forked from OSchip/llvm-project
875 lines
43 KiB
TableGen
875 lines
43 KiB
TableGen
//=- AArch64SchedExynosM3.td - Samsung Exynos M3 Sched Defs --*- 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file defines the machine model for the Samsung Exynos M3 to support
|
|
// instruction scheduling and other instruction cost heuristics.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// The Exynos-M3 is an advanced superscalar microprocessor with a 6-wide
|
|
// in-order stage for decode and dispatch and a wider issue stage.
|
|
// The execution units and loads and stores are out-of-order.
|
|
|
|
def ExynosM3Model : SchedMachineModel {
|
|
let IssueWidth = 6; // Up to 6 uops per cycle.
|
|
let MicroOpBufferSize = 228; // ROB size.
|
|
let LoopMicroOpBufferSize = 40; // Based on the instruction queue size.
|
|
let LoadLatency = 4; // Optimistic load cases.
|
|
let MispredictPenalty = 16; // Minimum branch misprediction penalty.
|
|
let CompleteModel = 1; // Use the default model otherwise.
|
|
|
|
list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
|
|
PAUnsupported.F);
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Define each kind of processor resource and number available on the Exynos-M3,
|
|
// which has 12 pipelines, each with its own queue with out-of-order dispatch.
|
|
|
|
let SchedModel = ExynosM3Model in {
|
|
|
|
def M3UnitA : ProcResource<2>; // Simple integer
|
|
def M3UnitC : ProcResource<2>; // Simple and complex integer
|
|
def M3UnitD : ProcResource<1>; // Integer division (inside C0, serialized)
|
|
def M3UnitB : ProcResource<2>; // Branch
|
|
def M3UnitL : ProcResource<2>; // Load
|
|
def M3UnitS : ProcResource<1>; // Store
|
|
def M3PipeF0 : ProcResource<1>; // FP #0
|
|
let Super = M3PipeF0 in {
|
|
def M3UnitFMAC0 : ProcResource<1>; // FP multiplication
|
|
def M3UnitFADD0 : ProcResource<1>; // Simple FP
|
|
def M3UnitFCVT0 : ProcResource<1>; // FP conversion
|
|
def M3UnitFSQR : ProcResource<2>; // FP square root (serialized)
|
|
def M3UnitNALU0 : ProcResource<1>; // Simple vector
|
|
def M3UnitNMSC : ProcResource<1>; // FP and vector miscellanea
|
|
def M3UnitNSHT0 : ProcResource<1>; // Vector shifting
|
|
def M3UnitNSHF0 : ProcResource<1>; // Vector shuffling
|
|
}
|
|
def M3PipeF1 : ProcResource<1>; // FP #1
|
|
let Super = M3PipeF1 in {
|
|
def M3UnitFMAC1 : ProcResource<1>; // FP multiplication
|
|
def M3UnitFADD1 : ProcResource<1>; // Simple FP
|
|
def M3UnitFDIV0 : ProcResource<2>; // FP division (serialized)
|
|
def M3UnitFCVT1 : ProcResource<1>; // FP conversion
|
|
def M3UnitFST0 : ProcResource<1>; // FP store
|
|
def M3UnitNALU1 : ProcResource<1>; // Simple vector
|
|
def M3UnitNCRY0 : ProcResource<1>; // Cryptographic
|
|
def M3UnitNMUL : ProcResource<1>; // Vector multiplication
|
|
def M3UnitNSHT1 : ProcResource<1>; // Vector shifting
|
|
def M3UnitNSHF1 : ProcResource<1>; // Vector shuffling
|
|
}
|
|
def M3PipeF2 : ProcResource<1>; // FP #2
|
|
let Super = M3PipeF2 in {
|
|
def M3UnitFMAC2 : ProcResource<1>; // FP multiplication
|
|
def M3UnitFADD2 : ProcResource<1>; // Simple FP
|
|
def M3UnitFDIV1 : ProcResource<2>; // FP division (serialized)
|
|
def M3UnitFST1 : ProcResource<1>; // FP store
|
|
def M3UnitNALU2 : ProcResource<1>; // Simple vector
|
|
def M3UnitNCRY1 : ProcResource<1>; // Cryptographic
|
|
def M3UnitNSHT2 : ProcResource<1>; // Vector shifting
|
|
def M3UnitNSHF2 : ProcResource<1>; // Vector shuffling
|
|
}
|
|
|
|
|
|
def M3UnitALU : ProcResGroup<[M3UnitA,
|
|
M3UnitC]>;
|
|
def M3UnitFMAC : ProcResGroup<[M3UnitFMAC0,
|
|
M3UnitFMAC1,
|
|
M3UnitFMAC2]>;
|
|
def M3UnitFADD : ProcResGroup<[M3UnitFADD0,
|
|
M3UnitFADD1,
|
|
M3UnitFADD2]>;
|
|
def M3UnitFDIV : ProcResGroup<[M3UnitFDIV0,
|
|
M3UnitFDIV1]>;
|
|
def M3UnitFCVT : ProcResGroup<[M3UnitFCVT0,
|
|
M3UnitFCVT1]>;
|
|
def M3UnitFST : ProcResGroup<[M3UnitFST0,
|
|
M3UnitFST1]>;
|
|
def M3UnitNALU : ProcResGroup<[M3UnitNALU0,
|
|
M3UnitNALU1,
|
|
M3UnitNALU2]>;
|
|
def M3UnitNCRY : ProcResGroup<[M3UnitNCRY0,
|
|
M3UnitNCRY1]>;
|
|
def M3UnitNSHT : ProcResGroup<[M3UnitNSHT0,
|
|
M3UnitNSHT1,
|
|
M3UnitNSHT2]>;
|
|
def M3UnitNSHF : ProcResGroup<[M3UnitNSHF0,
|
|
M3UnitNSHF1,
|
|
M3UnitNSHF2]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Coarse scheduling model.
|
|
|
|
def M3WriteZ0 : SchedWriteRes<[]> { let Latency = 0;
|
|
let NumMicroOps = 1; }
|
|
def M3WriteZ1 : SchedWriteRes<[]> { let Latency = 1;
|
|
let NumMicroOps = 0; }
|
|
|
|
def M3WriteA1 : SchedWriteRes<[M3UnitALU]> { let Latency = 1; }
|
|
def M3WriteAA : SchedWriteRes<[M3UnitALU]> { let Latency = 2;
|
|
let ResourceCycles = [2]; }
|
|
def M3WriteAB : SchedWriteRes<[M3UnitALU,
|
|
M3UnitC]> { let Latency = 1;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteAC : SchedWriteRes<[M3UnitALU,
|
|
M3UnitALU,
|
|
M3UnitC]> { let Latency = 2;
|
|
let NumMicroOps = 3; }
|
|
def M3WriteAD : SchedWriteRes<[M3UnitALU,
|
|
M3UnitC]> { let Latency = 2;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteC1 : SchedWriteRes<[M3UnitC]> { let Latency = 1; }
|
|
def M3WriteC2 : SchedWriteRes<[M3UnitC]> { let Latency = 2; }
|
|
def M3WriteAU : SchedWriteVariant<[SchedVar<IsCopyIdiomPred, [M3WriteZ0]>,
|
|
SchedVar<ExynosArithPred, [M3WriteA1]>,
|
|
SchedVar<ExynosLogicPred, [M3WriteA1]>,
|
|
SchedVar<NoSchedPred, [M3WriteAA]>]>;
|
|
def M3WriteAV : SchedWriteVariant<[SchedVar<IsCopyIdiomPred, [M3WriteZ0]>,
|
|
SchedVar<ExynosArithPred, [M3WriteA1]>,
|
|
SchedVar<NoSchedPred, [M3WriteAA]>]>;
|
|
def M3WriteAW : SchedWriteVariant<[SchedVar<IsZeroIdiomPred, [M3WriteZ0]>,
|
|
SchedVar<ExynosLogicPred, [M3WriteA1]>,
|
|
SchedVar<NoSchedPred, [M3WriteAA]>]>;
|
|
def M3WriteAX : SchedWriteVariant<[SchedVar<ExynosArithPred, [M3WriteA1]>,
|
|
SchedVar<ExynosLogicPred, [M3WriteA1]>,
|
|
SchedVar<NoSchedPred, [M3WriteAA]>]>;
|
|
def M3WriteAY : SchedWriteVariant<[SchedVar<ExynosRotateRightImmPred, [M3WriteA1]>,
|
|
SchedVar<NoSchedPred, [M3WriteAA]>]>;
|
|
|
|
def M3WriteB1 : SchedWriteRes<[M3UnitB]> { let Latency = 1; }
|
|
def M3WriteBX : SchedWriteVariant<[SchedVar<ExynosBranchLinkLRPred, [M3WriteAC]>,
|
|
SchedVar<NoSchedPred, [M3WriteAB]>]>;
|
|
|
|
def M3WriteL4 : SchedWriteRes<[M3UnitL]> { let Latency = 4; }
|
|
def M3WriteL5 : SchedWriteRes<[M3UnitL]> { let Latency = 5; }
|
|
def M3WriteLA : SchedWriteRes<[M3UnitL,
|
|
M3UnitL]> { let Latency = 5;
|
|
let NumMicroOps = 1; }
|
|
def M3WriteLB : SchedWriteRes<[M3UnitA,
|
|
M3UnitL]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteLC : SchedWriteRes<[M3UnitA,
|
|
M3UnitL,
|
|
M3UnitL]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteLD : SchedWriteRes<[M3UnitA,
|
|
M3UnitL]> { let Latency = 4;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteLE : SchedWriteRes<[M3UnitA,
|
|
M3UnitL]> { let Latency = 6;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteLH : SchedWriteRes<[]> { let Latency = 5;
|
|
let NumMicroOps = 0; }
|
|
def M3WriteLX : SchedWriteVariant<[SchedVar<ExynosScaledIdxPred, [M3WriteL5]>,
|
|
SchedVar<NoSchedPred, [M3WriteL4]>]>;
|
|
def M3WriteLY : SchedWriteVariant<[SchedVar<ExynosScaledIdxPred, [M3WriteLE]>,
|
|
SchedVar<NoSchedPred, [M3WriteL5]>]>;
|
|
|
|
def M3WriteS1 : SchedWriteRes<[M3UnitS]> { let Latency = 1; }
|
|
def M3WriteSA : SchedWriteRes<[M3UnitA,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 3;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteSB : SchedWriteRes<[M3UnitA,
|
|
M3UnitS]> { let Latency = 2;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteSC : SchedWriteRes<[M3UnitA,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 1;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteSY : SchedWriteVariant<[SchedVar<ExynosScaledIdxPred, [M3WriteSA]>,
|
|
SchedVar<NoSchedPred, [WriteVST]>]>;
|
|
|
|
def M3ReadAdrBase : SchedReadVariant<[SchedVar<ExynosScaledIdxPred, [ReadDefault]>,
|
|
SchedVar<NoSchedPred, [ReadDefault]>]>;
|
|
|
|
// Branch instructions.
|
|
def : SchedAlias<WriteBr, M3WriteZ0>;
|
|
def : SchedAlias<WriteBrReg, M3WriteC1>;
|
|
|
|
// Arithmetic and logical integer instructions.
|
|
def : SchedAlias<WriteI, M3WriteA1>;
|
|
def : SchedAlias<WriteISReg, M3WriteA1>;
|
|
def : SchedAlias<WriteIEReg, M3WriteA1>;
|
|
def : SchedAlias<WriteIS, M3WriteA1>;
|
|
|
|
// Move instructions.
