ARMSubtarget.h 31 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
//===-- ARMSubtarget.h - Define Subtarget for the ARM ----------*- C++ -*--===//
//
// 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 declares the ARM specific subclass of TargetSubtargetInfo.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_ARM_ARMSUBTARGET_H
#define LLVM_LIB_TARGET_ARM_ARMSUBTARGET_H

#include "ARMBaseInstrInfo.h"
#include "ARMBaseRegisterInfo.h"
#include "ARMConstantPoolValue.h"
#include "ARMFrameLowering.h"
#include "ARMISelLowering.h"
#include "ARMSelectionDAGInfo.h"
#include "llvm/ADT/Triple.h"
#include "llvm/CodeGen/GlobalISel/CallLowering.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
#include "llvm/CodeGen/GlobalISel/RegisterBankInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/MC/MCInstrItineraries.h"
#include "llvm/MC/MCSchedule.h"
#include "llvm/Target/TargetOptions.h"
#include <memory>
#include <string>

#define GET_SUBTARGETINFO_HEADER
#include "ARMGenSubtargetInfo.inc"

namespace llvm {

class ARMBaseTargetMachine;
class GlobalValue;
class StringRef;

class ARMSubtarget : public ARMGenSubtargetInfo {
protected:
  enum ARMProcFamilyEnum {
    Others,

    CortexA12,
    CortexA15,
    CortexA17,
    CortexA32,
    CortexA35,
    CortexA5,
    CortexA53,
    CortexA55,
    CortexA57,
    CortexA7,
    CortexA72,
    CortexA73,
    CortexA75,
    CortexA76,
    CortexA8,
    CortexA9,
    CortexM3,
    CortexR4,
    CortexR4F,
    CortexR5,
    CortexR52,
    CortexR7,
    Exynos,
    Krait,
    Kryo,
    NeoverseN1,
    Swift
  };
  enum ARMProcClassEnum {
    None,

    AClass,
    MClass,
    RClass
  };
  enum ARMArchEnum {
    ARMv2,
    ARMv2a,
    ARMv3,
    ARMv3m,
    ARMv4,
    ARMv4t,
    ARMv5,
    ARMv5t,
    ARMv5te,
    ARMv5tej,
    ARMv6,
    ARMv6k,
    ARMv6kz,
    ARMv6m,
    ARMv6sm,
    ARMv6t2,
    ARMv7a,
    ARMv7em,
    ARMv7m,
    ARMv7r,
    ARMv7ve,
    ARMv81a,
    ARMv82a,
    ARMv83a,
    ARMv84a,
    ARMv85a,
    ARMv8a,
    ARMv8mBaseline,
    ARMv8mMainline,
    ARMv8r,
    ARMv81mMainline,
  };

public:
  /// What kind of timing do load multiple/store multiple instructions have.
  enum ARMLdStMultipleTiming {
    /// Can load/store 2 registers/cycle.
    DoubleIssue,
    /// Can load/store 2 registers/cycle, but needs an extra cycle if the access
    /// is not 64-bit aligned.
    DoubleIssueCheckUnalignedAccess,
    /// Can load/store 1 register/cycle.
    SingleIssue,
    /// Can load/store 1 register/cycle, but needs an extra cycle for address
    /// computation and potentially also for register writeback.
    SingleIssuePlusExtras,
  };

protected:
  /// ARMProcFamily - ARM processor family: Cortex-A8, Cortex-A9, and others.
  ARMProcFamilyEnum ARMProcFamily = Others;

  /// ARMProcClass - ARM processor class: None, AClass, RClass or MClass.
  ARMProcClassEnum ARMProcClass = None;

  /// ARMArch - ARM architecture
  ARMArchEnum ARMArch = ARMv4t;

  /// HasV4TOps, HasV5TOps, HasV5TEOps,
  /// HasV6Ops, HasV6MOps, HasV6KOps, HasV6T2Ops, HasV7Ops, HasV8Ops -
  /// Specify whether target support specific ARM ISA variants.
  bool HasV4TOps = false;
  bool HasV5TOps = false;
  bool HasV5TEOps = false;
  bool HasV6Ops = false;
  bool HasV6MOps = false;
  bool HasV6KOps = false;
  bool HasV6T2Ops = false;
  bool HasV7Ops = false;
  bool HasV8Ops = false;
  bool HasV8_1aOps = false;
  bool HasV8_2aOps = false;
  bool HasV8_3aOps = false;
  bool HasV8_4aOps = false;
  bool HasV8_5aOps = false;
  bool HasV8MBaselineOps = false;
  bool HasV8MMainlineOps = false;
  bool HasV8_1MMainlineOps = false;
  bool HasMVEIntegerOps = false;
  bool HasMVEFloatOps = false;

