ARMScheduleSwift.td 50.5 KB
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
//=- ARMScheduleSwift.td - Swift Scheduling Definitions -*- tablegen -*----===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the itinerary class data for the Swift processor..
//
//===----------------------------------------------------------------------===//

// ===---------------------------------------------------------------------===//
// This section contains legacy support for itineraries. This is
// required until SD and PostRA schedulers are replaced by MachineScheduler.

def SW_DIS0 : FuncUnit;
def SW_DIS1 : FuncUnit;
def SW_DIS2 : FuncUnit;

def SW_ALU0 : FuncUnit;
def SW_ALU1 : FuncUnit;
def SW_LS   : FuncUnit;
def SW_IDIV : FuncUnit;
def SW_FDIV : FuncUnit;

// FIXME: Need bypasses.
// FIXME: Model the multiple stages of IIC_iMOVix2, IIC_iMOVix2addpc, and
//        IIC_iMOVix2ld better.
// FIXME: Model the special immediate shifts that are not microcoded.
// FIXME: Do we need to model the fact that uses of r15 in a micro-op force it
//        to issue on pipe 1?
// FIXME: Model the pipelined behavior of CMP / TST instructions.
// FIXME: Better model the microcode stages of multiply instructions, especially
//        conditional variants.
// FIXME: Add preload instruction when it is documented.
// FIXME: Model non-pipelined nature of FP div / sqrt unit.

// Swift machine model for scheduling and other instruction cost heuristics.
def SwiftModel : SchedMachineModel {
  let IssueWidth = 3; // 3 micro-ops are dispatched per cycle.
  let MicroOpBufferSize = 45; // Based on NEON renamed registers.
  let LoadLatency = 3;
  let MispredictPenalty = 14; // A branch direction mispredict.
  let CompleteModel = 0;      // FIXME: Remove if all instructions are covered.

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

// Swift predicates.
def IsFastImmShiftSwiftPred : SchedPredicate<[{TII->isSwiftFastImmShift(MI)}]>;

// Swift resource mapping.
let SchedModel = SwiftModel in {
  // Processor resources.
  def SwiftUnitP01 : ProcResource<2>; // ALU unit.
  def SwiftUnitP0 : ProcResource<1> { let Super = SwiftUnitP01; } // Mul unit.
  def SwiftUnitP1 : ProcResource<1> { let Super = SwiftUnitP01; } // Br unit.
  def SwiftUnitP2 : ProcResource<1>; // LS unit.
  def SwiftUnitDiv : ProcResource<1>;

  // Generic resource requirements.
  def SwiftWriteP0OneCycle : SchedWriteRes<[SwiftUnitP0]>;
  def SwiftWriteP0TwoCycle : SchedWriteRes<[SwiftUnitP0]> { let Latency = 2; }
  def SwiftWriteP0FourCycle : SchedWriteRes<[SwiftUnitP0]> { let Latency = 4; }
  def SwiftWriteP0SixCycle : SchedWriteRes<[SwiftUnitP0]> { let Latency = 6; }
  def SwiftWriteP0P1FourCycle : SchedWriteRes<[SwiftUnitP0, SwiftUnitP1]> {
    let Latency = 4;
  }
  def SwiftWriteP0P1SixCycle : SchedWriteRes<[SwiftUnitP0, SwiftUnitP1]> {
    let Latency = 6;
  }
  def SwiftWriteP01OneCycle : SchedWriteRes<[SwiftUnitP01]>;
  def SwiftWriteP1TwoCycle : SchedWriteRes<[SwiftUnitP1]> { let Latency = 2; }
  def SwiftWriteP1FourCycle : SchedWriteRes<[SwiftUnitP1]> { let Latency = 4; }
  def SwiftWriteP1SixCycle : SchedWriteRes<[SwiftUnitP1]> { let Latency = 6; }
  def SwiftWriteP1EightCycle : SchedWriteRes<[SwiftUnitP1]> { let Latency = 8; }
  def SwiftWriteP1TwelveCyc : SchedWriteRes<[SwiftUnitP1]> { let Latency = 12; }
  def SwiftWriteP01OneCycle2x : WriteSequence<[SwiftWriteP01OneCycle], 2>;
  def SwiftWriteP01OneCycle3x : WriteSequence<[SwiftWriteP01OneCycle], 3>;
  def SwiftWriteP01TwoCycle : SchedWriteRes<[SwiftUnitP01]> { let Latency = 2; }
  def SwiftWriteP01ThreeCycleTwoUops : SchedWriteRes<[SwiftUnitP01,
                                                      SwiftUnitP01]> {
    let Latency = 3;
    let NumMicroOps = 2;
  }
  def SwiftWriteP0ThreeCycleThreeUops : SchedWriteRes<[SwiftUnitP0]> {
    let Latency = 3;
    let NumMicroOps = 3;
    let ResourceCycles = [3];
  }
  // Plain load without writeback.
  def SwiftWriteP2ThreeCycle : SchedWriteRes<[SwiftUnitP2]> {
    let Latency = 3;
  }
  def SwiftWriteP2FourCycle : SchedWriteRes<[SwiftUnitP2]> {
    let Latency = 4;
  }
  // A store does not write to a register.
  def SwiftWriteP2 : SchedWriteRes<[SwiftUnitP2]> {
    let Latency = 0;
  }
  foreach Num = 1-4 in {
    def SwiftWrite#Num#xP2 : WriteSequence<[SwiftWriteP2], Num>;
  }
  def SwiftWriteP01OneCycle2x_load : WriteSequence<[SwiftWriteP01OneCycle,
                                                    SwiftWriteP01OneCycle,
                                                    SwiftWriteP2ThreeCycle]>;
  // 4.2.4 Arithmetic and Logical.
  // ALU operation register shifted by immediate variant.
  def SwiftWriteALUsi : SchedWriteVariant<[
    // lsl #2, lsl #1, or lsr #1.
    SchedVar<IsFastImmShiftSwiftPred, [SwiftWriteP01TwoCycle]>,
    SchedVar<NoSchedPred,             [WriteALU]>
  ]>;
  def SwiftWriteALUsr : SchedWriteVariant<[
    SchedVar<IsPredicatedPred, [SwiftWriteP01ThreeCycleTwoUops]>,
    SchedVar<NoSchedPred,      [SwiftWriteP01TwoCycle]>
  ]>;
  def SwiftWriteALUSsr : SchedWriteVariant<[
    SchedVar<IsPredicatedPred, [SwiftWriteP0ThreeCycleThreeUops]>,
    SchedVar<NoSchedPred,      [SwiftWriteP01TwoCycle]>
  ]>;
  def SwiftReadAdvanceALUsr : SchedReadVariant<[
    SchedVar<IsPredicatedPred, [SchedReadAdvance<2>]>,
    SchedVar<NoSchedPred,      [NoReadAdvance]>
  ]>;
  // ADC,ADD,NEG,RSB,RSC,SBC,SUB,ADR
  // AND,BIC,EOR,ORN,ORR
  // CLZ,RBIT,REV,REV16,REVSH,PKH
  def : WriteRes<WriteALU, [SwiftUnitP01]>;
  def : SchedAlias<WriteALUsi, SwiftWriteALUsi>;
  def : SchedAlias<WriteALUsr, SwiftWriteALUsr>;
  def : SchedAlias<WriteALUSsr, SwiftWriteALUSsr>;
  def : ReadAdvance<ReadALU, 0>;
  def : SchedAlias<ReadALUsr, SwiftReadAdvanceALUsr>;
  def : SchedAlias<WriteLd, SwiftWriteP2ThreeCycle>;
  def : SchedAlias<WriteST, SwiftWriteP2>;


  def SwiftChooseShiftKindP01OneOrTwoCycle : SchedWriteVariant<[
    SchedVar<IsFastImmShiftSwiftPred, [SwiftWriteP01OneCycle]>,
    SchedVar<NoSchedPred,             [SwiftWriteP01TwoCycle]>
  ]>;

