Title: A network performance sensitivity metric for parallel applications

Authors: Jeffrey J. Evans, Cynthia S. Hood

Addresses: Electrical and Computer Engineering Technology, Purdue University, West Lafayette, IN 47907, USA. ' Department of Computer Science, Illinois Institute of Technology, Chicago, IL 60616, USA

Abstract: Excessive run time variability of parallel application codes on commodity clusters is a significant challenge. To gain insight into this problem, our earlier work developed tools to emulate parallel applications (PACE) by simulating computation and using the cluster|s interconnection network for communication, and further study parallel application run time sensitivity effects to controlled network performance degradation (PARSE). This work expands our previous efforts by presenting a metric derived from PARSE test results conducted on several widely used parallel benchmarks and application code fragments. The metric suggests that a parallel application|s sensitivity to network performance variation can be quantified relative to its behaviour in optimal network performance conditions. Ideas on how this metric can be useful to parallel application development, cluster system performance management and system administration are also presented.

Keywords: parallel applications; run time sensitivity; high performance networks; network evaluation; performance management; run time variability; commodity clusters; simulation; performance degradation; performance variation.

DOI: 10.1504/IJHPCN.2011.038706

International Journal of High Performance Computing and Networking, 2011 Vol.7 No.1, pp.8 - 18

Published online: 21 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article