Analysis of communication data: compression network

Author

Nakano, Yasuhiko

Author_Institution

Electron. Syst. Labs., Fujitsu Labs. Ltd., Atsugi, Japan

fYear

1995

fDate

15-17 Mar 1995

Firstpage

199

Lastpage

205

Abstract

The paper reports the effect of compressed message delivery (a compression network) on a parallel processing system such as workstation clusters. Compression network is simulated on a massively parallel processor, the Thinking Machines CM-5, using the parallel language Split-C. To examine the benefit of data compression to the system, profiles, including message pattern, number of messages, and message size, are measured by simulation. The results indicate that compression increases the network bandwidth. A theoretical compression ratio of about a half was estimated for almost all messages. Network bandwidth can be efficiently doubled using data compression

Keywords

data compression; local area networks; message passing; parallel machines; performance evaluation; virtual machines; workstations; CM-5 Thinking Machines; Split-C parallel language; communication data; compressed message delivery; compression network; compression ratio; data compression; massively parallel processor; message pattern; message size; network bandwidth; parallel processing system; profiles; simulation; workstation clusters; Application software; Asynchronous transfer mode; Bandwidth; Concurrent computing; Costs; Data analysis; Data compression; Laboratories; Local area networks; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel Algorithms/Architecture Synthesis, 1995. Proceedings., First Aizu International Symposium on

Conference_Location

Fukushima

Print_ISBN

0-8186-7038-X

Type

conf

DOI

10.1109/AISPAS.1995.401337

Filename

401337