  // 4.2.5 Integer comparison
  def : WriteRes<WriteCMP, [SwiftUnitP01]>;
  def : SchedAlias<WriteCMPsi, SwiftChooseShiftKindP01OneOrTwoCycle>;
  def : SchedAlias<WriteCMPsr, SwiftWriteP01TwoCycle>;

  // 4.2.6 Shift, Move
  // Shift
  //  ASR,LSL,ROR,RRX
  //  MOV(register-shiftedregister)  MVN(register-shiftedregister)
  // Move
  //  MOV,MVN
  //  MOVT
  // Sign/Zero extension
  def : InstRW<[SwiftWriteP01OneCycle],
               (instregex "SXTB", "SXTH", "SXTB16", "UXTB", "UXTH", "UXTB16",
                          "t2SXTB", "t2SXTH", "t2SXTB16", "t2UXTB", "t2UXTH",
                          "t2UXTB16")>;
  // Pseudo instructions.
  def : InstRW<[SwiftWriteP01OneCycle2x],
        (instregex "MOVCCi32imm", "MOVi32imm", "t2MOVCCi32imm",
                   "t2MOVi32imm")>;
  def : InstRW<[SwiftWriteP01OneCycle3x],
        (instregex "MOV_ga_pcrel", "t2MOV_ga_pcrel", "t2MOVi16_ga_pcrel")>;
  def : InstRW<[SwiftWriteP01OneCycle2x_load],
        (instregex "MOV_ga_pcrel_ldr")>;

  def SwiftWriteP0TwoCycleTwoUops : WriteSequence<[SwiftWriteP0OneCycle], 2>;

  def SwiftPredP0OneOrTwoCycle : SchedWriteVariant<[
    SchedVar<IsPredicatedPred, [ SwiftWriteP0TwoCycleTwoUops ]>,
    SchedVar<NoSchedPred,     [ SwiftWriteP0OneCycle ]>
  ]>;

  // 4.2.7 Select
  // SEL
  def : InstRW<[SwiftPredP0OneOrTwoCycle], (instregex "SEL", "t2SEL")>;

  // 4.2.8 Bitfield
  // BFI,BFC, SBFX,UBFX
  def : InstRW< [SwiftWriteP01TwoCycle],
        (instregex "BFC", "BFI", "UBFX", "SBFX", "(t|t2)BFC", "(t|t2)BFI",
        "(t|t2)UBFX", "(t|t2)SBFX")>;

  // 4.2.9 Saturating arithmetic
  def : InstRW< [SwiftWriteP01TwoCycle],
        (instregex "QADD", "QSUB", "QDADD", "QDSUB", "SSAT", "SSAT16", "USAT",
        "USAT16", "QADD8", "QADD16", "QSUB8", "QSUB16", "QASX", "QSAX",
        "UQADD8", "UQADD16","UQSUB8","UQSUB16","UQASX","UQSAX", "t2QADD",
        "t2QSUB", "t2QDADD", "t2QDSUB", "t2SSAT", "t2SSAT16", "t2USAT",
        "t2QADD8", "t2QADD16", "t2QSUB8", "t2QSUB16", "t2QASX", "t2QSAX",
        "t2UQADD8", "t2UQADD16","t2UQSUB8","t2UQSUB16","t2UQASX","t2UQSAX")>;

  // 4.2.10 Parallel Arithmetic
  // Not flag setting.
  def : InstRW< [SwiftWriteALUsr],
        (instregex "SADD8", "SADD16", "SSUB8", "SSUB16", "SASX", "SSAX",
        "UADD8", "UADD16", "USUB8", "USUB16", "UASX", "USAX", "t2SADD8",
        "t2SADD16", "t2SSUB8", "t2SSUB16", "t2SASX", "t2SSAX", "t2UADD8",
        "t2UADD16", "t2USUB8", "t2USUB16", "t2UASX", "t2USAX")>;
  // Flag setting.
  def : InstRW< [SwiftWriteP01TwoCycle],
       (instregex "SHADD8", "SHADD16", "SHSUB8", "SHSUB16", "SHASX", "SHSAX",
       "SXTAB", "SXTAB16", "SXTAH", "UHADD8", "UHADD16", "UHSUB8", "UHSUB16",
       "UHASX", "UHSAX", "UXTAB", "UXTAB16", "UXTAH", "t2SHADD8", "t2SHADD16",
       "t2SHSUB8", "t2SHSUB16", "t2SHASX", "t2SHSAX", "t2SXTAB", "t2SXTAB16",
       "t2SXTAH", "t2UHADD8", "t2UHADD16", "t2UHSUB8", "t2UHSUB16", "t2UHASX",
       "t2UHSAX", "t2UXTAB", "t2UXTAB16", "t2UXTAH")>;

  // 4.2.11 Sum of Absolute Difference
  def : InstRW< [SwiftWriteP0P1FourCycle], (instregex "USAD8") >;
  def : InstRW<[SwiftWriteP0P1FourCycle, ReadALU, ReadALU, SchedReadAdvance<2>],
        (instregex "USADA8")>;

  // 4.2.12 Integer Multiply (32-bit result)
  // Two sources.
  def : InstRW< [SwiftWriteP0FourCycle],
        (instregex "MUL", "SMMUL", "SMMULR", "SMULBB", "SMULBT",
        "SMULTB", "SMULTT", "SMULWB", "SMULWT", "SMUSD", "SMUSDX", "t2MUL",
        "t2SMMUL", "t2SMMULR", "t2SMULBB", "t2SMULBT", "t2SMULTB", "t2SMULTT",
        "t2SMULWB", "t2SMULWT", "t2SMUSD")>;

  def SwiftWriteP0P01FiveCycleTwoUops :
      SchedWriteRes<[SwiftUnitP0, SwiftUnitP01]>  {
    let Latency = 5;
  }

  def SwiftPredP0P01FourFiveCycle : SchedWriteVariant<[
    SchedVar<IsPredicatedPred, [ SwiftWriteP0P01FiveCycleTwoUops ]>,
    SchedVar<NoSchedPred,      [ SwiftWriteP0FourCycle ]>
  ]>;

  def SwiftReadAdvanceFourCyclesPred : SchedReadVariant<[
     SchedVar<IsPredicatedPred, [SchedReadAdvance<4>]>,
     SchedVar<NoSchedPred,      [ReadALU]>
  ]>;

  // Multiply accumulate, three sources
  def : InstRW< [SwiftPredP0P01FourFiveCycle, ReadALU, ReadALU,
                 SwiftReadAdvanceFourCyclesPred],
        (instregex "MLA", "MLS", "SMMLA", "SMMLAR", "SMMLS", "SMMLSR",
        "t2MLA", "t2MLS", "t2SMMLA", "t2SMMLAR", "t2SMMLS",
        "t2SMMLSR")>;

  // 4.2.13 Integer Multiply (32-bit result, Q flag)
  def : InstRW< [SwiftWriteP0FourCycle],
        (instregex "SMUAD", "SMUADX", "t2SMUAD", "t2SMUADX")>;
  def : InstRW< [SwiftPredP0P01FourFiveCycle, ReadALU, ReadALU,
                 SwiftReadAdvanceFourCyclesPred],
        (instregex "SMLABB", "SMLABT", "SMLATB", "SMLATT", "SMLSD", "SMLSDX",
        "SMLAWB", "SMLAWT", "t2SMLABB", "t2SMLABT", "t2SMLATB", "t2SMLATT",
        "t2SMLSD", "t2SMLSDX", "t2SMLAWB", "t2SMLAWT")>;
  def : InstRW< [SwiftPredP0P01FourFiveCycle],
        (instregex "SMLAD", "SMLADX", "t2SMLAD", "t2SMLADX")>;

  def SwiftP0P0P01FiveCycle : SchedWriteRes<[SwiftUnitP0, SwiftUnitP01]> {
    let Latency = 5;
    let NumMicroOps = 3;
    let ResourceCycles = [2, 1];
  }
  def SwiftWrite1Cycle : SchedWriteRes<[]> {
    let Latency = 1;
    let NumMicroOps = 0;
  }
  def SwiftWrite5Cycle : SchedWriteRes<[]> {
    let Latency = 5;
    let NumMicroOps = 0;
  }
  def SwiftWrite6Cycle : SchedWriteRes<[]> {
    let Latency = 6;
    let NumMicroOps = 0;
  }

