aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm12/lib/Target/ARM/ARMScheduleA57.td
blob: 0c610a4839f8aa491c5578e6fcb2a3478d044e5d (plain) (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
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
//=- ARMScheduleA57.td - ARM Cortex-A57 Scheduling 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 ARM Cortex-A57 to support
// instruction scheduling and other instruction cost heuristics.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// *** Common description and scheduling model parameters taken from AArch64 ***
// The Cortex-A57 is a traditional superscalar microprocessor with a
// conservative 3-wide in-order stage for decode and dispatch. Combined with the
// much wider out-of-order issue stage, this produced a need to carefully
// schedule micro-ops so that all three decoded each cycle are successfully
// issued as the reservation station(s) simply don't stay occupied for long.
// Therefore, IssueWidth is set to the narrower of the two at three, while still
// modeling the machine as out-of-order.

def IsCPSRDefinedAndPredicated : CheckAll<[IsCPSRDefined, IsPredicated]>;
def IsCPSRDefinedAndPredicatedPred :
    MCSchedPredicate<IsCPSRDefinedAndPredicated>;

// Cortex A57 rev. r1p0 or later (false = r0px)
def IsR1P0AndLaterPred : MCSchedPredicate<FalsePred>;

def IsLdrAm3RegOffPred : MCSchedPredicate<CheckInvalidRegOperand<2>>;
def IsLdrAm3RegOffPredX2 : MCSchedPredicate<CheckInvalidRegOperand<3>>;
def IsLdrAm3RegOffPredX3 : MCSchedPredicate<CheckInvalidRegOperand<4>>;

// If Addrmode3 contains "minus register"
class Am3NegativeRegOffset<int n> : MCSchedPredicate<CheckAll<[
                                      CheckValidRegOperand<n>,
                                      CheckAM3OpSub<!add(n, 1)>]>>;

def IsLdrAm3NegRegOffPred : Am3NegativeRegOffset<2>;
def IsLdrAm3NegRegOffPredX2 : Am3NegativeRegOffset<3>;
def IsLdrAm3NegRegOffPredX3 : Am3NegativeRegOffset<4>;

// Load, scaled register offset, not plus LSL2
class ScaledRegNotPlusLsl2<int n> : CheckNot<
                                      CheckAny<[
                                        CheckAM2NoShift<n>,
                                        CheckAll<[
                                          CheckAM2OpAdd<n>,
                                          CheckAM2ShiftLSL<n>,
                                          CheckAM2Offset<n, 2>
                                        ]>
                                      ]>
                                    >;

def IsLdstsoScaledNotOptimalPredX0 : MCSchedPredicate<ScaledRegNotPlusLsl2<2>>;
def IsLdstsoScaledNotOptimalPred : MCSchedPredicate<ScaledRegNotPlusLsl2<3>>;
def IsLdstsoScaledNotOptimalPredX2 : MCSchedPredicate<ScaledRegNotPlusLsl2<4>>;

def IsLdstsoScaledPredX2 : MCSchedPredicate<CheckNot<CheckAM2NoShift<4>>>;

def IsLdstsoMinusRegPredX0 : MCSchedPredicate<CheckAM2OpSub<2>>;
def IsLdstsoMinusRegPred : MCSchedPredicate<CheckAM2OpSub<3>>;
def IsLdstsoMinusRegPredX2 : MCSchedPredicate<CheckAM2OpSub<4>>;

class A57WriteLMOpsListType<list<SchedWriteRes> writes> {
  list <SchedWriteRes> Writes = writes;
  SchedMachineModel SchedModel = ?;
}

// *** Common description and scheduling model parameters taken from AArch64 ***
// (AArch64SchedA57.td)
def CortexA57Model : SchedMachineModel {
  let IssueWidth        =   3; // 3-way decode and dispatch
  let MicroOpBufferSize = 128; // 128 micro-op re-order buffer
  let LoadLatency       =   4; // Optimistic load latency
  let MispredictPenalty =  16; // Fetch + Decode/Rename/Dispatch + Branch

  // Enable partial & runtime unrolling.
  let LoopMicroOpBufferSize = 16;
  let CompleteModel = 1;

  // FIXME: Remove when all errors have been fixed.
  let FullInstRWOverlapCheck = 0;

  let UnsupportedFeatures = [HasV8_1MMainline, HasMVEInt, HasMVEFloat,
                             HasFPRegsV8_1M, HasFP16FML, HasMatMulInt8, HasBF16];
}

//===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available on Cortex-A57.
// Cortex A-57 has 8 pipelines that each has its own 8-entry queue where
// micro-ops wait for their operands and then issue out-of-order.

def A57UnitB : ProcResource<1>;  // Type B micro-ops
def A57UnitI : ProcResource<2>;  // Type I micro-ops
def A57UnitM : ProcResource<1>;  // Type M micro-ops
def A57UnitL : ProcResource<1>;  // Type L micro-ops
def A57UnitS : ProcResource<1>;  // Type S micro-ops

def A57UnitX : ProcResource<1>;  // Type X micro-ops (F1)
def A57UnitW : ProcResource<1>;  // Type W micro-ops (F0)

let SchedModel = CortexA57Model in {
  def A57UnitV : ProcResGroup<[A57UnitX, A57UnitW]>;    // Type V micro-ops
}

let SchedModel = CortexA57Model in {

//===----------------------------------------------------------------------===//
// Define customized scheduler read/write types specific to the Cortex-A57.

include "ARMScheduleA57WriteRes.td"

// To have "CompleteModel = 1", support of pseudos and special instructions
def : InstRW<[WriteNoop], (instregex "(t)?BKPT$", "(t2)?CDP(2)?$",
  "(t2)?CLREX$", "CONSTPOOL_ENTRY$", "COPY_STRUCT_BYVAL_I32$",
  "(t2)?CPS[123]p$", "(t2)?DBG$", "(t2)?DMB$", "(t2)?DSB$", "ERET$",
  "(t2|t)?HINT$", "(t)?HLT$", "(t2)?HVC$", "(t2)?ISB$", "ITasm$",
  "(t2)?RFE(DA|DB|IA|IB)", "(t)?SETEND", "(t2)?SETPAN", "(t2)?SMC", "SPACE",
  "(t2)?SRS(DA|DB|IA|IB)", "SWP(B)?", "t?TRAP", "(t2|t)?UDF$", "t2DCPS", "t2SG",
  "t2TT", "tCPS", "CMP_SWAP", "t?SVC", "t2IT", "CompilerBarrier",
  "t__brkdiv0")>;

def : InstRW<[WriteNoop], (instregex "VMRS", "VMSR", "FMSTAT")>;

// Specific memory instrs
def : InstRW<[WriteNoop, WriteNoop], (instregex "(t2)?LDA", "(t2)?LDC", "(t2)?STC",
  "(t2)?STL", "(t2)?LDREX", "(t2)?STREX", "MEMCPY")>;

// coprocessor moves
def : InstRW<[WriteNoop, WriteNoop], (instregex
  "(t2)?MCR(2|R|R2)?$", "(t2)?MRC(2)?$",
  "(t2)?MRRC(2)?$", "(t2)?MRS(banked|sys|_AR|_M|sys_AR)?$",
  "(t2)?MSR(banked|i|_AR|_M)?$")>;

// Deprecated instructions
def : InstRW<[WriteNoop], (instregex "FLDM", "FSTM")>;

// Pseudos
def : InstRW<[WriteNoop], (instregex "(t2)?ABS$",
  "(t)?ADJCALLSTACKDOWN$", "(t)?ADJCALLSTACKUP$", "(t2|t)?Int_eh_sjlj",
  "tLDRpci_pic", "(t2)?SUBS_PC_LR",
  "JUMPTABLE", "tInt_WIN_eh_sjlj_longjmp",
  "VLD(1|2)LN(d|q)(WB_fixed_|WB_register_)?Asm",
  "VLD(3|4)(DUP|LN)?(d|q)(WB_fixed_|WB_register_)?Asm",
  "VST(1|2)LN(d|q)(WB_fixed_|WB_register_)?Asm",
  "VST(3|4)(DUP|LN)?(d|q)(WB_fixed_|WB_register_)?Asm",
  "WIN__CHKSTK", "WIN__DBZCHK")>;

// Miscellaneous
// -----------------------------------------------------------------------------

def : InstRW<[A57Write_1cyc_1I], (instrs COPY)>;

// --- 3.2 Branch Instructions ---
// B, BX, BL, BLX (imm, reg != LR, reg == LR), CBZ, CBNZ

def : InstRW<[A57Write_1cyc_1B], (instregex "(t2|t)?B$", "t?BX", "(t2|t)?Bcc$",
  "t?TAILJMP(d|r)", "TCRETURN(d|r)i", "tBfar", "tCBN?Z")>;
def : InstRW<[A57Write_1cyc_1B_1I],
  (instregex "t?BL$", "BL_pred$", "t?BLXi", "t?TPsoft")>;
def : InstRW<[A57Write_2cyc_1B_1I], (instregex "BLX", "tBLX(NS)?r")>;
// Pseudos
def : InstRW<[A57Write_2cyc_1B_1I], (instregex "BCCi64", "BCCZi64")>;
def : InstRW<[A57Write_3cyc_1B_1I], (instregex "BR_JTadd", "t?BR_JTr",
  "t2BR_JT", "t2BXJ", "(t2)?TB(B|H)(_JT)?$", "tBRIND")>;
def : InstRW<[A57Write_6cyc_1B_1L], (instregex "BR_JTm")>;

// --- 3.3 Arithmetic and Logical Instructions ---
// ADD{S}, ADC{S}, ADR,	AND{S},	BIC{S},	CMN, CMP, EOR{S}, ORN{S}, ORR{S},
// RSB{S}, RSC{S}, SUB{S}, SBC{S}, TEQ, TST

def : InstRW<[A57Write_1cyc_1I], (instregex "tADDframe")>;

// Check branch forms of ALU ops:
// check reg 0 for ARM_AM::PC
// if so adds 2 cyc to latency, 1 uop, 1 res cycle for A57UnitB
class A57BranchForm<SchedWriteRes non_br> :
  BranchWriteRes<2, 1, [A57UnitB], [1], non_br>;

// shift by register, conditional or unconditional
// TODO: according to the doc, conditional uses I0/I1, unconditional uses M
// Why more complex instruction uses more simple pipeline?
// May be an error in doc.
def A57WriteALUsr : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [CheckBranchForm<0, A57BranchForm<A57Write_2cyc_1I>>]>,
  SchedVar<NoSchedPred,      [CheckBranchForm<0, A57BranchForm<A57Write_2cyc_1M>>]>
]>;
def A57WriteALUSsr : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [CheckBranchForm<0, A57BranchForm<A57Write_2cyc_1I>>]>,
  SchedVar<NoSchedPred,      [CheckBranchForm<0, A57BranchForm<A57Write_2cyc_1M>>]>
]>;
def A57ReadALUsr : SchedReadVariant<[
  SchedVar<IsPredicatedPred, [ReadDefault]>,
  SchedVar<NoSchedPred,      [ReadDefault]>
]>;
def : SchedAlias<WriteALUsi,  CheckBranchForm<0, A57BranchForm<A57Write_2cyc_1M>>>;
def : SchedAlias<WriteALUsr,  A57WriteALUsr>;
def : SchedAlias<WriteALUSsr, A57WriteALUSsr>;
def : SchedAlias<ReadALUsr,   A57ReadALUsr>;

def A57WriteCMPsr : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57Write_2cyc_1I]>,
  SchedVar<NoSchedPred,      [A57Write_2cyc_1M]>
]>;
def : SchedAlias<WriteCMP,   A57Write_1cyc_1I>;
def : SchedAlias<WriteCMPsi, A57Write_2cyc_1M>;
def : SchedAlias<WriteCMPsr, A57WriteCMPsr>;

