maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/AMDGPU/AMDGPU.td

1499 lines
44 KiB
TableGen
Raw Blame History

//===-- AMDGPU.td - AMDGPU Tablegen files --------*- tablegen -*-===//
//
// 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
//
//===------------------------------------------------------------===//
include "llvm/TableGen/SearchableTable.td"
include "llvm/Target/Target.td"
include "AMDGPUFeatures.td"
def p0 : PtrValueType<i64, 0>;
def p1 : PtrValueType<i64, 1>;
def p2 : PtrValueType<i32, 2>;
def p3 : PtrValueType<i32, 3>;
def p4 : PtrValueType<i64, 4>;
def p5 : PtrValueType<i32, 5>;
def p6 : PtrValueType<i32, 6>;
class BoolToList<bit Value> {
list<int> ret = !if(Value, [1]<int>, []<int>);
}
//===------------------------------------------------------------===//
// Subtarget Features (device properties)
//===------------------------------------------------------------===//
def FeatureFastFMAF32 : SubtargetFeature<"fast-fmaf",
"FastFMAF32",
"true",
"Assuming f32 fma is at least as fast as mul + add"
>;
def FeatureFastDenormalF32 : SubtargetFeature<"fast-denormal-f32",
"FastDenormalF32",
"true",
"Enabling denormals does not cause f32 instructions to run at f64 rates"
>;
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 FullRate64Ops : SubtargetFeature<"full-rate-64-ops",
"FullRate64Ops",
"true",
"Most fp64 instructions are full rate"
>;
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 FeatureScalarFlatScratchInsts : SubtargetFeature<"scalar-flat-scratch-insts",
"ScalarFlatScratchInsts",
"true",
"Have s_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",
"Hardware supports 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 FeatureUnalignedDSAccess : SubtargetFeature<"unaligned-ds-access",
"UnalignedDSAccess",
"true",
"Hardware supports unaligned local and region 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"
>;
def FeatureSupportsXNACK : SubtargetFeature<"xnack-support",
"SupportsXNACK",
"true",
"Hardware supports XNACK"
>;
// 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 FeatureTgSplit : SubtargetFeature<"tgsplit",
"EnableTgSplit",
"true",
"Enable threadgroup split execution"
>;
def FeatureCuMode : SubtargetFeature<"cumode",
"EnableCuMode",
"true",
"Enable CU wavefront execution mode"
>;
def FeatureSGPRInitBug : SubtargetFeature<"sgpr-init-bug",
"SGPRInitBug",
"true",
"VI SGPR initialization bug requiring a fixed SGPR allocation size"
>;
def FeatureLdsMisalignedBug : SubtargetFeature<"lds-misaligned-bug",
"LDSMisalignedBug",
"true",
"Some GFX10 bug with multi-dword LDS and flat access that is not naturally aligned in WGP mode"
>;
def FeatureMFMAInlineLiteralBug : SubtargetFeature<"mfma-inline-literal-bug",
"HasMFMAInlineLiteralBug",
"true",
"MFMA cannot use inline literal as SrcC"
>;
def FeatureVcmpxPermlaneHazard : SubtargetFeature<"vcmpx-permlane-hazard",
"HasVcmpxPermlaneHazard",
"true",
"TODO: describe me"
>;
def FeatureVMEMtoScalarWriteHazard : SubtargetFeature<"vmem-to-scalar-write-hazard",
"HasVMEMtoScalarWriteHazard",
"true",
"VMEM instruction followed by scalar writing to EXEC mask, M0 or SGPR leads to incorrect execution."