  /// HasVFPv2, HasVFPv3, HasVFPv4, HasFPARMv8, HasNEON - Specify what
  /// floating point ISAs are supported.
  bool HasVFPv2 = false;
  bool HasVFPv3 = false;
  bool HasVFPv4 = false;
  bool HasFPARMv8 = false;
  bool HasNEON = false;
  bool HasFPRegs = false;
  bool HasFPRegs16 = false;
  bool HasFPRegs64 = false;

  /// Versions of the VFP flags restricted to single precision, or to
  /// 16 d-registers, or both.
  bool HasVFPv2SP = false;
  bool HasVFPv3SP = false;
  bool HasVFPv4SP = false;
  bool HasFPARMv8SP = false;
  bool HasVFPv3D16 = false;
  bool HasVFPv4D16 = false;
  bool HasFPARMv8D16 = false;
  bool HasVFPv3D16SP = false;
  bool HasVFPv4D16SP = false;
  bool HasFPARMv8D16SP = false;

  /// HasDotProd - True if the ARMv8.2A dot product instructions are supported.
  bool HasDotProd = false;

  /// UseNEONForSinglePrecisionFP - if the NEONFP attribute has been
  /// specified. Use the method useNEONForSinglePrecisionFP() to
  /// determine if NEON should actually be used.
  bool UseNEONForSinglePrecisionFP = false;

  /// UseMulOps - True if non-microcoded fused integer multiply-add and
  /// multiply-subtract instructions should be used.
  bool UseMulOps = false;

  /// SlowFPVMLx - If the VFP2 / NEON instructions are available, indicates
  /// whether the FP VML[AS] instructions are slow (if so, don't use them).
  bool SlowFPVMLx = false;

  /// SlowFPVFMx - If the VFP4 / NEON instructions are available, indicates
  /// whether the FP VFM[AS] instructions are slow (if so, don't use them).
  bool SlowFPVFMx = false;

  /// HasVMLxForwarding - If true, NEON has special multiplier accumulator
  /// forwarding to allow mul + mla being issued back to back.
  bool HasVMLxForwarding = false;

  /// SlowFPBrcc - True if floating point compare + branch is slow.
  bool SlowFPBrcc = false;

  /// InThumbMode - True if compiling for Thumb, false for ARM.
  bool InThumbMode = false;

  /// UseSoftFloat - True if we're using software floating point features.
  bool UseSoftFloat = false;

  /// UseMISched - True if MachineScheduler should be used for this subtarget.
  bool UseMISched = false;

  /// DisablePostRAScheduler - False if scheduling should happen again after
  /// register allocation.
  bool DisablePostRAScheduler = false;

  /// HasThumb2 - True if Thumb2 instructions are supported.
  bool HasThumb2 = false;

  /// NoARM - True if subtarget does not support ARM mode execution.
  bool NoARM = false;

  /// ReserveR9 - True if R9 is not available as a general purpose register.
  bool ReserveR9 = false;

  /// NoMovt - True if MOVT / MOVW pairs are not used for materialization of
  /// 32-bit imms (including global addresses).
  bool NoMovt = false;

  /// SupportsTailCall - True if the OS supports tail call. The dynamic linker
  /// must be able to synthesize call stubs for interworking between ARM and
  /// Thumb.
  bool SupportsTailCall = false;

  /// HasFP16 - True if subtarget supports half-precision FP conversions
  bool HasFP16 = false;

  /// HasFullFP16 - True if subtarget supports half-precision FP operations
  bool HasFullFP16 = false;

  /// HasFP16FML - True if subtarget supports half-precision FP fml operations
  bool HasFP16FML = false;

  /// HasD32 - True if subtarget has the full 32 double precision
  /// FP registers for VFPv3.
  bool HasD32 = false;

  /// HasHardwareDivide - True if subtarget supports [su]div in Thumb mode
  bool HasHardwareDivideInThumb = false;

  /// HasHardwareDivideInARM - True if subtarget supports [su]div in ARM mode
  bool HasHardwareDivideInARM = false;

  /// HasDataBarrier - True if the subtarget supports DMB / DSB data barrier
  /// instructions.
  bool HasDataBarrier = false;

