An Adaptive Mixed Approach of Load Balancing for Heterogeneous Cluster of Workstations

Babar Majeed, Haroon Rashid, and Kalim Qureshi

Keywords

Parallel Distributed Image Processing, Tasks Partitioning & Scheduling, Dynamic Load Balancing

Abstract

The Heterogeneous Cluster Computing (HCC) system has heterogeneity in processors and resources. For such system, we propose an Adaptive Mixed Task partitioning, Scheduling (AMTS), and load balancing strategy. The investigation is examined on a manager/master and workers/nodes model. The measured results show that, the AMTS strategy dramatically improves the performance of HCC system and remedy the defects of static and Runtime Task Scheduling (RTS) strategies.

Important Links:

• DOI: 10.2316/P.2011.757-010
• From Proceeding (757) Parallel and Distributed Computing and Systems - 2011

Go Back