Please use this identifier to cite or link to this item:
https://doi.org/10.1109/ICON.2011.6168521
Title: | Scheduling hybrid divisible and indivisible loads on clusters | Authors: | Hu, M. Veeravalli, B. |
Keywords: | cluster computing communication delay Divisible loads parallel processing |
Issue Date: | 2011 | Citation: | Hu, M.,Veeravalli, B. (2011). Scheduling hybrid divisible and indivisible loads on clusters. ICON 2011 - 17th IEEE International Conference on Networks : 141-146. ScholarBank@NUS Repository. https://doi.org/10.1109/ICON.2011.6168521 | Abstract: | Divisible load applications occur in many fields of science and engineering. Such applications can be easily parallelized in a master-worker fashion, but pose several scheduling challenges. In this paper we investigate the scheduling problem for processing a set of tasks comprising both divisible and indivisible tasks on cluster systems. Indivisible loads are characterized by the property that they need to be processed on their entirety on a single processor while divisible loads can be distributed across several processing nodes by fully exploiting the underlying data parallelism. We propose a novel scheduling algorithm referred to as Hybrid Load Scheduling (HLS) algorithm for handling a set of tasks comprising both divisible and indivisible tasks on clusters. HLS fully exploits the parallelism in divisible loads to achieve high resource utilization. It also utilizes a pipelining technique to hide communication time and thus further optimize the overall performance. Simulations are presented to evaluate and compare the performance of the proposed strategy. © 2011 IEEE. | Source Title: | ICON 2011 - 17th IEEE International Conference on Networks | URI: | http://scholarbank.nus.edu.sg/handle/10635/71713 | ISBN: | 9781457718250 | DOI: | 10.1109/ICON.2011.6168521 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.