aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/ARM/ARMInstrVFP.td
blob: c79ffddf6b5868d2c199eb89cf52486ea3be86df (plain)
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
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
//===-- ARMInstrVFP.td - VFP support for ARM ---------------*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file describes the ARM VFP instruction set.
//
//===----------------------------------------------------------------------===//

def SDT_FTOI    : SDTypeProfile<1, 1, [SDTCisVT<0, f32>, SDTCisFP<1>]>;
def SDT_ITOF    : SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisVT<1, f32>]>;
def SDT_CMPFP0  : SDTypeProfile<0, 1, [SDTCisFP<0>]>;
def SDT_VMOVDRR : SDTypeProfile<1, 2, [SDTCisVT<0, f64>, SDTCisVT<1, i32>,
                                       SDTCisSameAs<1, 2>]>;

def arm_ftoui  : SDNode<"ARMISD::FTOUI",   SDT_FTOI>;
def arm_ftosi  : SDNode<"ARMISD::FTOSI",   SDT_FTOI>;
def arm_sitof  : SDNode<"ARMISD::SITOF",   SDT_ITOF>;
def arm_uitof  : SDNode<"ARMISD::UITOF",   SDT_ITOF>;
def arm_fmstat : SDNode<"ARMISD::FMSTAT",  SDTNone, [SDNPInGlue, SDNPOutGlue]>;
def arm_cmpfp  : SDNode<"ARMISD::CMPFP",   SDT_ARMCmp, [SDNPOutGlue]>;
def arm_cmpfp0 : SDNode<"ARMISD::CMPFPw0", SDT_CMPFP0, [SDNPOutGlue]>;
def arm_fmdrr  : SDNode<"ARMISD::VMOVDRR", SDT_VMOVDRR>;


//===----------------------------------------------------------------------===//
// Operand Definitions.
//

// 8-bit floating-point immediate encodings.
def FPImmOperand : AsmOperandClass {
  let Name = "FPImm";
  let ParserMethod = "parseFPImm";
}

def vfp_f32imm : Operand<f32>,
                 PatLeaf<(f32 fpimm), [{
      return ARM_AM::getFP32Imm(N->getValueAPF()) != -1;
    }], SDNodeXForm<fpimm, [{
      APFloat InVal = N->getValueAPF();
      uint32_t enc = ARM_AM::getFP32Imm(InVal);
      return CurDAG->getTargetConstant(enc, MVT::i32);
    }]>> {
  let PrintMethod = "printFPImmOperand";
  let ParserMatchClass = FPImmOperand;
}

def vfp_f64imm : Operand<f64>,
                 PatLeaf<(f64 fpimm), [{
      return ARM_AM::getFP64Imm(N->getValueAPF()) != -1;
    }], SDNodeXForm<fpimm, [{
      APFloat InVal = N->getValueAPF();
      uint32_t enc = ARM_AM::getFP64Imm(InVal);
      return CurDAG->getTargetConstant(enc, MVT::i32);
    }]>> {
  let PrintMethod = "printFPImmOperand";
  let ParserMatchClass = FPImmOperand;
}

def alignedload32 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
  return cast<LoadSDNode>(N)->getAlignment() >= 4;
}]>;

def alignedstore32 : PatFrag<(ops node:$val, node:$ptr),
                             (store node:$val, node:$ptr), [{
  return cast<StoreSDNode>(N)->getAlignment() >= 4;
}]>;

// The VCVT to/from fixed-point instructions encode the 'fbits' operand
// (the number of fixed bits) differently than it appears in the assembly
// source. It's encoded as "Size - fbits" where Size is the size of the
// fixed-point representation (32 or 16) and fbits is the value appearing
// in the assembly source, an integer in [0,16] or (0,32], depending on size.
def fbits32_asm_operand : AsmOperandClass { let Name = "FBits32"; }
def fbits32 : Operand<i32> {
  let PrintMethod = "printFBits32";
  let ParserMatchClass = fbits32_asm_operand;
}

def fbits16_asm_operand : AsmOperandClass { let Name = "FBits16"; }
def fbits16 : Operand<i32> {
  let PrintMethod = "printFBits16";
  let ParserMatchClass = fbits16_asm_operand;
}

//===----------------------------------------------------------------------===//
//  Load / store Instructions.
//

let canFoldAsLoad = 1, isReMaterializable = 1 in {

def VLDRD : ADI5<0b1101, 0b01, (outs DPR:$Dd), (ins addrmode5:$addr),
                 IIC_fpLoad64, "vldr", "\t$Dd, $addr",
                 [(set DPR:$Dd, (f64 (alignedload32 addrmode5:$addr)))]>;

def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$Sd), (ins addrmode5:$addr),
                 IIC_fpLoad32, "vldr", "\t$Sd, $addr",
                 [(set SPR:$Sd, (load addrmode5:$addr))]> {
  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

} // End of 'let canFoldAsLoad = 1, isReMaterializable = 1 in'

def VSTRD : ADI5<0b1101, 0b00, (outs), (ins DPR:$Dd, addrmode5:$addr),
                 IIC_fpStore64, "vstr", "\t$Dd, $addr",
                 [(alignedstore32 (f64 DPR:$Dd), addrmode5:$addr)]>;

def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$Sd, addrmode5:$addr),
                 IIC_fpStore32, "vstr", "\t$Sd, $addr",
                 [(store SPR:$Sd, addrmode5:$addr)]> {
  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

//===----------------------------------------------------------------------===//
//  Load / store multiple Instructions.
//

multiclass vfp_ldst_mult<string asm, bit L_bit,
                         InstrItinClass itin, InstrItinClass itin_upd> {
  // Double Precision
  def DIA :
    AXDI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
          IndexModeNone, itin,
          !strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
    let Inst{24-23} = 0b01;       // Increment After
    let Inst{21}    = 0;          // No writeback
    let Inst{20}    = L_bit;
  }
  def DIA_UPD :
    AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
                               variable_ops),
          IndexModeUpd, itin_upd,
          !strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b01;       // Increment After
    let Inst{21}    = 1;          // Writeback
    let Inst{20}    = L_bit;
  }
  def DDB_UPD :
    AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
                               variable_ops),
          IndexModeUpd, itin_upd,
          !strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b10;       // Decrement Before
    let Inst{21}    = 1;          // Writeback
    let Inst{20}    = L_bit;
  }

  // Single Precision
  def SIA :
    AXSI4<(outs), (ins GPR:$Rn, pred:$p, spr_reglist:$regs, variable_ops),
          IndexModeNone, itin,
          !strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
    let Inst{24-23} = 0b01;       // Increment After
    let Inst{21}    = 0;          // No writeback
    let Inst{20}    = L_bit;

    // Some single precision VFP instructions may be executed on both NEON and
    // VFP pipelines.
    let D = VFPNeonDomain;
  }
  def SIA_UPD :
    AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
                               variable_ops),
          IndexModeUpd, itin_upd,
          !strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b01;       // Increment After
    let Inst{21}    = 1;          // Writeback
    let Inst{20}    = L_bit;

