POW: System-wide dynamic reallocation of limited power in HPC

Daniel A. Ellsworth, Allen D. Malony, Barry Rountree, Martin Schulz

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

29 Zitate (Scopus)

Abstract

Current trends for high-performance computing systems are leading us towards hardware over-provisioning where it is no longer possible to run each component at peak power without exceeding a system or facility wide power bound. In such scenarios, the power consumed by individual components must be artificially limited to guarantee system operation under a given power bound. In this paper, we present the design of a power scheduler capable of enforcing such a bound using dynamic system-wide power reallocation in an application-agnostic manner. Our scheduler achievies better job runtimes than a naïve power scheduling approach without requiring a priori knowledge of application power behavior.

OriginalspracheEnglisch
TitelHPDC 2015 - Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing
Herausgeber (Verlag)Association for Computing Machinery, Inc
Seiten145-148
Seitenumfang4
ISBN (elektronisch)9781450335508
DOIs
PublikationsstatusVeröffentlicht - 15 Juni 2015
Extern publiziertJa
Veranstaltung24th ACM Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015 - Portland, USA/Vereinigte Staaten
Dauer: 15 Juni 201519 Juni 2015

Publikationsreihe

NameHPDC 2015 - Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing

Konferenz

Konferenz24th ACM Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015
Land/GebietUSA/Vereinigte Staaten
OrtPortland
Zeitraum15/06/1519/06/15

Fingerprint

Untersuchen Sie die Forschungsthemen von „POW: System-wide dynamic reallocation of limited power in HPC“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren