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

317 lines
11 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
//===----------------------------------------------------------------------===//
// Debugging Features
def FeatureDumpCode : SubtargetFeature <"DumpCode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter">;
def FeatureDumpCodeLower : SubtargetFeature <"dumpcode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter">;
def FeatureIRStructurizer : SubtargetFeature <"disable-irstructurizer",
"EnableIRStructurizer",
"false",
"Disable IR Structurizer">;
def FeaturePromoteAlloca : SubtargetFeature <"promote-alloca",
"EnablePromoteAlloca",
"true",
"Enable promote alloca pass">;
// Target features
def FeatureIfCvt : SubtargetFeature <"disable-ifcvt",
"EnableIfCvt",
"false",
"Disable the if conversion pass">;
def FeatureFP64 : SubtargetFeature<"fp64",
"FP64",
"true",
"Enable double precision operations">;
def FeatureFP64Denormals : SubtargetFeature<"fp64-denormals",
"FP64Denormals",
"true",
"Enable double precision denormal handling",
[FeatureFP64]>;
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",
[]>;
// 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">;
def Feature64BitPtr : SubtargetFeature<"64BitPtr",
"Is64bit",
"true",
"Specify if 64-bit addressing should be used">;
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">;
// 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 FeatureFlatForGlobal : SubtargetFeature<"flat-for-global",
"FlatForGlobal",
"true",
"Force to generate flat instruction for global">;
def FeatureFlatAddressSpace : SubtargetFeature<"flat-address-space",
"FlatAddressSpace",
"true",
"Support flat address space">;
def FeatureXNACK : SubtargetFeature<"xnack",
"EnableXNACK",
"true",
"Enable XNACK support">;
def FeatureVGPRSpilling : SubtargetFeature<"vgpr-spilling",
"EnableVGPRSpilling",
"true",
"Enable spilling of VGPRs to scratch memory">;
def FeatureSGPRInitBug : SubtargetFeature<"sgpr-init-bug",
"SGPRInitBug",
"true",
"VI SGPR initilization bug requiring a fixed SGPR allocation size">;
def FeatureEnableHugeScratchBuffer : SubtargetFeature<"huge-scratch-buffer",
"EnableHugeScratchBuffer",
"true",
"Enable scratch buffer sizes greater than 128 GB">;
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 SubtargetFeatureISAVersion <int Major, int Minor, int Stepping>
: SubtargetFeature <
"isaver"#Major#"."#Minor#"."#Stepping,
"IsaVersion",
"ISAVersion"#Major#"_"#Minor#"_"#Stepping,
"Instruction set version number"
>;
def FeatureISAVersion7_0_0 : SubtargetFeatureISAVersion <7,0,0>;
def FeatureISAVersion7_0_1 : SubtargetFeatureISAVersion <7,0,1>;
def FeatureISAVersion8_0_0 : SubtargetFeatureISAVersion <8,0,0>;
def FeatureISAVersion8_0_1 : SubtargetFeatureISAVersion <8,0,1>;
def FeatureISAVersion8_0_3 : SubtargetFeatureISAVersion <8,0,3>;
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+">;
// 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",
[Feature64BitPtr, FeatureFP64, FeatureLocalMemorySize32768,
FeatureWavefrontSize64, FeatureGCN, FeatureGCN1Encoding,
FeatureLDSBankCount32]>;
def FeatureSeaIslands : SubtargetFeatureGeneration<"SEA_ISLANDS",
[Feature64BitPtr, FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureGCN, FeatureFlatAddressSpace,
FeatureGCN1Encoding, FeatureCIInsts]>;
def FeatureVolcanicIslands : SubtargetFeatureGeneration<"VOLCANIC_ISLANDS",
[Feature64BitPtr, FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureFlatAddressSpace, FeatureGCN,
FeatureGCN3Encoding, FeatureCIInsts, FeatureLDSBankCount32]>;
//===----------------------------------------------------------------------===//
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 AMDGPU : Target {
// Pull in Instruction Info:
let InstructionSet = AMDGPUInstrInfo;
let AssemblyParsers = [AMDGPUAsmParser];
}
// 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">;
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 "AMDGPUInstructions.td"
include "AMDGPUCallingConv.td"