  /// HasFullDataBarrier - True if the subtarget supports DFB data barrier
  /// instruction.
  bool HasFullDataBarrier = false;

  /// HasV7Clrex - True if the subtarget supports CLREX instructions
  bool HasV7Clrex = false;

  /// HasAcquireRelease - True if the subtarget supports v8 atomics (LDA/LDAEX etc)
  /// instructions
  bool HasAcquireRelease = false;

  /// Pref32BitThumb - If true, codegen would prefer 32-bit Thumb instructions
  /// over 16-bit ones.
  bool Pref32BitThumb = false;

  /// AvoidCPSRPartialUpdate - If true, codegen would avoid using instructions
  /// that partially update CPSR and add false dependency on the previous
  /// CPSR setting instruction.
  bool AvoidCPSRPartialUpdate = false;

  /// CheapPredicableCPSRDef - If true, disable +1 predication cost
  /// for instructions updating CPSR. Enabled for Cortex-A57.
  bool CheapPredicableCPSRDef = false;

  /// AvoidMOVsShifterOperand - If true, codegen should avoid using flag setting
  /// movs with shifter operand (i.e. asr, lsl, lsr).
  bool AvoidMOVsShifterOperand = false;

  /// HasRetAddrStack - Some processors perform return stack prediction. CodeGen should
  /// avoid issue "normal" call instructions to callees which do not return.
  bool HasRetAddrStack = false;

  /// HasBranchPredictor - True if the subtarget has a branch predictor. Having
  /// a branch predictor or not changes the expected cost of taking a branch
  /// which affects the choice of whether to use predicated instructions.
  bool HasBranchPredictor = true;

  /// HasMPExtension - True if the subtarget supports Multiprocessing
  /// extension (ARMv7 only).
  bool HasMPExtension = false;

  /// HasVirtualization - True if the subtarget supports the Virtualization
  /// extension.
  bool HasVirtualization = false;

  /// HasFP64 - If true, the floating point unit supports double
  /// precision.
  bool HasFP64 = false;

  /// If true, the processor supports the Performance Monitor Extensions. These
  /// include a generic cycle-counter as well as more fine-grained (often
  /// implementation-specific) events.
  bool HasPerfMon = false;

  /// HasTrustZone - if true, processor supports TrustZone security extensions
  bool HasTrustZone = false;

  /// Has8MSecExt - if true, processor supports ARMv8-M Security Extensions
  bool Has8MSecExt = false;

  /// HasSHA2 - if true, processor supports SHA1 and SHA256
  bool HasSHA2 = false;

  /// HasAES - if true, processor supports AES
  bool HasAES = false;

  /// HasCrypto - if true, processor supports Cryptography extensions
  bool HasCrypto = false;

  /// HasCRC - if true, processor supports CRC instructions
  bool HasCRC = false;

  /// HasRAS - if true, the processor supports RAS extensions
  bool HasRAS = false;

  /// HasLOB - if true, the processor supports the Low Overhead Branch extension
  bool HasLOB = false;

  /// If true, the instructions "vmov.i32 d0, #0" and "vmov.i32 q0, #0" are
  /// particularly effective at zeroing a VFP register.
  bool HasZeroCycleZeroing = false;

  /// HasFPAO - if true, processor  does positive address offset computation faster
  bool HasFPAO = false;

  /// HasFuseAES - if true, processor executes back to back AES instruction
  /// pairs faster.
  bool HasFuseAES = false;

  /// HasFuseLiterals - if true, processor executes back to back
  /// bottom and top halves of literal generation faster.
  bool HasFuseLiterals = false;

  /// If true, if conversion may decide to leave some instructions unpredicated.
  bool IsProfitableToUnpredicate = false;

  /// If true, VMOV will be favored over VGETLNi32.
  bool HasSlowVGETLNi32 = false;

  /// If true, VMOV will be favored over VDUP.
  bool HasSlowVDUP32 = false;

  /// If true, VMOVSR will be favored over VMOVDRR.
  bool PreferVMOVSR = false;

  /// If true, ISHST barriers will be used for Release semantics.
  bool PreferISHST = false;

  /// If true, a VLDM/VSTM starting with an odd register number is considered to
  /// take more microops than single VLDRS/VSTRS.
  bool SlowOddRegister = false;

  /// If true, loading into a D subregister will be penalized.
  bool SlowLoadDSubregister = false;

  /// If true, use a wider stride when allocating VFP registers.
  bool UseWideStrideVFP = false;

