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
| //=- AArch64SchedExynosM3.td - Samsung Exynos M3 Sched Defs --*- tablegen -*-=//
//
// 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 defines the machine model for the Samsung Exynos M3 to support
// instruction scheduling and other instruction cost heuristics.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// The Exynos-M3 is an advanced superscalar microprocessor with a 6-wide
// in-order stage for decode and dispatch and a wider issue stage.
// The execution units and loads and stores are out-of-order.
def ExynosM3Model : SchedMachineModel {
let IssueWidth = 6; // Up to 6 uops per cycle.
let MicroOpBufferSize = 228; // ROB size.
let LoopMicroOpBufferSize = 40; // Based on the instruction queue size.
let LoadLatency = 4; // Optimistic load cases.
let MispredictPenalty = 16; // Minimum branch misprediction penalty.
let CompleteModel = 1; // Use the default model otherwise.
list<Predicate> UnsupportedFeatures = SVEUnsupported.F;
}
//===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available on the Exynos-M3,
// which has 12 pipelines, each with its own queue with out-of-order dispatch.
let SchedModel = ExynosM3Model in {
def M3UnitA : ProcResource<2>; // Simple integer
def M3UnitC : ProcResource<2>; // Simple and complex integer
def M3UnitD : ProcResource<1>; // Integer division (inside C0, serialized)
def M3UnitB : ProcResource<2>; // Branch
def M3UnitL : ProcResource<2>; // Load
def M3UnitS : ProcResource<1>; // Store
def M3PipeF0 : ProcResource<1>; // FP #0
let Super = M3PipeF0 in {
def M3UnitFMAC0 : ProcResource<1>; // FP multiplication
def M3UnitFADD0 : ProcResource<1>; // Simple FP
def M3UnitFCVT0 : ProcResource<1>; // FP conversion
def M3UnitFSQR : ProcResource<2>; // FP square root (serialized)
def M3UnitNALU0 : ProcResource<1>; // Simple vector
def M3UnitNMSC : ProcResource<1>; // FP and vector miscellanea
def M3UnitNSHT0 : ProcResource<1>; // Vector shifting
def M3UnitNSHF0 : ProcResource<1>; // Vector shuffling
}
def M3PipeF1 : ProcResource<1>; // FP #1
let Super = M3PipeF1 in {
def M3UnitFMAC1 : ProcResource<1>; // FP multiplication
def M3UnitFADD1 : ProcResource<1>; // Simple FP
def M3UnitFDIV0 : ProcResource<2>; // FP division (serialized)
def M3UnitFCVT1 : ProcResource<1>; // FP conversion
def M3UnitFST0 : ProcResource<1>; // FP store
def M3UnitNALU1 : ProcResource<1>; // Simple vector
def M3UnitNCRY0 : ProcResource<1>; // Cryptographic
def M3UnitNMUL : ProcResource<1>; // Vector multiplication
def M3UnitNSHT1 : ProcResource<1>; // Vector shifting
def M3UnitNSHF1 : ProcResource<1>; // Vector shuffling
}
def M3PipeF2 : ProcResource<1>; // FP #2
let Super = M3PipeF2 in {
def M3UnitFMAC2 : ProcResource<1>; // FP multiplication
def M3UnitFADD2 : ProcResource<1>; // Simple FP
def M3UnitFDIV1 : ProcResource<2>; // FP division (serialized)
def M3UnitFST1 : ProcResource<1>; // FP store
def M3UnitNALU2 : ProcResource<1>; // Simple vector
def M3UnitNCRY1 : ProcResource<1>; // Cryptographic
def M3UnitNSHT2 : ProcResource<1>; // Vector shifting
def M3UnitNSHF2 : ProcResource<1>; // Vector shuffling
}
def M3UnitALU : ProcResGroup<[M3UnitA,
M3UnitC]>;
def M3UnitFMAC : ProcResGroup<[M3UnitFMAC0,
M3UnitFMAC1,
M3UnitFMAC2]>;
def M3UnitFADD : ProcResGroup<[M3UnitFADD0,
M3UnitFADD1,
M3UnitFADD2]>;
def M3UnitFDIV : ProcResGroup<[M3UnitFDIV0,
M3UnitFDIV1]>;
def M3UnitFCVT : ProcResGroup<[M3UnitFCVT0,
M3UnitFCVT1]>;
def M3UnitFST : ProcResGroup<[M3UnitFST0,
M3UnitFST1]>;
def M3UnitNALU : ProcResGroup<[M3UnitNALU0,
M3UnitNALU1,
M3UnitNALU2]>;
def M3UnitNCRY : ProcResGroup<[M3UnitNCRY0,
M3UnitNCRY1]>;
def M3UnitNSHT : ProcResGroup<[M3UnitNSHT0,
M3UnitNSHT1,
M3UnitNSHT2]>;
def M3UnitNSHF : ProcResGroup<[M3UnitNSHF0,
M3UnitNSHF1,
M3UnitNSHF2]>;
//===----------------------------------------------------------------------===//
// Coarse scheduling model.
