NVPTXISelLowering.h 15.7 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
//===-- NVPTXISelLowering.h - NVPTX DAG Lowering Interface ------*- 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 defines the interfaces that NVPTX uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_NVPTX_NVPTXISELLOWERING_H
#define LLVM_LIB_TARGET_NVPTX_NVPTXISELLOWERING_H

#include "NVPTX.h"
#include "llvm/CodeGen/SelectionDAG.h"
#include "llvm/CodeGen/TargetLowering.h"

namespace llvm {
namespace NVPTXISD {
enum NodeType : unsigned {
  // Start the numbering from where ISD NodeType finishes.
  FIRST_NUMBER = ISD::BUILTIN_OP_END,
  Wrapper,
  CALL,
  RET_FLAG,
  LOAD_PARAM,
  DeclareParam,
  DeclareScalarParam,
  DeclareRetParam,
  DeclareRet,
  DeclareScalarRet,
  PrintCall,
  PrintConvergentCall,
  PrintCallUni,
  PrintConvergentCallUni,
  CallArgBegin,
  CallArg,
  LastCallArg,
  CallArgEnd,
  CallVoid,
  CallVal,
  CallSymbol,
  Prototype,
  MoveParam,
  PseudoUseParam,
  RETURN,
  CallSeqBegin,
  CallSeqEnd,
  CallPrototype,
  ProxyReg,
  FUN_SHFL_CLAMP,
  FUN_SHFR_CLAMP,
  MUL_WIDE_SIGNED,
  MUL_WIDE_UNSIGNED,
  IMAD,
  SETP_F16X2,
  Dummy,

  LoadV2 = ISD::FIRST_TARGET_MEMORY_OPCODE,
  LoadV4,
  LDGV2, // LDG.v2
  LDGV4, // LDG.v4
  LDUV2, // LDU.v2
  LDUV4, // LDU.v4
  StoreV2,
  StoreV4,
  LoadParam,
  LoadParamV2,
  LoadParamV4,
  StoreParam,
  StoreParamV2,
  StoreParamV4,
  StoreParamS32, // to sext and store a <32bit value, not used currently
  StoreParamU32, // to zext and store a <32bit value, not used currently
  StoreRetval,
  StoreRetvalV2,
  StoreRetvalV4,