    // Some single precision VFP instructions may be executed on both NEON and
    // VFP pipelines.
    let D = VFPNeonDomain;
  }
  def SDB_UPD :
    AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
                               variable_ops),
          IndexModeUpd, itin_upd,
          !strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b10;       // Decrement Before
    let Inst{21}    = 1;          // Writeback
    let Inst{20}    = L_bit;

    // Some single precision VFP instructions may be executed on both NEON and
    // VFP pipelines.
    let D = VFPNeonDomain;
  }
}

let neverHasSideEffects = 1 in {

let mayLoad = 1, hasExtraDefRegAllocReq = 1 in
defm VLDM : vfp_ldst_mult<"vldm", 1, IIC_fpLoad_m, IIC_fpLoad_mu>;

let mayStore = 1, hasExtraSrcRegAllocReq = 1 in
defm VSTM : vfp_ldst_mult<"vstm", 0, IIC_fpLoad_m, IIC_fpLoad_mu>;

} // neverHasSideEffects

def : MnemonicAlias<"vldm", "vldmia">;
def : MnemonicAlias<"vstm", "vstmia">;

def : InstAlias<"vpush${p} $r", (VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r)>,
                Requires<[HasVFP2]>;
def : InstAlias<"vpush${p} $r", (VSTMSDB_UPD SP, pred:$p, spr_reglist:$r)>,
                Requires<[HasVFP2]>;
def : InstAlias<"vpop${p} $r",  (VLDMDIA_UPD SP, pred:$p, dpr_reglist:$r)>,
                Requires<[HasVFP2]>;
def : InstAlias<"vpop${p} $r",  (VLDMSIA_UPD SP, pred:$p, spr_reglist:$r)>,
                Requires<[HasVFP2]>;
defm : VFPDTAnyInstAlias<"vpush${p}", "$r",
                         (VSTMSDB_UPD SP, pred:$p, spr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpush${p}", "$r",
                         (VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpop${p}", "$r",
                         (VLDMSIA_UPD SP, pred:$p, spr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpop${p}", "$r",
                         (VLDMDIA_UPD SP, pred:$p, dpr_reglist:$r)>;

// FLDMX, FSTMX - Load and store multiple unknown precision registers for
// pre-armv6 cores.
// These instruction are deprecated so we don't want them to get selected.
multiclass vfp_ldstx_mult<string asm, bit L_bit> {
  // Unknown precision
  def XIA :
    AXXI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
          IndexModeNone, !strconcat(asm, "iax${p}\t$Rn, $regs"), "", []> {
    let Inst{24-23} = 0b01;       // Increment After
    let Inst{21}    = 0;          // No writeback
    let Inst{20}    = L_bit;
  }
  def XIA_UPD :
    AXXI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
          IndexModeUpd, !strconcat(asm, "iax${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b01;         // Increment After
    let Inst{21}    = 1;            // Writeback
    let Inst{20}    = L_bit;
  }
  def XDB_UPD :
    AXXI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
          IndexModeUpd, !strconcat(asm, "dbx${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
    let Inst{24-23} = 0b10;         // Decrement Before
    let Inst{21}    = 1;
    let Inst{20}    = L_bit;
  }
}

defm FLDM : vfp_ldstx_mult<"fldm", 1>;
defm FSTM : vfp_ldstx_mult<"fstm", 0>;

//===----------------------------------------------------------------------===//
// FP Binary Operations.
//

let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VADDD  : ADbI<0b11100, 0b11, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
                  IIC_fpALU64, "vadd", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fadd DPR:$Dn, (f64 DPR:$Dm)))]>;

let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VADDS  : ASbIn<0b11100, 0b11, 0, 0,
                   (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
                   IIC_fpALU32, "vadd", ".f32\t$Sd, $Sn, $Sm",
                   [(set SPR:$Sd, (fadd SPR:$Sn, SPR:$Sm))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VSUBD  : ADbI<0b11100, 0b11, 1, 0,
                  (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
                  IIC_fpALU64, "vsub", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fsub DPR:$Dn, (f64 DPR:$Dm)))]>;

let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VSUBS  : ASbIn<0b11100, 0b11, 1, 0,
                   (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
                   IIC_fpALU32, "vsub", ".f32\t$Sd, $Sn, $Sm",
                   [(set SPR:$Sd, (fsub SPR:$Sn, SPR:$Sm))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VDIVD  : ADbI<0b11101, 0b00, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
                  IIC_fpDIV64, "vdiv", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fdiv DPR:$Dn, (f64 DPR:$Dm)))]>;

let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VDIVS  : ASbI<0b11101, 0b00, 0, 0,
                  (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
                  IIC_fpDIV32, "vdiv", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fdiv SPR:$Sn, SPR:$Sm))]>;

let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VMULD  : ADbI<0b11100, 0b10, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
                  IIC_fpMUL64, "vmul", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fmul DPR:$Dn, (f64 DPR:$Dm)))]>;

let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VMULS  : ASbIn<0b11100, 0b10, 0, 0,
                   (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
                   IIC_fpMUL32, "vmul", ".f32\t$Sd, $Sn, $Sm",
                   [(set SPR:$Sd, (fmul SPR:$Sn, SPR:$Sm))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VNMULD : ADbI<0b11100, 0b10, 1, 0,
                  (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
                  IIC_fpMUL64, "vnmul", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fneg (fmul DPR:$Dn, (f64 DPR:$Dm))))]>;

def VNMULS : ASbI<0b11100, 0b10, 1, 0,
                  (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
                  IIC_fpMUL32, "vnmul", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fneg (fmul SPR:$Sn, SPR:$Sm)))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

// Match reassociated forms only if not sign dependent rounding.
def : Pat<(fmul (fneg DPR:$a), (f64 DPR:$b)),
          (VNMULD DPR:$a, DPR:$b)>, Requires<[NoHonorSignDependentRounding]>;
def : Pat<(fmul (fneg SPR:$a), SPR:$b),
          (VNMULS SPR:$a, SPR:$b)>, Requires<[NoHonorSignDependentRounding]>;

// These are encoded as unary instructions.
let Defs = [FPSCR_NZCV] in {
def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0,
                  (outs), (ins DPR:$Dd, DPR:$Dm),
                  IIC_fpCMP64, "vcmpe", ".f64\t$Dd, $Dm",
                  [(arm_cmpfp DPR:$Dd, (f64 DPR:$Dm))]>;

def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0,
                  (outs), (ins SPR:$Sd, SPR:$Sm),
                  IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm",
                  [(arm_cmpfp SPR:$Sd, SPR:$Sm)]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