>;
def FeatureSMEMtoVectorWriteHazard : SubtargetFeature<"smem-to-vector-write-hazard",
"HasSMEMtoVectorWriteHazard",
"true",
"s_load_dword followed by v_cmp page faults"
>;
def FeatureInstFwdPrefetchBug : SubtargetFeature<"inst-fwd-prefetch-bug",
"HasInstFwdPrefetchBug",
"true",
"S_INST_PREFETCH instruction causes shader to hang"
>;
def FeatureVcmpxExecWARHazard : SubtargetFeature<"vcmpx-exec-war-hazard",
"HasVcmpxExecWARHazard",
"true",
"V_CMPX WAR hazard on EXEC (V_CMPX issue ONLY)"
>;
def FeatureLdsBranchVmemWARHazard : SubtargetFeature<"lds-branch-vmem-war-hazard",
"HasLdsBranchVmemWARHazard",
"true",
"Switching between LDS and VMEM-tex not waiting VM_VSRC=0"
>;
def FeatureNSAtoVMEMBug : SubtargetFeature<"nsa-to-vmem-bug",
"HasNSAtoVMEMBug",
"true",
"MIMG-NSA followed by VMEM fail if EXEC_LO or EXEC_HI equals zero"
>;
def FeatureNSAClauseBug : SubtargetFeature<"nsa-clause-bug",
"HasNSAClauseBug",
"true",
"MIMG-NSA in a hard clause has unpredictable results on GFX10.1"
>;
def FeatureFlatSegmentOffsetBug : SubtargetFeature<"flat-segment-offset-bug",
"HasFlatSegmentOffsetBug",
"true",
"GFX10 bug where inst_offset is ignored when flat instructions access global memory"
>;
def FeatureNegativeScratchOffsetBug : SubtargetFeature<"negative-scratch-offset-bug",
"NegativeScratchOffsetBug",
"true",
"Negative immediate offsets in scratch instructions with an SGPR offset page fault on GFX9"
>;
def FeatureNegativeUnalignedScratchOffsetBug : SubtargetFeature<"negative-unaligned-scratch-offset-bug",
"NegativeUnalignedScratchOffsetBug",
"true",
"Scratch instructions with a VGPR offset and a negative immediate offset that is not a multiple of 4 read wrong memory on GFX10"
>;
def FeatureOffset3fBug : SubtargetFeature<"offset-3f-bug",
"HasOffset3fBug",
"true",
"Branch offset of 3f hardware bug"
>;
def FeatureImageStoreD16Bug : SubtargetFeature<"image-store-d16-bug",
"HasImageStoreD16Bug",
"true",
"Image Store D16 hardware bug"
>;
def FeatureImageGather4D16Bug : SubtargetFeature<"image-gather4-d16-bug",
"HasImageGather4D16Bug",
"true",
"Image Gather4 D16 hardware bug"
>;
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>;
def FeatureGCN3Encoding : SubtargetFeature<"gcn3-encoding",
"GCN3Encoding",
"true",
"Encoding format for VI"
>;
def FeatureCIInsts : SubtargetFeature<"ci-insts",
"CIInsts",
"true",
"Additional instructions for CI+"
>;
def FeatureGFX8Insts : SubtargetFeature<"gfx8-insts",
"GFX8Insts",
"true",
"Additional instructions for GFX8+"
>;
def FeatureGFX9Insts : SubtargetFeature<"gfx9-insts",
"GFX9Insts",
"true",
"Additional instructions for GFX9+"
>;
def FeatureGFX90AInsts : SubtargetFeature<"gfx90a-insts",
"GFX90AInsts",
"true",
"Additional instructions for GFX90A+"
>;
def FeatureGFX10Insts : SubtargetFeature<"gfx10-insts",
"GFX10Insts",
"true",
"Additional instructions for GFX10+"
>;
def FeatureGFX10_3Insts : SubtargetFeature<"gfx10-3-insts",
"GFX10_3Insts",
"true",
"Additional instructions for GFX10.3"
>;
def FeatureGFX7GFX8GFX9Insts : SubtargetFeature<"gfx7-gfx8-gfx9-insts",
"GFX7GFX8GFX9Insts",
"true",
"Instructions shared in GFX7, GFX8, 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"
>;
// DPP8 allows arbitrary cross-lane swizzling withing groups of 8 lanes.
def FeatureDPP8 : SubtargetFeature<"dpp8",
"HasDPP8",
"true",
"Support DPP8 (Data Parallel Primitives) extension"
>;
def Feature64BitDPP : SubtargetFeature<"dpp-64bit",
"Has64BitDPP",
"true",
"Support DPP (Data Parallel Primitives) extension"
>;
def FeaturePackedFP32Ops : SubtargetFeature<"packed-fp32-ops",
"HasPackedFP32Ops",
"true",
"Support packed fp32 instructions"
>;
def FeatureR128A16 : SubtargetFeature<"r128-a16",
"HasR128A16",
"true",
"Support gfx9-style A16 for 16-bit coordinates/gradients/lod/clamp/mip image operands, where a16 is aliased with r128"
>;
def FeatureGFX10A16 : SubtargetFeature<"a16",
"HasGFX10A16",
"true",
"Support gfx10-style A16 for 16-bit coordinates/gradients/lod/clamp/mip image operands"
>;
def FeatureG16 : SubtargetFeature<"g16",
"HasG16",
"true",
"Support G16 for 16-bit gradient image operands"
>;
def FeatureNSAEncoding : SubtargetFeature<"nsa-encoding",
"HasNSAEncoding",
"true",
"Support NSA encoding for image instructions"
