mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 12:02:58 +02:00
b3dd67f4cd
This adds extra scalar handling to isFMAFasterThanFMulAndFAdd, allowing the target independent code to handle more folds in more situations (for example if the fast math flags are present, but the global AllowFPOpFusion option isnt). It also splits apart the HasSlowFPVMLx into HasSlowFPVFMx, to allow VFMA and VMLA to be controlled separately if needed. Differential Revision: https://reviews.llvm.org/D72139
1269 lines
69 KiB
TableGen
1269 lines
69 KiB
TableGen
//===-- ARM.td - Describe the ARM Target Machine -----------*- 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Target-independent interfaces which we are implementing
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "llvm/Target/Target.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM Subtarget state.
|
|
//
|
|
|
|
def ModeThumb : SubtargetFeature<"thumb-mode", "InThumbMode",
|
|
"true", "Thumb mode">;
|
|
|
|
def ModeSoftFloat : SubtargetFeature<"soft-float","UseSoftFloat",
|
|
"true", "Use software floating "
|
|
"point features.">;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM Subtarget features.
|
|
//
|
|
|
|
// Floating Point, HW Division and Neon Support
|
|
|
|
// FP loads/stores/moves, shared between VFP and MVE (even in the integer-only
|
|
// version).
|
|
def FeatureFPRegs : SubtargetFeature<"fpregs", "HasFPRegs", "true",
|
|
"Enable FP registers">;
|
|
|
|
// 16-bit FP loads/stores/moves, shared between VFP (with the v8.2A FP16
|
|
// extension) and MVE (even in the integer-only version).
|
|
def FeatureFPRegs16 : SubtargetFeature<"fpregs16", "HasFPRegs16", "true",
|
|
"Enable 16-bit FP registers",
|
|
[FeatureFPRegs]>;
|
|
|
|
def FeatureFPRegs64 : SubtargetFeature<"fpregs64", "HasFPRegs64", "true",
|
|
"Enable 64-bit FP registers",
|
|
[FeatureFPRegs]>;
|
|
|
|
def FeatureFP64 : SubtargetFeature<"fp64", "HasFP64", "true",
|
|
"Floating point unit supports "
|
|
"double precision",
|
|
[FeatureFPRegs64]>;
|
|
|
|
def FeatureD32 : SubtargetFeature<"d32", "HasD32", "true",
|
|
"Extend FP to 32 double registers">;
|
|
|
|
multiclass VFPver<string name, string query, string description,
|
|
list<SubtargetFeature> prev,
|
|
list<SubtargetFeature> otherimplies,
|
|
list<SubtargetFeature> vfp2prev = []> {
|
|
def _D16_SP: SubtargetFeature<
|
|
name#"d16sp", query#"D16SP", "true",
|
|
description#" with only 16 d-registers and no double precision",
|
|
!foreach(v, prev, !cast<SubtargetFeature>(v # "_D16_SP")) #
|
|
!foreach(v, vfp2prev, !cast<SubtargetFeature>(v # "_SP")) #
|
|
otherimplies>;
|
|
def _SP: SubtargetFeature<
|
|
name#"sp", query#"SP", "true",
|
|
description#" with no double precision",
|
|
!foreach(v, prev, !cast<SubtargetFeature>(v # "_SP")) #
|
|
otherimplies # [FeatureD32, !cast<SubtargetFeature>(NAME # "_D16_SP")]>;
|
|
def _D16: SubtargetFeature<
|
|
name#"d16", query#"D16", "true",
|
|
description#" with only 16 d-registers",
|
|
!foreach(v, prev, !cast<SubtargetFeature>(v # "_D16")) #
|
|
vfp2prev #
|
|
otherimplies # [FeatureFP64, !cast<SubtargetFeature>(NAME # "_D16_SP")]>;
|
|
def "": SubtargetFeature<
|
|
name, query, "true", description,
|
|
prev # otherimplies # [
|
|
!cast<SubtargetFeature>(NAME # "_D16"),
|
|
!cast<SubtargetFeature>(NAME # "_SP")]>;
|
|
}
|
|
|
|
def FeatureVFP2_SP : SubtargetFeature<"vfp2sp", "HasVFPv2SP", "true",
|
|
"Enable VFP2 instructions with "
|
|
"no double precision",
|
|
[FeatureFPRegs]>;
|
|
|
|
def FeatureVFP2 : SubtargetFeature<"vfp2", "HasVFPv2", "true",
|
|
"Enable VFP2 instructions",
|
|
[FeatureFP64, FeatureVFP2_SP]>;
|
|
|
|
defm FeatureVFP3: VFPver<"vfp3", "HasVFPv3", "Enable VFP3 instructions",
|
|
[], [], [FeatureVFP2]>;
|
|
|
|
def FeatureNEON : SubtargetFeature<"neon", "HasNEON", "true",
|
|
"Enable NEON instructions",
|
|
[FeatureVFP3]>;
|
|
|
|
def FeatureFP16 : SubtargetFeature<"fp16", "HasFP16", "true",
|
|
"Enable half-precision "
|
|
"floating point">;
|
|
|
|
defm FeatureVFP4: VFPver<"vfp4", "HasVFPv4", "Enable VFP4 instructions",
|
|
[FeatureVFP3], [FeatureFP16]>;
|
|
|
|
defm FeatureFPARMv8: VFPver<"fp-armv8", "HasFPARMv8", "Enable ARMv8 FP",
|
|
[FeatureVFP4], []>;
|
|
|
|
def FeatureFullFP16 : SubtargetFeature<"fullfp16", "HasFullFP16", "true",
|
|
"Enable full half-precision "
|
|
"floating point",
|
|
[FeatureFPARMv8_D16_SP, FeatureFPRegs16]>;
|
|
|
|
def FeatureFP16FML : SubtargetFeature<"fp16fml", "HasFP16FML", "true",
|
|
"Enable full half-precision "
|
|
"floating point fml instructions",
|
|
[FeatureFullFP16]>;
|
|
|
|
def FeatureHWDivThumb : SubtargetFeature<"hwdiv",
|
|
"HasHardwareDivideInThumb", "true",
|
|
"Enable divide instructions in Thumb">;
|
|
|
|
def FeatureHWDivARM : SubtargetFeature<"hwdiv-arm",
|
|
"HasHardwareDivideInARM", "true",
|
|
"Enable divide instructions in ARM mode">;
|
|
|
|
// Atomic Support
|
|
def FeatureDB : SubtargetFeature<"db", "HasDataBarrier", "true",
|
|
"Has data barrier (dmb/dsb) instructions">;
|
|
|
|
def FeatureV7Clrex : SubtargetFeature<"v7clrex", "HasV7Clrex", "true",
|
|