def M3WriteZ0 : SchedWriteRes<[]> { let Latency = 0;
let NumMicroOps = 1; }
def M3WriteZ1 : SchedWriteRes<[]> { let Latency = 1;
let NumMicroOps = 0; }
def M3WriteA1 : SchedWriteRes<[M3UnitALU]> { let Latency = 1; }
def M3WriteAA : SchedWriteRes<[M3UnitALU]> { let Latency = 2;
let ResourceCycles = [2]; }
def M3WriteAB : SchedWriteRes<[M3UnitALU,
M3UnitC]> { let Latency = 1;
let NumMicroOps = 2; }
def M3WriteAC : SchedWriteRes<[M3UnitALU,
M3UnitALU,
M3UnitC]> { let Latency = 2;
let NumMicroOps = 3; }
def M3WriteAD : SchedWriteRes<[M3UnitALU,
M3UnitC]> { let Latency = 2;
let NumMicroOps = 2; }
def M3WriteC1 : SchedWriteRes<[M3UnitC]> { let Latency = 1; }
def M3WriteC2 : SchedWriteRes<[M3UnitC]> { let Latency = 2; }
def M3WriteAU : SchedWriteVariant<[SchedVar<IsCopyIdiomPred, [M3WriteZ0]>,
SchedVar<ExynosArithPred, [M3WriteA1]>,
SchedVar<ExynosLogicPred, [M3WriteA1]>,
SchedVar<NoSchedPred, [M3WriteAA]>]>;
def M3WriteAV : SchedWriteVariant<[SchedVar<IsCopyIdiomPred, [M3WriteZ0]>,
SchedVar<NoSchedPred, [M3WriteAA]>]>;
def M3WriteAW : SchedWriteVariant<[SchedVar<IsZeroIdiomPred, [M3WriteZ0]>,
SchedVar<NoSchedPred, [M3WriteAA]>]>;
def M3WriteAX : SchedWriteVariant<[SchedVar<ExynosArithPred, [M3WriteA1]>,
SchedVar<ExynosLogicPred, [M3WriteA1]>,
SchedVar<NoSchedPred, [M3WriteAA]>]>;
def M3WriteAY : SchedWriteVariant<[SchedVar<ExynosRotateRightImmPred, [M3WriteA1]>,
SchedVar<NoSchedPred, [M3WriteAA]>]>;
def M3WriteB1 : SchedWriteRes<[M3UnitB]> { let Latency = 1; }
def M3WriteBX : SchedWriteVariant<[SchedVar<ExynosBranchLinkLRPred, [M3WriteAC]>,
SchedVar<NoSchedPred, [M3WriteAB]>]>;
def M3WriteL4 : SchedWriteRes<[M3UnitL]> { let Latency = 4; }
def M3WriteL5 : SchedWriteRes<[M3UnitL]> { let Latency = 5; }
def M3WriteLA : SchedWriteRes<[M3UnitL,
M3UnitL]> { let Latency = 5;
let NumMicroOps = 1; }
def M3WriteLB : SchedWriteRes<[M3UnitA,
M3UnitL]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteLC : SchedWriteRes<[M3UnitA,
M3UnitL,
M3UnitL]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteLD : SchedWriteRes<[M3UnitA,
M3UnitL]> { let Latency = 4;
let NumMicroOps = 2; }
def M3WriteLE : SchedWriteRes<[M3UnitA,
M3UnitL]> { let Latency = 6;
let NumMicroOps = 2; }
def M3WriteLH : SchedWriteRes<[]> { let Latency = 5;
let NumMicroOps = 0; }
def M3WriteLX : SchedWriteVariant<[SchedVar<ExynosScaledIdxPred, [M3WriteL5]>,
SchedVar<NoSchedPred, [M3WriteL4]>]>;
def M3WriteS1 : SchedWriteRes<[M3UnitS]> { let Latency = 1; }
def M3WriteSA : SchedWriteRes<[M3UnitA,
M3UnitS,
M3UnitFST]> { let Latency = 3;
let NumMicroOps = 2; }
def M3WriteSB : SchedWriteRes<[M3UnitA,
M3UnitS]> { let Latency = 2;
let NumMicroOps = 2; }
def M3ReadAdrBase : SchedReadVariant<[SchedVar<ExynosScaledIdxPred, [ReadDefault]>,
SchedVar<NoSchedPred, [ReadDefault]>]>;
// Branch instructions.
def : SchedAlias<WriteBr, M3WriteZ0>;
def : SchedAlias<WriteBrReg, M3WriteC1>;
// Arithmetic and logical integer instructions.
def : SchedAlias<WriteI, M3WriteA1>;
def : SchedAlias<WriteISReg, M3WriteA1>;
def : SchedAlias<WriteIEReg, M3WriteA1>;
def : SchedAlias<WriteIS, M3WriteA1>;
// Move instructions.
def : SchedAlias<WriteImm, M3WriteA1>;
// Divide and multiply instructions.
def : WriteRes<WriteID32, [M3UnitC,
M3UnitD]> { let Latency = 12;
let ResourceCycles = [1, 12]; }
def : WriteRes<WriteID64, [M3UnitC,
M3UnitD]> { let Latency = 21;
let ResourceCycles = [1, 21]; }
def : WriteRes<WriteIM32, [M3UnitC]> { let Latency = 3; }
def : WriteRes<WriteIM64, [M3UnitC]> { let Latency = 4;
let ResourceCycles = [2]; }
// Miscellaneous instructions.
def : SchedAlias<WriteExtr, M3WriteAY>;
// Addressing modes.
def : SchedAlias<WriteAdr, M3WriteZ1>;
def : SchedAlias<ReadAdrBase, M3ReadAdrBase>;
// Load instructions.
def : SchedAlias<WriteLD, M3WriteL4>;
def : WriteRes<WriteLDHi, []> { let Latency = 4;
let NumMicroOps = 0; }
def : SchedAlias<WriteLDIdx, M3WriteLB>;
// Store instructions.
def : SchedAlias<WriteST, M3WriteS1>;
def : SchedAlias<WriteSTP, M3WriteS1>;
def : SchedAlias<WriteSTX, M3WriteS1>;
def : SchedAlias<WriteSTIdx, M3WriteSB>;
// FP data instructions.
def : WriteRes<WriteF, [M3UnitFADD]> { let Latency = 2; }
def : WriteRes<WriteFCmp, [M3UnitNMSC]> { let Latency = 2; }
def : WriteRes<WriteFDiv, [M3UnitFDIV]> { let Latency = 12;
let ResourceCycles = [12]; }
def : WriteRes<WriteFMul, [M3UnitFMAC]> { let Latency = 4; }
// FP miscellaneous instructions.
def : WriteRes<WriteFCvt, [M3UnitFCVT]> { let Latency = 3; }
def : WriteRes<WriteFImm, [M3UnitNALU]> { let Latency = 1; }
def : WriteRes<WriteFCopy, [M3UnitNALU]> { let Latency = 1; }
// FP load instructions.
def : SchedAlias<WriteVLD, M3WriteL5>;
// FP store instructions.
def : WriteRes<WriteVST, [M3UnitS,
M3UnitFST]> { let Latency = 1;
let NumMicroOps = 1; }
// ASIMD FP instructions.
def : WriteRes<WriteV, [M3UnitNALU]> { let Latency = 3; }
// Other miscellaneous instructions.
def : WriteRes<WriteAtomic, []> { let Unsupported = 1; }
def : WriteRes<WriteBarrier, []> { let Latency = 1; }
def : WriteRes<WriteHint, []> { let Latency = 1; }
def : WriteRes<WriteSys, []> { let Latency = 1; }
//===----------------------------------------------------------------------===//
// Generic fast forwarding.
// TODO: Add FP register forwarding rules.
def : ReadAdvance<ReadI, 0>;
def : ReadAdvance<ReadISReg, 0>;
def : ReadAdvance<ReadIEReg, 0>;
def : ReadAdvance<ReadIM, 0>;
// TODO: The forwarding for 32 bits actually saves 2 cycles.
def : ReadAdvance<ReadIMA, 3, [WriteIM32, WriteIM64]>;
def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
//===----------------------------------------------------------------------===//
// Finer scheduling model.
def M3WriteNEONA : SchedWriteRes<[M3UnitNSHF,
M3UnitFADD]> { let Latency = 3;
let NumMicroOps = 2; }
def M3WriteNEONB : SchedWriteRes<[M3UnitNALU,
M3UnitFST]> { let Latency = 10;
let NumMicroOps = 2; }
def M3WriteNEOND : SchedWriteRes<[M3UnitNSHF,
M3UnitFST]> { let Latency = 6;
let NumMicroOps = 2; }
def M3WriteNEONH : SchedWriteRes<[M3UnitNALU,
M3UnitS]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteNEONI : SchedWriteRes<[M3UnitNSHF,
M3UnitS]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteNEONV : SchedWriteRes<[M3UnitFDIV0,
M3UnitFDIV1]> { let Latency = 7;
let NumMicroOps = 2;
let ResourceCycles = [8, 8]; }
def M3WriteNEONW : SchedWriteRes<[M3UnitFDIV0,
M3UnitFDIV1]> { let Latency = 12;
let NumMicroOps = 2;
let ResourceCycles = [13, 13]; }
def M3WriteNEONX : SchedWriteRes<[M3UnitFSQR,
M3UnitFSQR]> { let Latency = 18;
let NumMicroOps = 2;
let ResourceCycles = [19, 19]; }
def M3WriteNEONY : SchedWriteRes<[M3UnitFSQR,
M3UnitFSQR]> { let Latency = 25;
let NumMicroOps = 2;
let ResourceCycles = [26, 26]; }
def M3WriteNEONZ : SchedWriteRes<[M3UnitNMSC,
M3UnitNMSC]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteFADD2 : SchedWriteRes<[M3UnitFADD]> { let Latency = 2; }
def M3WriteFCVT2 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 2; }
def M3WriteFCVT3 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 3; }
def M3WriteFCVT3A : SchedWriteRes<[M3UnitFCVT0]> { let Latency = 3; }
def M3WriteFCVT4A : SchedWriteRes<[M3UnitFCVT0]> { let Latency = 4; }
def M3WriteFCVT4 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 4; }
def M3WriteFDIV10 : SchedWriteRes<[M3UnitFDIV]> { let Latency = 7;
let ResourceCycles = [8]; }
def M3WriteFDIV12 : SchedWriteRes<[M3UnitFDIV]> { let Latency = 12;
let ResourceCycles = [13]; }
def M3WriteFMAC3 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 3; }
def M3WriteFMAC4 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 4; }
def M3WriteFMAC5 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 5; }
def M3WriteFSQR17 : SchedWriteRes<[M3UnitFSQR]> { let Latency = 18;
let ResourceCycles = [19]; }
def M3WriteFSQR25 : SchedWriteRes<[M3UnitFSQR]> { let Latency = 25;
let ResourceCycles = [26]; }
def M3WriteNALU1 : SchedWriteRes<[M3UnitNALU]> { let Latency = 1; }
def M3WriteNCRY1A : SchedWriteRes<[M3UnitNCRY0]> { let Latency = 1; }
def M3WriteNCRY3A : SchedWriteRes<[M3UnitNCRY0]> { let Latency = 3; }
def M3WriteNCRY5A : SchedWriteRes<[M3UnitNCRY]> { let Latency = 5; }