  // Texture intrinsics
  Tex1DFloatS32,
  Tex1DFloatFloat,
  Tex1DFloatFloatLevel,
  Tex1DFloatFloatGrad,
  Tex1DS32S32,
  Tex1DS32Float,
  Tex1DS32FloatLevel,
  Tex1DS32FloatGrad,
  Tex1DU32S32,
  Tex1DU32Float,
  Tex1DU32FloatLevel,
  Tex1DU32FloatGrad,
  Tex1DArrayFloatS32,
  Tex1DArrayFloatFloat,
  Tex1DArrayFloatFloatLevel,
  Tex1DArrayFloatFloatGrad,
  Tex1DArrayS32S32,
  Tex1DArrayS32Float,
  Tex1DArrayS32FloatLevel,
  Tex1DArrayS32FloatGrad,
  Tex1DArrayU32S32,
  Tex1DArrayU32Float,
  Tex1DArrayU32FloatLevel,
  Tex1DArrayU32FloatGrad,
  Tex2DFloatS32,
  Tex2DFloatFloat,
  Tex2DFloatFloatLevel,
  Tex2DFloatFloatGrad,
  Tex2DS32S32,
  Tex2DS32Float,
  Tex2DS32FloatLevel,
  Tex2DS32FloatGrad,
  Tex2DU32S32,
  Tex2DU32Float,
  Tex2DU32FloatLevel,
  Tex2DU32FloatGrad,
  Tex2DArrayFloatS32,
  Tex2DArrayFloatFloat,
  Tex2DArrayFloatFloatLevel,
  Tex2DArrayFloatFloatGrad,
  Tex2DArrayS32S32,
  Tex2DArrayS32Float,
  Tex2DArrayS32FloatLevel,
  Tex2DArrayS32FloatGrad,
  Tex2DArrayU32S32,
  Tex2DArrayU32Float,
  Tex2DArrayU32FloatLevel,
  Tex2DArrayU32FloatGrad,
  Tex3DFloatS32,
  Tex3DFloatFloat,
  Tex3DFloatFloatLevel,
  Tex3DFloatFloatGrad,
  Tex3DS32S32,
  Tex3DS32Float,
  Tex3DS32FloatLevel,
  Tex3DS32FloatGrad,
  Tex3DU32S32,
  Tex3DU32Float,
  Tex3DU32FloatLevel,
  Tex3DU32FloatGrad,
  TexCubeFloatFloat,
  TexCubeFloatFloatLevel,
  TexCubeS32Float,
  TexCubeS32FloatLevel,
  TexCubeU32Float,
  TexCubeU32FloatLevel,
  TexCubeArrayFloatFloat,
  TexCubeArrayFloatFloatLevel,
  TexCubeArrayS32Float,
  TexCubeArrayS32FloatLevel,
  TexCubeArrayU32Float,
  TexCubeArrayU32FloatLevel,
  Tld4R2DFloatFloat,
  Tld4G2DFloatFloat,
  Tld4B2DFloatFloat,
  Tld4A2DFloatFloat,
  Tld4R2DS64Float,
  Tld4G2DS64Float,
  Tld4B2DS64Float,
  Tld4A2DS64Float,
  Tld4R2DU64Float,
  Tld4G2DU64Float,
  Tld4B2DU64Float,
  Tld4A2DU64Float,
  TexUnified1DFloatS32,
  TexUnified1DFloatFloat,
  TexUnified1DFloatFloatLevel,
  TexUnified1DFloatFloatGrad,
  TexUnified1DS32S32,
  TexUnified1DS32Float,
  TexUnified1DS32FloatLevel,
  TexUnified1DS32FloatGrad,
  TexUnified1DU32S32,
  TexUnified1DU32Float,
  TexUnified1DU32FloatLevel,
  TexUnified1DU32FloatGrad,
  TexUnified1DArrayFloatS32,
  TexUnified1DArrayFloatFloat,
  TexUnified1DArrayFloatFloatLevel,
  TexUnified1DArrayFloatFloatGrad,
  TexUnified1DArrayS32S32,
  TexUnified1DArrayS32Float,
  TexUnified1DArrayS32FloatLevel,
  TexUnified1DArrayS32FloatGrad,
  TexUnified1DArrayU32S32,
  TexUnified1DArrayU32Float,
  TexUnified1DArrayU32FloatLevel,
  TexUnified1DArrayU32FloatGrad,
  TexUnified2DFloatS32,
  TexUnified2DFloatFloat,
  TexUnified2DFloatFloatLevel,
  TexUnified2DFloatFloatGrad,
  TexUnified2DS32S32,
  TexUnified2DS32Float,
  TexUnified2DS32FloatLevel,
  TexUnified2DS32FloatGrad,
  TexUnified2DU32S32,
  TexUnified2DU32Float,
  TexUnified2DU32FloatLevel,
  TexUnified2DU32FloatGrad,
  TexUnified2DArrayFloatS32,
  TexUnified2DArrayFloatFloat,
  TexUnified2DArrayFloatFloatLevel,
  TexUnified2DArrayFloatFloatGrad,
  TexUnified2DArrayS32S32,
  TexUnified2DArrayS32Float,
  TexUnified2DArrayS32FloatLevel,
  TexUnified2DArrayS32FloatGrad,
  TexUnified2DArrayU32S32,
  TexUnified2DArrayU32Float,
  TexUnified2DArrayU32FloatLevel,
  TexUnified2DArrayU32FloatGrad,
  TexUnified3DFloatS32,
  TexUnified3DFloatFloat,
  TexUnified3DFloatFloatLevel,
  TexUnified3DFloatFloatGrad,
  TexUnified3DS32S32,
  TexUnified3DS32Float,
  TexUnified3DS32FloatLevel,
  TexUnified3DS32FloatGrad,
  TexUnified3DU32S32,
  TexUnified3DU32Float,
  TexUnified3DU32FloatLevel,
  TexUnified3DU32FloatGrad,
  TexUnifiedCubeFloatFloat,
  TexUnifiedCubeFloatFloatLevel,
  TexUnifiedCubeS32Float,
  TexUnifiedCubeS32FloatLevel,
  TexUnifiedCubeU32Float,
  TexUnifiedCubeU32FloatLevel,
  TexUnifiedCubeArrayFloatFloat,
  TexUnifiedCubeArrayFloatFloatLevel,
  TexUnifiedCubeArrayS32Float,
  TexUnifiedCubeArrayS32FloatLevel,
  TexUnifiedCubeArrayU32Float,
  TexUnifiedCubeArrayU32FloatLevel,
  Tld4UnifiedR2DFloatFloat,
  Tld4UnifiedG2DFloatFloat,
  Tld4UnifiedB2DFloatFloat,
  Tld4UnifiedA2DFloatFloat,
  Tld4UnifiedR2DS64Float,
  Tld4UnifiedG2DS64Float,
  Tld4UnifiedB2DS64Float,
  Tld4UnifiedA2DS64Float,
  Tld4UnifiedR2DU64Float,
  Tld4UnifiedG2DU64Float,
  Tld4UnifiedB2DU64Float,
  Tld4UnifiedA2DU64Float,

