llvm.org GIT mirror llvm / 2edda52 lib / Target / ARM / ARMScheduleR52.td
2edda52

Tree @2edda52 (Download .tar.gz)

ARMScheduleR52.td @2edda52raw · history · blame

  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
//==- ARMScheduleR52.td - Cortex-R52 Scheduling Definitions -*- 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 SchedRead/Write data for the ARM Cortex-R52 processor.
//
//===----------------------------------------------------------------------===//

// ===---------------------------------------------------------------------===//
// The Cortex-R52 is an in-order pipelined superscalar microprocessor with
// a 8 stage pipeline. It can issue maximum two instructions in each cycle.
// There are two ALUs, one LDST, one MUL  and a non-pipelined integer DIV.
// A number of forwarding paths enable results of computations to be input
// to subsequent operations before they are written to registers.
// This scheduler is a MachineScheduler. See TargetSchedule.td for details.

def CortexR52Model : SchedMachineModel {
  let MicroOpBufferSize = 0;  // R52 is in-order processor
  let IssueWidth = 2;         // 2 micro-ops dispatched per cycle
  let LoadLatency = 1;        // Optimistic, assuming no misses
  let MispredictPenalty = 8;  // A branch direction mispredict, including PFU
  let CompleteModel = 0;      // Covers instructions applicable to cortex-r52.
}


//===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available.

// Modeling each pipeline as a ProcResource using the BufferSize = 0 since
// Cortex-R52 is an in-order processor.

def R52UnitALU    : ProcResource<2> { let BufferSize = 0; } // Int ALU
def R52UnitMAC    : ProcResource<1> { let BufferSize = 0; } // Int MAC
def R52UnitDiv    : ProcResource<1> { let BufferSize = 0; } // Int Division
def R52UnitLd     : ProcResource<1> { let BufferSize = 0; } // Load/Store
def R52UnitB      : ProcResource<1> { let BufferSize = 0; } // Branch
def R52UnitFPALU  : ProcResource<2> { let BufferSize = 0; } // FP ALU
def R52UnitFPMUL  : ProcResource<2> { let BufferSize = 0; } // FP MUL
def R52UnitFPDIV  : ProcResource<1> { let BufferSize = 0; } // FP DIV

// Cortex-R52 specific SchedReads
def R52Read_ISS   : SchedRead;
def R52Read_EX1   : SchedRead;
def R52Read_EX2   : SchedRead;
def R52Read_WRI   : SchedRead;
def R52Read_F0    : SchedRead; // F0 maps to ISS stage of integer pipe
def R52Read_F1    : SchedRead;
def R52Read_F2    : SchedRead;


//===----------------------------------------------------------------------===//
// Subtarget-specific SchedWrite types which map ProcResources and set latency.

let SchedModel = CortexR52Model in {

// ALU - Write occurs in Late EX2 (independent of whether shift was required)
def : WriteRes<WriteALU, [R52UnitALU]> { let Latency = 3; }
def : WriteRes<WriteALUsi, [R52UnitALU]> { let Latency = 3; }
def : WriteRes<WriteALUsr, [R52UnitALU]> { let Latency = 3; }
def : WriteRes<WriteALUSsr, [R52UnitALU]> { let Latency = 3; }

// Compares
def : WriteRes<WriteCMP, [R52UnitALU]> { let Latency = 0; }
def : WriteRes<WriteCMPsi, [R52UnitALU]> { let Latency = 0; }
def : WriteRes<WriteCMPsr, [R52UnitALU]> { let Latency = 0; }

// Multiply - aliased to sub-target specific later

// Div - may stall 0-9 cycles depending on input (i.e. WRI+(0-9)/2)
def : WriteRes<WriteDIV, [R52UnitDiv]> {
  let Latency = 8; let ResourceCycles = [8]; // non-pipelined
}

// Branches  - LR written in Late EX2
def : WriteRes<WriteBr, [R52UnitB]> { let Latency = 0; }
def : WriteRes<WriteBrL, [R52UnitB]> { let Latency = 0; }
def : WriteRes<WriteBrTbl, [R52UnitALU]> { let Latency = 0; }

// Misc
def : WriteRes<WriteNoop, []> { let Latency = 0; let NumMicroOps = 0; }

// Integer pipeline by-passes
def : ReadAdvance<ReadALU, 1>;   // Operand needed in EX1 stage
def : ReadAdvance<ReadALUsr, 0>; // Shift operands needed in ISS
def : ReadAdvance<ReadMUL, 0>;
def : ReadAdvance<ReadMAC, 0>;

// Floating-point. Map target-defined SchedReadWrites to subtarget
def : WriteRes<WriteFPMUL32, [R52UnitFPMUL]> { let Latency = 6; }

def : WriteRes<WriteFPMUL64, [R52UnitFPMUL, R52UnitFPMUL]> {
  let Latency = 6;
}

def : WriteRes<WriteFPMAC32, [R52UnitFPMUL, R52UnitFPALU]> {
  let Latency = 11;     // as it is internally two insns (MUL then ADD)
}

def : WriteRes<WriteFPMAC64, [R52UnitFPMUL, R52UnitFPMUL,
                              R52UnitFPALU, R52UnitFPALU]> {
  let Latency = 11;
}

def : WriteRes<WriteFPDIV32, [R52UnitDiv]> {
  let Latency = 7;          // FP div takes fixed #cycles
  let ResourceCycles = [7]; // is not pipelined
}

def : WriteRes<WriteFPDIV64, [R52UnitDiv]> {
  let Latency = 17;
  let ResourceCycles = [17];
}

def : WriteRes<WriteFPSQRT32, [R52UnitDiv]> { let Latency = 7; }
def : WriteRes<WriteFPSQRT64, [R52UnitDiv]> { let Latency = 17; }

// Overriden via InstRW for this processor.
def : WriteRes<WriteVST1, []>;
def : WriteRes<WriteVST2, []>;
def : WriteRes<WriteVST3, []>;
def : WriteRes<WriteVST4, []>;

def : ReadAdvance<ReadFPMUL, 1>; // mul operand read in F1
def : ReadAdvance<ReadFPMAC, 1>; // fp-mac operand read in F1

//===----------------------------------------------------------------------===//
// Subtarget-specific SchedReadWrites.

