forked from OSchip/llvm-project
867 lines
25 KiB
TableGen
867 lines
25 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/TableGen/SearchableTable.td"
|
|
include "llvm/Target/Target.td"
|
|
|
|
//===------------------------------------------------------------===//
|
|
// Subtarget Features (device properties)
|
|
//===------------------------------------------------------------===//
|
|
|
|
def FeatureFP64 : SubtargetFeature<"fp64",
|
|
"FP64",
|
|
"true",
|
|
"Enable double precision operations"
|
|
>;
|
|
|
|
def FeatureFMA : SubtargetFeature<"fmaf",
|
|
"FMA",
|
|
"true",
|
|
"Enable single precision FMA (not as fast as mul+add, but fused)"
|
|
>;
|
|
|
|
def FeatureFastFMAF32 : SubtargetFeature<"fast-fmaf",
|
|
"FastFMAF32",
|
|
"true",
|
|
"Assuming f32 fma is at least as fast as mul + add"
|
|
>;
|
|
|
|
def FeatureMIMG_R128 : SubtargetFeature<"mimg-r128",
|
|
"MIMG_R128",
|
|
"true",
|
|
"Support 128-bit texture resources"
|
|
>;
|
|
|
|
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 FeatureAddNoCarryInsts : SubtargetFeature<"add-no-carry-insts",
|
|
"AddNoCarryInsts",
|
|
"true",
|
|
"Have VALU add/sub instructions without carry out"
|
|
>;
|
|
|
|
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"
|
|
>;
|
|
|
|
def FeatureMadMixInsts : SubtargetFeature<"mad-mix-insts",
|
|
"HasMadMixInsts",
|
|
"true",
|
|
"Has v_mad_mix_f32, v_mad_mixlo_f16, v_mad_mixhi_f16 instructions"
|
|
>;
|
|
|
|
def FeatureFmaMixInsts : SubtargetFeature<"fma-mix-insts",
|
|
"HasFmaMixInsts",
|
|
"true",
|
|
"Has v_fma_mix_f32, v_fma_mixlo_f16, v_fma_mixhi_f16 instructions"
|
|
>;
|
|
|
|
// 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 initialization 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 FeatureGCN3Encoding : SubtargetFeature<"gcn3-encoding",
|
|
"GCN3Encoding",
|
|
"true",
|
|
"Encoding format for VI"
|
|
>;
|
|
|
|
def FeatureCIInsts : SubtargetFeature<"ci-insts",
|
|
"CIInsts",
|
|
"true",
|
|
"Additional instructions for CI+"
|
|
>;
|
|
|
|
def FeatureGFX9Insts : SubtargetFeature<"gfx9-insts",
|
|
"GFX9Insts",
|
|
"true",
|
|
"Additional instructions 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 FeatureScalarAtomics : SubtargetFeature<"scalar-atomics",
|
|
"HasScalarAtomics",
|
|
"true",
|
|
"Has atomic scalar memory instructions"
|
|
>;
|
|
|
|
def FeatureSDWA : SubtargetFeature<"sdwa",
|
|
"HasSDWA",
|
|
"true",
|
|
"Support SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureSDWAOmod : SubtargetFeature<"sdwa-omod",
|
|
"HasSDWAOmod",
|
|
"true",
|
|
"Support OMod with SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureSDWAScalar : SubtargetFeature<"sdwa-scalar",
|
|
"HasSDWAScalar",
|
|
"true",
|
|
"Support scalar register with SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureSDWASdst : SubtargetFeature<"sdwa-sdst",
|
|
"HasSDWASdst",
|
|
"true",
|
|
"Support scalar dst for VOPC with SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureSDWAMac : SubtargetFeature<"sdwa-mav",
|
|
"HasSDWAMac",
|
|
"true",
|
|
"Support v_mac_f32/f16 with SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureSDWAOutModsVOPC : SubtargetFeature<"sdwa-out-mods-vopc",
|
|
"HasSDWAOutModsVOPC",
|
|
"true",
|
|
"Support clamp for VOPC with SDWA (Sub-DWORD Addressing) extension"
|
|
>;
|
|
|
|
def FeatureDPP : SubtargetFeature<"dpp",
|
|
"HasDPP",
|
|
"true",
|
|
"Support DPP (Data Parallel Primitives) extension"
|
|
>;
|
|
|
|
def FeatureIntClamp : SubtargetFeature<"int-clamp-insts",
|
|
"HasIntClamp",
|
|
"true",
|
|
"Support clamp for integer destination"
|
|
>;
|
|
|
|
def FeatureUnpackedD16VMem : SubtargetFeature<"unpacked-d16-vmem",
|
|
"HasUnpackedD16VMem",
|
|
"true",
|
|
"Has unpacked d16 vmem instructions"
|
|
>;
|
|
|
|
def FeatureDLInsts : SubtargetFeature<"dl-insts",
|
|
"HasDLInsts",
|
|
"true",
|
|
"Has deep learning instructions"
|
|
>;
|
|
|
|
def FeatureD16PreservesUnusedBits : SubtargetFeature<
|
|
"d16-preserves-unused-bits",
|
|
"D16PreservesUnusedBits",
|
|
"true",
|
|
"If present, then instructions defined by HasD16LoadStore predicate preserve "
|
|
"unused bits. Otherwise instructions defined by HasD16LoadStore predicate "
|
|
"zero unused bits."