  // Surface intrinsics
  Suld1DI8Clamp,
  Suld1DI16Clamp,
  Suld1DI32Clamp,
  Suld1DI64Clamp,
  Suld1DV2I8Clamp,
  Suld1DV2I16Clamp,
  Suld1DV2I32Clamp,
  Suld1DV2I64Clamp,
  Suld1DV4I8Clamp,
  Suld1DV4I16Clamp,
  Suld1DV4I32Clamp,

  Suld1DArrayI8Clamp,
  Suld1DArrayI16Clamp,
  Suld1DArrayI32Clamp,
  Suld1DArrayI64Clamp,
  Suld1DArrayV2I8Clamp,
  Suld1DArrayV2I16Clamp,
  Suld1DArrayV2I32Clamp,
  Suld1DArrayV2I64Clamp,
  Suld1DArrayV4I8Clamp,
  Suld1DArrayV4I16Clamp,
  Suld1DArrayV4I32Clamp,

  Suld2DI8Clamp,
  Suld2DI16Clamp,
  Suld2DI32Clamp,
  Suld2DI64Clamp,
  Suld2DV2I8Clamp,
  Suld2DV2I16Clamp,
  Suld2DV2I32Clamp,
  Suld2DV2I64Clamp,
  Suld2DV4I8Clamp,
  Suld2DV4I16Clamp,
  Suld2DV4I32Clamp,

  Suld2DArrayI8Clamp,
  Suld2DArrayI16Clamp,
  Suld2DArrayI32Clamp,
  Suld2DArrayI64Clamp,
  Suld2DArrayV2I8Clamp,
  Suld2DArrayV2I16Clamp,
  Suld2DArrayV2I32Clamp,
  Suld2DArrayV2I64Clamp,
  Suld2DArrayV4I8Clamp,
  Suld2DArrayV4I16Clamp,
  Suld2DArrayV4I32Clamp,

  Suld3DI8Clamp,
  Suld3DI16Clamp,
  Suld3DI32Clamp,
  Suld3DI64Clamp,
  Suld3DV2I8Clamp,
  Suld3DV2I16Clamp,
  Suld3DV2I32Clamp,
  Suld3DV2I64Clamp,
  Suld3DV4I8Clamp,
  Suld3DV4I16Clamp,
  Suld3DV4I32Clamp,

  Suld1DI8Trap,
  Suld1DI16Trap,
  Suld1DI32Trap,
  Suld1DI64Trap,
  Suld1DV2I8Trap,
  Suld1DV2I16Trap,
  Suld1DV2I32Trap,
  Suld1DV2I64Trap,
  Suld1DV4I8Trap,
  Suld1DV4I16Trap,
  Suld1DV4I32Trap,

  Suld1DArrayI8Trap,
  Suld1DArrayI16Trap,
  Suld1DArrayI32Trap,
  Suld1DArrayI64Trap,
  Suld1DArrayV2I8Trap,
  Suld1DArrayV2I16Trap,
  Suld1DArrayV2I32Trap,
  Suld1DArrayV2I64Trap,
  Suld1DArrayV4I8Trap,
  Suld1DArrayV4I16Trap,
  Suld1DArrayV4I32Trap,

  Suld2DI8Trap,
  Suld2DI16Trap,
  Suld2DI32Trap,
  Suld2DI64Trap,
  Suld2DV2I8Trap,
  Suld2DV2I16Trap,
  Suld2DV2I32Trap,
  Suld2DV2I64Trap,
  Suld2DV4I8Trap,
  Suld2DV4I16Trap,
  Suld2DV4I32Trap,

