On the Reliability of the Probabilistic Worst-Case Execution Time Estimates

Abstract : Probabilistic Worst-Case Execution Time estimates, through Measurement-Based Probabilistic Timing Analyses and statistical inference, desperately need for formal definition and reliability. The automatic DIAGnostic tool for applying the eXTReMe value theory within the Probabilistic Timing Analysis framework we are proposing defines a complete set of statistical tests for studying execution time traces, e.g., the real-time task average execution behavior, and estimating the extreme behavior of the task execution time, in particular the probabilistic Worst-Case Execution Time. The tool allows also defining and evaluating the reliability of the probabilistic Worst-Case Execution Time estimates with the Extreme Value Theory by applying a fuzzy logic approach. We apply the tool to traces of execution time measurements of a task running on a Commercial off-the-shelf real-time multi-core system under different execution conditions. Application of the diagnostic tool to the traces of execution time measurements particularly validates the hypothesis of using the Extreme Value Theory for estimating the probabilistic Worst-Case Execution Time for this kind of system.
Type de document :
Communication dans un congrès
8th European Congress on Embedded Real Time Software and Systems (ERTS 2016), Jan 2016, TOULOUSE, France. Proceedings of the 8th European Congress on Embedded Real Time Software and Systems, 〈http://www.erts2016.org/〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01289477
Contributeur : Marc Boyer <>
Soumis le : mercredi 16 mars 2016 - 17:25:56
Dernière modification le : mercredi 13 juin 2018 - 10:28:02
Document(s) archivé(s) le : vendredi 17 juin 2016 - 10:54:57

Fichier

paper_16.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01289477, version 1

Collections

Citation

Fabrice Guet, Luca Santinelli, Jérôme Morio. On the Reliability of the Probabilistic Worst-Case Execution Time Estimates. 8th European Congress on Embedded Real Time Software and Systems (ERTS 2016), Jan 2016, TOULOUSE, France. Proceedings of the 8th European Congress on Embedded Real Time Software and Systems, 〈http://www.erts2016.org/〉. 〈hal-01289477〉

Partager

Métriques

Consultations de la notice

206

Téléchargements de fichiers

189