// Forwarding information - based on when an operand is read
def : ReadAdvance<R52Read_ISS, 0>;
def : ReadAdvance<R52Read_EX1, 1>;
def : ReadAdvance<R52Read_EX2, 2>;
def : ReadAdvance<R52Read_F0, 0>;
def : ReadAdvance<R52Read_F1, 1>;
def : ReadAdvance<R52Read_F2, 2>;


// Cortex-R52 specific SchedWrites for use with InstRW
def R52WriteMAC        : SchedWriteRes<[R52UnitMAC]> { let Latency = 4; }
def R52WriteMACHi      : SchedWriteRes<[R52UnitMAC]> {
  let Latency = 4; let NumMicroOps = 0;
}
def R52WriteDIV        : SchedWriteRes<[R52UnitDiv]> {
  let Latency = 8; let ResourceCycles = [8]; // not pipelined
}
def R52WriteLd         : SchedWriteRes<[R52UnitLd]> { let Latency = 4; }
def R52WriteST         : SchedWriteRes<[R52UnitLd]> { let Latency = 4; }
def R52WriteAdr        : SchedWriteRes<[]> { let Latency = 0; }
def R52WriteCC         : SchedWriteRes<[]> { let Latency = 0; }
def R52WriteALU_EX1    : SchedWriteRes<[R52UnitALU]> { let Latency = 2; }
def R52WriteALU_EX2    : SchedWriteRes<[R52UnitALU]> { let Latency = 3; }
def R52WriteALU_WRI    : SchedWriteRes<[R52UnitALU]> { let Latency = 4; }

def R52WriteNoRSRC_EX2 : SchedWriteRes<[]> { let Latency = 3; }
def R52WriteNoRSRC_WRI : SchedWriteRes<[]> { let Latency = 4; }

// Alias generics to sub-target specific
def : SchedAlias<WriteMUL16, R52WriteMAC>;
def : SchedAlias<WriteMUL32, R52WriteMAC>;
def : SchedAlias<WriteMUL64Lo, R52WriteMAC>;
def : SchedAlias<WriteMUL64Hi, R52WriteMACHi>;
def : SchedAlias<WriteMAC16, R52WriteMAC>;
def : SchedAlias<WriteMAC32, R52WriteMAC>;
def : SchedAlias<WriteMAC64Lo, R52WriteMAC>;
def : SchedAlias<WriteMAC64Hi, R52WriteMACHi>;
def : SchedAlias<WritePreLd, R52WriteLd>;
def : SchedAlias<WriteLd, R52WriteLd>;
def : SchedAlias<WriteST, R52WriteST>;

def R52WriteFPALU_F3   : SchedWriteRes<[R52UnitFPALU]> { let Latency = 4; }
def R52Write2FPALU_F3  : SchedWriteRes<[R52UnitFPALU, R52UnitFPALU]> {
  let Latency = 4;
}
def R52WriteFPALU_F4   : SchedWriteRes<[R52UnitFPALU]> { let Latency = 5; }
def R52Write2FPALU_F4  : SchedWriteRes<[R52UnitFPALU, R52UnitFPALU]> {
  let Latency = 5;
}
def R52WriteFPALU_F5   : SchedWriteRes<[R52UnitFPALU]> { let Latency = 6; }
def R52Write2FPALU_F5  : SchedWriteRes<[R52UnitFPALU, R52UnitFPALU]> {
  let Latency = 6;
}
def R52WriteFPMUL_F5   : SchedWriteRes<[R52UnitFPMUL]> { let Latency = 6; }
def R52Write2FPMUL_F5  : SchedWriteRes<[R52UnitFPMUL, R52UnitFPMUL]> {
  let Latency = 6;
}
def R52WriteFPMAC_F5   : SchedWriteRes<[R52UnitFPMUL, R52UnitFPALU]> {
  let Latency = 11;     // as it is internally two insns (MUL then ADD)
}
def R52Write2FPMAC_F5  : SchedWriteRes<[R52UnitFPMUL, R52UnitFPMUL,
                                         R52UnitFPALU, R52UnitFPALU]> {
  let Latency = 11;
}

def R52WriteFPLd_F4    : SchedWriteRes<[R52UnitLd]> { let Latency = 5; }
def R52WriteFPST_F4    : SchedWriteRes<[R52UnitLd]> { let Latency = 5; }

//===----------------------------------------------------------------------===//
// Floating-point. Map target defined SchedReadWrites to processor specific ones
//
def : SchedAlias<WriteFPCVT,   R52WriteFPALU_F5>;
def : SchedAlias<WriteFPMOV, R52WriteFPALU_F3>;
def : SchedAlias<WriteFPALU32, R52WriteFPALU_F5>;
def : SchedAlias<WriteFPALU64, R52WriteFPALU_F5>;

//===----------------------------------------------------------------------===//
// Subtarget-specific overrides. Map opcodes to list of SchedReadWrites types.
//
def : InstRW<[WriteALU], (instrs COPY)>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1, R52Read_ISS],
      (instregex "SXTB", "SXTH", "SXTB16", "UXTB", "UXTH", "UXTB16",
      "t2SXTB", "t2SXTH", "t2SXTB16", "t2UXTB", "t2UXTH", "t2UXTB16")>;

def : InstRW<[R52WriteALU_EX1, R52Read_ISS],
      (instregex "MOVCCi32imm", "MOVi32imm", "t2MOVCCi", "t2MOVi")>;
def : InstRW<[R52WriteALU_EX2, R52Read_EX1],
      (instregex "MOV_ga_pcrel$")>;
def : InstRW<[R52WriteLd,R52Read_ISS],
      (instregex "MOV_ga_pcrel_ldr")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1, R52Read_EX1], (instregex "SEL", "t2SEL")>;

def : InstRW< [R52WriteALU_EX2, R52Read_ISS, R52Read_ISS],
      (instregex "BFC", "BFI", "UBFX", "SBFX", "(t|t2)BFC", "(t|t2)BFI",
      "(t|t2)UBFX", "(t|t2)SBFX")>;