def M3WriteNMSC1 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 1; }
def M3WriteNMSC2 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 2; }
def M3WriteNMSC3 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 3; }
def M3WriteNMUL3 : SchedWriteRes<[M3UnitNMUL]> { let Latency = 3; }
def M3WriteNSHF1 : SchedWriteRes<[M3UnitNSHF]> { let Latency = 1; }
def M3WriteNSHF3 : SchedWriteRes<[M3UnitNSHF]> { let Latency = 3; }
def M3WriteNSHT1 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 1; }
def M3WriteNSHT2 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 2; }
def M3WriteNSHT3 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 3; }
def M3WriteVLDA : SchedWriteRes<[M3UnitL,
M3UnitL]> { let Latency = 5;
let NumMicroOps = 2; }
def M3WriteVLDB : SchedWriteRes<[M3UnitL,
M3UnitL,
M3UnitL]> { let Latency = 6;
let NumMicroOps = 3; }
def M3WriteVLDC : SchedWriteRes<[M3UnitL,
M3UnitL,
M3UnitL,
M3UnitL]> { let Latency = 6;
let NumMicroOps = 4; }
def M3WriteVLDD : SchedWriteRes<[M3UnitL,
M3UnitNALU]> { let Latency = 7;
let NumMicroOps = 2;
let ResourceCycles = [2, 1]; }
def M3WriteVLDE : SchedWriteRes<[M3UnitL,
M3UnitNALU]> { let Latency = 6;
let NumMicroOps = 2;
let ResourceCycles = [2, 1]; }
def M3WriteVLDF : SchedWriteRes<[M3UnitL,
M3UnitL]> { let Latency = 10;
let NumMicroOps = 2;
let ResourceCycles = [5, 5]; }
def M3WriteVLDG : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU]> { let Latency = 7;
let NumMicroOps = 3;
let ResourceCycles = [2, 1, 1]; }
def M3WriteVLDH : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU]> { let Latency = 6;
let NumMicroOps = 3;
let ResourceCycles = [2, 1, 1]; }
def M3WriteVLDI : SchedWriteRes<[M3UnitL,
M3UnitL,
M3UnitL]> { let Latency = 12;
let NumMicroOps = 3;
let ResourceCycles = [6, 6, 6]; }
def M3WriteVLDJ : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU,
M3UnitNALU]> { let Latency = 7;
let NumMicroOps = 4;
let ResourceCycles = [2, 1, 1, 1]; }
def M3WriteVLDK : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU,
M3UnitNALU,
M3UnitNALU]> { let Latency = 9;
let NumMicroOps = 5;
let ResourceCycles = [4, 1, 1, 1, 1]; }
def M3WriteVLDL : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU,
M3UnitL,
M3UnitNALU]> { let Latency = 6;
let NumMicroOps = 5;
let ResourceCycles = [6, 1, 1, 6, 1]; }
def M3WriteVLDM : SchedWriteRes<[M3UnitL,
M3UnitNALU,
M3UnitNALU,
M3UnitL,
M3UnitNALU,
M3UnitNALU]> { let Latency = 7;
let NumMicroOps = 6;
let ResourceCycles = [6, 1, 1, 6, 1, 1]; }
def M3WriteVLDN : SchedWriteRes<[M3UnitL,
M3UnitL,
M3UnitL,
M3UnitL]> { let Latency = 14;
let NumMicroOps = 4;
let ResourceCycles = [6, 6, 6, 6]; }
def M3WriteVSTA : WriteSequence<[WriteVST], 2>;
def M3WriteVSTB : WriteSequence<[WriteVST], 3>;
def M3WriteVSTC : WriteSequence<[WriteVST], 4>;
def M3WriteVSTD : SchedWriteRes<[M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 7;
let NumMicroOps = 4;
let ResourceCycles = [1, 3, 1, 3]; }
def M3WriteVSTE : SchedWriteRes<[M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 8;
let NumMicroOps = 6;
let ResourceCycles = [1, 3, 1, 3, 1, 3]; }
def M3WriteVSTF : SchedWriteRes<[M3UnitNALU,
M3UnitFST,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 15;
let NumMicroOps = 7;
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3]; }
def M3WriteVSTG : SchedWriteRes<[M3UnitNALU,
M3UnitFST,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 16;
let NumMicroOps = 9;
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3, 1, 3]; }
def M3WriteVSTH : SchedWriteRes<[M3UnitNALU,
M3UnitFST,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 14;
let NumMicroOps = 5;
let ResourceCycles = [1, 3, 3, 1, 3]; }
def M3WriteVSTI : SchedWriteRes<[M3UnitNALU,
M3UnitFST,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST,
M3UnitS,
M3UnitFST]> { let Latency = 17;
let NumMicroOps = 9;
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3, 1, 3]; }
// Special cases.
def M3WriteAES : SchedWriteRes<[M3UnitNCRY]> { let Latency = 1; }
def M3WriteCOPY : SchedWriteVariant<[SchedVar<ExynosFPPred, [M3WriteNALU1]>,
SchedVar<NoSchedPred, [M3WriteZ0]>]>;
def M3WriteMOVI : SchedWriteVariant<[SchedVar<IsZeroFPIdiomPred, [M3WriteZ0]>,
SchedVar<NoSchedPred, [M3WriteNALU1]>]>;
// Fast forwarding.
def M3ReadAES : SchedReadAdvance<1, [M3WriteAES]>;
def M3ReadFMAC : SchedReadAdvance<1, [M3WriteFMAC4,
M3WriteFMAC5]>;
def M3ReadNMUL : SchedReadAdvance<1, [M3WriteNMUL3]>;
// Branch instructions
def : InstRW<[M3WriteB1], (instrs Bcc)>;
def : InstRW<[M3WriteA1], (instrs BL)>;
def : InstRW<[M3WriteBX], (instrs BLR)>;
def : InstRW<[M3WriteC1], (instregex "^CBN?Z[WX]")>;
def : InstRW<[M3WriteAD], (instregex "^TBN?Z[WX]")>;
// Arithmetic and logical integer instructions.
def : InstRW<[M3WriteAX], (instregex "^(ADD|AND|BIC|EON|EOR|ORN|SUB)[WX]rs$")>;
def : InstRW<[M3WriteAU], (instrs ORRWrs, ORRXrs)>;
def : InstRW<[M3WriteAX], (instregex "^(ADD|SUB)S?[WX]rx(64)?$")>;
def : InstRW<[M3WriteAX], (instregex "^(ADD|AND|BIC|SUB)S[WX]rs$")>;
def : InstRW<[M3WriteAV], (instrs ADDWri, ADDXri)>;
def : InstRW<[M3WriteAW], (instrs ORRWri, ORRXri)>;
// Move instructions.
def : InstRW<[M3WriteCOPY], (instrs COPY)>;
def : InstRW<[M3WriteZ0], (instrs ADR, ADRP)>;
def : InstRW<[M3WriteZ0], (instregex "^MOV[NZ][WX]i")>;
// Divide and multiply instructions.
// Miscellaneous instructions.
// Load instructions.
def : InstRW<[M3WriteLD,
WriteLDHi,
WriteAdr], (instregex "^LDP(SW|W|X)(post|pre)")>;
def : InstRW<[M3WriteLB,
ReadAdrBase], (instregex "^LDR(BB|SBW|SBX|HH|SHW|SHX|SW|W|X)roW")>;
def : InstRW<[M3WriteLX,
ReadAdrBase], (instregex "^LDR(BB|SBW|SBX|HH|SHW|SHX|SW|W|X)roX")>;
def : InstRW<[M3WriteLB,
ReadAdrBase], (instrs PRFMroW)>;
def : InstRW<[M3WriteLX,
ReadAdrBase], (instrs PRFMroX)>;
// Store instructions.
def : InstRW<[M3WriteSB,
ReadAdrBase], (instregex "^STR(BB|HH|W|X)roW")>;
def : InstRW<[WriteST,
ReadAdrBase], (instregex "^STR(BB|HH|W|X)roX")>;
// FP data instructions.
def : InstRW<[M3WriteNSHF1], (instregex "^FABS[DS]r")>;
def : InstRW<[M3WriteFADD2], (instregex "^F(ADD|SUB)[DS]rr")>;
def : InstRW<[M3WriteFDIV10], (instrs FDIVSrr)>;
def : InstRW<[M3WriteFDIV12], (instrs FDIVDrr)>;
def : InstRW<[M3WriteNMSC1], (instregex "^F(MAX|MIN).+rr")>;
def : InstRW<[M3WriteFMAC3], (instregex "^FN?MUL[DS]rr")>;
def : InstRW<[M3WriteFMAC4,
M3ReadFMAC], (instregex "^FN?M(ADD|SUB)[DS]rrr")>;
def : InstRW<[M3WriteNALU1], (instregex "^FNEG[DS]r")>;
def : InstRW<[M3WriteFCVT3A], (instregex "^FRINT.+r")>;
def : InstRW<[M3WriteNEONH], (instregex "^FCSEL[DS]rrr")>;
def : InstRW<[M3WriteFSQR17], (instrs FSQRTSr)>;
def : InstRW<[M3WriteFSQR25], (instrs FSQRTDr)>;
// FP miscellaneous instructions.
def : InstRW<[M3WriteFCVT3], (instregex "^FCVT[DHS][DHS]r")>;
def : InstRW<[M3WriteFCVT4A], (instregex "^[SU]CVTF[SU][XW][DHS]ri")>;
def : InstRW<[M3WriteFCVT3A], (instregex "^FCVT[AMNPZ][SU]U[XW][DHS]r")>;
def : InstRW<[M3WriteFCVT3A], (instregex "^FCVTZ[SU][dhs]")>;
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[DS][ir]")>;
def : InstRW<[M3WriteFCVT4], (instregex "^[FU](RECP|RSQRT)Ev1")>;
def : InstRW<[M3WriteNMSC1], (instregex "^FRECPXv1")>;
def : InstRW<[M3WriteFMAC4,
M3ReadFMAC], (instregex "^F(RECP|RSQRT)S(16|32|64)")>;
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[WX][DS]r")>;
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[DS][WX]r")>;
def : InstRW<[M3WriteNEONI], (instregex "^FMOV(DX|XD)Highr")>;
// FP load instructions.
def : InstRW<[WriteVLD], (instregex "^LDR[DSQ]l")>;
def : InstRW<[WriteVLD], (instregex "^LDUR[BDHSQ]i")>;
def : InstRW<[WriteVLD,
WriteAdr], (instregex "^LDR[BDHSQ](post|pre)")>;
def : InstRW<[WriteVLD], (instregex "^LDR[BDHSQ]ui")>;
def : InstRW<[M3WriteLE,
ReadAdrBase], (instregex "^LDR[BDHS]roW")>;
def : InstRW<[WriteVLD,
ReadAdrBase], (instregex "^LDR[BDHS]roX")>;
def : InstRW<[M3WriteLE,
ReadAdrBase], (instregex "^LDRQro[WX]")>;
def : InstRW<[WriteVLD,
M3WriteLH], (instregex "^LDN?P[DS]i")>;
def : InstRW<[M3WriteLA,
M3WriteLH], (instregex "^LDN?PQi")>;
def : InstRW<[M3WriteLB,
M3WriteLH,
WriteAdr], (instregex "^LDP[DS](post|pre)")>;
def : InstRW<[M3WriteLC,
M3WriteLH,
WriteAdr], (instregex "^LDPQ(post|pre)")>;
// FP store instructions.