  /// If true, the AGU and NEON/FPU units are multiplexed.
  bool HasMuxedUnits = false;

  /// If true, VMOVS will never be widened to VMOVD.
  bool DontWidenVMOVS = false;

  /// If true, splat a register between VFP and NEON instructions.
  bool SplatVFPToNeon = false;

  /// If true, run the MLx expansion pass.
  bool ExpandMLx = false;

  /// If true, VFP/NEON VMLA/VMLS have special RAW hazards.
  bool HasVMLxHazards = false;

  // If true, read thread pointer from coprocessor register.
  bool ReadTPHard = false;

  /// If true, VMOVRS, VMOVSR and VMOVS will be converted from VFP to NEON.
  bool UseNEONForFPMovs = false;

  /// If true, VLDn instructions take an extra cycle for unaligned accesses.
  bool CheckVLDnAlign = false;

  /// If true, VFP instructions are not pipelined.
  bool NonpipelinedVFP = false;

  /// StrictAlign - If true, the subtarget disallows unaligned memory
  /// accesses for some types.  For details, see
  /// ARMTargetLowering::allowsMisalignedMemoryAccesses().
  bool StrictAlign = false;

  /// RestrictIT - If true, the subtarget disallows generation of deprecated IT
  ///  blocks to conform to ARMv8 rule.
  bool RestrictIT = false;

  /// HasDSP - If true, the subtarget supports the DSP (saturating arith
  /// and such) instructions.
  bool HasDSP = false;

  /// NaCl TRAP instruction is generated instead of the regular TRAP.
  bool UseNaClTrap = false;

  /// Generate calls via indirect call instructions.
  bool GenLongCalls = false;

  /// Generate code that does not contain data access to code sections.
  bool GenExecuteOnly = false;

  /// Target machine allowed unsafe FP math (such as use of NEON fp)
  bool UnsafeFPMath = false;

  /// UseSjLjEH - If true, the target uses SjLj exception handling (e.g. iOS).
  bool UseSjLjEH = false;

  /// Has speculation barrier
  bool HasSB = false;

  /// Implicitly convert an instruction to a different one if its immediates
  /// cannot be encoded. For example, ADD r0, r1, #FFFFFFFF -> SUB r0, r1, #1.
  bool NegativeImmediates = true;

  /// stackAlignment - The minimum alignment known to hold of the stack frame on
  /// entry to the function and which must be maintained by every function.
  Align stackAlignment = Align(4);

  /// CPUString - String name of used CPU.
  std::string CPUString;

  unsigned MaxInterleaveFactor = 1;

  /// Clearance before partial register updates (in number of instructions)
  unsigned PartialUpdateClearance = 0;

  /// What kind of timing do load multiple/store multiple have (double issue,
  /// single issue etc).
  ARMLdStMultipleTiming LdStMultipleTiming = SingleIssue;

  /// The adjustment that we need to apply to get the operand latency from the
  /// operand cycle returned by the itinerary data for pre-ISel operands.
  int PreISelOperandLatencyAdjustment = 2;

  /// What alignment is preferred for loop bodies, in log2(bytes).
  unsigned PrefLoopLogAlignment = 0;

  /// The cost factor for MVE instructions, representing the multiple beats an
  // instruction can take. The default is 2, (set in initSubtargetFeatures so
  // that we can use subtarget features less than 2).
  unsigned MVEVectorCostFactor = 0;

  /// OptMinSize - True if we're optimising for minimum code size, equal to
  /// the function attribute.
  bool OptMinSize = false;

  /// IsLittle - The target is Little Endian
  bool IsLittle;

  /// TargetTriple - What processor and OS we're targeting.
  Triple TargetTriple;

  /// SchedModel - Processor specific instruction costs.
  MCSchedModel SchedModel;

  /// Selected instruction itineraries (one entry per itinerary class.)
  InstrItineraryData InstrItins;

  /// Options passed via command line that could influence the target
  const TargetOptions &Options;

  const ARMBaseTargetMachine &TM;

public:
  /// This constructor initializes the data members to match that
  /// of the specified triple.
  ///
  ARMSubtarget(const Triple &TT, const std::string &CPU, const std::string &FS,
               const ARMBaseTargetMachine &TM, bool IsLittle,
               bool MinSize = false);

  /// getMaxInlineSizeThreshold - Returns the maximum memset / memcpy size
  /// that still makes it profitable to inline the call.
  unsigned getMaxInlineSizeThreshold() const {
    return 64;
  }

