Dynamic load-balancing in a data parallel object-oriented system

Author

Wei Jie ; Wentong Cai ; Turner, S.J.

Author_Institution

Sch. of Comput. Eng., Nanyang Technol. Inst., Singapore

fYear

2001

fDate

29-29 June 2001

Firstpage

279

Lastpage

286

Abstract

In this paper, a parallel object collection (POC) model is introduced to support data parallelism in a parallel object-oriented system. This model is based on the idea of data partitioning and method replication. To achieve load-balancing, partition objects are dynamically migrated at runtime according to the system load situation. A threshold-based strategy is used in the dynamic load-balancing. To avoid over-convergence of load during partition object migration, a new destination node selection algorithm is proposed. The threshold values used in the algorithm are also adaptively adjusted to better reflect the fluctuation of the load during execution. To evaluate the performance of the dynamic load balancing algorithm, simulation experiments are conducted. The simulation results are reported and discussed in the paper.

Keywords

digital simulation; object-oriented programming; parallel programming; resource allocation; data parallel object-oriented system; data parallelism; data partitioning; destination node selection algorithm; dynamic load-balancing; method replication; parallel object collection model; partition objects; simulation results; threshold-based strategy; Computer aided instruction; Concurrent computing; Data engineering; Fluctuations; Load management; Object oriented modeling; Parallel processing; Partitioning algorithms; Runtime; Yarn;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Systems, 2001. ICPADS 2001. Proceedings. Eighth International Conference on

Conference_Location

Kyongju City, South Korea

ISSN

1521-9097

Print_ISBN

0-7695-1153-8

Type

conf

DOI

10.1109/ICPADS.2001.934831

Filename

934831