|
|
def : SchedAlias<WriteImm, M3WriteA1>;
|
|
|
|
// Divide and multiply instructions.
|
|
def : WriteRes<WriteID32, [M3UnitC,
|
|
M3UnitD]> { let Latency = 12;
|
|
let ResourceCycles = [1, 12]; }
|
|
def : WriteRes<WriteID64, [M3UnitC,
|
|
M3UnitD]> { let Latency = 21;
|
|
let ResourceCycles = [1, 21]; }
|
|
def : WriteRes<WriteIM32, [M3UnitC]> { let Latency = 3; }
|
|
def : WriteRes<WriteIM64, [M3UnitC]> { let Latency = 4;
|
|
let ResourceCycles = [2]; }
|
|
|
|
// Miscellaneous instructions.
|
|
def : SchedAlias<WriteExtr, M3WriteAY>;
|
|
|
|
// Addressing modes.
|
|
def : SchedAlias<WriteAdr, M3WriteZ1>;
|
|
def : SchedAlias<ReadAdrBase, M3ReadAdrBase>;
|
|
|
|
// Load instructions.
|
|
def : SchedAlias<WriteLD, M3WriteL4>;
|
|
def : WriteRes<WriteLDHi, []> { let Latency = 4;
|
|
let NumMicroOps = 0; }
|
|
def : SchedAlias<WriteLDIdx, M3WriteLB>;
|
|
|
|
// Store instructions.
|
|
def : SchedAlias<WriteST, M3WriteS1>;
|
|
def : SchedAlias<WriteSTP, M3WriteS1>;
|
|
def : SchedAlias<WriteSTX, M3WriteS1>;
|
|
def : SchedAlias<WriteSTIdx, M3WriteSB>;
|
|
|
|
// FP data instructions.
|
|
def : WriteRes<WriteF, [M3UnitFADD]> { let Latency = 2; }
|
|
def : WriteRes<WriteFCmp, [M3UnitNMSC]> { let Latency = 2; }
|
|
def : WriteRes<WriteFDiv, [M3UnitFDIV]> { let Latency = 12;
|
|
let ResourceCycles = [12]; }
|
|
def : WriteRes<WriteFMul, [M3UnitFMAC]> { let Latency = 4; }
|
|
|
|
// FP miscellaneous instructions.
|
|
def : WriteRes<WriteFCvt, [M3UnitFCVT]> { let Latency = 3; }
|
|
def : WriteRes<WriteFImm, [M3UnitNALU]> { let Latency = 1; }
|
|
def : WriteRes<WriteFCopy, [M3UnitNALU]> { let Latency = 1; }
|
|
|
|
// FP load instructions.
|
|
def : SchedAlias<WriteVLD, M3WriteL5>;
|
|
|
|
// FP store instructions.
|
|
def : WriteRes<WriteVST, [M3UnitS,
|
|
M3UnitFST]> { let Latency = 1;
|
|
let NumMicroOps = 1; }
|
|
|
|
// ASIMD FP instructions.
|
|
def : WriteRes<WriteV, [M3UnitNALU]> { let Latency = 3; }
|
|
|
|
// Other miscellaneous instructions.
|
|
def : WriteRes<WriteAtomic, []> { let Unsupported = 1; }
|
|
def : WriteRes<WriteBarrier, []> { let Latency = 1; }
|
|
def : WriteRes<WriteHint, []> { let Latency = 1; }
|
|
def : WriteRes<WriteSys, []> { let Latency = 1; }
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Generic fast forwarding.
|
|
|
|
// TODO: Add FP register forwarding rules.
|
|
|
|
def : ReadAdvance<ReadI, 0>;
|
|
def : ReadAdvance<ReadISReg, 0>;
|
|
def : ReadAdvance<ReadIEReg, 0>;
|
|
def : ReadAdvance<ReadIM, 0>;
|
|
// TODO: The forwarding for 32 bits actually saves 2 cycles.
|
|
def : ReadAdvance<ReadIMA, 3, [WriteIM32, WriteIM64]>;
|
|
def : ReadAdvance<ReadID, 0>;
|
|
def : ReadAdvance<ReadExtrHi, 0>;
|
|
def : ReadAdvance<ReadAdrBase, 0>;
|
|
def : ReadAdvance<ReadVLD, 0>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Finer scheduling model.
