Parallel Algorithms / Architecture Synthesis, AIZU International Symposium on (1995)
Aizu-Wakamatsu, Fukushima, Japan
Mar. 15, 1995 to Mar. 17, 1995
Y. Nakano , Electron. Syst. Labs., Fujitsu Labs. Ltd., Atsugi, Japan
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.
parallel machines; data compression; workstations; local area networks; virtual machines; message passing; performance evaluation; compression network; compressed message delivery; communication data; parallel processing system; workstation clusters; massively parallel processor; CM-5 Thinking Machines; Split-C parallel language; data compression; profiles; message pattern; message size; simulation; compression ratio; network bandwidth
Y. Nakano, "Analysis of communication data: compression network," Parallel Algorithms / Architecture Synthesis, AIZU International Symposium on(PAS), Aizu-Wakamatsu, Fukushima, Japan, 1995, pp. 199.