Performance debugging in the enterprise parallel programming system

Authors:
David Woloschuk;Paul Iglinski;Steven MacDonald;Diego Novillo;Ian Parsons;Jonathan Schaeffer;Duane Szafron
Affiliations:
Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1;Department of Computing Science, University of Alberta, Edmonton, Alberta, CANADA T6G 2H1
Venue:
CASCON '95 Proceedings of the 1995 conference of the Centre for Advanced Studies on Collaborative research
Year:
1995

Citing 5
Cited 0

Graphical development tools for network-based concurrent supercomputing

Proceedings of the 1991 ACM/IEEE conference on Supercomputing
Network-based concurrent computing on the PVM system

Concurrency: Practice and Experience
Breaking the silence: auralization of parallel program behavior

Journal of Parallel and Distributed Computing - Special issue on tools and methods for visualization of parallel systems and computations
The Enterprise Model for Developing Distributed Applications

IEEE Parallel & Distributed Technology: Systems & Technology
A prototype debugger for Hermes

CASCON '92 Proceedings of the 1992 conference of the Centre for Advanced Studies on Collaborative research - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Debugging parallel/distributed programs is an iterative process, alternating between correctness debugging and performance debugging. Performance debugging involves identifying bottlenecks in a parallel computation and providing meaningful feedback to the user. The quality of this feedback can play a major role in the quick resolution of performance problems. Many feedback systems provide the user with endless streams of statistics, relying on the user to do the interpretation. This paper discusses the performance debugging facilities in the Enterprise parallel programming system. Through visual and aural cues, performance information is conveyed to the user in an intuitive manner.