llvm-project/llvm/lib/Target/AArch64/AArch64.td

583 lines
26 KiB
TableGen

//=- AArch64.td - Describe the AArch64 Target Machine --------*- tablegen -*-=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Target-independent interfaces which we are implementing.
//===----------------------------------------------------------------------===//
include "llvm/Target/Target.td"
//===----------------------------------------------------------------------===//
// AArch64 Subtarget features.
//
def FeatureFPARMv8 : SubtargetFeature<"fp-armv8", "HasFPARMv8", "true",
"Enable ARMv8 FP">;
def FeatureNEON : SubtargetFeature<"neon", "HasNEON", "true",
"Enable Advanced SIMD instructions", [FeatureFPARMv8]>;
def FeatureSM4 : SubtargetFeature<
"sm4", "HasSM4", "true",
"Enable SM3 and SM4 support", [FeatureNEON]>;
def FeatureSHA2 : SubtargetFeature<
"sha2", "HasSHA2", "true",
"Enable SHA1 and SHA256 support", [FeatureNEON]>;
def FeatureSHA3 : SubtargetFeature<
"sha3", "HasSHA3", "true",
"Enable SHA512 and SHA3 support", [FeatureNEON, FeatureSHA2]>;
def FeatureAES : SubtargetFeature<
"aes", "HasAES", "true",
"Enable AES support", [FeatureNEON]>;
// Crypto has been split up and any combination is now valid (see the
// crypto defintions above). Also, crypto is now context sensitive:
// it has a different meaning for e.g. Armv8.4 than it has for Armv8.2.
// Therefore, we rely on Clang, the user interacing tool, to pass on the
// appropriate crypto options. But here in the backend, crypto has very little
// meaning anymore. We kept the Crypto defintion here for backward
// compatibility, and now imply features SHA2 and AES, which was the
// "traditional" meaning of Crypto.
def FeatureCrypto : SubtargetFeature<"crypto", "HasCrypto", "true",
"Enable cryptographic instructions", [FeatureNEON, FeatureSHA2, FeatureAES]>;
def FeatureCRC : SubtargetFeature<"crc", "HasCRC", "true",
"Enable ARMv8 CRC-32 checksum instructions">;
def FeatureRAS : SubtargetFeature<"ras", "HasRAS", "true",
"Enable ARMv8 Reliability, Availability and Serviceability Extensions">;
def FeatureLSE : SubtargetFeature<"lse", "HasLSE", "true",
"Enable ARMv8.1 Large System Extension (LSE) atomic instructions">;
def FeatureRDM : SubtargetFeature<"rdm", "HasRDM", "true",
"Enable ARMv8.1 Rounding Double Multiply Add/Subtract instructions">;
def FeaturePerfMon : SubtargetFeature<"perfmon", "HasPerfMon", "true",
"Enable ARMv8 PMUv3 Performance Monitors extension">;
def FeatureFullFP16 : SubtargetFeature<"fullfp16", "HasFullFP16", "true",
"Full FP16", [FeatureFPARMv8]>;
def FeatureFP16FML : SubtargetFeature<"fp16fml", "HasFP16FML", "true",
"Enable FP16 FML instructions", [FeatureFullFP16]>;
def FeatureSPE : SubtargetFeature<"spe", "HasSPE", "true",
"Enable Statistical Profiling extension">;
def FeatureSVE : SubtargetFeature<"sve", "HasSVE", "true",
"Enable Scalable Vector Extension (SVE) instructions">;
/// Cyclone has register move instructions which are "free".
def FeatureZCRegMove : SubtargetFeature<"zcm", "HasZeroCycleRegMove", "true",
"Has zero-cycle register moves">;
/// Cyclone has instructions which zero registers for "free".
def FeatureZCZeroing : SubtargetFeature<"zcz", "HasZeroCycleZeroing", "true",
"Has zero-cycle zeroing instructions">;
/// ... but the floating-point version doesn't quite work in rare cases on older
/// CPUs.