// Saturating arithmetic
def : InstRW< [R52WriteALU_WRI, R52Read_EX1, R52Read_EX1],
      (instregex "QADD", "QSUB", "QDADD", "QDSUB", "SSAT", "SSAT16", "USAT",
      "QADD8", "QADD16", "QSUB8", "QSUB16", "QASX", "QSAX",
      "UQADD8", "UQADD16","UQSUB8","UQSUB16","UQASX","UQSAX", "t2QADD",
      "t2QSUB", "t2QDADD", "t2QDSUB", "t2SSAT", "t2SSAT16", "t2USAT",
      "t2QADD8", "t2QADD16", "t2QSUB8", "t2QSUB16", "t2QASX", "t2QSAX",
      "t2UQADD8", "t2UQADD16","t2UQSUB8","t2UQSUB16","t2UQASX","t2UQSAX","t2ABS")>;

// Parallel arithmetic
def : InstRW< [R52WriteALU_EX2, R52Read_EX1, R52Read_EX1],
      (instregex "SADD8", "SADD16", "SSUB8", "SSUB16", "SASX", "SSAX",
      "UADD8", "UADD16", "USUB8", "USUB16", "UASX", "USAX", "t2SADD8",
      "t2SADD16", "t2SSUB8", "t2SSUB16", "t2SASX", "t2SSAX", "t2UADD8",
      "t2UADD16", "t2USUB8", "t2USUB16", "t2UASX", "t2USAX")>;

// Flag setting.
def : InstRW< [R52WriteALU_EX2, R52Read_EX1, R52Read_EX1],
      (instregex "SHADD8", "SHADD16", "SHSUB8", "SHSUB16", "SHASX", "SHSAX",
      "SXTAB", "SXTAB16", "SXTAH", "UHADD8", "UHADD16", "UHSUB8", "UHSUB16",
      "UHASX", "UHSAX", "UXTAB", "UXTAB16", "UXTAH", "t2SHADD8", "t2SHADD16",
      "t2SHSUB8", "t2SHSUB16", "t2SHASX", "t2SHSAX", "t2SXTAB", "t2SXTAB16",
      "t2SXTAH", "t2UHADD8", "t2UHADD16", "t2UHSUB8", "t2UHSUB16", "t2UHASX",
      "t2UHSAX", "t2UXTAB", "t2UXTAB16", "t2UXTAH")>;

// Sum of Absolute Difference
def : InstRW< [R52WriteALU_WRI, R52Read_ISS, R52Read_ISS, R52Read_ISS],
      (instregex "USAD8", "t2USAD8", "USADA8", "t2USADA8") >;

// Integer Multiply
def : InstRW<[R52WriteMAC, R52Read_ISS, R52Read_ISS],
      (instregex "MUL", "SMMUL", "SMMULR", "SMULBB", "SMULBT",
      "SMULTB", "SMULTT", "SMULWB", "SMULWT", "SMUSD", "SMUSDX", "t2MUL",
      "t2SMMUL", "t2SMMULR", "t2SMULBB", "t2SMULBT", "t2SMULTB", "t2SMULTT",
      "t2SMULWB", "t2SMULWT", "t2SMUSD")>;

// Multiply Accumulate
// Even for 64-bit accumulation (or Long), the single MAC is used (not ALUs).
// The store pipeline is used partly for 64-bit operations.
def : InstRW<[R52WriteMAC, R52Read_ISS, R52Read_ISS, R52Read_ISS],
      (instregex "MLA", "MLS", "SMMLA", "SMMLAR", "SMMLS", "SMMLSR",
      "t2MLA", "t2MLS", "t2SMMLA", "t2SMMLAR", "t2SMMLS", "t2SMMLSR",
      "SMUAD", "SMUADX", "t2SMUAD", "t2SMUADX",
      "SMLABB", "SMLABT", "SMLATB", "SMLATT", "SMLSD", "SMLSDX",
      "SMLAWB", "SMLAWT", "t2SMLABB", "t2SMLABT", "t2SMLATB", "t2SMLATT",
      "t2SMLSD", "t2SMLSDX", "t2SMLAWB", "t2SMLAWT",
      "SMLAD", "SMLADX", "t2SMLAD", "t2SMLADX",
      "SMULL$", "UMULL$", "t2SMULL$", "t2UMULL$",
      "SMLAL", "UMLAL", "SMLALBT",
      "SMLALTB", "SMLALTT", "SMLALD", "SMLALDX", "SMLSLD", "SMLSLDX",
      "UMAAL", "t2SMLAL", "t2UMLAL",
      "t2SMLALBT", "t2SMLALTB", "t2SMLALTT", "t2SMLALD", "t2SMLALDX",
      "t2SMLSLD", "t2SMLSLDX", "t2UMAAL")>;

def : InstRW <[R52WriteDIV, R52Read_ISS, R52Read_ISS],
      (instregex "t2SDIV", "t2UDIV")>;