|
|
>;
|
|
|
|
//===------------------------------------------------------------===//
|
|
// 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 FeatureEnableHugePrivateBuffer : SubtargetFeature<
|
|
"huge-private-buffer",
|
|
"EnableHugePrivateBuffer",
|
|
"true",
|
|
"Enable private/scratch buffer sizes greater than 128 GB"
|
|
>;
|
|
|
|
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"
|
|
>;
|
|
|
|
def FeatureEnableDS128 : SubtargetFeature<"enable-ds128",
|
|
"EnableDS128",
|
|
"true",
|
|
"Use ds_{read|write}_b128"
|
|
>;
|
|
|
|
// 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"
|
|
>;
|
|
|
|
def FeatureCodeObjectV3 : SubtargetFeature <
|
|
"code-object-v3",
|
|
"CodeObjectV3",
|
|
"true",
|
|
"Generate code object version 3"
|
|
>;
|
|
|
|
// 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, FeatureMIMG_R128,
|
|
FeatureWavefrontSize64, FeatureGCN,
|
|
FeatureLDSBankCount32, FeatureMovrel]
|
|
>;
|
|
|
|
def FeatureSeaIslands : SubtargetFeatureGeneration<"SEA_ISLANDS",
|
|
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
|
|
FeatureWavefrontSize64, FeatureGCN, FeatureFlatAddressSpace,
|
|
FeatureCIInsts, FeatureMovrel]
|
|
>;
|
|
|
|
def FeatureVolcanicIslands : SubtargetFeatureGeneration<"VOLCANIC_ISLANDS",
|
|
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
|
|
FeatureWavefrontSize64, FeatureFlatAddressSpace, FeatureGCN,
|
|
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
|
|
FeatureSMemRealTime, FeatureVGPRIndexMode, FeatureMovrel,
|
|
FeatureScalarStores, FeatureInv2PiInlineImm,
|
|
FeatureSDWA, FeatureSDWAOutModsVOPC, FeatureSDWAMac, FeatureDPP,
|
|
FeatureIntClamp
|
|
]
|
|
>;
|
|
|
|
def FeatureGFX9 : SubtargetFeatureGeneration<"GFX9",
|
|
[FeatureFP64, FeatureLocalMemorySize65536,
|
|
FeatureWavefrontSize64, FeatureFlatAddressSpace, FeatureGCN,
|
|
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
|
|
FeatureSMemRealTime, FeatureScalarStores, FeatureInv2PiInlineImm,
|
|
FeatureApertureRegs, FeatureGFX9Insts, FeatureVOP3P, FeatureVGPRIndexMode,
|
|
FeatureFastFMAF32, FeatureDPP, FeatureIntClamp,
|
|
FeatureSDWA, FeatureSDWAOmod, FeatureSDWAScalar, FeatureSDWASdst,
|
|
FeatureFlatInstOffsets, FeatureFlatGlobalInsts, FeatureFlatScratchInsts,
|
|
FeatureAddNoCarryInsts, FeatureScalarAtomics
|
|
]
|
|
>;
|
|
|
|
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,
|
|
FeatureFastFMAF32]>;
|
|
|
|
def FeatureISAVersion7_0_3 : SubtargetFeatureISAVersion <7,0,3,
|
|
[FeatureSeaIslands,
|
|
FeatureLDSBankCount16]>;
|
|
|
|
def FeatureISAVersion7_0_4 : SubtargetFeatureISAVersion <7,0,4,
|
|
[FeatureSeaIslands,
|
|
FeatureLDSBankCount32]>;
|
|
|
|
def FeatureISAVersion8_0_1 : SubtargetFeatureISAVersion <8,0,1,
|
|
[FeatureVolcanicIslands,
|
|
FeatureFastFMAF32,
|
|
HalfRate64Ops,
|
|