// FIXME: Verify encoding after integrated assembler is working.
def VCMPD  : ADuI<0b11101, 0b11, 0b0100, 0b01, 0,
                  (outs), (ins DPR:$Dd, DPR:$Dm),
                  IIC_fpCMP64, "vcmp", ".f64\t$Dd, $Dm",
                  [/* For disassembly only; pattern left blank */]>;

def VCMPS  : ASuI<0b11101, 0b11, 0b0100, 0b01, 0,
                  (outs), (ins SPR:$Sd, SPR:$Sm),
                  IIC_fpCMP32, "vcmp", ".f32\t$Sd, $Sm",
                  [/* For disassembly only; pattern left blank */]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}
} // Defs = [FPSCR_NZCV]

//===----------------------------------------------------------------------===//
// FP Unary Operations.
//

def VABSD  : ADuI<0b11101, 0b11, 0b0000, 0b11, 0,
                  (outs DPR:$Dd), (ins DPR:$Dm),
                  IIC_fpUNA64, "vabs", ".f64\t$Dd, $Dm",
                  [(set DPR:$Dd, (fabs (f64 DPR:$Dm)))]>;

def VABSS  : ASuIn<0b11101, 0b11, 0b0000, 0b11, 0,
                   (outs SPR:$Sd), (ins SPR:$Sm),
                   IIC_fpUNA32, "vabs", ".f32\t$Sd, $Sm",
                   [(set SPR:$Sd, (fabs SPR:$Sm))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

let Defs = [FPSCR_NZCV] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
                   (outs), (ins DPR:$Dd),
                   IIC_fpCMP64, "vcmpe", ".f64\t$Dd, #0",
                   [(arm_cmpfp0 (f64 DPR:$Dd))]> {
  let Inst{3-0} = 0b0000;
  let Inst{5}   = 0;
}

def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0,
                   (outs), (ins SPR:$Sd),
                   IIC_fpCMP32, "vcmpe", ".f32\t$Sd, #0",
                   [(arm_cmpfp0 SPR:$Sd)]> {
  let Inst{3-0} = 0b0000;
  let Inst{5}   = 0;

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

// FIXME: Verify encoding after integrated assembler is working.
def VCMPZD  : ADuI<0b11101, 0b11, 0b0101, 0b01, 0,
                   (outs), (ins DPR:$Dd),
                   IIC_fpCMP64, "vcmp", ".f64\t$Dd, #0",
                   [/* For disassembly only; pattern left blank */]> {
  let Inst{3-0} = 0b0000;
  let Inst{5}   = 0;
}

def VCMPZS  : ASuI<0b11101, 0b11, 0b0101, 0b01, 0,
                   (outs), (ins SPR:$Sd),
                   IIC_fpCMP32, "vcmp", ".f32\t$Sd, #0",
                   [/* For disassembly only; pattern left blank */]> {
  let Inst{3-0} = 0b0000;
  let Inst{5}   = 0;

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}
} // Defs = [FPSCR_NZCV]

def VCVTDS  : ASuI<0b11101, 0b11, 0b0111, 0b11, 0,
                   (outs DPR:$Dd), (ins SPR:$Sm),
                   IIC_fpCVTDS, "vcvt", ".f64.f32\t$Dd, $Sm",
                   [(set DPR:$Dd, (fextend SPR:$Sm))]> {
  // Instruction operands.
  bits<5> Dd;
  bits<5> Sm;

  // Encode instruction operands.
  let Inst{3-0}   = Sm{4-1};
  let Inst{5}     = Sm{0};
  let Inst{15-12} = Dd{3-0};
  let Inst{22}    = Dd{4};
}

// Special case encoding: bits 11-8 is 0b1011.
def VCVTSD  : VFPAI<(outs SPR:$Sd), (ins DPR:$Dm), VFPUnaryFrm,
                    IIC_fpCVTSD, "vcvt", ".f32.f64\t$Sd, $Dm",
                    [(set SPR:$Sd, (fround DPR:$Dm))]> {
  // Instruction operands.
  bits<5> Sd;
  bits<5> Dm;

  // Encode instruction operands.
  let Inst{3-0}   = Dm{3-0};
  let Inst{5}     = Dm{4};
  let Inst{15-12} = Sd{4-1};
  let Inst{22}    = Sd{0};

  let Inst{27-23} = 0b11101;
  let Inst{21-16} = 0b110111;
  let Inst{11-8}  = 0b1011;
  let Inst{7-6}   = 0b11;
  let Inst{4}     = 0;
}

// Between half-precision and single-precision.  For disassembly only.

// FIXME: Verify encoding after integrated assembler is working.
def VCVTBHS: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
                 /* FIXME */ IIC_fpCVTSH, "vcvtb", ".f32.f16\t$Sd, $Sm",
                 [/* For disassembly only; pattern left blank */]>;

def VCVTBSH: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
                 /* FIXME */ IIC_fpCVTHS, "vcvtb", ".f16.f32\t$Sd, $Sm",
                 [/* For disassembly only; pattern left blank */]>;

def : Pat<(f32_to_f16 SPR:$a),
          (i32 (COPY_TO_REGCLASS (VCVTBSH SPR:$a), GPR))>;

def : Pat<(f16_to_f32 GPR:$a),
          (VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>;

def VCVTTHS: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
                 /* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$Sd, $Sm",
                 [/* For disassembly only; pattern left blank */]>;

def VCVTTSH: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
                 /* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$Sd, $Sm",
                 [/* For disassembly only; pattern left blank */]>;

def VNEGD  : ADuI<0b11101, 0b11, 0b0001, 0b01, 0,
                  (outs DPR:$Dd), (ins DPR:$Dm),
                  IIC_fpUNA64, "vneg", ".f64\t$Dd, $Dm",
                  [(set DPR:$Dd, (fneg (f64 DPR:$Dm)))]>;

def VNEGS  : ASuIn<0b11101, 0b11, 0b0001, 0b01, 0,
                   (outs SPR:$Sd), (ins SPR:$Sm),
                   IIC_fpUNA32, "vneg", ".f32\t$Sd, $Sm",
                   [(set SPR:$Sd, (fneg SPR:$Sm))]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VSQRTD : ADuI<0b11101, 0b11, 0b0001, 0b11, 0,
                  (outs DPR:$Dd), (ins DPR:$Dm),
                  IIC_fpSQRT64, "vsqrt", ".f64\t$Dd, $Dm",
                  [(set DPR:$Dd, (fsqrt (f64 DPR:$Dm)))]>;

def VSQRTS : ASuI<0b11101, 0b11, 0b0001, 0b11, 0,
                  (outs SPR:$Sd), (ins SPR:$Sm),
                  IIC_fpSQRT32, "vsqrt", ".f32\t$Sd, $Sm",
                  [(set SPR:$Sd, (fsqrt SPR:$Sm))]>;

let neverHasSideEffects = 1 in {
def VMOVD  : ADuI<0b11101, 0b11, 0b0000, 0b01, 0,
                  (outs DPR:$Dd), (ins DPR:$Dm),
                  IIC_fpUNA64, "vmov", ".f64\t$Dd, $Dm", []>;

def VMOVS  : ASuI<0b11101, 0b11, 0b0000, 0b01, 0,
                  (outs SPR:$Sd), (ins SPR:$Sm),
                  IIC_fpUNA32, "vmov", ".f32\t$Sd, $Sm", []>;
} // neverHasSideEffects

