forked from llvm/llvm-project
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathPPCInstrInfo.cpp
5495 lines (4935 loc) · 202 KB
/
PPCInstrInfo.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
//===-- PPCInstrInfo.cpp - PowerPC Instruction Information ----------------===//
//
// 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 contains the PowerPC implementation of the TargetInstrInfo class.
//
//===----------------------------------------------------------------------===//
#include "PPCInstrInfo.h"
#include "MCTargetDesc/PPCPredicates.h"
#include "PPC.h"
#include "PPCHazardRecognizers.h"
#include "PPCInstrBuilder.h"
#include "PPCMachineFunctionInfo.h"
#include "PPCTargetMachine.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/CodeGen/LiveIntervals.h"
#include "llvm/CodeGen/MachineConstantPool.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineMemOperand.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/PseudoSourceValue.h"
#include "llvm/CodeGen/RegisterClassInfo.h"
#include "llvm/CodeGen/RegisterPressure.h"
#include "llvm/CodeGen/ScheduleDAG.h"
#include "llvm/CodeGen/SlotIndexes.h"
#include "llvm/CodeGen/StackMaps.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCInst.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
#define DEBUG_TYPE "ppc-instr-info"
#define GET_INSTRMAP_INFO
#define GET_INSTRINFO_CTOR_DTOR
#include "PPCGenInstrInfo.inc"
STATISTIC(NumStoreSPILLVSRRCAsVec,
"Number of spillvsrrc spilled to stack as vec");
STATISTIC(NumStoreSPILLVSRRCAsGpr,
"Number of spillvsrrc spilled to stack as gpr");
STATISTIC(NumGPRtoVSRSpill, "Number of gpr spills to spillvsrrc");
STATISTIC(CmpIselsConverted,
"Number of ISELs that depend on comparison of constants converted");
STATISTIC(MissedConvertibleImmediateInstrs,
"Number of compare-immediate instructions fed by constants");
STATISTIC(NumRcRotatesConvertedToRcAnd,
"Number of record-form rotates converted to record-form andi");
static cl::
opt<bool> DisableCTRLoopAnal("disable-ppc-ctrloop-analysis", cl::Hidden,
cl::desc("Disable analysis for CTR loops"));
static cl::opt<bool> DisableCmpOpt("disable-ppc-cmp-opt",
cl::desc("Disable compare instruction optimization"), cl::Hidden);
static cl::opt<bool> VSXSelfCopyCrash("crash-on-ppc-vsx-self-copy",
cl::desc("Causes the backend to crash instead of generating a nop VSX copy"),
cl::Hidden);
static cl::opt<bool>
UseOldLatencyCalc("ppc-old-latency-calc", cl::Hidden,
cl::desc("Use the old (incorrect) instruction latency calculation"));
static cl::opt<float>
FMARPFactor("ppc-fma-rp-factor", cl::Hidden, cl::init(1.5),
cl::desc("register pressure factor for the transformations."));
static cl::opt<bool> EnableFMARegPressureReduction(
"ppc-fma-rp-reduction", cl::Hidden, cl::init(true),
cl::desc("enable register pressure reduce in machine combiner pass."));
// Pin the vtable to this file.
void PPCInstrInfo::anchor() {}
PPCInstrInfo::PPCInstrInfo(PPCSubtarget &STI)
: PPCGenInstrInfo(PPC::ADJCALLSTACKDOWN, PPC::ADJCALLSTACKUP,
/* CatchRetOpcode */ -1,
STI.isPPC64() ? PPC::BLR8 : PPC::BLR),
Subtarget(STI), RI(STI.getTargetMachine()) {}
/// CreateTargetHazardRecognizer - Return the hazard recognizer to use for
/// this target when scheduling the DAG.
ScheduleHazardRecognizer *
PPCInstrInfo::CreateTargetHazardRecognizer(const TargetSubtargetInfo *STI,
const ScheduleDAG *DAG) const {
unsigned Directive =
static_cast<const PPCSubtarget *>(STI)->getCPUDirective();
if (Directive == PPC::DIR_440 || Directive == PPC::DIR_A2 ||
Directive == PPC::DIR_E500mc || Directive == PPC::DIR_E5500) {
const InstrItineraryData *II =
static_cast<const PPCSubtarget *>(STI)->getInstrItineraryData();
return new ScoreboardHazardRecognizer(II, DAG);
}
return TargetInstrInfo::CreateTargetHazardRecognizer(STI, DAG);
}
/// CreateTargetPostRAHazardRecognizer - Return the postRA hazard recognizer
/// to use for this target when scheduling the DAG.
ScheduleHazardRecognizer *
PPCInstrInfo::CreateTargetPostRAHazardRecognizer(const InstrItineraryData *II,
const ScheduleDAG *DAG) const {
unsigned Directive =
DAG->MF.getSubtarget<PPCSubtarget>().getCPUDirective();
// FIXME: Leaving this as-is until we have POWER9 scheduling info
if (Directive == PPC::DIR_PWR7 || Directive == PPC::DIR_PWR8)
return new PPCDispatchGroupSBHazardRecognizer(II, DAG);
// Most subtargets use a PPC970 recognizer.