FeatureLDSBankCount32,
|
|
FeatureXNACK,
|
|
FeatureUnpackedD16VMem]>;
|
|
|
|
def FeatureISAVersion8_0_2 : SubtargetFeatureISAVersion <8,0,2,
|
|
[FeatureVolcanicIslands,
|
|
FeatureLDSBankCount32,
|
|
FeatureSGPRInitBug,
|
|
FeatureUnpackedD16VMem]>;
|
|
|
|
def FeatureISAVersion8_0_3 : SubtargetFeatureISAVersion <8,0,3,
|
|
[FeatureVolcanicIslands,
|
|
FeatureLDSBankCount32,
|
|
FeatureUnpackedD16VMem]>;
|
|
|
|
def FeatureISAVersion8_1_0 : SubtargetFeatureISAVersion <8,1,0,
|
|
[FeatureVolcanicIslands,
|
|
FeatureLDSBankCount16,
|
|
FeatureXNACK]>;
|
|
|
|
def FeatureISAVersion9_0_0 : SubtargetFeatureISAVersion <9,0,0,
|
|
[FeatureGFX9,
|
|
FeatureMadMixInsts,
|
|
FeatureLDSBankCount32,
|
|
FeatureD16PreservesUnusedBits]>;
|
|
|
|
def FeatureISAVersion9_0_2 : SubtargetFeatureISAVersion <9,0,2,
|
|
[FeatureGFX9,
|
|
FeatureMadMixInsts,
|
|
FeatureLDSBankCount32,
|
|
FeatureXNACK,
|
|
FeatureD16PreservesUnusedBits]>;
|
|
|
|
def FeatureISAVersion9_0_4 : SubtargetFeatureISAVersion <9,0,4,
|
|
[FeatureGFX9,
|
|
FeatureLDSBankCount32,
|
|
FeatureFmaMixInsts,
|
|
FeatureD16PreservesUnusedBits]>;
|
|
|
|
def FeatureISAVersion9_0_6 : SubtargetFeatureISAVersion <9,0,6,
|
|
[FeatureGFX9,
|
|
HalfRate64Ops,
|
|
FeatureFmaMixInsts,
|
|
FeatureLDSBankCount32,
|
|
FeatureDLInsts]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Debugger related subtarget features.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def FeatureDebuggerInsertNops : SubtargetFeature<
|
|
"amdgpu-debugger-insert-nops",
|
|
"DebuggerInsertNops",
|
|
"true",
|
|
"Insert one nop instruction for each high level source statement"
|
|
>;
|
|
|
|
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];
|
|
let AllowRegisterRenaming = 1;
|
|
}
|
|
|
|
// 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<"!FeatureGCN3Encoding">;
|
|
|
|
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 HasFlatScratchInsts : Predicate<"Subtarget->hasFlatScratchInsts()">,
|
|
AssemblerPredicate<"FeatureFlatScratchInsts">;
|
|
def HasD16LoadStore : Predicate<"Subtarget->hasD16LoadStore()">,
|
|
AssemblerPredicate<"FeatureGFX9Insts">;
|
|
|
|
def HasUnpackedD16VMem : Predicate<"Subtarget->hasUnpackedD16VMem()">,
|
|
AssemblerPredicate<"FeatureUnpackedD16VMem">;
|
|
def HasPackedD16VMem : Predicate<"!Subtarget->hasUnpackedD16VMem()">,
|
|
AssemblerPredicate<"!FeatureUnpackedD16VMem">;
|
|
|
|
def D16PreservesUnusedBits : Predicate<"Subtarget->d16PreservesUnusedBits()">,
|
|
AssemblerPredicate<"FeatureD16PreservesUnusedBits">;
|
|
|
|
def LDSRequiresM0Init : Predicate<"Subtarget->ldsRequiresM0Init()">;
|
|
def NotLDSRequiresM0Init : Predicate<"!Subtarget->ldsRequiresM0Init()">;
|
|
|
|
def HasDSAddTid : Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
|
|
AssemblerPredicate<"FeatureGFX9Insts">;