// Loads (except POST) with SHL > 2, or ror, require 2 extra cycles.
// However, that's non-trivial to specify, so we keep it uniform
def : InstRW<[R52WriteLd, R52Read_ISS, R52Read_ISS],
      (instregex "LDR(i12|rs)$", "LDRB(i12|rs)$", "t2LDR(i8|i12|s|pci)",
      "t2LDR(H|B)(i8|i12|s|pci)", "LDREX", "t2LDREX",
      "tLDR[BH](r|i|spi|pci|pciASM)", "tLDR(r|i|spi|pci|pciASM)",
      "LDRH$",  "PICLDR$", "PICLDR(H|B)$", "LDRcp$",
      "PICLDRS(H|B)$", "t2LDRS(H|B)(i|r|p|s)", "LDRS(H|B)$",
      "t2LDRpci_pic", "tLDRS(B|H)", "t2LDRDi8", "LDRD$", "LDA", "t2LDA")>;
def : InstRW<[R52WriteLd, R52WriteAdr, R52Read_ISS, R52Read_ISS],
      (instregex "LD(RB|R)(_|T_)(POST|PRE)_(IMM|REG)", "LDRH(_PRE|_POST)",
      "LDRBT_POST$", "LDR(T|BT)_POST_(REG|IMM)", "LDRHT(i|r)",
      "t2LD(R|RB|RH)_(PRE|POST)", "t2LD(R|RB|RH)T",
      "LDR(SH|SB)(_POST|_PRE)", "t2LDR(SH|SB)(_POST|_PRE)",
      "LDRS(B|H)T(i|r)", "t2LDRS(B|H)T(i|r)?",
      "LDRD_(POST|PRE)", "t2LDRD_(POST|PRE)")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1], (instregex "MOVS?sr", "t2MOVS?sr")>;
def : InstRW<[R52WriteALU_WRI, R52Read_EX2], (instregex "MOVT", "t2MOVT")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1], (instregex "AD(C|D)S?ri", "ANDS?ri",
      "BICS?ri", "CLZ", "EORri", "MVNS?r", "ORRri", "RSBS?ri", "RSCri", "SBCri",
      "t2AD(C|D)S?ri", "t2ANDS?ri", "t2BICS?ri","t2CLZ", "t2EORri", "t2MVN",
      "t2ORRri", "t2RSBS?ri", "t2SBCri")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1, R52Read_EX1], (instregex "AD(C|D)S?rr",
      "ANDS?rr", "BICS?rr", "CRC", "EORrr", "ORRrr", "RSBrr", "RSCrr", "SBCrr",
      "t2AD(C|D)S?rr", "t2ANDS?rr", "t2BICS?rr", "t2CRC", "t2EORrr", "t2SBCrr")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1, R52Read_ISS], (instregex "AD(C|D)S?rsi",
      "ANDS?rsi", "BICS?rsi", "EORrsi", "ORRrsi", "RSBrsi", "RSCrsi", "SBCrsi",
      "t2AD(C|D)S?rs", "t2ANDS?rs", "t2BICS?rs", "t2EORrs", "t2ORRrs", "t2RSBrs", "t2SBCrs")>;

def : InstRW<[R52WriteALU_EX2, R52Read_EX1, R52Read_ISS, R52Read_ISS],
      (instregex "AD(C|D)S?rsr", "ANDS?rsr", "BICS?rsr", "EORrsr", "MVNS?sr",
      "ORRrsr", "RSBrsr", "RSCrsr", "SBCrsr")>;

def : InstRW<[R52WriteALU_EX1],
    (instregex "ADR", "MOVsi", "MVNS?s?i", "t2MOVS?si")>;

def : InstRW<[R52WriteALU_EX1, R52Read_ISS], (instregex "ASRi", "RORS?i")>;
def : InstRW<[R52WriteALU_EX1, R52Read_ISS, R52Read_ISS],
      (instregex "ASRr", "RORS?r", "LSR", "LSL")>;

def : InstRW<[R52WriteCC, R52Read_EX1], (instregex "CMPri", "CMNri")>;
def : InstRW<[R52WriteCC, R52Read_EX1, R52Read_EX1], (instregex "CMPrr", "CMNzrr")>;
def : InstRW<[R52WriteCC, R52Read_EX1, R52Read_ISS], (instregex "CMPrsi", "CMNzrsi")>;
def : InstRW<[R52WriteCC, R52Read_EX1, R52Read_ISS, R52Read_ISS], (instregex "CMPrsr", "CMNzrsr")>;

def : InstRW<[R52WriteALU_EX2, R52Read_ISS],
      (instregex "t2LDC", "RBIT", "REV", "REV16", "REVSH", "RRX")>;

def : InstRW<[R52WriteCC, R52Read_ISS], (instregex "TST")>;

def : InstRW<[R52WriteLd], (instregex "MRS", "MRSbanked")>;
def : InstRW<[R52WriteLd, R52Read_EX1], (instregex "MSR", "MSRbanked")>;

// Integer Load, Multiple.
foreach Lat = 3-25 in {
  def R52WriteILDM#Lat#Cy : SchedWriteRes<[R52UnitLd]> {
    let Latency = Lat;
  }
  def R52WriteILDM#Lat#CyNo : SchedWriteRes<[]> {
    let Latency = Lat;
    let NumMicroOps = 0;
  }
}
foreach NAddr = 1-16 in {
  def R52ILDMAddr#NAddr#Pred : SchedPredicate<"TII->getNumLDMAddresses(*MI) == "#NAddr>;
}
def R52WriteILDMAddrNoWB : SchedWriteRes<[R52UnitLd]> { let Latency = 0; }
def R52WriteILDMAddrWB : SchedWriteRes<[R52UnitLd]>;
def R52WriteILDM : SchedWriteVariant<[
    SchedVar<R52ILDMAddr2Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy]>,

    SchedVar<R52ILDMAddr3Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy]>,
    SchedVar<R52ILDMAddr4Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy]>,

    SchedVar<R52ILDMAddr5Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy]>,
    SchedVar<R52ILDMAddr6Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy]>,

    SchedVar<R52ILDMAddr7Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy]>,
    SchedVar<R52ILDMAddr8Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy]>,

    SchedVar<R52ILDMAddr9Pred, [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy]>,
    SchedVar<R52ILDMAddr10Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy]>,

    SchedVar<R52ILDMAddr11Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy]>,
    SchedVar<R52ILDMAddr12Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy, R52WriteILDM15Cy]>,

    SchedVar<R52ILDMAddr13Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy, R52WriteILDM15Cy,
                                 R52WriteILDM16Cy]>,
    SchedVar<R52ILDMAddr14Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy, R52WriteILDM15Cy,
                                 R52WriteILDM16Cy, R52WriteILDM17Cy]>,

    SchedVar<R52ILDMAddr15Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy, R52WriteILDM15Cy,
                                 R52WriteILDM16Cy, R52WriteILDM17Cy,
                                 R52WriteILDM18Cy]>,
    SchedVar<R52ILDMAddr15Pred,[R52WriteILDM4Cy, R52WriteILDM5Cy,
                                 R52WriteILDM6Cy, R52WriteILDM7Cy,
                                 R52WriteILDM8Cy, R52WriteILDM9Cy,
                                 R52WriteILDM10Cy, R52WriteILDM11Cy,
                                 R52WriteILDM12Cy, R52WriteILDM13Cy,
                                 R52WriteILDM14Cy, R52WriteILDM15Cy,
                                 R52WriteILDM16Cy, R52WriteILDM17Cy,
                                 R52WriteILDM18Cy, R52WriteILDM19Cy]>,