// --- 3.4 Move and Shift Instructions ---
// Move, basic
// MOV{S}, MOVW, MVN{S}
def : InstRW<[A57Write_1cyc_1I], (instregex "MOV(r|i|i16|r_TC)",
  "(t2)?MVN(CC)?(r|i)", "BMOVPCB_CALL", "BMOVPCRX_CALL",
  "MOVCC(r|i|i16|i32imm)", "tMOV", "tMVN")>;

// Move, shift by immed, setflags/no setflags
// (ASR, LSL, LSR, ROR, RRX)=MOVsi, MVN
// setflags = isCPSRDefined
def A57WriteMOVsi : SchedWriteVariant<[
  SchedVar<IsCPSRDefinedPred,              [A57Write_2cyc_1M]>,
  SchedVar<NoSchedPred,                    [A57Write_1cyc_1I]>
]>;
def : InstRW<[A57WriteMOVsi], (instregex "MOV(CC)?si", "MVNsi",
  "ASRi", "(t2|t)ASRri", "LSRi", "(t2|t)LSRri", "LSLi", "(t2|t)LSLri", "RORi",
  "(t2|t)RORri", "(t2)?RRX", "t2MOV", "tROR")>;

// shift by register, conditional or unconditional, setflags/no setflags
def A57WriteMOVsr : SchedWriteVariant<[
  SchedVar<IsCPSRDefinedAndPredicatedPred, [A57Write_2cyc_1I]>,
  SchedVar<IsCPSRDefinedPred,              [A57Write_2cyc_1M]>,
  SchedVar<IsPredicatedPred,               [A57Write_2cyc_1I]>,
  SchedVar<NoSchedPred,                    [A57Write_1cyc_1I]>
]>;
def : InstRW<[A57WriteMOVsr], (instregex "MOV(CC)?sr", "MVNsr", "t2MVNs",
  "ASRr", "(t2|t)ASRrr", "LSRr", "(t2|t)LSRrr", "LSLr", "(t2|t)?LSLrr", "RORr",
  "(t2|t)RORrr")>;

// Move, top
// MOVT - A57Write_2cyc_1M for r0px, A57Write_1cyc_1I for r1p0 and later
def A57WriteMOVT : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred,             [A57Write_1cyc_1I]>,
  SchedVar<NoSchedPred,                    [A57Write_2cyc_1M]>
]>;
def : InstRW<[A57WriteMOVT], (instregex "MOVTi16")>;

def A57WriteI2pc :
  WriteSequence<[A57Write_1cyc_1I, A57Write_1cyc_1I, A57Write_1cyc_1I]>;
def A57WriteI2ld :
  WriteSequence<[A57Write_1cyc_1I, A57Write_1cyc_1I, A57Write_4cyc_1L]>;
def : InstRW< [A57WriteI2pc], (instregex "MOV_ga_pcrel")>;
def : InstRW< [A57WriteI2ld], (instregex "MOV_ga_pcrel_ldr")>;

// +2cyc for branch forms
def : InstRW<[A57Write_3cyc_1I], (instregex "MOVPC(LR|RX)")>;

// --- 3.5 Divide and Multiply Instructions ---
// Divide: SDIV, UDIV
// latency from documentration: 4 ­‐ 20, maximum taken
def : SchedAlias<WriteDIV, A57Write_20cyc_1M>;
// Multiply: tMul not bound to common WriteRes types
def : InstRW<[A57Write_3cyc_1M], (instregex "tMUL")>;
def : SchedAlias<WriteMUL16, A57Write_3cyc_1M>;
def : SchedAlias<WriteMUL32, A57Write_3cyc_1M>;
def : ReadAdvance<ReadMUL, 0>;

// Multiply accumulate: MLA, MLS, SMLABB, SMLABT, SMLATB, SMLATT, SMLAWB,
// SMLAWT, SMLAD{X}, SMLSD{X}, SMMLA{R}, SMMLS{R}
// Multiply-accumulate pipelines support late-forwarding of accumulate operands
// from similar μops, allowing a typical sequence of multiply-accumulate μops
// to issue one every 1 cycle (sched advance = 2).
def A57WriteMLA : SchedWriteRes<[A57UnitM]> { let Latency = 3; }
def A57WriteMLAL : SchedWriteVariant<[
  SchedVar<IsCPSRDefinedPred, [A57Write_5cyc_1I_1M]>,
  SchedVar<NoSchedPred,       [A57Write_4cyc_1M]>
]>;

def A57ReadMLA  : SchedReadAdvance<2, [A57WriteMLA, A57WriteMLAL]>;

def : InstRW<[A57WriteMLA],
  (instregex "t2SMLAD", "t2SMLADX", "t2SMLSD", "t2SMLSDX")>;

def : SchedAlias<WriteMAC16, A57WriteMLA>;
def : SchedAlias<WriteMAC32, A57WriteMLA>;
def : SchedAlias<ReadMAC,    A57ReadMLA>;

def : SchedAlias<WriteMAC64Lo, A57WriteMLAL>;
def : SchedAlias<WriteMAC64Hi, A57WriteMLAL>;

// Multiply long: SMULL, UMULL
def : SchedAlias<WriteMUL64Lo, A57Write_4cyc_1M>;
def : SchedAlias<WriteMUL64Hi, A57Write_4cyc_1M>;

// --- 3.6 Saturating and Parallel Arithmetic Instructions ---
// Parallel	arith
// SADD16, SADD8, SSUB16, SSUB8, UADD16, UADD8, USUB16, USUB8
// Conditional GE-setting instructions require three extra μops
// and two additional cycles to conditionally update the GE field.
def A57WriteParArith : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57Write_4cyc_1I_1M]>,
  SchedVar<NoSchedPred,      [A57Write_2cyc_1I_1M]>
]>;
def : InstRW< [A57WriteParArith], (instregex
  "(t2)?SADD(16|8)", "(t2)?SSUB(16|8)",
  "(t2)?UADD(16|8)", "(t2)?USUB(16|8)")>;

// Parallel	arith with exchange: SASX, SSAX, UASX, USAX
def A57WriteParArithExch : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57Write_5cyc_1I_1M]>,
  SchedVar<NoSchedPred,      [A57Write_3cyc_1I_1M]>
]>;
def : InstRW<[A57WriteParArithExch],
  (instregex "(t2)?SASX", "(t2)?SSAX", "(t2)?UASX", "(t2)?USAX")>;

// Parallel	halving	arith
// SHADD16, SHADD8, SHSUB16, SHSUB8, UHADD16, UHADD8, UHSUB16,	UHSUB8
def : InstRW<[A57Write_2cyc_1M], (instregex
  "(t2)?SHADD(16|8)", "(t2)?SHSUB(16|8)",
  "(t2)?UHADD(16|8)", "(t2)?UHSUB(16|8)")>;

// Parallel halving arith with exchange
// SHASX, SHSAX, UHASX, UHSAX
def : InstRW<[A57Write_3cyc_1I_1M], (instregex "(t2)?SHASX", "(t2)?SHSAX",
  "(t2)?UHASX", "(t2)?UHSAX")>;

// Parallel	saturating arith
// QADD16, QADD8, QSUB16, QSUB8, UQADD16, UQADD8, UQSUB16, UQSUB8
def : InstRW<[A57Write_2cyc_1M], (instregex "QADD(16|8)", "QSUB(16|8)",
  "UQADD(16|8)", "UQSUB(16|8)", "t2(U?)QADD", "t2(U?)QSUB")>;

// Parallel	saturating arith with exchange
// QASX, QSAX, UQASX, UQSAX
def : InstRW<[A57Write_3cyc_1I_1M], (instregex "(t2)?QASX", "(t2)?QSAX",
  "(t2)?UQASX", "(t2)?UQSAX")>;

// Saturate: SSAT, SSAT16, USAT, USAT16
def : InstRW<[A57Write_2cyc_1M],
  (instregex "(t2)?SSAT(16)?", "(t2)?USAT(16)?")>;

// Saturating arith: QADD, QSUB
def : InstRW<[A57Write_2cyc_1M], (instregex "QADD$", "QSUB$")>;

// Saturating doubling arith: QDADD, QDSUB
def : InstRW<[A57Write_3cyc_1I_1M], (instregex "(t2)?QDADD", "(t2)?QDSUB")>;

// --- 3.7 Miscellaneous Data-Processing Instructions ---
// Bit field extract: SBFX, UBFX
def : InstRW<[A57Write_1cyc_1I], (instregex "(t2)?SBFX", "(t2)?UBFX")>;

// Bit field insert/clear: BFI, BFC
def : InstRW<[A57Write_2cyc_1M], (instregex "(t2)?BFI", "(t2)?BFC")>;

// Select bytes, conditional/unconditional
def A57WriteSEL : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57Write_2cyc_1I]>,
  SchedVar<NoSchedPred,      [A57Write_1cyc_1I]>
]>;
def : InstRW<[A57WriteSEL], (instregex "(t2)?SEL")>;

// Sign/zero extend, normal: SXTB, SXTH, UXTB, UXTH
def : InstRW<[A57Write_1cyc_1I],
  (instregex "(t2|t)?SXT(B|H)$", "(t2|t)?UXT(B|H)$")>;

// Sign/zero extend and add, normal: SXTAB, SXTAH, UXTAB, UXTAH
def : InstRW<[A57Write_2cyc_1M],
  (instregex "(t2)?SXTA(B|H)$", "(t2)?UXTA(B|H)$")>;

// Sign/zero extend and add, parallel: SXTAB16, UXTAB16
def : InstRW<[A57Write_4cyc_1M], (instregex "(t2)?SXTAB16", "(t2)?UXTAB16")>;

// Sum of absolute differences: USAD8, USADA8
def : InstRW<[A57Write_3cyc_1M], (instregex "(t2)?USAD8", "(t2)?USADA8")>;

// --- 3.8 Load Instructions ---

// Load, immed offset
// LDR and LDRB have LDRi12 and LDRBi12 forms for immediate
def : InstRW<[A57Write_4cyc_1L], (instregex "LDRi12", "LDRBi12",
  "LDRcp", "(t2|t)?LDRConstPool", "LDRLIT_ga_(pcrel|abs)",
  "PICLDR", "tLDR")>;

def : InstRW<[A57Write_4cyc_1L],
  (instregex "t2LDRS?(B|H)?(pcrel|T|i8|i12|pci|pci_pic|s)?$")>;