"Has v7 clrex instruction">;
|
|
|
|
def FeatureDFB : SubtargetFeature<"dfb", "HasFullDataBarrier", "true",
|
|
"Has full data barrier (dfb) instruction">;
|
|
|
|
def FeatureAcquireRelease : SubtargetFeature<"acquire-release",
|
|
"HasAcquireRelease", "true",
|
|
"Has v8 acquire/release (lda/ldaex "
|
|
" etc) instructions">;
|
|
|
|
|
|
def FeatureSlowFPBrcc : SubtargetFeature<"slow-fp-brcc", "SlowFPBrcc", "true",
|
|
"FP compare + branch is slow">;
|
|
|
|
def FeaturePerfMon : SubtargetFeature<"perfmon", "HasPerfMon", "true",
|
|
"Enable support for Performance "
|
|
"Monitor extensions">;
|
|
|
|
|
|
// TrustZone Security Extensions
|
|
def FeatureTrustZone : SubtargetFeature<"trustzone", "HasTrustZone", "true",
|
|
"Enable support for TrustZone "
|
|
"security extensions">;
|
|
|
|
def Feature8MSecExt : SubtargetFeature<"8msecext", "Has8MSecExt", "true",
|
|
"Enable support for ARMv8-M "
|
|
"Security Extensions">;
|
|
|
|
def FeatureSHA2 : SubtargetFeature<"sha2", "HasSHA2", "true",
|
|
"Enable SHA1 and SHA256 support", [FeatureNEON]>;
|
|
|
|
def FeatureAES : SubtargetFeature<"aes", "HasAES", "true",
|
|
"Enable AES support", [FeatureNEON]>;
|
|
|
|
def FeatureCrypto : SubtargetFeature<"crypto", "HasCrypto", "true",
|
|
"Enable support for "
|
|
"Cryptography extensions",
|
|
[FeatureNEON, FeatureSHA2, FeatureAES]>;
|
|
|
|
def FeatureCRC : SubtargetFeature<"crc", "HasCRC", "true",
|
|
"Enable support for CRC instructions">;
|
|
|
|
def FeatureDotProd : SubtargetFeature<"dotprod", "HasDotProd", "true",
|
|
"Enable support for dot product instructions",
|
|
[FeatureNEON]>;
|
|
|
|
// Not to be confused with FeatureHasRetAddrStack (return address stack)
|
|
def FeatureRAS : SubtargetFeature<"ras", "HasRAS", "true",
|
|
"Enable Reliability, Availability "
|
|
"and Serviceability extensions">;
|
|
|
|
// Fast computation of non-negative address offsets
|
|
def FeatureFPAO : SubtargetFeature<"fpao", "HasFPAO", "true",
|
|
"Enable fast computation of "
|
|
"positive address offsets">;
|
|
|
|
// Fast execution of AES crypto operations
|
|
def FeatureFuseAES : SubtargetFeature<"fuse-aes", "HasFuseAES", "true",
|
|
"CPU fuses AES crypto operations">;
|
|
|
|
// Fast execution of bottom and top halves of literal generation
|
|
def FeatureFuseLiterals : SubtargetFeature<"fuse-literals", "HasFuseLiterals", "true",
|
|
"CPU fuses literal generation operations">;
|
|
|
|
// The way of reading thread pointer
|
|
def FeatureReadTp : SubtargetFeature<"read-tp-hard", "ReadTPHard", "true",
|
|
"Reading thread pointer from register">;
|
|
|
|
// Cyclone can zero VFP registers in 0 cycles.
|
|
def FeatureZCZeroing : SubtargetFeature<"zcz", "HasZeroCycleZeroing", "true",
|
|
"Has zero-cycle zeroing instructions">;
|
|
|
|
// Whether it is profitable to unpredicate certain instructions during if-conversion
|
|
def FeatureProfUnpredicate : SubtargetFeature<"prof-unpr",
|
|
"IsProfitableToUnpredicate", "true",
|
|
"Is profitable to unpredicate">;
|
|
|
|
// Some targets (e.g. Swift) have microcoded VGETLNi32.
|
|
def FeatureSlowVGETLNi32 : SubtargetFeature<"slow-vgetlni32",
|
|
"HasSlowVGETLNi32", "true",
|
|
"Has slow VGETLNi32 - prefer VMOV">;
|
|
|
|
// Some targets (e.g. Swift) have microcoded VDUP32.
|
|
def FeatureSlowVDUP32 : SubtargetFeature<"slow-vdup32", "HasSlowVDUP32",
|
|
"true",
|
|
"Has slow VDUP32 - prefer VMOV">;
|
|
|
|
// Some targets (e.g. Cortex-A9) prefer VMOVSR to VMOVDRR even when using NEON
|
|
// for scalar FP, as this allows more effective execution domain optimization.
|
|
def FeaturePreferVMOVSR : SubtargetFeature<"prefer-vmovsr", "PreferVMOVSR",
|
|
"true", "Prefer VMOVSR">;
|
|
|
|
// Swift has ISHST barriers compatible with Atomic Release semantics but weaker
|
|
// than ISH
|
|
def FeaturePrefISHSTBarrier : SubtargetFeature<"prefer-ishst", "PreferISHST",
|
|
"true", "Prefer ISHST barriers">;
|
|
|
|
// Some targets (e.g. Cortex-A9) have muxed AGU and NEON/FPU.
|
|
def FeatureMuxedUnits : SubtargetFeature<"muxed-units", "HasMuxedUnits",
|
|
"true",
|
|
"Has muxed AGU and NEON/FPU">;
|
|
|
|
// Whether VLDM/VSTM starting with odd register number need more microops
|
|
// than single VLDRS
|
|
def FeatureSlowOddRegister : SubtargetFeature<"slow-odd-reg", "SlowOddRegister",
|
|
"true", "VLDM/VSTM starting "
|
|
"with an odd register is slow">;
|
|
|
|
// Some targets have a renaming dependency when loading into D subregisters.
|
|
def FeatureSlowLoadDSubreg : SubtargetFeature<"slow-load-D-subreg",
|
|
"SlowLoadDSubregister", "true",
|
|
"Loading into D subregs is slow">;
|
|
|
|
def FeatureUseWideStrideVFP : SubtargetFeature<"wide-stride-vfp",
|
|
"UseWideStrideVFP", "true",
|
|
"Use a wide stride when allocating VFP registers">;
|
|
|
|
// Some targets (e.g. Cortex-A15) never want VMOVS to be widened to VMOVD.
|
|
def FeatureDontWidenVMOVS : SubtargetFeature<"dont-widen-vmovs",
|
|
"DontWidenVMOVS", "true",
|
|
"Don't widen VMOVS to VMOVD">;
|
|
|
|
// Some targets (e.g. Cortex-A15) prefer to avoid mixing operations on different
|
|
// VFP register widths.