  /// ParseSubtargetFeatures - Parses features string setting specified
  /// subtarget options.  Definition of function is auto generated by tblgen.
  void ParseSubtargetFeatures(StringRef CPU, StringRef FS);

  /// initializeSubtargetDependencies - Initializes using a CPU and feature string
  /// so that we can use initializer lists for subtarget initialization.
  ARMSubtarget &initializeSubtargetDependencies(StringRef CPU, StringRef FS);

  const ARMSelectionDAGInfo *getSelectionDAGInfo() const override {
    return &TSInfo;
  }

  const ARMBaseInstrInfo *getInstrInfo() const override {
    return InstrInfo.get();
  }

  const ARMTargetLowering *getTargetLowering() const override {
    return &TLInfo;
  }

  const ARMFrameLowering *getFrameLowering() const override {
    return FrameLowering.get();
  }

  const ARMBaseRegisterInfo *getRegisterInfo() const override {
    return &InstrInfo->getRegisterInfo();
  }

  const CallLowering *getCallLowering() const override;
  InstructionSelector *getInstructionSelector() const override;
  const LegalizerInfo *getLegalizerInfo() const override;
  const RegisterBankInfo *getRegBankInfo() const override;

private:
  ARMSelectionDAGInfo TSInfo;
  // Either Thumb1FrameLowering or ARMFrameLowering.
  std::unique_ptr<ARMFrameLowering> FrameLowering;
  // Either Thumb1InstrInfo or Thumb2InstrInfo.
  std::unique_ptr<ARMBaseInstrInfo> InstrInfo;
  ARMTargetLowering   TLInfo;

  /// GlobalISel related APIs.
  std::unique_ptr<CallLowering> CallLoweringInfo;
  std::unique_ptr<InstructionSelector> InstSelector;
  std::unique_ptr<LegalizerInfo> Legalizer;
  std::unique_ptr<RegisterBankInfo> RegBankInfo;

  void initializeEnvironment();
  void initSubtargetFeatures(StringRef CPU, StringRef FS);
  ARMFrameLowering *initializeFrameLowering(StringRef CPU, StringRef FS);

public:
  void computeIssueWidth();

  bool hasV4TOps()  const { return HasV4TOps;  }
  bool hasV5TOps()  const { return HasV5TOps;  }
  bool hasV5TEOps() const { return HasV5TEOps; }
  bool hasV6Ops()   const { return HasV6Ops;   }
  bool hasV6MOps()  const { return HasV6MOps;  }
  bool hasV6KOps()  const { return HasV6KOps; }
  bool hasV6T2Ops() const { return HasV6T2Ops; }
  bool hasV7Ops()   const { return HasV7Ops;  }
  bool hasV8Ops()   const { return HasV8Ops;  }
  bool hasV8_1aOps() const { return HasV8_1aOps; }
  bool hasV8_2aOps() const { return HasV8_2aOps; }
  bool hasV8_3aOps() const { return HasV8_3aOps; }
  bool hasV8_4aOps() const { return HasV8_4aOps; }
  bool hasV8_5aOps() const { return HasV8_5aOps; }
  bool hasV8MBaselineOps() const { return HasV8MBaselineOps; }
  bool hasV8MMainlineOps() const { return HasV8MMainlineOps; }
  bool hasV8_1MMainlineOps() const { return HasV8_1MMainlineOps; }
  bool hasMVEIntegerOps() const { return HasMVEIntegerOps; }
  bool hasMVEFloatOps() const { return HasMVEFloatOps; }
  bool hasFPRegs() const { return HasFPRegs; }
  bool hasFPRegs16() const { return HasFPRegs16; }
  bool hasFPRegs64() const { return HasFPRegs64; }

  /// @{
  /// These functions are obsolete, please consider adding subtarget features
  /// or properties instead of calling them.
  bool isCortexA5() const { return ARMProcFamily == CortexA5; }
  bool isCortexA7() const { return ARMProcFamily == CortexA7; }
  bool isCortexA8() const { return ARMProcFamily == CortexA8; }
  bool isCortexA9() const { return ARMProcFamily == CortexA9; }
  bool isCortexA15() const { return ARMProcFamily == CortexA15; }
  bool isSwift()    const { return ARMProcFamily == Swift; }
  bool isCortexM3() const { return ARMProcFamily == CortexM3; }
  bool isLikeA9() const { return isCortexA9() || isCortexA15() || isKrait(); }
  bool isCortexR5() const { return ARMProcFamily == CortexR5; }
  bool isKrait() const { return ARMProcFamily == Krait; }
  /// @}

