A network contention model for the extreme-scale simulator

Christian Engelmann; Thomas Naughton

doi:10.2316/P.2015.826-043

A network contention model for the extreme-scale simulator

Christian Engelmann, Thomas Naughton

Intelligent Systems and Facilities

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The Extreme-scale Simulator (xSim) is a performance investigation toolkit for high-performance computing (HPC) hardware/software co-design. It permits running a HPC application with millions of concurrent execution threads, while observing its performance in a simulated extreme-scale system. This paper details a newly developed network modeling feature for xSim, eliminating the shortcomings of the existing network modeling capabilities. The approach takes a different path for implementing network contention and bandwidth capacity modeling using a less synchronous and accurate enough model design. With the new network modeling feature, xSim is able to simulate on-chip and on-node networks with reasonable accuracy and overheads.

Original language	English
Title of host publication	Proceedings of the IASTED International Conference Modelling, Identification and Control, MIC 2015
Publisher	Acta Press
Pages	139-146
Number of pages	8
ISBN (Electronic)	9780889869752
DOIs	https://doi.org/10.2316/P.2015.826-043
State	Published - 2015
Event	2015 IASTED International Conference on Modelling, Identification and Control, MIC 2015 - Innsbruck, Austria Duration: Feb 16 2015 → Feb 17 2015

Publication series

Name	Proceedings of the IASTED International Conference on Modelling, Identification and Control
ISSN (Print)	1025-8973

Conference

Conference	2015 IASTED International Conference on Modelling, Identification and Control, MIC 2015
Country/Territory	Austria
City	Innsbruck
Period	02/16/15 → 02/17/15

Funding

This work was sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory (ORNL) and the U.S. Department of Energy's Office of Advanced Scientific Computing Research. This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). This work was sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory (ORNL) and the U.S. Department of Energy’s Office of Advanced Scientific Computing Research.

Funders	Funder number
DOE Public Access Plan
United States Government
U.S. Department of Energy
Advanced Scientific Computing Research	DE-AC05-00OR22725
Oak Ridge National Laboratory

Keywords

Computer network modeling
High-performance computing
Parallel discrete event simulation
Performance evaluation

Access to Document

10.2316/P.2015.826-043

Cite this

@inproceedings{7ab07e5b42aa4fd48eff55b6366611a6,

title = "A network contention model for the extreme-scale simulator",

abstract = "The Extreme-scale Simulator (xSim) is a performance investigation toolkit for high-performance computing (HPC) hardware/software co-design. It permits running a HPC application with millions of concurrent execution threads, while observing its performance in a simulated extreme-scale system. This paper details a newly developed network modeling feature for xSim, eliminating the shortcomings of the existing network modeling capabilities. The approach takes a different path for implementing network contention and bandwidth capacity modeling using a less synchronous and accurate enough model design. With the new network modeling feature, xSim is able to simulate on-chip and on-node networks with reasonable accuracy and overheads.",

keywords = "Computer network modeling, High-performance computing, Parallel discrete event simulation, Performance evaluation",

author = "Christian Engelmann and Thomas Naughton",

note = "Publisher Copyright: {\textcopyright} 2015, Acta Press. All rights reserved.; 2015 IASTED International Conference on Modelling, Identification and Control, MIC 2015 ; Conference date: 16-02-2015 Through 17-02-2015",

year = "2015",

doi = "10.2316/P.2015.826-043",

language = "English",

series = "Proceedings of the IASTED International Conference on Modelling, Identification and Control",

publisher = "Acta Press",

pages = "139--146",

booktitle = "Proceedings of the IASTED International Conference Modelling, Identification and Control, MIC 2015",

}

Engelmann, C & Naughton, T 2015, A network contention model for the extreme-scale simulator. in Proceedings of the IASTED International Conference Modelling, Identification and Control, MIC 2015. Proceedings of the IASTED International Conference on Modelling, Identification and Control, Acta Press, pp. 139-146, 2015 IASTED International Conference on Modelling, Identification and Control, MIC 2015, Innsbruck, Austria, 02/16/15. https://doi.org/10.2316/P.2015.826-043

A network contention model for the extreme-scale simulator. / Engelmann, Christian ; Naughton, Thomas.
Proceedings of the IASTED International Conference Modelling, Identification and Control, MIC 2015. Acta Press, 2015. p. 139-146 (Proceedings of the IASTED International Conference on Modelling, Identification and Control).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A network contention model for the extreme-scale simulator

AU - Engelmann, Christian

AU - Naughton, Thomas

PY - 2015

Y1 - 2015

N2 - The Extreme-scale Simulator (xSim) is a performance investigation toolkit for high-performance computing (HPC) hardware/software co-design. It permits running a HPC application with millions of concurrent execution threads, while observing its performance in a simulated extreme-scale system. This paper details a newly developed network modeling feature for xSim, eliminating the shortcomings of the existing network modeling capabilities. The approach takes a different path for implementing network contention and bandwidth capacity modeling using a less synchronous and accurate enough model design. With the new network modeling feature, xSim is able to simulate on-chip and on-node networks with reasonable accuracy and overheads.

AB - The Extreme-scale Simulator (xSim) is a performance investigation toolkit for high-performance computing (HPC) hardware/software co-design. It permits running a HPC application with millions of concurrent execution threads, while observing its performance in a simulated extreme-scale system. This paper details a newly developed network modeling feature for xSim, eliminating the shortcomings of the existing network modeling capabilities. The approach takes a different path for implementing network contention and bandwidth capacity modeling using a less synchronous and accurate enough model design. With the new network modeling feature, xSim is able to simulate on-chip and on-node networks with reasonable accuracy and overheads.

KW - Computer network modeling

KW - High-performance computing

KW - Parallel discrete event simulation

KW - Performance evaluation

UR - http://www.scopus.com/inward/record.url?scp=85015753377&partnerID=8YFLogxK

U2 - 10.2316/P.2015.826-043

DO - 10.2316/P.2015.826-043

M3 - Conference contribution

AN - SCOPUS:85015753377

T3 - Proceedings of the IASTED International Conference on Modelling, Identification and Control

SP - 139

EP - 146

BT - Proceedings of the IASTED International Conference Modelling, Identification and Control, MIC 2015

PB - Acta Press

T2 - 2015 IASTED International Conference on Modelling, Identification and Control, MIC 2015

Y2 - 16 February 2015 through 17 February 2015

ER -

A network contention model for the extreme-scale simulator

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this