The Community for Technology Leaders
2011 IEEE 36th Conference on Local Computer Networks (2011)
Bonn
Oct. 4, 2011 to Oct. 7, 2011
ISSN: 0742-1303
ISBN: 978-1-61284-926-3
pp: 195-198
Wenji Wu , Computing Division, Fermilab, Batavia, IL 60510, USA
Phil DeMar , Computing Division, Fermilab, Batavia, IL 60510, USA
Don Holmgren , Computing Division, Fermilab, Batavia, IL 60510, USA
Amitoj Singh , Computing Division, Fermilab, Batavia, IL 60510, USA
Ruth Pordes , Computing Division, Fermilab, Batavia, IL 60510, USA
ABSTRACT
We have prototyped a GPU-accelerated network performance monitoring system, called G-NetMon, to support large-scale scientific collaborations at Fermilab. Our system exploits the data parallelism that exists within network flow data to provide fast analysis of bulk data movement between Fermilab and collaboration sites. Experiments demonstrate that our G-NetMon can rapidly detect sub-optimal bulk data movements.
INDEX TERMS
computer network performance evaluation, data flow analysis, graphics processing units, parallel processing, physics computing, system monitoring
CITATION

W. Wu, P. DeMar, D. Holmgren, A. Singh and R. Pordes, "G-NetMon: A GPU-accelerated network performance monitoring system for large scale scientific collaborations," 2011 IEEE 36th Conference on Local Computer Networks(LCN), Bonn, 2012, pp. 195-198.
doi:10.1109/LCN.2011.6115186
88 ms
(Ver 3.3 (11022016))