def FeatureZCZeroingFPWorkaround : SubtargetFeature<"zcz-fp-workaround",
"HasZeroCycleZeroingFPWorkaround", "true",
"The zero-cycle floating-point zeroing instruction has a bug">;
def FeatureStrictAlign : SubtargetFeature<"strict-align",
"StrictAlign", "true",
"Disallow all unaligned memory "
"access">;
def FeatureReserveX18 : SubtargetFeature<"reserve-x18", "ReserveX18", "true",
"Reserve X18, making it unavailable "
"as a GPR">;
def FeatureReserveX20 : SubtargetFeature<"reserve-x20", "ReserveX20", "true",
"Reserve X20, making it unavailable "
"as a GPR">;
def FeatureUseAA : SubtargetFeature<"use-aa", "UseAA", "true",
"Use alias analysis during codegen">;
def FeatureBalanceFPOps : SubtargetFeature<"balance-fp-ops", "BalanceFPOps",
"true",
"balance mix of odd and even D-registers for fp multiply(-accumulate) ops">;
def FeaturePredictableSelectIsExpensive : SubtargetFeature<
"predictable-select-expensive", "PredictableSelectIsExpensive", "true",
"Prefer likely predicted branches over selects">;
def FeatureCustomCheapAsMoveHandling : SubtargetFeature<"custom-cheap-as-move",
"CustomAsCheapAsMove", "true",
"Use custom code for TargetInstrInfo::isAsCheapAsAMove()">;
def FeatureExynosCheapAsMoveHandling : SubtargetFeature<"exynos-cheap-as-move",
"ExynosAsCheapAsMove", "true",
"Use Exynos specific code in TargetInstrInfo::isAsCheapAsAMove()",
[FeatureCustomCheapAsMoveHandling]>;
def FeaturePostRAScheduler : SubtargetFeature<"use-postra-scheduler",
"UsePostRAScheduler", "true", "Schedule again after register allocation">;
def FeatureSlowMisaligned128Store : SubtargetFeature<"slow-misaligned-128store",
"Misaligned128StoreIsSlow", "true", "Misaligned 128 bit stores are slow">;
def FeatureSlowPaired128 : SubtargetFeature<"slow-paired-128",
"Paired128IsSlow", "true", "Paired 128 bit loads and stores are slow">;
def FeatureSlowSTRQro : SubtargetFeature<"slow-strqro-store", "STRQroIsSlow",
"true", "STR of Q register with register offset is slow">;
def FeatureAlternateSExtLoadCVTF32Pattern : SubtargetFeature<
"alternate-sextload-cvt-f32-pattern", "UseAlternateSExtLoadCVTF32Pattern",
"true", "Use alternative pattern for sextload convert to f32">;
def FeatureArithmeticBccFusion : SubtargetFeature<
"arith-bcc-fusion", "HasArithmeticBccFusion", "true",
"CPU fuses arithmetic+bcc operations">;
def FeatureArithmeticCbzFusion : SubtargetFeature<
"arith-cbz-fusion", "HasArithmeticCbzFusion", "true",
"CPU fuses arithmetic + cbz/cbnz operations">;
def FeatureFuseAddress : SubtargetFeature<
"fuse-address", "HasFuseAddress", "true",
"CPU fuses address generation and memory operations">;
def FeatureFuseAES : SubtargetFeature<
"fuse-aes", "HasFuseAES", "true",
"CPU fuses AES crypto operations">;
def FeatureFuseCCSelect : SubtargetFeature<
"fuse-csel", "HasFuseCCSelect", "true",
"CPU fuses conditional select operations">;
def FeatureFuseLiterals : SubtargetFeature<
"fuse-literals", "HasFuseLiterals", "true",
"CPU fuses literal generation operations">;
def FeatureDisableLatencySchedHeuristic : SubtargetFeature<
"disable-latency-sched-heuristic", "DisableLatencySchedHeuristic", "true",
"Disable latency scheduling heuristic">;
def FeatureRCPC : SubtargetFeature<"rcpc", "HasRCPC", "true",
"Enable support for RCPC extension">;
def FeatureUseRSqrt : SubtargetFeature<
"use-reciprocal-square-root", "UseRSqrt", "true",
"Use the reciprocal square root approximation">;
def FeatureDotProd : SubtargetFeature<
"dotprod", "HasDotProd", "true",
"Enable dot product support">;
def FeatureNoNegativeImmediates : SubtargetFeature<"no-neg-immediates",
"NegativeImmediates", "false",
"Convert immediates and instructions "
"to their negated or complemented "
"equivalent when the immediate does "
"not fit in the encoding.">;
def FeatureLSLFast : SubtargetFeature<
"lsl-fast", "HasLSLFast", "true",
"CPU has a fastpath logical shift of up to 3 places">;
def FeatureAggressiveFMA :
SubtargetFeature<"aggressive-fma",
"HasAggressiveFMA",
"true",
"Enable Aggressive FMA for floating-point.">;
//===----------------------------------------------------------------------===//
// Architectures.