if (Directive != PPC::DIR_440 && Directive != PPC::DIR_A2 &&
Directive != PPC::DIR_E500mc && Directive != PPC::DIR_E5500) {
assert(DAG->TII && "No InstrInfo?");
return new PPCHazardRecognizer970(*DAG);
}
return new ScoreboardHazardRecognizer(II, DAG);
}
unsigned PPCInstrInfo::getInstrLatency(const InstrItineraryData *ItinData,
const MachineInstr &MI,
unsigned *PredCost) const {
if (!ItinData || UseOldLatencyCalc)
return PPCGenInstrInfo::getInstrLatency(ItinData, MI, PredCost);
// The default implementation of getInstrLatency calls getStageLatency, but
// getStageLatency does not do the right thing for us. While we have
// itinerary, most cores are fully pipelined, and so the itineraries only
// express the first part of the pipeline, not every stage. Instead, we need
// to use the listed output operand cycle number (using operand 0 here, which
// is an output).
unsigned Latency = 1;
unsigned DefClass = MI.getDesc().getSchedClass();
for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) {
const MachineOperand &MO = MI.getOperand(i);
if (!MO.isReg() || !MO.isDef() || MO.isImplicit())
continue;
int Cycle = ItinData->getOperandCycle(DefClass, i);
if (Cycle < 0)
continue;
Latency = std::max(Latency, (unsigned) Cycle);
}
return Latency;
}
int PPCInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
const MachineInstr &DefMI, unsigned DefIdx,
const MachineInstr &UseMI,
unsigned UseIdx) const {
int Latency = PPCGenInstrInfo::getOperandLatency(ItinData, DefMI, DefIdx,
UseMI, UseIdx);
if (!DefMI.getParent())
return Latency;
const MachineOperand &DefMO = DefMI.getOperand(DefIdx);
Register Reg = DefMO.getReg();
bool IsRegCR;
if (Register::isVirtualRegister(Reg)) {
const MachineRegisterInfo *MRI =
&DefMI.getParent()->getParent()->getRegInfo();
IsRegCR = MRI->getRegClass(Reg)->hasSuperClassEq(&PPC::CRRCRegClass) ||
MRI->getRegClass(Reg)->hasSuperClassEq(&PPC::CRBITRCRegClass);
} else {
IsRegCR = PPC::CRRCRegClass.contains(Reg) ||
PPC::CRBITRCRegClass.contains(Reg);
}
if (UseMI.isBranch() && IsRegCR) {
if (Latency < 0)
Latency = getInstrLatency(ItinData, DefMI);
// On some cores, there is an additional delay between writing to a condition
// register, and using it from a branch.
unsigned Directive = Subtarget.getCPUDirective();
switch (Directive) {
default: break;
case PPC::DIR_7400:
case PPC::DIR_750:
case PPC::DIR_970:
case PPC::DIR_E5500:
case PPC::DIR_PWR4:
case PPC::DIR_PWR5:
case PPC::DIR_PWR5X:
case PPC::DIR_PWR6:
case PPC::DIR_PWR6X:
case PPC::DIR_PWR7:
case PPC::DIR_PWR8:
// FIXME: Is this needed for POWER9?
Latency += 2;
break;
}
}
return Latency;
}
/// This is an architecture-specific helper function of reassociateOps.
/// Set special operand attributes for new instructions after reassociation.
void PPCInstrInfo::setSpecialOperandAttr(MachineInstr &OldMI1,
MachineInstr &OldMI2,
MachineInstr &NewMI1,
MachineInstr &NewMI2) const {
// Propagate FP flags from the original instructions.
// But clear poison-generating flags because those may not be valid now.
uint16_t IntersectedFlags = OldMI1.getFlags() & OldMI2.getFlags();
NewMI1.setFlags(IntersectedFlags);
NewMI1.clearFlag(MachineInstr::MIFlag::NoSWrap);
NewMI1.clearFlag(MachineInstr::MIFlag::NoUWrap);
NewMI1.clearFlag(MachineInstr::MIFlag::IsExact);
NewMI2.setFlags(IntersectedFlags);
NewMI2.clearFlag(MachineInstr::MIFlag::NoSWrap);
NewMI2.clearFlag(MachineInstr::MIFlag::NoUWrap);
NewMI2.clearFlag(MachineInstr::MIFlag::IsExact);
}
void PPCInstrInfo::setSpecialOperandAttr(MachineInstr &MI,
uint16_t Flags) const {
MI.setFlags(Flags);
MI.clearFlag(MachineInstr::MIFlag::NoSWrap);
MI.clearFlag(MachineInstr::MIFlag::NoUWrap);
MI.clearFlag(MachineInstr::MIFlag::IsExact);
}
// This function does not list all associative and commutative operations, but
// only those worth feeding through the machine combiner in an attempt to
// reduce the critical path. Mostly, this means floating-point operations,
// because they have high latencies(>=5) (compared to other operations, such as
// and/or, which are also associative and commutative, but have low latencies).