  // 4.2.14 Integer Multiply, Long
  def : InstRW< [SwiftP0P0P01FiveCycle, SwiftWrite5Cycle],
        (instregex "SMULL$", "UMULL$", "t2SMULL$", "t2UMULL$")>;

  def Swift2P03P01FiveCycle : SchedWriteRes<[SwiftUnitP0, SwiftUnitP01]> {
    let Latency = 7;
    let NumMicroOps = 5;
    let ResourceCycles = [2, 3];
  }

  // Aliasing sub-target specific WriteRes to generic ones
  def : SchedAlias<WriteMUL16, SwiftWriteP0FourCycle>;
  def : SchedAlias<WriteMUL32, SwiftWriteP0FourCycle>;
  def : SchedAlias<WriteMUL64Lo, SwiftP0P0P01FiveCycle>;
  def : SchedAlias<WriteMUL64Hi, SwiftWrite5Cycle>;
  def : SchedAlias<WriteMAC16, SwiftPredP0P01FourFiveCycle>;
  def : SchedAlias<WriteMAC32, SwiftPredP0P01FourFiveCycle>;
  def : SchedAlias<WriteMAC64Lo, SwiftWrite5Cycle>;
  def : SchedAlias<WriteMAC64Hi, Swift2P03P01FiveCycle>;
  def : ReadAdvance<ReadMUL, 0>;
  def : SchedAlias<ReadMAC, SwiftReadAdvanceFourCyclesPred>;

  // 4.2.15 Integer Multiply Accumulate, Long
  // 4.2.16 Integer Multiply Accumulate, Dual
  // 4.2.17 Integer Multiply Accumulate Accumulate, Long
  // We are being a bit inaccurate here.
  def : InstRW< [SwiftWrite5Cycle, Swift2P03P01FiveCycle, ReadALU, ReadALU,
                 SchedReadAdvance<4>, SchedReadAdvance<3>],
        (instregex "SMLAL", "UMLAL", "SMLALBT",
        "SMLALTB", "SMLALTT", "SMLALD", "SMLALDX", "SMLSLD", "SMLSLDX",
        "UMAAL", "t2SMLAL", "t2UMLAL", "t2SMLALBB", "t2SMLALBT",
        "t2SMLALTB", "t2SMLALTT", "t2SMLALD", "t2SMLALDX", "t2SMLSLD", "t2SMLSLDX",
        "t2UMAAL")>;

  def SwiftDiv : SchedWriteRes<[SwiftUnitP0, SwiftUnitDiv]> {
    let NumMicroOps = 1;
    let Latency = 14;
    let ResourceCycles = [1, 14];
  }
  // 4.2.18 Integer Divide
  def : WriteRes<WriteDIV, [SwiftUnitDiv]>; // Workaround.
  def : InstRW <[SwiftDiv],
        (instregex "SDIV", "UDIV", "t2SDIV", "t2UDIV")>;

  // 4.2.19 Integer Load Single Element
  // 4.2.20 Integer Load Signextended
  def SwiftWriteP2P01ThreeCycle : SchedWriteRes<[SwiftUnitP2, SwiftUnitP01]> {
    let Latency = 3;
    let NumMicroOps = 2;
  }
  def SwiftWriteP2P01FourCycle : SchedWriteRes<[SwiftUnitP2, SwiftUnitP01]> {
    let Latency = 4;
    let NumMicroOps = 2;
  }
  def SwiftWriteP2P01P01FourCycle : SchedWriteRes<[SwiftUnitP2, SwiftUnitP01,
                                                   SwiftUnitP01]> {
    let Latency = 4;
    let NumMicroOps = 3;
  }
  def SwiftWriteP2P2ThreeCycle : SchedWriteRes<[SwiftUnitP2, SwiftUnitP2]> {
    let Latency = 3;
    let NumMicroOps = 2;
  }
  def SwiftWriteP2P2P01ThreeCycle : SchedWriteRes<[SwiftUnitP2, SwiftUnitP2,
                                                   SwiftUnitP01]> {
    let Latency = 3;
    let NumMicroOps = 3;
  }
  def SwiftWrBackOne : SchedWriteRes<[]> {
    let Latency = 1;
    let NumMicroOps = 0;
  }
  def SwiftWriteLdFour : SchedWriteRes<[]> {
    let Latency = 4;
    let NumMicroOps = 0;
  }
   // Not accurate.
  def : InstRW<[SwiftWriteP2ThreeCycle],
        (instregex "LDR(i12|rs)$", "LDRB(i12|rs)$", "t2LDR(i8|i12|s|pci)",
        "t2LDR(H|B)(i8|i12|s|pci)", "LDREX", "tLDR[BH](r|i|spi|pci|pciASM)",
        "tLDR(r|i|spi|pci|pciASM)")>;
  def : InstRW<[SwiftWriteP2ThreeCycle],
        (instregex "LDRH$",  "PICLDR$", "PICLDR(H|B)$", "LDRcp$")>;
  def : InstRW<[SwiftWriteP2P01FourCycle],
        (instregex "PICLDRS(H|B)$", "t2LDRS(H|B)(i|r|p|s)", "LDRS(H|B)$",
        "t2LDRpci_pic", "tLDRS(B|H)")>;
  def : InstRW<[SwiftWriteP2P01ThreeCycle,  SwiftWrBackOne],
        (instregex "LD(RB|R)(_|T_)(POST|PRE)_(IMM|REG)", "LDRH(_PRE|_POST)",
        "LDR(T|BT)_POST_(REG|IMM)", "LDRHT(i|r)",
        "t2LD(R|RB|RH)_(PRE|POST)", "t2LD(R|RB|RH)T")>;
  def : InstRW<[SwiftWriteP2P01P01FourCycle, SwiftWrBackOne],
        (instregex "LDR(SH|SB)(_POST|_PRE)", "t2LDR(SH|SB)(_POST|_PRE)",
        "LDRS(B|H)T(i|r)", "t2LDRS(B|H)T(i|r)?")>;

  // 4.2.21 Integer Dual Load
  // Not accurate.
  def : InstRW<[SwiftWriteP2P2ThreeCycle, SwiftWriteLdFour],
        (instregex "t2LDRDi8", "LDRD$")>;
  def : InstRW<[SwiftWriteP2P2P01ThreeCycle, SwiftWriteLdFour, SwiftWrBackOne],
        (instregex "LDRD_(POST|PRE)", "t2LDRD_(POST|PRE)")>;

  // 4.2.22 Integer Load, Multiple
  // NumReg = 1 .. 16
  foreach Lat = 3-25 in {
    def SwiftWriteLM#Lat#Cy : SchedWriteRes<[SwiftUnitP2]> {
      let Latency = Lat;
    }
    def SwiftWriteLM#Lat#CyNo : SchedWriteRes<[]> {
      let Latency = Lat;
      let NumMicroOps = 0;
    }
  }
  // Predicate.
  foreach NumAddr = 1-16 in {
    def SwiftLMAddr#NumAddr#Pred : SchedPredicate<"TII->getNumLDMAddresses(*MI) == "#NumAddr>;
  }
  def SwiftWriteLDMAddrNoWB : SchedWriteRes<[SwiftUnitP01]> { let Latency = 0; }
  def SwiftWriteLDMAddrWB : SchedWriteRes<[SwiftUnitP01, SwiftUnitP01]>;
  def SwiftWriteLM : SchedWriteVariant<[
    SchedVar<SwiftLMAddr2Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy]>,
    SchedVar<SwiftLMAddr3Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy]>,
    SchedVar<SwiftLMAddr4Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy]>,
    SchedVar<SwiftLMAddr5Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy]>,
    SchedVar<SwiftLMAddr6Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy]>,
    SchedVar<SwiftLMAddr7Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy]>,
    SchedVar<SwiftLMAddr8Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy]>,
    SchedVar<SwiftLMAddr9Pred, [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy]>,
    SchedVar<SwiftLMAddr10Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy]>,
    SchedVar<SwiftLMAddr11Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy]>,
    SchedVar<SwiftLMAddr12Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy]>,
    SchedVar<SwiftLMAddr13Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM15Cy]>,
    SchedVar<SwiftLMAddr14Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM15Cy, SwiftWriteLM16Cy]>,
    SchedVar<SwiftLMAddr15Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM15Cy, SwiftWriteLM16Cy,
                                SwiftWriteLM17Cy]>,
    SchedVar<SwiftLMAddr16Pred,[SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5Cy, SwiftWriteLM6Cy,
                                SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM12Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM15Cy, SwiftWriteLM16Cy,
                                SwiftWriteLM17Cy, SwiftWriteLM18Cy]>,
    // Unknow number of registers, just use resources for two registers.
    SchedVar<NoSchedPred,      [SwiftWriteLM3Cy, SwiftWriteLM4Cy,
                                SwiftWriteLM5CyNo, SwiftWriteLM6CyNo,
                                SwiftWriteLM7CyNo, SwiftWriteLM8CyNo,
                                SwiftWriteLM9CyNo, SwiftWriteLM10CyNo,
                                SwiftWriteLM11CyNo, SwiftWriteLM12CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteLM15CyNo, SwiftWriteLM16CyNo,
                                SwiftWriteLM17CyNo, SwiftWriteLM18CyNo]>

  ]> { let Variadic=1; }

  def : InstRW<[SwiftWriteLM, SwiftWriteLDMAddrNoWB],
        (instregex "LDM(IA|DA|DB|IB)$", "t2LDM(IA|DA|DB|IB)$",
        "(t|sys)LDM(IA|DA|DB|IB)$")>;
  def : InstRW<[SwiftWriteLDMAddrWB, SwiftWriteLM],
        (instregex /*"t2LDMIA_RET", "tLDMIA_RET", "LDMIA_RET",*/
        "LDM(IA|DA|DB|IB)_UPD", "(t2|sys|t)LDM(IA|DA|DB|IB)_UPD")>;
  def : InstRW<[SwiftWriteLDMAddrWB, SwiftWriteLM, SwiftWriteP1TwoCycle],
        (instregex "LDMIA_RET", "(t|t2)LDMIA_RET", "tPOP")>;
  // 4.2.23 Integer Store, Single Element
  def : InstRW<[SwiftWriteP2],
        (instregex "PICSTR", "STR(i12|rs)", "STRB(i12|rs)", "STRH$", "STREX",
        "t2STR(i12|i8|s)$", "t2STR[BH](i12|i8|s)$", "tSTR[BH](i|r)", "tSTR(i|r)", "tSTRspi")>;

  def : InstRW<[SwiftWriteP01OneCycle, SwiftWriteP2],
        (instregex "STR(B_|_|BT_|T_)(PRE_IMM|PRE_REG|POST_REG|POST_IMM)",
        "STR(i|r)_preidx", "STRB(i|r)_preidx", "STRH_preidx", "STR(H_|HT_)(PRE|POST)",
        "STR(BT|HT|T)", "t2STR_(PRE|POST)", "t2STR[BH]_(PRE|POST)",
        "t2STR_preidx", "t2STR[BH]_preidx", "t2ST(RB|RH|R)T")>;

  // 4.2.24 Integer Store, Dual
  def : InstRW<[SwiftWriteP2, SwiftWriteP2, SwiftWriteP01OneCycle],
        (instregex "STRD$", "t2STRDi8")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWriteP2, SwiftWriteP2,
                SwiftWriteP01OneCycle],
        (instregex "(t2|t)STRD_(POST|PRE)", "STRD_(POST|PRE)")>;

  // 4.2.25 Integer Store, Multiple
  def SwiftWriteStIncAddr : SchedWriteRes<[SwiftUnitP2, SwiftUnitP01]> {
    let Latency = 0;
    let NumMicroOps = 2;
  }
  foreach NumAddr = 1-16 in {
     def SwiftWriteSTM#NumAddr : WriteSequence<[SwiftWriteStIncAddr], NumAddr>;
  }
  def SwiftWriteSTM : SchedWriteVariant<[
    SchedVar<SwiftLMAddr2Pred, [SwiftWriteSTM2]>,
    SchedVar<SwiftLMAddr3Pred, [SwiftWriteSTM3]>,
    SchedVar<SwiftLMAddr4Pred, [SwiftWriteSTM4]>,
    SchedVar<SwiftLMAddr5Pred, [SwiftWriteSTM5]>,
    SchedVar<SwiftLMAddr6Pred, [SwiftWriteSTM6]>,
    SchedVar<SwiftLMAddr7Pred, [SwiftWriteSTM7]>,
    SchedVar<SwiftLMAddr8Pred, [SwiftWriteSTM8]>,
    SchedVar<SwiftLMAddr9Pred, [SwiftWriteSTM9]>,
    SchedVar<SwiftLMAddr10Pred,[SwiftWriteSTM10]>,
    SchedVar<SwiftLMAddr11Pred,[SwiftWriteSTM11]>,
    SchedVar<SwiftLMAddr12Pred,[SwiftWriteSTM12]>,
    SchedVar<SwiftLMAddr13Pred,[SwiftWriteSTM13]>,
    SchedVar<SwiftLMAddr14Pred,[SwiftWriteSTM14]>,
    SchedVar<SwiftLMAddr15Pred,[SwiftWriteSTM15]>,
    SchedVar<SwiftLMAddr16Pred,[SwiftWriteSTM16]>,
    // Unknow number of registers, just use resources for two registers.
    SchedVar<NoSchedPred,      [SwiftWriteSTM2]>
  ]>;
  def : InstRW<[SwiftWriteSTM],
        (instregex "STM(IB|IA|DB|DA)$", "(t2|sys|t)STM(IB|IA|DB|DA)$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWriteSTM],
        (instregex "STM(IB|IA|DB|DA)_UPD", "(t2|sys|t)STM(IB|IA|DB|DA)_UPD",
        "tPUSH")>;

  // LDRLIT pseudo instructions, they expand to LDR + PICADD
  def : InstRW<[SwiftWriteP2ThreeCycle, WriteALU],
        (instregex "t?LDRLIT_ga_abs", "t?LDRLIT_ga_pcrel")>;
  // LDRLIT_ga_pcrel_ldr expands to LDR + PICLDR
  def : InstRW<[SwiftWriteP2ThreeCycle, SwiftWriteP2ThreeCycle],
        (instregex "LDRLIT_ga_pcrel_ldr")>;

  // 4.2.26 Branch
  def : WriteRes<WriteBr, [SwiftUnitP1]> { let Latency = 0; }
  def : WriteRes<WriteBrL, [SwiftUnitP1]> { let Latency = 2; }
  def : WriteRes<WriteBrTbl, [SwiftUnitP1, SwiftUnitP2]> { let Latency = 0; }

  // 4.2.27 Not issued
  def : WriteRes<WriteNoop, []> { let Latency = 0; let NumMicroOps = 0; }
  def : InstRW<[WriteNoop], (instregex "t2IT", "IT")>;

