Publication Details

High Performance Computing on Low Power Devices

NIKL Vojtěch. High Performance Computing on Low Power Devices. In: Computer achitectures and diagnostics 2016. Brno: Faculty of Information Technology BUT, 2016, pp. 81-84. ISBN 978-80-214-5376-0. Available from: http://www.fit.vutbr.cz/events/pad2016/download/sbornik_pad_2016.pdf
Czech title
Vysoce náročné výpočty na nízkopříkonových zařízeních
Type
conference paper
Language
english
Authors
Nikl Vojtěch, Ing. (DCSY FIT BUT)
URL
Keywords

HPC, parallelism, low power, processor architecture, supercomputers, k-Wave, MPI, OpenMP, performance evaluation, numerical methods, clocking

Abstract

Nowadays, the power efficiency of modern processors is becoming more and more important next to the overall performance itself. Many programming tasks and problems do not scale very well with higher number of cores due to being memory or communication bound, therefore it is often not beneficial to use faster chips to achieve better runtimes. In this case, employing slower low power processors or accelerators may be much more efficient, mainly because it is possible to get the same results using much less energy. Dynamic runtime adjustments applied to the system based on the properties of a given algorithm, such as frequency and voltage scaling or switching off unneeded parts, may further enhance power efficiency. This paper describes the benefits of using low power chips for building an HPC cluster, the group of algorithms where this approach can be useful, possible system adjustments towards better power efficiency, results achieved so far and future plans.

Published
2016
Pages
81-84
Proceedings
Computer achitectures and diagnostics 2016
Conference
Počítačové architektury a diagnostika 2016, Bořetice, CZ
ISBN
978-80-214-5376-0
Publisher
Faculty of Information Technology BUT
Place
Brno, CZ
BibTeX
@INPROCEEDINGS{FITPUB11201,
   author = "Vojt\v{e}ch Nikl",
   title = "High Performance Computing on Low Power Devices",
   pages = "81--84",
   booktitle = "Computer achitectures and diagnostics 2016",
   year = 2016,
   location = "Brno, CZ",
   publisher = "Faculty of Information Technology BUT",
   ISBN = "978-80-214-5376-0",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11201"
}
Back to top