llvm-project/llvm/lib/Target/AMDGPU/AMDGPU.td

689 lines
20 KiB
TableGen

//===-- AMDGPU.td - AMDGPU Tablegen files --------*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===------------------------------------------------------------===//
include "llvm/Target/Target.td"
//===------------------------------------------------------------===//
// Subtarget Features (device properties)
//===------------------------------------------------------------===//
def FeatureFP64 : SubtargetFeature<"fp64",
"FP64",
"true",
"Enable double precision operations"
>;
def FeatureFastFMAF32 : SubtargetFeature<"fast-fmaf",
"FastFMAF32",
"true",
"Assuming f32 fma is at least as fast as mul + add"
>;
def HalfRate64Ops : SubtargetFeature<"half-rate-64-ops",
"HalfRate64Ops",
"true",
"Most fp64 instructions are half rate instead of quarter"
>;
def FeatureR600ALUInst : SubtargetFeature<"R600ALUInst",
"R600ALUInst",
"false",
"Older version of ALU instructions encoding"
>;
def FeatureVertexCache : SubtargetFeature<"HasVertexCache",
"HasVertexCache",
"true",
"Specify use of dedicated vertex cache"
>;
def FeatureCaymanISA : SubtargetFeature<"caymanISA",
"CaymanISA",
"true",
"Use Cayman ISA"
>;
def FeatureCFALUBug : SubtargetFeature<"cfalubug",
"CFALUBug",
"true",
"GPU has CF_ALU bug"
>;
def FeatureFlatAddressSpace : SubtargetFeature<"flat-address-space",
"FlatAddressSpace",
"true",
"Support flat address space"
>;
def FeatureFlatInstOffsets : SubtargetFeature<"flat-inst-offsets",
"FlatInstOffsets",
"true",
"Flat instructions have immediate offset addressing mode"
>;
def FeatureFlatGlobalInsts : SubtargetFeature<"flat-global-insts",
"FlatGlobalInsts",
"true",
"Have global_* flat memory instructions"
>;
def FeatureFlatScratchInsts : SubtargetFeature<"flat-scratch-insts",
"FlatScratchInsts",
"true",
"Have scratch_* flat memory instructions"
>;
def FeatureUnalignedBufferAccess : SubtargetFeature<"unaligned-buffer-access",
"UnalignedBufferAccess",
"true",
"Support unaligned global loads and stores"
>;
def FeatureTrapHandler: SubtargetFeature<"trap-handler",
"TrapHandler",
"true",
"Trap handler support"
>;
def FeatureUnalignedScratchAccess : SubtargetFeature<"unaligned-scratch-access",
"UnalignedScratchAccess",
"true",
"Support unaligned scratch loads and stores"
>;
def FeatureApertureRegs : SubtargetFeature<"aperture-regs",
"HasApertureRegs",
"true",
"Has Memory Aperture Base and Size Registers"
>;
// XNACK is disabled if SH_MEM_CONFIG.ADDRESS_MODE = GPUVM on chips that support
// XNACK. The current default kernel driver setting is:
// - graphics ring: XNACK disabled
// - compute ring: XNACK enabled
//
// If XNACK is enabled, the VMEM latency can be worse.
// If XNACK is disabled, the 2 SGPRs can be used for general purposes.
def FeatureXNACK : SubtargetFeature<"xnack",
"EnableXNACK",
"true",
"Enable XNACK support"
>;
def FeatureSGPRInitBug : SubtargetFeature<"sgpr-init-bug",
"SGPRInitBug",
"true",
"VI SGPR initilization bug requiring a fixed SGPR allocation size"
>;
class SubtargetFeatureFetchLimit <string Value> :
SubtargetFeature <"fetch"#Value,
"TexVTXClauseSize",
Value,
"Limit the maximum number of fetches in a clause to "#Value
>;
def FeatureFetchLimit8 : SubtargetFeatureFetchLimit <"8">;
def FeatureFetchLimit16 : SubtargetFeatureFetchLimit <"16">;
class SubtargetFeatureWavefrontSize <int Value> : SubtargetFeature<
"wavefrontsize"#Value,
"WavefrontSize",
!cast<string>(Value),
"The number of threads per wavefront"
>;
def FeatureWavefrontSize16 : SubtargetFeatureWavefrontSize<16>;
def FeatureWavefrontSize32 : SubtargetFeatureWavefrontSize<32>;
def FeatureWavefrontSize64 : SubtargetFeatureWavefrontSize<64>;
class SubtargetFeatureLDSBankCount <int Value> : SubtargetFeature <
"ldsbankcount"#Value,
"LDSBankCount",
!cast<string>(Value),
"The number of LDS banks per compute unit."