>;
def FeatureExtendedImageInsts : SubtargetFeature<"extended-image-insts",
"HasExtendedImageInsts",
"true",
"Support mips != 0, lod != 0, gather4, and get_lod"
>;
def FeatureGFX10_AEncoding : SubtargetFeature<"gfx10_a-encoding",
"GFX10_AEncoding",
"true",
"Has BVH ray tracing instructions"
>;
def FeatureGFX10_BEncoding : SubtargetFeature<"gfx10_b-encoding",
"GFX10_BEncoding",
"true",
"Encoding format GFX10_B"
>;
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 v_fmac_f32 and v_xnor_b32 instructions"
>;
def FeatureDot1Insts : SubtargetFeature<"dot1-insts",
"HasDot1Insts",
"true",
"Has v_dot4_i32_i8 and v_dot8_i32_i4 instructions"
>;
def FeatureDot2Insts : SubtargetFeature<"dot2-insts",
"HasDot2Insts",
"true",
"Has v_dot2_i32_i16, v_dot2_u32_u16 instructions"
>;
def FeatureDot3Insts : SubtargetFeature<"dot3-insts",
"HasDot3Insts",
"true",
"Has v_dot8c_i32_i4 instruction"
>;
def FeatureDot4Insts : SubtargetFeature<"dot4-insts",
"HasDot4Insts",
"true",
"Has v_dot2c_i32_i16 instruction"
>;
def FeatureDot5Insts : SubtargetFeature<"dot5-insts",
"HasDot5Insts",
"true",
"Has v_dot2c_f32_f16 instruction"
>;
def FeatureDot6Insts : SubtargetFeature<"dot6-insts",
"HasDot6Insts",
"true",
"Has v_dot4c_i32_i8 instruction"
>;
def FeatureDot7Insts : SubtargetFeature<"dot7-insts",
"HasDot7Insts",
"true",
"Has v_dot2_f32_f16, v_dot4_u32_u8, v_dot8_u32_u4 instructions"
>;
def FeatureMAIInsts : SubtargetFeature<"mai-insts",
"HasMAIInsts",
"true",
"Has mAI instructions"
>;
def FeaturePkFmacF16Inst : SubtargetFeature<"pk-fmac-f16-inst",
"HasPkFmacF16Inst",
"true",
"Has v_pk_fmac_f16 instruction"
>;
def FeatureAtomicFaddInsts : SubtargetFeature<"atomic-fadd-insts",
"HasAtomicFaddInsts",
"true",
"Has buffer_atomic_add_f32, buffer_atomic_pk_add_f16, global_atomic_add_f32, "
"global_atomic_pk_add_f16 instructions",
[FeatureFlatGlobalInsts]
>;
def FeatureSupportsSRAMECC : SubtargetFeature<"sramecc-support",
"SupportsSRAMECC",
"true",
"Hardware supports SRAMECC"
>;
def FeatureSRAMECC : SubtargetFeature<"sramecc",
"EnableSRAMECC",
"true",
"Enable SRAMECC"
>;
def FeatureNoSdstCMPX : SubtargetFeature<"no-sdst-cmpx",
"HasNoSdstCMPX",
"true",
"V_CMPX does not write VCC/SGPR in addition to EXEC"
>;
def FeatureVscnt : SubtargetFeature<"vscnt",
"HasVscnt",
"true",
"Has separate store vscnt counter"
>;
def FeatureGetWaveIdInst : SubtargetFeature<"get-wave-id-inst",
"HasGetWaveIdInst",
"true",
"Has s_get_waveid_in_workgroup instruction"
>;
def FeatureSMemTimeInst : SubtargetFeature<"s-memtime-inst",
"HasSMemTimeInst",
"true",
"Has s_memtime instruction"
>;
def FeatureShaderCyclesRegister : SubtargetFeature<"shader-cycles-register",
"HasShaderCyclesRegister",
"true",
"Has SHADER_CYCLES hardware register"
>;
def FeatureMadMacF32Insts : SubtargetFeature<"mad-mac-f32-insts",
"HasMadMacF32Insts",
"true",
"Has v_mad_f32/v_mac_f32/v_madak_f32/v_madmk_f32 instructions"
>;
def FeatureDsSrc2Insts : SubtargetFeature<"ds-src2-insts",
"HasDsSrc2Insts",
"true",
"Has ds_*_src2 instructions"
>;
def FeatureRegisterBanking : SubtargetFeature<"register-banking",
"HasRegisterBanking",
"true",
"Has register banking"
>;
def FeatureVOP3Literal : SubtargetFeature<"vop3-literal",
"HasVOP3Literal",
"true",
"Can use one literal in VOP3"
>;
def FeatureNoDataDepHazard : SubtargetFeature<"no-data-dep-hazard",
"HasNoDataDepHazard",
"true",
"Does not need SW waitstates"
>;
//===------------------------------------------------------------===//
// Subtarget Features (options and debugging)
//===------------------------------------------------------------===//
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 FeatureDumpCode : SubtargetFeature <"DumpCode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter"
>;
def FeatureDumpCodeLower : SubtargetFeature <"dumpcode",
"DumpCode",
"true",
"Dump MachineInstrs in the CodeEmitter"
>;
// 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"
>;
// Sparse texture support requires that all result registers are zeroed when
// PRTStrictNull is set to true. This feature is turned on for all architectures
// but is enabled as a feature in case there are situations where PRTStrictNull
// is disabled by the driver.