|
|
|
|
def M3WriteNEONA : SchedWriteRes<[M3UnitNSHF,
|
|
M3UnitFADD]> { let Latency = 3;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteNEONB : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitFST]> { let Latency = 10;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteNEOND : SchedWriteRes<[M3UnitNSHF,
|
|
M3UnitFST]> { let Latency = 6;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteNEONH : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitS]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteNEONI : SchedWriteRes<[M3UnitNSHF,
|
|
M3UnitS]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteNEONV : SchedWriteRes<[M3UnitFDIV0,
|
|
M3UnitFDIV1]> { let Latency = 7;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [8, 8]; }
|
|
def M3WriteNEONW : SchedWriteRes<[M3UnitFDIV0,
|
|
M3UnitFDIV1]> { let Latency = 12;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [13, 13]; }
|
|
def M3WriteNEONX : SchedWriteRes<[M3UnitFSQR,
|
|
M3UnitFSQR]> { let Latency = 18;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [19, 19]; }
|
|
def M3WriteNEONY : SchedWriteRes<[M3UnitFSQR,
|
|
M3UnitFSQR]> { let Latency = 25;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [26, 26]; }
|
|
def M3WriteNEONZ : SchedWriteRes<[M3UnitNMSC,
|
|
M3UnitNMSC]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteFADD2 : SchedWriteRes<[M3UnitFADD]> { let Latency = 2; }
|
|
def M3WriteFCVT2 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 2; }
|
|
def M3WriteFCVT3 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 3; }
|
|
def M3WriteFCVT3A : SchedWriteRes<[M3UnitFCVT0]> { let Latency = 3; }
|
|
def M3WriteFCVT4A : SchedWriteRes<[M3UnitFCVT0]> { let Latency = 4; }
|
|
def M3WriteFCVT4 : SchedWriteRes<[M3UnitFCVT]> { let Latency = 4; }
|
|
def M3WriteFDIV10 : SchedWriteRes<[M3UnitFDIV]> { let Latency = 7;
|
|
let ResourceCycles = [8]; }
|
|
def M3WriteFDIV12 : SchedWriteRes<[M3UnitFDIV]> { let Latency = 12;
|
|
let ResourceCycles = [13]; }
|
|
def M3WriteFMAC3 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 3; }
|
|
def M3WriteFMAC4 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 4; }
|
|
def M3WriteFMAC5 : SchedWriteRes<[M3UnitFMAC]> { let Latency = 5; }
|
|
def M3WriteFSQR17 : SchedWriteRes<[M3UnitFSQR]> { let Latency = 18;
|
|
let ResourceCycles = [19]; }
|
|
def M3WriteFSQR25 : SchedWriteRes<[M3UnitFSQR]> { let Latency = 25;
|
|
let ResourceCycles = [26]; }
|
|
def M3WriteNALU1 : SchedWriteRes<[M3UnitNALU]> { let Latency = 1; }
|
|
def M3WriteNCRY1A : SchedWriteRes<[M3UnitNCRY0]> { let Latency = 1; }
|
|
def M3WriteNCRY3A : SchedWriteRes<[M3UnitNCRY0]> { let Latency = 3; }
|
|
def M3WriteNCRY5A : SchedWriteRes<[M3UnitNCRY]> { let Latency = 5; }
|
|
def M3WriteNMSC1 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 1; }
|
|
def M3WriteNMSC2 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 2; }
|
|
def M3WriteNMSC3 : SchedWriteRes<[M3UnitNMSC]> { let Latency = 3; }
|
|
def M3WriteNMUL3 : SchedWriteRes<[M3UnitNMUL]> { let Latency = 3; }
|
|
def M3WriteNSHF1 : SchedWriteRes<[M3UnitNSHF]> { let Latency = 1; }
|
|
def M3WriteNSHF3 : SchedWriteRes<[M3UnitNSHF]> { let Latency = 3; }
|
|
def M3WriteNSHT1 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 1; }
|
|
def M3WriteNSHT2 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 2; }
|
|
def M3WriteNSHT3 : SchedWriteRes<[M3UnitNSHT]> { let Latency = 3; }
|
|
def M3WriteVLDA : SchedWriteRes<[M3UnitL,
|
|
M3UnitL]> { let Latency = 5;
|
|
let NumMicroOps = 2; }
|
|
def M3WriteVLDB : SchedWriteRes<[M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL]> { let Latency = 6;
|
|
let NumMicroOps = 3; }
|
|
def M3WriteVLDC : SchedWriteRes<[M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL]> { let Latency = 6;
|
|
let NumMicroOps = 4; }
|
|
def M3WriteVLDD : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU]> { let Latency = 7;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [2, 1]; }
|
|
def M3WriteVLDE : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU]> { let Latency = 6;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [2, 1]; }
|
|
def M3WriteVLDF : SchedWriteRes<[M3UnitL,
|
|
M3UnitL]> { let Latency = 10;
|
|
let NumMicroOps = 2;
|
|
let ResourceCycles = [5, 5]; }
|
|
def M3WriteVLDG : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU]> { let Latency = 7;
|
|
let NumMicroOps = 3;
|
|
let ResourceCycles = [2, 1, 1]; }
|
|
def M3WriteVLDH : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU]> { let Latency = 6;
|
|
let NumMicroOps = 3;
|
|
let ResourceCycles = [2, 1, 1]; }
|
|
def M3WriteVLDI : SchedWriteRes<[M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL]> { let Latency = 12;
|
|
let NumMicroOps = 3;
|
|
let ResourceCycles = [6, 6, 6]; }
|
|
def M3WriteVLDJ : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU,
|
|
M3UnitNALU]> { let Latency = 7;
|
|
let NumMicroOps = 4;
|
|
let ResourceCycles = [2, 1, 1, 1]; }
|
|
def M3WriteVLDK : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU,
|
|
M3UnitNALU,
|
|
M3UnitNALU]> { let Latency = 9;
|
|
let NumMicroOps = 5;
|
|
let ResourceCycles = [4, 1, 1, 1, 1]; }
|
|
def M3WriteVLDL : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU,
|
|
M3UnitL,
|
|
M3UnitNALU]> { let Latency = 6;
|
|
let NumMicroOps = 5;
|
|
let ResourceCycles = [6, 1, 1, 6, 1]; }
|
|
def M3WriteVLDM : SchedWriteRes<[M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU,
|
|
M3UnitL,
|
|
M3UnitNALU,
|
|
M3UnitNALU]> { let Latency = 7;
|
|
let NumMicroOps = 6;
|
|
let ResourceCycles = [6, 1, 1, 6, 1, 1]; }
|
|
def M3WriteVLDN : SchedWriteRes<[M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL,
|
|
M3UnitL]> { let Latency = 14;
|
|
let NumMicroOps = 4;
|
|
let ResourceCycles = [6, 6, 6, 6]; }
|
|
def M3WriteVSTA : WriteSequence<[WriteVST], 2>;
|
|
def M3WriteVSTB : WriteSequence<[WriteVST], 3>;
|
|
def M3WriteVSTC : WriteSequence<[WriteVST], 4>;
|
|
def M3WriteVSTD : SchedWriteRes<[M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 7;
|
|
let NumMicroOps = 4;
|
|
let ResourceCycles = [1, 3, 1, 3]; }
|
|
def M3WriteVSTE : SchedWriteRes<[M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 8;
|
|
let NumMicroOps = 6;
|
|
let ResourceCycles = [1, 3, 1, 3, 1, 3]; }
|
|
def M3WriteVSTF : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitFST,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 15;
|
|
let NumMicroOps = 7;
|
|
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3]; }
|
|
def M3WriteVSTG : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitFST,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 16;
|
|
let NumMicroOps = 9;
|
|
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3, 1, 3]; }
|
|
def M3WriteVSTH : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitFST,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 14;
|
|
let NumMicroOps = 5;
|
|
let ResourceCycles = [1, 3, 3, 1, 3]; }
|
|
def M3WriteVSTI : SchedWriteRes<[M3UnitNALU,
|
|
M3UnitFST,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST,
|
|
M3UnitS,
|
|
M3UnitFST]> { let Latency = 17;
|
|
let NumMicroOps = 9;
|
|
let ResourceCycles = [1, 3, 3, 1, 3, 1, 3, 1, 3]; }
|
|
|
|
// Special cases.