|
|
def FeatureSplatVFPToNeon : SubtargetFeature<"splat-vfp-neon",
|
|
"SplatVFPToNeon", "true",
|
|
"Splat register from VFP to NEON",
|
|
[FeatureDontWidenVMOVS]>;
|
|
|
|
// Whether or not it is profitable to expand VFP/NEON MLA/MLS instructions.
|
|
def FeatureExpandMLx : SubtargetFeature<"expand-fp-mlx",
|
|
"ExpandMLx", "true",
|
|
"Expand VFP/NEON MLA/MLS instructions">;
|
|
|
|
// Some targets have special RAW hazards for VFP/NEON VMLA/VMLS.
|
|
def FeatureHasVMLxHazards : SubtargetFeature<"vmlx-hazards", "HasVMLxHazards",
|
|
"true", "Has VMLx hazards">;
|
|
|
|
// Some targets (e.g. Cortex-A9) want to convert VMOVRS, VMOVSR and VMOVS from
|
|
// VFP to NEON, as an execution domain optimization.
|
|
def FeatureNEONForFPMovs : SubtargetFeature<"neon-fpmovs",
|
|
"UseNEONForFPMovs", "true",
|
|
"Convert VMOVSR, VMOVRS, "
|
|
"VMOVS to NEON">;
|
|
|
|
// Some processors benefit from using NEON instructions for scalar
|
|
// single-precision FP operations. This affects instruction selection and should
|
|
// only be enabled if the handling of denormals is not important.
|
|
def FeatureNEONForFP : SubtargetFeature<"neonfp",
|
|
"UseNEONForSinglePrecisionFP",
|
|
"true",
|
|
"Use NEON for single precision FP">;
|
|
|
|
// On some processors, VLDn instructions that access unaligned data take one
|
|
// extra cycle. Take that into account when computing operand latencies.
|
|
def FeatureCheckVLDnAlign : SubtargetFeature<"vldn-align", "CheckVLDnAlign",
|
|
"true",
|
|
"Check for VLDn unaligned access">;
|
|
|
|
// Some processors have a nonpipelined VFP coprocessor.
|
|
def FeatureNonpipelinedVFP : SubtargetFeature<"nonpipelined-vfp",
|
|
"NonpipelinedVFP", "true",
|
|
"VFP instructions are not pipelined">;
|
|
|
|
// Some processors have FP multiply-accumulate instructions that don't
|
|
// play nicely with other VFP / NEON instructions, and it's generally better
|
|
// to just not use them.
|
|
def FeatureHasSlowFPVMLx : SubtargetFeature<"slowfpvmlx", "SlowFPVMLx", "true",
|
|
"Disable VFP / NEON MAC instructions">;
|
|
|
|
// VFPv4 added VFMA instructions that can similar be fast or slow.
|
|
def FeatureHasSlowFPVFMx : SubtargetFeature<"slowfpvfmx", "SlowFPVFMx", "true",
|
|
"Disable VFP / NEON FMA instructions">;
|
|
|
|
// Cortex-A8 / A9 Advanced SIMD has multiplier accumulator forwarding.
|
|
def FeatureVMLxForwarding : SubtargetFeature<"vmlx-forwarding",
|
|
"HasVMLxForwarding", "true",
|
|
"Has multiplier accumulator forwarding">;
|
|
|
|
// Disable 32-bit to 16-bit narrowing for experimentation.
|
|
def FeaturePref32BitThumb : SubtargetFeature<"32bit", "Pref32BitThumb", "true",
|
|
"Prefer 32-bit Thumb instrs">;
|
|
|
|
def FeaturePrefLoopAlign32 : SubtargetFeature<"loop-align", "PrefLoopLogAlignment","2",
|
|
"Prefer 32-bit alignment for loops">;
|
|
|
|
def FeatureMVEVectorCostFactor1 : SubtargetFeature<"mve1beat", "MVEVectorCostFactor", "1",
|
|
"Model MVE instructions as a 1 beat per tick architecture">;
|
|
|
|
def FeatureMVEVectorCostFactor2 : SubtargetFeature<"mve2beat", "MVEVectorCostFactor", "2",
|
|
"Model MVE instructions as a 2 beats per tick architecture">;
|
|
|
|
def FeatureMVEVectorCostFactor4 : SubtargetFeature<"mve4beat", "MVEVectorCostFactor", "4",
|
|
"Model MVE instructions as a 4 beats per tick architecture">;
|
|
|
|
/// Some instructions update CPSR partially, which can add false dependency for
|
|
/// out-of-order implementation, e.g. Cortex-A9, unless each individual bit is
|
|
/// mapped to a separate physical register. Avoid partial CPSR update for these
|
|
/// processors.
|
|
def FeatureAvoidPartialCPSR : SubtargetFeature<"avoid-partial-cpsr",
|
|
"AvoidCPSRPartialUpdate", "true",
|
|
"Avoid CPSR partial update for OOO execution">;
|
|
|
|
/// Disable +1 predication cost for instructions updating CPSR.
|
|
/// Enabled for Cortex-A57.
|
|
def FeatureCheapPredicableCPSR : SubtargetFeature<"cheap-predicable-cpsr",
|
|
"CheapPredicableCPSRDef",
|
|
"true",
|
|
"Disable +1 predication cost for instructions updating CPSR">;
|
|
|
|
def FeatureAvoidMOVsShOp : SubtargetFeature<"avoid-movs-shop",
|
|
"AvoidMOVsShifterOperand", "true",
|
|
"Avoid movs instructions with "
|
|
"shifter operand">;
|
|
|
|
// Some processors perform return stack prediction. CodeGen should avoid issue
|
|
// "normal" call instructions to callees which do not return.
|
|
def FeatureHasRetAddrStack : SubtargetFeature<"ret-addr-stack",
|
|
"HasRetAddrStack", "true",
|
|
"Has return address stack">;
|
|
|
|
// Some processors have no branch predictor, which changes the expected cost of
|
|
// taking a branch which affects the choice of whether to use predicated
|
|
// instructions.
|
|
def FeatureHasNoBranchPredictor : SubtargetFeature<"no-branch-predictor",
|
|
"HasBranchPredictor", "false",
|
|
"Has no branch predictor">;
|
|
|
|
/// DSP extension.
|
|
def FeatureDSP : SubtargetFeature<"dsp", "HasDSP", "true",
|
|
"Supports DSP instructions in "
|
|
"ARM and/or Thumb2">;
|
|
|
|
// Multiprocessing extension.
|
|
def FeatureMP : SubtargetFeature<"mp", "HasMPExtension", "true",
|
|
"Supports Multiprocessing extension">;
|
|
|
|
// Virtualization extension - requires HW divide (ARMv7-AR ARMARM - 4.4.8).
|
|
def FeatureVirtualization : SubtargetFeature<"virtualization",
|
|
"HasVirtualization", "true",
|
|
"Supports Virtualization extension",
|
|
[FeatureHWDivThumb, FeatureHWDivARM]>;
|
|
|
|
// Special TRAP encoding for NaCl, which looks like a TRAP in Thumb too.
