Potentials and Limitations for Energy Efficiency Auto-Tuning
Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/Gutachten › Beitrag in Buch/Sammelband/Gutachten › Beigetragen › Begutachtung
Beitragende
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
Originalsprache | Englisch |
---|---|
Titel | Parallel Computing: Accelerating Computational Sciene and Engineering (CSE) |
Redakteure/-innen | Michael Bader, Arndt Bode, Hans-Joachim Bungartz, Michael Gerndt, Gerhard R. Joubert, Frans Peters |
Herausgeber (Verlag) | IOS Press, Amsterdam [u. a.] |
Seiten | 678-687 |
Seitenumfang | 10 |
Band | 25 |
ISBN (Print) | 978-1-61499-381-3 |
Publikationsstatus | Veröffentlicht - 1 Dez. 2013 |
Peer-Review-Status | Ja |
Konferenz
Titel | International Conference on Parallel Computing 2013 |
---|---|
Kurztitel | ParCo 2013 |
Dauer | 10 - 13 September 2013 |
Webseite | |
Bekanntheitsgrad | Internationale Veranstaltung |
Ort | Technische Universität München |
Stadt | München |
Land | Deutschland |
Externe IDs
Scopus | 84902284275 |
---|---|
ORCID | /0009-0003-0666-4166/work/151475604 |