bool PPCInstrInfo::isAssociativeAndCommutative(const MachineInstr &Inst) const {
switch (Inst.getOpcode()) {
// Floating point:
// FP Add:
case PPC::FADD:
case PPC::FADDS:
// FP Multiply:
case PPC::FMUL:
case PPC::FMULS:
// Altivec Add:
case PPC::VADDFP:
// VSX Add:
case PPC::XSADDDP:
case PPC::XVADDDP:
case PPC::XVADDSP:
case PPC::XSADDSP:
// VSX Multiply:
case PPC::XSMULDP:
case PPC::XVMULDP:
case PPC::XVMULSP:
case PPC::XSMULSP:
return Inst.getFlag(MachineInstr::MIFlag::FmReassoc) &&
Inst.getFlag(MachineInstr::MIFlag::FmNsz);
// Fixed point:
// Multiply:
case PPC::MULHD:
case PPC::MULLD:
case PPC::MULHW:
case PPC::MULLW:
return true;
default:
return false;
}
}
#define InfoArrayIdxFMAInst 0
#define InfoArrayIdxFAddInst 1
#define InfoArrayIdxFMULInst 2
#define InfoArrayIdxAddOpIdx 3
#define InfoArrayIdxMULOpIdx 4
#define InfoArrayIdxFSubInst 5
// Array keeps info for FMA instructions:
// Index 0(InfoArrayIdxFMAInst): FMA instruction;
// Index 1(InfoArrayIdxFAddInst): ADD instruction associated with FMA;
// Index 2(InfoArrayIdxFMULInst): MUL instruction associated with FMA;
// Index 3(InfoArrayIdxAddOpIdx): ADD operand index in FMA operands;
// Index 4(InfoArrayIdxMULOpIdx): first MUL operand index in FMA operands;
// second MUL operand index is plus 1;
// Index 5(InfoArrayIdxFSubInst): SUB instruction associated with FMA.
static const uint16_t FMAOpIdxInfo[][6] = {
// FIXME: Add more FMA instructions like XSNMADDADP and so on.
{PPC::XSMADDADP, PPC::XSADDDP, PPC::XSMULDP, 1, 2, PPC::XSSUBDP},
{PPC::XSMADDASP, PPC::XSADDSP, PPC::XSMULSP, 1, 2, PPC::XSSUBSP},
{PPC::XVMADDADP, PPC::XVADDDP, PPC::XVMULDP, 1, 2, PPC::XVSUBDP},
{PPC::XVMADDASP, PPC::XVADDSP, PPC::XVMULSP, 1, 2, PPC::XVSUBSP},
{PPC::FMADD, PPC::FADD, PPC::FMUL, 3, 1, PPC::FSUB},
{PPC::FMADDS, PPC::FADDS, PPC::FMULS, 3, 1, PPC::FSUBS}};
// Check if an opcode is a FMA instruction. If it is, return the index in array
// FMAOpIdxInfo. Otherwise, return -1.
int16_t PPCInstrInfo::getFMAOpIdxInfo(unsigned Opcode) const {
for (unsigned I = 0; I < array_lengthof(FMAOpIdxInfo); I++)
if (FMAOpIdxInfo[I][InfoArrayIdxFMAInst] == Opcode)
return I;
return -1;
}
// On PowerPC target, we have two kinds of patterns related to FMA:
// 1: Improve ILP.
// Try to reassociate FMA chains like below:
//
// Pattern 1:
// A = FADD X, Y (Leaf)
// B = FMA A, M21, M22 (Prev)
// C = FMA B, M31, M32 (Root)
// -->
// A = FMA X, M21, M22
// B = FMA Y, M31, M32
// C = FADD A, B
//
// Pattern 2:
// A = FMA X, M11, M12 (Leaf)
// B = FMA A, M21, M22 (Prev)
// C = FMA B, M31, M32 (Root)
// -->
// A = FMUL M11, M12
// B = FMA X, M21, M22
// D = FMA A, M31, M32
// C = FADD B, D
//
// breaking the dependency between A and B, allowing FMA to be executed in
// parallel (or back-to-back in a pipeline) instead of depending on each other.
//
// 2: Reduce register pressure.
// Try to reassociate FMA with FSUB and a constant like below:
// C is a floating point const.
//
// Pattern 1:
// A = FSUB X, Y (Leaf)
// D = FMA B, C, A (Root)
// -->
// A = FMA B, Y, -C
// D = FMA A, X, C
//
// Pattern 2:
// A = FSUB X, Y (Leaf)
// D = FMA B, A, C (Root)
// -->
// A = FMA B, Y, -C
// D = FMA A, X, C
//
// Before the transformation, A must be assigned with different hardware
// register with D. After the transformation, A and D must be assigned with
// same hardware register due to TIE attribute of FMA instructions.
//
bool PPCInstrInfo::getFMAPatterns(
MachineInstr &Root, SmallVectorImpl<MachineCombinerPattern> &Patterns,
bool DoRegPressureReduce) const {
MachineBasicBlock *MBB = Root.getParent();
const MachineRegisterInfo *MRI = &MBB->getParent()->getRegInfo();
const TargetRegisterInfo *TRI = &getRegisterInfo();
auto IsAllOpsVirtualReg = [](const MachineInstr &Instr) {
for (const auto &MO : Instr.explicit_operands())
if (!(MO.isReg() && Register::isVirtualRegister(MO.getReg())))
return false;
return true;
};
auto IsReassociableAddOrSub = [&](const MachineInstr &Instr,
unsigned OpType) {
if (Instr.getOpcode() !=
FMAOpIdxInfo[getFMAOpIdxInfo(Root.getOpcode())][OpType])
return false;
// Instruction can be reassociated.
// fast math flags may prohibit reassociation.
if (!(Instr.getFlag(MachineInstr::MIFlag::FmReassoc) &&
Instr.getFlag(MachineInstr::MIFlag::FmNsz)))
return false;
// Instruction operands are virtual registers for reassociation.
if (!IsAllOpsVirtualReg(Instr))
return false;
// For register pressure reassociation, the FSub must have only one use as
// we want to delete the sub to save its def.
if (OpType == InfoArrayIdxFSubInst &&
!MRI->hasOneNonDBGUse(Instr.getOperand(0).getReg()))
return false;
return true;
};
auto IsReassociableFMA = [&](const MachineInstr &Instr, int16_t &AddOpIdx,
int16_t &MulOpIdx, bool IsLeaf) {
int16_t Idx = getFMAOpIdxInfo(Instr.getOpcode());
if (Idx < 0)
return false;
// Instruction can be reassociated.