//
def HasV8_1aOps : SubtargetFeature<"v8.1a", "HasV8_1aOps", "true",
"Support ARM v8.1a instructions", [FeatureCRC, FeatureLSE, FeatureRDM]>;
def HasV8_2aOps : SubtargetFeature<"v8.2a", "HasV8_2aOps", "true",
"Support ARM v8.2a instructions", [HasV8_1aOps, FeatureRAS]>;
def HasV8_3aOps : SubtargetFeature<"v8.3a", "HasV8_3aOps", "true",
"Support ARM v8.3a instructions", [HasV8_2aOps, FeatureRCPC]>;
def HasV8_4aOps : SubtargetFeature<"v8.4a", "HasV8_4aOps", "true",
"Support ARM v8.4a instructions", [HasV8_3aOps, FeatureDotProd]>;
//===----------------------------------------------------------------------===//
// Register File Description
//===----------------------------------------------------------------------===//
include "AArch64RegisterInfo.td"
include "AArch64RegisterBanks.td"
include "AArch64CallingConvention.td"
//===----------------------------------------------------------------------===//
// Instruction Descriptions
//===----------------------------------------------------------------------===//
include "AArch64Schedule.td"
include "AArch64InstrInfo.td"
def AArch64InstrInfo : InstrInfo;
//===----------------------------------------------------------------------===//
// Named operands for MRS/MSR/TLBI/...
//===----------------------------------------------------------------------===//
include "AArch64SystemOperands.td"
//===----------------------------------------------------------------------===//
// AArch64 Processors supported.
//
include "AArch64SchedA53.td"
include "AArch64SchedA57.td"
include "AArch64SchedCyclone.td"
include "AArch64SchedFalkor.td"
include "AArch64SchedKryo.td"
include "AArch64SchedExynosM1.td"
include "AArch64SchedExynosM3.td"
include "AArch64SchedThunderX.td"
include "AArch64SchedThunderX2T99.td"
def ProcA35 : SubtargetFeature<"a35", "ARMProcFamily", "CortexA35",
"Cortex-A35 ARM processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeatureNEON,
FeaturePerfMon
]>;
def ProcA53 : SubtargetFeature<"a53", "ARMProcFamily", "CortexA53",
"Cortex-A53 ARM processors", [
FeatureBalanceFPOps,
FeatureCRC,
FeatureCrypto,
FeatureCustomCheapAsMoveHandling,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeatureUseAA
]>;
def ProcA55 : SubtargetFeature<"a55", "ARMProcFamily", "CortexA55",
"Cortex-A55 ARM processors", [
HasV8_2aOps,
FeatureCrypto,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeatureFullFP16,
FeatureDotProd,
FeatureRCPC,
FeaturePerfMon
]>;
def ProcA57 : SubtargetFeature<"a57", "ARMProcFamily", "CortexA57",
"Cortex-A57 ARM processors", [
FeatureBalanceFPOps,
FeatureCRC,
FeatureCrypto,
FeatureCustomCheapAsMoveHandling,
FeatureFPARMv8,
FeatureFuseAES,
FeatureFuseLiterals,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive
]>;
def ProcA72 : SubtargetFeature<"a72", "ARMProcFamily", "CortexA72",
"Cortex-A72 ARM processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon
]>;
def ProcA73 : SubtargetFeature<"a73", "ARMProcFamily", "CortexA73",
"Cortex-A73 ARM processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon
]>;
def ProcA75 : SubtargetFeature<"a75", "ARMProcFamily", "CortexA75",
"Cortex-A75 ARM processors", [
HasV8_2aOps,
FeatureCrypto,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeatureFullFP16,
FeatureDotProd,
FeatureRCPC,
FeaturePerfMon
]>;
// Note that cyclone does not fuse AES instructions, but newer apple chips do
// perform the fusion and cyclone is used by default when targetting apple OSes.
