Potentials and Limitations for Energy Efficiency Auto-Tuning

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in Buch/Sammelband/GutachtenBeigetragenBegutachtung

Abstract

With an objective target of 20 MW for an Exascale system, the power budget for future super computers has a severe restriction. Fortunately, current hardware and runtime environments feature various adjustable parameters that can be changed at runtime in order to confine the power usage. We present an overview of the potentials and limitations of several power saving mechanisms and describe the integration of energy efficiency optimizations in existing performance analysis tools. We also introduce an energy efficiency tuning cycle and exemplify its usage.

Details

OriginalspracheEnglisch
TitelParallel Computing: Accelerating Computational Sciene and Engineering (CSE)
Redakteure/-innenMichael Bader, Arndt Bode, Hans-Joachim Bungartz, Michael Gerndt, Gerhard R. Joubert, Frans Peters
Herausgeber (Verlag)IOS Press, Amsterdam [u. a.]
Seiten678-687
Seitenumfang10
Band25
ISBN (Print)978-1-61499-381-3
PublikationsstatusVeröffentlicht - 1 Dez. 2013
Peer-Review-StatusJa

Konferenz

TitelInternational Conference on Parallel Computing 2013
KurztitelParCo 2013
Dauer10 - 13 September 2013
Webseite
BekanntheitsgradInternationale Veranstaltung
OrtTechnische Universität München
StadtMünchen
LandDeutschland

Externe IDs

Scopus 84902284275
ORCID /0009-0003-0666-4166/work/151475604

Schlagworte

Ziele für nachhaltige Entwicklung