Introduction to algorithms
Dynamic mapping of a class of independent tasks onto heterogeneous computing systems
Journal of Parallel and Distributed Computing - Special issue on software support for distributed computing
Scheduling Resources in Multi-User, Heterogeneous, Computing Environments with SmartNet
HCW '98 Proceedings of the Seventh Heterogeneous Computing Workshop
Dynamic Matching and Scheduling of a Class of Independent Tasks onto Heterogeneous Computing Systems
HCW '99 Proceedings of the Eighth Heterogeneous Computing Workshop
Grid Harvest Service: A System for Long-Term, Application-Level Task Scheduling
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Agent-Based Grid Load Balancing Using Performance-Driven Task Scheduling
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
A De-Centralized Scheduling and Load Balancing Algorithm for Heterogeneous Grid Environments
ICPPW '02 Proceedings of the 2002 International Conference on Parallel Processing Workshops
QoS guided min-min heuristic for grid task scheduling
Journal of Computer Science and Technology - Grid computing
ISPDC'03 Proceedings of the Second international conference on Parallel and distributed computing
A Controlled Scheduling Algorithm Decreasing the Incidence of Starvation in Grid Environments
AICI '09 Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence
Hi-index | 0.00 |
Scheduling a set of independent tasks onto a network of heterogeneous computing systems to minimize the overall execution time is NP-hard. Among the algorithms that have been proposed in the past, the Sufferage algorithm [5] has the best performance in minimizing the makespan of a set of independent tasks. We propose a new low complexity scheduling algorithm, Heterogeneous Largest Task First (HLTF). Its complexity is O(s(Log s + m)) vs. O(s2*m) of Sufferage, where s is the number of tasks and m is the number of available machines. Simulation results reveal that in terms of minimizing the makespan, the performance of HLTF is slightly better than that of the Sufferage algorithm. In terms of running cost, HLTF significantly outperforms the Sufferage algorithm.