Name
Abstract | ||
|---|---|---|
During the last years considerable effort has been put into developing scheduling and load balancing techniques and models for the processing of tasks in parallel and distributed systems. In this paper we extend an existing scheduling model called the divisible task model to adapt it to cluster architectures and make it applicable to a broader class of applications. To achieve this we present two new modifications which allows recursive modelling and will increase the models flexibility and performance. The goal of this work is to reduce the data volume which has to be transfered over the communication links to get an equally balanced load on the nodes of the system. As test-system we use a cluster-based image retrieval system to check the achieved performance. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.1016/S0927-5452(04)80030-3 | PARALLEL COMPUTING: SOFTWARE TECHNOLOGY, ALGORITHMS, ARCHITECTURES AND APPLICATIONS |
DocType | Volume | ISSN |
Conference | 13 | 0927-5452 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
3 | ||