>;
def FeatureLDSBankCount16 : SubtargetFeatureLDSBankCount<16>;
def FeatureLDSBankCount32 : SubtargetFeatureLDSBankCount<32>;
class SubtargetFeatureLocalMemorySize <int Value> : SubtargetFeature<
"localmemorysize"#Value,
"LocalMemorySize",
!cast<string>(Value),
"The size of local memory in bytes"
>;
def FeatureGCN : SubtargetFeature<"gcn",
"IsGCN",
"true",
"GCN or newer GPU"
>;
def FeatureGCN1Encoding : SubtargetFeature<"gcn1-encoding",
"GCN1Encoding",
"true",
"Encoding format for SI and CI"
>;
def FeatureGCN3Encoding : SubtargetFeature<"gcn3-encoding",
"GCN3Encoding",
"true",
"Encoding format for VI"
>;
def FeatureCIInsts : SubtargetFeature<"ci-insts",
"CIInsts",
"true",
"Additional intstructions for CI+"
>;
def FeatureGFX9Insts : SubtargetFeature<"gfx9-insts",
"GFX9Insts",
"true",
"Additional intstructions for GFX9+"
>;
def FeatureSMemRealTime : SubtargetFeature<"s-memrealtime",
"HasSMemRealTime",
"true",
"Has s_memrealtime instruction"
>;
def FeatureInv2PiInlineImm : SubtargetFeature<"inv-2pi-inline-imm",
"HasInv2PiInlineImm",
"true",
"Has 1 / (2 * pi) as inline immediate"
>;
def Feature16BitInsts : SubtargetFeature<"16-bit-insts",
"Has16BitInsts",
"true",
"Has i16/f16 instructions"
>;
def FeatureVOP3P : SubtargetFeature<"vop3p",
"HasVOP3PInsts",
"true",
"Has VOP3P packed instructions"
>;
def FeatureMovrel : SubtargetFeature<"movrel",
"HasMovrel",
"true",
"Has v_movrel*_b32 instructions"
>;
def FeatureVGPRIndexMode : SubtargetFeature<"vgpr-index-mode",
"HasVGPRIndexMode",
"true",
"Has VGPR mode register indexing"
>;
def FeatureScalarStores : SubtargetFeature<"scalar-stores",
"HasScalarStores",
"true",
"Has store scalar memory instructions"
>;
def FeatureSDWA : SubtargetFeature<"sdwa",
"HasSDWA",
"true",
"Support SDWA (Sub-DWORD Addressing) extension"
>;
def FeatureDPP : SubtargetFeature<"dpp",
"HasDPP",
"true",
"Support DPP (Data Parallel Primitives) extension"
>;
//===------------------------------------------------------------===//
// Subtarget Features (options and debugging)
//===------------------------------------------------------------===//
// Some instructions do not support denormals despite this flag. Using
// fp32 denormals also causes instructions to run at the double
// precision rate for the device.
def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
"FP32Denormals",
"true",
"Enable single precision denormal handling"
>;
// Denormal handling for fp64 and fp16 is controlled by the same
// config register when fp16 supported.
// TODO: Do we need a separate f16 setting when not legal?
def FeatureFP64FP16Denormals : SubtargetFeature<"fp64-fp16-denormals",
"FP64FP16Denormals",
"true",
"Enable double and half precision denormal handling",
[FeatureFP64]
>;
def FeatureFP64Denormals : SubtargetFeature<"fp64-denormals",
"FP64FP16Denormals",
"true",
"Enable double and half precision denormal handling",
[FeatureFP64, FeatureFP64FP16Denormals]
>;
def FeatureFP16Denormals : SubtargetFeature<"fp16-denormals",
"FP64FP16Denormals",
"true",
"Enable half precision denormal handling",
[FeatureFP64FP16Denormals]
>;
def FeatureDX10Clamp : SubtargetFeature<"dx10-clamp",
"DX10Clamp",
"true",
"clamp modifier clamps NaNs to 0.0"
>;
def FeatureFPExceptions : SubtargetFeature<"fp-exceptions",
"FPExceptions",
"true",
"Enable floating point exceptions"
>;
class FeatureMaxPrivateElementSize<int size> : SubtargetFeature<
"max-private-element-size-"#size,
"MaxPrivateElementSize",
!cast<string>(size),
"Maximum private access size may be "#size
>;
def FeatureMaxPrivateElementSize4 : FeatureMaxPrivateElementSize<4>;
def FeatureMaxPrivateElementSize8 : FeatureMaxPrivateElementSize<8>;
def FeatureMaxPrivateElementSize16 : FeatureMaxPrivateElementSize<16>;
def FeatureVGPRSpilling : SubtargetFeature<"vgpr-spilling",
"EnableVGPRSpilling",
"true",
"Enable spilling of VGPRs to scratch memory"
>;
def FeatureDumpCode : SubtargetFeature <"DumpCode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter"
>;
def FeatureDumpCodeLower : SubtargetFeature <"dumpcode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter"
>;
def FeaturePromoteAlloca : SubtargetFeature <"promote-alloca",
"EnablePromoteAlloca",
"true",
"Enable promote alloca pass"
>;
// XXX - This should probably be removed once enabled by default
def FeatureEnableLoadStoreOpt : SubtargetFeature <"load-store-opt",
"EnableLoadStoreOpt",
"true",
"Enable SI load/store optimizer pass"
>;
// Performance debugging feature. Allow using DS instruction immediate
// offsets even if the base pointer can't be proven to be base. On SI,
// base pointer values that won't give the same result as a 16-bit add
// are not safe to fold, but this will override the conservative test
// for the base pointer.