  bool hasARMOps() const { return !NoARM; }

  bool hasVFP2Base() const { return HasVFPv2SP; }
  bool hasVFP3Base() const { return HasVFPv3D16SP; }
  bool hasVFP4Base() const { return HasVFPv4D16SP; }
  bool hasFPARMv8Base() const { return HasFPARMv8D16SP; }
  bool hasNEON() const { return HasNEON;  }
  bool hasSHA2() const { return HasSHA2; }
  bool hasAES() const { return HasAES; }
  bool hasCrypto() const { return HasCrypto; }
  bool hasDotProd() const { return HasDotProd; }
  bool hasCRC() const { return HasCRC; }
  bool hasRAS() const { return HasRAS; }
  bool hasLOB() const { return HasLOB; }
  bool hasVirtualization() const { return HasVirtualization; }

  bool useNEONForSinglePrecisionFP() const {
    return hasNEON() && UseNEONForSinglePrecisionFP;
  }

  bool hasDivideInThumbMode() const { return HasHardwareDivideInThumb; }
  bool hasDivideInARMMode() const { return HasHardwareDivideInARM; }
  bool hasDataBarrier() const { return HasDataBarrier; }
  bool hasFullDataBarrier() const { return HasFullDataBarrier; }
  bool hasV7Clrex() const { return HasV7Clrex; }
  bool hasAcquireRelease() const { return HasAcquireRelease; }

  bool hasAnyDataBarrier() const {
    return HasDataBarrier || (hasV6Ops() && !isThumb());
  }

  bool useMulOps() const { return UseMulOps; }
  bool useFPVMLx() const { return !SlowFPVMLx; }
  bool useFPVFMx() const {
    return !isTargetDarwin() && hasVFP4Base() && !SlowFPVFMx;
  }
  bool useFPVFMx16() const { return useFPVFMx() && hasFullFP16(); }
  bool useFPVFMx64() const { return useFPVFMx() && hasFP64(); }
  bool hasVMLxForwarding() const { return HasVMLxForwarding; }
  bool isFPBrccSlow() const { return SlowFPBrcc; }
  bool hasFP64() const { return HasFP64; }
  bool hasPerfMon() const { return HasPerfMon; }
  bool hasTrustZone() const { return HasTrustZone; }
  bool has8MSecExt() const { return Has8MSecExt; }
  bool hasZeroCycleZeroing() const { return HasZeroCycleZeroing; }
  bool hasFPAO() const { return HasFPAO; }
  bool isProfitableToUnpredicate() const { return IsProfitableToUnpredicate; }
  bool hasSlowVGETLNi32() const { return HasSlowVGETLNi32; }
  bool hasSlowVDUP32() const { return HasSlowVDUP32; }
  bool preferVMOVSR() const { return PreferVMOVSR; }
  bool preferISHSTBarriers() const { return PreferISHST; }
  bool expandMLx() const { return ExpandMLx; }
  bool hasVMLxHazards() const { return HasVMLxHazards; }
  bool hasSlowOddRegister() const { return SlowOddRegister; }
  bool hasSlowLoadDSubregister() const { return SlowLoadDSubregister; }
  bool useWideStrideVFP() const { return UseWideStrideVFP; }
  bool hasMuxedUnits() const { return HasMuxedUnits; }
  bool dontWidenVMOVS() const { return DontWidenVMOVS; }
  bool useSplatVFPToNeon() const { return SplatVFPToNeon; }
  bool useNEONForFPMovs() const { return UseNEONForFPMovs; }
  bool checkVLDnAccessAlignment() const { return CheckVLDnAlign; }
  bool nonpipelinedVFP() const { return NonpipelinedVFP; }
  bool prefers32BitThumb() const { return Pref32BitThumb; }
  bool avoidCPSRPartialUpdate() const { return AvoidCPSRPartialUpdate; }
  bool cheapPredicableCPSRDef() const { return CheapPredicableCPSRDef; }
  bool avoidMOVsShifterOperand() const { return AvoidMOVsShifterOperand; }
  bool hasRetAddrStack() const { return HasRetAddrStack; }
  bool hasBranchPredictor() const { return HasBranchPredictor; }
  bool hasMPExtension() const { return HasMPExtension; }
  bool hasDSP() const { return HasDSP; }
  bool useNaClTrap() const { return UseNaClTrap; }
  bool useSjLjEH() const { return UseSjLjEH; }
  bool hasSB() const { return HasSB; }
  bool genLongCalls() const { return GenLongCalls; }
  bool genExecuteOnly() const { return GenExecuteOnly; }
  bool hasBaseDSP() const {
    if (isThumb())
      return hasDSP();
    else
      return hasV5TEOps();
  }

