Resource sharing in a hybrid partitioned/global scheduling framework for multiprocessors

S. Afshar, M. Behnam, R.J. Bril, T. Nolte

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)

Abstract

For resource-constrained embedded real-time systems, resource-efficient approaches are very important. Such an approach is presented in this paper, targeting systems where a critical application is partitioned on a multi-core platform and the remaining capacity on each core is provided to a noncritical application using resource reservation techniques. To exploit the potential parallelism of the non-critical application, global scheduling is used for its constituent tasks. Previously, we enabled intra-application resource sharing for such a framework, i.e. each application has its own dedicated set of resources. In this paper, we enable inter-application resource sharing, in particular between the critical application and the non-critical application. This effectively enables resource sharing in a hybrid partitioned/global scheduling framework on multiprocessors. For resource sharing, we use a spin-based synchronization protocol. We derive blocking bounds and extend existing schedulability analysis for such a system.
Original languageEnglish
Title of host publication20th IEEE International Symposium on Emerging Technologies and Factory Automation (ETFA)
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1-10
Number of pages10
ISBN (Electronic)978-1-4673-7929-8
DOIs
Publication statusPublished - Jun 2015
Event20th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2015) - University of Luxembourg, Luxembourg, Luxembourg
Duration: 8 Sep 201511 Sep 2015
Conference number: 20
http://www.etfa2015.org/
http://www.etfa2015.org/

Conference

Conference20th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2015)
Abbreviated titleEFTA'2015
CountryLuxembourg
CityLuxembourg
Period8/09/1511/09/15
Internet address

Fingerprint Dive into the research topics of 'Resource sharing in a hybrid partitioned/global scheduling framework for multiprocessors'. Together they form a unique fingerprint.

Cite this