Load Balancing and Efficient Memory Usage for Homogeneous Distributed Real-Time Embedded Systems - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Load Balancing and Efficient Memory Usage for Homogeneous Distributed Real-Time Embedded Systems

Abstract

This paper deals with load balancing and efficient memory usage for homogeneous distributed real-time embedded applications with dependence and strict periodicity constraints. Most of load balancing heuristics tend to minimize the total execution time of distributed applications by equalizing the workloads of processors. In addition, our heuristic satisfies dependence and strict periodicity constraints which are of great importance in embedded systems. However, since resources are limited some tasks distributed onto a processor may require more data memory than available. Thus, we propose a fast heuristic achieving both load balancing and efficient memory usage under dependence and strict periodicity constraints. Complexity and theoretical performance studies have showed that the proposed heuristic is respectively efficient and fast. Thus, an efficient memory usage is also necessary, especially in embedded systems where memory is limited. Although the total execution time of tasks is minimized some tasks could not be executed because the processors where they were distributed do not own enough memory to store the data used by these tasks. However, memory usage plays a significant role in determining the applications performances.
Fichier principal
Vignette du fichier
srmpds08.pdf (202.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00413485 , version 1 (04-09-2009)

Identifiers

  • HAL Id : inria-00413485 , version 1

Cite

Omar Kermia, Yves Sorel. Load Balancing and Efficient Memory Usage for Homogeneous Distributed Real-Time Embedded Systems. Proceedings of the 4th International Workshop on Scheduling and Resource Management for Parallel and Distributed Systems, SRMPDS'08, 2008, Portland, Oregon, United States. ⟨inria-00413485⟩
162 View
169 Download

Share

Gmail Facebook Twitter LinkedIn More