// fast math flags may prohibit reassociation.
if (!(Instr.getFlag(MachineInstr::MIFlag::FmReassoc) &&
Instr.getFlag(MachineInstr::MIFlag::FmNsz)))
return false;
// Instruction operands are virtual registers for reassociation.
if (!IsAllOpsVirtualReg(Instr))
return false;
MulOpIdx = FMAOpIdxInfo[Idx][InfoArrayIdxMULOpIdx];
if (IsLeaf)
return true;
AddOpIdx = FMAOpIdxInfo[Idx][InfoArrayIdxAddOpIdx];
const MachineOperand &OpAdd = Instr.getOperand(AddOpIdx);
MachineInstr *MIAdd = MRI->getUniqueVRegDef(OpAdd.getReg());
// If 'add' operand's def is not in current block, don't do ILP related opt.
if (!MIAdd || MIAdd->getParent() != MBB)
return false;
// If this is not Leaf FMA Instr, its 'add' operand should only have one use
// as this fma will be changed later.
return IsLeaf ? true : MRI->hasOneNonDBGUse(OpAdd.getReg());
};
int16_t AddOpIdx = -1;
int16_t MulOpIdx = -1;
bool IsUsedOnceL = false;
bool IsUsedOnceR = false;
MachineInstr *MULInstrL = nullptr;
MachineInstr *MULInstrR = nullptr;
auto IsRPReductionCandidate = [&]() {
// Currently, we only support float and double.
// FIXME: add support for other types.
unsigned Opcode = Root.getOpcode();
if (Opcode != PPC::XSMADDASP && Opcode != PPC::XSMADDADP)
return false;
// Root must be a valid FMA like instruction.
// Treat it as leaf as we don't care its add operand.
if (IsReassociableFMA(Root, AddOpIdx, MulOpIdx, true)) {
assert((MulOpIdx >= 0) && "mul operand index not right!");
Register MULRegL = TRI->lookThruSingleUseCopyChain(
Root.getOperand(MulOpIdx).getReg(), MRI);
Register MULRegR = TRI->lookThruSingleUseCopyChain(
Root.getOperand(MulOpIdx + 1).getReg(), MRI);
if (!MULRegL && !MULRegR)
return false;
if (MULRegL && !MULRegR) {
MULRegR =
TRI->lookThruCopyLike(Root.getOperand(MulOpIdx + 1).getReg(), MRI);
IsUsedOnceL = true;
} else if (!MULRegL && MULRegR) {
MULRegL =
TRI->lookThruCopyLike(Root.getOperand(MulOpIdx).getReg(), MRI);
IsUsedOnceR = true;
} else {
IsUsedOnceL = true;
IsUsedOnceR = true;
}
if (!Register::isVirtualRegister(MULRegL) ||
!Register::isVirtualRegister(MULRegR))
return false;
MULInstrL = MRI->getVRegDef(MULRegL);
MULInstrR = MRI->getVRegDef(MULRegR);
return true;
}
return false;
};
// Register pressure fma reassociation patterns.
if (DoRegPressureReduce && IsRPReductionCandidate()) {
assert((MULInstrL && MULInstrR) && "wrong register preduction candidate!");
// Register pressure pattern 1
if (isLoadFromConstantPool(MULInstrL) && IsUsedOnceR &&
IsReassociableAddOrSub(*MULInstrR, InfoArrayIdxFSubInst)) {
LLVM_DEBUG(dbgs() << "add pattern REASSOC_XY_BCA\n");
Patterns.push_back(MachineCombinerPattern::REASSOC_XY_BCA);
return true;
}
// Register pressure pattern 2
if ((isLoadFromConstantPool(MULInstrR) && IsUsedOnceL &&
IsReassociableAddOrSub(*MULInstrL, InfoArrayIdxFSubInst))) {
LLVM_DEBUG(dbgs() << "add pattern REASSOC_XY_BAC\n");
Patterns.push_back(MachineCombinerPattern::REASSOC_XY_BAC);
return true;
}
}
// ILP fma reassociation patterns.
// Root must be a valid FMA like instruction.
AddOpIdx = -1;
if (!IsReassociableFMA(Root, AddOpIdx, MulOpIdx, false))
return false;
assert((AddOpIdx >= 0) && "add operand index not right!");
Register RegB = Root.getOperand(AddOpIdx).getReg();
MachineInstr *Prev = MRI->getUniqueVRegDef(RegB);
// Prev must be a valid FMA like instruction.
