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

1174 lines
34 KiB
TableGen

//===-- 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 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 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",
"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"
>;
def FeatureDoesNotSupportXNACK : SubtargetFeature<"no-xnack-support",
"DoesNotSupportXNACK",
"true",
"Hardware does not support 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 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 misaligned multi-dword LDS access 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 FeatureFlatSegmentOffsetBug : SubtargetFeature<"flat-segment-offset-bug",
"HasFlatSegmentOffsetBug",
"true",
"GFX10 bug, inst_offset ignored in flat segment"
>;
def FeatureOffset3fBug : SubtargetFeature<"offset-3f-bug",
"HasOffset3fBug",
"true",
"Branch offset of 3f 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 FeatureGFX10Insts : SubtargetFeature<"gfx10-insts",
"GFX10Insts",
"true",
"Additional instructions for GFX10+"
>;
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 FeatureR128A16 : SubtargetFeature<"r128-a16",
"HasR128A16",
"true",
"Support 16 bit coordindates/gradients/lod/clamp/mip types on gfx9"
>;
def FeatureNSAEncoding : SubtargetFeature<"nsa-encoding",
"HasNSAEncoding",
"true",
"Support NSA encoding for image instructions"
>;
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_f32_f16, v_dot2_i32_i16, v_dot2_u32_u16, v_dot4_u32_u8, v_dot8_u32_u4 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 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"
>;
def FeatureDoesNotSupportSRAMECC : SubtargetFeature<"no-sram-ecc-support",
"DoesNotSupportSRAMECC",
"true",
"Hardware does not support SRAM ECC"
>;
def FeatureSRAMECC : SubtargetFeature<"sram-ecc",
"EnableSRAMECC",
"true",
"Enable SRAM ECC"
>;
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 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)
//===------------------------------------------------------------===//
// 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 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 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 FeatureCodeObjectV3 : SubtargetFeature <
"code-object-v3",
"CodeObjectV3",
"true",
"Generate code object version 3"
>;
def FeatureTrigReducedRange : SubtargetFeature<"trig-reduced-range",
"HasTrigReducedRange",
"true",
"Requires use of fract on arguments to trig instructions"
>;
// 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,
FeatureLDSBankCount32, FeatureMovrel, FeatureTrigReducedRange,
FeatureDoesNotSupportSRAMECC, FeatureDoesNotSupportXNACK]
>;
def FeatureSeaIslands : GCNSubtargetFeatureGeneration<"SEA_ISLANDS",
"sea-islands",
[FeatureFP64, FeatureLocalMemorySize65536, FeatureMIMG_R128,
FeatureWavefrontSize64, FeatureFlatAddressSpace,
FeatureCIInsts, FeatureMovrel, FeatureTrigReducedRange,
FeatureGFX7GFX8GFX9Insts, FeatureDoesNotSupportSRAMECC]
>;
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, FeatureDoesNotSupportSRAMECC,
FeatureGFX8Insts, FeatureGFX7GFX8GFX9Insts
]
>;
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
]
>;
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,
FeatureNoDataDepHazard, FeaturePkFmacF16Inst, FeatureDoesNotSupportSRAMECC
]
>;
class FeatureSet<list<SubtargetFeature> Features_> {
list<SubtargetFeature> Features = Features_;
}
def FeatureISAVersion6_0_0 : FeatureSet<[FeatureSouthernIslands,
FeatureFastFMAF32,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion6_0_1 : FeatureSet<
[FeatureSouthernIslands,
FeatureLDSBankCount32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion7_0_0 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion7_0_1 : FeatureSet<
[FeatureSeaIslands,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureFastFMAF32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion7_0_2 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount16,
FeatureFastFMAF32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion7_0_3 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount16,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion7_0_4 : FeatureSet<