|
|
// See ARMInstrInfo.td for details.
|
|
def FeatureNaClTrap : SubtargetFeature<"nacl-trap", "UseNaClTrap", "true",
|
|
"NaCl trap">;
|
|
|
|
def FeatureStrictAlign : SubtargetFeature<"strict-align",
|
|
"StrictAlign", "true",
|
|
"Disallow all unaligned memory "
|
|
"access">;
|
|
|
|
def FeatureLongCalls : SubtargetFeature<"long-calls", "GenLongCalls", "true",
|
|
"Generate calls via indirect call "
|
|
"instructions">;
|
|
|
|
def FeatureExecuteOnly : SubtargetFeature<"execute-only",
|
|
"GenExecuteOnly", "true",
|
|
"Enable the generation of "
|
|
"execute only code.">;
|
|
|
|
def FeatureReserveR9 : SubtargetFeature<"reserve-r9", "ReserveR9", "true",
|
|
"Reserve R9, making it unavailable"
|
|
" as GPR">;
|
|
|
|
def FeatureNoMovt : SubtargetFeature<"no-movt", "NoMovt", "true",
|
|
"Don't use movt/movw pairs for "
|
|
"32-bit imms">;
|
|
|
|
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.">;
|
|
|
|
// Use the MachineScheduler for instruction scheduling for the subtarget.
|
|
def FeatureUseMISched: SubtargetFeature<"use-misched", "UseMISched", "true",
|
|
"Use the MachineScheduler">;
|
|
|
|
def FeatureNoPostRASched : SubtargetFeature<"disable-postra-scheduler",
|
|
"DisablePostRAScheduler", "true",
|
|
"Don't schedule again after register allocation">;
|
|
|
|
// Armv8.5-A extensions
|
|
|
|
def FeatureSB : SubtargetFeature<"sb", "HasSB", "true",
|
|
"Enable v8.5a Speculation Barrier" >;
|
|
|
|
// Armv8.1-M extensions
|
|
|
|
def FeatureLOB : SubtargetFeature<"lob", "HasLOB", "true",
|
|
"Enable Low Overhead Branch "
|
|
"extensions">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM architecture class
|
|
//
|
|
|
|
// A-series ISA
|
|
def FeatureAClass : SubtargetFeature<"aclass", "ARMProcClass", "AClass",
|
|
"Is application profile ('A' series)">;
|
|
|
|
// R-series ISA
|
|
def FeatureRClass : SubtargetFeature<"rclass", "ARMProcClass", "RClass",
|
|
"Is realtime profile ('R' series)">;
|
|
|
|
// M-series ISA
|
|
def FeatureMClass : SubtargetFeature<"mclass", "ARMProcClass", "MClass",
|
|
"Is microcontroller profile ('M' series)">;
|
|
|
|
|
|
def FeatureThumb2 : SubtargetFeature<"thumb2", "HasThumb2", "true",
|
|
"Enable Thumb2 instructions">;
|
|
|
|
def FeatureNoARM : SubtargetFeature<"noarm", "NoARM", "true",
|
|
"Does not support ARM mode execution">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM ISAa.
|
|
//
|
|
|
|
def HasV4TOps : SubtargetFeature<"v4t", "HasV4TOps", "true",
|
|
"Support ARM v4T instructions">;
|
|
|
|
def HasV5TOps : SubtargetFeature<"v5t", "HasV5TOps", "true",
|
|
"Support ARM v5T instructions",
|
|
[HasV4TOps]>;
|
|
|
|
def HasV5TEOps : SubtargetFeature<"v5te", "HasV5TEOps", "true",
|
|
"Support ARM v5TE, v5TEj, and "
|
|
"v5TExp instructions",
|
|
[HasV5TOps]>;
|
|
|
|
def HasV6Ops : SubtargetFeature<"v6", "HasV6Ops", "true",
|
|
"Support ARM v6 instructions",
|
|
[HasV5TEOps]>;
|
|
|
|
def HasV6MOps : SubtargetFeature<"v6m", "HasV6MOps", "true",
|
|
"Support ARM v6M instructions",
|
|
[HasV6Ops]>;
|
|
|
|
def HasV8MBaselineOps : SubtargetFeature<"v8m", "HasV8MBaselineOps", "true",
|
|
"Support ARM v8M Baseline instructions",
|
|
[HasV6MOps]>;
|
|
|
|
def HasV6KOps : SubtargetFeature<"v6k", "HasV6KOps", "true",
|
|
"Support ARM v6k instructions",
|
|
[HasV6Ops]>;
|
|
|
|
def HasV6T2Ops : SubtargetFeature<"v6t2", "HasV6T2Ops", "true",
|
|
"Support ARM v6t2 instructions",
|
|
[HasV8MBaselineOps, HasV6KOps, FeatureThumb2]>;
|
|
|
|
def HasV7Ops : SubtargetFeature<"v7", "HasV7Ops", "true",
|
|
"Support ARM v7 instructions",
|
|
[HasV6T2Ops, FeaturePerfMon,
|
|
FeatureV7Clrex]>;
|
|
|
|
def HasV8MMainlineOps :
|
|
SubtargetFeature<"v8m.main", "HasV8MMainlineOps", "true",
|
|
"Support ARM v8M Mainline instructions",
|
|
[HasV7Ops]>;
|
|
|
|
def HasV8Ops : SubtargetFeature<"v8", "HasV8Ops", "true",
|
|
"Support ARM v8 instructions",
|
|
[HasV7Ops, FeatureAcquireRelease]>;
|
|
|
|
def HasV8_1aOps : SubtargetFeature<"v8.1a", "HasV8_1aOps", "true",
|
|
"Support ARM v8.1a instructions",
|
|
[HasV8Ops]>;
|
|
|
|
def HasV8_2aOps : SubtargetFeature<"v8.2a", "HasV8_2aOps", "true",
|
|
"Support ARM v8.2a instructions",
|
|
[HasV8_1aOps]>;
|
|
|
|
def HasV8_3aOps : SubtargetFeature<"v8.3a", "HasV8_3aOps", "true",
|
|
"Support ARM v8.3a instructions",
|
|
[HasV8_2aOps]>;
|
|
|
|
def HasV8_4aOps : SubtargetFeature<"v8.4a", "HasV8_4aOps", "true",
|
|
"Support ARM v8.4a instructions",
|
|
[HasV8_3aOps, FeatureDotProd]>;
|
|
|
|
def HasV8_5aOps : SubtargetFeature<"v8.5a", "HasV8_5aOps", "true",
|
|
"Support ARM v8.5a instructions",
|
|
[HasV8_4aOps, FeatureSB]>;
|
|
|
|
def HasV8_1MMainlineOps : SubtargetFeature<
|
|
"v8.1m.main", "HasV8_1MMainlineOps", "true",
|
|
"Support ARM v8-1M Mainline instructions",
|
|
[HasV8MMainlineOps]>;
|
|
def HasMVEIntegerOps : SubtargetFeature<
|
|
"mve", "HasMVEIntegerOps", "true",
|
|
"Support M-Class Vector Extension with integer ops",
|
|
[HasV8_1MMainlineOps, FeatureDSP, FeatureFPRegs16, FeatureFPRegs64]>;
|
|
def HasMVEFloatOps : SubtargetFeature<
|
|
"mve.fp", "HasMVEFloatOps", "true",
|
|
"Support M-Class Vector Extension with integer and floating ops",
|
|
[HasMVEIntegerOps, FeatureFPARMv8_D16_SP, FeatureFullFP16]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM Processor subtarget features.