AddOpIdx = -1;
if (!IsReassociableFMA(*Prev, AddOpIdx, MulOpIdx, false))
return false;
assert((AddOpIdx >= 0) && "add operand index not right!");
Register RegA = Prev->getOperand(AddOpIdx).getReg();
MachineInstr *Leaf = MRI->getUniqueVRegDef(RegA);
AddOpIdx = -1;
if (IsReassociableFMA(*Leaf, AddOpIdx, MulOpIdx, true)) {
Patterns.push_back(MachineCombinerPattern::REASSOC_XMM_AMM_BMM);
LLVM_DEBUG(dbgs() << "add pattern REASSOC_XMM_AMM_BMM\n");
return true;
}
if (IsReassociableAddOrSub(*Leaf, InfoArrayIdxFAddInst)) {
Patterns.push_back(MachineCombinerPattern::REASSOC_XY_AMM_BMM);
LLVM_DEBUG(dbgs() << "add pattern REASSOC_XY_AMM_BMM\n");
return true;
}
return false;
}
void PPCInstrInfo::finalizeInsInstrs(
MachineInstr &Root, MachineCombinerPattern &P,
SmallVectorImpl<MachineInstr *> &InsInstrs) const {
assert(!InsInstrs.empty() && "Instructions set to be inserted is empty!");
MachineFunction *MF = Root.getMF();
MachineRegisterInfo *MRI = &MF->getRegInfo();
const TargetRegisterInfo *TRI = &getRegisterInfo();
MachineConstantPool *MCP = MF->getConstantPool();
int16_t Idx = getFMAOpIdxInfo(Root.getOpcode());
if (Idx < 0)
return;
uint16_t FirstMulOpIdx = FMAOpIdxInfo[Idx][InfoArrayIdxMULOpIdx];
// For now we only need to fix up placeholder for register pressure reduce
// patterns.
Register ConstReg = 0;
switch (P) {
case MachineCombinerPattern::REASSOC_XY_BCA:
ConstReg =
TRI->lookThruCopyLike(Root.getOperand(FirstMulOpIdx).getReg(), MRI);
break;
case MachineCombinerPattern::REASSOC_XY_BAC:
ConstReg =
TRI->lookThruCopyLike(Root.getOperand(FirstMulOpIdx + 1).getReg(), MRI);
break;
default:
// Not register pressure reduce patterns.
return;
}
MachineInstr *ConstDefInstr = MRI->getVRegDef(ConstReg);
// Get const value from const pool.
const Constant *C = getConstantFromConstantPool(ConstDefInstr);
assert(isa<llvm::ConstantFP>(C) && "not a valid constant!");
// Get negative fp const.
APFloat F1((dyn_cast<ConstantFP>(C))->getValueAPF());
F1.changeSign();
Constant *NegC = ConstantFP::get(dyn_cast<ConstantFP>(C)->getContext(), F1);
Align Alignment = MF->getDataLayout().getPrefTypeAlign(C->getType());
// Put negative fp const into constant pool.
unsigned ConstPoolIdx = MCP->getConstantPoolIndex(NegC, Alignment);
MachineOperand *Placeholder = nullptr;
// Record the placeholder PPC::ZERO8 we add in reassociateFMA.
for (auto *Inst : InsInstrs) {
for (MachineOperand &Operand : Inst->explicit_operands()) {
assert(Operand.isReg() && "Invalid instruction in InsInstrs!");
if (Operand.getReg() == PPC::ZERO8) {
Placeholder = &Operand;
break;
}
}
}
assert(Placeholder && "Placeholder does not exist!");
// Generate instructions to load the const fp from constant pool.
// We only support PPC64 and medium code model.
Register LoadNewConst =
generateLoadForNewConst(ConstPoolIdx, &Root, C->getType(), InsInstrs);
// Fill the placeholder with the new load from constant pool.
Placeholder->setReg(LoadNewConst);
}
bool PPCInstrInfo::shouldReduceRegisterPressure(
MachineBasicBlock *MBB, RegisterClassInfo *RegClassInfo) const {
if (!EnableFMARegPressureReduction)
return false;
// Currently, we only enable register pressure reducing in machine combiner
// for: 1: PPC64; 2: Code Model is Medium; 3: Power9 which also has vector
// support.
//
// So we need following instructions to access a TOC entry:
//
// %6:g8rc_and_g8rc_nox0 = ADDIStocHA8 $x2, %const.0
// %7:vssrc = DFLOADf32 target-flags(ppc-toc-lo) %const.0,
// killed %6:g8rc_and_g8rc_nox0, implicit $x2 :: (load 4 from constant-pool)
//
// FIXME: add more supported targets, like Small and Large code model, PPC32,
// AIX.
if (!(Subtarget.isPPC64() && Subtarget.hasP9Vector() &&
Subtarget.getTargetMachine().getCodeModel() == CodeModel::Medium))
return false;
const TargetRegisterInfo *TRI = &getRegisterInfo();
MachineFunction *MF = MBB->getParent();
MachineRegisterInfo *MRI = &MF->getRegInfo();
auto GetMBBPressure = [&](MachineBasicBlock *MBB) -> std::vector<unsigned> {
RegionPressure Pressure;
RegPressureTracker RPTracker(Pressure);
// Initialize the register pressure tracker.
RPTracker.init(MBB->getParent(), RegClassInfo, nullptr, MBB, MBB->end(),
/*TrackLaneMasks*/ false, /*TrackUntiedDefs=*/true);
for (MachineBasicBlock::iterator MII = MBB->instr_end(),
MIE = MBB->instr_begin();
MII != MIE; --MII) {
MachineInstr &MI = *std::prev(MII);
if (MI.isDebugValue() || MI.isDebugLabel())
continue;
RegisterOperands RegOpers;
RegOpers.collect(MI, *TRI, *MRI, false, false);
RPTracker.recedeSkipDebugValues();
assert(&*RPTracker.getPos() == &MI && "RPTracker sync error!");
RPTracker.recede(RegOpers);
}
// Close the RPTracker to finalize live ins.
RPTracker.closeRegion();
return RPTracker.getPressure().MaxSetPressure;
};
// For now we only care about float and double type fma.
unsigned VSSRCLimit = TRI->getRegPressureSetLimit(
*MBB->getParent(), PPC::RegisterPressureSets::VSSRC);
// Only reduce register pressure when pressure is high.
return GetMBBPressure(MBB)[PPC::RegisterPressureSets::VSSRC] >
(float)VSSRCLimit * FMARPFactor;
}
bool PPCInstrInfo::isLoadFromConstantPool(MachineInstr *I) const {
// I has only one memory operand which is load from constant pool.
if (!I->hasOneMemOperand())
return false;
MachineMemOperand *Op = I->memoperands()[0];
return Op->isLoad() && Op->getPseudoValue() &&
Op->getPseudoValue()->kind() == PseudoSourceValue::ConstantPool;
}
Register PPCInstrInfo::generateLoadForNewConst(
unsigned Idx, MachineInstr *MI, Type *Ty,
SmallVectorImpl<MachineInstr *> &InsInstrs) const {
// Now we only support PPC64, Medium code model and P9 with vector.
// We have immutable pattern to access const pool. See function
// shouldReduceRegisterPressure.
assert((Subtarget.isPPC64() && Subtarget.hasP9Vector() &&
Subtarget.getTargetMachine().getCodeModel() == CodeModel::Medium) &&
"Target not supported!\n");
MachineFunction *MF = MI->getMF();
MachineRegisterInfo *MRI = &MF->getRegInfo();
// Generate ADDIStocHA8
Register VReg1 = MRI->createVirtualRegister(&PPC::G8RC_and_G8RC_NOX0RegClass);
MachineInstrBuilder TOCOffset =
BuildMI(*MF, MI->getDebugLoc(), get(PPC::ADDIStocHA8), VReg1)
.addReg(PPC::X2)
.addConstantPoolIndex(Idx);
assert((Ty->isFloatTy() || Ty->isDoubleTy()) &&
"Only float and double are supported!");
unsigned LoadOpcode;
// Should be float type or double type.
if (Ty->isFloatTy())
LoadOpcode = PPC::DFLOADf32;
else
LoadOpcode = PPC::DFLOADf64;
const TargetRegisterClass *RC = MRI->getRegClass(MI->getOperand(0).getReg());
Register VReg2 = MRI->createVirtualRegister(RC);
MachineMemOperand *MMO = MF->getMachineMemOperand(
MachinePointerInfo::getConstantPool(*MF), MachineMemOperand::MOLoad,
Ty->getScalarSizeInBits() / 8, MF->getDataLayout().getPrefTypeAlign(Ty));
// Generate Load from constant pool.
MachineInstrBuilder Load =
BuildMI(*MF, MI->getDebugLoc(), get(LoadOpcode), VReg2)
.addConstantPoolIndex(Idx)
.addReg(VReg1, getKillRegState(true))
.addMemOperand(MMO);
Load->getOperand(1).setTargetFlags(PPCII::MO_TOC_LO);
// Insert the toc load instructions into InsInstrs.
InsInstrs.insert(InsInstrs.begin(), Load);
InsInstrs.insert(InsInstrs.begin(), TOCOffset);
return VReg2;
}
// This function returns the const value in constant pool if the \p I is a load
// from constant pool.
const Constant *
PPCInstrInfo::getConstantFromConstantPool(MachineInstr *I) const {
MachineFunction *MF = I->getMF();
MachineRegisterInfo *MRI = &MF->getRegInfo();
MachineConstantPool *MCP = MF->getConstantPool();
assert(I->mayLoad() && "Should be a load instruction.\n");
for (auto MO : I->uses()) {
if (!MO.isReg())
continue;
Register Reg = MO.getReg();
if (Reg == 0 || !Register::isVirtualRegister(Reg))
continue;
// Find the toc address.
MachineInstr *DefMI = MRI->getVRegDef(Reg);
for (auto MO2 : DefMI->uses())
if (MO2.isCPI())
return (MCP->getConstants())[MO2.getIndex()].Val.ConstVal;
}
return nullptr;
}
bool PPCInstrInfo::getMachineCombinerPatterns(
MachineInstr &Root, SmallVectorImpl<MachineCombinerPattern> &Patterns,
bool DoRegPressureReduce) const {
// Using the machine combiner in this way is potentially expensive, so
// restrict to when aggressive optimizations are desired.
if (Subtarget.getTargetMachine().getOptLevel() != CodeGenOpt::Aggressive)
return false;
if (getFMAPatterns(Root, Patterns, DoRegPressureReduce))
return true;
return TargetInstrInfo::getMachineCombinerPatterns(Root, Patterns,
DoRegPressureReduce);
}
void PPCInstrInfo::genAlternativeCodeSequence(
MachineInstr &Root, MachineCombinerPattern Pattern,
SmallVectorImpl<MachineInstr *> &InsInstrs,
SmallVectorImpl<MachineInstr *> &DelInstrs,
DenseMap<unsigned, unsigned> &InstrIdxForVirtReg) const {
switch (Pattern) {
case MachineCombinerPattern::REASSOC_XY_AMM_BMM:
case MachineCombinerPattern::REASSOC_XMM_AMM_BMM:
case MachineCombinerPattern::REASSOC_XY_BCA:
case MachineCombinerPattern::REASSOC_XY_BAC:
reassociateFMA(Root, Pattern, InsInstrs, DelInstrs, InstrIdxForVirtReg);
break;
default:
// Reassociate default patterns.
