Abstract
To evaluate the communication capabilities of clusters, we must take into account not only the interconnection network but also the system software. In this paper, we evaluate the communication capabilities of a cluster based on dual-Opteron SMP nodes interconnected with QsNetII. In particular, we study the raw network performance, the ability of MPI to overlap computation and communication, and the appropriateness of the local operating systems to support parallel processing. Experimental results show a stable system with a really efficient communication subsystem which is able to deliver 875 MB/s unidirectional bandwidth, 1.6 μsec unidirectional latency, and up to 99.5% CPU availability while communication is in progress.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Boden, N.J., Cohen, D., Felderman, R.E., Kulawik, A.E., Seitz, C.L., Seizovic, J.N., Su, W.-K.: Myrinet: A Gigabit-per-Second Local Area Network. IEEE Micro 15(1), 29–36 (1995)
Fernández, J., Frachtenberg, E., Petrini, F.: BCS-MPI: A New Approach in the System Software Design for Large-Scale Parallel Computers. In: Proceedings of IEEE/ACM Conference on SuperComputing, Phoenix, AZ (USA) (November 2003)
Jones, T., Tuel, W., Maskell, B.: Improving the Scalability of Parallel Jobs by adding Parallel Awareness to the Operating System. In: Proceedings of IEEE/ACM Conference on SuperComputing, Phoenix, AZ (USA) (November 2003)
Lawry, W., Wilson, C., Maccabe, A.B.: COMB: A Portable Benchmark Suite for Assessing MPI Overlap. In: Proceedings of IEEE International Conference on Cluster Computing, Chicago, IL (USA) (September 2002)
Quadrics Supercomputers World Ltd. Elan4 Reference Manual
Moody, A., Fernández, J., Petrini, F., Panda, D.K.: Scalable NIC-Based Reduction on Large-Scale Clusters. In: Proceedings of IEEE/ACM Conference on SuperComputing, Phoenix, AZ (USA) (November 2003)
Petrini, F., Feng, W.C., Hoisie, A., Coll, S., Frachtenberg, E.: The Quadrics Network: High-Performance Clustering Technology. IEEE Micro. 22(1), 46–57 (2002)
Petrini, F., Kerbyson, D.J., Pakin, S.: The Case of the Missing Supercomputer Performance: Achieving Optimal Performance on the 8192 Processors of ASCI Q. In: Proceedings of ACM/IEEE Conference on SuperComputing, Phoenix, AZ (USA) (November 2003)
Shivam, P., Wyckoff, P., Panda, D.K.: EMP: Zero-copy OS-bypass NIC-driven Gigabit Ethernet Message Passing. In: Proceedings of IEEE/ACM Conference on SuperComputing, Denver, CO (USA) (November 2001)
Snir, M., Otto, S., Huss-Lederman, S., Walker, D., Dongarra, J.: MPI: The Complete Reference. MIT Press, Cambridge (1996)
Infiniband Trade Association, http://www.infinibandta.org
Myricom, Inc., http://www.myri.com
Quadrics Supercomputers World Ltd., http://www.quadrics.com
Top500 Supercomputing Sites, http://www.top500.org
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
García, P.E., Fernández, J., Petrini, F., García, J.M. (2005). Assessing MPI Performance on QsNetII . In: Di Martino, B., Kranzlmüller, D., Dongarra, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2005. Lecture Notes in Computer Science, vol 3666. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11557265_51
Download citation
DOI: https://doi.org/10.1007/11557265_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29009-4
Online ISBN: 978-3-540-31943-6
eBook Packages: Computer ScienceComputer Science (R0)