def FeatureEnableUnsafeDSOffsetFolding : SubtargetFeature <
"unsafe-ds-offset-folding",
"EnableUnsafeDSOffsetFolding",
"true",
"Force using DS instruction immediate offsets on SI"
>;
def FeatureEnableSIScheduler : SubtargetFeature<"si-scheduler",
"EnableSIScheduler",
"true",
"Enable SI Machine Scheduler"
>;
// Unless +-flat-for-global is specified, turn on FlatForGlobal for
// all OS-es on VI and newer hardware to avoid assertion failures due
// to missing ADDR64 variants of MUBUF instructions.
// FIXME: moveToVALU should be able to handle converting addr64 MUBUF
// instructions.
def FeatureFlatForGlobal : SubtargetFeature<"flat-for-global",
"FlatForGlobal",
"true",
"Force to generate flat instruction for global"
>;
def FeatureAutoWaitcntBeforeBarrier : SubtargetFeature <
"auto-waitcnt-before-barrier",
"AutoWaitcntBeforeBarrier",
"true",
"Hardware automatically inserts waitcnt before barrier"
>;
// Dummy feature used to disable assembler instructions.
def FeatureDisable : SubtargetFeature<"",
"FeatureDisable","true",
"Dummy feature to disable assembler instructions"
>;
class SubtargetFeatureGeneration <string Value,
list<SubtargetFeature> Implies> :
SubtargetFeature <Value, "Gen", "AMDGPUSubtarget::"#Value,
Value#" GPU generation", Implies>;
def FeatureLocalMemorySize0 : SubtargetFeatureLocalMemorySize<0>;
def FeatureLocalMemorySize32768 : SubtargetFeatureLocalMemorySize<32768>;
def FeatureLocalMemorySize65536 : SubtargetFeatureLocalMemorySize<65536>;
def FeatureR600 : SubtargetFeatureGeneration<"R600",
[FeatureR600ALUInst, FeatureFetchLimit8, FeatureLocalMemorySize0]
>;
def FeatureR700 : SubtargetFeatureGeneration<"R700",
[FeatureFetchLimit16, FeatureLocalMemorySize0]
>;
def FeatureEvergreen : SubtargetFeatureGeneration<"EVERGREEN",
[FeatureFetchLimit16, FeatureLocalMemorySize32768]
>;
def FeatureNorthernIslands : SubtargetFeatureGeneration<"NORTHERN_ISLANDS",
[FeatureFetchLimit16, FeatureWavefrontSize64,
FeatureLocalMemorySize32768]
>;
def FeatureSouthernIslands : SubtargetFeatureGeneration<"SOUTHERN_ISLANDS",
[FeatureFP64, FeatureLocalMemorySize32768,
FeatureWavefrontSize64, FeatureGCN, FeatureGCN1Encoding,
FeatureLDSBankCount32, FeatureMovrel]
>;
def FeatureSeaIslands : SubtargetFeatureGeneration<"SEA_ISLANDS",
[FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureGCN, FeatureFlatAddressSpace,
FeatureGCN1Encoding, FeatureCIInsts, FeatureMovrel]
>;
def FeatureVolcanicIslands : SubtargetFeatureGeneration<"VOLCANIC_ISLANDS",
[FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureFlatAddressSpace, FeatureGCN,
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
FeatureSMemRealTime, FeatureVGPRIndexMode, FeatureMovrel,
FeatureScalarStores, FeatureInv2PiInlineImm, FeatureSDWA,
FeatureDPP
]
>;
def FeatureGFX9 : SubtargetFeatureGeneration<"GFX9",
[FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureFlatAddressSpace, FeatureGCN,
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
FeatureSMemRealTime, FeatureScalarStores, FeatureInv2PiInlineImm,
FeatureApertureRegs, FeatureGFX9Insts, FeatureVOP3P, FeatureVGPRIndexMode,
FeatureFastFMAF32, FeatureSDWA, FeatureDPP,
FeatureFlatInstOffsets, FeatureFlatGlobalInsts, FeatureFlatScratchInsts