  Suld2DArrayI8Trap,
  Suld2DArrayI16Trap,
  Suld2DArrayI32Trap,
  Suld2DArrayI64Trap,
  Suld2DArrayV2I8Trap,
  Suld2DArrayV2I16Trap,
  Suld2DArrayV2I32Trap,
  Suld2DArrayV2I64Trap,
  Suld2DArrayV4I8Trap,
  Suld2DArrayV4I16Trap,
  Suld2DArrayV4I32Trap,

  Suld3DI8Trap,
  Suld3DI16Trap,
  Suld3DI32Trap,
  Suld3DI64Trap,
  Suld3DV2I8Trap,
  Suld3DV2I16Trap,
  Suld3DV2I32Trap,
  Suld3DV2I64Trap,
  Suld3DV4I8Trap,
  Suld3DV4I16Trap,
  Suld3DV4I32Trap,

  Suld1DI8Zero,
  Suld1DI16Zero,
  Suld1DI32Zero,
  Suld1DI64Zero,
  Suld1DV2I8Zero,
  Suld1DV2I16Zero,
  Suld1DV2I32Zero,
  Suld1DV2I64Zero,
  Suld1DV4I8Zero,
  Suld1DV4I16Zero,
  Suld1DV4I32Zero,

  Suld1DArrayI8Zero,
  Suld1DArrayI16Zero,
  Suld1DArrayI32Zero,
  Suld1DArrayI64Zero,
  Suld1DArrayV2I8Zero,
  Suld1DArrayV2I16Zero,
  Suld1DArrayV2I32Zero,
  Suld1DArrayV2I64Zero,
  Suld1DArrayV4I8Zero,
  Suld1DArrayV4I16Zero,
  Suld1DArrayV4I32Zero,

  Suld2DI8Zero,
  Suld2DI16Zero,
  Suld2DI32Zero,
  Suld2DI64Zero,
  Suld2DV2I8Zero,
  Suld2DV2I16Zero,
  Suld2DV2I32Zero,
  Suld2DV2I64Zero,
  Suld2DV4I8Zero,
  Suld2DV4I16Zero,
  Suld2DV4I32Zero,

  Suld2DArrayI8Zero,
  Suld2DArrayI16Zero,
  Suld2DArrayI32Zero,
  Suld2DArrayI64Zero,
  Suld2DArrayV2I8Zero,
  Suld2DArrayV2I16Zero,
  Suld2DArrayV2I32Zero,
  Suld2DArrayV2I64Zero,
  Suld2DArrayV4I8Zero,
  Suld2DArrayV4I16Zero,
  Suld2DArrayV4I32Zero,

  Suld3DI8Zero,
  Suld3DI16Zero,
  Suld3DI32Zero,
  Suld3DI64Zero,
  Suld3DV2I8Zero,
  Suld3DV2I16Zero,
  Suld3DV2I32Zero,
  Suld3DV2I64Zero,
  Suld3DV4I8Zero,
  Suld3DV4I16Zero,
  Suld3DV4I32Zero
};
}

class NVPTXSubtarget;

//===--------------------------------------------------------------------===//
// TargetLowering Implementation
//===--------------------------------------------------------------------===//
class NVPTXTargetLowering : public TargetLowering {
public:
  explicit NVPTXTargetLowering(const NVPTXTargetMachine &TM,
                               const NVPTXSubtarget &STI);
  SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;

  SDValue LowerGlobalAddress(SDValue Op, SelectionDAG &DAG) const;

  const char *getTargetNodeName(unsigned Opcode) const override;

  bool getTgtMemIntrinsic(IntrinsicInfo &Info, const CallInst &I,
                          MachineFunction &MF,
                          unsigned Intrinsic) const override;

  /// isLegalAddressingMode - Return true if the addressing mode represented
  /// by AM is legal for this target, for a load/store of the specified type
  /// Used to guide target specific optimizations, like loop strength
  /// reduction (LoopStrengthReduce.cpp) and memory optimization for
  /// address mode (CodeGenPrepare.cpp)
  bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
                             unsigned AS,
                             Instruction *I = nullptr) const override;

  bool isTruncateFree(Type *SrcTy, Type *DstTy) const override {
    // Truncating 64-bit to 32-bit is free in SASS.
    if (!SrcTy->isIntegerTy() || !DstTy->isIntegerTy())
      return false;
    return SrcTy->getPrimitiveSizeInBits() == 64 &&
           DstTy->getPrimitiveSizeInBits() == 32;
  }

  EVT getSetCCResultType(const DataLayout &DL, LLVMContext &Ctx,
                         EVT VT) const override {
    if (VT.isVector())
      return EVT::getVectorVT(Ctx, MVT::i1, VT.getVectorNumElements());
    return MVT::i1;
  }

