NOMeS: Near-Optimal Metaheuristic Scheduling for MPSoCs

A4 Conference proceedings


Internal Authors/Editors


Publication Details

List of Authors: Amin Majd, Masoud Daneshtalab, Juha Plosila, Nima Khalilzad, Golnaz Sahebi, Elena Troubitsyna
Publication year: 2018
Publisher: IEEE
Book title: 2017 19th International Symposium on Computer Architecture and Digital Systems (CADS)
Start page: 70
End page: 75
ISBN: 978-1-5386-4380-8
eISBN: 978-1-5386-4379-2


Abstract

The task scheduling problem for Multiprocessor
System-on-Chips (MPSoC), which plays a vital role in performance, is an NP-hard
problem. Exploring the whole search space in order to find the optimal solution
is not time efficient, thus metaheuristics are mostly used to find a
near-optimal solution in a reasonable amount of time. We propose a novel metaheuristic
method for near-optimal scheduling that can provide performance guarantees for
multiple applications implemented on a shared platform. Applications are
represented as directed acyclic task graphs (DAG) and are executed on an MPSoC
platform with given communication costs. We introduce a novel multi-population
method inspired by both genetic and imperialist competitive algorithms. It is specialized
for the scheduling problem with the goal to improve the convergence policy and
selection pressure. The potential of the approach is demonstrated by
experiments using a Sobel filter, a SUSAN filter, RASTA-PLP and JPEG encoder as
real-world case studies.


Last updated on 2019-16-07 at 05:44