]
>;
class SubtargetFeatureISAVersion <int Major, int Minor, int Stepping,
list<SubtargetFeature> Implies>
: SubtargetFeature <
"isaver"#Major#"."#Minor#"."#Stepping,
"IsaVersion",
"ISAVersion"#Major#"_"#Minor#"_"#Stepping,
"Instruction set version number",
Implies
>;
def FeatureISAVersion6_0_0 : SubtargetFeatureISAVersion <6,0,0,
[FeatureSouthernIslands,
FeatureFastFMAF32,
HalfRate64Ops,
FeatureLDSBankCount32]>;
def FeatureISAVersion6_0_1 : SubtargetFeatureISAVersion <6,0,1,
[FeatureSouthernIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion7_0_0 : SubtargetFeatureISAVersion <7,0,0,
[FeatureSeaIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion7_0_1 : SubtargetFeatureISAVersion <7,0,1,
[FeatureSeaIslands,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureFastFMAF32]>;
def FeatureISAVersion7_0_2 : SubtargetFeatureISAVersion <7,0,2,
[FeatureSeaIslands,
FeatureLDSBankCount16]>;
def FeatureISAVersion7_0_3 : SubtargetFeatureISAVersion <7,0,3,
[FeatureSeaIslands,
FeatureLDSBankCount16]>;
def FeatureISAVersion8_0_0 : SubtargetFeatureISAVersion <8,0,0,
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureSGPRInitBug]>;
def FeatureISAVersion8_0_1 : SubtargetFeatureISAVersion <8,0,1,
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureXNACK]>;
def FeatureISAVersion8_0_2 : SubtargetFeatureISAVersion <8,0,2,
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureSGPRInitBug]>;
def FeatureISAVersion8_0_3 : SubtargetFeatureISAVersion <8,0,3,
[FeatureVolcanicIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion8_0_4 : SubtargetFeatureISAVersion <8,0,4,
[FeatureVolcanicIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion8_1_0 : SubtargetFeatureISAVersion <8,1,0,
[FeatureVolcanicIslands,
FeatureLDSBankCount16,
FeatureXNACK]>;
def FeatureISAVersion9_0_0 : SubtargetFeatureISAVersion <9,0,0,
[FeatureGFX9,
FeatureLDSBankCount32]>;
def FeatureISAVersion9_0_1 : SubtargetFeatureISAVersion <9,0,1,
[FeatureGFX9,
FeatureLDSBankCount32,
FeatureXNACK]>;
def FeatureISAVersion9_0_2 : SubtargetFeatureISAVersion <9,0,2,
[FeatureGFX9,
FeatureLDSBankCount32]>;
def FeatureISAVersion9_0_3 : SubtargetFeatureISAVersion <9,0,3,
[FeatureGFX9,
FeatureLDSBankCount32,
FeatureXNACK]>;
//===----------------------------------------------------------------------===//
// Debugger related subtarget features.
//===----------------------------------------------------------------------===//
def FeatureDebuggerInsertNops : SubtargetFeature<
"amdgpu-debugger-insert-nops",
"DebuggerInsertNops",
"true",
"Insert one nop instruction for each high level source statement"
>;
def FeatureDebuggerReserveRegs : SubtargetFeature<
"amdgpu-debugger-reserve-regs",
"DebuggerReserveRegs",
"true",
"Reserve registers for debugger usage"
>;
def FeatureDebuggerEmitPrologue : SubtargetFeature<
"amdgpu-debugger-emit-prologue",
"DebuggerEmitPrologue",
"true",
"Emit debugger prologue"
>;
//===----------------------------------------------------------------------===//
def AMDGPUInstrInfo : InstrInfo {
let guessInstructionProperties = 1;
let noNamedPositionallyEncodedOperands = 1;
}
def AMDGPUAsmParser : AsmParser {
// Some of the R600 registers have the same name, so this crashes.