// For "Load, register offset, minus" we need +1cyc, +1I
def A57WriteLdrAm3 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPred, [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,           [A57Write_4cyc_1L]>
]>;
def : InstRW<[A57WriteLdrAm3], (instregex "LDR(H|SH|SB)$")>;
def A57WriteLdrAm3X2 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX2, [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,             [A57Write_4cyc_1L]>
]>;
def : InstRW<[A57WriteLdrAm3X2, A57WriteLdrAm3X2], (instregex "LDRD$")>;
def : InstRW<[A57Write_4cyc_1L, A57Write_4cyc_1L], (instregex "t2LDRDi8")>;

def A57WriteLdrAmLDSTSO : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledNotOptimalPred, [A57Write_5cyc_1I_1L]>,
  SchedVar<IsLdstsoMinusRegPred,         [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,                  [A57Write_4cyc_1L]>
]>;
def : InstRW<[A57WriteLdrAmLDSTSO], (instregex "LDRrs", "LDRBrs")>;

def A57WrBackOne : SchedWriteRes<[]> {
  let Latency = 1;
  let NumMicroOps = 0;
}
def A57WrBackTwo : SchedWriteRes<[]> {
  let Latency = 2;
  let NumMicroOps = 0;
}
def A57WrBackThree : SchedWriteRes<[]> {
  let Latency = 3;
  let NumMicroOps = 0;
}

// --- LDR pre-indexed ---
// Load, immed pre-indexed (4 cyc for load result, 1 cyc for Base update)
def : InstRW<[A57Write_4cyc_1L_1I, A57WrBackOne], (instregex "LDR_PRE_IMM",
  "LDRB_PRE_IMM", "t2LDRB_PRE")>;

// Load, register pre-indexed (4 cyc for load result, 2 cyc for Base update)
// (5 cyc load result for not-lsl2 scaled)
def A57WriteLdrAmLDSTSOPre : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledNotOptimalPredX2, [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,                    [A57Write_4cyc_1L_1I]>
]>;
def : InstRW<[A57WriteLdrAmLDSTSOPre, A57WrBackTwo],
  (instregex "LDR_PRE_REG", "LDRB_PRE_REG")>;

def A57WriteLdrAm3PreWrBack : SchedWriteVariant<[
  SchedVar<IsLdrAm3RegOffPredX2, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,          [A57WrBackOne]>
]>;
def : InstRW<[A57Write_4cyc_1L, A57WriteLdrAm3PreWrBack],
  (instregex "LDR(H|SH|SB)_PRE")>;
def : InstRW<[A57Write_4cyc_1L, A57WrBackOne],
  (instregex "t2LDR(H|SH|SB)?_PRE")>;

// LDRD pre-indexed: 5(2) cyc for reg, 4(1) cyc for imm.
def A57WriteLdrDAm3Pre : SchedWriteVariant<[
  SchedVar<IsLdrAm3RegOffPredX3, [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,          [A57Write_4cyc_1L_1I]>
]>;
def A57WriteLdrDAm3PreWrBack : SchedWriteVariant<[
  SchedVar<IsLdrAm3RegOffPredX3, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,          [A57WrBackOne]>
]>;
def : InstRW<[A57WriteLdrDAm3Pre, A57WriteLdrDAm3Pre, A57WriteLdrDAm3PreWrBack],
  (instregex "LDRD_PRE")>;
def : InstRW<[A57Write_4cyc_1L_1I, A57Write_4cyc_1L_1I, A57WrBackOne],
  (instregex "t2LDRD_PRE")>;

// --- LDR post-indexed ---
def : InstRW<[A57Write_4cyc_1L_1I, A57WrBackOne], (instregex "LDR(T?)_POST_IMM",
  "LDRB(T?)_POST_IMM", "LDR(SB|H|SH)Ti", "t2LDRB_POST")>;

def A57WriteLdrAm3PostWrBack : SchedWriteVariant<[
  SchedVar<IsLdrAm3RegOffPred, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,        [A57WrBackOne]>
]>;
def : InstRW<[A57Write_4cyc_1L_1I, A57WriteLdrAm3PostWrBack],
  (instregex "LDR(H|SH|SB)_POST")>;
def : InstRW<[A57Write_4cyc_1L, A57WrBackOne],
  (instregex "t2LDR(H|SH|SB)?_POST")>;

def : InstRW<[A57Write_4cyc_1L_1I, A57WrBackTwo], (instregex "LDR_POST_REG",
  "LDRB_POST_REG", "LDR(B?)T_POST$")>;

def A57WriteLdrTRegPost : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledPredX2, [A57Write_4cyc_1I_1L_1M]>,
  SchedVar<NoSchedPred,        [A57Write_4cyc_1L_1I]>
]>;
def A57WriteLdrTRegPostWrBack : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledPredX2, [A57WrBackThree]>,
  SchedVar<NoSchedPred,        [A57WrBackTwo]>
]>;
// 4(3) "I0/I1,L,M" for scaled register, otherwise 4(2) "I0/I1,L"
def : InstRW<[A57WriteLdrTRegPost, A57WriteLdrTRegPostWrBack],
  (instregex "LDRT_POST_REG", "LDRBT_POST_REG")>;

def : InstRW<[A57Write_4cyc_1L_1I, A57WrBackTwo], (instregex "LDR(SB|H|SH)Tr")>;

def A57WriteLdrAm3PostWrBackX3 : SchedWriteVariant<[
  SchedVar<IsLdrAm3RegOffPredX3, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,          [A57WrBackOne]>
]>;
// LDRD post-indexed: 4(2) cyc for reg, 4(1) cyc for imm.
def : InstRW<[A57Write_4cyc_1L_1I, A57Write_4cyc_1L_1I,
  A57WriteLdrAm3PostWrBackX3], (instregex "LDRD_POST")>;
def : InstRW<[A57Write_4cyc_1L_1I, A57Write_4cyc_1L_1I, A57WrBackOne],
  (instregex "t2LDRD_POST")>;

// --- Preload instructions ---
// Preload, immed offset
def : InstRW<[A57Write_4cyc_1L], (instregex "(t2)?PLDi12", "(t2)?PLDWi12",
  "t2PLDW?(i8|pci|s)", "(t2)?PLI")>;

// Preload, register offset,
// 5cyc "I0/I1,L" for minus reg or scaled not plus lsl2
// otherwise 4cyc "L"
def A57WritePLD : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledNotOptimalPredX0, [A57Write_5cyc_1I_1L]>,
  SchedVar<IsLdstsoMinusRegPredX0,         [A57Write_5cyc_1I_1L]>,
  SchedVar<NoSchedPred,                    [A57Write_4cyc_1L]>
]>;
def : InstRW<[A57WritePLD], (instregex "PLDrs", "PLDWrs")>;

// --- Load multiple instructions ---
foreach NumAddr = 1-8 in {
  def A57LMAddrPred#NumAddr : MCSchedPredicate<CheckAny<[
                                CheckNumOperands<!add(!shl(NumAddr, 1), 2)>,
                                CheckNumOperands<!add(!shl(NumAddr, 1), 3)>]>>;
  def A57LMAddrUpdPred#NumAddr : MCSchedPredicate<CheckAny<[
                                   CheckNumOperands<!add(!shl(NumAddr, 1), 3)>,
                                   CheckNumOperands<!add(!shl(NumAddr, 1), 4)>]>>;
}

def A57LDMOpsListNoregin : A57WriteLMOpsListType<
                [A57Write_3cyc_1L, A57Write_3cyc_1L,
                 A57Write_4cyc_1L, A57Write_4cyc_1L,
                 A57Write_5cyc_1L, A57Write_5cyc_1L,
                 A57Write_6cyc_1L, A57Write_6cyc_1L,
                 A57Write_7cyc_1L, A57Write_7cyc_1L,
                 A57Write_8cyc_1L, A57Write_8cyc_1L,
                 A57Write_9cyc_1L, A57Write_9cyc_1L,
                 A57Write_10cyc_1L, A57Write_10cyc_1L]>;
def A57WriteLDMnoreginlist : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,     A57LDMOpsListNoregin.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,     A57LDMOpsListNoregin.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,     A57LDMOpsListNoregin.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,     A57LDMOpsListNoregin.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,     A57LDMOpsListNoregin.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,     A57LDMOpsListNoregin.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,     A57LDMOpsListNoregin.Writes[0-13]>,
  SchedVar<A57LMAddrPred8,     A57LDMOpsListNoregin.Writes[0-15]>,
  SchedVar<NoSchedPred,        A57LDMOpsListNoregin.Writes[0-15]>
]> { let Variadic=1; }

def A57LDMOpsListRegin : A57WriteLMOpsListType<
                [A57Write_4cyc_1L_1I, A57Write_4cyc_1L_1I,
                 A57Write_5cyc_1L_1I, A57Write_5cyc_1L_1I,
                 A57Write_6cyc_1L_1I, A57Write_6cyc_1L_1I,
                 A57Write_7cyc_1L_1I, A57Write_7cyc_1L_1I,
                 A57Write_8cyc_1L_1I, A57Write_8cyc_1L_1I,
                 A57Write_9cyc_1L_1I, A57Write_9cyc_1L_1I,
                 A57Write_10cyc_1L_1I, A57Write_10cyc_1L_1I,
                 A57Write_11cyc_1L_1I, A57Write_11cyc_1L_1I]>;
def A57WriteLDMreginlist : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,     A57LDMOpsListRegin.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,     A57LDMOpsListRegin.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,     A57LDMOpsListRegin.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,     A57LDMOpsListRegin.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,     A57LDMOpsListRegin.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,     A57LDMOpsListRegin.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,     A57LDMOpsListRegin.Writes[0-13]>,
  SchedVar<A57LMAddrPred8,     A57LDMOpsListRegin.Writes[0-15]>,
  SchedVar<NoSchedPred,        A57LDMOpsListRegin.Writes[0-15]>
]> { let Variadic=1; }

def A57LDMOpsList_Upd : A57WriteLMOpsListType<
              [A57WrBackOne,
               A57Write_3cyc_1L_1I, A57Write_3cyc_1L_1I,
               A57Write_4cyc_1L_1I, A57Write_4cyc_1L_1I,
               A57Write_5cyc_1L_1I, A57Write_5cyc_1L_1I,
               A57Write_6cyc_1L_1I, A57Write_6cyc_1L_1I,
               A57Write_7cyc_1L_1I, A57Write_7cyc_1L_1I,
               A57Write_8cyc_1L_1I, A57Write_8cyc_1L_1I,
               A57Write_9cyc_1L_1I, A57Write_9cyc_1L_1I,
               A57Write_10cyc_1L_1I, A57Write_10cyc_1L_1I]>;
def A57WriteLDM_Upd : SchedWriteVariant<[
  SchedVar<A57LMAddrUpdPred1,     A57LDMOpsList_Upd.Writes[0-2]>,
  SchedVar<A57LMAddrUpdPred2,     A57LDMOpsList_Upd.Writes[0-4]>,
  SchedVar<A57LMAddrUpdPred3,     A57LDMOpsList_Upd.Writes[0-6]>,
  SchedVar<A57LMAddrUpdPred4,     A57LDMOpsList_Upd.Writes[0-8]>,
  SchedVar<A57LMAddrUpdPred5,     A57LDMOpsList_Upd.Writes[0-10]>,
  SchedVar<A57LMAddrUpdPred6,     A57LDMOpsList_Upd.Writes[0-12]>,
  SchedVar<A57LMAddrUpdPred7,     A57LDMOpsList_Upd.Writes[0-14]>,
  SchedVar<A57LMAddrUpdPred8,     A57LDMOpsList_Upd.Writes[0-16]>,
  SchedVar<NoSchedPred,           A57LDMOpsList_Upd.Writes[0-16]>
]> { let Variadic=1; }

def A57WriteLDM : SchedWriteVariant<[
  SchedVar<IsLDMBaseRegInListPred, [A57WriteLDMreginlist]>,
  SchedVar<NoSchedPred,            [A57WriteLDMnoreginlist]>
]> { let Variadic=1; }

def : InstRW<[A57WriteLDM], (instregex "(t|t2|sys)?LDM(IA|DA|DB|IB)$")>;

