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
|
//=====-- AMDGPUSubtarget.h - Define Subtarget for AMDGPU ------*- C++ -*-====//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//==-----------------------------------------------------------------------===//
//
/// \file
/// \brief AMDGPU specific subclass of TargetSubtarget.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
#include "AMDGPU.h"
#include "R600InstrInfo.h"
#include "R600ISelLowering.h"
#include "R600FrameLowering.h"
#include "SIInstrInfo.h"
#include "SIISelLowering.h"
#include "SIFrameLowering.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/CodeGen/GlobalISel/GISelAccessor.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#define GET_SUBTARGETINFO_HEADER
#include "AMDGPUGenSubtargetInfo.inc"
namespace llvm {
class SIMachineFunctionInfo;
class StringRef;
class AMDGPUSubtarget : public AMDGPUGenSubtargetInfo {
public:
enum Generation {
R600 = 0,
R700,
EVERGREEN,
NORTHERN_ISLANDS,
SOUTHERN_ISLANDS,
SEA_ISLANDS,
VOLCANIC_ISLANDS,
};
enum {
ISAVersion0_0_0,
ISAVersion7_0_0,
ISAVersion7_0_1,
ISAVersion8_0_0,
ISAVersion8_0_1,
ISAVersion8_0_3
};
protected:
// Basic subtarget description.
Triple TargetTriple;
Generation Gen;
unsigned IsaVersion;
unsigned WavefrontSize;
int LocalMemorySize;
int LDSBankCount;
unsigned MaxPrivateElementSize;
// Possibly statically set by tablegen, but may want to be overridden.
bool FastFMAF32;
bool HalfRate64Ops;
// Dynamially set bits that enable features.
bool FP32Denormals;
bool FP64Denormals;
bool FPExceptions;
bool FlatForGlobal;
bool UnalignedBufferAccess;
bool EnableXNACK;
bool DebuggerInsertNops;
bool DebuggerReserveRegs;
bool DebuggerEmitPrologue;
// Used as options.
bool EnableVGPRSpilling;
bool EnablePromoteAlloca;
bool EnableLoadStoreOpt;
bool EnableUnsafeDSOffsetFolding;
bool EnableSIScheduler;
bool DumpCode;
// Subtarget statically properties set by tablegen
bool FP64;
bool IsGCN;
bool GCN1Encoding;
bool GCN3Encoding;
bool CIInsts;
bool SGPRInitBug;
bool HasSMemRealTime;
bool Has16BitInsts;
bool FlatAddressSpace;
bool R600ALUInst;
bool CaymanISA;
bool CFALUBug;
bool HasVertexCache;
short TexVTXClauseSize;
// Dummy feature to use for assembler in tablegen.
bool FeatureDisable;
InstrItineraryData InstrItins;
public:
AMDGPUSubtarget(const Triple &TT, StringRef GPU, StringRef FS,
const TargetMachine &TM);
virtual ~AMDGPUSubtarget();
AMDGPUSubtarget &initializeSubtargetDependencies(const Triple &TT,
StringRef GPU, StringRef FS);
const AMDGPUInstrInfo *getInstrInfo() const override;
const AMDGPUFrameLowering *getFrameLowering() const override;
const AMDGPUTargetLowering *getTargetLowering() const override;
const AMDGPURegisterInfo *getRegisterInfo() const override;
const InstrItineraryData *getInstrItineraryData() const override {
return &InstrItins;
}
void ParseSubtargetFeatures(StringRef CPU, StringRef FS);
bool isAmdHsaOS() const {
return TargetTriple.getOS() == Triple::AMDHSA;
}
Generation getGeneration() const {
return Gen;
}
unsigned getWavefrontSize() const {
return WavefrontSize;
}
int getLocalMemorySize() const {
return LocalMemorySize;
}
int getLDSBankCount() const {
return LDSBankCount;
}
unsigned getMaxPrivateElementSize() const {
return MaxPrivateElementSize;
}
bool hasHWFP64() const {
return FP64;
}
bool hasFastFMAF32() const {
return FastFMAF32;
}
bool hasHalfRate64Ops() const {
return HalfRate64Ops;
}
bool hasAddr64() const {
return (getGeneration() < VOLCANIC_ISLANDS);
}
bool hasBFE() const {
return (getGeneration() >= EVERGREEN);
}
bool hasBFI() const {
return (getGeneration() >= EVERGREEN);
}
bool hasBFM() const {
return hasBFE();
}
bool hasBCNT(unsigned Size) const {
if (Size == 32)
return (getGeneration() >= EVERGREEN);
if (Size == 64)
return (getGeneration() >= SOUTHERN_ISLANDS);
return false;
}
bool hasMulU24() const {
return (getGeneration() >= EVERGREEN);
}
bool hasMulI24() const {
return (getGeneration() >= SOUTHERN_ISLANDS ||
hasCaymanISA());
}
bool hasFFBL() const {
return (getGeneration() >= EVERGREEN);
}
bool hasFFBH() const {
return (getGeneration() >= EVERGREEN);
}
bool hasCARRY() const {
return (getGeneration() >= EVERGREEN);
}
bool hasBORROW() const {
return (getGeneration() >= EVERGREEN);
}
bool hasCaymanISA() const {
return CaymanISA;
}
bool isPromoteAllocaEnabled() const {
return EnablePromoteAlloca;
}
bool unsafeDSOffsetFoldingEnabled() const {
return EnableUnsafeDSOffsetFolding;
}
bool dumpCode() const {
return DumpCode;
}
/// Return the amount of LDS that can be used that will not restrict the
/// occupancy lower than WaveCount.
unsigned getMaxLocalMemSizeWithWaveCount(unsigned WaveCount) const;
/// Inverse of getMaxLocalMemWithWaveCount. Return the maximum wavecount if
/// the given LDS memory size is the only constraint.