//===----------------------------------------------------------------------===//
// FP <-> GPR Copies.  Int <-> FP Conversions.
//

def VMOVRS : AVConv2I<0b11100001, 0b1010,
                      (outs GPR:$Rt), (ins SPR:$Sn),
                      IIC_fpMOVSI, "vmov", "\t$Rt, $Sn",
                      [(set GPR:$Rt, (bitconvert SPR:$Sn))]> {
  // Instruction operands.
  bits<4> Rt;
  bits<5> Sn;

  // Encode instruction operands.
  let Inst{19-16} = Sn{4-1};
  let Inst{7}     = Sn{0};
  let Inst{15-12} = Rt;

  let Inst{6-5}   = 0b00;
  let Inst{3-0}   = 0b0000;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

// Bitcast i32 -> f32.  NEON prefers to use VMOVDRR.
def VMOVSR : AVConv4I<0b11100000, 0b1010,
                      (outs SPR:$Sn), (ins GPR:$Rt),
                      IIC_fpMOVIS, "vmov", "\t$Sn, $Rt",
                      [(set SPR:$Sn, (bitconvert GPR:$Rt))]>,
             Requires<[HasVFP2, UseVMOVSR]> {
  // Instruction operands.
  bits<5> Sn;
  bits<4> Rt;

  // Encode instruction operands.
  let Inst{19-16} = Sn{4-1};
  let Inst{7}     = Sn{0};
  let Inst{15-12} = Rt;

  let Inst{6-5}   = 0b00;
  let Inst{3-0}   = 0b0000;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

let neverHasSideEffects = 1 in {
def VMOVRRD  : AVConv3I<0b11000101, 0b1011,
                        (outs GPR:$Rt, GPR:$Rt2), (ins DPR:$Dm),
                        IIC_fpMOVDI, "vmov", "\t$Rt, $Rt2, $Dm",
                 [/* FIXME: Can't write pattern for multiple result instr*/]> {
  // Instruction operands.
  bits<5> Dm;
  bits<4> Rt;
  bits<4> Rt2;

  // Encode instruction operands.
  let Inst{3-0}   = Dm{3-0};
  let Inst{5}     = Dm{4};
  let Inst{15-12} = Rt;
  let Inst{19-16} = Rt2;

  let Inst{7-6} = 0b00;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

def VMOVRRS  : AVConv3I<0b11000101, 0b1010,
                      (outs GPR:$Rt, GPR:$Rt2), (ins SPR:$src1, SPR:$src2),
                 IIC_fpMOVDI, "vmov", "\t$Rt, $Rt2, $src1, $src2",
                 [/* For disassembly only; pattern left blank */]> {
  bits<5> src1;
  bits<4> Rt;
  bits<4> Rt2;

  // Encode instruction operands.
  let Inst{3-0}   = src1{4-1};
  let Inst{5}     = src1{0};
  let Inst{15-12} = Rt;
  let Inst{19-16} = Rt2;

  let Inst{7-6} = 0b00;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
  let DecoderMethod = "DecodeVMOVRRS";
}
} // neverHasSideEffects

// FMDHR: GPR -> SPR
// FMDLR: GPR -> SPR

def VMOVDRR : AVConv5I<0b11000100, 0b1011,
                      (outs DPR:$Dm), (ins GPR:$Rt, GPR:$Rt2),
                      IIC_fpMOVID, "vmov", "\t$Dm, $Rt, $Rt2",
                      [(set DPR:$Dm, (arm_fmdrr GPR:$Rt, GPR:$Rt2))]> {
  // Instruction operands.
  bits<5> Dm;
  bits<4> Rt;
  bits<4> Rt2;

  // Encode instruction operands.
  let Inst{3-0}   = Dm{3-0};
  let Inst{5}     = Dm{4};
  let Inst{15-12} = Rt;
  let Inst{19-16} = Rt2;

  let Inst{7-6}   = 0b00;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;
}

let neverHasSideEffects = 1 in
def VMOVSRR : AVConv5I<0b11000100, 0b1010,
                     (outs SPR:$dst1, SPR:$dst2), (ins GPR:$src1, GPR:$src2),
                IIC_fpMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2",
                [/* For disassembly only; pattern left blank */]> {
  // Instruction operands.
  bits<5> dst1;
  bits<4> src1;
  bits<4> src2;

  // Encode instruction operands.
  let Inst{3-0}   = dst1{4-1};
  let Inst{5}     = dst1{0};
  let Inst{15-12} = src1;
  let Inst{19-16} = src2;

  let Inst{7-6} = 0b00;

  // Some single precision VFP instructions may be executed on both NEON and VFP
  // pipelines.
  let D = VFPNeonDomain;

  let DecoderMethod = "DecodeVMOVSRR";
}

// FMRDH: SPR -> GPR
// FMRDL: SPR -> GPR
// FMRRS: SPR -> GPR
// FMRX:  SPR system reg -> GPR
// FMSRR: GPR -> SPR
// FMXR:  GPR -> VFP system reg


// Int -> FP:

class AVConv1IDs_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
                        bits<4> opcod4, dag oops, dag iops,
                        InstrItinClass itin, string opc, string asm,
                        list<dag> pattern>
  : AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
             pattern> {
  // Instruction operands.
  bits<5> Dd;
  bits<5> Sm;

  // Encode instruction operands.
  let Inst{3-0}   = Sm{4-1};
  let Inst{5}     = Sm{0};
  let Inst{15-12} = Dd{3-0};
  let Inst{22}    = Dd{4};
}

class AVConv1InSs_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
                         bits<4> opcod4, dag oops, dag iops,InstrItinClass itin,
                         string opc, string asm, list<dag> pattern>
  : AVConv1In<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
              pattern> {
  // Instruction operands.
  bits<5> Sd;
  bits<5> Sm;

  // Encode instruction operands.
  let Inst{3-0}   = Sm{4-1};
  let Inst{5}     = Sm{0};
  let Inst{15-12} = Sd{4-1};
  let Inst{22}    = Sd{0};
}

def VSITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011,
                               (outs DPR:$Dd), (ins SPR:$Sm),
                               IIC_fpCVTID, "vcvt", ".f64.s32\t$Dd, $Sm",
                               [(set DPR:$Dd, (f64 (arm_sitof SPR:$Sm)))]> {
  let Inst{7} = 1; // s32
}

def VSITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010,
                                (outs SPR:$Sd),(ins SPR:$Sm),
                                IIC_fpCVTIS, "vcvt", ".f32.s32\t$Sd, $Sm",
                                [(set SPR:$Sd, (arm_sitof SPR:$Sm))]> {
  let Inst{7} = 1; // s32