// TODO: no writeback latency defined in documentation (implemented as 1 cyc)
def : InstRW<[A57WriteLDM_Upd],
  (instregex "(t|t2|sys)?LDM(IA_UPD|DA_UPD|DB_UPD|IB_UPD|IA_RET)", "tPOP")>;

def : InstRW<[A57Write_5cyc_1L], (instregex "VLLDM")>;

// --- 3.9 Store Instructions ---

// Store, immed offset
def : InstRW<[A57Write_1cyc_1S], (instregex "STRi12", "STRBi12", "PICSTR",
  "t2STR(B?)(T|i12|i8|s)", "t2STRDi8", "t2STRH(i12|i8|s)", "tSTR")>;

// Store, register offset
// For minus or for not plus lsl2 scaled we need 3cyc "I0/I1, S",
// otherwise 1cyc S.
def A57WriteStrAmLDSTSO : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledNotOptimalPred, [A57Write_3cyc_1I_1S]>,
  SchedVar<IsLdstsoMinusRegPred,         [A57Write_3cyc_1I_1S]>,
  SchedVar<NoSchedPred,                  [A57Write_1cyc_1S]>
]>;
def : InstRW<[A57WriteStrAmLDSTSO], (instregex "STRrs", "STRBrs")>;

// STRH,STRD: 3cyc "I0/I1, S" for minus reg, 1cyc S for imm or for plus reg.
def A57WriteStrAm3 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPred, [A57Write_3cyc_1I_1S]>,
  SchedVar<NoSchedPred,           [A57Write_1cyc_1S]>
]>;
def : InstRW<[A57WriteStrAm3], (instregex "STRH$")>;
def A57WriteStrAm3X2 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX2, [A57Write_3cyc_1I_1S]>,
  SchedVar<NoSchedPred,             [A57Write_1cyc_1S]>
]>;
def : InstRW<[A57WriteStrAm3X2], (instregex "STRD$")>;

// Store, immed pre-indexed (1cyc "S, I0/I1", 1cyc writeback)
def : InstRW<[A57WrBackOne, A57Write_1cyc_1S_1I], (instregex "STR_PRE_IMM",
  "STRB_PRE_IMM", "STR(B)?(r|i)_preidx", "(t2)?STRH_(preidx|PRE)",
  "t2STR(B?)_(PRE|preidx)", "t2STRD_PRE")>;

// Store, register pre-indexed:
// 1(1) "S, I0/I1" for plus reg
// 3(2) "I0/I1, S" for minus reg
// 1(2) "S, M" for scaled plus lsl2
// 3(2) "I0/I1, S" for other scaled
def A57WriteStrAmLDSTSOPre : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledNotOptimalPredX2, [A57Write_3cyc_1I_1S]>,
  SchedVar<IsLdstsoMinusRegPredX2,         [A57Write_3cyc_1I_1S]>,
  SchedVar<IsLdstsoScaledPredX2,           [A57Write_1cyc_1S_1M]>,
  SchedVar<NoSchedPred,                    [A57Write_1cyc_1S_1I]>
]>;
def A57WriteStrAmLDSTSOPreWrBack : SchedWriteVariant<[
  SchedVar<IsLdstsoScaledPredX2,           [A57WrBackTwo]>,
  SchedVar<IsLdstsoMinusRegPredX2,         [A57WrBackTwo]>,
  SchedVar<NoSchedPred,                    [A57WrBackOne]>
]>;
def : InstRW<[A57WriteStrAmLDSTSOPreWrBack, A57WriteStrAmLDSTSOPre],
  (instregex "STR_PRE_REG", "STRB_PRE_REG")>;

// pre-indexed STRH/STRD (STRH_PRE, STRD_PRE)
// 1(1) "S, I0/I1" for imm or reg plus
// 3(2) "I0/I1, S" for reg minus
def A57WriteStrAm3PreX2 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX2, [A57Write_3cyc_1I_1S]>,
  SchedVar<NoSchedPred,             [A57Write_1cyc_1S_1I]>
]>;
def A57WriteStrAm3PreWrBackX2 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX2, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,             [A57WrBackOne]>
]>;
def : InstRW<[A57WriteStrAm3PreWrBackX2, A57WriteStrAm3PreX2],
  (instregex "STRH_PRE")>;

def A57WriteStrAm3PreX3 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX3, [A57Write_3cyc_1I_1S]>,
  SchedVar<NoSchedPred,             [A57Write_1cyc_1S_1I]>
]>;
def A57WriteStrAm3PreWrBackX3 : SchedWriteVariant<[
  SchedVar<IsLdrAm3NegRegOffPredX3, [A57WrBackTwo]>,
  SchedVar<NoSchedPred,             [A57WrBackOne]>
]>;
def : InstRW<[A57WriteStrAm3PreWrBackX3, A57WriteStrAm3PreX3],
  (instregex "STRD_PRE")>;

def : InstRW<[A57WrBackOne, A57Write_1cyc_1S_1I], (instregex "STR(T?)_POST_IMM",
  "STRB(T?)_POST_IMM", "t2STR(B?)_POST")>;

// 1(2) "S, M" for STR/STRB register post-indexed (both scaled or not)
def : InstRW<[A57WrBackTwo, A57Write_1cyc_1S_1M], (instregex "STR(T?)_POST_REG",
  "STRB(T?)_POST_REG", "STR(B?)T_POST$")>;

// post-indexed STRH/STRD(STRH_POST, STRD_POST), STRHTi, STRHTr
// 1(1) "S, I0/I1" both for reg or imm
def : InstRW<[A57WrBackOne, A57Write_1cyc_1S_1I],
  (instregex "(t2)?STR(H|D)_POST", "STRHT(i|r)", "t2STRHT")>;

// --- Store multiple instructions ---
// TODO: no writeback latency defined in documentation
def A57WriteSTM : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_1cyc_1S]>,
    SchedVar<A57LMAddrPred2, [A57Write_2cyc_1S]>,
    SchedVar<A57LMAddrPred3, [A57Write_3cyc_1S]>,
    SchedVar<A57LMAddrPred4, [A57Write_4cyc_1S]>,
    SchedVar<A57LMAddrPred5, [A57Write_5cyc_1S]>,
    SchedVar<A57LMAddrPred6, [A57Write_6cyc_1S]>,
    SchedVar<A57LMAddrPred7, [A57Write_7cyc_1S]>,
    SchedVar<A57LMAddrPred8, [A57Write_8cyc_1S]>,
    SchedVar<NoSchedPred,    [A57Write_2cyc_1S]>
]>;
def A57WriteSTM_Upd : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_1cyc_1S_1I]>,
    SchedVar<A57LMAddrPred2, [A57Write_2cyc_1S_1I]>,
    SchedVar<A57LMAddrPred3, [A57Write_3cyc_1S_1I]>,
    SchedVar<A57LMAddrPred4, [A57Write_4cyc_1S_1I]>,
    SchedVar<A57LMAddrPred5, [A57Write_5cyc_1S_1I]>,
    SchedVar<A57LMAddrPred6, [A57Write_6cyc_1S_1I]>,
    SchedVar<A57LMAddrPred7, [A57Write_7cyc_1S_1I]>,
    SchedVar<A57LMAddrPred8, [A57Write_8cyc_1S_1I]>,
    SchedVar<NoSchedPred,    [A57Write_2cyc_1S_1I]>
]>;

def : InstRW<[A57WriteSTM], (instregex "(t2|sys|t)?STM(IA|DA|DB|IB)$")>;
def : InstRW<[A57WrBackOne, A57WriteSTM_Upd],
  (instregex "(t2|sys|t)?STM(IA_UPD|DA_UPD|DB_UPD|IB_UPD)", "tPUSH")>;

def : InstRW<[A57Write_5cyc_1S], (instregex "VLSTM")>;

// --- 3.10 FP Data Processing Instructions ---
def : SchedAlias<WriteFPALU32, A57Write_5cyc_1V>;
def : SchedAlias<WriteFPALU64, A57Write_5cyc_1V>;

def : InstRW<[A57Write_3cyc_1V], (instregex "VABS(S|D|H)")>;

// fp compare - 3cyc F1 for unconditional, 6cyc "F0/F1, F1" for conditional
def A57WriteVcmp : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57Write_6cyc_1V_1X]>,
  SchedVar<NoSchedPred,      [A57Write_3cyc_1X]>
]>;
def : InstRW<[A57WriteVcmp],
  (instregex "VCMP(D|S|H|ZD|ZS|ZH)$", "VCMPE(D|S|H|ZD|ZS|ZH)")>;

// fp convert
def : InstRW<[A57Write_5cyc_1V], (instregex
  "VCVT(A|N|P|M)(SH|UH|SS|US|SD|UD)", "VCVT(BDH|THD|TDH)")>;
def : InstRW<[A57Write_5cyc_1V], (instregex "VTOSLS", "VTOUHS", "VTOULS")>;
def : SchedAlias<WriteFPCVT, A57Write_5cyc_1V>;

def : InstRW<[A57Write_5cyc_1V], (instregex "VJCVT")>;

// FP round to integral
def : InstRW<[A57Write_5cyc_1V], (instregex "VRINT(A|N|P|M|Z|R|X)(H|S|D)$")>;

// FP divide, FP square root
def : SchedAlias<WriteFPDIV32, A57Write_17cyc_1W>;
def : SchedAlias<WriteFPDIV64, A57Write_32cyc_1W>;
def : SchedAlias<WriteFPSQRT32, A57Write_17cyc_1W>;
def : SchedAlias<WriteFPSQRT64, A57Write_32cyc_1W>;

def : InstRW<[A57Write_17cyc_1W], (instregex "VSQRTH")>;