def FeatureEnablePRTStrictNull : SubtargetFeature<"enable-prt-strict-null",
"EnablePRTStrictNull",
"true",
"Enable zeroing of result registers for sparse texture fetches"
>;
// 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 FeatureTrigReducedRange : SubtargetFeature<"trig-reduced-range",
"HasTrigReducedRange",
"true",
"Requires use of fract on arguments to trig instructions"
>;
// Alignment enforcement is controlled by a configuration register:
// SH_MEM_CONFIG.alignment_mode
def FeatureUnalignedAccessMode : SubtargetFeature<"unaligned-access-mode",
"UnalignedAccessMode",
"true",
"Enable unaligned global, local and region loads and stores if the hardware"
" supports it"
>;
def FeaturePackedTID : SubtargetFeature<"packed-tid",
"HasPackedTID",
"true",
"Workitem IDs are packed into v0 at kernel launch"
>;
def FeatureArchitectedFlatScratch : SubtargetFeature<"architected-flat-scratch",
"HasArchitectedFlatScratch",
"true",
"Flat Scratch register is a readonly SPI initialized architected register"
>;
// Dummy feature used to disable assembler instructions.
def FeatureDisable : SubtargetFeature<"",
"FeatureDisable","true",
"Dummy feature to disable assembler instructions"
>;
class GCNSubtargetFeatureGeneration <string Value,
string FeatureName,
list<SubtargetFeature> Implies> :
SubtargetFeatureGeneration <Value, FeatureName, "GCNSubtarget", Implies>;
def FeatureSouthernIslands : GCNSubtargetFeatureGeneration<"SOUTHERN_ISLANDS",
"southern-islands",
[FeatureFP64, FeatureLocalMemorySize32768, FeatureMIMG_R128,
FeatureWavefrontSize64, FeatureSMemTimeInst, FeatureMadMacF32Insts,
FeatureDsSrc2Insts, FeatureLDSBankCount32, FeatureMovrel,
FeatureTrigReducedRange, FeatureExtendedImageInsts
]
>;
def FeatureSeaIslands : GCNSubtargetFeatureGeneration<"SEA_ISLANDS",
"sea-islands",
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
FeatureWavefrontSize64, FeatureFlatAddressSpace,
FeatureCIInsts, FeatureMovrel, FeatureTrigReducedRange,
FeatureGFX7GFX8GFX9Insts, FeatureSMemTimeInst, FeatureMadMacF32Insts,
FeatureDsSrc2Insts, FeatureExtendedImageInsts, FeatureUnalignedBufferAccess
]
>;
def FeatureVolcanicIslands : GCNSubtargetFeatureGeneration<"VOLCANIC_ISLANDS",
"volcanic-islands",
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
FeatureWavefrontSize64, FeatureFlatAddressSpace,
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
FeatureSMemRealTime, FeatureVGPRIndexMode, FeatureMovrel,
FeatureScalarStores, FeatureInv2PiInlineImm,
FeatureSDWA, FeatureSDWAOutModsVOPC, FeatureSDWAMac, FeatureDPP,
FeatureIntClamp, FeatureTrigReducedRange, FeatureGFX8Insts,
FeatureGFX7GFX8GFX9Insts, FeatureSMemTimeInst, FeatureMadMacF32Insts,
FeatureDsSrc2Insts, FeatureExtendedImageInsts, FeatureFastDenormalF32,
FeatureUnalignedBufferAccess
]
>;
def FeatureGFX9 : GCNSubtargetFeatureGeneration<"GFX9",
"gfx9",
[FeatureFP64, FeatureLocalMemorySize65536,
FeatureWavefrontSize64, FeatureFlatAddressSpace,
FeatureGCN3Encoding, FeatureCIInsts, Feature16BitInsts,
FeatureSMemRealTime, FeatureScalarStores, FeatureInv2PiInlineImm,
FeatureApertureRegs, FeatureGFX9Insts, FeatureVOP3P, FeatureVGPRIndexMode,
FeatureFastFMAF32, FeatureDPP, FeatureIntClamp,
FeatureSDWA, FeatureSDWAOmod, FeatureSDWAScalar, FeatureSDWASdst,
FeatureFlatInstOffsets, FeatureFlatGlobalInsts, FeatureFlatScratchInsts,
FeatureAddNoCarryInsts, FeatureGFX8Insts, FeatureGFX7GFX8GFX9Insts,
FeatureScalarFlatScratchInsts, FeatureScalarAtomics, FeatureR128A16,
FeatureSMemTimeInst, FeatureFastDenormalF32, FeatureSupportsXNACK,
FeatureUnalignedBufferAccess, FeatureUnalignedDSAccess,
FeatureNegativeScratchOffsetBug
]
>;
def FeatureGFX10 : GCNSubtargetFeatureGeneration<"GFX10",
"gfx10",
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
FeatureFlatAddressSpace,
FeatureCIInsts, Feature16BitInsts,
FeatureSMemRealTime, FeatureInv2PiInlineImm,
FeatureApertureRegs, FeatureGFX9Insts, FeatureGFX10Insts, FeatureVOP3P,