// Unknown number of registers, just use resources for two registers.
    SchedVar<NoSchedPred,      [R52WriteILDM4Cy, R52WriteILDM5Cy,
                                R52WriteILDM6CyNo, R52WriteILDM7CyNo,
                                R52WriteILDM8CyNo, R52WriteILDM9CyNo,
                                R52WriteILDM10CyNo, R52WriteILDM11CyNo,
                                R52WriteILDM12CyNo, R52WriteILDM13CyNo,
                                R52WriteILDM14CyNo, R52WriteILDM15CyNo,
                                R52WriteILDM16CyNo, R52WriteILDM17CyNo,
                                R52WriteILDM18Cy, R52WriteILDM19Cy]>
]> { let Variadic=1; }

// Integer Store, Multiple
def R52WriteIStIncAddr : SchedWriteRes<[R52UnitLd]> {
  let Latency = 4;
  let NumMicroOps = 2;
}
foreach NumAddr = 1-16 in {
  def R52WriteISTM#NumAddr : WriteSequence<[R52WriteIStIncAddr], NumAddr>;
}
def R52WriteISTM : SchedWriteVariant<[
    SchedVar<R52ILDMAddr2Pred, [R52WriteISTM2]>,
    SchedVar<R52ILDMAddr3Pred, [R52WriteISTM3]>,
    SchedVar<R52ILDMAddr4Pred, [R52WriteISTM4]>,
    SchedVar<R52ILDMAddr5Pred, [R52WriteISTM5]>,
    SchedVar<R52ILDMAddr6Pred, [R52WriteISTM6]>,
    SchedVar<R52ILDMAddr7Pred, [R52WriteISTM7]>,
    SchedVar<R52ILDMAddr8Pred, [R52WriteISTM8]>,
    SchedVar<R52ILDMAddr9Pred, [R52WriteISTM9]>,
    SchedVar<R52ILDMAddr10Pred,[R52WriteISTM10]>,
    SchedVar<R52ILDMAddr11Pred,[R52WriteISTM11]>,
    SchedVar<R52ILDMAddr12Pred,[R52WriteISTM12]>,
    SchedVar<R52ILDMAddr13Pred,[R52WriteISTM13]>,
    SchedVar<R52ILDMAddr14Pred,[R52WriteISTM14]>,
    SchedVar<R52ILDMAddr15Pred,[R52WriteISTM15]>,
    SchedVar<R52ILDMAddr16Pred,[R52WriteISTM16]>,
    // Unknow number of registers, just use resources for two registers.
    SchedVar<NoSchedPred,      [R52WriteISTM2]>
]>;

def : InstRW<[R52WriteILDM, R52Read_ISS],
      (instregex "LDM(IA|DA|DB|IB)$", "t2LDM(IA|DA|DB|IB)$",
      "(t|sys)LDM(IA|DA|DB|IB)$")>;
def : InstRW<[R52WriteILDM, R52WriteAdr, R52Read_ISS],
      (instregex "LDM(IA|DA|DB|IB)_UPD", "(t2|sys|t)LDM(IA|DA|DB|IB)_UPD")>;
def : InstRW<[R52WriteILDM, R52WriteAdr, R52Read_ISS],
        (instregex "LDMIA_RET", "(t|t2)LDMIA_RET", "tPOP")>;

// Integer Store, Single Element
def : InstRW<[R52WriteLd, R52Read_ISS, R52Read_EX2],
      (instregex "PICSTR", "STR(i12|rs)", "STRB(i12|rs)", "STRH$", "STREX", "SRS", "t2SRS",
      "t2SRSDB", "t2STREX", "t2STREXB", "t2STREXD", "t2STREXH", "t2STR(i12|i8|s)$",
      "RFE", "t2RFE", "t2STR[BH](i12|i8|s)$", "tSTR[BH](i|r)", "tSTR(i|r)", "tSTRspi")>;

def : InstRW<[R52WriteLd, R52WriteAdr, R52Read_ISS, R52Read_EX2],
      (instregex "STR(B_|_|BT_|T_)(PRE_IMM|PRE_REG|POST_REG|POST_IMM)",
      "STR(i|r)_preidx", "STRB(i|r)_preidx", "STRH_preidx", "STR(H_|HT_)(PRE|POST)",
      "STR(BT|HT|T)", "t2STR_(PRE|POST)", "t2STR[BH]_(PRE|POST)",
      "t2STR_preidx", "t2STR[BH]_preidx", "t2ST(RB|RH|R)T")>;

// Integer Store, Dual
def : InstRW<[R52WriteLd, R52Read_ISS, R52Read_EX2],
    (instregex "STRD$", "t2STRDi8", "STL", "t2STL")>;
def : InstRW<[R52WriteLd, R52WriteAdr, R52Read_ISS, R52Read_EX2],
    (instregex "(t2|t)STRD_(POST|PRE)", "STRD_(POST|PRE)")>;

def : InstRW<[R52WriteISTM, R52Read_ISS, R52Read_EX2],
    (instregex "STM(IB|IA|DB|DA)$", "(t2|sys|t)STM(IB|IA|DB|DA)$")>;
def : InstRW<[R52WriteISTM, R52WriteAdr, R52Read_ISS, R52Read_EX2],
    (instregex "STM(IB|IA|DB|DA)_UPD", "(t2|sys|t)STM(IB|IA|DB|DA)_UPD",
    "tPUSH")>;

// LDRLIT pseudo instructions, they expand to LDR + PICADD
def : InstRW<[R52WriteLd],
      (instregex "t?LDRLIT_ga_abs", "t?LDRLIT_ga_pcrel$")>;
// LDRLIT_ga_pcrel_ldr expands to LDR + PICLDR
def : InstRW<[R52WriteLd], (instregex "LDRLIT_ga_pcrel_ldr")>;