unsigned getOccupancyWithLocalMemSize(uint32_t Bytes) const;
bool hasFP32Denormals() const {
return FP32Denormals;
}
bool hasFP64Denormals() const {
return FP64Denormals;
}
bool hasFPExceptions() const {
return FPExceptions;
}
bool useFlatForGlobal() const {
return FlatForGlobal;
}
bool hasUnalignedBufferAccess() const {
return UnalignedBufferAccess;
}
bool isXNACKEnabled() const {
return EnableXNACK;
}
unsigned getMaxWavesPerCU() const {
if (getGeneration() >= AMDGPUSubtarget::SOUTHERN_ISLANDS)
return 10;
// FIXME: Not sure what this is for other subtagets.
return 8;
}
/// \brief Returns the offset in bytes from the start of the input buffer
/// of the first explicit kernel argument.
unsigned getExplicitKernelArgOffset() const {
return isAmdHsaOS() ? 0 : 36;
}
unsigned getStackAlignment() const {
// Scratch is allocated in 256 dword per wave blocks.
return 4 * 256 / getWavefrontSize();
}
bool enableMachineScheduler() const override {
return true;
}
bool enableSubRegLiveness() const override {
return true;
}
};
class R600Subtarget final : public AMDGPUSubtarget {
private:
R600InstrInfo InstrInfo;
R600FrameLowering FrameLowering;
R600TargetLowering TLInfo;
public:
R600Subtarget(const Triple &TT, StringRef CPU, StringRef FS,
const TargetMachine &TM);
const R600InstrInfo *getInstrInfo() const override {
return &InstrInfo;
}
const R600FrameLowering *getFrameLowering() const override {
return &FrameLowering;
}
const R600TargetLowering *getTargetLowering() const override {
return &TLInfo;
}
const R600RegisterInfo *getRegisterInfo() const override {
return &InstrInfo.getRegisterInfo();
}
bool hasCFAluBug() const {
return CFALUBug;
}
bool hasVertexCache() const {
return HasVertexCache;
}
short getTexVTXClauseSize() const {
return TexVTXClauseSize;
}
unsigned getStackEntrySize() const;
};
class SISubtarget final : public AMDGPUSubtarget {
public:
enum {
FIXED_SGPR_COUNT_FOR_INIT_BUG = 80
};
private:
SIInstrInfo InstrInfo;
SIFrameLowering FrameLowering;
SITargetLowering TLInfo;
std::unique_ptr<GISelAccessor> GISel;
public:
SISubtarget(const Triple &TT, StringRef CPU, StringRef FS,
const TargetMachine &TM);
const SIInstrInfo *getInstrInfo() const override {
return &InstrInfo;
}
const SIFrameLowering *getFrameLowering() const override {
return &FrameLowering;
}
const SITargetLowering *getTargetLowering() const override {
return &TLInfo;
}
const CallLowering *getCallLowering() const override {
assert(GISel && "Access to GlobalISel APIs not set");
return GISel->getCallLowering();
}
const SIRegisterInfo *getRegisterInfo() const override {
return &InstrInfo.getRegisterInfo();
}
void setGISelAccessor(GISelAccessor &GISel) {
this->GISel.reset(&GISel);
}
void overrideSchedPolicy(MachineSchedPolicy &Policy,
unsigned NumRegionInstrs) const override;
bool isVGPRSpillingEnabled(const Function& F) const;
unsigned getAmdKernelCodeChipID() const;
AMDGPU::IsaVersion getIsaVersion() const;
unsigned getMaxNumUserSGPRs() const {
return 16;
}
bool hasFlatAddressSpace() const {
return FlatAddressSpace;
}
bool hasSMemRealTime() const {
return HasSMemRealTime;
}
bool has16BitInsts() const {
return Has16BitInsts;
}
bool enableSIScheduler() const {
return EnableSIScheduler;
}
bool debuggerSupported() const {
return debuggerInsertNops() && debuggerReserveRegs() &&
debuggerEmitPrologue();
}
bool debuggerInsertNops() const {
return DebuggerInsertNops;
}
bool debuggerReserveRegs() const {
return DebuggerReserveRegs;
}
bool debuggerEmitPrologue() const {
return DebuggerEmitPrologue;
}
bool loadStoreOptEnabled() const {
return EnableLoadStoreOpt;
}
bool hasSGPRInitBug() const {
return SGPRInitBug;
}
};
inline const AMDGPUInstrInfo *AMDGPUSubtarget::getInstrInfo() const {
if (getGeneration() >= SOUTHERN_ISLANDS)
return static_cast<const SISubtarget *>(this)->getInstrInfo();
return static_cast<const R600Subtarget *>(this)->getInstrInfo();
}
inline const AMDGPUFrameLowering *AMDGPUSubtarget::getFrameLowering() const {
if (getGeneration() >= SOUTHERN_ISLANDS)
return static_cast<const SISubtarget *>(this)->getFrameLowering();
return static_cast<const R600Subtarget *>(this)->getFrameLowering();
}
inline const AMDGPUTargetLowering *AMDGPUSubtarget::getTargetLowering() const {
if (getGeneration() >= SOUTHERN_ISLANDS)
return static_cast<const SISubtarget *>(this)->getTargetLowering();
return static_cast<const R600Subtarget *>(this)->getTargetLowering();
}
inline const AMDGPURegisterInfo *AMDGPUSubtarget::getRegisterInfo() const {
if (getGeneration() >= SOUTHERN_ISLANDS)
return static_cast<const SISubtarget *>(this)->getRegisterInfo();
return static_cast<const R600Subtarget *>(this)->getRegisterInfo();
}
} // End namespace llvm
#endif
|