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VUITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011,
                               (outs DPR:$Dd), (ins SPR:$Sm),
                               IIC_fpCVTID, "vcvt", ".f64.u32\t$Dd, $Sm",
                               [(set DPR:$Dd, (f64 (arm_uitof SPR:$Sm)))]> {
  let Inst{7} = 0; // u32
}

def VUITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010,
                                (outs SPR:$Sd), (ins SPR:$Sm),
                                IIC_fpCVTIS, "vcvt", ".f32.u32\t$Sd, $Sm",
                                [(set SPR:$Sd, (arm_uitof SPR:$Sm))]> {
  let Inst{7} = 0; // u32

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

// FP -> Int:

class AVConv1IsD_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
                        bits<4> opcod4, dag oops, dag iops,
                        InstrItinClass itin, string opc, string asm,
                        list<dag> pattern>
  : AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
             pattern> {
  // Instruction operands.
  bits<5> Sd;
  bits<5> Dm;

  // Encode instruction operands.
  let Inst{3-0}   = Dm{3-0};
  let Inst{5}     = Dm{4};
  let Inst{15-12} = Sd{4-1};
  let Inst{22}    = Sd{0};
}

class AVConv1InsS_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
                         bits<4> opcod4, dag oops, dag iops,
                         InstrItinClass itin, string opc, string asm,
                         list<dag> pattern>
  : AVConv1In<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
              pattern> {
  // Instruction operands.
  bits<5> Sd;
  bits<5> Sm;

  // Encode instruction operands.
  let Inst{3-0}   = Sm{4-1};
  let Inst{5}     = Sm{0};
  let Inst{15-12} = Sd{4-1};
  let Inst{22}    = Sd{0};
}

// Always set Z bit in the instruction, i.e. "round towards zero" variants.
def VTOSIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011,
                                (outs SPR:$Sd), (ins DPR:$Dm),
                                IIC_fpCVTDI, "vcvt", ".s32.f64\t$Sd, $Dm",
                                [(set SPR:$Sd, (arm_ftosi (f64 DPR:$Dm)))]> {
  let Inst{7} = 1; // Z bit
}

def VTOSIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1101, 0b1010,
                                 (outs SPR:$Sd), (ins SPR:$Sm),
                                 IIC_fpCVTSI, "vcvt", ".s32.f32\t$Sd, $Sm",
                                 [(set SPR:$Sd, (arm_ftosi SPR:$Sm))]> {
  let Inst{7} = 1; // Z bit

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VTOUIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011,
                               (outs SPR:$Sd), (ins DPR:$Dm),
                               IIC_fpCVTDI, "vcvt", ".u32.f64\t$Sd, $Dm",
                               [(set SPR:$Sd, (arm_ftoui (f64 DPR:$Dm)))]> {
  let Inst{7} = 1; // Z bit
}

def VTOUIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010,
                                 (outs SPR:$Sd), (ins SPR:$Sm),
                                 IIC_fpCVTSI, "vcvt", ".u32.f32\t$Sd, $Sm",
                                 [(set SPR:$Sd, (arm_ftoui SPR:$Sm))]> {
  let Inst{7} = 1; // Z bit

  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

// And the Z bit '0' variants, i.e. use the rounding mode specified by FPSCR.
let Uses = [FPSCR] in {
// FIXME: Verify encoding after integrated assembler is working.
def VTOSIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011,
                                (outs SPR:$Sd), (ins DPR:$Dm),
                                IIC_fpCVTDI, "vcvtr", ".s32.f64\t$Sd, $Dm",
                                [(set SPR:$Sd, (int_arm_vcvtr (f64 DPR:$Dm)))]>{
  let Inst{7} = 0; // Z bit
}

def VTOSIRS : AVConv1InsS_Encode<0b11101, 0b11, 0b1101, 0b1010,
                                 (outs SPR:$Sd), (ins SPR:$Sm),
                                 IIC_fpCVTSI, "vcvtr", ".s32.f32\t$Sd, $Sm",
                                 [(set SPR:$Sd, (int_arm_vcvtr SPR:$Sm))]> {
  let Inst{7} = 0; // Z bit
}

def VTOUIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011,
                                (outs SPR:$Sd), (ins DPR:$Dm),
                                IIC_fpCVTDI, "vcvtr", ".u32.f64\t$Sd, $Dm",
                                [(set SPR:$Sd, (int_arm_vcvtru(f64 DPR:$Dm)))]>{
  let Inst{7} = 0; // Z bit
}

def VTOUIRS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010,
                                 (outs SPR:$Sd), (ins SPR:$Sm),
                                 IIC_fpCVTSI, "vcvtr", ".u32.f32\t$Sd, $Sm",
                                 [(set SPR:$Sd, (int_arm_vcvtru SPR:$Sm))]> {
  let Inst{7} = 0; // Z bit
}
}

// Convert between floating-point and fixed-point
// Data type for fixed-point naming convention:
//   S16 (U=0, sx=0) -> SH
//   U16 (U=1, sx=0) -> UH
//   S32 (U=0, sx=1) -> SL
//   U32 (U=1, sx=1) -> UL

let Constraints = "$a = $dst" in {

// FP to Fixed-Point:

// Single Precision register
class AVConv1XInsS_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
                          bit op5, dag oops, dag iops, InstrItinClass itin,
                          string opc, string asm, list<dag> pattern>
  : AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern>,
  Sched<[WriteCvtFP]> {
  bits<5> dst;
  // if dp_operation then UInt(D:Vd) else UInt(Vd:D);
  let Inst{22} = dst{0};
  let Inst{15-12} = dst{4-1};
}

// Double Precision register
class AVConv1XInsD_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
                          bit op5, dag oops, dag iops, InstrItinClass itin,
                          string opc, string asm, list<dag> pattern>
  : AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern>,
    Sched<[WriteCvtFP]> {
  bits<5> dst;
  // if dp_operation then UInt(D:Vd) else UInt(Vd:D);
  let Inst{22} = dst{4};
  let Inst{15-12} = dst{3-0};
}

def VTOSHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 0,
                       (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
                 IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VTOUHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 0,
                       (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
                 IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VTOSLS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 1,
                       (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
                 IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VTOULS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 1,
                       (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
                 IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VTOSHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 0,
                       (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
                 IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits", []>;

def VTOUHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 0,
                       (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
                 IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits", []>;

def VTOSLD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 1,
                       (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
                 IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits", []>;

def VTOULD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 1,
                       (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
                 IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits", []>;

// Fixed-Point to FP:

def VSHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 0,
                       (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
                 IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VUHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 0,
                       (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
                 IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VSLTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 1,
                       (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
                 IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VULTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 1,
                       (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
                 IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits", []> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def VSHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 0,
                       (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
                 IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits", []>;

def VUHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 0,
                       (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
                 IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits", []>;

def VSLTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 1,
                       (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
                 IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits", []>;

def VULTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 1,
                       (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
                 IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits", []>;

} // End of 'let Constraints = "$a = $dst" in'