def ProcCyclone : SubtargetFeature<"cyclone", "ARMProcFamily", "Cyclone",
"Cyclone", [
FeatureAlternateSExtLoadCVTF32Pattern,
FeatureArithmeticBccFusion,
FeatureArithmeticCbzFusion,
FeatureCrypto,
FeatureDisableLatencySchedHeuristic,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon,
FeatureZCRegMove,
FeatureZCZeroing,
FeatureZCZeroingFPWorkaround
]>;
def ProcExynosM1 : SubtargetFeature<"exynosm1", "ARMProcFamily", "ExynosM1",
"Samsung Exynos-M1 processors",
[FeatureSlowPaired128,
FeatureCRC,
FeatureCrypto,
FeatureExynosCheapAsMoveHandling,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeatureSlowMisaligned128Store,
FeatureUseRSqrt,
FeatureZCZeroing]>;
def ProcExynosM2 : SubtargetFeature<"exynosm2", "ARMProcFamily", "ExynosM1",
"Samsung Exynos-M2 processors",
[FeatureSlowPaired128,
FeatureCRC,
FeatureCrypto,
FeatureExynosCheapAsMoveHandling,
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeatureSlowMisaligned128Store,
FeatureZCZeroing]>;
def ProcExynosM3 : SubtargetFeature<"exynosm3", "ARMProcFamily", "ExynosM3",
"Samsung Exynos-M3 processors",
[FeatureCRC,
FeatureCrypto,
FeatureExynosCheapAsMoveHandling,
FeatureFPARMv8,
FeatureFuseAddress,
FeatureFuseAES,
FeatureFuseCCSelect,
FeatureFuseLiterals,
FeatureLSLFast,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureZCZeroing]>;
def ProcKryo : SubtargetFeature<"kryo", "ARMProcFamily", "Kryo",
"Qualcomm Kryo processors", [
FeatureCRC,
FeatureCrypto,
FeatureCustomCheapAsMoveHandling,
FeatureFPARMv8,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureZCZeroing,
FeatureLSLFast
]>;
def ProcFalkor : SubtargetFeature<"falkor", "ARMProcFamily", "Falkor",
"Qualcomm Falkor processors", [
FeatureCRC,
FeatureCrypto,
FeatureCustomCheapAsMoveHandling,
FeatureFPARMv8,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureRDM,
FeatureZCZeroing,
FeatureLSLFast,
FeatureSlowSTRQro
]>;
def ProcSaphira : SubtargetFeature<"saphira", "ARMProcFamily", "Saphira",
"Qualcomm Saphira processors", [
FeatureCrypto,
FeatureCustomCheapAsMoveHandling,
FeatureFPARMv8,
FeatureNEON,
FeatureSPE,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureZCZeroing,
FeatureLSLFast,
HasV8_3aOps]>;
def ProcThunderX2T99 : SubtargetFeature<"thunderx2t99", "ARMProcFamily",
"ThunderX2T99",
"Cavium ThunderX2 processors", [
FeatureAggressiveFMA,
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeatureArithmeticBccFusion,
FeatureNEON,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureLSE,
HasV8_1aOps]>;
def ProcThunderX : SubtargetFeature<"thunderx", "ARMProcFamily", "ThunderX",
"Cavium ThunderX processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureNEON]>;
def ProcThunderXT88 : SubtargetFeature<"thunderxt88", "ARMProcFamily",
"ThunderXT88",
"Cavium ThunderX processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureNEON]>;
def ProcThunderXT81 : SubtargetFeature<"thunderxt81", "ARMProcFamily",
"ThunderXT81",
"Cavium ThunderX processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureNEON]>;
def ProcThunderXT83 : SubtargetFeature<"thunderxt83", "ARMProcFamily",
"ThunderXT83",
"Cavium ThunderX processors", [
FeatureCRC,
FeatureCrypto,
FeatureFPARMv8,
FeaturePerfMon,
FeaturePostRAScheduler,
FeaturePredictableSelectIsExpensive,
FeatureNEON]>;
def : ProcessorModel<"generic", NoSchedModel, [
FeatureFPARMv8,
FeatureFuseAES,
FeatureNEON,
FeaturePerfMon,
FeaturePostRAScheduler
]>;
// FIXME: Cortex-A35 and Cortex-A55 are currently modeled as a Cortex-A53.