|
|
|
|
def HasAddNoCarryInsts : Predicate<"Subtarget->hasAddNoCarryInsts()">,
|
|
AssemblerPredicate<"FeatureAddNoCarryInsts">;
|
|
|
|
def NotHasAddNoCarryInsts : Predicate<"!Subtarget->hasAddNoCarryInsts()">,
|
|
AssemblerPredicate<"!FeatureAddNoCarryInsts">;
|
|
|
|
def Has16BitInsts : Predicate<"Subtarget->has16BitInsts()">,
|
|
AssemblerPredicate<"Feature16BitInsts">;
|
|
def HasVOP3PInsts : Predicate<"Subtarget->hasVOP3PInsts()">,
|
|
AssemblerPredicate<"FeatureVOP3P">;
|
|
|
|
def NotHasVOP3PInsts : 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">;
|
|
|
|
def HasIntClamp : Predicate<"Subtarget->hasIntClamp()">,
|
|
AssemblerPredicate<"FeatureIntClamp">;
|
|
|
|
def HasMadMixInsts : Predicate<"Subtarget->hasMadMixInsts()">,
|
|
AssemblerPredicate<"FeatureMadMixInsts">;
|
|
|
|
def HasScalarAtomics : Predicate<"Subtarget->hasScalarAtomics()">,
|
|
AssemblerPredicate<"FeatureScalarAtomics">;
|
|
|
|
def has16BankLDS : Predicate<"Subtarget->getLDSBankCount() == 16">;
|
|
def has32BankLDS : Predicate<"Subtarget->getLDSBankCount() == 32">;
|
|
def HasVGPRIndexMode : Predicate<"Subtarget->hasVGPRIndexMode()">,
|
|
AssemblerPredicate<"FeatureVGPRIndexMode">;
|
|
def HasMovrel : Predicate<"Subtarget->hasMovrel()">,
|
|
AssemblerPredicate<"FeatureMovrel">;
|
|
|
|
def HasFmaMixInsts : Predicate<"Subtarget->hasFmaMixInsts()">,
|
|
AssemblerPredicate<"FeatureFmaMixInsts">;
|
|
|
|
def HasDLInsts : Predicate<"Subtarget->hasDLInsts()">,
|
|
AssemblerPredicate<"FeatureDLInsts">;
|
|
|
|
|
|
def EnableLateCFGStructurize : Predicate<
|
|
"EnableLateStructurizeCFG">;
|
|
|
|
// Exists to help track down where SubtargetPredicate isn't set rather
|
|
// than letting tablegen crash with an unhelpful error.
|
|
def InvalidPred : Predicate<"predicate not set on instruction or pattern">;
|
|
|
|
class PredicateControl {
|
|
Predicate SubtargetPredicate = InvalidPred;
|
|
Predicate SIAssemblerPredicate = isSICI;
|
|
Predicate VIAssemblerPredicate = isVI;
|
|
list<Predicate> AssemblerPredicates = [];
|
|
Predicate AssemblerPredicate = TruePredicate;
|
|
list<Predicate> OtherPredicates = [];
|
|
list<Predicate> Predicates = !listconcat([SubtargetPredicate,
|
|
AssemblerPredicate],
|
|
AssemblerPredicates,
|
|
OtherPredicates);
|
|
}
|
|
|
|
class AMDGPUPat<dag pattern, dag result> : Pat<pattern, result>,
|
|
PredicateControl;
|
|
|
|
|
|
// Include AMDGPU TD files
|
|
include "R600Schedule.td"
|
|
include "R600Processors.td"
|
|
include "SISchedule.td"
|
|
include "GCNProcessors.td"
|
|
include "AMDGPUInstrInfo.td"
|
|
include "AMDGPUIntrinsics.td"
|
|
include "AMDGPURegisterInfo.td"
|
|
include "AMDGPURegisterBanks.td"
|
|
include "AMDGPUInstructions.td"
|
|
include "AMDGPUCallingConv.td"
|
|
include "AMDGPUSearchableTables.td"
|