1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00
llvm-mirror/lib/Target/AArch64/AArch64SchedFalkor.td
Cullen Rhodes e25a1a8f41 [AArch64] Add target features for Armv9-A Scalable Matrix Extension (SME)
First patch in a series adding MC layer support for the Arm Scalable
Matrix Extension.

This patch adds the following features:

    sme, sme-i64, sme-f64

The sme-i64 and sme-f64 flags are for the optional I16I64 and F64F64
features.

If a target supports I16I64 then the following instructions are
implemented:

  * 64-bit integer ADDHA and ADDVA variants (D105570).
  * SMOPA, SMOPS, SUMOPA, SUMOPS, UMOPA, UMOPS, USMOPA, and USMOPS
    instructions that accumulate 16-bit integer outer products into 64-bit
    integer tiles.

If a target supports F64F64 then the FMOPA and FMOPS instructions that
accumulate double-precision floating-point outer products into
double-precision tiles are implemented.

Outer products are implemented in D105571.

The reference can be found here:
https://developer.arm.com/documentation/ddi0602/2021-06

Reviewed By: CarolineConcatto

Differential Revision: https://reviews.llvm.org/D105569
2021-07-12 13:28:10 +00:00

120 lines
5.4 KiB
TableGen

//==- AArch64SchedFalkor.td - Falkor Scheduling Definitions -*- 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 Qualcomm Falkor to support
// instruction scheduling and other instruction cost heuristics.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Define the SchedMachineModel and provide basic properties for coarse grained
// instruction cost model.
def FalkorModel : SchedMachineModel {
let IssueWidth = 8; // 8 uops are dispatched per cycle.
let MicroOpBufferSize = 128; // Out-of-order with temporary unified issue buffer.
let LoopMicroOpBufferSize = 16;
let LoadLatency = 3; // Optimistic load latency.
let MispredictPenalty = 11; // Minimum branch misprediction penalty.
let CompleteModel = 1;
list<Predicate> UnsupportedFeatures = !listconcat(SVEUnsupported.F,
PAUnsupported.F,
SMEUnsupported.F);
// FIXME: Remove when all errors have been fixed.
let FullInstRWOverlapCheck = 0;
}
//===----------------------------------------------------------------------===//
// Define each kind of processor resource and number available on Falkor.
let SchedModel = FalkorModel in {
def FalkorUnitB : ProcResource<1>; // Branch
def FalkorUnitLD : ProcResource<1>; // Load pipe
def FalkorUnitSD : ProcResource<1>; // Store data
def FalkorUnitST : ProcResource<1>; // Store pipe
def FalkorUnitX : ProcResource<1>; // Complex arithmetic
def FalkorUnitY : ProcResource<1>; // Simple arithmetic
def FalkorUnitZ : ProcResource<1>; // Simple arithmetic
def FalkorUnitVSD : ProcResource<1>; // Vector store data
def FalkorUnitVX : ProcResource<1>; // Vector X-pipe
def FalkorUnitVY : ProcResource<1>; // Vector Y-pipe
def FalkorUnitGTOV : ProcResource<1>; // Scalar to Vector
def FalkorUnitVTOG : ProcResource<1>; // Vector to Scalar
// Define the resource groups.
def FalkorUnitXY : ProcResGroup<[FalkorUnitX, FalkorUnitY]>;
def FalkorUnitXYZ : ProcResGroup<[FalkorUnitX, FalkorUnitY, FalkorUnitZ]>;
def FalkorUnitXYZB : ProcResGroup<[FalkorUnitX, FalkorUnitY, FalkorUnitZ,
FalkorUnitB]>;
def FalkorUnitZB : ProcResGroup<[FalkorUnitZ, FalkorUnitB]>;
def FalkorUnitVXVY : ProcResGroup<[FalkorUnitVX, FalkorUnitVY]>;
}
//===----------------------------------------------------------------------===//
// Map the target-defined scheduler read/write resources and latency for
// Falkor.
let SchedModel = FalkorModel in {
// These WriteRes entries are not used in the Falkor sched model.
def : WriteRes<WriteImm, []> { let Unsupported = 1; }
def : WriteRes<WriteI, []> { let Unsupported = 1; }
def : WriteRes<WriteISReg, []> { let Unsupported = 1; }
def : WriteRes<WriteIEReg, []> { let Unsupported = 1; }
def : WriteRes<WriteExtr, []> { let Unsupported = 1; }
def : WriteRes<WriteIS, []> { let Unsupported = 1; }
def : WriteRes<WriteID32, []> { let Unsupported = 1; }
def : WriteRes<WriteID64, []> { let Unsupported = 1; }
def : WriteRes<WriteIM32, []> { let Unsupported = 1; }
def : WriteRes<WriteIM64, []> { let Unsupported = 1; }
def : WriteRes<WriteBr, []> { let Unsupported = 1; }
def : WriteRes<WriteBrReg, []> { let Unsupported = 1; }
def : WriteRes<WriteLD, []> { let Unsupported = 1; }
def : WriteRes<WriteST, []> { let Unsupported = 1; }
def : WriteRes<WriteSTP, []> { let Unsupported = 1; }
def : WriteRes<WriteAdr, []> { let Unsupported = 1; }
def : WriteRes<WriteLDIdx, []> { let Unsupported = 1; }
def : WriteRes<WriteSTIdx, []> { let Unsupported = 1; }
def : WriteRes<WriteF, []> { let Unsupported = 1; }
def : WriteRes<WriteFCmp, []> { let Unsupported = 1; }
def : WriteRes<WriteFCvt, []> { let Unsupported = 1; }
def : WriteRes<WriteFCopy, []> { let Unsupported = 1; }
def : WriteRes<WriteFImm, []> { let Unsupported = 1; }
def : WriteRes<WriteFMul, []> { let Unsupported = 1; }
def : WriteRes<WriteFDiv, []> { let Unsupported = 1; }
def : WriteRes<WriteV, []> { let Unsupported = 1; }
def : WriteRes<WriteVLD, []> { let Unsupported = 1; }
def : WriteRes<WriteVST, []> { let Unsupported = 1; }
def : WriteRes<WriteSys, []> { let Unsupported = 1; }
def : WriteRes<WriteBarrier, []> { let Unsupported = 1; }
def : WriteRes<WriteHint, []> { let Unsupported = 1; }
def : WriteRes<WriteLDHi, []> { let Unsupported = 1; }
def : WriteRes<WriteAtomic, []> { let Unsupported = 1; }
// These ReadAdvance entries are not used in the Falkor sched model.
def : ReadAdvance<ReadI, 0>;
def : ReadAdvance<ReadISReg, 0>;
def : ReadAdvance<ReadIEReg, 0>;
def : ReadAdvance<ReadIM, 0>;
def : ReadAdvance<ReadIMA, 0>;
def : ReadAdvance<ReadID, 0>;
def : ReadAdvance<ReadExtrHi, 0>;
def : ReadAdvance<ReadAdrBase, 0>;
def : ReadAdvance<ReadVLD, 0>;
// Detailed Refinements
// -----------------------------------------------------------------------------
include "AArch64SchedFalkorDetails.td"
}