//===----------------------------------------------------------------------===//
// VFP, Floating Point Support
def : InstRW<[R52WriteFPALU_F5, R52Read_F1, R52Read_F1], (instregex "VABD(fd|hd)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1, R52Read_F1], (instregex "VABD(fq|hq)")>;

def : InstRW<[R52WriteFPALU_F5, R52Read_F1], (instregex "VABS(D|S|H)")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F1], (instregex "VABS(fd|hd)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1], (instregex "VABS(fq|hq)")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F1], (instregex "(VACGE|VACGT)(fd|hd)")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F1, R52Read_F1], (instregex "(VACGE|VACGT)(fq|hq)")>;

def : InstRW<[R52WriteFPALU_F5, R52Read_F1, R52Read_F1], (instregex "(VADD|VSUB)(D|S|H|fd|hd)$")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1, R52Read_F1], (instregex "(VADD|VSUB)(fq|hq)")>;

def : InstRW<[R52WriteFPLd_F4, R52Read_ISS, R52Read_F1], (instregex "VLDR")>;
def : InstRW<[R52WriteFPST_F4, R52Read_ISS, R52Read_F1], (instregex "VSTR")>;


//===----------------------------------------------------------------------===//
// Neon Support

// vector multiple load stores
foreach NumAddr = 1-16 in {
  def R52LMAddrPred#NumAddr :
    SchedPredicate<"MI->getNumOperands() == "#NumAddr>;
}
foreach Lat = 1-32 in {
  def R52WriteLM#Lat#Cy : SchedWriteRes<[]> {
    let Latency = Lat;
  }
}
foreach Num = 1-32 in { // reserve LdSt resource, no dual-issue
  def R52ReserveLd#Num#Cy : SchedWriteRes<[R52UnitLd]> {
    let Latency = 0;
    let NumMicroOps = Num;
    let ResourceCycles = [Num];
  }
}
def R52WriteVLDM : SchedWriteVariant<[
  // 1 D reg
  SchedVar<R52LMAddrPred1,  [R52WriteLM5Cy,
                              R52ReserveLd5Cy]>,
  SchedVar<R52LMAddrPred2,  [R52WriteLM5Cy,
                              R52ReserveLd5Cy]>,

  // 2 D reg
  SchedVar<R52LMAddrPred3,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52ReserveLd6Cy]>,
  SchedVar<R52LMAddrPred4,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52ReserveLd6Cy]>,

  // 3 D reg
  SchedVar<R52LMAddrPred5,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy,
                              R52ReserveLd4Cy]>,
  SchedVar<R52LMAddrPred6,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy,
                              R52ReserveLd7Cy]>,

  // 4 D reg
  SchedVar<R52LMAddrPred7,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52ReserveLd8Cy]>,
  SchedVar<R52LMAddrPred8,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52ReserveLd8Cy]>,

  // 5 D reg
  SchedVar<R52LMAddrPred9,  [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy,
                              R52ReserveLd9Cy]>,
  SchedVar<R52LMAddrPred10, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy,
                              R52ReserveLd9Cy]>,

  // 6 D reg
  SchedVar<R52LMAddrPred11, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52ReserveLd10Cy]>,
  SchedVar<R52LMAddrPred12, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52ReserveLd10Cy]>,

  // 7 D reg
  SchedVar<R52LMAddrPred13, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52WriteLM11Cy,
                              R52ReserveLd11Cy]>,
  SchedVar<R52LMAddrPred14, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52WriteLM11Cy,
                              R52ReserveLd11Cy]>,

  // 8 D reg
  SchedVar<R52LMAddrPred14, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52WriteLM11Cy, R52WriteLM12Cy,
                              R52ReserveLd12Cy]>,
  SchedVar<R52LMAddrPred15, [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52WriteLM11Cy, R52WriteLM12Cy,
                              R52ReserveLd12Cy]>,
  // unknown number of reg.
  SchedVar<NoSchedPred,      [R52WriteLM5Cy, R52WriteLM6Cy,
                              R52WriteLM7Cy, R52WriteLM8Cy,
                              R52WriteLM9Cy, R52WriteLM10Cy,
                              R52WriteLM11Cy, R52WriteLM12Cy,
                              R52ReserveLd5Cy]>
]> { let Variadic=1;}

// variable stores. Cannot dual-issue
def R52WriteSTM5  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 5;
  let NumMicroOps = 2;
  let ResourceCycles = [1];
}
def R52WriteSTM6  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 6;
  let NumMicroOps = 4;
  let ResourceCycles = [2];
}
def R52WriteSTM7  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 7;
  let NumMicroOps = 6;
  let ResourceCycles = [3];
}
def R52WriteSTM8  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 8;
  let NumMicroOps = 8;
  let ResourceCycles = [4];
}
def R52WriteSTM9  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 9;
  let NumMicroOps = 10;
  let ResourceCycles = [5];
}
def R52WriteSTM10 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 10;
  let NumMicroOps = 12;
  let ResourceCycles = [6];
}
def R52WriteSTM11 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 11;
  let NumMicroOps = 14;
  let ResourceCycles = [7];
}
def R52WriteSTM12 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 12;
  let NumMicroOps = 16;
  let ResourceCycles = [8];
}
def R52WriteSTM13 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 13;
  let NumMicroOps = 18;
  let ResourceCycles = [9];
}
def R52WriteSTM14 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 14;
  let NumMicroOps = 20;
  let ResourceCycles = [10];
}
def R52WriteSTM15 : SchedWriteRes<[R52UnitLd]> {
  let Latency = 15;
  let NumMicroOps = 22;
  let ResourceCycles = [11];
}

def R52WriteSTM : SchedWriteVariant<[
  SchedVar<R52LMAddrPred1, [R52WriteSTM5]>,
  SchedVar<R52LMAddrPred2, [R52WriteSTM5]>,
  SchedVar<R52LMAddrPred3, [R52WriteSTM6]>,
  SchedVar<R52LMAddrPred4, [R52WriteSTM6]>,
  SchedVar<R52LMAddrPred5, [R52WriteSTM7]>,
  SchedVar<R52LMAddrPred6, [R52WriteSTM7]>,
  SchedVar<R52LMAddrPred7, [R52WriteSTM8]>,
  SchedVar<R52LMAddrPred8, [R52WriteSTM8]>,
  SchedVar<R52LMAddrPred9,  [R52WriteSTM9]>,
  SchedVar<R52LMAddrPred10, [R52WriteSTM9]>,
  SchedVar<R52LMAddrPred11, [R52WriteSTM10]>,
  SchedVar<R52LMAddrPred12, [R52WriteSTM10]>,
  SchedVar<R52LMAddrPred13, [R52WriteSTM11]>,
  SchedVar<R52LMAddrPred14, [R52WriteSTM11]>,
  SchedVar<R52LMAddrPred15, [R52WriteSTM12]>,
  SchedVar<R52LMAddrPred16, [R52WriteSTM12]>,
  // unknown number of registers, just use resources for two
  SchedVar<NoSchedPred,      [R52WriteSTM6]>
]>;

