A Novel Heuristic Algorithm for Mapping AUTOSAR Runnables to Tasks

Fouad Khenfri, Khaled Chaaban, Maryline Chetto

Abstract

This paper describes a novel algorithm that permits to automate the process to map runnables to tasks in any AUTOSAR architecture. This enables to boost system performance by reducing the number of tasks to be implemented and while preserving system schedulability. Our algorithm uses some properties related to the activation offset for mapping runnables with distinct periods to the same task. We consider periodic, independent and fixed-priority tasks running on a single processor. The results of an experimental study are reported. First, they show that our algorithm reduces significantly the number of tasks with distinct periods while preserving system schedulability. And second, the system schedulability bound is increased by 34% compared to the typical periodic solution and the average response time of tasks is reduced by 30% related to ohers solutions.

References

  1. Audsley, N. (1991). Optimal Priority Assignment and Feasibility of Static Priority Tasks with Arbitrary Start Times. Technical report. University of York, Department of Computer Science.
  2. Bini, E. and Buttazzo, G. C. (2005). Measuring the performance of schedulability tests. Real-Time Systems, 30(1-2):129-154.
  3. Haibo, Z. and Di Natale, M. Efficient implementation of autosar components with minimal memory usage. In Industrial Embedded Systems (SIES), 2012 7th IEEE International Symposium on, pages 130-137.
  4. Liu, C. L. and Layland, J. W. (1973). Scheduling algorithms for multiprogramming in a hard-real-time environment. Journal of the ACM (JACM), 20(1):46-61.
  5. Ming, Z. and Zonghua, G. Optimization issues in mapping autosar components to distributed multithreaded implementations. In Rapid System Prototyping (RSP), 2011 22nd IEEE International Symposium on, pages 23-29.
  6. Monot, A., Navet, N., Bavoux, B., and Simonot-Lion, F. (2012). Multisource software on multicore automotive ecus: Combining runnable sequencing with task scheduling. Industrial Electronics, IEEE Transactions on, 59(10):3934-3942.
  7. Navet, N., Monot, A., Bavoux, B., and Simonot-Lion, F. (2010). Multi-source and multicore automotive ecus - os protection mechanisms and scheduling. In Industrial Electronics (ISIE), 2010 IEEE International Symposium on, pages 3734-3741.
  8. Partnership, A. (2011). Technical http://www.autosar.org/, V2.2.2 R3.2 Rev 1.
  9. Rongshen, L., Hong, L., Wei, P., Yi, Z., and Minde, Z. An approach to optimize intra-ecu communication based on mapping of autosar runnable entities. In Embedded Software and Systems, 2009. ICESS 7809. International Conference on, pages 138-143.
  10. Wozniak, E., Mehiaoui, A., Mraidha, C., Piergiovanni, S. T., and Gerard, S. (2013). An optimization approach for the synthesis of AUTOSAR architectures. In Proceedings of 2013 IEEE 18th Conference on Emerging Technologies & Factory Automation, ETFA 2013, Cagliari, Italy, September 10-13, 2013, pages 1-10.
  11. Zeng, H., Di Natale, M., and Zhu, Q. (2012). Optimizing stack memory requirements for real-time embedded applications. In Emerging Technologies & Factory Automation (ETFA), 2012 IEEE 17th Conference on, pages 1-8. IEEE.
Download


Paper Citation


in Harvard Style

Khenfri F., Chaaban K. and Chetto M. (2015). A Novel Heuristic Algorithm for Mapping AUTOSAR Runnables to Tasks . In Proceedings of the 5th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS, ISBN 978-989-758-084-0, pages 239-246. DOI: 10.5220/0005234202390246


in Bibtex Style

@conference{peccs15,
author={Fouad Khenfri and Khaled Chaaban and Maryline Chetto},
title={A Novel Heuristic Algorithm for Mapping AUTOSAR Runnables to Tasks},
booktitle={Proceedings of the 5th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,},
year={2015},
pages={239-246},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005234202390246},
isbn={978-989-758-084-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PECCS,
TI - A Novel Heuristic Algorithm for Mapping AUTOSAR Runnables to Tasks
SN - 978-989-758-084-0
AU - Khenfri F.
AU - Chaaban K.
AU - Chetto M.
PY - 2015
SP - 239
EP - 246
DO - 10.5220/0005234202390246