Effects of communication latency, overhead, and bandwidth in a cluster architecture

DMCA

Effects of communication latency, overhead, and bandwidth in a cluster architecture (1997)

Cached

Download Links

by Richard P. Martin , Amin M. Vahdat , David E. Culler , Thomas E. Anderson

Venue:	In Proceedings of the 24th Annual International Symposium on Computer Architecture
Citations:	108 - 6 self

BibTeX

@INPROCEEDINGS{Martin97effectsof,
    author = {Richard P. Martin and Amin M. Vahdat and David E. Culler and Thomas E. Anderson},
    title = {Effects of communication latency, overhead, and bandwidth in a cluster architecture},
    booktitle = {In Proceedings of the 24th Annual International Symposium on Computer Architecture},
    year = {1997},
    pages = {85--97}
}

OpenURL

Abstract

This work provides a systematic study of the impact of communication performance on parallel applications in a high performance network of workstations. We develop an experimental system in which the communication latency, overhead, and bandwidth can be independently varied to observe the effects on a wide range of applications. Our results indicate that current efforts to improve cluster communication performance to that of tightly integrated parallel machines results in significantly improved application performance. We show that applications demonstrate strong sensitivity to overhead, slowing down by a factor of 60 on 32 processors when overhead is increased from 3 to 103 s. Applications in this study are also sensitive to per-message bandwidth, but are surprisingly tolerant of increased latency and lower per-byte bandwidth. Finally, most applications demonstrate a highly linear dependence to both overhead and per-message bandwidth, indicating that further improvements in communication performance will continue to improve application performance. 1

Keyphrases

communication latency cluster architecture application performance per-message bandwidth communication performance high performance network linear dependence experimental system parallel application cluster communication performance parallel machine result current effort increased latency wide range strong sensitivity systematic study per-byte bandwidth

DMCA