def : InstRW<[WriteVST], (instregex "^STUR[BDHSQ]i")>;
def : InstRW<[WriteVST,
WriteAdr], (instregex "^STR[BDHSQ](post|pre)")>;
def : InstRW<[WriteVST], (instregex "^STR[BDHSQ]ui")>;
def : InstRW<[M3WriteSA,
ReadAdrBase], (instregex "^STR[BDHS]roW")>;
def : InstRW<[WriteVST,
ReadAdrBase], (instregex "^STR[BDHS]roX")>;
def : InstRW<[M3WriteSA,
ReadAdrBase], (instregex "^STRQro[WX]")>;
def : InstRW<[WriteVST], (instregex "^STN?P[DSQ]i")>;
def : InstRW<[WriteVST,
WriteAdr], (instregex "^STP[DS](post|pre)")>;
def : InstRW<[M3WriteSA,
WriteAdr], (instregex "^STPQ(post|pre)")>;
// ASIMD instructions.
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]ABAL?v")>;
def : InstRW<[M3WriteNMSC1], (instregex "^[SU]ABDL?v")>;
def : InstRW<[M3WriteNMSC1], (instregex "^((SQ)?ABS|SQNEG)v")>;
def : InstRW<[M3WriteNALU1], (instregex "^(ADD|NEG|SUB)v")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]?ADDL?Pv")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]H(ADD|SUB)v")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU](ADD|SUB)[LW]V?v")>;
def : InstRW<[M3WriteNMSC3], (instregex "^R?(ADD|SUB)HN2?v")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]Q(ADD|SUB)v")>;
def : InstRW<[M3WriteNMSC3], (instregex "^(SU|US)QADDv")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]RHADDv")>;
def : InstRW<[M3WriteNMSC1], (instregex "^CM(EQ|GE|GT|HI|HS|LE|LT)v")>;
def : InstRW<[M3WriteNALU1], (instregex "^CMTSTv")>;
def : InstRW<[M3WriteNALU1], (instregex "^(AND|BIC|EOR|MVNI|NOT|ORN|ORR)v")>;
def : InstRW<[M3WriteNMSC1], (instregex "^[SU](MIN|MAX)v")>;
def : InstRW<[M3WriteNMSC2], (instregex "^[SU](MIN|MAX)Pv")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU](MIN|MAX)Vv")>;
def : InstRW<[M3WriteNMUL3], (instregex "^(MUL|SQR?DMULH)v")>;
def : InstRW<[M3WriteNMUL3,
M3ReadNMUL], (instregex "^ML[AS]v")>;
def : InstRW<[M3WriteNMUL3], (instregex "^[SU]ML[AS]Lv")>;
def : InstRW<[M3WriteNMUL3], (instregex "^SQDML[AS]L")>;
def : InstRW<[M3WriteNMUL3], (instregex "^(S|U|SQD)MULLv")>;
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]ADALPv")>;
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]R?SRAv")>;
def : InstRW<[M3WriteNSHT1], (instregex "^SHL[dv]")>;
def : InstRW<[M3WriteNSHT1], (instregex "^[SU]SH[LR][dv]")>;
def : InstRW<[M3WriteNSHT1], (instregex "^S[RS]I[dv]")>;
def : InstRW<[M3WriteNSHT2], (instregex "^[SU]?SHLLv")>;
def : InstRW<[M3WriteNSHT3], (instregex "^(([SU]Q)?R)?SHRU?N[bhsv]")>;
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]RSH[LR][dv]")>;
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]QR?SHLU?[bdhsv]")>;
// ASIMD FP instructions.
def : InstRW<[M3WriteNSHF1], (instregex "^FABSv")>;
def : InstRW<[M3WriteFADD2], (instregex "^F(ABD|ADD|SUB)v")>;
def : InstRW<[M3WriteNEONA], (instregex "^FADDP")>;
def : InstRW<[M3WriteNMSC1], (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)v[^1]")>;
def : InstRW<[M3WriteFCVT3], (instregex "^FCVT(L|N|XN)v")>;
def : InstRW<[M3WriteFCVT2], (instregex "^FCVT[AMNPZ][SU]v")>;
def : InstRW<[M3WriteFCVT2], (instregex "^[SU]CVTFv")>;
def : InstRW<[M3WriteFDIV10], (instrs FDIVv2f32)>;
def : InstRW<[M3WriteNEONV], (instrs FDIVv4f32)>;
def : InstRW<[M3WriteNEONW], (instrs FDIVv2f64)>;
def : InstRW<[M3WriteNMSC1], (instregex "^F(MAX|MIN)(NM)?v")>;
def : InstRW<[M3WriteNMSC2], (instregex "^F(MAX|MIN)(NM)?Pv")>;
def : InstRW<[M3WriteNEONZ], (instregex "^F(MAX|MIN)(NM)?Vv")>;
def : InstRW<[M3WriteFMAC3], (instregex "^FMULX?v.[fi]")>;
def : InstRW<[M3WriteFMAC4,
M3ReadFMAC], (instregex "^FML[AS]v.f")>;
def : InstRW<[M3WriteFMAC5,
M3ReadFMAC], (instregex "^FML[AS]v.i")>;
def : InstRW<[M3WriteNALU1], (instregex "^FNEGv")>;
def : InstRW<[M3WriteFCVT3A], (instregex "^FRINT[AIMNPXZ]v")>;
def : InstRW<[M3WriteFSQR17], (instrs FSQRTv2f32)>;
def : InstRW<[M3WriteNEONX], (instrs FSQRTv4f32)>;
def : InstRW<[M3WriteNEONY], (instrs FSQRTv2f64)>;
// ASIMD miscellaneous instructions.