// FP max/min
def : InstRW<[A57Write_5cyc_1V], (instregex "VMAX", "VMIN")>;

// FP multiply-accumulate pipelines support late forwarding of the result
// from FP multiply μops to the accumulate operands of an
// FP multiply-accumulate μop. The latter can potentially be issued 1 cycle
// after the FP multiply μop has been issued
// FP multiply, FZ
def A57WriteVMUL : SchedWriteRes<[A57UnitV]> { let Latency = 5; }

def : SchedAlias<WriteFPMUL32, A57WriteVMUL>;
def : SchedAlias<WriteFPMUL64, A57WriteVMUL>;
def : ReadAdvance<ReadFPMUL, 0>;

// FP multiply accumulate, FZ: 9cyc "F0/F1" or 4 cyc for sequenced accumulate
// VFMA, VFMS, VFNMA, VFNMS, VMLA, VMLS, VNMLA, VNMLS
def A57WriteVFMA : SchedWriteRes<[A57UnitV]> { let Latency = 9;  }

// VFMA takes 9 cyc for common case and 4 cyc for VFMA->VFMA chain (5 read adv.)
// VMUL takes 5 cyc for common case and 1 cyc for VMUL->VFMA chain (4 read adv.)
// Currently, there is no way to define different read advances for VFMA operand
// from VFMA or from VMUL, so there will be 5 read advance.
// Zero latency (instead of one) for VMUL->VFMA shouldn't break something.
// The same situation with ASIMD VMUL/VFMA instructions
// def A57ReadVFMA : SchedRead;
// def : ReadAdvance<A57ReadVFMA, 5, [A57WriteVFMA]>;
// def : ReadAdvance<A57ReadVFMA, 4, [A57WriteVMUL]>;
def A57ReadVFMA5 : SchedReadAdvance<5, [A57WriteVFMA, A57WriteVMUL]>;

def : SchedAlias<WriteFPMAC32, A57WriteVFMA>;
def : SchedAlias<WriteFPMAC64, A57WriteVFMA>;
def : SchedAlias<ReadFPMAC, A57ReadVFMA5>;

// VMLAH/VMLSH are not binded to scheduling classes by default, so here custom:
def : InstRW<[A57WriteVFMA, A57ReadVFMA5, ReadFPMUL, ReadFPMUL],
  (instregex "VMLAH", "VMLSH", "VNMLAH", "VNMLSH")>;

def : InstRW<[A57WriteVMUL],
  (instregex "VUDOTD", "VSDOTD", "VUDOTQ", "VSDOTQ")>;

def : InstRW<[A57Write_3cyc_1V], (instregex "VNEG")>;
def : InstRW<[A57Write_3cyc_1V], (instregex "VSEL")>;

// --- 3.11 FP Miscellaneous Instructions ---
// VMOV: 3cyc "F0/F1" for imm/reg
def : InstRW<[A57Write_3cyc_1V], (instregex "FCONST(D|S|H)")>;
def : InstRW<[A57Write_3cyc_1V], (instregex "VMOV(D|S|H)(cc)?$")>;

def : InstRW<[A57Write_3cyc_1V], (instregex "VINSH")>;

// 5cyc L for FP transfer, vfp to core reg,
// 5cyc L for FP transfer, core reg to vfp
def : SchedAlias<WriteFPMOV, A57Write_5cyc_1L>;
// VMOVRRS/VMOVRRD in common code declared with one WriteFPMOV (instead of 2).
def : InstRW<[A57Write_5cyc_1L, A57Write_5cyc_1L], (instregex "VMOV(RRS|RRD)")>;

// 8cyc "L,F0/F1" for FP transfer, core reg to upper or lower half of vfp D-reg
def : InstRW<[A57Write_8cyc_1L_1I], (instregex "VMOVDRR")>;

// --- 3.12 FP Load Instructions ---
def : InstRW<[A57Write_5cyc_1L], (instregex "VLDR(D|S|H)")>;

def : InstRW<[A57Write_5cyc_1L], (instregex "VLDMQIA$")>;

// FP load multiple (VLDM)

def A57VLDMOpsListUncond : A57WriteLMOpsListType<
               [A57Write_5cyc_1L, A57Write_5cyc_1L,
                A57Write_6cyc_1L, A57Write_6cyc_1L,
                A57Write_7cyc_1L, A57Write_7cyc_1L,
                A57Write_8cyc_1L, A57Write_8cyc_1L,
                A57Write_9cyc_1L, A57Write_9cyc_1L,
                A57Write_10cyc_1L, A57Write_10cyc_1L,
                A57Write_11cyc_1L, A57Write_11cyc_1L,
                A57Write_12cyc_1L, A57Write_12cyc_1L]>;
def A57WriteVLDMuncond : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,  A57VLDMOpsListUncond.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,  A57VLDMOpsListUncond.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,  A57VLDMOpsListUncond.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,  A57VLDMOpsListUncond.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,  A57VLDMOpsListUncond.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,  A57VLDMOpsListUncond.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,  A57VLDMOpsListUncond.Writes[0-13]>,
  SchedVar<NoSchedPred,     A57VLDMOpsListUncond.Writes[0-15]>
]> { let Variadic=1; }

def A57VLDMOpsListCond : A57WriteLMOpsListType<
               [A57Write_5cyc_1L, A57Write_6cyc_1L,
                A57Write_7cyc_1L, A57Write_8cyc_1L,
                A57Write_9cyc_1L, A57Write_10cyc_1L,
                A57Write_11cyc_1L, A57Write_12cyc_1L,
                A57Write_13cyc_1L, A57Write_14cyc_1L,
                A57Write_15cyc_1L, A57Write_16cyc_1L,
                A57Write_17cyc_1L, A57Write_18cyc_1L,
                A57Write_19cyc_1L, A57Write_20cyc_1L]>;
def A57WriteVLDMcond : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,  A57VLDMOpsListCond.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,  A57VLDMOpsListCond.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,  A57VLDMOpsListCond.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,  A57VLDMOpsListCond.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,  A57VLDMOpsListCond.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,  A57VLDMOpsListCond.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,  A57VLDMOpsListCond.Writes[0-13]>,
  SchedVar<NoSchedPred,     A57VLDMOpsListCond.Writes[0-15]>
]> { let Variadic=1; }

def A57WriteVLDM : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57WriteVLDMcond]>,
  SchedVar<NoSchedPred,      [A57WriteVLDMuncond]>
]> { let Variadic=1; }

def : InstRW<[A57WriteVLDM], (instregex "VLDM(DIA|SIA)$")>;

def A57VLDMOpsListUncond_Upd : A57WriteLMOpsListType<
               [A57Write_5cyc_1L_1I, A57Write_5cyc_1L_1I,
                A57Write_6cyc_1L_1I, A57Write_6cyc_1L_1I,
                A57Write_7cyc_1L_1I, A57Write_7cyc_1L_1I,
                A57Write_8cyc_1L_1I, A57Write_8cyc_1L_1I,
                A57Write_9cyc_1L_1I, A57Write_9cyc_1L_1I,
                A57Write_10cyc_1L_1I, A57Write_10cyc_1L_1I,
                A57Write_11cyc_1L_1I, A57Write_11cyc_1L_1I,
                A57Write_12cyc_1L_1I, A57Write_12cyc_1L_1I]>;
def A57WriteVLDMuncond_UPD : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,  A57VLDMOpsListUncond_Upd.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,  A57VLDMOpsListUncond_Upd.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,  A57VLDMOpsListUncond_Upd.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,  A57VLDMOpsListUncond_Upd.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,  A57VLDMOpsListUncond_Upd.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,  A57VLDMOpsListUncond_Upd.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,  A57VLDMOpsListUncond_Upd.Writes[0-13]>,
  SchedVar<NoSchedPred,     A57VLDMOpsListUncond_Upd.Writes[0-15]>
]> { let Variadic=1; }

def A57VLDMOpsListCond_Upd : A57WriteLMOpsListType<
               [A57Write_5cyc_1L_1I, A57Write_6cyc_1L_1I,
                A57Write_7cyc_1L_1I, A57Write_8cyc_1L_1I,
                A57Write_9cyc_1L_1I, A57Write_10cyc_1L_1I,
                A57Write_11cyc_1L_1I, A57Write_12cyc_1L_1I,
                A57Write_13cyc_1L_1I, A57Write_14cyc_1L_1I,
                A57Write_15cyc_1L_1I, A57Write_16cyc_1L_1I,
                A57Write_17cyc_1L_1I, A57Write_18cyc_1L_1I,
                A57Write_19cyc_1L_1I, A57Write_20cyc_1L_1I]>;
def A57WriteVLDMcond_UPD : SchedWriteVariant<[
  SchedVar<A57LMAddrPred1,  A57VLDMOpsListCond_Upd.Writes[0-1]>,
  SchedVar<A57LMAddrPred2,  A57VLDMOpsListCond_Upd.Writes[0-3]>,
  SchedVar<A57LMAddrPred3,  A57VLDMOpsListCond_Upd.Writes[0-5]>,
  SchedVar<A57LMAddrPred4,  A57VLDMOpsListCond_Upd.Writes[0-7]>,
  SchedVar<A57LMAddrPred5,  A57VLDMOpsListCond_Upd.Writes[0-9]>,
  SchedVar<A57LMAddrPred6,  A57VLDMOpsListCond_Upd.Writes[0-11]>,
  SchedVar<A57LMAddrPred7,  A57VLDMOpsListCond_Upd.Writes[0-13]>,
  SchedVar<NoSchedPred,     A57VLDMOpsListCond_Upd.Writes[0-15]>
]> { let Variadic=1; }

def A57WriteVLDM_UPD : SchedWriteVariant<[
  SchedVar<IsPredicatedPred, [A57WriteVLDMcond_UPD]>,
  SchedVar<NoSchedPred,      [A57WriteVLDMuncond_UPD]>
]> { let Variadic=1; }

def : InstRW<[A57WrBackOne, A57WriteVLDM_UPD],
  (instregex "VLDM(DIA_UPD|DDB_UPD|SIA_UPD|SDB_UPD)")>;