[FeatureSeaIslands,
FeatureLDSBankCount32,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion8_0_1 : FeatureSet<
[FeatureVolcanicIslands,
FeatureFastFMAF32,
HalfRate64Ops,
FeatureLDSBankCount32,
FeatureXNACK,
FeatureUnpackedD16VMem,
FeatureCodeObjectV3]>;
def FeatureISAVersion8_0_2 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureSGPRInitBug,
FeatureUnpackedD16VMem,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion8_0_3 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount32,
FeatureUnpackedD16VMem,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion8_1_0 : FeatureSet<
[FeatureVolcanicIslands,
FeatureLDSBankCount16,
FeatureXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion9_0_0 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureCodeObjectV3,
FeatureDoesNotSupportXNACK,
FeatureDoesNotSupportSRAMECC]>;
def FeatureISAVersion9_0_2 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureXNACK,
FeatureDoesNotSupportSRAMECC,
FeatureCodeObjectV3]>;
def FeatureISAVersion9_0_4 : FeatureSet<
[FeatureGFX9,
FeatureLDSBankCount32,
FeatureFmaMixInsts,
FeatureDoesNotSupportXNACK,
FeatureDoesNotSupportSRAMECC,
FeatureCodeObjectV3]>;
def FeatureISAVersion9_0_6 : FeatureSet<
[FeatureGFX9,
HalfRate64Ops,
FeatureFmaMixInsts,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3]>;
def FeatureISAVersion9_0_8 : FeatureSet<
[FeatureGFX9,
HalfRate64Ops,
FeatureFmaMixInsts,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot3Insts,
FeatureDot4Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureMAIInsts,
FeaturePkFmacF16Inst,
FeatureAtomicFaddInsts,
FeatureSRAMECC,
FeatureMFMAInlineLiteralBug,
FeatureCodeObjectV3]>;
def FeatureISAVersion9_0_9 : FeatureSet<
[FeatureGFX9,
FeatureMadMixInsts,
FeatureLDSBankCount32,
FeatureXNACK,
FeatureCodeObjectV3]>;
// 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,
FeatureOffset3fBug,
FeatureFlatSegmentOffsetBug
];
}
def FeatureISAVersion10_1_0 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureLdsMisalignedBug,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3])>;
def FeatureISAVersion10_1_1 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3])>;
def FeatureISAVersion10_1_2 : FeatureSet<
!listconcat(FeatureGroup.GFX10_1_Bugs,
[FeatureGFX10,
FeatureLDSBankCount32,
FeatureDLInsts,
FeatureDot1Insts,
FeatureDot2Insts,
FeatureDot5Insts,
FeatureDot6Insts,
FeatureNSAEncoding,
FeatureWavefrontSize32,
FeatureScalarStores,
FeatureScalarAtomics,
FeatureScalarFlatScratchInsts,
FeatureLdsMisalignedBug,
FeatureDoesNotSupportXNACK,
FeatureCodeObjectV3])>;
//===----------------------------------------------------------------------===//
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<"FeatureSouthernIslands">;
def isGFX6GFX7 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<"!FeatureGCN3Encoding,!FeatureGFX10Insts">;
def isGFX6GFX7GFX10 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX10">,
AssemblerPredicate<"!FeatureGCN3Encoding">;
def isGFX7Only :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<"!FeatureGCN3Encoding,FeatureCIInsts,!FeatureGFX10Insts">;
def isGFX7GFX10 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX10">,
AssemblerPredicate<"!FeatureGCN3Encoding,FeatureCIInsts">;
def isGFX7GFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGFX7GFX8GFX9Insts">;
def isGFX6GFX7GFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::SEA_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"!FeatureGFX10Insts">;
def isGFX7Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::SEA_ISLANDS">,
AssemblerPredicate<"FeatureCIInsts">;
def isGFX8Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS">,
AssemblerPredicate<"FeatureGFX8Insts">;
def isGFX8Only : Predicate<"Subtarget->getGeneration() =="
"AMDGPUSubtarget::VOLCANIC_ISLANDS">,
AssemblerPredicate <"FeatureVolcanicIslands">;
def isGFX9Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGFX9Insts">;
def isGFX9Only : Predicate <
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGCN3Encoding,FeatureGFX9Insts">;
