llvm-project/llvm/lib/Target/ARM64/ARM64SchedA53.td

271 lines
13 KiB
TableGen

//=- ARM64SchedA53.td - ARM Cortex-A53 Scheduling Definitions -*- tablegen -*-=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the itinerary class data for the ARM Cortex A53 processors.
//
//===----------------------------------------------------------------------===//
// ===---------------------------------------------------------------------===//
// The following definitions describe the simpler per-operand machine model.
// This works with MachineScheduler. See MCSchedModel.h for details.
// Cortex-A53 machine model for scheduling and other instruction cost heuristics.
def CortexA53Model : SchedMachineModel {
let MicroOpBufferSize = 0; // Explicitly set to zero since A53 is in-order.
let IssueWidth = 2; // 2 micro-ops are dispatched per cycle.
let MinLatency = 1 ; // OperandCycles are interpreted as MinLatency.
let LoadLatency = 3; // Optimistic load latency assuming bypass.
// This is overriden by OperandCycles if the
// Itineraries are queried instead.
let MispredictPenalty = 9; // Based on "Cortex-A53 Software Optimisation
// Specification - Instruction Timings"
// v 1.0 Spreadsheet
}
//===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available.
// Modeling each pipeline as a ProcResource using the BufferSize = 0 since
// Cortex-A53 is in-order.
def A53UnitALU : ProcResource<2> { let BufferSize = 0; } // Int ALU
def A53UnitMAC : ProcResource<1> { let BufferSize = 0; } // Int MAC
def A53UnitDiv : ProcResource<1> { let BufferSize = 0; } // Int Division
def A53UnitLdSt : ProcResource<1> { let BufferSize = 0; } // Load/Store
def A53UnitB : ProcResource<1> { let BufferSize = 0; } // Branch
def A53UnitFPALU : ProcResource<1> { let BufferSize = 0; } // FP ALU
def A53UnitFPMDS : ProcResource<1> { let BufferSize = 0; } // FP Mult/Div/Sqrt
//===----------------------------------------------------------------------===//
// Subtarget-specific SchedWrite types which both map the ProcResources and
// set the latency.
let SchedModel = CortexA53Model in {
// ALU - Despite having a full latency of 4, most of the ALU instructions can
// forward a cycle earlier and then two cycles earlier in the case of a
// shift-only instruction. These latencies will be incorrect when the
// result cannot be forwarded, but modeling isn't rocket surgery.
def : WriteRes<WriteImm, [A53UnitALU]> { let Latency = 3; }
def : WriteRes<WriteI, [A53UnitALU]> { let Latency = 3; }
def : WriteRes<WriteISReg, [A53UnitALU]> { let Latency = 3; }
def : WriteRes<WriteIEReg, [A53UnitALU]> { let Latency = 3; }
def : WriteRes<WriteIS, [A53UnitALU]> { let Latency = 2; }
def : WriteRes<WriteExtr, [A53UnitALU]> { let Latency = 3; }
// MAC
def : WriteRes<WriteIM32, [A53UnitMAC]> { let Latency = 4; }
def : WriteRes<WriteIM64, [A53UnitMAC]> { let Latency = 4; }
// Div
def : WriteRes<WriteID32, [A53UnitDiv]> { let Latency = 4; }
def : WriteRes<WriteID64, [A53UnitDiv]> { let Latency = 4; }
// Load
def : WriteRes<WriteLD, [A53UnitLdSt]> { let Latency = 4; }
def : WriteRes<WriteLDIdx, [A53UnitLdSt]> { let Latency = 4; }
def : WriteRes<WriteLDHi, [A53UnitLdSt]> { let Latency = 4; }
// Vector Load - Vector loads take 1-5 cycles to issue. For the WriteVecLd
// below, choosing the median of 3 which makes the latency 6.