  bool hasFP16() const { return HasFP16; }
  bool hasD32() const { return HasD32; }
  bool hasFullFP16() const { return HasFullFP16; }
  bool hasFP16FML() const { return HasFP16FML; }

  bool hasFuseAES() const { return HasFuseAES; }
  bool hasFuseLiterals() const { return HasFuseLiterals; }
  /// Return true if the CPU supports any kind of instruction fusion.
  bool hasFusion() const { return hasFuseAES() || hasFuseLiterals(); }

  const Triple &getTargetTriple() const { return TargetTriple; }

  bool isTargetDarwin() const { return TargetTriple.isOSDarwin(); }
  bool isTargetIOS() const { return TargetTriple.isiOS(); }
  bool isTargetWatchOS() const { return TargetTriple.isWatchOS(); }
  bool isTargetWatchABI() const { return TargetTriple.isWatchABI(); }
  bool isTargetLinux() const { return TargetTriple.isOSLinux(); }
  bool isTargetNaCl() const { return TargetTriple.isOSNaCl(); }
  bool isTargetNetBSD() const { return TargetTriple.isOSNetBSD(); }
  bool isTargetWindows() const { return TargetTriple.isOSWindows(); }

  bool isTargetCOFF() const { return TargetTriple.isOSBinFormatCOFF(); }
  bool isTargetELF() const { return TargetTriple.isOSBinFormatELF(); }
  bool isTargetMachO() const { return TargetTriple.isOSBinFormatMachO(); }

  // ARM EABI is the bare-metal EABI described in ARM ABI documents and
  // can be accessed via -target arm-none-eabi. This is NOT GNUEABI.
  // FIXME: Add a flag for bare-metal for that target and set Triple::EABI
  // even for GNUEABI, so we can make a distinction here and still conform to
  // the EABI on GNU (and Android) mode. This requires change in Clang, too.
  // FIXME: The Darwin exception is temporary, while we move users to
  // "*-*-*-macho" triples as quickly as possible.
  bool isTargetAEABI() const {
    return (TargetTriple.getEnvironment() == Triple::EABI ||
            TargetTriple.getEnvironment() == Triple::EABIHF) &&
           !isTargetDarwin() && !isTargetWindows();
  }
  bool isTargetGNUAEABI() const {
    return (TargetTriple.getEnvironment() == Triple::GNUEABI ||
            TargetTriple.getEnvironment() == Triple::GNUEABIHF) &&
           !isTargetDarwin() && !isTargetWindows();
  }
  bool isTargetMuslAEABI() const {
    return (TargetTriple.getEnvironment() == Triple::MuslEABI ||
            TargetTriple.getEnvironment() == Triple::MuslEABIHF) &&
           !isTargetDarwin() && !isTargetWindows();
  }

  // ARM Targets that support EHABI exception handling standard
  // Darwin uses SjLj. Other targets might need more checks.
  bool isTargetEHABICompatible() const {
    return (TargetTriple.getEnvironment() == Triple::EABI ||
            TargetTriple.getEnvironment() == Triple::GNUEABI ||
            TargetTriple.getEnvironment() == Triple::MuslEABI ||
            TargetTriple.getEnvironment() == Triple::EABIHF ||
            TargetTriple.getEnvironment() == Triple::GNUEABIHF ||
            TargetTriple.getEnvironment() == Triple::MuslEABIHF ||
            isTargetAndroid()) &&
           !isTargetDarwin() && !isTargetWindows();
  }

  bool isTargetHardFloat() const;

  bool isTargetAndroid() const { return TargetTriple.isAndroid(); }

  bool isXRaySupported() const override;

  bool isAPCS_ABI() const;
  bool isAAPCS_ABI() const;
  bool isAAPCS16_ABI() const;

  bool isROPI() const;
  bool isRWPI() const;