|
|
def M3WriteAES : SchedWriteRes<[M3UnitNCRY]> { let Latency = 1; }
|
|
def M3WriteCOPY : SchedWriteVariant<[SchedVar<ExynosFPPred, [M3WriteNALU1]>,
|
|
SchedVar<NoSchedPred, [M3WriteZ0]>]>;
|
|
def M3WriteMOVI : SchedWriteVariant<[SchedVar<IsZeroFPIdiomPred, [M3WriteZ0]>,
|
|
SchedVar<NoSchedPred, [M3WriteNALU1]>]>;
|
|
|
|
// Fast forwarding.
|
|
def M3ReadAES : SchedReadAdvance<1, [M3WriteAES]>;
|
|
def M3ReadFMAC : SchedReadAdvance<1, [M3WriteFMAC4,
|
|
M3WriteFMAC5]>;
|
|
def M3ReadNMUL : SchedReadAdvance<1, [M3WriteNMUL3]>;
|
|
|
|
// Branch instructions
|
|
def : InstRW<[M3WriteB1], (instrs Bcc)>;
|
|
def : InstRW<[M3WriteA1], (instrs BL)>;
|
|
def : InstRW<[M3WriteBX], (instrs BLR)>;
|
|
def : InstRW<[M3WriteC1], (instregex "^CBN?Z[WX]")>;
|
|
def : InstRW<[M3WriteAD], (instregex "^TBN?Z[WX]")>;
|
|
|
|
// Arithmetic and logical integer instructions.
|
|
def : InstRW<[M3WriteAX], (instregex "^(ADD|AND|BIC|EON|EOR|ORN|SUB)[WX]rs$")>;
|
|
def : InstRW<[M3WriteAU], (instrs ORRWrs, ORRXrs)>;
|
|
def : InstRW<[M3WriteAX], (instregex "^(ADD|SUB)S?[WX]rx(64)?$")>;
|
|
def : InstRW<[M3WriteAX], (instregex "^(ADD|AND|BIC|SUB)S[WX]rs$")>;
|
|
def : InstRW<[M3WriteAV], (instrs ADDWri, ADDXri)>;
|
|
def : InstRW<[M3WriteAW], (instrs ORRWri, ORRXri)>;
|
|
|
|
// Move instructions.
|
|
def : InstRW<[M3WriteCOPY], (instrs COPY)>;
|
|
def : InstRW<[M3WriteZ0], (instrs ADR, ADRP)>;
|
|
def : InstRW<[M3WriteZ0], (instregex "^MOV[NZ][WX]i")>;
|
|
|
|
// Divide and multiply instructions.
|
|
|
|
// Miscellaneous instructions.
|
|
|
|
// Load instructions.
|
|
def : InstRW<[M3WriteLD,
|
|
WriteLDHi,
|
|
WriteAdr], (instregex "^LDP(SW|W|X)(post|pre)")>;
|
|
def : InstRW<[M3WriteLB,
|
|
ReadAdrBase], (instregex "^LDR(BB|SBW|SBX|HH|SHW|SHX|SW|W|X)roW")>;
|
|
def : InstRW<[M3WriteLX,
|
|
ReadAdrBase], (instregex "^LDR(BB|SBW|SBX|HH|SHW|SHX|SW|W|X)roX")>;
|
|
def : InstRW<[M3WriteLB,
|
|
ReadAdrBase], (instrs PRFMroW)>;
|
|
def : InstRW<[M3WriteLX,
|
|
ReadAdrBase], (instrs PRFMroX)>;
|
|
|
|
// Store instructions.
|
|
def : InstRW<[M3WriteSB,
|
|
ReadAdrBase], (instregex "^STR(BB|HH|W|X)roW")>;
|
|
def : InstRW<[WriteST,
|
|
ReadAdrBase], (instregex "^STR(BB|HH|W|X)roX")>;
|
|
|
|
// FP data instructions.
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^FABS[DS]r")>;
|
|
def : InstRW<[M3WriteFADD2], (instregex "^F(ADD|SUB)[DS]rr")>;
|
|
def : InstRW<[M3WriteFDIV10], (instrs FDIVSrr)>;
|
|
def : InstRW<[M3WriteFDIV12], (instrs FDIVDrr)>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^F(MAX|MIN).+rr")>;
|
|
def : InstRW<[M3WriteFMAC3], (instregex "^FN?MUL[DS]rr")>;
|
|
def : InstRW<[M3WriteFMAC4,
|
|
M3ReadFMAC], (instregex "^FN?M(ADD|SUB)[DS]rrr")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FNEG[DS]r")>;
|
|
def : InstRW<[M3WriteFCVT3A], (instregex "^FRINT.+r")>;
|
|
def : InstRW<[M3WriteNEONH], (instregex "^FCSEL[DS]rrr")>;
|
|
def : InstRW<[M3WriteFSQR17], (instrs FSQRTSr)>;
|
|
def : InstRW<[M3WriteFSQR25], (instrs FSQRTDr)>;
|
|
|
|
// FP miscellaneous instructions.