def isGFX8GFX9 :
Predicate<"Subtarget->getGeneration() == AMDGPUSubtarget::VOLCANIC_ISLANDS ||"
"Subtarget->getGeneration() == AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGFX8Insts,FeatureGCN3Encoding">;
def isGFX10Plus :
Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX10">,
AssemblerPredicate<"FeatureGFX10Insts">;
def HasFlatAddressSpace : Predicate<"Subtarget->hasFlatAddressSpace()">,
AssemblerPredicate<"FeatureFlatAddressSpace">;
def HasFlatGlobalInsts : Predicate<"Subtarget->hasFlatGlobalInsts()">,
AssemblerPredicate<"FeatureFlatGlobalInsts">;
def HasFlatScratchInsts : Predicate<"Subtarget->hasFlatScratchInsts()">,
AssemblerPredicate<"FeatureFlatScratchInsts">;
def HasScalarFlatScratchInsts : Predicate<"Subtarget->hasScalarFlatScratchInsts()">,
AssemblerPredicate<"FeatureScalarFlatScratchInsts">;
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<"FeatureGFX9Insts,!FeatureSRAMECC">;
def LDSRequiresM0Init : Predicate<"Subtarget->ldsRequiresM0Init()">;
def NotLDSRequiresM0Init : Predicate<"!Subtarget->ldsRequiresM0Init()">;
def HasDSAddTid : Predicate<"Subtarget->getGeneration() >= AMDGPUSubtarget::GFX9">,
AssemblerPredicate<"FeatureGFX9Insts">;
def HasAddNoCarryInsts : Predicate<"Subtarget->hasAddNoCarry()">,
AssemblerPredicate<"FeatureAddNoCarryInsts">;
def NotHasAddNoCarryInsts : Predicate<"!Subtarget->hasAddNoCarry()">;
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<"FeatureGCN3Encoding,FeatureGFX9Insts,FeatureSDWA">;
def HasSDWA10 :
Predicate<"Subtarget->hasSDWA()">,
AssemblerPredicate<"!FeatureGCN3Encoding,FeatureGFX10Insts,FeatureSDWA">;
def HasDPP : Predicate<"Subtarget->hasDPP()">,
AssemblerPredicate<"FeatureGCN3Encoding,FeatureDPP">;
def HasDPP8 : Predicate<"Subtarget->hasDPP8()">,
AssemblerPredicate<"!FeatureGCN3Encoding,FeatureGFX10Insts,FeatureDPP8">;
def HasR128A16 : Predicate<"Subtarget->hasR128A16()">,
AssemblerPredicate<"FeatureR128A16">;
def HasDPP16 : Predicate<"Subtarget->hasDPP()">,
AssemblerPredicate<"!FeatureGCN3Encoding,FeatureGFX10Insts,FeatureDPP">;
def HasIntClamp : Predicate<"Subtarget->hasIntClamp()">,
AssemblerPredicate<"FeatureIntClamp">;
def HasMadMixInsts : Predicate<"Subtarget->hasMadMixInsts()">,
AssemblerPredicate<"FeatureMadMixInsts">;
def HasScalarStores : Predicate<"Subtarget->hasScalarStores()">,
AssemblerPredicate<"FeatureScalarStores">;
def HasScalarAtomics : Predicate<"Subtarget->hasScalarAtomics()">,
AssemblerPredicate<"FeatureScalarAtomics">;
def HasNoSdstCMPX : Predicate<"Subtarget->hasNoSdstCMPX()">,
AssemblerPredicate<"FeatureNoSdstCMPX">;
def HasSdstCMPX : Predicate<"!Subtarget->hasNoSdstCMPX()">,
AssemblerPredicate<"!FeatureNoSdstCMPX">;
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 HasDot1Insts : Predicate<"Subtarget->hasDot1Insts()">,
AssemblerPredicate<"FeatureDot1Insts">;
def HasDot2Insts : Predicate<"Subtarget->hasDot2Insts()">,
AssemblerPredicate<"FeatureDot2Insts">;
def HasDot3Insts : Predicate<"Subtarget->hasDot3Insts()">,
AssemblerPredicate<"FeatureDot3Insts">;
def HasDot4Insts : Predicate<"Subtarget->hasDot4Insts()">,
AssemblerPredicate<"FeatureDot4Insts">;
def HasDot5Insts : Predicate<"Subtarget->hasDot5Insts()">,
AssemblerPredicate<"FeatureDot5Insts">;
def HasDot6Insts : Predicate<"Subtarget->hasDot6Insts()">,
AssemblerPredicate<"FeatureDot6Insts">;
def HasMAIInsts : Predicate<"Subtarget->hasMAIInsts()">,
AssemblerPredicate<"FeatureMAIInsts">;
def HasPkFmacF16Inst : Predicate<"Subtarget->hasPkFmacF16Inst()">,
AssemblerPredicate<"FeaturePkFmacF16Inst">;
def HasAtomicFaddInsts : Predicate<"Subtarget->hasAtomicFaddInsts()">,
AssemblerPredicate<"FeatureAtomicFaddInsts">;
def HasOffset3fBug : Predicate<"!Subtarget->hasOffset3fBug()">,
AssemblerPredicate<"FeatureOffset3fBug">;
def EnableLateCFGStructurize : Predicate<
"EnableLateStructurizeCFG">;
// Include AMDGPU TD files
include "SISchedule.td"
include "GCNProcessors.td"
include "AMDGPUInstrInfo.td"
include "AMDGPURegisterInfo.td"
include "AMDGPURegisterBanks.td"
include "AMDGPUInstructions.td"
include "SIInstrInfo.td"
include "AMDGPUCallingConv.td"
include "AMDGPUSearchableTables.td"