// --- 3.13 FP Store Instructions ---
def : InstRW<[A57Write_1cyc_1S], (instregex "VSTR(D|S|H)")>;

def : InstRW<[A57Write_2cyc_1S], (instregex "VSTMQIA$")>;

def A57WriteVSTMs : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_1cyc_1S]>,
    SchedVar<A57LMAddrPred2, [A57Write_2cyc_1S]>,
    SchedVar<A57LMAddrPred3, [A57Write_3cyc_1S]>,
    SchedVar<A57LMAddrPred4, [A57Write_4cyc_1S]>,
    SchedVar<A57LMAddrPred5, [A57Write_5cyc_1S]>,
    SchedVar<A57LMAddrPred6, [A57Write_6cyc_1S]>,
    SchedVar<A57LMAddrPred7, [A57Write_7cyc_1S]>,
    SchedVar<A57LMAddrPred8, [A57Write_8cyc_1S]>,
    SchedVar<NoSchedPred,    [A57Write_2cyc_1S]>
]>;
def A57WriteVSTMd : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_2cyc_1S]>,
    SchedVar<A57LMAddrPred2, [A57Write_4cyc_1S]>,
    SchedVar<A57LMAddrPred3, [A57Write_6cyc_1S]>,
    SchedVar<A57LMAddrPred4, [A57Write_8cyc_1S]>,
    SchedVar<A57LMAddrPred5, [A57Write_10cyc_1S]>,
    SchedVar<A57LMAddrPred6, [A57Write_12cyc_1S]>,
    SchedVar<A57LMAddrPred7, [A57Write_14cyc_1S]>,
    SchedVar<A57LMAddrPred8, [A57Write_16cyc_1S]>,
    SchedVar<NoSchedPred,    [A57Write_4cyc_1S]>
]>;
def A57WriteVSTMs_Upd : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_1cyc_1S_1I]>,
    SchedVar<A57LMAddrPred2, [A57Write_2cyc_1S_1I]>,
    SchedVar<A57LMAddrPred3, [A57Write_3cyc_1S_1I]>,
    SchedVar<A57LMAddrPred4, [A57Write_4cyc_1S_1I]>,
    SchedVar<A57LMAddrPred5, [A57Write_5cyc_1S_1I]>,
    SchedVar<A57LMAddrPred6, [A57Write_6cyc_1S_1I]>,
    SchedVar<A57LMAddrPred7, [A57Write_7cyc_1S_1I]>,
    SchedVar<A57LMAddrPred8, [A57Write_8cyc_1S_1I]>,
    SchedVar<NoSchedPred,    [A57Write_2cyc_1S_1I]>
]>;
def A57WriteVSTMd_Upd : SchedWriteVariant<[
    SchedVar<A57LMAddrPred1, [A57Write_2cyc_1S_1I]>,
    SchedVar<A57LMAddrPred2, [A57Write_4cyc_1S_1I]>,
    SchedVar<A57LMAddrPred3, [A57Write_6cyc_1S_1I]>,
    SchedVar<A57LMAddrPred4, [A57Write_8cyc_1S_1I]>,
    SchedVar<A57LMAddrPred5, [A57Write_10cyc_1S_1I]>,
    SchedVar<A57LMAddrPred6, [A57Write_12cyc_1S_1I]>,
    SchedVar<A57LMAddrPred7, [A57Write_14cyc_1S_1I]>,
    SchedVar<A57LMAddrPred8, [A57Write_16cyc_1S_1I]>,
    SchedVar<NoSchedPred,    [A57Write_2cyc_1S_1I]>
]>;

def : InstRW<[A57WriteVSTMs], (instregex "VSTMSIA$")>;
def : InstRW<[A57WriteVSTMd], (instregex "VSTMDIA$")>;
def : InstRW<[A57WrBackOne, A57WriteVSTMs_Upd],
  (instregex "VSTM(SIA_UPD|SDB_UPD)")>;
def : InstRW<[A57WrBackOne, A57WriteVSTMd_Upd],
  (instregex "VSTM(DIA_UPD|DDB_UPD)")>;

// --- 3.14 ASIMD Integer Instructions ---

// ASIMD absolute diff, 3cyc F0/F1 for integer VABD
def : InstRW<[A57Write_3cyc_1V], (instregex "VABD(s|u)")>;

// ASIMD absolute diff accum: 4(1) F1 for D-form, 5(2) F1 for Q-form
def A57WriteVABAD : SchedWriteRes<[A57UnitX]> { let Latency = 4; }
def A57ReadVABAD  : SchedReadAdvance<3, [A57WriteVABAD]>;
def : InstRW<[A57WriteVABAD, A57ReadVABAD],
  (instregex "VABA(s|u)(v8i8|v4i16|v2i32)")>;
def A57WriteVABAQ : SchedWriteRes<[A57UnitX]> { let Latency = 5; }
def A57ReadVABAQ  : SchedReadAdvance<3, [A57WriteVABAQ]>;
def : InstRW<[A57WriteVABAQ, A57ReadVABAQ],
  (instregex "VABA(s|u)(v16i8|v8i16|v4i32)")>;

// ASIMD absolute diff accum long: 4(1) F1 for VABAL
def A57WriteVABAL : SchedWriteRes<[A57UnitX]> { let Latency = 4; }
def A57ReadVABAL  : SchedReadAdvance<3, [A57WriteVABAL]>;
def : InstRW<[A57WriteVABAL, A57ReadVABAL], (instregex "VABAL(s|u)")>;

// ASIMD absolute diff long: 3cyc F0/F1 for VABDL
def : InstRW<[A57Write_3cyc_1V], (instregex "VABDL(s|u)")>;

// ASIMD arith, basic
def : InstRW<[A57Write_3cyc_1V], (instregex "VADDv", "VADDL", "VADDW",
  "VNEG(s8d|s16d|s32d|s8q|s16q|s32q|d|q)",
  "VPADDi", "VPADDL", "VSUBv", "VSUBL", "VSUBW")>;

// ASIMD arith, complex
def : InstRW<[A57Write_3cyc_1V], (instregex "VABS", "VADDHN", "VHADD", "VHSUB",
  "VQABS", "VQADD", "VQNEG", "VQSUB",
  "VRADDHN", "VRHADD", "VRSUBHN", "VSUBHN")>;

// ASIMD compare
def : InstRW<[A57Write_3cyc_1V],
  (instregex "VCEQ", "VCGE", "VCGT", "VCLE", "VTST", "VCLT")>;

// ASIMD logical
def : InstRW<[A57Write_3cyc_1V],
  (instregex "VAND", "VBIC", "VMVN", "VORR", "VORN", "VEOR")>;

// ASIMD max/min
def : InstRW<[A57Write_3cyc_1V],
  (instregex "(VMAX|VMIN)(s|u)", "(VPMAX|VPMIN)(s8|s16|s32|u8|u16|u32)")>;

// ASIMD multiply, D-form: 5cyc F0 for r0px, 4cyc F0 for r1p0 and later
// Cortex-A57 r1p0 and later reduce the latency of ASIMD multiply
// and multiply-with-accumulate instructions relative to r0pX.
def A57WriteVMULD_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_4cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_5cyc_1W]>]>;
def : InstRW<[A57WriteVMULD_VecInt], (instregex
  "VMUL(v8i8|v4i16|v2i32|pd)", "VMULsl(v4i16|v2i32)",
  "VQDMULH(sl)?(v4i16|v2i32)", "VQRDMULH(sl)?(v4i16|v2i32)")>;

// ASIMD multiply, Q-form: 6cyc F0 for r0px, 5cyc F0 for r1p0 and later
def A57WriteVMULQ_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_5cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_6cyc_1W]>]>;
def : InstRW<[A57WriteVMULQ_VecInt], (instregex
  "VMUL(v16i8|v8i16|v4i32|pq)", "VMULsl(v8i16|v4i32)",
  "VQDMULH(sl)?(v8i16|v4i32)", "VQRDMULH(sl)?(v8i16|v4i32)")>;

// ASIMD multiply accumulate, D-form
// 5cyc F0 for r0px, 4cyc F0 for r1p0 and later, 1cyc for accumulate sequence
// (4 or 3 ReadAdvance)
def A57WriteVMLAD_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_4cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_5cyc_1W]>]>;
def A57ReadVMLAD_VecInt : SchedReadVariant<[
  SchedVar<IsR1P0AndLaterPred, [SchedReadAdvance<3, [A57WriteVMLAD_VecInt]>]>,
  SchedVar<NoSchedPred,        [SchedReadAdvance<4, [A57WriteVMLAD_VecInt]>]>
]>;
def : InstRW<[A57WriteVMLAD_VecInt, A57ReadVMLAD_VecInt],
  (instregex "VMLA(sl)?(v8i8|v4i16|v2i32)", "VMLS(sl)?(v8i8|v4i16|v2i32)")>;

// ASIMD multiply accumulate, Q-form
// 6cyc F0 for r0px, 5cyc F0 for r1p0 and later, 2cyc for accumulate sequence
// (4 or 3 ReadAdvance)
def A57WriteVMLAQ_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_5cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_6cyc_1W]>]>;
def A57ReadVMLAQ_VecInt : SchedReadVariant<[
  SchedVar<IsR1P0AndLaterPred, [SchedReadAdvance<3, [A57WriteVMLAQ_VecInt]>]>,
  SchedVar<NoSchedPred,        [SchedReadAdvance<4, [A57WriteVMLAQ_VecInt]>]>
]>;
def : InstRW<[A57WriteVMLAQ_VecInt, A57ReadVMLAQ_VecInt],
  (instregex "VMLA(sl)?(v16i8|v8i16|v4i32)", "VMLS(sl)?(v16i8|v8i16|v4i32)")>;

// ASIMD multiply accumulate long
// 5cyc F0 for r0px, 4cyc F0 for r1p0 and later, 1cyc for accumulate sequence
// (4 or 3 ReadAdvance)
def A57WriteVMLAL_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_4cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_5cyc_1W]>]>;
def A57ReadVMLAL_VecInt : SchedReadVariant<[
  SchedVar<IsR1P0AndLaterPred, [SchedReadAdvance<3, [A57WriteVMLAL_VecInt]>]>,
  SchedVar<NoSchedPred,        [SchedReadAdvance<4, [A57WriteVMLAL_VecInt]>]>
]>;
def : InstRW<[A57WriteVMLAL_VecInt, A57ReadVMLAL_VecInt],
  (instregex "VMLAL(s|u)", "VMLSL(s|u)")>;

// ASIMD multiply accumulate saturating long
// 5cyc F0 for r0px, 4cyc F0 for r1p0 and later, 2cyc for accumulate sequence
// (3 or 2 ReadAdvance)
def A57WriteVQDMLAL_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_4cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_5cyc_1W]>]>;
def A57ReadVQDMLAL_VecInt : SchedReadVariant<[
  SchedVar<IsR1P0AndLaterPred, [SchedReadAdvance<2, [A57WriteVQDMLAL_VecInt]>]>,
  SchedVar<NoSchedPred,        [SchedReadAdvance<3, [A57WriteVQDMLAL_VecInt]>]>
]>;
def : InstRW<[A57WriteVQDMLAL_VecInt, A57ReadVQDMLAL_VecInt],
  (instregex "VQDMLAL", "VQDMLSL")>;

// Vector Saturating Rounding Doubling Multiply Accumulate/Subtract Long
// Scheduling info from VQDMLAL/VQDMLSL
def : InstRW<[A57WriteVQDMLAL_VecInt, A57ReadVQDMLAL_VecInt],
  (instregex "VQRDMLAH", "VQRDMLSH")>;

// ASIMD multiply long
// 5cyc F0 for r0px, 4cyc F0 for r1p0 and later
def A57WriteVMULL_VecInt : SchedWriteVariant<[
  SchedVar<IsR1P0AndLaterPred, [A57Write_4cyc_1W]>,
  SchedVar<NoSchedPred,        [A57Write_5cyc_1W]>]>;
def : InstRW<[A57WriteVMULL_VecInt],
  (instregex "VMULL(s|u|p8|sls|slu)", "VQDMULL")>;

// ASIMD pairwise add and accumulate
// 4cyc F1, 1cyc for accumulate sequence (3cyc ReadAdvance)
def A57WriteVPADAL : SchedWriteRes<[A57UnitX]> { let Latency = 4; }
def A57ReadVPADAL  : SchedReadAdvance<3, [A57WriteVPADAL]>;
def : InstRW<[A57WriteVPADAL, A57ReadVPADAL], (instregex "VPADAL(s|u)")>;

// ASIMD shift accumulate
// 4cyc F1, 1cyc for accumulate sequence (3cyc ReadAdvance)
def A57WriteVSRA : SchedWriteRes<[A57UnitX]> { let Latency = 4;  }
def A57ReadVSRA  : SchedReadAdvance<3, [A57WriteVSRA]>;
def : InstRW<[A57WriteVSRA, A57ReadVSRA], (instregex "VSRA", "VRSRA")>;

// ASIMD shift by immed, basic
def : InstRW<[A57Write_3cyc_1X],
  (instregex "VMOVL", "VSHLi", "VSHLL", "VSHR(s|u)", "VSHRN")>;

// ASIMD shift by immed, complex
def : InstRW<[A57Write_4cyc_1X], (instregex
  "VQRSHRN", "VQRSHRUN", "VQSHL(si|ui|su)", "VQSHRN", "VQSHRUN", "VRSHR(s|u)",
  "VRSHRN")>;

// ASIMD shift by immed and insert, basic, D-form
def : InstRW<[A57Write_4cyc_1X], (instregex
  "VSLI(v8i8|v4i16|v2i32|v1i64)", "VSRI(v8i8|v4i16|v2i32|v1i64)")>;

// ASIMD shift by immed and insert, basic, Q-form
def : InstRW<[A57Write_5cyc_1X], (instregex
  "VSLI(v16i8|v8i16|v4i32|v2i64)", "VSRI(v16i8|v8i16|v4i32|v2i64)")>;

// ASIMD shift by register, basic, D-form
def : InstRW<[A57Write_3cyc_1X], (instregex
  "VSHL(s|u)(v8i8|v4i16|v2i32|v1i64)")>;

// ASIMD shift by register, basic, Q-form
def : InstRW<[A57Write_4cyc_1X], (instregex
  "VSHL(s|u)(v16i8|v8i16|v4i32|v2i64)")>;

// ASIMD shift by register, complex, D-form
// VQRSHL, VQSHL, VRSHL
def : InstRW<[A57Write_4cyc_1X], (instregex
  "VQRSHL(s|u)(v8i8|v4i16|v2i32|v1i64)", "VQSHL(s|u)(v8i8|v4i16|v2i32|v1i64)",
  "VRSHL(s|u)(v8i8|v4i16|v2i32|v1i64)")>;

// ASIMD shift by register, complex, Q-form
def : InstRW<[A57Write_5cyc_1X], (instregex
  "VQRSHL(s|u)(v16i8|v8i16|v4i32|v2i64)", "VQSHL(s|u)(v16i8|v8i16|v4i32|v2i64)",
  "VRSHL(s|u)(v16i8|v8i16|v4i32|v2i64)")>;

// --- 3.15 ASIMD Floating-Point Instructions ---
// ASIMD FP absolute value
def : InstRW<[A57Write_3cyc_1V], (instregex "VABS(fd|fq|hd|hq)")>;

// ASIMD FP arith
def : InstRW<[A57Write_5cyc_1V], (instregex "VABD(fd|fq|hd|hq)",
  "VADD(fd|fq|hd|hq)", "VPADD(f|h)", "VSUB(fd|fq|hd|hq)")>;

def : InstRW<[A57Write_5cyc_1V], (instregex "VCADD", "VCMLA")>;

// ASIMD FP compare
def : InstRW<[A57Write_5cyc_1V], (instregex "VAC(GE|GT|LE|LT)",
  "VC(EQ|GE|GT|LE)(fd|fq|hd|hq)")>;

// ASIMD FP convert, integer
def : InstRW<[A57Write_5cyc_1V], (instregex
  "VCVT(f2sd|f2ud|s2fd|u2fd|f2sq|f2uq|s2fq|u2fq|f2xsd|f2xud|xs2fd|xu2fd)",
  "VCVT(f2xsq|f2xuq|xs2fq|xu2fq)",
  "VCVT(AN|MN|NN|PN)(SDf|SQf|UDf|UQf|SDh|SQh|UDh|UQh)")>;

// ASIMD FP convert, half-precision: 8cyc F0/F1
def : InstRW<[A57Write_8cyc_1V], (instregex
  "VCVT(h2sd|h2ud|s2hd|u2hd|h2sq|h2uq|s2hq|u2hq|h2xsd|h2xud|xs2hd|xu2hd)",
  "VCVT(h2xsq|h2xuq|xs2hq|xu2hq)",
  "VCVT(f2h|h2f)")>;

// ASIMD FP max/min
def : InstRW<[A57Write_5cyc_1V], (instregex
  "(VMAX|VMIN)(fd|fq|hd|hq)", "(VPMAX|VPMIN)(f|h)", "(NEON|VFP)_VMAXNM",
  "(NEON|VFP)_VMINNM")>;

// ASIMD FP multiply
def A57WriteVMUL_VecFP  : SchedWriteRes<[A57UnitV]> { let Latency = 5;  }
def : InstRW<[A57WriteVMUL_VecFP], (instregex "VMUL(sl)?(fd|fq|hd|hq)")>;

// ASIMD FP multiply accumulate: 9cyc F0/F1, 4cyc for accumulate sequence
def A57WriteVMLA_VecFP  : SchedWriteRes<[A57UnitV]> { let Latency = 9;  }
def A57ReadVMLA_VecFP  :
  SchedReadAdvance<5, [A57WriteVMLA_VecFP, A57WriteVMUL_VecFP]>;
def : InstRW<[A57WriteVMLA_VecFP, A57ReadVMLA_VecFP],
  (instregex "(VMLA|VMLS)(sl)?(fd|fq|hd|hq)", "(VFMA|VFMS)(fd|fq|hd|hq)")>;

// ASIMD FP negate
def : InstRW<[A57Write_3cyc_1V], (instregex "VNEG(fd|f32q|hd|hq)")>;

// ASIMD FP round to integral
def : InstRW<[A57Write_5cyc_1V], (instregex
  "VRINT(AN|MN|NN|PN|XN|ZN)(Df|Qf|Dh|Qh)")>;

// --- 3.16 ASIMD Miscellaneous Instructions ---

// ASIMD bitwise insert
def : InstRW<[A57Write_3cyc_1V], (instregex "VBIF", "VBIT", "VBSL", "VBSP")>;

// ASIMD count
def : InstRW<[A57Write_3cyc_1V], (instregex "VCLS", "VCLZ", "VCNT")>;

// ASIMD duplicate, core reg: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V], (instregex "VDUP(8|16|32)(d|q)")>;

// ASIMD duplicate, scalar: 3cyc "F0/F1"
def : InstRW<[A57Write_3cyc_1V], (instregex "VDUPLN(8|16|32)(d|q)")>;

// ASIMD extract
def : InstRW<[A57Write_3cyc_1V], (instregex "VEXT(d|q)(8|16|32|64)")>;

// ASIMD move, immed
def : InstRW<[A57Write_3cyc_1V], (instregex
  "VMOV(v8i8|v16i8|v4i16|v8i16|v2i32|v4i32|v1i64|v2i64|v2f32|v4f32)",
  "VMOVD0", "VMOVQ0")>;

// ASIMD move, narrowing
def : InstRW<[A57Write_3cyc_1V], (instregex "VMOVN")>;

// ASIMD move, saturating
def : InstRW<[A57Write_4cyc_1X], (instregex "VQMOVN")>;

// ASIMD reciprocal estimate
def : InstRW<[A57Write_5cyc_1V], (instregex "VRECPE", "VRSQRTE")>;

// ASIMD reciprocal step, FZ
def : InstRW<[A57Write_9cyc_1V], (instregex "VRECPS", "VRSQRTS")>;

// ASIMD reverse, swap, table lookup (1-2 reg)
def : InstRW<[A57Write_3cyc_1V], (instregex "VREV", "VSWP", "VTB(L|X)(1|2)")>;

// ASIMD table lookup (3-4 reg)
def : InstRW<[A57Write_6cyc_1V], (instregex "VTBL(3|4)", "VTBX(3|4)")>;

// ASIMD transfer, scalar to core reg: 6cyc "L, I0/I1"
def : InstRW<[A57Write_6cyc_1L_1I], (instregex "VGETLN")>;

// ASIMD transfer, core reg to scalar: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V], (instregex "VSETLN")>;

// ASIMD transpose
def : InstRW<[A57Write_3cyc_1V, A57Write_3cyc_1V], (instregex "VTRN")>;

// ASIMD unzip/zip, D-form
def : InstRW<[A57Write_3cyc_1V, A57Write_3cyc_1V],
  (instregex "VUZPd", "VZIPd")>;

// ASIMD unzip/zip, Q-form
def : InstRW<[A57Write_6cyc_1V, A57Write_6cyc_1V],
  (instregex "VUZPq", "VZIPq")>;

// --- 3.17 ASIMD Load Instructions ---

// Overriden via InstRW for this processor.
def : WriteRes<WriteVLD1, []>;
def : WriteRes<WriteVLD2, []>;
def : WriteRes<WriteVLD3, []>;
def : WriteRes<WriteVLD4, []>;
def : WriteRes<WriteVST1, []>;
def : WriteRes<WriteVST2, []>;
def : WriteRes<WriteVST3, []>;
def : WriteRes<WriteVST4, []>;

// 1-2 reg: 5cyc L, +I for writeback, 1 cyc wb latency
def : InstRW<[A57Write_5cyc_1L], (instregex "VLD1(d|q)(8|16|32|64)$")>;
def : InstRW<[A57Write_5cyc_1L_1I, A57WrBackOne],
  (instregex "VLD1(d|q)(8|16|32|64)wb")>;

// 3-4 reg: 6cyc L, +I for writeback, 1 cyc wb latency
def : InstRW<[A57Write_6cyc_1L],
  (instregex "VLD1(d|q)(8|16|32|64)(T|Q)$", "VLD1d64(T|Q)Pseudo")>;

def : InstRW<[A57Write_6cyc_1L_1I, A57WrBackOne],
  (instregex "VLD1(d|q)(8|16|32|64)(T|Q)wb")>;

// ASIMD load, 1 element, one lane and all lanes: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V], (instregex
  "VLD1(LN|DUP)(d|q)(8|16|32)$", "VLD1(LN|DUP)(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne], (instregex
  "VLD1(LN|DUP)(d|q)(8|16|32)(wb|_UPD)", "VLD1LNq(8|16|32)Pseudo_UPD")>;

