Skip to Main content Skip to Navigation
Theses

Étude et évaluation des politiques d'ordonnancement temps réel multiprocesseur

Abstract : Numerous algorithms have been proposed to address the scheduling of real-time tasks for multiprocessor architectures. Yet, new scheduling algorithms have been defined very recently. Therefore, and without any guarantee of completeness, we have identified more than fifty of them. This large diversity makes the comparison of their behavior and performance difficult. This research aims at allowing the study and the evaluation of key scheduling algorithms. The first contribution is SimSo, a new simulation tool dedicated to the evaluation of scheduling algorithms. Using this tool, we were able to compare the performance of twenty algorithms. The second contribution is the consideration, in the simulation, of temporal overheads related to the execution of the scheduler and the impact of memory caches on the computation time of the jobs. This is done by the introduction of statistical models evaluating the cache miss ratios.
Document type :
Theses
Complete list of metadata

Cited literature [155 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01104953
Contributor : Arlette Evrard <>
Submitted on : Monday, January 19, 2015 - 3:03:39 PM
Last modification on : Thursday, June 10, 2021 - 3:05:20 AM
Long-term archiving on: : Friday, September 11, 2015 - 7:17:10 AM

Identifiers

  • HAL Id : tel-01104953, version 1

Citation

Maxime Chéramy. Étude et évaluation des politiques d'ordonnancement temps réel multiprocesseur. Systèmes embarqués. Institut National des Sciences Appliquées de Toulouse (INSA Toulouse), 2014. Français. ⟨tel-01104953⟩

Share

Metrics

Record views

491

Files downloads

5397