TargetInstrInfo::genAlternativeCodeSequence(Root, Pattern, InsInstrs,
DelInstrs, InstrIdxForVirtReg);
break;
}
}
void PPCInstrInfo::reassociateFMA(
MachineInstr &Root, MachineCombinerPattern Pattern,
SmallVectorImpl<MachineInstr *> &InsInstrs,
SmallVectorImpl<MachineInstr *> &DelInstrs,
DenseMap<unsigned, unsigned> &InstrIdxForVirtReg) const {
MachineFunction *MF = Root.getMF();
MachineRegisterInfo &MRI = MF->getRegInfo();
const TargetRegisterInfo *TRI = &getRegisterInfo();
MachineOperand &OpC = Root.getOperand(0);
Register RegC = OpC.getReg();
const TargetRegisterClass *RC = MRI.getRegClass(RegC);
MRI.constrainRegClass(RegC, RC);
unsigned FmaOp = Root.getOpcode();
int16_t Idx = getFMAOpIdxInfo(FmaOp);
assert(Idx >= 0 && "Root must be a FMA instruction");
bool IsILPReassociate =
(Pattern == MachineCombinerPattern::REASSOC_XY_AMM_BMM) ||
(Pattern == MachineCombinerPattern::REASSOC_XMM_AMM_BMM);
uint16_t AddOpIdx = FMAOpIdxInfo[Idx][InfoArrayIdxAddOpIdx];
uint16_t FirstMulOpIdx = FMAOpIdxInfo[Idx][InfoArrayIdxMULOpIdx];
MachineInstr *Prev = nullptr;
MachineInstr *Leaf = nullptr;
switch (Pattern) {
default:
llvm_unreachable("not recognized pattern!");
case MachineCombinerPattern::REASSOC_XY_AMM_BMM:
case MachineCombinerPattern::REASSOC_XMM_AMM_BMM:
Prev = MRI.getUniqueVRegDef(Root.getOperand(AddOpIdx).getReg());
Leaf = MRI.getUniqueVRegDef(Prev->getOperand(AddOpIdx).getReg());
break;
case MachineCombinerPattern::REASSOC_XY_BAC: {
Register MULReg =
TRI->lookThruCopyLike(Root.getOperand(FirstMulOpIdx).getReg(), &MRI);
Leaf = MRI.getVRegDef(MULReg);
break;
}
case MachineCombinerPattern::REASSOC_XY_BCA: {
Register MULReg = TRI->lookThruCopyLike(
Root.getOperand(FirstMulOpIdx + 1).getReg(), &MRI);
Leaf = MRI.getVRegDef(MULReg);
break;
}
}
uint16_t IntersectedFlags = 0;
if (IsILPReassociate)
IntersectedFlags = Root.getFlags() & Prev->getFlags() & Leaf->getFlags();
else
IntersectedFlags = Root.getFlags() & Leaf->getFlags();
auto GetOperandInfo = [&](const MachineOperand &Operand, Register &Reg,
bool &KillFlag) {
Reg = Operand.getReg();
MRI.constrainRegClass(Reg, RC);
KillFlag = Operand.isKill();
};
auto GetFMAInstrInfo = [&](const MachineInstr &Instr, Register &MulOp1,
Register &MulOp2, Register &AddOp,
bool &MulOp1KillFlag, bool &MulOp2KillFlag,
bool &AddOpKillFlag) {
GetOperandInfo(Instr.getOperand(FirstMulOpIdx), MulOp1, MulOp1KillFlag);
GetOperandInfo(Instr.getOperand(FirstMulOpIdx + 1), MulOp2, MulOp2KillFlag);
GetOperandInfo(Instr.getOperand(AddOpIdx), AddOp, AddOpKillFlag);
};
Register RegM11, RegM12, RegX, RegY, RegM21, RegM22, RegM31, RegM32, RegA11,
RegA21, RegB;
bool KillX = false, KillY = false, KillM11 = false, KillM12 = false,
KillM21 = false, KillM22 = false, KillM31 = false, KillM32 = false,
KillA11 = false, KillA21 = false, KillB = false;
GetFMAInstrInfo(Root, RegM31, RegM32, RegB, KillM31, KillM32, KillB);
if (IsILPReassociate)
GetFMAInstrInfo(*Prev, RegM21, RegM22, RegA21, KillM21, KillM22, KillA21);
if (Pattern == MachineCombinerPattern::REASSOC_XMM_AMM_BMM) {
GetFMAInstrInfo(*Leaf, RegM11, RegM12, RegA11, KillM11, KillM12, KillA11);
GetOperandInfo(Leaf->getOperand(AddOpIdx), RegX, KillX);
} else if (Pattern == MachineCombinerPattern::REASSOC_XY_AMM_BMM) {
GetOperandInfo(Leaf->getOperand(1), RegX, KillX);
GetOperandInfo(Leaf->getOperand(2), RegY, KillY);
} else {
// Get FSUB instruction info.
GetOperandInfo(Leaf->getOperand(1), RegX, KillX);
GetOperandInfo(Leaf->getOperand(2), RegY, KillY);
}
// Create new virtual registers for the new results instead of
// recycling legacy ones because the MachineCombiner's computation of the
// critical path requires a new register definition rather than an existing
// one.
// For register pressure reassociation, we only need create one virtual
// register for the new fma.
