Using Program Visualization for Tuning Parallel-Loop Scheduling

Authors:
Susan Flynn Hummel;Doug Kimelman;Edith Schonberg;Marsha Tennenhouse;Dror Zernik
Affiliations:
-;-;-;-;-
Venue:
IEEE Parallel & Distributed Technology: Systems & Technology
Year:
1997

Citing 9
Cited 0

Guided self-scheduling: A practical scheduling scheme for parallel supercomputers

IEEE Transactions on Computers
Factoring: a method for scheduling parallel loops

Communications of the ACM
Operating system support for parallel programming on RP3

IBM Journal of Research and Development
The RP3 program visualization environment

IBM Journal of Research and Development
Low-overhead scheduling of nested parallelism

IBM Journal of Research and Development
On-the-fly topological sort—a basis for interactive debugging and live visualization of parallel programs

PADD '93 Proceedings of the 1993 ACM/ONR workshop on Parallel and distributed debugging
SP2 system architecture

IBM Systems Journal
The communication software and parallel environment of the IBM SP2

IBM Systems Journal
Strata-various: multi-layer visualization of dynamics in software system behavior

VIS '94 Proceedings of the conference on Visualization '94

Quantified Score

Hi-index	0.00

Visualization

Abstract

Scheduling parallel programs optimally on multiple processors is difficult, partly because of interactions between applications, system software, and hardware having unexpected effects on performance. These interactions are hard to quantify and difficult to model. A convenient and effective means of quickly examining the behavior of such systems can make the evaluation and refinement of scheduling paradigms easier. The authors have used a program-visualization tool called PV to help them develop and tune runtime systems for scheduling nested parallel loops on shared- and distributed-memory machines. In a series of experiments, PV gave feedback concerning the effectiveness of alternative algorithms and parameters. A prevalent and striking revelation of the visualizations was that, because of systemic effects, parallel-loop iterations exhibit execution-time variance, even when there is no algorithmic variance. This suggests that dynamic scheduling might be necessary to effectively use processors.