// ASIMD load, 2 element, multiple, 2 reg: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V],
      (instregex "VLD2(d|q)(8|16|32)$", "VLD2q(8|16|32)Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD2(d|q)(8|16|32)wb", "VLD2q(8|16|32)PseudoWB")>;

// ASIMD load, 2 element, multiple, 4 reg: 9cyc "L, F0/F1"
def : InstRW<[A57Write_9cyc_1L_1V], (instregex "VLD2b(8|16|32)$")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD2b(8|16|32)wb")>;

// ASIMD load, 2 element, one lane and all lanes: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V],
      (instregex "VLD2(DUP|LN)(d|q)(8|16|32|8x2|16x2|32x2)$",
                 "VLD2LN(d|q)(8|16|32)Pseudo$")>;
// 2 results + wb result
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V, A57WrBackOne],
      (instregex "VLD2LN(d|q)(8|16|32)_UPD$")>;
// 1 result + wb result
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD2DUPd(8|16|32|8x2|16x2|32x2)wb",
                 "VLD2LN(d|q)(8|16|32)Pseudo_UPD")>;

// ASIMD load, 3 element, multiple, 3 reg: 9cyc "L, F0/F1"
// 3 results
def : InstRW<[A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V],
      (instregex "VLD3(d|q)(8|16|32)$")>;
// 1 result
def : InstRW<[A57Write_9cyc_1L_1V],
      (instregex "VLD3(d|q)(8|16|32)(oddP|P)seudo$")>;
// 3 results + wb
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I,
              A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3(d|q)(8|16|32)_UPD$")>;
// 1 result + wb
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3(d|q)(8|16|32)(oddP|P)seudo_UPD")>;

// ASIMD load, 3 element, one lane, size 32: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V],
      (instregex "VLD3LN(d|q)32$",
                 "VLD3LN(d|q)32Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3LN(d|q)32_UPD")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3LN(d|q)32Pseudo_UPD")>;

// ASIMD load, 3 element, one lane, size 8/16: 9cyc "L, F0/F1"
def : InstRW<[A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V],
      (instregex "VLD3LN(d|q)(8|16)$",
                 "VLD3LN(d|q)(8|16)Pseudo$")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I,
              A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3LN(d|q)(8|16)_UPD")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3LN(d|q)(8|16)Pseudo_UPD")>;

// ASIMD load, 3 element, all lanes: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V],
      (instregex "VLD3DUP(d|q)(8|16|32)$",
                 "VLD3DUP(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3DUP(d|q)(8|16|32)_UPD")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD3DUP(d|q)(8|16|32)Pseudo_UPD")>;

// ASIMD load, 4 element, multiple, 4 reg: 9cyc "L, F0/F1"
def : InstRW<[A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V,
              A57Write_9cyc_1L_1V],
      (instregex "VLD4(d|q)(8|16|32)$")>;
def : InstRW<[A57Write_9cyc_1L_1V],
      (instregex "VLD4(d|q)(8|16|32)(oddP|P)seudo$")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I,
              A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD4(d|q)(8|16|32)_UPD")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex  "VLD4(d|q)(8|16|32)(oddP|P)seudo_UPD")>;

// ASIMD load, 4 element, one lane, size 32: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V,
              A57Write_8cyc_1L_1V],
      (instregex "VLD4LN(d|q)32$",
                 "VLD4LN(d|q)32Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57WrBackOne],
      (instregex "VLD4LN(d|q)32_UPD")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD4LN(d|q)32Pseudo_UPD")>;

// ASIMD load, 4 element, one lane, size 8/16: 9cyc "L, F0/F1"
def : InstRW<[A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V, A57Write_9cyc_1L_1V,
              A57Write_9cyc_1L_1V],
      (instregex "VLD4LN(d|q)(8|16)$",
                 "VLD4LN(d|q)(8|16)Pseudo$")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I,
              A57Write_9cyc_1L_1V_1I, A57Write_9cyc_1L_1V_1I,
              A57WrBackOne],
      (instregex "VLD4LN(d|q)(8|16)_UPD")>;
def : InstRW<[A57Write_9cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD4LN(d|q)(8|16)Pseudo_UPD")>;

// ASIMD load, 4 element, all lanes: 8cyc "L, F0/F1"
def : InstRW<[A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V, A57Write_8cyc_1L_1V,
              A57Write_8cyc_1L_1V],
      (instregex "VLD4DUP(d|q)(8|16|32)$",
                 "VLD4DUP(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57Write_8cyc_1L_1V_1I, A57Write_8cyc_1L_1V_1I,
              A57WrBackOne],
      (instregex "VLD4DUP(d|q)(8|16|32)_UPD")>;
def : InstRW<[A57Write_8cyc_1L_1V_1I, A57WrBackOne],
      (instregex "VLD4DUP(d|q)(8|16|32)Pseudo_UPD")>;

// --- 3.18 ASIMD Store Instructions ---

// ASIMD store, 1 element, multiple, 1 reg: 1cyc S
def : InstRW<[A57Write_1cyc_1S], (instregex "VST1d(8|16|32|64)$")>;
def : InstRW<[A57WrBackOne, A57Write_1cyc_1S_1I],
      (instregex "VST1d(8|16|32|64)wb")>;
// ASIMD store, 1 element, multiple, 2 reg: 2cyc S
def : InstRW<[A57Write_2cyc_1S], (instregex "VST1q(8|16|32|64)$")>;
def : InstRW<[A57WrBackOne, A57Write_2cyc_1S_1I],
      (instregex "VST1q(8|16|32|64)wb")>;
// ASIMD store, 1 element, multiple, 3 reg: 3cyc S
def : InstRW<[A57Write_3cyc_1S],
      (instregex "VST1d(8|16|32|64)T$", "VST1d64TPseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1I],
      (instregex "VST1d(8|16|32|64)Twb", "VST1d64TPseudoWB")>;
// ASIMD store, 1 element, multiple, 4 reg: 4cyc S
def : InstRW<[A57Write_4cyc_1S],
      (instregex "VST1d(8|16|32|64)(Q|QPseudo)$")>;
def : InstRW<[A57WrBackOne, A57Write_4cyc_1S_1I],
      (instregex "VST1d(8|16|32|64)(Qwb|QPseudoWB)")>;
// ASIMD store, 1 element, one lane: 3cyc "F0/F1, S"
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST1LNd(8|16|32)$", "VST1LNq(8|16|32)Pseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST1LNd(8|16|32)_UPD", "VST1LNq(8|16|32)Pseudo_UPD")>;
// ASIMD store, 2 element, multiple, 2 reg: 3cyc "F0/F1, S"
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST2(d|b)(8|16|32)$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST2(b|d)(8|16|32)wb")>;
// ASIMD store, 2 element, multiple, 4 reg: 4cyc "F0/F1, S"
def : InstRW<[A57Write_4cyc_1S_1V],
      (instregex "VST2q(8|16|32)$", "VST2q(8|16|32)Pseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_4cyc_1S_1V_1I],
      (instregex "VST2q(8|16|32)wb", "VST2q(8|16|32)PseudoWB")>;
// ASIMD store, 2 element, one lane: 3cyc "F0/F1, S"
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST2LN(d|q)(8|16|32)$", "VST2LN(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST2LN(d|q)(8|16|32)_UPD",
                 "VST2LN(d|q)(8|16|32)Pseudo_UPD")>;
// ASIMD store, 3 element, multiple, 3 reg
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST3(d|q)(8|16|32)$", "VST3(d|q)(8|16|32)(oddP|P)seudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST3(d|q)(8|16|32)_UPD",
                 "VST3(d|q)(8|16|32)(oddP|P)seudo_UPD$")>;
// ASIMD store, 3 element, one lane
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST3LN(d|q)(8|16|32)$", "VST3LN(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST3LN(d|q)(8|16|32)_UPD",
                 "VST3LN(d|q)(8|16|32)Pseudo_UPD")>;
// ASIMD store, 4 element, multiple, 4 reg
def : InstRW<[A57Write_4cyc_1S_1V],
      (instregex "VST4(d|q)(8|16|32)$", "VST4(d|q)(8|16|32)(oddP|P)seudo$")>;
def : InstRW<[A57WrBackOne, A57Write_4cyc_1S_1V_1I],
      (instregex "VST4(d|q)(8|16|32)_UPD",
                 "VST4(d|q)(8|16|32)(oddP|P)seudo_UPD$")>;
// ASIMD store, 4 element, one lane
def : InstRW<[A57Write_3cyc_1S_1V],
      (instregex "VST4LN(d|q)(8|16|32)$", "VST4LN(d|q)(8|16|32)Pseudo$")>;
def : InstRW<[A57WrBackOne, A57Write_3cyc_1S_1V_1I],
      (instregex "VST4LN(d|q)(8|16|32)_UPD",
                 "VST4LN(d|q)(8|16|32)Pseudo_UPD")>;

// --- 3.19 Cryptography Extensions ---
// Crypto AES ops
// AESD, AESE, AESIMC, AESMC: 3cyc F0
def : InstRW<[A57Write_3cyc_1W], (instregex "^AES")>;
// Crypto polynomial (64x64) multiply long (VMULL.P64): 3cyc F0
def : InstRW<[A57Write_3cyc_1W], (instregex "^VMULLp64")>;
// Crypto SHA1 xor ops: 6cyc F0/F1
def : InstRW<[A57Write_6cyc_2V], (instregex "^SHA1SU0")>;
// Crypto SHA1 fast ops: 3cyc F0
def : InstRW<[A57Write_3cyc_1W], (instregex "^SHA1(H|SU1)")>;
// Crypto SHA1 slow ops: 6cyc F0
def : InstRW<[A57Write_6cyc_2W], (instregex "^SHA1[CMP]")>;
// Crypto SHA256 fast ops: 3cyc F0
def : InstRW<[A57Write_3cyc_1W], (instregex "^SHA256SU0")>;
// Crypto SHA256 slow ops: 6cyc F0
def : InstRW<[A57Write_6cyc_2W], (instregex "^SHA256(H|H2|SU1)")>;

// --- 3.20 CRC ---
def : InstRW<[A57Write_3cyc_1W], (instregex "^(t2)?CRC32")>;

// -----------------------------------------------------------------------------
// Common definitions
def : WriteRes<WriteNoop, []> { let Latency = 0; let NumMicroOps = 0; }
def : SchedAlias<WriteALU, CheckBranchForm<0, A57BranchForm<A57Write_1cyc_1I>>>;

def : SchedAlias<WriteBr, A57Write_1cyc_1B>;
def : SchedAlias<WriteBrL, A57Write_1cyc_1B_1I>;
def : SchedAlias<WriteBrTbl, A57Write_1cyc_1B_1I>;
def : SchedAlias<WritePreLd, A57Write_4cyc_1L>;

def : SchedAlias<WriteLd, A57Write_4cyc_1L>;
def : SchedAlias<WriteST, A57Write_1cyc_1S>;
def : ReadAdvance<ReadALU, 0>;

} // SchedModel = CortexA57Model