def : ProcessorModel<"cortex-a35", CortexA53Model, [ProcA35]>;
def : ProcessorModel<"cortex-a53", CortexA53Model, [ProcA53]>;
def : ProcessorModel<"cortex-a55", CortexA53Model, [ProcA55]>;
def : ProcessorModel<"cortex-a57", CortexA57Model, [ProcA57]>;
// FIXME: Cortex-A72, Cortex-A73 and Cortex-A75 are currently modeled as a Cortex-A57.
def : ProcessorModel<"cortex-a72", CortexA57Model, [ProcA72]>;
def : ProcessorModel<"cortex-a73", CortexA57Model, [ProcA73]>;
def : ProcessorModel<"cortex-a75", CortexA57Model, [ProcA75]>;
def : ProcessorModel<"cyclone", CycloneModel, [ProcCyclone]>;
def : ProcessorModel<"exynos-m1", ExynosM1Model, [ProcExynosM1]>;
def : ProcessorModel<"exynos-m2", ExynosM1Model, [ProcExynosM2]>;
def : ProcessorModel<"exynos-m3", ExynosM3Model, [ProcExynosM3]>;
def : ProcessorModel<"exynos-m4", ExynosM3Model, [ProcExynosM3]>;
def : ProcessorModel<"falkor", FalkorModel, [ProcFalkor]>;
def : ProcessorModel<"saphira", FalkorModel, [ProcSaphira]>;
def : ProcessorModel<"kryo", KryoModel, [ProcKryo]>;
// Cavium ThunderX/ThunderX T8X Processors
def : ProcessorModel<"thunderx", ThunderXT8XModel, [ProcThunderX]>;
def : ProcessorModel<"thunderxt88", ThunderXT8XModel, [ProcThunderXT88]>;
def : ProcessorModel<"thunderxt81", ThunderXT8XModel, [ProcThunderXT81]>;
def : ProcessorModel<"thunderxt83", ThunderXT8XModel, [ProcThunderXT83]>;
// Cavium ThunderX2T9X Processors. Formerly Broadcom Vulcan.
def : ProcessorModel<"thunderx2t99", ThunderX2T99Model, [ProcThunderX2T99]>;
//===----------------------------------------------------------------------===//
// Assembly parser
//===----------------------------------------------------------------------===//
def GenericAsmParserVariant : AsmParserVariant {
int Variant = 0;
string Name = "generic";
string BreakCharacters = ".";
string TokenizingCharacters = "[]*!/";
}
def AppleAsmParserVariant : AsmParserVariant {
int Variant = 1;
string Name = "apple-neon";
string BreakCharacters = ".";
string TokenizingCharacters = "[]*!/";
}
//===----------------------------------------------------------------------===//
// Assembly printer
//===----------------------------------------------------------------------===//
// AArch64 Uses the MC printer for asm output, so make sure the TableGen
// AsmWriter bits get associated with the correct class.
def GenericAsmWriter : AsmWriter {
string AsmWriterClassName = "InstPrinter";
int PassSubtarget = 1;
int Variant = 0;
bit isMCAsmWriter = 1;
}
def AppleAsmWriter : AsmWriter {
let AsmWriterClassName = "AppleInstPrinter";
int PassSubtarget = 1;
int Variant = 1;
int isMCAsmWriter = 1;
}
//===----------------------------------------------------------------------===//
// Target Declaration
//===----------------------------------------------------------------------===//
def AArch64 : Target {
let InstructionSet = AArch64InstrInfo;
let AssemblyParserVariants = [GenericAsmParserVariant, AppleAsmParserVariant];
let AssemblyWriters = [GenericAsmWriter, AppleAsmWriter];
let AllowRegisterRenaming = 1;
}