Simulating power scheduling at scale

Daniel Ellsworth, Tapasya Patki, Martin Schulz, Barry Rountree, Allen Malony

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

4 Zitate (Scopus)

Abstract

Comparison of power scheduling strategies at scale is challenging due to the limited availability of high performance computing (HPC) systems exposing power control to researchers. In this paper we describe PowSim, a simulator for comparing different power management strategies at large-scale for HPC systems. PowSim enables light-weight simulation of dynamically-changing hardware-enforced processor power caps at the scale of an HPC cluster, supporting power scheduling research. PowSim’s architecture supports easily changing power scheduler, job scheduler, and application models to enable comparison studies. Preliminary results comparing generalized power scheduling strategies are also presented.

OriginalspracheEnglisch
TitelProceedings of E2SC 2017
Untertitel5th International Workshop on Energy Efficient Supercomputing - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis
Herausgeber (Verlag)Association for Computing Machinery, Inc
ISBN (Print)9781450351324
DOIs
PublikationsstatusVeröffentlicht - 12 Nov. 2017
Extern publiziertJa
Veranstaltung5th International Workshop on Energy Efficient Supercomputing, E2SC 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017 - Denver, USA/Vereinigte Staaten
Dauer: 12 Nov. 201717 Nov. 2017

Publikationsreihe

NameProceedings of E2SC 2017: 5th International Workshop on Energy Efficient Supercomputing - Held in conjunction with SC 2017: The International Conference for High Performance Computing, Networking, Storage and Analysis

Konferenz

Konferenz5th International Workshop on Energy Efficient Supercomputing, E2SC 2017 - Held in conjunction with the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2017
Land/GebietUSA/Vereinigte Staaten
OrtDenver
Zeitraum12/11/1717/11/17

Fingerprint

Untersuchen Sie die Forschungsthemen von „Simulating power scheduling at scale“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren