MVT::i1) {
assert(RegVT.getSizeInBits() <= 32);
SDValue T = DAG.getNode(ISD::AND, dl, RegVT,
Copy, DAG.getConstant(1, dl, RegVT));
Copy = DAG.getSetCC(dl, MVT::i1, T, DAG.getConstant(0, dl, RegVT),
ISD::SETNE);
} else {
#ifndef NDEBUG
unsigned RegSize = RegVT.getSizeInBits();
assert(RegSize == 32 || RegSize == 64 ||
Subtarget.isHVXVectorType(RegVT));
#endif
}
InVals.push_back(Copy);
MRI.addLiveIn(VA.getLocReg(), VReg);
HFL.FirstVarArgSavedReg = NextSingleReg(*RC, VA.getLocReg());
} else {
assert(VA.isMemLoc() && "Argument should be passed in memory");
// If it's a byval parameter, then we need to compute the
// "real" size, not the size of the pointer.
unsigned ObjSize = Flags.isByVal()
? Flags.getByValSize()
: VA.getLocVT().getStoreSizeInBits() / 8;
// Create the frame index object for this incoming parameter.
int Offset = HEXAGON_LRFP_SIZE + VA.getLocMemOffset();
int FI = MFI.CreateFixedObject(ObjSize, Offset, true);
SDValue FIN = DAG.getFrameIndex(FI, MVT::i32);
if (Flags.isByVal()) {
// If it's a pass-by-value aggregate, then do not dereference the stack
// location. Instead, we should generate a reference to the stack
// location.
InVals.push_back(FIN);
} else {
SDValue L = DAG.getLoad(VA.getValVT(), dl, Chain, FIN,
MachinePointerInfo::getFixedStack(MF, FI, 0));
InVals.push_back(L);
}
}
}
if (IsVarArg && Subtarget.isEnvironmentMusl()) {
for (int i = HFL.FirstVarArgSavedReg; i < 6; i++)
MRI.addLiveIn(Hexagon::R0+i);
}
if (IsVarArg && Subtarget.isEnvironmentMusl()) {
HMFI.setFirstNamedArgFrameIndex(HMFI.getFirstNamedArgFrameIndex() - 1);
HMFI.setLastNamedArgFrameIndex(-int(MFI.getNumFixedObjects()));
// Create Frame index for the start of register saved area.
int NumVarArgRegs = 6 - HFL.FirstVarArgSavedReg;
bool RequiresPadding = (NumVarArgRegs & 1);
int RegSaveAreaSizePlusPadding = RequiresPadding
? (NumVarArgRegs + 1) * 4
: NumVarArgRegs * 4;
if (RegSaveAreaSizePlusPadding > 0) {
// The offset to saved register area should be 8 byte aligned.
int RegAreaStart = HEXAGON_LRFP_SIZE + CCInfo.getStackSize();
if (!(RegAreaStart % 8))
RegAreaStart = (RegAreaStart + 7) & -8;
int RegSaveAreaFrameIndex =
MFI.CreateFixedObject(RegSaveAreaSizePlusPadding, RegAreaStart, true);
HMFI.setRegSavedAreaStartFrameIndex(RegSaveAreaFrameIndex);
// This will point to the next argument passed via stack.
int Offset = RegAreaStart + RegSaveAreaSizePlusPadding;
int FI = MFI.CreateFixedObject(Hexagon_PointerSize, Offset, true);
HMFI.setVarArgsFrameIndex(FI);
} else {
// This will point to the next argument passed via stack, when
// there is no saved register area.
int Offset = HEXAGON_LRFP_SIZE + CCInfo.getStackSize();
int FI = MFI.CreateFixedObject(Hexagon_PointerSize, Offset, true);
HMFI.setRegSavedAreaStartFrameIndex(FI);
HMFI.setVarArgsFrameIndex(FI);
}
}
if (IsVarArg && !Subtarget.isEnvironmentMusl()) {
// This will point to the next argument passed via stack.
int Offset = HEXAGON_LRFP_SIZE + CCInfo.getStackSize();
int FI = MFI.CreateFixedObject(Hexagon_PointerSize, Offset, true);
HMFI.setVarArgsFrameIndex(FI);
}
return Chain;
}
SDValue
HexagonTargetLowering::LowerVASTART(SDValue Op, SelectionDAG &DAG) const {
// VASTART stores the address of the VarArgsFrameIndex slot into the
// memory location argument.
MachineFunction &MF = DAG.getMachineFunction();
HexagonMachineFunctionInfo *QFI = MF.getInfo<HexagonMachineFunctionInfo>();
SDValue Addr = DAG.getFrameIndex(QFI->getVarArgsFrameIndex(), MVT::i32);
const Value *SV = cast<SrcValueSDNode>(Op.getOperand(2))->getValue();
if (!Subtarget.isEnvironmentMusl()) {
return DAG.getStore(Op.getOperand(0), SDLoc(Op), Addr, Op.getOperand(1),
MachinePointerInfo(SV));
}
auto &FuncInfo = *MF.getInfo<HexagonMachineFunctionInfo>();
auto &HFL = *Subtarget.getFrameLowering();
SDLoc DL(Op);
SmallVector<SDValue, 8> MemOps;
// Get frame index of va_list.
SDValue FIN = Op.getOperand(1);
// If first Vararg register is odd, add 4 bytes to start of
// saved register area to point to the first register location.
// This is because the saved register area has to be 8 byte aligned.
// Incase of an odd start register, there will be 4 bytes of padding in
// the beginning of saved register area. If all registers area used up,
// the following condition will handle it correctly.
SDValue SavedRegAreaStartFrameIndex =
DAG.getFrameIndex(FuncInfo.getRegSavedAreaStartFrameIndex(), MVT::i32);
auto PtrVT = getPointerTy(DAG.getDataLayout());
if (HFL.FirstVarArgSavedReg & 1)
SavedRegAreaStartFrameIndex =
DAG.getNode(ISD::ADD, DL, PtrVT,
DAG.getFrameIndex(FuncInfo.getRegSavedAreaStartFrameIndex(),
MVT::i32),
DAG.getIntPtrConstant(4, DL));
// Store the saved register area start pointer.
SDValue Store =
DAG.getStore(Op.getOperand(0), DL,
SavedRegAreaStartFrameIndex,