  // 4.2.28 Advanced SIMD, Integer, 2 cycle
  def : InstRW<[SwiftWriteP0TwoCycle],
        (instregex "VADDv", "VSUBv", "VNEG(s|f|v)", "VADDL", "VSUBL",
                   "VADDW", "VSUBW", "VHADD", "VHSUB", "VRHADD", "VPADDi",
                   "VPADDL", "VAND", "VBIC", "VEOR", "VORN", "VORR", "VTST",
                   "VSHL", "VSHR(s|u)", "VSHLL", "VQSHL(s|u)", "VBIF",
                   "VBIT", "VBSL", "VSLI", "VSRI", "VCLS", "VCLZ", "VCNT")>;

  def : InstRW<[SwiftWriteP1TwoCycle],
        (instregex "VEXT", "VREV16", "VREV32", "VREV64")>;

  // 4.2.29 Advanced SIMD, Integer, 4 cycle
  // 4.2.30 Advanced SIMD, Integer with Accumulate
  def : InstRW<[SwiftWriteP0FourCycle],
        (instregex "VABA", "VABAL", "VPADAL", "VRSRA", "VSRA", "VACGE", "VACGT",
        "VCEQ", "VCGE", "VCGT", "VCLE", "VCLT", "VRSHL",
        "VQRSHL", "VRSHR(u|s)", "VABS(f|v)", "VQABS", "VQNEG", "VQADD",
        "VQSUB")>;
  def : InstRW<[SwiftWriteP1FourCycle],
        (instregex "VRECPE", "VRSQRTE")>;

  // 4.2.31 Advanced SIMD, Add and Shift with Narrow
  def : InstRW<[SwiftWriteP0P1FourCycle],
        (instregex "VADDHN", "VSUBHN", "VSHRN")>;
  def : InstRW<[SwiftWriteP0P1SixCycle],
        (instregex "VRADDHN", "VRSUBHN", "VRSHRN", "VQSHRN", "VQSHRUN",
                   "VQRSHRN", "VQRSHRUN")>;

  // 4.2.32 Advanced SIMD, Vector Table Lookup
  foreach Num = 1-4 in {
    def SwiftWrite#Num#xP1TwoCycle : WriteSequence<[SwiftWriteP1TwoCycle], Num>;
  }
  def : InstRW<[SwiftWrite1xP1TwoCycle],
        (instregex "VTB(L|X)1")>;
  def : InstRW<[SwiftWrite2xP1TwoCycle],
        (instregex "VTB(L|X)2")>;
  def : InstRW<[SwiftWrite3xP1TwoCycle],
        (instregex "VTB(L|X)3")>;
  def : InstRW<[SwiftWrite4xP1TwoCycle],
        (instregex "VTB(L|X)4")>;

  // 4.2.33 Advanced SIMD, Transpose
  def : InstRW<[SwiftWriteP1FourCycle, SwiftWriteP1FourCycle,
                SwiftWriteP1TwoCycle/*RsrcOnly*/, SchedReadAdvance<2>],
        (instregex "VSWP", "VTRN", "VUZP", "VZIP")>;

  // 4.2.34 Advanced SIMD and VFP, Floating Point
  def : InstRW<[SwiftWriteP0TwoCycle], (instregex "VABS(S|D)$", "VNEG(S|D)$")>;
  def : InstRW<[SwiftWriteP0FourCycle],
        (instregex "VCMP(D|S|ZD|ZS)$", "VCMPE(D|S|ZD|ZS)")>;
  def : InstRW<[SwiftWriteP0FourCycle],
        (instregex "VADD(S|f)", "VSUB(S|f)", "VABD", "VPADDf", "VMAX", "VMIN", "VPMAX",
                   "VPMIN")>;
  def : InstRW<[SwiftWriteP0SixCycle], (instregex "VADDD$", "VSUBD$")>;
  def : InstRW<[SwiftWriteP1EightCycle], (instregex "VRECPS", "VRSQRTS")>;

  // 4.2.35 Advanced SIMD and VFP, Multiply
  def : InstRW<[SwiftWriteP1FourCycle],
        (instregex "VMUL(S|v|p|f|s)", "VNMULS", "VQDMULH", "VQRDMULH",
                   "VMULL", "VQDMULL")>;
  def : InstRW<[SwiftWriteP1FourCycle],
        (instregex "VMLA", "VMLS", "VNMLA", "VNMLS", "VFMA(S|D)", "VFMS(S|D)",
        "VFNMA", "VFNMS", "VMLAL", "VMLSL","VQDMLAL", "VQDMLSL")>;
  def : InstRW<[SwiftWriteP1EightCycle], (instregex "VFMAfd", "VFMSfd")>;
  def : InstRW<[SwiftWriteP1TwelveCyc], (instregex "VFMAfq", "VFMSfq")>;

  // 4.2.36 Advanced SIMD and VFP, Convert
  def : InstRW<[SwiftWriteP1FourCycle], (instregex "VCVT", "V(S|U)IT", "VTO(S|U)")>;

  // 4.2.37 Advanced SIMD and VFP, Move
  def : InstRW<[SwiftWriteP0TwoCycle],
        (instregex "VMOVv", "VMOV(S|D)$", "VMOV(S|D)cc",
                   "VMVNv", "VMVN(d|q)",
                   "FCONST(D|S)")>;
  def : InstRW<[SwiftWriteP1TwoCycle], (instregex "VMOVN", "VMOVL")>;
  def : InstRW<[WriteSequence<[SwiftWriteP0FourCycle, SwiftWriteP1TwoCycle]>],
        (instregex "VQMOVN")>;
  def : InstRW<[SwiftWriteP1TwoCycle], (instregex "VDUPLN")>;
  def : InstRW<[WriteSequence<[SwiftWriteP2FourCycle, SwiftWriteP1TwoCycle]>],
        (instregex "VDUP(8|16|32)")>;
  def : InstRW<[SwiftWriteP2ThreeCycle], (instregex "VMOVRS$")>;
  def : InstRW<[WriteSequence<[SwiftWriteP2FourCycle, SwiftWriteP0TwoCycle]>],
        (instregex "VMOVSR$", "VSETLN")>;
  def : InstRW<[SwiftWriteP2ThreeCycle, SwiftWriteP2FourCycle],
        (instregex "VMOVRR(D|S)$")>;
  def : InstRW<[SwiftWriteP2FourCycle], (instregex "VMOVDRR$")>;
  def : InstRW<[WriteSequence<[SwiftWriteP2FourCycle, SwiftWriteP1TwoCycle]>,
                WriteSequence<[SwiftWrite1Cycle, SwiftWriteP2FourCycle,
                               SwiftWriteP1TwoCycle]>],
                (instregex "VMOVSRR$")>;
  def : InstRW<[WriteSequence<[SwiftWriteP1TwoCycle, SwiftWriteP2ThreeCycle]>],
        (instregex "VGETLN(u|i)")>;
  def : InstRW<[WriteSequence<[SwiftWriteP1TwoCycle, SwiftWriteP2ThreeCycle,
                               SwiftWriteP01OneCycle]>],
        (instregex "VGETLNs")>;

  // 4.2.38 Advanced SIMD and VFP, Move FPSCR
  // Serializing instructions.
  def SwiftWaitP0For15Cy : SchedWriteRes<[SwiftUnitP0]> {
    let Latency = 15;
    let ResourceCycles = [15];
  }
  def SwiftWaitP1For15Cy : SchedWriteRes<[SwiftUnitP1]> {
    let Latency = 15;
    let ResourceCycles = [15];
  }
  def SwiftWaitP2For15Cy : SchedWriteRes<[SwiftUnitP2]> {
    let Latency = 15;
    let ResourceCycles = [15];
  }
  def : InstRW<[SwiftWaitP0For15Cy, SwiftWaitP1For15Cy, SwiftWaitP2For15Cy],
        (instregex "VMRS")>;
  def : InstRW<[SwiftWaitP0For15Cy, SwiftWaitP1For15Cy, SwiftWaitP2For15Cy],
        (instregex "VMSR")>;
  // Not serializing.
  def : InstRW<[SwiftWriteP0TwoCycle], (instregex "FMSTAT")>;