Register NewVRA = MRI.createVirtualRegister(RC);
InstrIdxForVirtReg.insert(std::make_pair(NewVRA, 0));
Register NewVRB = 0;
if (IsILPReassociate) {
NewVRB = MRI.createVirtualRegister(RC);
InstrIdxForVirtReg.insert(std::make_pair(NewVRB, 1));
}
Register NewVRD = 0;
if (Pattern == MachineCombinerPattern::REASSOC_XMM_AMM_BMM) {
NewVRD = MRI.createVirtualRegister(RC);
InstrIdxForVirtReg.insert(std::make_pair(NewVRD, 2));
}
auto AdjustOperandOrder = [&](MachineInstr *MI, Register RegAdd, bool KillAdd,
Register RegMul1, bool KillRegMul1,
Register RegMul2, bool KillRegMul2) {
MI->getOperand(AddOpIdx).setReg(RegAdd);
MI->getOperand(AddOpIdx).setIsKill(KillAdd);
MI->getOperand(FirstMulOpIdx).setReg(RegMul1);
MI->getOperand(FirstMulOpIdx).setIsKill(KillRegMul1);
MI->getOperand(FirstMulOpIdx + 1).setReg(RegMul2);
MI->getOperand(FirstMulOpIdx + 1).setIsKill(KillRegMul2);
};
MachineInstrBuilder NewARegPressure, NewCRegPressure;
switch (Pattern) {
default:
llvm_unreachable("not recognized pattern!");
case MachineCombinerPattern::REASSOC_XY_AMM_BMM: {
// Create new instructions for insertion.
MachineInstrBuilder MINewB =
BuildMI(*MF, Prev->getDebugLoc(), get(FmaOp), NewVRB)
.addReg(RegX, getKillRegState(KillX))
.addReg(RegM21, getKillRegState(KillM21))
.addReg(RegM22, getKillRegState(KillM22));
MachineInstrBuilder MINewA =
BuildMI(*MF, Root.getDebugLoc(), get(FmaOp), NewVRA)
.addReg(RegY, getKillRegState(KillY))
.addReg(RegM31, getKillRegState(KillM31))
.addReg(RegM32, getKillRegState(KillM32));
// If AddOpIdx is not 1, adjust the order.
if (AddOpIdx != 1) {
AdjustOperandOrder(MINewB, RegX, KillX, RegM21, KillM21, RegM22, KillM22);
AdjustOperandOrder(MINewA, RegY, KillY, RegM31, KillM31, RegM32, KillM32);
}
MachineInstrBuilder MINewC =
BuildMI(*MF, Root.getDebugLoc(),
get(FMAOpIdxInfo[Idx][InfoArrayIdxFAddInst]), RegC)
.addReg(NewVRB, getKillRegState(true))
.addReg(NewVRA, getKillRegState(true));
// Update flags for newly created instructions.
setSpecialOperandAttr(*MINewA, IntersectedFlags);
setSpecialOperandAttr(*MINewB, IntersectedFlags);
setSpecialOperandAttr(*MINewC, IntersectedFlags);
// Record new instructions for insertion.
InsInstrs.push_back(MINewA);
InsInstrs.push_back(MINewB);
InsInstrs.push_back(MINewC);
break;
}
case MachineCombinerPattern::REASSOC_XMM_AMM_BMM: {
assert(NewVRD && "new FMA register not created!");
// Create new instructions for insertion.
MachineInstrBuilder MINewA =
BuildMI(*MF, Leaf->getDebugLoc(),
get(FMAOpIdxInfo[Idx][InfoArrayIdxFMULInst]), NewVRA)
.addReg(RegM11, getKillRegState(KillM11))
.addReg(RegM12, getKillRegState(KillM12));
MachineInstrBuilder MINewB =
BuildMI(*MF, Prev->getDebugLoc(), get(FmaOp), NewVRB)
.addReg(RegX, getKillRegState(KillX))
.addReg(RegM21, getKillRegState(KillM21))
.addReg(RegM22, getKillRegState(KillM22));
MachineInstrBuilder MINewD =
BuildMI(*MF, Root.getDebugLoc(), get(FmaOp), NewVRD)
.addReg(NewVRA, getKillRegState(true))
.addReg(RegM31, getKillRegState(KillM31))
.addReg(RegM32, getKillRegState(KillM32));
// If AddOpIdx is not 1, adjust the order.
if (AddOpIdx != 1) {
AdjustOperandOrder(MINewB, RegX, KillX, RegM21, KillM21, RegM22, KillM22);
AdjustOperandOrder(MINewD, NewVRA, true, RegM31, KillM31, RegM32,
KillM32);
}
MachineInstrBuilder MINewC =
BuildMI(*MF, Root.getDebugLoc(),
get(FMAOpIdxInfo[Idx][InfoArrayIdxFAddInst]), RegC)
.addReg(NewVRB, getKillRegState(true))
.addReg(NewVRD, getKillRegState(true));
// Update flags for newly created instructions.
setSpecialOperandAttr(*MINewA, IntersectedFlags);
setSpecialOperandAttr(*MINewB, IntersectedFlags);
setSpecialOperandAttr(*MINewD, IntersectedFlags);
setSpecialOperandAttr(*MINewC, IntersectedFlags);
// Record new instructions for insertion.
InsInstrs.push_back(MINewA);
InsInstrs.push_back(MINewB);
InsInstrs.push_back(MINewD);
InsInstrs.push_back(MINewC);
break;