|
|
//
|
|
|
|
def ProcA5 : SubtargetFeature<"a5", "ARMProcFamily", "CortexA5",
|
|
"Cortex-A5 ARM processors", []>;
|
|
def ProcA7 : SubtargetFeature<"a7", "ARMProcFamily", "CortexA7",
|
|
"Cortex-A7 ARM processors", []>;
|
|
def ProcA8 : SubtargetFeature<"a8", "ARMProcFamily", "CortexA8",
|
|
"Cortex-A8 ARM processors", []>;
|
|
def ProcA9 : SubtargetFeature<"a9", "ARMProcFamily", "CortexA9",
|
|
"Cortex-A9 ARM processors", []>;
|
|
def ProcA12 : SubtargetFeature<"a12", "ARMProcFamily", "CortexA12",
|
|
"Cortex-A12 ARM processors", []>;
|
|
def ProcA15 : SubtargetFeature<"a15", "ARMProcFamily", "CortexA15",
|
|
"Cortex-A15 ARM processors", []>;
|
|
def ProcA17 : SubtargetFeature<"a17", "ARMProcFamily", "CortexA17",
|
|
"Cortex-A17 ARM processors", []>;
|
|
def ProcA32 : SubtargetFeature<"a32", "ARMProcFamily", "CortexA32",
|
|
"Cortex-A32 ARM processors", []>;
|
|
def ProcA35 : SubtargetFeature<"a35", "ARMProcFamily", "CortexA35",
|
|
"Cortex-A35 ARM processors", []>;
|
|
def ProcA53 : SubtargetFeature<"a53", "ARMProcFamily", "CortexA53",
|
|
"Cortex-A53 ARM processors", []>;
|
|
def ProcA55 : SubtargetFeature<"a55", "ARMProcFamily", "CortexA55",
|
|
"Cortex-A55 ARM processors", []>;
|
|
def ProcA57 : SubtargetFeature<"a57", "ARMProcFamily", "CortexA57",
|
|
"Cortex-A57 ARM processors", []>;
|
|
def ProcA72 : SubtargetFeature<"a72", "ARMProcFamily", "CortexA72",
|
|
"Cortex-A72 ARM processors", []>;
|
|
def ProcA73 : SubtargetFeature<"a73", "ARMProcFamily", "CortexA73",
|
|
"Cortex-A73 ARM processors", []>;
|
|
def ProcA75 : SubtargetFeature<"a75", "ARMProcFamily", "CortexA75",
|
|
"Cortex-A75 ARM processors", []>;
|
|
def ProcA76 : SubtargetFeature<"a76", "ARMProcFamily", "CortexA76",
|
|
"Cortex-A76 ARM processors", []>;
|
|
|
|
def ProcKrait : SubtargetFeature<"krait", "ARMProcFamily", "Krait",
|
|
"Qualcomm Krait processors", []>;
|
|
def ProcKryo : SubtargetFeature<"kryo", "ARMProcFamily", "Kryo",
|
|
"Qualcomm Kryo processors", []>;
|
|
def ProcSwift : SubtargetFeature<"swift", "ARMProcFamily", "Swift",
|
|
"Swift ARM processors", []>;
|
|
|
|
def ProcExynos : SubtargetFeature<"exynos", "ARMProcFamily", "Exynos",
|
|
"Samsung Exynos processors",
|
|
[FeatureZCZeroing,
|
|
FeatureUseWideStrideVFP,
|
|
FeatureSplatVFPToNeon,
|
|
FeatureSlowVGETLNi32,
|
|
FeatureSlowVDUP32,
|
|
FeatureSlowFPBrcc,
|
|
FeatureProfUnpredicate,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureHasRetAddrStack,
|
|
FeatureFuseLiterals,
|
|
FeatureFuseAES,
|
|
FeatureExpandMLx,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def ProcR4 : SubtargetFeature<"r4", "ARMProcFamily", "CortexR4",
|
|
"Cortex-R4 ARM processors", []>;
|
|
def ProcR5 : SubtargetFeature<"r5", "ARMProcFamily", "CortexR5",
|
|
"Cortex-R5 ARM processors", []>;
|
|
def ProcR7 : SubtargetFeature<"r7", "ARMProcFamily", "CortexR7",
|
|
"Cortex-R7 ARM processors", []>;
|
|
def ProcR52 : SubtargetFeature<"r52", "ARMProcFamily", "CortexR52",
|
|
"Cortex-R52 ARM processors", []>;
|
|
|
|
def ProcM3 : SubtargetFeature<"m3", "ARMProcFamily", "CortexM3",
|
|
"Cortex-M3 ARM processors", []>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM Helper classes.
