Balance Algorithm — a New Approach to Solving the Mapping Problem on Heterogeneous Systems

Nguyen Thanh Son (), Tran Nguyen Hoang Huy () and Nguyen Anh Kiet
Additional contact information
Nguyen Thanh Son: HCM University of Technology, Department of Information Technology
Tran Nguyen Hoang Huy: HCM University of Technology, Department of Information Technology
Nguyen Anh Kiet: HCM University of Technology, Department of Information Technology

A chapter in Modeling, Simulation and Optimization of Complex Processes, 2005, pp 461-470 from Springer

Abstract: Summary A fundamental issue affecting the performance of a parallel program is the assignment of tasks to processors in order to achieve the minimum completion time. Most of state-of-the-art approaches consider homogeneous MIMD multiprocessor systems, in which all communication channels have the same bandwidth and all processors are equally powerful. These algorithms do not run efficiently on heterogeneous systems. In this paper, we present a new approach for the mapping problem on arbitrary systems. The main idea is based on the "global load balancing, local cut-size optimization" principle. This approach has achieved encouraged results that are verified by experiments for various random graphs and processor numbers.

Keywords: partitioning; mapping; load balance; heterogeneous system (search for similar items in EconPapers)
Date: 2005
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-540-27170-3_35

Ordering information: This item can be ordered from
http://www.springer.com/9783540271703

DOI: 10.1007/3-540-27170-8_35

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().