// Vector Load/Stores. Can issue only in slot-0. Can dual-issue with
// another instruction in slot-1, but only in the last issue.
def : WriteRes<WriteVLD1, [R52UnitLd]> { let Latency = 5;}
def : WriteRes<WriteVLD2, [R52UnitLd]> {
  let Latency = 6;
  let NumMicroOps = 3;
  let ResourceCycles = [2];
  let SingleIssue = 1;
}
def : WriteRes<WriteVLD3, [R52UnitLd]> {
  let Latency = 7;
  let NumMicroOps = 5;
  let ResourceCycles = [3];
  let SingleIssue = 1;
}
def : WriteRes<WriteVLD4, [R52UnitLd]> {
  let Latency = 8;
  let NumMicroOps = 7;
  let ResourceCycles = [4];
  let SingleIssue = 1;
}
def R52WriteVST1Mem  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 5;
  let NumMicroOps = 1;
  let ResourceCycles = [1];
}
def R52WriteVST2Mem  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 6;
  let NumMicroOps = 3;
  let ResourceCycles = [2];
}
def R52WriteVST3Mem  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 7;
  let NumMicroOps = 5;
  let ResourceCycles = [3];
}
def R52WriteVST4Mem  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 8;
  let NumMicroOps = 7;
  let ResourceCycles = [4];
}
def R52WriteVST5Mem  : SchedWriteRes<[R52UnitLd]> {
  let Latency = 9;
  let NumMicroOps = 9;
  let ResourceCycles = [5];
}


def : InstRW<[R52WriteFPALU_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "VABA(u|s)(v8i8|v4i16|v2i32)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "VABA(u|s)(v16i8|v8i16|v4i32)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "VABAL(u|s)(v8i16|v4i32|v2i64)")>;

def : InstRW<[R52WriteFPALU_F4, R52Read_F1, R52Read_F1], (instregex "VABD(u|s)(v8i8|v4i16|v2i32)")>;
def : InstRW<[R52Write2FPALU_F4, R52Read_F1, R52Read_F1], (instregex "VABD(u|s)(v16i8|v8i16|v4i32)")>;
def : InstRW<[R52Write2FPALU_F4, R52Read_F1, R52Read_F1], (instregex "VABDL(u|s)(v16i8|v8i16|v4i32)")>;

def : InstRW<[R52Write2FPALU_F4, R52Read_F1], (instregex "VABS(v16i8|v8i16|v4i32)")>;

def : InstRW<[R52WriteFPALU_F4, R52Read_F2, R52Read_F2],
                               (instregex "(VADD|VSUB)(v8i8|v4i16|v2i32|v1i64)")>;
def : InstRW<[R52Write2FPALU_F4, R52Read_F2, R52Read_F2],
                                (instregex "(VADD|VSUB)(v16i8|v8i16|v4i32|v2i64)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F2, R52Read_F2],
                               (instregex "(VADDHN|VRADDHN|VSUBHN|VRSUBHN)(v8i8|v4i16|v2i32)")>;

def : InstRW<[R52Write2FPALU_F4, R52Read_F1, R52Read_F1],
                                            (instregex "VADDL", "VADDW", "VSUBL", "VSUBW")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F2, R52Read_F2], (instregex "(VAND|VBIC|VEOR)d")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F2, R52Read_F2], (instregex "(VAND|VBIC|VEOR)q")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F2], (instregex "VBICi(v4i16|v2i32)")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F2], (instregex "VBICi(v8i16|v4i32)")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F2, R52Read_F2], (instregex "(VBIF|VBIT|VBSL)d")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F1, R52Read_F2, R52Read_F2], (instregex "(VBIF|VBIT|VBSL)q")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F1],
      (instregex "(VCEQ|VCGE|VCGT|VCLE|VCLT|VCLZ|VCMP|VCMPE|VCNT)")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F1, R52Read_F1],
      (instregex "VCVT", "VSITO", "VUITO", "VTO")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_ISS], (instregex "VDUP(8|16|32)d")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_ISS], (instregex "VDUP(8|16|32)q")>;
def : InstRW<[R52WriteFPALU_F3, R52Read_F1], (instregex "VDUPLN(8|16|32)d")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F1], (instregex "VDUPLN(8|16|32)q")>;

def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F1], (instregex "VEXTd(8|16|32)", "VSEL")>;
def : InstRW<[R52Write2FPALU_F3, R52Read_F1, R52Read_F1], (instregex "VEXTq(8|16|32|64)")>;

def : InstRW<[R52WriteFPMAC_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "(VFMA|VFMS)(f|h)d")>;
def : InstRW<[R52Write2FPMAC_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "(VFMA|VFMS)(f|h)q")>;

def : InstRW<[R52WriteFPALU_F4, R52Read_F2, R52Read_F2], (instregex "(VHADD|VHSUB)(u|s)(v8i8|v4i16|v2i32)")>;
def : InstRW<[R52Write2FPALU_F4, R52Read_F2, R52Read_F2], (instregex "(VHADD|VHSUB)(u|s)(v16i8|v8i16|v4i32)")>;