|
|
def : InstRW<[M3WriteFCVT3], (instregex "^FCVT[DHS][DHS]r")>;
|
|
def : InstRW<[M3WriteFCVT4A], (instregex "^[SU]CVTF[SU][XW][DHS]ri")>;
|
|
def : InstRW<[M3WriteFCVT3A], (instregex "^FCVT[AMNPZ][SU]U[XW][DHS]r")>;
|
|
def : InstRW<[M3WriteFCVT3A], (instregex "^FCVTZ[SU][dhs]")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[DS][ir]")>;
|
|
def : InstRW<[M3WriteFCVT4], (instregex "^[FU](RECP|RSQRT)Ev1")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^FRECPXv1")>;
|
|
def : InstRW<[M3WriteFMAC4,
|
|
M3ReadFMAC], (instregex "^F(RECP|RSQRT)S(16|32|64)")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[WX][DS]r")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FMOV[DS][WX]r")>;
|
|
def : InstRW<[M3WriteNEONI], (instregex "^FMOV(DX|XD)Highr")>;
|
|
|
|
// FP load instructions.
|
|
def : InstRW<[WriteVLD], (instregex "^LDR[DSQ]l")>;
|
|
def : InstRW<[WriteVLD], (instregex "^LDUR[BDHSQ]i")>;
|
|
def : InstRW<[WriteVLD,
|
|
WriteAdr], (instregex "^LDR[BDHSQ](post|pre)")>;
|
|
def : InstRW<[WriteVLD], (instregex "^LDR[BDHSQ]ui")>;
|
|
def : InstRW<[M3WriteLE,
|
|
ReadAdrBase], (instregex "^LDR[BDHS]roW")>;
|
|
def : InstRW<[WriteVLD,
|
|
ReadAdrBase], (instregex "^LDR[BDHS]roX")>;
|
|
def : InstRW<[M3WriteLY,
|
|
ReadAdrBase], (instregex "^LDRQro[WX]")>;
|
|
def : InstRW<[WriteVLD,
|
|
M3WriteLH], (instregex "^LDN?P[DS]i")>;
|
|
def : InstRW<[M3WriteLA,
|
|
M3WriteLH], (instregex "^LDN?PQi")>;
|
|
def : InstRW<[M3WriteLB,
|
|
M3WriteLH,
|
|
WriteAdr], (instregex "^LDP[DS](post|pre)")>;
|
|
def : InstRW<[M3WriteLC,
|
|
M3WriteLH,
|
|
WriteAdr], (instregex "^LDPQ(post|pre)")>;
|
|
|
|
// FP store instructions.
|
|
def : InstRW<[WriteVST], (instregex "^STUR[BDHSQ]i")>;
|
|
def : InstRW<[WriteVST,
|
|
WriteAdr], (instregex "^STR[BDHSQ](post|pre)")>;
|
|
def : InstRW<[WriteVST], (instregex "^STR[BDHSQ]ui")>;
|
|
def : InstRW<[M3WriteSA,
|
|
ReadAdrBase], (instregex "^STR[BDHS]roW")>;
|
|
def : InstRW<[M3WriteSA,
|
|
ReadAdrBase], (instregex "^STRQroW")>;
|
|
def : InstRW<[WriteVST,
|
|
ReadAdrBase], (instregex "^STR[BDHS]roX")>;
|
|
def : InstRW<[M3WriteSY,
|
|
ReadAdrBase], (instregex "^STRQroX")>;
|
|
def : InstRW<[WriteVST], (instregex "^STN?P[DSQ]i")>;
|
|
def : InstRW<[WriteVST,
|
|
WriteAdr], (instregex "^STP[DS](post|pre)")>;
|
|
def : InstRW<[M3WriteSC,
|
|
WriteAdr], (instregex "^STPQ(post|pre)")>;
|
|
|
|
// ASIMD instructions.
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]ABAL?v")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^[SU]ABDL?v")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^((SQ)?ABS|SQNEG)v")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^(ADD|NEG|SUB)v")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]?ADDL?Pv")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]H(ADD|SUB)v")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU](ADD|SUB)[LW]V?v")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^R?(ADD|SUB)HN2?v")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]Q(ADD|SUB)v")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^(SU|US)QADDv")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]RHADDv")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^CM(EQ|GE|GT|HI|HS|LE|LT)v")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^CMTSTv")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^(AND|BIC|EOR|MVNI|NOT|ORN|ORR)v")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^[SU](MIN|MAX)v")>;
|
|
def : InstRW<[M3WriteNMSC2], (instregex "^[SU](MIN|MAX)Pv")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU](MIN|MAX)Vv")>;
|
|
def : InstRW<[M3WriteNMUL3], (instregex "^(MUL|SQR?DMULH)v")>;
|
|
def : InstRW<[M3WriteNMUL3,
|
|
M3ReadNMUL], (instregex "^ML[AS]v")>;
|
|
def : InstRW<[M3WriteNMUL3], (instregex "^[SU]ML[AS]Lv")>;
|
|
def : InstRW<[M3WriteNMUL3], (instregex "^SQDML[AS]L")>;
|
|
def : InstRW<[M3WriteNMUL3], (instregex "^(S|U|SQD)MULLv")>;
|
|
def : InstRW<[M3WriteNMSC3], (instregex "^[SU]ADALPv")>;
|
|
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]R?SRAv")>;
|
|
def : InstRW<[M3WriteNSHT1], (instregex "^SHL[dv]")>;
|
|
def : InstRW<[M3WriteNSHT1], (instregex "^[SU]SH[LR][dv]")>;
|
|
def : InstRW<[M3WriteNSHT1], (instregex "^S[RS]I[dv]")>;
|
|
def : InstRW<[M3WriteNSHT2], (instregex "^[SU]?SHLLv")>;
|
|
def : InstRW<[M3WriteNSHT3], (instregex "^(([SU]Q)?R)?SHRU?N[bhsv]")>;
|
|
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]RSH[LR][dv]")>;
|
|
def : InstRW<[M3WriteNSHT3], (instregex "^[SU]QR?SHLU?[bdhsv]")>;
|
|
|
|
// ASIMD FP instructions.