FeatureMovrel, FeatureFastFMAF32, FeatureDPP, FeatureIntClamp,
FeatureSDWA, FeatureSDWAOmod, FeatureSDWAScalar, FeatureSDWASdst,
FeatureFlatInstOffsets, FeatureFlatGlobalInsts, FeatureFlatScratchInsts,
FeatureAddNoCarryInsts, FeatureFmaMixInsts, FeatureGFX8Insts,
FeatureNoSdstCMPX, FeatureVscnt, FeatureRegisterBanking,
FeatureVOP3Literal, FeatureDPP8, FeatureExtendedImageInsts,
FeatureNoDataDepHazard, FeaturePkFmacF16Inst,
FeatureGFX10A16, FeatureSMemTimeInst, FeatureFastDenormalF32, FeatureG16,
FeatureUnalignedBufferAccess, FeatureUnalignedDSAccess
]
>;
class FeatureSet<list<SubtargetFeature> Features_> {
list<SubtargetFeature> Features = Features_;
}
def FeatureISAVersion6_0_0 : FeatureSet<[FeatureSouthernIslands,
FeatureFastFMAF32,
HalfRate64Ops,
FeatureLDSBankCount32]>;
def FeatureISAVersion6_0_1 : FeatureSet<
[FeatureSouthernIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion6_0_2 : FeatureSet<
[FeatureSouthernIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion7_0_0 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion7_0_1 : FeatureSet<
[FeatureSeaIslands,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureFastFMAF32]>;
def FeatureISAVersion7_0_2 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount16,
FeatureFastFMAF32]>;
def FeatureISAVersion7_0_3 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount16]>;
def FeatureISAVersion7_0_4 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount32]>;
def FeatureISAVersion7_0_5 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount16]>;
def FeatureISAVersion8_0_1 : FeatureSet<
[FeatureVolcanicIslands,
FeatureFastFMAF32,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureSupportsXNACK,
FeatureUnpackedD16VMem]>;
def FeatureISAVersion8_0_2 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureSGPRInitBug,
FeatureUnpackedD16VMem]>;
def FeatureISAVersion8_0_3 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureUnpackedD16VMem]>;
def FeatureISAVersion8_0_5 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureSGPRInitBug,
FeatureUnpackedD16VMem]>;
def FeatureISAVersion8_1_0 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount16,
FeatureSupportsXNACK,
FeatureImageStoreD16Bug,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_0 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_2 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_4 : FeatureSet<
[FeatureGFX9,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureFmaMixInsts,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_6 : FeatureSet<
[FeatureGFX9,
HalfRate64Ops,
FeatureFmaMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot7Insts,
FeatureSupportsSRAMECC,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_8 : FeatureSet<
[FeatureGFX9,
HalfRate64Ops,
FeatureFmaMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot3Insts,
FeatureDot4Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureDot7Insts,
FeatureMAIInsts,
FeaturePkFmacF16Inst,
FeatureAtomicFaddInsts,
FeatureSupportsSRAMECC,
FeatureMFMAInlineLiteralBug,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_9 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureImageGather4D16Bug]>;
def FeatureISAVersion9_0_A : FeatureSet<
[FeatureGFX9,
FeatureGFX90AInsts,
FeatureFmaMixInsts,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot3Insts,
FeatureDot4Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureDot7Insts,
Feature64BitDPP,
FeaturePackedFP32Ops,
FeatureMAIInsts,
FeaturePkFmacF16Inst,
FeatureAtomicFaddInsts,
FeatureMadMacF32Insts,
FeatureSupportsSRAMECC,
FeaturePackedTID,
FullRate64Ops]>;
def FeatureISAVersion9_0_C : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureDsSrc2Insts,
FeatureExtendedImageInsts,
FeatureMadMacF32Insts,
FeatureImageGather4D16Bug]>;
// TODO: Organize more features into groups.
def FeatureGroup {
// Bugs present on gfx10.1.
