Home // SIMUL 2013, The Fifth International Conference on Advances in System Simulation // View article

Simulation and Validation of a Heuristic Scheduling Algorithm for Multicore Systems

Authors:
James Docherty
Alex Bystrov
Alex Yakovlev

Keywords: Energy Harvesting; Heuristic Algorithms; Monte Carlo Simulations;

Abstract:
The number of embedded systems used worldwide is increasing rapidly. With each generation of equipment, consumers are expecting more computational power and functionality, meaning current designs can be considered unsuitable. As transistor feature size reaches its atomic limit, manufacturers have moved from single to multi-core environments to bridge the performance gap and continue to meet Moores Law. However, this means job scheduling has become exponentially more complex and is reaching a point where standard algorithms are failing to cope. This paper summarizes the initial work performed creating a heuristic based algorithm that is aware of both requests and available resources and therefore is capable of managing the uncertainty brought about by these factors. The work uses Monte Carlo Simulation combined with multi-vary analysis to identify primary contributors and their contribution to scheduling.

Pages: 47 to 52

Copyright: Copyright (c) IARIA, 2013

Publication date: October 27, 2013

Published in: conference

ISSN: 2308-4537

ISBN: 978-1-61208-308-7

Location: Venice, Italy

Dates: from October 27, 2013 to October 31, 2013