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^FABSv")>;
|
|
def : InstRW<[M3WriteFADD2], (instregex "^F(ABD|ADD|SUB)v")>;
|
|
def : InstRW<[M3WriteNEONA], (instregex "^FADDP")>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^F(AC|CM)(EQ|GE|GT|LE|LT)v[^1]")>;
|
|
def : InstRW<[M3WriteFCVT3], (instregex "^FCVT(L|N|XN)v")>;
|
|
def : InstRW<[M3WriteFCVT2], (instregex "^FCVT[AMNPZ][SU]v")>;
|
|
def : InstRW<[M3WriteFCVT2], (instregex "^[SU]CVTFv")>;
|
|
def : InstRW<[M3WriteFDIV10], (instrs FDIVv2f32)>;
|
|
def : InstRW<[M3WriteNEONV], (instrs FDIVv4f32)>;
|
|
def : InstRW<[M3WriteNEONW], (instrs FDIVv2f64)>;
|
|
def : InstRW<[M3WriteNMSC1], (instregex "^F(MAX|MIN)(NM)?v")>;
|
|
def : InstRW<[M3WriteNMSC2], (instregex "^F(MAX|MIN)(NM)?Pv")>;
|
|
def : InstRW<[M3WriteNEONZ], (instregex "^F(MAX|MIN)(NM)?Vv")>;
|
|
def : InstRW<[M3WriteFMAC3], (instregex "^FMULX?v.[fi]")>;
|
|
def : InstRW<[M3WriteFMAC4,
|
|
M3ReadFMAC], (instregex "^FML[AS]v.f")>;
|
|
def : InstRW<[M3WriteFMAC5,
|
|
M3ReadFMAC], (instregex "^FML[AS]v.i")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FNEGv")>;
|
|
def : InstRW<[M3WriteFCVT3A], (instregex "^FRINT[AIMNPXZ]v")>;
|
|
def : InstRW<[M3WriteFSQR17], (instrs FSQRTv2f32)>;
|
|
def : InstRW<[M3WriteNEONX], (instrs FSQRTv4f32)>;
|
|
def : InstRW<[M3WriteNEONY], (instrs FSQRTv2f64)>;
|
|
|
|
// ASIMD miscellaneous instructions.
|
|
def : InstRW<[M3WriteNALU1], (instregex "^RBITv")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^(BIF|BIT|BSL|BSP)v")>;
|
|
def : InstRW<[M3WriteNEONB], (instregex "^DUPv.+gpr")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^DUPv.+lane")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^EXTv")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^[SU]?Q?XTU?Nv")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^CPY")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^INSv.+lane")>;
|
|
def : InstRW<[M3WriteMOVI], (instregex "^MOVI")>;
|
|
def : InstRW<[M3WriteNALU1], (instregex "^FMOVv")>;
|
|
def : InstRW<[M3WriteFCVT4], (instregex "^[FU](RECP|RSQRT)Ev[248]")>;
|
|
def : InstRW<[M3WriteFMAC4,
|
|
M3ReadFMAC], (instregex "^F(RECP|RSQRT)Sv")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^REV(16|32|64)v")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^TB[LX]v")>;
|
|
def : InstRW<[M3WriteNEOND], (instregex "^[SU]MOVv")>;
|
|
def : InstRW<[M3WriteNSHF3], (instregex "^INSv.+gpr")>;
|
|
def : InstRW<[M3WriteNSHF1], (instregex "^(TRN|UZP|ZIP)[12]v")>;
|
|
|
|
// ASIMD load instructions.
|
|
def : InstRW<[M3WriteL5], (instregex "LD1Onev(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteL5,
|
|
M3WriteA1], (instregex "LD1Onev(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteL5], (instregex "LD1Onev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteL5,
|
|
M3WriteA1], (instregex "LD1Onev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDA], (instregex "LD1Twov(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDA,
|
|
M3WriteA1], (instregex "LD1Twov(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDA], (instregex "LD1Twov(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDA,
|
|
M3WriteA1], (instregex "LD1Twov(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDB], (instregex "LD1Threev(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDB,
|
|
M3WriteA1], (instregex "LD1Threev(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDB], (instregex "LD1Threev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDB,
|
|
M3WriteA1], (instregex "LD1Threev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDC], (instregex "LD1Fourv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDC,
|
|
M3WriteA1], (instregex "LD1Fourv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDC], (instregex "LD1Fourv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDC,
|
|
M3WriteA1], (instregex "LD1Fourv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDD], (instregex "LD1i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVLDD,
|
|
M3WriteA1], (instregex "LD1i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVLDE], (instregex "LD1i(64)$")>;
|
|
def : InstRW<[M3WriteVLDE,
|
|
M3WriteA1], (instregex "LD1i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteL5], (instregex "LD1Rv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteL5,
|
|
M3WriteA1], (instregex "LD1Rv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteL5], (instregex "LD1Rv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteL5,
|
|
M3WriteA1], (instregex "LD1Rv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDF], (instregex "LD2Twov(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVLDF,
|
|
M3WriteA1], (instregex "LD2Twov(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVLDF], (instregex "LD2Twov(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDF,
|
|
M3WriteA1], (instregex "LD2Twov(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDG], (instregex "LD2i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVLDG,
|
|
M3WriteA1], (instregex "LD2i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVLDH], (instregex "LD2i(64)$")>;
|
|
def : InstRW<[M3WriteVLDH,
|
|
M3WriteA1], (instregex "LD2i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDA], (instregex "LD2Rv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDA,
|
|
M3WriteA1], (instregex "LD2Rv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDA], (instregex "LD2Rv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDA,
|
|
M3WriteA1], (instregex "LD2Rv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDI], (instregex "LD3Threev(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVLDI,
|
|
M3WriteA1], (instregex "LD3Threev(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVLDI], (instregex "LD3Threev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDI,
|
|
M3WriteA1], (instregex "LD3Threev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDJ], (instregex "LD3i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVLDJ,
|
|
M3WriteA1], (instregex "LD3i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVLDL], (instregex "LD3i(64)$")>;
|
|
def : InstRW<[M3WriteVLDL,
|
|
M3WriteA1], (instregex "LD3i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDB], (instregex "LD3Rv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDB,
|
|
M3WriteA1], (instregex "LD3Rv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDB], (instregex "LD3Rv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDB,
|
|
M3WriteA1], (instregex "LD3Rv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDN], (instregex "LD4Fourv(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVLDN,
|
|
M3WriteA1], (instregex "LD4Fourv(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVLDN], (instregex "LD4Fourv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDN,
|
|
M3WriteA1], (instregex "LD4Fourv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDK], (instregex "LD4i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVLDK,
|
|
M3WriteA1], (instregex "LD4i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVLDM], (instregex "LD4i(64)$")>;
|
|
def : InstRW<[M3WriteVLDM,
|
|
M3WriteA1], (instregex "LD4i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVLDC], (instregex "LD4Rv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVLDC,
|
|
M3WriteA1], (instregex "LD4Rv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVLDC], (instregex "LD4Rv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVLDC,
|
|
M3WriteA1], (instregex "LD4Rv(16b|8h|4s|2d)_POST")>;
|
|
|
|
// ASIMD store instructions.