def : InstRW<[R52WriteVLDM], (instregex "VLDM[SD](IA|DB)$")>;
def : InstRW<[R52WriteFPALU_F4, R52Read_F1, R52Read_F1], (instregex "VMAX", "VMIN", "VPMAX", "VPMIN")>;
def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F1], (instregex "VORR", "VORN", "VREV")>;
def : InstRW<[R52WriteNoRSRC_WRI], (instregex "VMRS")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F1], (instregex "VNEG")>;
def : InstRW<[R52WriteFPALU_F4, R52Read_F1, R52Read_F1], (instregex "VPADDi")>;
def : InstRW<[R52Write2FPALU_F4, R52Read_F1, R52Read_F1], (instregex "VPADAL", "VPADDL")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F1], (instregex "VQABS(v8i8|v4i16|v2i32|v1i64)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F1], (instregex "VQABS(v16i8|v8i16|v4i32|v2i64)")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F2, R52Read_F2],
                  (instregex "(VQADD|VQSUB)(u|s)(v8i8|v4i16|v2i32|v1i64)")>;
def : InstRW<[R52Write2FPALU_F5, R52Read_F2, R52Read_F2],
                  (instregex "(VQADD|VQSUB)(u|s)(v16i8|v8i16|v4i32|v2i64)")>;
def : InstRW<[R52Write2FPMAC_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "VQDMLAL", "VQDMLSL")>;
def : InstRW<[R52WriteFPMUL_F5, R52Read_F1, R52Read_F1, R52Read_F1], (instregex "VQDMUL","VQRDMUL")>;
def : InstRW<[R52WriteFPALU_F5, R52Read_F1, R52Read_F1],
                 (instregex "VQMOVN", "VQNEG", "VQSHL", "VQSHRN")>;
def : InstRW<[R52WriteFPALU_F4, R52Read_F1, R52Read_F1], (instregex "VRSHL", "VRSHR", "VRSHRN", "VTB")>;
def : InstRW<[R52WriteFPALU_F3, R52Read_F1, R52Read_F1], (instregex "VSWP", "VTRN", "VUZP", "VZIP")>;

//---
// VSTx. Vector Stores
//---
// 1-element structure store
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST1q(8|16|32|64)$")>;
def : InstRW<[R52WriteVST3Mem, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)T$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)Q$")>;
def : InstRW<[R52WriteVST3Mem, R52Read_ISS, R52Read_F2], (instregex "VST1d64TPseudo$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST1d64QPseudo$")>;

def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST1LNd(8|16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST1LNdAsm_(8|16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST1LNq(8|16|32)Pseudo$")>;

def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)wb")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1q(8|16|32|64)wb")>;
def : InstRW<[R52WriteVST3Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)Twb")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1d(8|16|32|64)Qwb")>;
def : InstRW<[R52WriteVST3Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1d64TPseudoWB")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1d64QPseudoWB")>;

def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1LNd(8|16|32)_UPD")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1LNdWB_(fixed|register)_Asm_(8|16|32)")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST1LNq(8|16|32)Pseudo_UPD")>;

// 2-element structure store
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST2(d|b)(8|16|32)$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST2q(8|16|32)$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST2q(8|16|32)Pseudo$")>;

def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNd(8|16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNdAsm_(8|16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNd(8|16|32)Pseudo$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNq(16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNqAsm_(16|32)$")>;
def : InstRW<[R52WriteVST1Mem, R52Read_ISS, R52Read_F2], (instregex "VST2LNq(16|32)Pseudo$")>;

def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2(d|b)(8|16|32)wb")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2q(8|16|32)wb")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2q(8|16|32)PseudoWB")>;

def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNd(8|16|32)_UPD")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNdWB_(fixed|register)_Asm_(8|16|32)")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNd(8|16|32)Pseudo_UPD")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNq(16|32)_UPD")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNqWB_(fixed|register)_Asm_(16|32)")>;
def : InstRW<[R52WriteVST1Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST2LNq(16|32)Pseudo_UPD")>;

// 3-element structure store
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST3(d|q)(8|16|32)$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST3(d|q)Asm_(8|16|32)$")>;
def : InstRW<[R52WriteVST4Mem, R52Read_ISS, R52Read_F2], (instregex "VST3d(8|16|32)(oddP|P)seudo$")>;

def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNd(8|16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNdAsm_(8|16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNd(8|16|32)Pseudo$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNq(16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNqAsm_(16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST3LNq(16|32)Pseudo$")>;

def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3(d|q)(8|16|32)_UPD$")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3(d|q)WB_(fixed|register)_Asm_(8|16|32)$")>;
def : InstRW<[R52WriteVST4Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3(d|q)(8|16|32)(oddP|P)seudo_UPD$")>;

def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNd(8|16|32)_UPD$")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNdWB_(fixed|register)_Asm_(8|16|32)")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNd(8|16|32)Pseudo_UPD$")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNq(16|32)_UPD$")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNqWB_(fixed|register)_Asm_(16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST3LNq(16|32)Pseudo_UPD$")>;

// 4-element structure store
def : InstRW<[R52WriteVST5Mem, R52Read_ISS, R52Read_F2], (instregex "VST4(d|q)(8|16|32)$")>;
def : InstRW<[R52WriteVST5Mem, R52Read_ISS, R52Read_F2], (instregex "VST4(d|q)Asm_(8|16|32)$")>;
def : InstRW<[R52WriteVST5Mem, R52Read_ISS, R52Read_F2], (instregex "VST4d(8|16|32)Pseudo$")>;

def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNd(8|16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNdAsm_(8|16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNd(8|16|32)Pseudo$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNq(16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNqAsm_(16|32)$")>;
def : InstRW<[R52WriteVST2Mem, R52Read_ISS, R52Read_F2], (instregex "VST4LNq(16|32)Pseudo$")>;

def : InstRW<[R52WriteVST5Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4(d|q)(8|16|32)_UPD")>;
def : InstRW<[R52WriteVST5Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4(d|q)WB_(fixed|register)_Asm_(8|16|32)")>;
def : InstRW<[R52WriteVST5Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4(d|q)(8|16|32)(oddP|P)seudo_UPD")>;

def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNd(8|16|32)_UPD")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNdWB_(fixed|register)_Asm_(8|16|32)")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNd(8|16|32)Pseudo_UPD")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNq(16|32)_UPD")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNqWB_(fixed|register)_Asm_(16|32)")>;
def : InstRW<[R52WriteVST2Mem, R52WriteAdr, R52Read_ISS, R52Read_F2], (instregex "VST4LNq(16|32)Pseudo_UPD")>;

} // R52 SchedModel