list<SubtargetFeature> GFX10_1_Bugs = [
FeatureVcmpxPermlaneHazard,
FeatureVMEMtoScalarWriteHazard,
FeatureSMEMtoVectorWriteHazard,
FeatureInstFwdPrefetchBug,
FeatureVcmpxExecWARHazard,
FeatureLdsBranchVmemWARHazard,
FeatureNSAtoVMEMBug,
FeatureNSAClauseBug,
FeatureOffset3fBug,
FeatureFlatSegmentOffsetBug,
FeatureNegativeUnalignedScratchOffsetBug
];
}
def FeatureISAVersion10_1_0 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureGetWaveIdInst,
FeatureMadMacF32Insts,
FeatureDsSrc2Insts,
FeatureLdsMisalignedBug,
FeatureSupportsXNACK])>;
def FeatureISAVersion10_1_1 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureDot7Insts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureGetWaveIdInst,
FeatureMadMacF32Insts,
FeatureDsSrc2Insts,
FeatureLdsMisalignedBug,
FeatureSupportsXNACK])>;
def FeatureISAVersion10_1_2 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureDot7Insts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureGetWaveIdInst,
FeatureMadMacF32Insts,
FeatureDsSrc2Insts,
FeatureLdsMisalignedBug,
FeatureSupportsXNACK])>;
def FeatureISAVersion10_1_3 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureGFX10_AEncoding,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureGetWaveIdInst,
FeatureMadMacF32Insts,
FeatureDsSrc2Insts,
FeatureLdsMisalignedBug,
FeatureSupportsXNACK])>;
def FeatureISAVersion10_3_0 : FeatureSet<
[FeatureGFX10,
FeatureGFX10_AEncoding,
FeatureGFX10_BEncoding,
FeatureGFX10_3Insts,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureDot7Insts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureShaderCyclesRegister]>;
//===----------------------------------------------------------------------===//
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 isGFX6 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS">,
AssemblerPredicate<(all_of FeatureSouthernIslands)>;
def isGFX6GFX7 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), (not FeatureGFX10Insts))>;
def isGFX6GFX7GFX10 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX10">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding))>;
def isGFX7Only :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), FeatureCIInsts, (not FeatureGFX10Insts))>;
def isGFX7GFX10 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX10">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), FeatureCIInsts)>;
def isGFX7GFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of FeatureGFX7GFX8GFX9Insts)>;
def isGFX6GFX7GFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of (not FeatureGFX10Insts))>;
def isGFX6GFX7GFX8GFX9NotGFX90A :
Predicate<"!Subtarget->hasGFX90AInsts() &&"
"(Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
" Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
" Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
" Subtarget->getGeneration() == AMDGPUSubtarget::GFX9)">,
AssemblerPredicate<(all_of (not FeatureGFX10Insts), (not FeatureGFX90AInsts))>;
def isGFX7Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<(all_of FeatureCIInsts)>;
def isGFX8Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS">,
AssemblerPredicate<(all_of FeatureGFX8Insts)>;
def isGFX8Only : Predicate<"Subtarget->getGeneration() =="
"AMDGPUSubtarget::VOLCANIC_ISLANDS">,
AssemblerPredicate <(all_of FeatureVolcanicIslands)>;
def isGFX9Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of FeatureGFX9Insts)>;
def isGFX9Only : Predicate <
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of FeatureGCN3Encoding, FeatureGFX9Insts)>;
def isGCN3ExcludingGFX90A :
Predicate<"Subtarget->isGCN3Encoding() && !Subtarget->hasGFX90AInsts()">,
AssemblerPredicate<(all_of FeatureGCN3Encoding, (not FeatureGFX90AInsts))>;
def isGFX90APlus :
Predicate<"Subtarget->hasGFX90AInsts()">,
AssemblerPredicate<(all_of FeatureGFX90AInsts)>;
def isNotGFX90APlus :
Predicate<"!Subtarget->hasGFX90AInsts()">,
AssemblerPredicate<(all_of (not FeatureGFX90AInsts))>;
def isGFX8GFX9NotGFX90A :
Predicate<"!Subtarget->hasGFX90AInsts() &&"
"(Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
" Subtarget->getGeneration() == AMDGPUSubtarget::GFX9)">,
AssemblerPredicate<(all_of FeatureGFX8Insts, FeatureGCN3Encoding, (not FeatureGFX90AInsts))>;