  // 4.2.39 Advanced SIMD and VFP, Load Single Element
  def : InstRW<[SwiftWriteLM4Cy], (instregex "VLDRD$", "VLDRS$")>;

  // 4.2.40 Advanced SIMD and VFP, Store Single Element
  def : InstRW<[SwiftWriteLM4Cy], (instregex "VSTRD$", "VSTRS$")>;

  // 4.2.41 Advanced SIMD and VFP, Load Multiple
  // 4.2.42 Advanced SIMD and VFP, Store Multiple

  // Resource requirement for permuting, just reserves the resources.
  foreach Num = 1-28 in {
    def SwiftVLDMPerm#Num : SchedWriteRes<[SwiftUnitP1]> {
      let Latency = 0;
      let NumMicroOps = Num;
      let ResourceCycles = [Num];
    }
  }

  // Pre RA pseudos - load/store to a Q register as a D register pair.
  def : InstRW<[SwiftWriteLM4Cy], (instregex "VLDMQIA$", "VSTMQIA$")>;

  // Post RA not modelled accurately. We assume that register use of width 64
  // bit maps to a D register, 128 maps to a Q register. Not all different kinds
  // are accurately represented.
  def SwiftWriteVLDM : SchedWriteVariant<[
    // Load of one S register.
    SchedVar<SwiftLMAddr1Pred, [SwiftWriteLM4Cy]>,
    // Load of one D register.
    SchedVar<SwiftLMAddr2Pred, [SwiftWriteLM4Cy, SwiftWriteLM4CyNo]>,
    // Load of 3 S register.
    SchedVar<SwiftLMAddr3Pred, [SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm3]>,
    // Load of a Q register (not necessarily true). We should not be mapping to
    // 4 S registers, either.
    SchedVar<SwiftLMAddr4Pred, [SwiftWriteLM4Cy, SwiftWriteLM4CyNo,
                                SwiftWriteLM4CyNo, SwiftWriteLM4CyNo]>,
    // Load of 5 S registers.
    SchedVar<SwiftLMAddr5Pred, [SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteLM17CyNo,  SwiftWriteP01OneCycle,
                                SwiftVLDMPerm5]>,
    // Load of 3 D registers. (Must also be able to handle s register list -
    // though, not accurate)
    SchedVar<SwiftLMAddr6Pred, [SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM10Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteP01OneCycle, SwiftVLDMPerm5]>,
    // Load of 7 S registers.
    SchedVar<SwiftLMAddr7Pred, [SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM17CyNo, SwiftWriteLM18CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm7]>,
    // Load of two Q registers.
    SchedVar<SwiftLMAddr8Pred, [SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteP01OneCycle,  SwiftVLDMPerm2]>,
    // Load of 9 S registers.
    SchedVar<SwiftLMAddr9Pred, [SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM17CyNo, SwiftWriteLM18CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM25CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm9]>,
    // Load of 5 D registers.
    SchedVar<SwiftLMAddr10Pred,[SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM10Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM14CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo,  SwiftWriteLM14CyNo,
                                SwiftWriteP01OneCycle, SwiftVLDMPerm5]>,
    // Inaccurate: reuse describtion from 9 S registers.
    SchedVar<SwiftLMAddr11Pred,[SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM17CyNo, SwiftWriteLM18CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM25CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm9]>,
    // Load of three Q registers.
    SchedVar<SwiftLMAddr12Pred,[SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM11Cy,
                                SwiftWriteLM11CyNo, SwiftWriteLM11CyNo,
                                SwiftWriteLM11CyNo, SwiftWriteLM11CyNo,
                                SwiftWriteLM11CyNo, SwiftWriteLM11CyNo,
                                SwiftWriteLM11CyNo, SwiftWriteLM11CyNo,
                                SwiftWriteP01OneCycle, SwiftVLDMPerm3]>,
    // Inaccurate: reuse describtion from 9 S registers.
    SchedVar<SwiftLMAddr13Pred, [SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM17CyNo, SwiftWriteLM18CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM25CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm9]>,
    // Load of 7 D registers inaccurate.
    SchedVar<SwiftLMAddr14Pred,[SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM10Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM14Cy, SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo, SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo,  SwiftWriteLM14CyNo,
                                SwiftWriteLM14CyNo,  SwiftWriteLM14CyNo,
                                SwiftWriteP01OneCycle, SwiftVLDMPerm7]>,
    SchedVar<SwiftLMAddr15Pred,[SwiftWriteLM9Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM17Cy, SwiftWriteLM18CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM21CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM25CyNo, SwiftWriteP01OneCycle,
                                SwiftVLDMPerm9]>,
    // Load of 4 Q registers.
    SchedVar<SwiftLMAddr16Pred,[SwiftWriteLM7Cy, SwiftWriteLM10Cy,
                                SwiftWriteLM11Cy, SwiftWriteLM14Cy,
                                SwiftWriteLM15Cy, SwiftWriteLM18CyNo,
                                SwiftWriteLM19CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM19CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM19CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM19CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteLM19CyNo, SwiftWriteLM22CyNo,
                                SwiftWriteP01OneCycle, SwiftVLDMPerm4]>,
    // Unknow number of registers, just use resources for two registers.
    SchedVar<NoSchedPred,      [SwiftWriteLM7Cy, SwiftWriteLM8Cy,
                                SwiftWriteLM13Cy, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteLM13CyNo, SwiftWriteLM13CyNo,
                                SwiftWriteP01OneCycle,  SwiftVLDMPerm2]>
  ]> { let Variadic = 1; }

  def : InstRW<[SwiftWriteVLDM], (instregex "VLDM[SD](IA|DB)$")>;

  def : InstRW<[SwiftWriteP01OneCycle2x, SwiftWriteVLDM],
        (instregex "VLDM[SD](IA|DB)_UPD$")>;

  def SwiftWriteVSTM : SchedWriteVariant<[
    // One S register.
    SchedVar<SwiftLMAddr1Pred, [SwiftWriteSTM1]>,
    // One D register.
    SchedVar<SwiftLMAddr2Pred, [SwiftWriteSTM1]>,
    // Three S registers.
    SchedVar<SwiftLMAddr3Pred, [SwiftWriteSTM4]>,
    // Assume one Q register.
    SchedVar<SwiftLMAddr4Pred, [SwiftWriteSTM1]>,
    SchedVar<SwiftLMAddr5Pred, [SwiftWriteSTM6]>,
    // Assume three D registers.
    SchedVar<SwiftLMAddr6Pred, [SwiftWriteSTM4]>,
    SchedVar<SwiftLMAddr7Pred, [SwiftWriteSTM8]>,
    // Assume two Q registers.
    SchedVar<SwiftLMAddr8Pred, [SwiftWriteSTM3]>,
    SchedVar<SwiftLMAddr9Pred, [SwiftWriteSTM10]>,
    // Assume 5 D registers.
    SchedVar<SwiftLMAddr10Pred, [SwiftWriteSTM6]>,
    SchedVar<SwiftLMAddr11Pred, [SwiftWriteSTM12]>,
    // Assume three Q registers.
    SchedVar<SwiftLMAddr12Pred, [SwiftWriteSTM4]>,
    SchedVar<SwiftLMAddr13Pred, [SwiftWriteSTM14]>,
    // Assume 7 D registers.
    SchedVar<SwiftLMAddr14Pred, [SwiftWriteSTM8]>,
    SchedVar<SwiftLMAddr15Pred, [SwiftWriteSTM16]>,
    // Assume four Q registers.
    SchedVar<SwiftLMAddr16Pred, [SwiftWriteSTM5]>,
    // Asumme two Q registers.
    SchedVar<NoSchedPred, [SwiftWriteSTM3]>
  ]> { let Variadic = 1; }

  def : InstRW<[SwiftWriteVSTM], (instregex "VSTM[SD](IA|DB)$")>;

  def : InstRW<[SwiftWriteP01OneCycle2x, SwiftWriteVSTM],
        (instregex "VSTM[SD](IA|DB)_UPD")>;