  bool useMachineScheduler() const { return UseMISched; }
  bool disablePostRAScheduler() const { return DisablePostRAScheduler; }
  bool useSoftFloat() const { return UseSoftFloat; }
  bool isThumb() const { return InThumbMode; }
  bool hasMinSize() const { return OptMinSize; }
  bool isThumb1Only() const { return InThumbMode && !HasThumb2; }
  bool isThumb2() const { return InThumbMode && HasThumb2; }
  bool hasThumb2() const { return HasThumb2; }
  bool isMClass() const { return ARMProcClass == MClass; }
  bool isRClass() const { return ARMProcClass == RClass; }
  bool isAClass() const { return ARMProcClass == AClass; }
  bool isReadTPHard() const { return ReadTPHard; }

  bool isR9Reserved() const {
    return isTargetMachO() ? (ReserveR9 || !HasV6Ops) : ReserveR9;
  }

  bool useR7AsFramePointer() const {
    return isTargetDarwin() || (!isTargetWindows() && isThumb());
  }

  /// Returns true if the frame setup is split into two separate pushes (first
  /// r0-r7,lr then r8-r11), principally so that the frame pointer is adjacent
  /// to lr. This is always required on Thumb1-only targets, as the push and
  /// pop instructions can't access the high registers.
  bool splitFramePushPop(const MachineFunction &MF) const {
    return (useR7AsFramePointer() &&
            MF.getTarget().Options.DisableFramePointerElim(MF)) ||
           isThumb1Only();
  }

  bool useStride4VFPs() const;

  bool useMovt() const;

  bool supportsTailCall() const { return SupportsTailCall; }

  bool allowsUnalignedMem() const { return !StrictAlign; }

  bool restrictIT() const { return RestrictIT; }

  const std::string & getCPUString() const { return CPUString; }

  bool isLittle() const { return IsLittle; }

  unsigned getMispredictionPenalty() const;

  /// Returns true if machine scheduler should be enabled.
  bool enableMachineScheduler() const override;

  /// True for some subtargets at > -O0.
  bool enablePostRAScheduler() const override;

  /// True for some subtargets at > -O0.
  bool enablePostRAMachineScheduler() const override;

  /// Check whether this subtarget wants to use subregister liveness.
  bool enableSubRegLiveness() const override;

  /// Enable use of alias analysis during code generation (during MI
  /// scheduling, DAGCombine, etc.).
  bool useAA() const override { return true; }

  // enableAtomicExpand- True if we need to expand our atomics.
  bool enableAtomicExpand() const override;

  /// getInstrItins - Return the instruction itineraries based on subtarget
  /// selection.
  const InstrItineraryData *getInstrItineraryData() const override {
    return &InstrItins;
  }

  /// getStackAlignment - Returns the minimum alignment known to hold of the
  /// stack frame on entry to the function and which must be maintained by every
  /// function for this subtarget.
  Align getStackAlignment() const { return stackAlignment; }

  unsigned getMaxInterleaveFactor() const { return MaxInterleaveFactor; }

  unsigned getPartialUpdateClearance() const { return PartialUpdateClearance; }

  ARMLdStMultipleTiming getLdStMultipleTiming() const {
    return LdStMultipleTiming;
  }

  int getPreISelOperandLatencyAdjustment() const {
    return PreISelOperandLatencyAdjustment;
  }

  /// True if the GV will be accessed via an indirect symbol.
  bool isGVIndirectSymbol(const GlobalValue *GV) const;

  /// Returns the constant pool modifier needed to access the GV.
  bool isGVInGOT(const GlobalValue *GV) const;

  /// True if fast-isel is used.
  bool useFastISel() const;

  /// Returns the correct return opcode for the current feature set.
  /// Use BX if available to allow mixing thumb/arm code, but fall back
  /// to plain mov pc,lr on ARMv4.
  unsigned getReturnOpcode() const {
    if (isThumb())
      return ARM::tBX_RET;
    if (hasV4TOps())
      return ARM::BX_RET;
    return ARM::MOVPCLR;
  }

  /// Allow movt+movw for PIC global address calculation.
  /// ELF does not have GOT relocations for movt+movw.
  /// ROPI does not use GOT.
  bool allowPositionIndependentMovt() const {
    return isROPI() || !isTargetELF();
  }

  unsigned getPrefLoopLogAlignment() const { return PrefLoopLogAlignment; }

  unsigned getMVEVectorCostFactor() const { return MVEVectorCostFactor; }

  bool ignoreCSRForAllocationOrder(const MachineFunction &MF,
                                   unsigned PhysReg) const override;
  unsigned getGPRAllocationOrder(const MachineFunction &MF) const;
};

} // end namespace llvm

#endif  // LLVM_LIB_TARGET_ARM_ARMSUBTARGET_H