|
|
//
|
|
|
|
class Architecture<string fname, string aname, list<SubtargetFeature> features>
|
|
: SubtargetFeature<fname, "ARMArch", aname,
|
|
!strconcat(aname, " architecture"), features>;
|
|
|
|
class ProcNoItin<string Name, list<SubtargetFeature> Features>
|
|
: Processor<Name, NoItineraries, Features>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM architectures
|
|
//
|
|
|
|
def ARMv2 : Architecture<"armv2", "ARMv2", []>;
|
|
|
|
def ARMv2a : Architecture<"armv2a", "ARMv2a", []>;
|
|
|
|
def ARMv3 : Architecture<"armv3", "ARMv3", []>;
|
|
|
|
def ARMv3m : Architecture<"armv3m", "ARMv3m", []>;
|
|
|
|
def ARMv4 : Architecture<"armv4", "ARMv4", []>;
|
|
|
|
def ARMv4t : Architecture<"armv4t", "ARMv4t", [HasV4TOps]>;
|
|
|
|
def ARMv5t : Architecture<"armv5t", "ARMv5t", [HasV5TOps]>;
|
|
|
|
def ARMv5te : Architecture<"armv5te", "ARMv5te", [HasV5TEOps]>;
|
|
|
|
def ARMv5tej : Architecture<"armv5tej", "ARMv5tej", [HasV5TEOps]>;
|
|
|
|
def ARMv6 : Architecture<"armv6", "ARMv6", [HasV6Ops,
|
|
FeatureDSP]>;
|
|
|
|
def ARMv6t2 : Architecture<"armv6t2", "ARMv6t2", [HasV6T2Ops,
|
|
FeatureDSP]>;
|
|
|
|
def ARMv6k : Architecture<"armv6k", "ARMv6k", [HasV6KOps]>;
|
|
|
|
def ARMv6kz : Architecture<"armv6kz", "ARMv6kz", [HasV6KOps,
|
|
FeatureTrustZone]>;
|
|
|
|
def ARMv6m : Architecture<"armv6-m", "ARMv6m", [HasV6MOps,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureMClass,
|
|
FeatureStrictAlign]>;
|
|
|
|
def ARMv6sm : Architecture<"armv6s-m", "ARMv6sm", [HasV6MOps,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureMClass,
|
|
FeatureStrictAlign]>;
|
|
|
|
def ARMv7a : Architecture<"armv7-a", "ARMv7a", [HasV7Ops,
|
|
FeatureNEON,
|
|
FeatureDB,
|
|
FeatureDSP,
|
|
FeatureAClass]>;
|
|
|
|
def ARMv7ve : Architecture<"armv7ve", "ARMv7ve", [HasV7Ops,
|
|
FeatureNEON,
|
|
FeatureDB,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureAClass]>;
|
|
|
|
def ARMv7r : Architecture<"armv7-r", "ARMv7r", [HasV7Ops,
|
|
FeatureDB,
|
|
FeatureDSP,
|
|
FeatureHWDivThumb,
|
|
FeatureRClass]>;
|
|
|
|
def ARMv7m : Architecture<"armv7-m", "ARMv7m", [HasV7Ops,
|
|
FeatureThumb2,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureHWDivThumb,
|
|
FeatureMClass]>;
|
|
|
|
def ARMv7em : Architecture<"armv7e-m", "ARMv7em", [HasV7Ops,
|
|
FeatureThumb2,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureHWDivThumb,
|
|
FeatureMClass,
|
|
FeatureDSP]>;
|
|
|
|
def ARMv8a : Architecture<"armv8-a", "ARMv8a", [HasV8Ops,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def ARMv81a : Architecture<"armv8.1-a", "ARMv81a", [HasV8_1aOps,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def ARMv82a : Architecture<"armv8.2-a", "ARMv82a", [HasV8_2aOps,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureRAS]>;
|
|
|
|
def ARMv83a : Architecture<"armv8.3-a", "ARMv83a", [HasV8_3aOps,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureRAS]>;
|
|
|
|
def ARMv84a : Architecture<"armv8.4-a", "ARMv84a", [HasV8_4aOps,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureRAS,
|
|
FeatureDotProd]>;
|
|
|
|
def ARMv85a : Architecture<"armv8.5-a", "ARMv85a", [HasV8_5aOps,
|
|
FeatureAClass,
|
|
FeatureDB,
|
|
FeatureFPARMv8,
|
|
FeatureNEON,
|
|
FeatureDSP,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureRAS,
|
|
FeatureDotProd]>;
|
|
|
|
def ARMv8r : Architecture<"armv8-r", "ARMv8r", [HasV8Ops,
|
|
FeatureRClass,
|
|
FeatureDB,
|
|
FeatureDFB,
|
|
FeatureDSP,
|
|
FeatureCRC,
|
|
FeatureMP,
|
|
FeatureVirtualization,
|
|
FeatureFPARMv8,
|
|
FeatureNEON]>;
|
|
|
|
def ARMv8mBaseline : Architecture<"armv8-m.base", "ARMv8mBaseline",
|
|
[HasV8MBaselineOps,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureHWDivThumb,
|
|
FeatureV7Clrex,
|
|
Feature8MSecExt,
|
|
FeatureAcquireRelease,
|
|
FeatureMClass,
|
|
FeatureStrictAlign]>;
|
|
|
|
def ARMv8mMainline : Architecture<"armv8-m.main", "ARMv8mMainline",
|
|
[HasV8MMainlineOps,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureHWDivThumb,
|
|
Feature8MSecExt,
|
|
FeatureAcquireRelease,
|
|
FeatureMClass]>;
|
|
|
|
def ARMv81mMainline : Architecture<"armv8.1-m.main", "ARMv81mMainline",
|
|
[HasV8_1MMainlineOps,
|
|
FeatureNoARM,
|
|
ModeThumb,
|
|
FeatureDB,
|
|
FeatureHWDivThumb,
|
|
Feature8MSecExt,
|
|
FeatureAcquireRelease,
|
|
FeatureMClass,
|
|
FeatureRAS,
|
|
FeatureLOB]>;
|
|
|
|
// Aliases
|
|
def IWMMXT : Architecture<"iwmmxt", "ARMv5te", [ARMv5te]>;
|
|
def IWMMXT2 : Architecture<"iwmmxt2", "ARMv5te", [ARMv5te]>;
|
|
def XScale : Architecture<"xscale", "ARMv5te", [ARMv5te]>;
|
|
def ARMv6j : Architecture<"armv6j", "ARMv7a", [ARMv6]>;
|
|
def ARMv7k : Architecture<"armv7k", "ARMv7a", [ARMv7a]>;
|
|
def ARMv7s : Architecture<"armv7s", "ARMv7a", [ARMv7a]>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM schedules.
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
include "ARMPredicates.td"
|
|
include "ARMSchedule.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// ARM processors
|
|
//
|
|
|
|
// Dummy CPU, used to target architectures
|
|
def : ProcessorModel<"generic", CortexA8Model, []>;
|
|
|
|
// FIXME: Several processors below are not using their own scheduler
|
|
// model, but one of similar/previous processor. These should be fixed.