// May model this more carefully in the future. The remaining
// A53WriteVLD# types represent the 1-5 cycle issues explicitly.
def : WriteRes<WriteVLD, [A53UnitLdSt]> { let Latency = 6;
let ResourceCycles = [3]; }
def A53WriteVLD1 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 4; }
def A53WriteVLD2 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 5;
let ResourceCycles = [2]; }
def A53WriteVLD3 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 6;
let ResourceCycles = [3]; }
def A53WriteVLD4 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 7;
let ResourceCycles = [4]; }
def A53WriteVLD5 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 8;
let ResourceCycles = [5]; }
// Pre/Post Indexing - Performed as part of address generation which is already
// accounted for in the WriteST* latencies below
def : WriteRes<WriteAdr, []> { let Latency = 0; }
// Store
def : WriteRes<WriteST, [A53UnitLdSt]> { let Latency = 4; }
def : WriteRes<WriteSTP, [A53UnitLdSt]> { let Latency = 4; }
def : WriteRes<WriteSTIdx, [A53UnitLdSt]> { let Latency = 4; }
def : WriteRes<WriteSTX, [A53UnitLdSt]> { let Latency = 4; }
// Vector Store - Similar to vector loads, can take 1-3 cycles to issue.
def : WriteRes<WriteVST, [A53UnitLdSt]> { let Latency = 5;
let ResourceCycles = [2];}
def A53WriteVST1 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 4; }
def A53WriteVST2 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 5;
let ResourceCycles = [2]; }
def A53WriteVST3 : SchedWriteRes<[A53UnitLdSt]> { let Latency = 6;
let ResourceCycles = [3]; }
// Branch
def : WriteRes<WriteBr, [A53UnitB]>;
def : WriteRes<WriteBrReg, [A53UnitB]>;
def : WriteRes<WriteSys, [A53UnitB]>;
def : WriteRes<WriteBarrier, [A53UnitB]>;
def : WriteRes<WriteHint, [A53UnitB]>;
// FP ALU
def : WriteRes<WriteF, [A53UnitFPALU]> { let Latency = 6; }
def : WriteRes<WriteFCmp, [A53UnitFPALU]> { let Latency = 6; }
def : WriteRes<WriteFCvt, [A53UnitFPALU]> { let Latency = 6; }
def : WriteRes<WriteFCopy, [A53UnitFPALU]> { let Latency = 6; }
def : WriteRes<WriteFImm, [A53UnitFPALU]> { let Latency = 6; }
def : WriteRes<WriteV, [A53UnitFPALU]> { let Latency = 6; }
// FP Mul, Div, Sqrt
def : WriteRes<WriteFMul, [A53UnitFPMDS]> { let Latency = 6; }
def : WriteRes<WriteFDiv, [A53UnitFPMDS]> { let Latency = 33;
let ResourceCycles = [29]; }
def A53WriteFMAC : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 10; }
def A53WriteFDivSP : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 18;
let ResourceCycles = [14]; }
def A53WriteFDivDP : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 33;
let ResourceCycles = [29]; }
def A53WriteFSqrtSP : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 17;
let ResourceCycles = [13]; }
def A53WriteFSqrtDP : SchedWriteRes<[A53UnitFPMDS]> { let Latency = 32;
let ResourceCycles = [28]; }
//===----------------------------------------------------------------------===//
// Subtarget-specific SchedRead types.
// No forwarding for these reads.
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
// ALU - Most operands in the ALU pipes are not needed for two cycles. Shiftable
// operands are needed one cycle later if and only if they are to be
// shifted. Otherwise, they too are needed two cycle later.
def : ReadAdvance<ReadI, 2, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
def A53ReadShifted : SchedReadAdvance<1, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
def A53ReadNotShifted : SchedReadAdvance<2, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
def A53ReadISReg : SchedReadVariant<[
SchedVar<RegShiftedPred, [A53ReadShifted]>,
SchedVar<NoSchedPred, [A53ReadNotShifted]>]>;
def : SchedAlias<ReadISReg, A53ReadISReg>;
def A53ReadIEReg : SchedReadVariant<[
SchedVar<RegShiftedPred, [A53ReadShifted]>,
SchedVar<NoSchedPred, [A53ReadNotShifted]>]>;
def : SchedAlias<ReadIEReg, A53ReadIEReg>;
// MAC - Operands are generally needed one cycle later in the MAC pipe.