  ConstraintType getConstraintType(StringRef Constraint) const override;
  std::pair<unsigned, const TargetRegisterClass *>
  getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
                               StringRef Constraint, MVT VT) const override;

  SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
                               bool isVarArg,
                               const SmallVectorImpl<ISD::InputArg> &Ins,
                               const SDLoc &dl, SelectionDAG &DAG,
                               SmallVectorImpl<SDValue> &InVals) const override;

  SDValue LowerCall(CallLoweringInfo &CLI,
                    SmallVectorImpl<SDValue> &InVals) const override;

  std::string getPrototype(const DataLayout &DL, Type *, const ArgListTy &,
                           const SmallVectorImpl<ISD::OutputArg> &,
                           unsigned retAlignment,
                           ImmutableCallSite CS) const;

  SDValue LowerReturn(SDValue Chain, CallingConv::ID CallConv, bool isVarArg,
                      const SmallVectorImpl<ISD::OutputArg> &Outs,
                      const SmallVectorImpl<SDValue> &OutVals, const SDLoc &dl,
                      SelectionDAG &DAG) const override;

  void LowerAsmOperandForConstraint(SDValue Op, std::string &Constraint,
                                    std::vector<SDValue> &Ops,
                                    SelectionDAG &DAG) const override;

  const NVPTXTargetMachine *nvTM;

  // PTX always uses 32-bit shift amounts
  MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override {
    return MVT::i32;
  }

  TargetLoweringBase::LegalizeTypeAction
  getPreferredVectorAction(MVT VT) const override;

  // Get the degree of precision we want from 32-bit floating point division
  // operations.
  //
  //  0 - Use ptx div.approx
  //  1 - Use ptx.div.full (approximate, but less so than div.approx)
  //  2 - Use IEEE-compliant div instructions, if available.
  int getDivF32Level() const;

  // Get whether we should use a precise or approximate 32-bit floating point
  // sqrt instruction.
  bool usePrecSqrtF32() const;

  // Get whether we should use instructions that flush floating-point denormals
  // to sign-preserving zero.
  bool useF32FTZ(const MachineFunction &MF) const;

  SDValue getSqrtEstimate(SDValue Operand, SelectionDAG &DAG, int Enabled,
                          int &ExtraSteps, bool &UseOneConst,
                          bool Reciprocal) const override;

  unsigned combineRepeatedFPDivisors() const override { return 2; }

  bool allowFMA(MachineFunction &MF, CodeGenOpt::Level OptLevel) const;
  bool allowUnsafeFPMath(MachineFunction &MF) const;

  bool isFMAFasterThanFMulAndFAdd(const MachineFunction &MF,
                                  EVT) const override {
    return true;
  }

  bool enableAggressiveFMAFusion(EVT VT) const override { return true; }

  // The default is to transform llvm.ctlz(x, false) (where false indicates that
  // x == 0 is not undefined behavior) into a branch that checks whether x is 0
  // and avoids calling ctlz in that case.  We have a dedicated ctlz
  // instruction, so we say that ctlz is cheap to speculate.
  bool isCheapToSpeculateCtlz() const override { return true; }

private:
  const NVPTXSubtarget &STI; // cache the subtarget here
  SDValue getParamSymbol(SelectionDAG &DAG, int idx, EVT) const;

  SDValue LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerCONCAT_VECTORS(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;

  SDValue LowerFROUND(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerFROUND32(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerFROUND64(SDValue Op, SelectionDAG &DAG) const;

  SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerLOADi1(SDValue Op, SelectionDAG &DAG) const;

  SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerSTOREi1(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerSTOREVector(SDValue Op, SelectionDAG &DAG) const;

  SDValue LowerShiftRightParts(SDValue Op, SelectionDAG &DAG) const;
  SDValue LowerShiftLeftParts(SDValue Op, SelectionDAG &DAG) const;

  SDValue LowerSelect(SDValue Op, SelectionDAG &DAG) const;

  void ReplaceNodeResults(SDNode *N, SmallVectorImpl<SDValue> &Results,
                          SelectionDAG &DAG) const override;
  SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;

  unsigned getArgumentAlignment(SDValue Callee, ImmutableCallSite CS, Type *Ty,
                                unsigned Idx, const DataLayout &DL) const;
};
} // namespace llvm

#endif