  // 4.2.43 Advanced SIMD, Element or Structure Load and Store
  def SwiftWrite2xP2FourCy : SchedWriteRes<[SwiftUnitP2]> {
      let Latency = 4;
      let ResourceCycles = [2];
  }
  def SwiftWrite3xP2FourCy : SchedWriteRes<[SwiftUnitP2]> {
      let Latency = 4;
      let ResourceCycles = [3];
  }
  foreach Num = 1-2 in {
    def SwiftExt#Num#xP0 : SchedWriteRes<[SwiftUnitP0]> {
      let Latency = 0;
      let NumMicroOps = Num;
      let ResourceCycles = [Num];
    }
  }
  // VLDx
  // Multiple structures.
  // Single element structure loads.
  // We assume aligned.
  // Single/two register.
  def : InstRW<[SwiftWriteLM4Cy], (instregex "VLD1(d|q)(8|16|32|64)$")>;
  def : InstRW<[SwiftWriteLM4Cy, SwiftWriteP01OneCycle],
        (instregex "VLD1(d|q)(8|16|32|64)wb")>;
  // Three register.
  def : InstRW<[SwiftWrite3xP2FourCy],
        (instregex "VLD1(d|q)(8|16|32|64)T$", "VLD1d64TPseudo")>;
  def : InstRW<[SwiftWrite3xP2FourCy, SwiftWriteP01OneCycle],
        (instregex "VLD1(d|q)(8|16|32|64)Twb")>;
  /// Four Register.
  def : InstRW<[SwiftWrite2xP2FourCy],
        (instregex "VLD1(d|q)(8|16|32|64)Q$", "VLD1d64QPseudo")>;
  def : InstRW<[SwiftWrite2xP2FourCy, SwiftWriteP01OneCycle],
        (instregex "VLD1(d|q)(8|16|32|64)Qwb")>;
  // Two element structure loads.
  // Two/four register.
  def : InstRW<[SwiftWriteLM9Cy, SwiftExt2xP0, SwiftVLDMPerm2],
        (instregex "VLD2(d|q|b)(8|16|32)$", "VLD2q(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteLM9Cy, SwiftWriteP01OneCycle, SwiftExt2xP0,
                SwiftVLDMPerm2],
        (instregex "VLD2(d|q|b)(8|16|32)wb", "VLD2q(8|16|32)PseudoWB")>;
  // Three element structure.
  def : InstRW<[SwiftWriteLM9Cy, SwiftWriteLM9CyNo, SwiftWriteLM9CyNo,
                SwiftVLDMPerm3, SwiftWrite3xP2FourCy],
        (instregex "VLD3(d|q)(8|16|32)$")>;
  def : InstRW<[SwiftWriteLM9Cy, SwiftVLDMPerm3, SwiftWrite3xP2FourCy],
        (instregex "VLD3(d|q)(8|16|32)(oddP|P)seudo$")>;

  def : InstRW<[SwiftWriteLM9Cy, SwiftWriteLM9CyNo, SwiftWriteLM9CyNo,
                SwiftWriteP01OneCycle, SwiftVLDMPerm3, SwiftWrite3xP2FourCy],
        (instregex "VLD3(d|q)(8|16|32)_UPD$")>;
  def : InstRW<[SwiftWriteLM9Cy, SwiftWriteP01OneCycle, SwiftVLDMPerm3,
                SwiftWrite3xP2FourCy],
        (instregex "VLD3(d|q)(8|16|32)(oddP|P)seudo_UPD")>;
  // Four element structure loads.
  def : InstRW<[SwiftWriteLM11Cy, SwiftWriteLM11Cy, SwiftWriteLM11Cy,
                SwiftWriteLM11Cy, SwiftExt2xP0, SwiftVLDMPerm4,
                SwiftWrite3xP2FourCy],
        (instregex "VLD4(d|q)(8|16|32)$")>;
  def : InstRW<[SwiftWriteLM11Cy,  SwiftExt2xP0, SwiftVLDMPerm4,
                SwiftWrite3xP2FourCy],
        (instregex "VLD4(d|q)(8|16|32)(oddP|P)seudo$")>;
  def : InstRW<[SwiftWriteLM11Cy, SwiftWriteLM11Cy, SwiftWriteLM11Cy,
                SwiftWriteLM11Cy, SwiftWriteP01OneCycle, SwiftExt2xP0,
                SwiftVLDMPerm4, SwiftWrite3xP2FourCy],
        (instregex "VLD4(d|q)(8|16|32)_UPD")>;
  def : InstRW<[SwiftWriteLM11Cy, SwiftWriteP01OneCycle, SwiftExt2xP0,
                SwiftVLDMPerm4, SwiftWrite3xP2FourCy],
        (instregex  "VLD4(d|q)(8|16|32)(oddP|P)seudo_UPD")>;

