Dynamic Load Balancing of Unbalanced Computations Using Message Passing

This paper examines MPI's ability to support continuous, dynamic load balancing for unbalanced parallel applications. We use an unbalanced tree search benchmark (UTS) to compare two approaches, 1) work sharing using a centralized work queue, and 2) work stealing using explicit polling to handle...

Full description

Saved in:
Bibliographic Details
Published in2007 IEEE International Parallel and Distributed Processing Symposium pp. 1 - 8
Main Authors Dinan, J., Olivier, S., Sabin, G., Prins, J., Sadayappan, P., Tseng, C.-W.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2007
Subjects
Application software
Communication system operations and management
Computer science
Concurrent computing
Educational institutions
Load management
Message passing
Parallel programming
Runtime
Shape
Online AccessGet full text

Cover

More Information
Summary:This paper examines MPI's ability to support continuous, dynamic load balancing for unbalanced parallel applications. We use an unbalanced tree search benchmark (UTS) to compare two approaches, 1) work sharing using a centralized work queue, and 2) work stealing using explicit polling to handle steal requests. Experiments indicate that in addition to a parameter defining the granularity of load balancing, message-passing paradigms require additional parameters such as polling intervals to manage runtime overhead. Using these additional parameters, we observed an improvement of up to 2times in parallel performance. Overall we found that while work sharing may achieve better peak performance on certain workloads, work stealing achieves comparable if not better performance across a wider range of chunk sizes and workloads.
ISBN:1424409098
9781424409099
ISSN:1530-2075
DOI:10.1109/IPDPS.2007.370581