Load balancing on PC clusters with the super-programming model
Document Type
Conference Proceeding
Publication Date
1-1-2003
Abstract
Recent work in high-performance computing has shifted attention to PC cluster.. For PC-clusters, member nodes are independent computers connected by generalpurpose networks. The latency of data communications is long and load balancing among the nodes becomes a critical issue. We introduce a new model for program development on PC clusters, namely the Super-Programming Model (SPM) to address this issue. In SPM PC clusters are modeled as a single virtual machine with PC as their processing units. The workload is modeled as a collection of Super-Instructions (SIs). Each SIs can achieve a limited workload. Application programs are coded using SIs. SIs are dynamically assigned to available PC at run time. For limited workload, no SIs overloads any PC. Therefore, dynamic load balancing becomes an easier task. We apply SPM to mining association rules. Our experiments show that under normal conditions the workload is balanced very well. A performance model is also developed to describe the scalable behavior of SPM.
Identifier
84943258931 (Scopus)
ISBN
[0769520189]
Publication Title
Proceedings of the International Conference on Parallel Processing Workshops
External Full Text Location
https://doi.org/10.1109/ICPPW.2003.1240355
ISSN
15302016
First Page
63
Last Page
70
Volume
2003-January
Grant
ER63384
Recommended Citation
Jin, Dejiang and Ziavras, S. G., "Load balancing on PC clusters with the super-programming model" (2003). Faculty Publications. 14298.
https://digitalcommons.njit.edu/fac_pubs/14298