  // Single all/lane loads.
  // One element structure.
  def : InstRW<[SwiftWriteLM6Cy, SwiftVLDMPerm2],
        (instregex "VLD1(LN|DUP)(d|q)(8|16|32)$", "VLD1(LN|DUP)(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteLM6Cy, SwiftWriteP01OneCycle, SwiftVLDMPerm2],
        (instregex "VLD1(LN|DUP)(d|q)(8|16|32)(wb|_UPD)",
                  "VLD1LNq(8|16|32)Pseudo_UPD")>;
  // Two element structure.
  def : InstRW<[SwiftWriteLM6Cy, SwiftWriteLM6Cy, SwiftExt1xP0, SwiftVLDMPerm2],
        (instregex "VLD2(DUP|LN)(d|q)(8|16|32|8x2|16x2|32x2)$",
                   "VLD2LN(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteLM6Cy, SwiftWriteLM6Cy, SwiftWriteP01OneCycle,
                SwiftExt1xP0, SwiftVLDMPerm2],
        (instregex "VLD2LN(d|q)(8|16|32)_UPD$")>;
  def : InstRW<[SwiftWriteLM6Cy, SwiftWriteP01OneCycle, SwiftWriteLM6Cy,
                SwiftExt1xP0, SwiftVLDMPerm2],
        (instregex "VLD2DUPd(8|16|32|8x2|16x2|32x2)wb")>;
  def : InstRW<[SwiftWriteLM6Cy, SwiftWriteP01OneCycle, SwiftWriteLM6Cy,
                SwiftExt1xP0, SwiftVLDMPerm2],
        (instregex "VLD2LN(d|q)(8|16|32)Pseudo_UPD")>;
  // Three element structure.
  def : InstRW<[SwiftWriteLM7Cy, SwiftWriteLM8Cy, SwiftWriteLM8Cy, SwiftExt1xP0,
                SwiftVLDMPerm3],
        (instregex "VLD3(DUP|LN)(d|q)(8|16|32)$",
                   "VLD3(LN|DUP)(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteLM7Cy, SwiftWriteLM8Cy, SwiftWriteLM8Cy,
                SwiftWriteP01OneCycle, SwiftExt1xP0, SwiftVLDMPerm3],
        (instregex "VLD3(LN|DUP)(d|q)(8|16|32)_UPD")>;
  def : InstRW<[SwiftWriteLM7Cy, SwiftWriteP01OneCycle, SwiftWriteLM8Cy,
                SwiftWriteLM8Cy, SwiftExt1xP0, SwiftVLDMPerm3],
        (instregex "VLD3(LN|DUP)(d|q)(8|16|32)Pseudo_UPD")>;
  // Four element struture.
  def : InstRW<[SwiftWriteLM8Cy, SwiftWriteLM9Cy, SwiftWriteLM10CyNo,
                SwiftWriteLM10CyNo, SwiftExt1xP0, SwiftVLDMPerm5],
        (instregex "VLD4(LN|DUP)(d|q)(8|16|32)$",
                   "VLD4(LN|DUP)(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteLM8Cy, SwiftWriteLM9Cy, SwiftWriteLM10CyNo,
                SwiftWriteLM10CyNo, SwiftWriteP01OneCycle, SwiftExt1xP0,
                SwiftVLDMPerm5],
        (instregex "VLD4(DUP|LN)(d|q)(8|16|32)_UPD")>;
  def : InstRW<[SwiftWriteLM8Cy, SwiftWriteP01OneCycle, SwiftWriteLM9Cy,
                SwiftWriteLM10CyNo, SwiftWriteLM10CyNo, SwiftExt1xP0,
                SwiftVLDMPerm5],
        (instregex "VLD4(DUP|LN)(d|q)(8|16|32)Pseudo_UPD")>;
  // VSTx
  // Multiple structures.
  // Single element structure store.
  def : InstRW<[SwiftWrite1xP2], (instregex "VST1d(8|16|32|64)$")>;
  def : InstRW<[SwiftWrite2xP2], (instregex "VST1q(8|16|32|64)$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite1xP2],
        (instregex "VST1d(8|16|32|64)wb")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite2xP2],
        (instregex "VST1q(8|16|32|64)wb")>;
  def : InstRW<[SwiftWrite3xP2],
        (instregex "VST1d(8|16|32|64)T$", "VST1d64TPseudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite3xP2],
        (instregex "VST1d(8|16|32|64)Twb", "VST1d64TPseudoWB")>;
  def : InstRW<[SwiftWrite4xP2],
        (instregex "VST1d(8|16|32|64)(Q|QPseudo)$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite4xP2],
        (instregex "VST1d(8|16|32|64)(Qwb|QPseudoWB)")>;
  // Two element structure store.
  def : InstRW<[SwiftWrite1xP2, SwiftVLDMPerm1],
        (instregex "VST2(d|b)(8|16|32)$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite1xP2, SwiftVLDMPerm1],
        (instregex "VST2(b|d)(8|16|32)wb")>;
  def : InstRW<[SwiftWrite2xP2, SwiftVLDMPerm2],
        (instregex "VST2q(8|16|32)$", "VST2q(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWrite2xP2, SwiftVLDMPerm2],
        (instregex "VST2q(8|16|32)wb", "VST2q(8|16|32)PseudoWB")>;
  // Three element structure store.
  def : InstRW<[SwiftWrite4xP2, SwiftVLDMPerm2],
        (instregex "VST3(d|q)(8|16|32)$", "VST3(d|q)(8|16|32)(oddP|P)seudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite4xP2, SwiftVLDMPerm2],
        (instregex "VST3(d|q)(8|16|32)_UPD",
                   "VST3(d|q)(8|16|32)(oddP|P)seudo_UPD$")>;
  // Four element structure store.
  def : InstRW<[SwiftWrite4xP2, SwiftVLDMPerm2],
        (instregex "VST4(d|q)(8|16|32)$", "VST4(d|q)(8|16|32)(oddP|P)seudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite4xP2, SwiftVLDMPerm4],
        (instregex "VST4(d|q)(8|16|32)_UPD",
                   "VST4(d|q)(8|16|32)(oddP|P)seudo_UPD$")>;
  // Single/all lane store.
  // One element structure.
  def : InstRW<[SwiftWrite1xP2, SwiftVLDMPerm1],
        (instregex "VST1LNd(8|16|32)$", "VST1LNq(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite1xP2, SwiftVLDMPerm1],
        (instregex "VST1LNd(8|16|32)_UPD", "VST1LNq(8|16|32)Pseudo_UPD")>;
  // Two element structure.
  def : InstRW<[SwiftWrite1xP2, SwiftVLDMPerm2],
        (instregex "VST2LN(d|q)(8|16|32)$", "VST2LN(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite1xP2, SwiftVLDMPerm2],
        (instregex "VST2LN(d|q)(8|16|32)_UPD",
                   "VST2LN(d|q)(8|16|32)Pseudo_UPD")>;
  // Three element structure.
  def : InstRW<[SwiftWrite4xP2, SwiftVLDMPerm2],
        (instregex "VST3LN(d|q)(8|16|32)$", "VST3LN(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite4xP2, SwiftVLDMPerm2],
        (instregex "VST3LN(d|q)(8|16|32)_UPD",
                   "VST3LN(d|q)(8|16|32)Pseudo_UPD")>;
  // Four element structure.
  def : InstRW<[SwiftWrite2xP2, SwiftVLDMPerm2],
        (instregex "VST4LN(d|q)(8|16|32)$", "VST4LN(d|q)(8|16|32)Pseudo$")>;
  def : InstRW<[SwiftWriteP01OneCycle, SwiftWrite2xP2, SwiftVLDMPerm2],
        (instregex "VST4LN(d|q)(8|16|32)_UPD",
                   "VST4LN(d|q)(8|16|32)Pseudo_UPD")>;

  // 4.2.44 VFP, Divide and Square Root
  def SwiftDiv17 : SchedWriteRes<[SwiftUnitP0, SwiftUnitDiv]> {
    let NumMicroOps = 1;
    let Latency = 17;
    let ResourceCycles = [1, 15];
  }
  def SwiftDiv32 : SchedWriteRes<[SwiftUnitP0, SwiftUnitDiv]> {
    let NumMicroOps = 1;
    let Latency = 32;
    let ResourceCycles = [1, 30];
  }
  def : InstRW<[SwiftDiv17], (instregex "VDIVS", "VSQRTS")>;
  def : InstRW<[SwiftDiv32], (instregex "VDIVD", "VSQRTD")>;

  // ===---------------------------------------------------------------------===//
  // Floating-point. Map target defined SchedReadWrite to processor specific ones
  //
  def : SchedAlias<WriteFPCVT, SwiftWriteP1FourCycle>;
  def : SchedAlias<WriteFPMOV, SwiftWriteP2ThreeCycle>;

  def : SchedAlias<WriteFPALU32, SwiftWriteP0FourCycle>;
  def : SchedAlias<WriteFPALU64, SwiftWriteP0SixCycle>;

  def : SchedAlias<WriteFPMUL32, SwiftWriteP1FourCycle>;
  def : SchedAlias<WriteFPMUL64, SwiftWriteP1SixCycle>;

  def : SchedAlias<WriteFPMAC32, SwiftWriteP1FourCycle>;
  def : SchedAlias<WriteFPMAC64, SwiftWriteP1FourCycle>;

  def : SchedAlias<WriteFPDIV32, SwiftDiv17>;
  def : SchedAlias<WriteFPSQRT32, SwiftDiv17>;

  def : SchedAlias<WriteFPDIV64, SwiftDiv32>;
  def : SchedAlias<WriteFPSQRT64, SwiftDiv32>;

  def : ReadAdvance<ReadFPMUL, 0>;
  def : ReadAdvance<ReadFPMAC, 0>;

  // 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, []>;

  // Not specified.
  def : InstRW<[SwiftWriteP01OneCycle2x], (instregex "ABS")>;
  // Preload.
  def : WriteRes<WritePreLd, [SwiftUnitP2]> { let Latency = 0;
    let ResourceCycles = [0];
  }

}