// Accumulator operands are needed two cycles later.
def : ReadAdvance<ReadIM, 1, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
def : ReadAdvance<ReadIMA, 2, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
// Div
def : ReadAdvance<ReadID, 1, [WriteImm,WriteI,
WriteISReg, WriteIEReg,WriteIS,
WriteID32,WriteID64,
WriteIM32,WriteIM64]>;
//===----------------------------------------------------------------------===//
// Subtarget-specific InstRWs.
//---
// Miscellaneous
//---
def : InstRW<[WriteI], (instrs COPY)>;
//---
// Vector Mul with Accumulate
//---
//def : InstRW<[WriteIM32, A53ReadIMA], (instregex "^M(ADD|SUB)W.*")>;
//def : InstRW<[WriteIM64, A53ReadIMA], (instregex "^M(ADD|SUB)X.*")>;
//---
// Vector Loads
//---
def : InstRW<[A53WriteVLD1], (instregex "LD1i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVLD1], (instregex "LD1Rv(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD1], (instregex "LD1Onev(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD1Twov(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD3], (instregex "LD1Threev(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD4], (instregex "LD1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD1], (instregex "LD2i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVLD1], (instregex "LD2Rv(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD2Twov(8b|4h|2s)(_POST)?$")>;
def : InstRW<[A53WriteVLD4], (instregex "LD2Twov(16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD3i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD3Rv(8b|4h|2s|1d|16b|8h|4s|2dq)(_POST)?$")>;
def : InstRW<[A53WriteVLD4], (instregex "LD3Threev(8b|4h|2s|1d|16b|8h|4s)(_POST)?$")>;
def : InstRW<[A53WriteVLD3], (instregex "LD3Threev(2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD4i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVLD2], (instregex "LD4Rv(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD5], (instregex "LD4Fourv(8b|4h|2s|1d|16b|8h|4s)(_POST)?$")>;
def : InstRW<[A53WriteVLD4], (instregex "LD4Fourv(2d)(_POST)?$")>;
def : InstRW<[A53WriteVLD1, A53WriteVLD1], (instregex "LDN?PS.*$")>;
def : InstRW<[A53WriteVLD2, A53WriteVLD2], (instregex "LDN?PD.*$")>;
def : InstRW<[A53WriteVLD4, A53WriteVLD4], (instregex "LDN?PQ.*$")>;
//---
// Vector Stores
//---
def : InstRW<[A53WriteVST1], (instregex "ST1i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVST1], (instregex "ST1Onev(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVST1], (instregex "ST1Twov(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST1Threev(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST1Fourv(8b|4h|2s|1d|16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVST1], (instregex "ST2i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVST1], (instregex "ST2Twov(8b|4h|2s)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST2Twov(16b|8h|4s|2d)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST3i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVST3], (instregex "ST3Threev(8b|4h|2s|1d|16b|8h|4s)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST3Threev(2d)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST4i(8|16|32|64)(_POST)?$")>;
def : InstRW<[A53WriteVST3], (instregex "ST4Fourv(8b|4h|2s|1d|16b|8h|4s)(_POST)?$")>;
def : InstRW<[A53WriteVST2], (instregex "ST4Fourv(2d)(_POST)?$")>;
def : InstRW<[A53WriteVST1], (instregex "STN?P(S|D).*$")>;
def : InstRW<[A53WriteVST2], (instregex "STN?PQ.*$")>;
//---
// Floating Point MAC, DIV, SQRT
//---
def : InstRW<[A53WriteFMAC], (instregex "^FN?M(ADD|SUB).*")>;
def : InstRW<[A53WriteFMAC], (instregex "^FML(A|S).*")>;
def : InstRW<[A53WriteFDivSP], (instrs FDIVSrr)>;
def : InstRW<[A53WriteFDivDP], (instrs FDIVDrr)>;
def : InstRW<[A53WriteFDivSP], (instregex "^FDIVv.*32$")>;
def : InstRW<[A53WriteFDivDP], (instregex "^FDIVv.*64$")>;
def : InstRW<[A53WriteFSqrtSP], (instregex "^.*SQRT.*32$")>;
def : InstRW<[A53WriteFSqrtDP], (instregex "^.*SQRT.*64$")>;
}