|
|
def : InstRW<[WriteVST], (instregex "ST1Onev(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[WriteVST,
|
|
WriteAdr], (instregex "ST1Onev(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[WriteVST], (instregex "ST1Onev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[WriteVST,
|
|
WriteAdr], (instregex "ST1Onev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTA], (instregex "ST1Twov(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVSTA,
|
|
WriteAdr], (instregex "ST1Twov(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVSTA], (instregex "ST1Twov(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTA,
|
|
WriteAdr], (instregex "ST1Twov(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTB], (instregex "ST1Threev(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVSTB,
|
|
WriteAdr], (instregex "ST1Threev(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVSTB], (instregex "ST1Threev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTB,
|
|
WriteAdr], (instregex "ST1Threev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTC], (instregex "ST1Fourv(8b|4h|2s|1d)$")>;
|
|
def : InstRW<[M3WriteVSTC,
|
|
WriteAdr], (instregex "ST1Fourv(8b|4h|2s|1d)_POST")>;
|
|
def : InstRW<[M3WriteVSTC], (instregex "ST1Fourv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTC,
|
|
WriteAdr], (instregex "ST1Fourv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTD], (instregex "ST1i(8|16|32|64)$")>;
|
|
def : InstRW<[M3WriteVSTD,
|
|
WriteAdr], (instregex "ST1i(8|16|32|64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTD], (instregex "ST2Twov(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVSTD,
|
|
WriteAdr], (instregex "ST2Twov(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVSTE], (instregex "ST2Twov(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTE,
|
|
WriteAdr], (instregex "ST2Twov(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTD], (instregex "ST2i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVSTD,
|
|
WriteAdr], (instregex "ST2i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVSTD], (instregex "ST2i(64)$")>;
|
|
def : InstRW<[M3WriteVSTD,
|
|
WriteAdr], (instregex "ST2i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTF], (instregex "ST3Threev(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVSTF,
|
|
WriteAdr], (instregex "ST3Threev(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVSTG], (instregex "ST3Threev(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTG,
|
|
WriteAdr], (instregex "ST3Threev(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTH], (instregex "ST3i(8|16|32)$")>;
|
|
def : InstRW<[M3WriteVSTH,
|
|
WriteAdr], (instregex "ST3i(8|16|32)_POST")>;
|
|
def : InstRW<[M3WriteVSTF], (instregex "ST3i(64)$")>;
|
|
def : InstRW<[M3WriteVSTF,
|
|
WriteAdr], (instregex "ST3i(64)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTF], (instregex "ST4Fourv(8b|4h|2s)$")>;
|
|
def : InstRW<[M3WriteVSTF,
|
|
WriteAdr], (instregex "ST4Fourv(8b|4h|2s)_POST")>;
|
|
def : InstRW<[M3WriteVSTI], (instregex "ST4Fourv(16b|8h|4s|2d)$")>;
|
|
def : InstRW<[M3WriteVSTI,
|
|
WriteAdr], (instregex "ST4Fourv(16b|8h|4s|2d)_POST")>;
|
|
|
|
def : InstRW<[M3WriteVSTF], (instregex "ST4i(8|16|32|64)$")>;
|
|
def : InstRW<[M3WriteVSTF,
|
|
WriteAdr], (instregex "ST4i(8|16|32|64)_POST")>;
|
|
|
|
// Cryptography instructions.
|
|
def : InstRW<[M3WriteAES], (instregex "^AES[DE]")>;
|
|
def : InstRW<[M3WriteAES,
|
|
M3ReadAES], (instregex "^AESI?MC")>;
|
|
|
|
def : InstRW<[M3WriteNCRY3A], (instregex "^PMULL?v")>;
|
|
|
|
def : InstRW<[M3WriteNCRY1A], (instregex "^SHA1([CHMP]|SU[01])")>;
|
|
def : InstRW<[M3WriteNCRY1A], (instregex "^SHA256SU0")>;
|
|
def : InstRW<[M3WriteNCRY5A], (instregex "^SHA256(H2?|SU1)")>;
|
|
|
|
// CRC instructions.
|
|
def : InstRW<[M3WriteC2], (instregex "^CRC32")>;
|
|
|
|
} // SchedModel = ExynosM3Model
|