Automated runnable to task mapping

Antoine Bertout (1, 2, 3) , Julien Forget (1, 2, 3) , Richard Olejnik (1, 2, 3)

1 DART - Contributions of the Data parallelism to real time
2 LIFL - DART/Émeraude
3 LIFL - Laboratoire d'Informatique Fondamentale de Lille

We propose in this paper, a method to automatically map runnables (blocks of code with dedicated functionality) with real-time constraints to tasks (or threads). We aim at reducing the number of tasks runnables are mapped to, while preserving the schedulability of the initial system. We consider independent tasks running on a single processor. Our approach has been applied with fixed-task or fixed-job priorities assigned in a Deadline Monotonic (DM) or a Earliest Deadline First (EDF) manner.

Mots clés: real-time; scheduling; task clustering; runnable-to-task; mapping

Domaines: Systèmes embarqués

Antoine Bertout, Julien Forget, