Toggle Main Menu Toggle Search

Open Access padlockePrints

Using Machine Learning in Trace-driven Energy-Aware Simulations of High-Throughput Computing Systems

Lookup NU author(s): Dr Stephen McGough, Dr Matthew ForshawORCiD

Downloads


Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by ACM, 2017.

For re-use rights please refer to the publisher's terms and conditions.


Abstract

© 2017 ACM. When performing a trace-driven simulation of a High Through- put Computing system we are limited to the knowledge which should be available to the system at the current point within the simulation. However, the trace-log contains information we would not be privy to during the simulation. Through the use of Machine Learning we can extract the latent patterns within the trace-log allowing us to accurately predict characteristics of tasks based only on the information we would know. These characteristics will allow us to make better decisions within simulations allowing us to derive better policies for saving energy. We demonstrate that we can accurately predict (up-To 99% accuracy), using oversampling and deep learning, those tasks which will complete while at the same time provide accurate predictions for the task execution time and memory footprint using Random Forest Regression.


Publication metadata

Author(s): McGough AS, Moubayed NA, Forshaw M

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: ICPE 2017 Companion: Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering

Year of Conference: 2017

Pages: 55-60

Online publication date: 18/04/2017

Acceptance date: 02/04/2016

Date deposited: 10/07/2017

Publisher: ACM

URL: https://doi.org/10.1145/3053600.3053612

DOI: 10.1145/3053600.3053612

Library holdings: Search Newcastle University Library for this item

ISBN: 9781450348997


Share