Campus HPC network design and monitoring

Yvonne James, Violeta Holmes, Daniel Munnings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The needs of the research communities in research institutes and Higher Education (HE) establishments are demanding evermore powerful computing resources for supporting complex scientific and industrial simulation and modeling, manipulating and storage of large quantities of data [6, 9]. In this paper we present our experience at the University of Huddersfield (UoH), UK in developing the HPC systems infrastructure, removing a technical burden from researchers and enabling quicker and more insightful research outcomes. We have designed and implemented the University of Huddersfield, Queens gate Grid (QGG) campus grid [7]. In the process of building QGG systems and optimising its performance, we have designed and implemented a reliable network system infrastructure. The network topology was re-designed in various stages of system deployment resulting in a reduction of the number of switches, routers and network interconnects. This has led to an improvement in data transmission, a reduction in the possibility of bottlenecks and much reduced data loss [2, 9]. The rapid expansion of our campus grid has led us to question the energy efficiency of our HPC systems. Our initial investigation has targeted the transfer of data and power usage with a view to extending this work to incorporate other metrics, which is the subject of further work.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013
PublisherIEEE Computer Society
Pages1504-1511
Number of pages8
ISBN (Print)9780769550886
DOIs
Publication statusPublished - 2014
Event15th IEEE International Conference on High Performance Computing and Communications and 11th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing - Zhangjiajie, Hunan, China
Duration: 13 Nov 201315 Nov 2013
Conference number: 15

Conference

Conference15th IEEE International Conference on High Performance Computing and Communications and 11th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing
Abbreviated titleEUC / HPCC 2013
CountryChina
CityHunan
Period13/11/1315/11/13

Fingerprint

Monitoring
Routers
Data communication systems
Energy efficiency
Education
Switches
Topology

Cite this

James, Y., Holmes, V., & Munnings, D. (2014). Campus HPC network design and monitoring. In Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013 (pp. 1504-1511). [6832094] IEEE Computer Society. https://doi.org/10.1109/HPCC.and.EUC.2013.212
James, Yvonne ; Holmes, Violeta ; Munnings, Daniel. / Campus HPC network design and monitoring. Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013. IEEE Computer Society, 2014. pp. 1504-1511
@inproceedings{224e9abb1d4a4e1eb3ab2fd3f3ab92dc,
title = "Campus HPC network design and monitoring",
abstract = "The needs of the research communities in research institutes and Higher Education (HE) establishments are demanding evermore powerful computing resources for supporting complex scientific and industrial simulation and modeling, manipulating and storage of large quantities of data [6, 9]. In this paper we present our experience at the University of Huddersfield (UoH), UK in developing the HPC systems infrastructure, removing a technical burden from researchers and enabling quicker and more insightful research outcomes. We have designed and implemented the University of Huddersfield, Queens gate Grid (QGG) campus grid [7]. In the process of building QGG systems and optimising its performance, we have designed and implemented a reliable network system infrastructure. The network topology was re-designed in various stages of system deployment resulting in a reduction of the number of switches, routers and network interconnects. This has led to an improvement in data transmission, a reduction in the possibility of bottlenecks and much reduced data loss [2, 9]. The rapid expansion of our campus grid has led us to question the energy efficiency of our HPC systems. Our initial investigation has targeted the transfer of data and power usage with a view to extending this work to incorporate other metrics, which is the subject of further work.",
keywords = "energy efficiency, green computing, HPC network design, performance, topology",
author = "Yvonne James and Violeta Holmes and Daniel Munnings",
year = "2014",
doi = "10.1109/HPCC.and.EUC.2013.212",
language = "English",
isbn = "9780769550886",
pages = "1504--1511",
booktitle = "Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013",
publisher = "IEEE Computer Society",
address = "United States",

}

James, Y, Holmes, V & Munnings, D 2014, Campus HPC network design and monitoring. in Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013., 6832094, IEEE Computer Society, pp. 1504-1511, 15th IEEE International Conference on High Performance Computing and Communications and 11th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, Hunan, China, 13/11/13. https://doi.org/10.1109/HPCC.and.EUC.2013.212

Campus HPC network design and monitoring. / James, Yvonne; Holmes, Violeta; Munnings, Daniel.

Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013. IEEE Computer Society, 2014. p. 1504-1511 6832094.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Campus HPC network design and monitoring

AU - James, Yvonne

AU - Holmes, Violeta

AU - Munnings, Daniel

PY - 2014

Y1 - 2014

N2 - The needs of the research communities in research institutes and Higher Education (HE) establishments are demanding evermore powerful computing resources for supporting complex scientific and industrial simulation and modeling, manipulating and storage of large quantities of data [6, 9]. In this paper we present our experience at the University of Huddersfield (UoH), UK in developing the HPC systems infrastructure, removing a technical burden from researchers and enabling quicker and more insightful research outcomes. We have designed and implemented the University of Huddersfield, Queens gate Grid (QGG) campus grid [7]. In the process of building QGG systems and optimising its performance, we have designed and implemented a reliable network system infrastructure. The network topology was re-designed in various stages of system deployment resulting in a reduction of the number of switches, routers and network interconnects. This has led to an improvement in data transmission, a reduction in the possibility of bottlenecks and much reduced data loss [2, 9]. The rapid expansion of our campus grid has led us to question the energy efficiency of our HPC systems. Our initial investigation has targeted the transfer of data and power usage with a view to extending this work to incorporate other metrics, which is the subject of further work.

AB - The needs of the research communities in research institutes and Higher Education (HE) establishments are demanding evermore powerful computing resources for supporting complex scientific and industrial simulation and modeling, manipulating and storage of large quantities of data [6, 9]. In this paper we present our experience at the University of Huddersfield (UoH), UK in developing the HPC systems infrastructure, removing a technical burden from researchers and enabling quicker and more insightful research outcomes. We have designed and implemented the University of Huddersfield, Queens gate Grid (QGG) campus grid [7]. In the process of building QGG systems and optimising its performance, we have designed and implemented a reliable network system infrastructure. The network topology was re-designed in various stages of system deployment resulting in a reduction of the number of switches, routers and network interconnects. This has led to an improvement in data transmission, a reduction in the possibility of bottlenecks and much reduced data loss [2, 9]. The rapid expansion of our campus grid has led us to question the energy efficiency of our HPC systems. Our initial investigation has targeted the transfer of data and power usage with a view to extending this work to incorporate other metrics, which is the subject of further work.

KW - energy efficiency

KW - green computing

KW - HPC network design

KW - performance

KW - topology

UR - http://www.scopus.com/inward/record.url?scp=84903976260&partnerID=8YFLogxK

U2 - 10.1109/HPCC.and.EUC.2013.212

DO - 10.1109/HPCC.and.EUC.2013.212

M3 - Conference contribution

SN - 9780769550886

SP - 1504

EP - 1511

BT - Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013

PB - IEEE Computer Society

ER -

James Y, Holmes V, Munnings D. Campus HPC network design and monitoring. In Proceedings - 2013 IEEE International Conference on High Performance Computing and Communications, HPCC 2013 and 2013 IEEE International Conference on Embedded and Ubiquitous Computing, EUC 2013. IEEE Computer Society. 2014. p. 1504-1511. 6832094 https://doi.org/10.1109/HPCC.and.EUC.2013.212