def : InstRW<[M3WriteNALU1], (instregex "^RBITv")>;
def : InstRW<[M3WriteNALU1], (instregex "^(BIF|BIT|BSL)v")>;
def : InstRW<[M3WriteNEONB], (instregex "^DUPv.+gpr")>;
def : InstRW<[M3WriteNSHF1], (instregex "^DUPv.+lane")>;
def : InstRW<[M3WriteNSHF1], (instregex "^EXTv")>;
def : InstRW<[M3WriteNSHF1], (instregex "^[SU]?Q?XTU?Nv")>;
def : InstRW<[M3WriteNSHF1], (instregex "^CPY")>;
def : InstRW<[M3WriteNSHF1], (instregex "^INSv.+lane")>;
def : InstRW<[M3WriteMOVI], (instregex "^MOVI")>;
def : InstRW<[M3WriteNALU1], (instregex "^FMOVv")>;
def : InstRW<[M3WriteFCVT4], (instregex "^[FU](RECP|RSQRT)Ev[248]")>;
def : InstRW<[M3WriteFMAC4,
M3ReadFMAC], (instregex "^F(RECP|RSQRT)Sv")>;
def : InstRW<[M3WriteNSHF1], (instregex "^REV(16|32|64)v")>;
def : InstRW<[M3WriteNSHF1], (instregex "^TB[LX]v")>;
def : InstRW<[M3WriteNEOND], (instregex "^[SU]MOVv")>;
def : InstRW<[M3WriteNSHF3], (instregex "^INSv.+gpr")>;
def : InstRW<[M3WriteNSHF1], (instregex "^(TRN|UZP|ZIP)[12]v")>;
// ASIMD load instructions.
def : InstRW<[M3WriteL5], (instregex "LD1Onev(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteL5,
M3WriteA1], (instregex "LD1Onev(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteL5], (instregex "LD1Onev(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteL5,
M3WriteA1], (instregex "LD1Onev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDA], (instregex "LD1Twov(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDA,
M3WriteA1], (instregex "LD1Twov(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDA], (instregex "LD1Twov(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDA,
M3WriteA1], (instregex "LD1Twov(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDB], (instregex "LD1Threev(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDB,
M3WriteA1], (instregex "LD1Threev(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDB], (instregex "LD1Threev(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDB,
M3WriteA1], (instregex "LD1Threev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDC], (instregex "LD1Fourv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDC,
M3WriteA1], (instregex "LD1Fourv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDC], (instregex "LD1Fourv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDC,
M3WriteA1], (instregex "LD1Fourv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDD], (instregex "LD1i(8|16|32)$")>;
def : InstRW<[M3WriteVLDD,
M3WriteA1], (instregex "LD1i(8|16|32)_POST")>;
def : InstRW<[M3WriteVLDE], (instregex "LD1i(64)$")>;
def : InstRW<[M3WriteVLDE,
M3WriteA1], (instregex "LD1i(64)_POST")>;
def : InstRW<[M3WriteL5], (instregex "LD1Rv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteL5,
M3WriteA1], (instregex "LD1Rv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteL5], (instregex "LD1Rv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteL5,
M3WriteA1], (instregex "LD1Rv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDF], (instregex "LD2Twov(8b|4h|2s)$")>;
def : InstRW<[M3WriteVLDF,
M3WriteA1], (instregex "LD2Twov(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVLDF], (instregex "LD2Twov(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDF,
M3WriteA1], (instregex "LD2Twov(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDG], (instregex "LD2i(8|16|32)$")>;
def : InstRW<[M3WriteVLDG,
M3WriteA1], (instregex "LD2i(8|16|32)_POST")>;
def : InstRW<[M3WriteVLDH], (instregex "LD2i(64)$")>;
def : InstRW<[M3WriteVLDH,
M3WriteA1], (instregex "LD2i(64)_POST")>;
def : InstRW<[M3WriteVLDA], (instregex "LD2Rv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDA,
M3WriteA1], (instregex "LD2Rv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDA], (instregex "LD2Rv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDA,
M3WriteA1], (instregex "LD2Rv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDI], (instregex "LD3Threev(8b|4h|2s)$")>;
def : InstRW<[M3WriteVLDI,
M3WriteA1], (instregex "LD3Threev(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVLDI], (instregex "LD3Threev(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDI,
M3WriteA1], (instregex "LD3Threev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDJ], (instregex "LD3i(8|16|32)$")>;
def : InstRW<[M3WriteVLDJ,
M3WriteA1], (instregex "LD3i(8|16|32)_POST")>;
def : InstRW<[M3WriteVLDL], (instregex "LD3i(64)$")>;
def : InstRW<[M3WriteVLDL,
M3WriteA1], (instregex "LD3i(64)_POST")>;
def : InstRW<[M3WriteVLDB], (instregex "LD3Rv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDB,
M3WriteA1], (instregex "LD3Rv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDB], (instregex "LD3Rv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDB,
M3WriteA1], (instregex "LD3Rv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDN], (instregex "LD4Fourv(8b|4h|2s)$")>;
def : InstRW<[M3WriteVLDN,
M3WriteA1], (instregex "LD4Fourv(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVLDN], (instregex "LD4Fourv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDN,
M3WriteA1], (instregex "LD4Fourv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVLDK], (instregex "LD4i(8|16|32)$")>;
def : InstRW<[M3WriteVLDK,
M3WriteA1], (instregex "LD4i(8|16|32)_POST")>;
def : InstRW<[M3WriteVLDM], (instregex "LD4i(64)$")>;
def : InstRW<[M3WriteVLDM,
M3WriteA1], (instregex "LD4i(64)_POST")>;
def : InstRW<[M3WriteVLDC], (instregex "LD4Rv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVLDC,
M3WriteA1], (instregex "LD4Rv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVLDC], (instregex "LD4Rv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVLDC,
M3WriteA1], (instregex "LD4Rv(16b|8h|4s|2d)_POST")>;
// ASIMD store instructions.