|
|
|
|
def : ProcNoItin<"arm8", [ARMv4]>;
|
|
def : ProcNoItin<"arm810", [ARMv4]>;
|
|
def : ProcNoItin<"strongarm", [ARMv4]>;
|
|
def : ProcNoItin<"strongarm110", [ARMv4]>;
|
|
def : ProcNoItin<"strongarm1100", [ARMv4]>;
|
|
def : ProcNoItin<"strongarm1110", [ARMv4]>;
|
|
|
|
def : ProcNoItin<"arm7tdmi", [ARMv4t]>;
|
|
def : ProcNoItin<"arm7tdmi-s", [ARMv4t]>;
|
|
def : ProcNoItin<"arm710t", [ARMv4t]>;
|
|
def : ProcNoItin<"arm720t", [ARMv4t]>;
|
|
def : ProcNoItin<"arm9", [ARMv4t]>;
|
|
def : ProcNoItin<"arm9tdmi", [ARMv4t]>;
|
|
def : ProcNoItin<"arm920", [ARMv4t]>;
|
|
def : ProcNoItin<"arm920t", [ARMv4t]>;
|
|
def : ProcNoItin<"arm922t", [ARMv4t]>;
|
|
def : ProcNoItin<"arm940t", [ARMv4t]>;
|
|
def : ProcNoItin<"ep9312", [ARMv4t]>;
|
|
|
|
def : ProcNoItin<"arm10tdmi", [ARMv5t]>;
|
|
def : ProcNoItin<"arm1020t", [ARMv5t]>;
|
|
|
|
def : ProcNoItin<"arm9e", [ARMv5te]>;
|
|
def : ProcNoItin<"arm926ej-s", [ARMv5te]>;
|
|
def : ProcNoItin<"arm946e-s", [ARMv5te]>;
|
|
def : ProcNoItin<"arm966e-s", [ARMv5te]>;
|
|
def : ProcNoItin<"arm968e-s", [ARMv5te]>;
|
|
def : ProcNoItin<"arm10e", [ARMv5te]>;
|
|
def : ProcNoItin<"arm1020e", [ARMv5te]>;
|
|
def : ProcNoItin<"arm1022e", [ARMv5te]>;
|
|
def : ProcNoItin<"xscale", [ARMv5te]>;
|
|
def : ProcNoItin<"iwmmxt", [ARMv5te]>;
|
|
|
|
def : Processor<"arm1136j-s", ARMV6Itineraries, [ARMv6]>;
|
|
def : Processor<"arm1136jf-s", ARMV6Itineraries, [ARMv6,
|
|
FeatureVFP2,
|
|
FeatureHasSlowFPVMLx]>;
|
|
|
|
def : Processor<"cortex-m0", ARMV6Itineraries, [ARMv6m]>;
|
|
def : Processor<"cortex-m0plus", ARMV6Itineraries, [ARMv6m]>;
|
|
def : Processor<"cortex-m1", ARMV6Itineraries, [ARMv6m]>;
|
|
def : Processor<"sc000", ARMV6Itineraries, [ARMv6m]>;
|
|
|
|
def : Processor<"arm1176j-s", ARMV6Itineraries, [ARMv6kz]>;
|
|
def : Processor<"arm1176jz-s", ARMV6Itineraries, [ARMv6kz]>;
|
|
def : Processor<"arm1176jzf-s", ARMV6Itineraries, [ARMv6kz,
|
|
FeatureVFP2,
|
|
FeatureHasSlowFPVMLx]>;
|
|
|
|
def : Processor<"mpcorenovfp", ARMV6Itineraries, [ARMv6k]>;
|
|
def : Processor<"mpcore", ARMV6Itineraries, [ARMv6k,
|
|
FeatureVFP2,
|
|
FeatureHasSlowFPVMLx]>;
|
|
|
|
def : Processor<"arm1156t2-s", ARMV6Itineraries, [ARMv6t2]>;
|
|
def : Processor<"arm1156t2f-s", ARMV6Itineraries, [ARMv6t2,
|
|
FeatureVFP2,
|
|
FeatureHasSlowFPVMLx]>;
|
|
|
|
def : ProcessorModel<"cortex-a5", CortexA8Model, [ARMv7a, ProcA5,
|
|
FeatureHasRetAddrStack,
|
|
FeatureTrustZone,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureVMLxForwarding,
|
|
FeatureMP,
|
|
FeatureVFP4]>;
|
|
|
|
def : ProcessorModel<"cortex-a7", CortexA8Model, [ARMv7a, ProcA7,
|
|
FeatureHasRetAddrStack,
|
|
FeatureTrustZone,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHasVMLxHazards,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureVMLxForwarding,
|
|
FeatureMP,
|
|
FeatureVFP4,
|
|
FeatureVirtualization]>;
|
|
|
|
def : ProcessorModel<"cortex-a8", CortexA8Model, [ARMv7a, ProcA8,
|
|
FeatureHasRetAddrStack,
|
|
FeatureNonpipelinedVFP,
|
|
FeatureTrustZone,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHasVMLxHazards,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureVMLxForwarding]>;
|
|
|
|
def : ProcessorModel<"cortex-a9", CortexA9Model, [ARMv7a, ProcA9,
|
|
FeatureHasRetAddrStack,
|
|
FeatureTrustZone,
|
|
FeatureHasVMLxHazards,
|
|
FeatureVMLxForwarding,
|
|
FeatureFP16,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureExpandMLx,
|
|
FeaturePreferVMOVSR,
|
|
FeatureMuxedUnits,
|
|
FeatureNEONForFPMovs,
|
|
FeatureCheckVLDnAlign,
|
|
FeatureMP]>;
|
|
|
|
def : ProcessorModel<"cortex-a12", CortexA9Model, [ARMv7a, ProcA12,
|
|
FeatureHasRetAddrStack,
|
|
FeatureTrustZone,
|
|
FeatureVMLxForwarding,
|
|
FeatureVFP4,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureVirtualization,
|
|
FeatureMP]>;
|
|
|
|
def : ProcessorModel<"cortex-a15", CortexA9Model, [ARMv7a, ProcA15,
|
|
FeatureDontWidenVMOVS,
|
|
FeatureSplatVFPToNeon,
|
|
FeatureHasRetAddrStack,
|
|
FeatureMuxedUnits,
|
|
FeatureTrustZone,
|
|
FeatureVFP4,
|
|
FeatureMP,
|
|
FeatureCheckVLDnAlign,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureVirtualization]>;
|
|
|
|
def : ProcessorModel<"cortex-a17", CortexA9Model, [ARMv7a, ProcA17,
|
|
FeatureHasRetAddrStack,
|
|
FeatureTrustZone,
|
|
FeatureMP,
|
|
FeatureVMLxForwarding,
|
|
FeatureVFP4,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureVirtualization]>;
|
|
|
|
// FIXME: krait has currently the same features as A9 plus VFP4 and HWDiv
|
|
def : ProcessorModel<"krait", CortexA9Model, [ARMv7a, ProcKrait,
|
|
FeatureHasRetAddrStack,
|
|
FeatureMuxedUnits,
|
|
FeatureCheckVLDnAlign,
|
|
FeatureVMLxForwarding,
|
|
FeatureFP16,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureVFP4,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM]>;
|
|
|
|
def : ProcessorModel<"swift", SwiftModel, [ARMv7a, ProcSwift,
|
|
FeatureHasRetAddrStack,
|
|
FeatureNEONForFP,
|
|
FeatureVFP4,
|
|
FeatureUseWideStrideVFP,
|
|
FeatureMP,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureAvoidMOVsShOp,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureHasVMLxHazards,
|
|
FeatureProfUnpredicate,
|
|
FeaturePrefISHSTBarrier,
|
|
FeatureSlowOddRegister,
|
|
FeatureSlowLoadDSubreg,
|
|
FeatureSlowVGETLNi32,
|
|
FeatureSlowVDUP32,
|
|
FeatureUseMISched,
|
|
FeatureNoPostRASched]>;
|
|
|
|
def : ProcessorModel<"cortex-r4", CortexA8Model, [ARMv7r, ProcR4,
|
|
FeatureHasRetAddrStack,
|
|
FeatureAvoidPartialCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-r4f", CortexA8Model, [ARMv7r, ProcR4,
|
|