def isGFX90AOnly :
Predicate<"Subtarget->hasGFX90AInsts()">,
AssemblerPredicate<(all_of FeatureGFX90AInsts)>;
def isGFX908orGFX90A :
Predicate<"Subtarget->hasMAIInsts()">,
AssemblerPredicate<(all_of FeatureMAIInsts)>;
def isGFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of FeatureGFX8Insts, FeatureGCN3Encoding)>;
def isGFX10Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX10">,
AssemblerPredicate<(all_of FeatureGFX10Insts)>;
def isGFX10Before1030 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::GFX10 &&"
"!Subtarget->hasGFX10_3Insts()">,
AssemblerPredicate<(all_of FeatureGFX10Insts,(not FeatureGFX10_3Insts))>;
def HasFlatAddressSpace : Predicate<"Subtarget->hasFlatAddressSpace()">,
AssemblerPredicate<(all_of FeatureFlatAddressSpace)>;
def HasFlatGlobalInsts : Predicate<"Subtarget->hasFlatGlobalInsts()">,
AssemblerPredicate<(all_of FeatureFlatGlobalInsts)>;
def HasFlatScratchInsts : Predicate<"Subtarget->hasFlatScratchInsts()">,
AssemblerPredicate<(all_of FeatureFlatScratchInsts)>;
def HasScalarFlatScratchInsts : Predicate<"Subtarget->hasScalarFlatScratchInsts()">,
AssemblerPredicate<(all_of FeatureScalarFlatScratchInsts)>;
def HasD16LoadStore : Predicate<"Subtarget->hasD16LoadStore()">,
AssemblerPredicate<(all_of FeatureGFX9Insts)>;
def HasFlatScratchSTMode : Predicate<"Subtarget->hasFlatScratchSTMode()">,
AssemblerPredicate<(any_of FeatureGFX10_3Insts)>;
def HasGFX10_AEncoding : Predicate<"Subtarget->hasGFX10_AEncoding()">,
AssemblerPredicate<(all_of FeatureGFX10_AEncoding)>;
def HasGFX10_BEncoding : Predicate<"Subtarget->hasGFX10_BEncoding()">,
AssemblerPredicate<(all_of FeatureGFX10_BEncoding)>;
def HasUnpackedD16VMem : Predicate<"Subtarget->hasUnpackedD16VMem()">,
AssemblerPredicate<(all_of FeatureUnpackedD16VMem)>;
def HasPackedD16VMem : Predicate<"!Subtarget->hasUnpackedD16VMem()">,
AssemblerPredicate<(all_of (not FeatureUnpackedD16VMem))>;
def D16PreservesUnusedBits :
Predicate<"Subtarget->d16PreservesUnusedBits()">,
AssemblerPredicate<(all_of FeatureGFX9Insts, (not FeatureSRAMECC))>;
def LDSRequiresM0Init : Predicate<"Subtarget->ldsRequiresM0Init()">;
def NotLDSRequiresM0Init : Predicate<"!Subtarget->ldsRequiresM0Init()">;
def HasDSAddTid : Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
AssemblerPredicate<(all_of FeatureGFX9Insts)>;
def HasLDSFPAtomics : Predicate<"Subtarget->hasLDSFPAtomics()">,
AssemblerPredicate<(all_of FeatureGFX8Insts)>;
def HasAddNoCarryInsts : Predicate<"Subtarget->hasAddNoCarry()">,
AssemblerPredicate<(all_of FeatureAddNoCarryInsts)>;
def NotHasAddNoCarryInsts : Predicate<"!Subtarget->hasAddNoCarry()">;
def Has16BitInsts : Predicate<"Subtarget->has16BitInsts()">,
AssemblerPredicate<(all_of Feature16BitInsts)>;
def HasVOP3PInsts : Predicate<"Subtarget->hasVOP3PInsts()">,
AssemblerPredicate<(all_of FeatureVOP3P)>;
def HasMinMaxDenormModes : Predicate<"Subtarget->supportsMinMaxDenormModes()">;
def NotHasMinMaxDenormModes : Predicate<"!Subtarget->supportsMinMaxDenormModes()">;
def HasSDWA : Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<(all_of FeatureSDWA, FeatureVolcanicIslands)>;
def HasSDWA9 :
Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<(all_of FeatureGCN3Encoding, FeatureGFX9Insts,FeatureSDWA)>;
def HasSDWA10 :
Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), FeatureGFX10Insts, FeatureSDWA)>;
def HasDPP : Predicate<"Subtarget->hasDPP()">,
AssemblerPredicate<(all_of FeatureGCN3Encoding, FeatureDPP)>;
def HasDPP8 : Predicate<"Subtarget->hasDPP8()">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), FeatureGFX10Insts, FeatureDPP8)>;
def Has64BitDPP : Predicate<"Subtarget->has64BitDPP()">,
AssemblerPredicate<(all_of Feature64BitDPP)>;
def HasPackedFP32Ops : Predicate<"Subtarget->hasPackedFP32Ops()">,
AssemblerPredicate<(all_of FeaturePackedFP32Ops)>;
def HasFmaakFmamkF32Insts :
Predicate<"Subtarget->hasFmaakFmamkF32Insts()">,
AssemblerPredicate<(any_of FeatureGFX10Insts)>;
def HasExtendedImageInsts : Predicate<"Subtarget->hasExtendedImageInsts()">,
AssemblerPredicate<(all_of FeatureExtendedImageInsts)>;
def HasR128A16 : Predicate<"Subtarget->hasR128A16()">,
AssemblerPredicate<(all_of FeatureR128A16)>;