//===----------------------------------------------------------------------===//
// FP Multiply-Accumulate Operations.
//

def VMLAD : ADbI<0b11100, 0b00, 0, 0,
                 (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                 IIC_fpMAC64, "vmla", ".f64\t$Dd, $Dn, $Dm",
                 [(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
                                          (f64 DPR:$Ddin)))]>,
              RegConstraint<"$Ddin = $Dd">,
              Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;

def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpMAC32, "vmla", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
                                           SPR:$Sdin))]>,
              RegConstraint<"$Sdin = $Sd">,
              Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
          (VMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
          (VMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx,DontUseFusedMAC]>;

def VMLSD : ADbI<0b11100, 0b00, 1, 0,
                 (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                 IIC_fpMAC64, "vmls", ".f64\t$Dd, $Dn, $Dm",
                 [(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
                                          (f64 DPR:$Ddin)))]>,
              RegConstraint<"$Ddin = $Dd">,
              Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;

def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpMAC32, "vmls", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
                                           SPR:$Sdin))]>,
              RegConstraint<"$Sdin = $Sd">,
              Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
          (VMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
          (VMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;

def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpMAC64, "vnmla", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
                                          (f64 DPR:$Ddin)))]>,
                RegConstraint<"$Ddin = $Dd">,
                Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;

def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpMAC32, "vnmla", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
                                           SPR:$Sdin))]>,
                RegConstraint<"$Sdin = $Sd">,
                Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
          (VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
          (VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;

def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpMAC64, "vnmls", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm),
                                           (f64 DPR:$Ddin)))]>,
               RegConstraint<"$Ddin = $Dd">,
               Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;

def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpMAC32, "vnmls", ".f32\t$Sd, $Sn, $Sm",
             [(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
                         RegConstraint<"$Sdin = $Sd">,
                Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines on A8.
  let D = VFPNeonA8Domain;
}

def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin),
          (VNMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
          (VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;

//===----------------------------------------------------------------------===//
// Fused FP Multiply-Accumulate Operations.
//
def VFMAD : ADbI<0b11101, 0b10, 0, 0,
                 (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                 IIC_fpFMAC64, "vfma", ".f64\t$Dd, $Dn, $Dm",
                 [(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
                                          (f64 DPR:$Ddin)))]>,
              RegConstraint<"$Ddin = $Dd">,
              Requires<[HasVFP4,UseFusedMAC]>;

def VFMAS : ASbIn<0b11101, 0b10, 0, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpFMAC32, "vfma", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
                                           SPR:$Sdin))]>,
              RegConstraint<"$Sdin = $Sd">,
              Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines.
}

def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
          (VFMAD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP4,UseFusedMAC]>;
def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
          (VFMAS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;

// Match @llvm.fma.* intrinsics
// (fma x, y, z) -> (vfms z, x, y)
def : Pat<(f64 (fma DPR:$Dn, DPR:$Dm, DPR:$Ddin)),
          (VFMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(f32 (fma SPR:$Sn, SPR:$Sm, SPR:$Sdin)),
          (VFMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;

def VFMSD : ADbI<0b11101, 0b10, 1, 0,
                 (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                 IIC_fpFMAC64, "vfms", ".f64\t$Dd, $Dn, $Dm",
                 [(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
                                          (f64 DPR:$Ddin)))]>,
              RegConstraint<"$Ddin = $Dd">,
              Requires<[HasVFP4,UseFusedMAC]>;

def VFMSS : ASbIn<0b11101, 0b10, 1, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpFMAC32, "vfms", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
                                           SPR:$Sdin))]>,
              RegConstraint<"$Sdin = $Sd">,
              Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines.
}

def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
          (VFMSD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP4,UseFusedMAC]>;
def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
          (VFMSS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;

// Match @llvm.fma.* intrinsics
// (fma (fneg x), y, z) -> (vfms z, x, y)
def : Pat<(f64 (fma (fneg DPR:$Dn), DPR:$Dm, DPR:$Ddin)),
          (VFMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(f32 (fma (fneg SPR:$Sn), SPR:$Sm, SPR:$Sdin)),
          (VFMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;
// (fma x, (fneg y), z) -> (vfms z, x, y)
def : Pat<(f64 (fma DPR:$Dn, (fneg DPR:$Dm), DPR:$Ddin)),
          (VFMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(f32 (fma SPR:$Sn, (fneg SPR:$Sm), SPR:$Sdin)),
          (VFMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;

def VFNMAD : ADbI<0b11101, 0b01, 1, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpFMAC64, "vfnma", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
                                          (f64 DPR:$Ddin)))]>,
                RegConstraint<"$Ddin = $Dd">,
                Requires<[HasVFP4,UseFusedMAC]>;

def VFNMAS : ASbI<0b11101, 0b01, 1, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpFMAC32, "vfnma", ".f32\t$Sd, $Sn, $Sm",
                  [(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
                                           SPR:$Sdin))]>,
                RegConstraint<"$Sdin = $Sd">,
                Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines.
}

def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
          (VFNMAD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP4,UseFusedMAC]>;
def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
          (VFNMAS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;

// Match @llvm.fma.* intrinsics
// (fneg (fma x, y, z)) -> (vfnma z, x, y)
def : Pat<(fneg (fma (f64 DPR:$Dn), (f64 DPR:$Dm), (f64 DPR:$Ddin))),
          (VFNMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(fneg (fma (f32 SPR:$Sn), (f32 SPR:$Sm), (f32 SPR:$Sdin))),
          (VFNMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;
// (fma (fneg x), y, (fneg z)) -> (vfnma z, x, y)
def : Pat<(f64 (fma (fneg DPR:$Dn), DPR:$Dm, (fneg DPR:$Ddin))),
          (VFNMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(f32 (fma (fneg SPR:$Sn), SPR:$Sm, (fneg SPR:$Sdin))),
          (VFNMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;

def VFNMSD : ADbI<0b11101, 0b01, 0, 0,
                  (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
                  IIC_fpFMAC64, "vfnms", ".f64\t$Dd, $Dn, $Dm",
                  [(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm),
                                           (f64 DPR:$Ddin)))]>,
               RegConstraint<"$Ddin = $Dd">,
               Requires<[HasVFP4,UseFusedMAC]>;

def VFNMSS : ASbI<0b11101, 0b01, 0, 0,
                  (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
                  IIC_fpFMAC32, "vfnms", ".f32\t$Sd, $Sn, $Sm",
             [(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
                         RegConstraint<"$Sdin = $Sd">,
                  Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> {
  // Some single precision VFP instructions may be executed on both NEON and
  // VFP pipelines.
}

def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin),
          (VFNMSD DPR:$dstin, DPR:$a, DPR:$b)>,
          Requires<[HasVFP4,UseFusedMAC]>;
def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
          (VFNMSS SPR:$dstin, SPR:$a, SPR:$b)>,
          Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;