// For example T0_XYZW and T0_XY both have the asm name T0.
let ShouldEmitMatchRegisterName = 0;
}
def AMDGPUAsmWriter : AsmWriter {
int PassSubtarget = 1;
}
def AMDGPUAsmVariants {
string Default = "Default";
int Default_ID = 0;
string VOP3 = "VOP3";
int VOP3_ID = 1;
string SDWA = "SDWA";
int SDWA_ID = 2;
string SDWA9 = "SDWA9";
int SDWA9_ID = 3;
string DPP = "DPP";
int DPP_ID = 4;
string Disable = "Disable";
int Disable_ID = 5;
}
def DefaultAMDGPUAsmParserVariant : AsmParserVariant {
let Variant = AMDGPUAsmVariants.Default_ID;
let Name = AMDGPUAsmVariants.Default;
}
def VOP3AsmParserVariant : AsmParserVariant {
let Variant = AMDGPUAsmVariants.VOP3_ID;
let Name = AMDGPUAsmVariants.VOP3;
}
def SDWAAsmParserVariant : AsmParserVariant {
let Variant = AMDGPUAsmVariants.SDWA_ID;
let Name = AMDGPUAsmVariants.SDWA;
}
def SDWA9AsmParserVariant : AsmParserVariant {
let Variant = AMDGPUAsmVariants.SDWA9_ID;
let Name = AMDGPUAsmVariants.SDWA9;
}
def DPPAsmParserVariant : AsmParserVariant {
let Variant = AMDGPUAsmVariants.DPP_ID;
let Name = AMDGPUAsmVariants.DPP;
}
def AMDGPU : Target {
// Pull in Instruction Info:
let InstructionSet = AMDGPUInstrInfo;
let AssemblyParsers = [AMDGPUAsmParser];
let AssemblyParserVariants = [DefaultAMDGPUAsmParserVariant,
VOP3AsmParserVariant,
SDWAAsmParserVariant,
SDWA9AsmParserVariant,
DPPAsmParserVariant];
let AssemblyWriters = [AMDGPUAsmWriter];
}
// Dummy Instruction itineraries for pseudo instructions
def ALU_NULL : FuncUnit;
def NullALU : InstrItinClass;
//===----------------------------------------------------------------------===//
// Predicate helper class
//===----------------------------------------------------------------------===//
def TruePredicate : Predicate<"true">;
def isSICI : Predicate<
"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS"
>, AssemblerPredicate<"FeatureGCN1Encoding">;
def isVI : Predicate <
"Subtarget->getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS">,
AssemblerPredicate<"FeatureGCN3Encoding">;
def isGFX9 : Predicate <
"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGFX9Insts">;
// TODO: Either the name to be changed or we simply use IsCI!
def isCIVI : Predicate <
"Subtarget->getGeneration() >= AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<"FeatureCIInsts">;
def HasFlatAddressSpace : Predicate<"Subtarget->hasFlatAddressSpace()">,
AssemblerPredicate<"FeatureFlatAddressSpace">;
def HasFlatGlobalInsts : Predicate<"Subtarget->hasFlatGlobalInsts()">,
AssemblerPredicate<"FeatureFlatGlobalInsts">;
def Has16BitInsts : Predicate<"Subtarget->has16BitInsts()">,
AssemblerPredicate<"Feature16BitInsts">;
def HasVOP3PInsts : Predicate<"Subtarget->hasVOP3PInsts()">,
AssemblerPredicate<"FeatureVOP3P">;
def HasSDWA : Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<"FeatureSDWA,FeatureVolcanicIslands">;
def HasSDWA9 : Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<"FeatureSDWA,FeatureGFX9">;
def HasDPP : Predicate<"Subtarget->hasDPP()">,
AssemblerPredicate<"FeatureDPP">;
class PredicateControl {
Predicate SubtargetPredicate;
Predicate SIAssemblerPredicate = isSICI;
Predicate VIAssemblerPredicate = isVI;
list<Predicate> AssemblerPredicates = [];
Predicate AssemblerPredicate = TruePredicate;
list<Predicate> OtherPredicates = [];
list<Predicate> Predicates = !listconcat([SubtargetPredicate, AssemblerPredicate],
AssemblerPredicates,
OtherPredicates);
}
// Include AMDGPU TD files
include "R600Schedule.td"
include "SISchedule.td"
include "Processors.td"
include "AMDGPUInstrInfo.td"
include "AMDGPUIntrinsics.td"
include "AMDGPURegisterInfo.td"
include "AMDGPURegisterBanks.td"
include "AMDGPUInstructions.td"
include "AMDGPUCallingConv.td"