def HasGFX10A16 : Predicate<"Subtarget->hasGFX10A16()">,
AssemblerPredicate<(all_of FeatureGFX10A16)>;
def HasG16 : Predicate<"Subtarget->hasG16()">,
AssemblerPredicate<(all_of FeatureG16)>;
def HasDPP16 : Predicate<"Subtarget->hasDPP()">,
AssemblerPredicate<(all_of (not FeatureGCN3Encoding), FeatureGFX10Insts, FeatureDPP)>;
def HasIntClamp : Predicate<"Subtarget->hasIntClamp()">,
AssemblerPredicate<(all_of FeatureIntClamp)>;
def HasMadMixInsts : Predicate<"Subtarget->hasMadMixInsts()">,
AssemblerPredicate<(all_of FeatureMadMixInsts)>;
def HasScalarStores : Predicate<"Subtarget->hasScalarStores()">,
AssemblerPredicate<(all_of FeatureScalarStores)>;
def HasScalarAtomics : Predicate<"Subtarget->hasScalarAtomics()">,
AssemblerPredicate<(all_of FeatureScalarAtomics)>;
def HasNoSdstCMPX : Predicate<"Subtarget->hasNoSdstCMPX()">,
AssemblerPredicate<(all_of FeatureNoSdstCMPX)>;
def HasSdstCMPX : Predicate<"!Subtarget->hasNoSdstCMPX()">,
AssemblerPredicate<(all_of (not FeatureNoSdstCMPX))>;
def has16BankLDS : Predicate<"Subtarget->getLDSBankCount() == 16">;
def has32BankLDS : Predicate<"Subtarget->getLDSBankCount() == 32">;
def HasVGPRIndexMode : Predicate<"Subtarget->hasVGPRIndexMode()">,
AssemblerPredicate<(all_of FeatureVGPRIndexMode)>;
def HasMovrel : Predicate<"Subtarget->hasMovrel()">,
AssemblerPredicate<(all_of FeatureMovrel)>;
def HasFmaMixInsts : Predicate<"Subtarget->hasFmaMixInsts()">,
AssemblerPredicate<(all_of FeatureFmaMixInsts)>;
def HasDLInsts : Predicate<"Subtarget->hasDLInsts()">,
AssemblerPredicate<(all_of FeatureDLInsts)>;
def HasDot1Insts : Predicate<"Subtarget->hasDot1Insts()">,
AssemblerPredicate<(all_of FeatureDot1Insts)>;
def HasDot2Insts : Predicate<"Subtarget->hasDot2Insts()">,
AssemblerPredicate<(all_of FeatureDot2Insts)>;
def HasDot3Insts : Predicate<"Subtarget->hasDot3Insts()">,
AssemblerPredicate<(all_of FeatureDot3Insts)>;
def HasDot4Insts : Predicate<"Subtarget->hasDot4Insts()">,
AssemblerPredicate<(all_of FeatureDot4Insts)>;
def HasDot5Insts : Predicate<"Subtarget->hasDot5Insts()">,
AssemblerPredicate<(all_of FeatureDot5Insts)>;
def HasDot6Insts : Predicate<"Subtarget->hasDot6Insts()">,
AssemblerPredicate<(all_of FeatureDot6Insts)>;
def HasDot7Insts : Predicate<"Subtarget->hasDot7Insts()">,
AssemblerPredicate<(all_of FeatureDot7Insts)>;
def HasGetWaveIdInst : Predicate<"Subtarget->hasGetWaveIdInst()">,
AssemblerPredicate<(all_of FeatureGetWaveIdInst)>;
def HasMAIInsts : Predicate<"Subtarget->hasMAIInsts()">,
AssemblerPredicate<(all_of FeatureMAIInsts)>;
def HasSMemRealTime : Predicate<"Subtarget->hasSMemRealTime()">,
AssemblerPredicate<(all_of FeatureSMemRealTime)>;
def HasSMemTimeInst : Predicate<"Subtarget->hasSMemTimeInst()">,
AssemblerPredicate<(all_of FeatureSMemTimeInst)>;
def HasShaderCyclesRegister : Predicate<"Subtarget->hasShaderCyclesRegister()">,
AssemblerPredicate<(all_of FeatureShaderCyclesRegister)>;
def HasPkFmacF16Inst : Predicate<"Subtarget->hasPkFmacF16Inst()">,
AssemblerPredicate<(all_of FeaturePkFmacF16Inst)>;
def HasMadMacF32Insts : Predicate<"Subtarget->hasMadMacF32Insts()">,
AssemblerPredicate<(all_of FeatureMadMacF32Insts)>;
def HasFmaLegacy32 : Predicate<"Subtarget->hasGFX10_3Insts()">,
AssemblerPredicate<(any_of FeatureGFX10_3Insts)>;
def HasAtomicFaddInsts : Predicate<"Subtarget->hasAtomicFaddInsts()">,
AssemblerPredicate<(all_of FeatureAtomicFaddInsts)>;
def HasDsSrc2Insts : Predicate<"!Subtarget->hasDsSrc2Insts()">,
AssemblerPredicate<(all_of FeatureDsSrc2Insts)>;
def EnableLateCFGStructurize : Predicate<
"EnableLateStructurizeCFG">;
def EnableFlatScratch : Predicate<"Subtarget->enableFlatScratch()">;
def DisableFlatScratch : Predicate<"!Subtarget->enableFlatScratch()">;
def HasUnalignedAccessMode : Predicate<"Subtarget->hasUnalignedAccessMode()">,
AssemblerPredicate<(all_of FeatureUnalignedAccessMode)>;
// Include AMDGPU TD files
include "SISchedule.td"
include "GCNProcessors.td"
include "AMDGPUInstrInfo.td"
include "SIRegisterInfo.td"
include "AMDGPURegisterBanks.td"
include "AMDGPUInstructions.td"
include "SIInstrInfo.td"
include "AMDGPUCallingConv.td"
include "AMDGPUSearchableTables.td"
Reference in New Issue View Git Blame Copy Permalink