// Match @llvm.fma.* intrinsics

// (fma x, y, (fneg z)) -> (vfnms z, x, y))
def : Pat<(f64 (fma DPR:$Dn, DPR:$Dm, (fneg DPR:$Ddin))),
          (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(f32 (fma SPR:$Sn, SPR:$Sm, (fneg SPR:$Sdin))),
          (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;
// (fneg (fma (fneg x), y, z)) -> (vfnms z, x, y)
def : Pat<(fneg (f64 (fma (fneg DPR:$Dn), DPR:$Dm, DPR:$Ddin))),
          (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(fneg (f32 (fma (fneg SPR:$Sn), SPR:$Sm, SPR:$Sdin))),
          (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;
// (fneg (fma x, (fneg y), z) -> (vfnms z, x, y)
def : Pat<(fneg (f64 (fma DPR:$Dn, (fneg DPR:$Dm), DPR:$Ddin))),
          (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
      Requires<[HasVFP4]>;
def : Pat<(fneg (f32 (fma SPR:$Sn, (fneg SPR:$Sm), SPR:$Sdin))),
          (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
      Requires<[HasVFP4]>;

//===----------------------------------------------------------------------===//
// FP Conditional moves.
//

let neverHasSideEffects = 1 in {
def VMOVDcc  : ARMPseudoInst<(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm, pred:$p),
                    4, IIC_fpUNA64,
                    [/*(set DPR:$Dd, (ARMcmov DPR:$Dn, DPR:$Dm, imm:$cc))*/]>,
                 RegConstraint<"$Dn = $Dd">;

def VMOVScc  : ARMPseudoInst<(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm, pred:$p),
                    4, IIC_fpUNA32,
                    [/*(set SPR:$Sd, (ARMcmov SPR:$Sn, SPR:$Sm, imm:$cc))*/]>,
                 RegConstraint<"$Sn = $Sd">;
} // neverHasSideEffects

//===----------------------------------------------------------------------===//
// Move from VFP System Register to ARM core register.
//

class MovFromVFP<bits<4> opc19_16, dag oops, dag iops, string opc, string asm,
                 list<dag> pattern>:
  VFPAI<oops, iops, VFPMiscFrm, IIC_fpSTAT, opc, asm, pattern> {

  // Instruction operand.
  bits<4> Rt;

  let Inst{27-20} = 0b11101111;
  let Inst{19-16} = opc19_16;
  let Inst{15-12} = Rt;
  let Inst{11-8}  = 0b1010;
  let Inst{7}     = 0;
  let Inst{6-5}   = 0b00;
  let Inst{4}     = 1;
  let Inst{3-0}   = 0b0000;
}

// APSR is the application level alias of CPSR. This FPSCR N, Z, C, V flags
// to APSR.
let Defs = [CPSR], Uses = [FPSCR_NZCV], Rt = 0b1111 /* apsr_nzcv */ in
def FMSTAT : MovFromVFP<0b0001 /* fpscr */, (outs), (ins),
                        "vmrs", "\tAPSR_nzcv, fpscr", [(arm_fmstat)]>;

// Application level FPSCR -> GPR
let hasSideEffects = 1, Uses = [FPSCR] in
def VMRS : MovFromVFP<0b0001 /* fpscr */, (outs GPR:$Rt), (ins),
                      "vmrs", "\t$Rt, fpscr",
                      [(set GPR:$Rt, (int_arm_get_fpscr))]>;

// System level FPEXC, FPSID -> GPR
let Uses = [FPSCR] in {
  def VMRS_FPEXC : MovFromVFP<0b1000 /* fpexc */, (outs GPR:$Rt), (ins),
                              "vmrs", "\t$Rt, fpexc", []>;
  def VMRS_FPSID : MovFromVFP<0b0000 /* fpsid */, (outs GPR:$Rt), (ins),
                              "vmrs", "\t$Rt, fpsid", []>;
  def VMRS_MVFR0 : MovFromVFP<0b0111 /* mvfr0 */, (outs GPR:$Rt), (ins),
                              "vmrs", "\t$Rt, mvfr0", []>;
  def VMRS_MVFR1 : MovFromVFP<0b0110 /* mvfr1 */, (outs GPR:$Rt), (ins),
                              "vmrs", "\t$Rt, mvfr1", []>;
}

//===----------------------------------------------------------------------===//
// Move from ARM core register to VFP System Register.
//

class MovToVFP<bits<4> opc19_16, dag oops, dag iops, string opc, string asm,
               list<dag> pattern>:
  VFPAI<oops, iops, VFPMiscFrm, IIC_fpSTAT, opc, asm, pattern> {

  // Instruction operand.
  bits<4> src;

  // Encode instruction operand.
  let Inst{15-12} = src;

  let Inst{27-20} = 0b11101110;
  let Inst{19-16} = opc19_16;
  let Inst{11-8}  = 0b1010;
  let Inst{7}     = 0;
  let Inst{4}     = 1;
}

let Defs = [FPSCR] in {
  // Application level GPR -> FPSCR
  def VMSR : MovToVFP<0b0001 /* fpscr */, (outs), (ins GPR:$src),
                      "vmsr", "\tfpscr, $src", [(int_arm_set_fpscr GPR:$src)]>;
  // System level GPR -> FPEXC
  def VMSR_FPEXC : MovToVFP<0b1000 /* fpexc */, (outs), (ins GPR:$src),
                      "vmsr", "\tfpexc, $src", []>;
  // System level GPR -> FPSID
  def VMSR_FPSID : MovToVFP<0b0000 /* fpsid */, (outs), (ins GPR:$src),
                      "vmsr", "\tfpsid, $src", []>;
}

//===----------------------------------------------------------------------===//
// Misc.
//

// Materialize FP immediates. VFP3 only.
let isReMaterializable = 1 in {
def FCONSTD : VFPAI<(outs DPR:$Dd), (ins vfp_f64imm:$imm),
                    VFPMiscFrm, IIC_fpUNA64,
                    "vmov", ".f64\t$Dd, $imm",
                    [(set DPR:$Dd, vfp_f64imm:$imm)]>, Requires<[HasVFP3]> {
  bits<5> Dd;
  bits<8> imm;

  let Inst{27-23} = 0b11101;
  let Inst{22}    = Dd{4};
  let Inst{21-20} = 0b11;
  let Inst{19-16} = imm{7-4};
  let Inst{15-12} = Dd{3-0};
  let Inst{11-9}  = 0b101;
  let Inst{8}     = 1;          // Double precision.
  let Inst{7-4}   = 0b0000;
  let Inst{3-0}   = imm{3-0};
}

def FCONSTS : VFPAI<(outs SPR:$Sd), (ins vfp_f32imm:$imm),
                     VFPMiscFrm, IIC_fpUNA32,
                     "vmov", ".f32\t$Sd, $imm",
                     [(set SPR:$Sd, vfp_f32imm:$imm)]>, Requires<[HasVFP3]> {
  bits<5> Sd;
  bits<8> imm;

  let Inst{27-23} = 0b11101;
  let Inst{22}    = Sd{0};
  let Inst{21-20} = 0b11;
  let Inst{19-16} = imm{7-4};
  let Inst{15-12} = Sd{4-1};
  let Inst{11-9}  = 0b101;
  let Inst{8}     = 0;          // Single precision.
  let Inst{7-4}   = 0b0000;
  let Inst{3-0}   = imm{3-0};
}
}

