Abstract
This paper addresses the problem of supporting communications in parallel computing applications over ATM networks. We propose a mechanism specifically conceived for optimizing the cost-performance tradeoff in fairly long parallel executions. The proposed mechanism relies on a modified version of the loss recovery procedure of SSCOP, which is enhanced by means of a more intensive exploitation of ATM service categories in order to reduce the occurrence of cell loss. For this purpose, we make use of both the UBR and ABR service categories, with ABR being only introduced in the periods of high latency. These periods are determined by periodically monitoring the experienced latency. This approach can achieve equivalent latency as the plain ABR service but with a use of this service of only 30%–70% of the parallel computing traffic, depending on the load of the network and the characteristics of the application.
The original version of this chapter was revised: The copyright line was incorrect. This has been corrected. The Erratum to this chapter is available at DOI: 10.1007/978-0-387-35388-3_42
Chapter PDF
Similar content being viewed by others
References
ITU-T, Recommendation I.121. Broadband Aspects of ISDN. Geneva, April 1991.
T. E. Anderson, D. E. Culler, D. A. Patterson, et al. A Case for NOW (Networks of Workstations). IEEE Micro, 15 (1): 54–64, February 1995.
K. Castagnera et al. NAS Experiences with a Prototype Cluster of Workstations. In Proceedings of Supercomputing’94, pages 410–419, 1994.
ATM Forum Technical Committee. Traffic Management Specification, Version 4.0. Document ATMYorum/95–0013R10, February 1996.
J. L. Hennessy and D. A. Patterson. Computer Architecture. A Quantitative Approach. Morgan Kaufmann, 2nd edition, 1996.
J. Solé-Pareta and J. Vila-Sallent. Network-Based Parallel Computing over ATM Using Improved SSCOP Protocol. Computer Communications, 19 (11): 915–926, September 1996.
ITU-T, Draft Recommendation Q. 2110. B-ISDN ATM Adaptation Layer - Service Specific Connection Oriented Protocol (SSCOP). Geneva, March 1994.
A. Geist et al. PVM 3 Users’ Guide and Reference Manual. Oak Ridge National Laboratory, 1994.
C. A. Addison, V. S. Getov, A. J. G. Hey, R. W. Hockney, and I. C. Wolton. The GENESIS Distributed-Memory Benchmarks. Advances in Parallel Computing, 8 (Computer Benchmarks): 257–271, 1991.
J. Solé-Pareta and J. Domingo-Pascual. Burstiness Characterization of ATM Cell Streams. Computer Networks and ISDN Systems, 26 (11): 1351–1363, August 1994.
R. Jain, S. Kalyanaraman, R. Goyal, S Fahmy, and R. Viswanathan. The ERICA Switch Algorithm: A Complete Description. ATM Forum, Contribution ATMYorum/96–1172, August 1996.
R. Jain, S. Kalyanaraman, R. Viswanathan, and R. Goyal. A Sample Switch Algorithm. ATM Forum, Contribution ATMYorum/95–0178R1, February 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 IFIP International Federation for Information Processing
About this chapter
Cite this chapter
Vila-Sallent, J., Solé-Pareta, J. (1998). Integrating Parallel Computing Applications in an ATM Scenario. In: van As, H.R. (eds) High Performance Networking. HPN 1998. IFIP — The International Federation for Information Processing, vol 8. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-35388-3_14
Download citation
DOI: https://doi.org/10.1007/978-0-387-35388-3_14
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-5397-4
Online ISBN: 978-0-387-35388-3
eBook Packages: Springer Book Archive