FeatureHasRetAddrStack,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureVFP3_D16,
|
|
FeatureAvoidPartialCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-r5", CortexA8Model, [ARMv7r, ProcR5,
|
|
FeatureHasRetAddrStack,
|
|
FeatureVFP3_D16,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHWDivARM,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureAvoidPartialCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-r7", CortexA8Model, [ARMv7r, ProcR7,
|
|
FeatureHasRetAddrStack,
|
|
FeatureVFP3_D16,
|
|
FeatureFP16,
|
|
FeatureMP,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHWDivARM,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureAvoidPartialCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-r8", CortexA8Model, [ARMv7r,
|
|
FeatureHasRetAddrStack,
|
|
FeatureVFP3_D16,
|
|
FeatureFP16,
|
|
FeatureMP,
|
|
FeatureSlowFPBrcc,
|
|
FeatureHWDivARM,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureAvoidPartialCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-m3", CortexM4Model, [ARMv7m,
|
|
ProcM3,
|
|
FeaturePrefLoopAlign32,
|
|
FeatureUseMISched,
|
|
FeatureHasNoBranchPredictor]>;
|
|
|
|
def : ProcessorModel<"sc300", CortexM4Model, [ARMv7m,
|
|
ProcM3,
|
|
FeatureUseMISched,
|
|
FeatureHasNoBranchPredictor]>;
|
|
|
|
def : ProcessorModel<"cortex-m4", CortexM4Model, [ARMv7em,
|
|
FeatureVFP4_D16_SP,
|
|
FeaturePrefLoopAlign32,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureUseMISched,
|
|
FeatureHasNoBranchPredictor]>;
|
|
|
|
def : ProcNoItin<"cortex-m7", [ARMv7em,
|
|
FeatureFPARMv8_D16]>;
|
|
|
|
def : ProcNoItin<"cortex-m23", [ARMv8mBaseline,
|
|
FeatureNoMovt]>;
|
|
|
|
def : ProcessorModel<"cortex-m33", CortexM4Model, [ARMv8mMainline,
|
|
FeatureDSP,
|
|
FeatureFPARMv8_D16_SP,
|
|
FeaturePrefLoopAlign32,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureUseMISched,
|
|
FeatureHasNoBranchPredictor]>;
|
|
|
|
def : ProcessorModel<"cortex-m35p", CortexM4Model, [ARMv8mMainline,
|
|
FeatureDSP,
|
|
FeatureFPARMv8_D16_SP,
|
|
FeaturePrefLoopAlign32,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureUseMISched,
|
|
FeatureHasNoBranchPredictor]>;
|
|
|
|
|
|
def : ProcNoItin<"cortex-a32", [ARMv8a,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def : ProcNoItin<"cortex-a35", [ARMv8a, ProcA35,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def : ProcNoItin<"cortex-a53", [ARMv8a, ProcA53,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureFPAO]>;
|
|
|
|
def : ProcNoItin<"cortex-a55", [ARMv82a, ProcA55,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcessorModel<"cortex-a57", CortexA57Model, [ARMv8a, ProcA57,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureFPAO,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureCheapPredicableCPSR]>;
|
|
|
|
def : ProcessorModel<"cortex-a72", CortexA57Model, [ARMv8a, ProcA72,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def : ProcNoItin<"cortex-a73", [ARMv8a, ProcA73,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def : ProcNoItin<"cortex-a75", [ARMv82a, ProcA75,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcNoItin<"cortex-a76", [ARMv82a, ProcA76,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureFullFP16,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcNoItin<"cortex-a76ae", [ARMv82a, ProcA76,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureFullFP16,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcNoItin<"neoverse-n1", [ARMv82a,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcessorModel<"cyclone", SwiftModel, [ARMv8a, ProcSwift,
|
|
FeatureHasRetAddrStack,
|
|
FeatureNEONForFP,
|
|
FeatureVFP4,
|
|
FeatureMP,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureAvoidPartialCPSR,
|
|
FeatureAvoidMOVsShOp,
|
|
FeatureHasSlowFPVMLx,
|
|
FeatureHasSlowFPVFMx,
|
|
FeatureCrypto,
|
|
FeatureUseMISched,
|
|
FeatureZCZeroing,
|
|
FeatureNoPostRASched]>;
|
|
|
|
def : ProcNoItin<"exynos-m3", [ARMv8a, ProcExynos]>;
|
|
def : ProcNoItin<"exynos-m4", [ARMv82a, ProcExynos,
|
|
FeatureFullFP16,
|
|
FeatureDotProd]>;
|
|
def : ProcNoItin<"exynos-m5", [ARMv82a, ProcExynos,
|
|
FeatureFullFP16,
|
|
FeatureDotProd]>;
|
|
|
|
def : ProcNoItin<"kryo", [ARMv8a, ProcKryo,
|
|
FeatureHWDivThumb,
|
|
FeatureHWDivARM,
|
|
FeatureCrypto,
|
|
FeatureCRC]>;
|
|
|
|
def : ProcessorModel<"cortex-r52", CortexR52Model, [ARMv8r, ProcR52,
|
|
FeatureUseMISched,
|
|
FeatureFPAO]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Register File Description
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "ARMRegisterInfo.td"
|
|
include "ARMRegisterBanks.td"
|
|
include "ARMCallingConv.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Descriptions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "ARMInstrInfo.td"
|
|
def ARMInstrInfo : InstrInfo;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Declare the target which we are implementing
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def ARMAsmWriter : AsmWriter {
|
|
string AsmWriterClassName = "InstPrinter";
|
|
int PassSubtarget = 1;
|
|
int Variant = 0;
|
|
bit isMCAsmWriter = 1;
|
|
}
|
|
|
|
def ARMAsmParser : AsmParser {
|
|
bit ReportMultipleNearMisses = 1;
|
|
}
|
|
|
|
def ARMAsmParserVariant : AsmParserVariant {
|
|
int Variant = 0;
|
|
string Name = "ARM";
|
|
string BreakCharacters = ".";
|
|
}
|
|
|
|
def ARM : Target {
|
|
// Pull in Instruction Info.
|
|
let InstructionSet = ARMInstrInfo;
|
|
let AssemblyWriters = [ARMAsmWriter];
|
|
let AssemblyParsers = [ARMAsmParser];
|
|
let AssemblyParserVariants = [ARMAsmParserVariant];
|
|
let AllowRegisterRenaming = 1;
|
|
}
|