How network topology affects dynamic loading balancing
- 1 January 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Parallel & Distributed Technology: Systems & Applications
- Vol. 4 (3) , 25-35
- https://doi.org/10.1109/88.532137
Abstract
Previous research has proposed several, different load balancing strategies and measured their performances on either a distributed system or a multiprocessor network of specific topology. This paper addresses the performances of five dynamic load balancing strategies. A simulator has been developed to allow performance comparisons to be made across a range of network topologies: a 2D-mesh, a 4D-hypercube, a linear array, and a composite Fibonacci cube. The Fibonacci cube is one of the more recently proposed novel interconnection topologies. Results show that the performance of a dynamic load balancing strategy is affected by both the average processor distance and average node degree of the network.Keywords
This publication has 10 references indexed in Scilit:
- Parallel load-balancing: An extension to the gradient modelParallel Computing, 1995
- Dynamic load balancing using task-transfer probabilitiesParallel Computing, 1993
- Prediction-based dynamic load-sharing heuristicsIEEE Transactions on Parallel and Distributed Systems, 1993
- Strategies for dynamic load balancing on highly parallel computersIEEE Transactions on Parallel and Distributed Systems, 1993
- Fibonacci cubes-a new interconnection TopologyIEEE Transactions on Parallel and Distributed Systems, 1993
- Methodical analysis of adaptive load sharing algorithmsIEEE Transactions on Parallel and Distributed Systems, 1992
- A dynamic load-balancing policy with a central job dispatcher (LBC)IEEE Transactions on Software Engineering, 1992
- A trace-driven simulation study of dynamic load balancingIEEE Transactions on Software Engineering, 1988
- The Gradient Model Load Balancing MethodIEEE Transactions on Software Engineering, 1987
- A comparison of receiver-initiated and sender-initiated adaptive load sharingPerformance Evaluation, 1986