//===----------------------------------------------------------------------===//
// Assembler aliases.
//
// A few mnemnoic aliases for pre-unifixed syntax. We don't guarantee to
// support them all, but supporting at least some of the basics is
// good to be friendly.
def : VFP2MnemonicAlias<"flds", "vldr">;
def : VFP2MnemonicAlias<"fldd", "vldr">;
def : VFP2MnemonicAlias<"fmrs", "vmov">;
def : VFP2MnemonicAlias<"fmsr", "vmov">;
def : VFP2MnemonicAlias<"fsqrts", "vsqrt">;
def : VFP2MnemonicAlias<"fsqrtd", "vsqrt">;
def : VFP2MnemonicAlias<"fadds", "vadd.f32">;
def : VFP2MnemonicAlias<"faddd", "vadd.f64">;
def : VFP2MnemonicAlias<"fmrdd", "vmov">;
def : VFP2MnemonicAlias<"fmrds", "vmov">;
def : VFP2MnemonicAlias<"fmrrd", "vmov">;
def : VFP2MnemonicAlias<"fmdrr", "vmov">;
def : VFP2MnemonicAlias<"fmuls", "vmul.f32">;
def : VFP2MnemonicAlias<"fmuld", "vmul.f64">;
def : VFP2MnemonicAlias<"fnegs", "vneg.f32">;
def : VFP2MnemonicAlias<"fnegd", "vneg.f64">;
def : VFP2MnemonicAlias<"ftosizd", "vcvt.s32.f64">;
def : VFP2MnemonicAlias<"ftosid", "vcvtr.s32.f64">;
def : VFP2MnemonicAlias<"ftosizs", "vcvt.s32.f32">;
def : VFP2MnemonicAlias<"ftosis", "vcvtr.s32.f32">;
def : VFP2MnemonicAlias<"ftouizd", "vcvt.u32.f64">;
def : VFP2MnemonicAlias<"ftouid", "vcvtr.u32.f64">;
def : VFP2MnemonicAlias<"ftouizs", "vcvt.u32.f32">;
def : VFP2MnemonicAlias<"ftouis", "vcvtr.u32.f32">;
def : VFP2MnemonicAlias<"fsitod", "vcvt.f64.s32">;
def : VFP2MnemonicAlias<"fsitos", "vcvt.f32.s32">;
def : VFP2MnemonicAlias<"fuitod", "vcvt.f64.u32">;
def : VFP2MnemonicAlias<"fuitos", "vcvt.f32.u32">;
def : VFP2MnemonicAlias<"fsts", "vstr">;
def : VFP2MnemonicAlias<"fstd", "vstr">;
def : VFP2MnemonicAlias<"fmacd", "vmla.f64">;
def : VFP2MnemonicAlias<"fmacs", "vmla.f32">;
def : VFP2MnemonicAlias<"fcpys", "vmov.f32">;
def : VFP2MnemonicAlias<"fcpyd", "vmov.f64">;
def : VFP2MnemonicAlias<"fcmps", "vcmp.f32">;
def : VFP2MnemonicAlias<"fcmpd", "vcmp.f64">;
def : VFP2MnemonicAlias<"fdivs", "vdiv.f32">;
def : VFP2MnemonicAlias<"fdivd", "vdiv.f64">;
def : VFP2MnemonicAlias<"fmrx", "vmrs">;
def : VFP2MnemonicAlias<"fmxr", "vmsr">;

// Be friendly and accept the old form of zero-compare
def : VFP2InstAlias<"fcmpzd${p} $val", (VCMPZD DPR:$val, pred:$p)>;
def : VFP2InstAlias<"fcmpzs${p} $val", (VCMPZS SPR:$val, pred:$p)>;


def : VFP2InstAlias<"fmstat${p}", (FMSTAT pred:$p)>;
def : VFP2InstAlias<"fadds${p} $Sd, $Sn, $Sm",
                    (VADDS SPR:$Sd, SPR:$Sn, SPR:$Sm, pred:$p)>;
def : VFP2InstAlias<"faddd${p} $Dd, $Dn, $Dm",
                    (VADDD DPR:$Dd, DPR:$Dn, DPR:$Dm, pred:$p)>;
def : VFP2InstAlias<"fsubs${p} $Sd, $Sn, $Sm",
                    (VSUBS SPR:$Sd, SPR:$Sn, SPR:$Sm, pred:$p)>;
def : VFP2InstAlias<"fsubd${p} $Dd, $Dn, $Dm",
                    (VSUBD DPR:$Dd, DPR:$Dn, DPR:$Dm, pred:$p)>;

// No need for the size suffix on VSQRT. It's implied by the register classes.
def : VFP2InstAlias<"vsqrt${p} $Sd, $Sm", (VSQRTS SPR:$Sd, SPR:$Sm, pred:$p)>;
def : VFP2InstAlias<"vsqrt${p} $Dd, $Dm", (VSQRTD DPR:$Dd, DPR:$Dm, pred:$p)>;

// VLDR/VSTR accept an optional type suffix.
def : VFP2InstAlias<"vldr${p}.32 $Sd, $addr",
                    (VLDRS SPR:$Sd, addrmode5:$addr, pred:$p)>;
def : VFP2InstAlias<"vstr${p}.32 $Sd, $addr",
                    (VSTRS SPR:$Sd, addrmode5:$addr, pred:$p)>;
def : VFP2InstAlias<"vldr${p}.64 $Dd, $addr",
                    (VLDRD DPR:$Dd, addrmode5:$addr, pred:$p)>;
def : VFP2InstAlias<"vstr${p}.64 $Dd, $addr",
                    (VSTRD DPR:$Dd, addrmode5:$addr, pred:$p)>;

// VMOV can accept optional 32-bit or less data type suffix suffix.
def : VFP2InstAlias<"vmov${p}.8 $Rt, $Sn",
                    (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.16 $Rt, $Sn",
                    (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.32 $Rt, $Sn",
                    (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.8 $Sn, $Rt",
                    (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.16 $Sn, $Rt",
                    (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.32 $Sn, $Rt",
                    (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>;

def : VFP2InstAlias<"vmov${p}.f64 $Rt, $Rt2, $Dn",
                    (VMOVRRD GPR:$Rt, GPR:$Rt2, DPR:$Dn, pred:$p)>;
def : VFP2InstAlias<"vmov${p}.f64 $Dn, $Rt, $Rt2",
                    (VMOVDRR DPR:$Dn, GPR:$Rt, GPR:$Rt2, pred:$p)>;

// VMOVS doesn't need the .f32 to disambiguate from the NEON encoding the way
// VMOVD does.
def : VFP2InstAlias<"vmov${p} $Sd, $Sm",
                    (VMOVS SPR:$Sd, SPR:$Sm, pred:$p)>;