def : InstRW<[WriteVST], (instregex "ST1Onev(8b|4h|2s|1d)$")>;
def : InstRW<[WriteVST,
WriteAdr], (instregex "ST1Onev(8b|4h|2s|1d)_POST")>;
def : InstRW<[WriteVST], (instregex "ST1Onev(16b|8h|4s|2d)$")>;
def : InstRW<[WriteVST,
WriteAdr], (instregex "ST1Onev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTA], (instregex "ST1Twov(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVSTA,
WriteAdr], (instregex "ST1Twov(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVSTA], (instregex "ST1Twov(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTA,
WriteAdr], (instregex "ST1Twov(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTB], (instregex "ST1Threev(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVSTB,
WriteAdr], (instregex "ST1Threev(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVSTB], (instregex "ST1Threev(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTB,
WriteAdr], (instregex "ST1Threev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTC], (instregex "ST1Fourv(8b|4h|2s|1d)$")>;
def : InstRW<[M3WriteVSTC,
WriteAdr], (instregex "ST1Fourv(8b|4h|2s|1d)_POST")>;
def : InstRW<[M3WriteVSTC], (instregex "ST1Fourv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTC,
WriteAdr], (instregex "ST1Fourv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTD], (instregex "ST1i(8|16|32|64)$")>;
def : InstRW<[M3WriteVSTD,
WriteAdr], (instregex "ST1i(8|16|32|64)_POST")>;
def : InstRW<[M3WriteVSTD], (instregex "ST2Twov(8b|4h|2s)$")>;
def : InstRW<[M3WriteVSTD,
WriteAdr], (instregex "ST2Twov(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVSTE], (instregex "ST2Twov(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTE,
WriteAdr], (instregex "ST2Twov(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTD], (instregex "ST2i(8|16|32)$")>;
def : InstRW<[M3WriteVSTD,
WriteAdr], (instregex "ST2i(8|16|32)_POST")>;
def : InstRW<[M3WriteVSTD], (instregex "ST2i(64)$")>;
def : InstRW<[M3WriteVSTD,
WriteAdr], (instregex "ST2i(64)_POST")>;
def : InstRW<[M3WriteVSTF], (instregex "ST3Threev(8b|4h|2s)$")>;
def : InstRW<[M3WriteVSTF,
WriteAdr], (instregex "ST3Threev(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVSTG], (instregex "ST3Threev(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTG,
WriteAdr], (instregex "ST3Threev(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTH], (instregex "ST3i(8|16|32)$")>;
def : InstRW<[M3WriteVSTH,
WriteAdr], (instregex "ST3i(8|16|32)_POST")>;
def : InstRW<[M3WriteVSTF], (instregex "ST3i(64)$")>;
def : InstRW<[M3WriteVSTF,
WriteAdr], (instregex "ST3i(64)_POST")>;
def : InstRW<[M3WriteVSTF], (instregex "ST4Fourv(8b|4h|2s)$")>;
def : InstRW<[M3WriteVSTF,
WriteAdr], (instregex "ST4Fourv(8b|4h|2s)_POST")>;
def : InstRW<[M3WriteVSTI], (instregex "ST4Fourv(16b|8h|4s|2d)$")>;
def : InstRW<[M3WriteVSTI,
WriteAdr], (instregex "ST4Fourv(16b|8h|4s|2d)_POST")>;
def : InstRW<[M3WriteVSTF], (instregex "ST4i(8|16|32|64)$")>;
def : InstRW<[M3WriteVSTF,
WriteAdr], (instregex "ST4i(8|16|32|64)_POST")>;
// Cryptography instructions.
def : InstRW<[M3WriteAES], (instregex "^AES[DE]")>;
def : InstRW<[M3WriteAES,
M3ReadAES], (instregex "^AESI?MC")>;
def : InstRW<[M3WriteNCRY3A], (instregex "^PMULL?v")>;
def : InstRW<[M3WriteNCRY1A], (instregex "^SHA1([CHMP]|SU[01])")>;
def : InstRW<[M3WriteNCRY1A], (instregex "^SHA256SU0")>;
def : InstRW<[M3WriteNCRY5A], (instregex "^SHA256(H2?|SU1)")>;
// CRC instructions.
def : InstRW<[M3WriteC2], (instregex "^CRC32")>;
} // SchedModel = ExynosM3Model
|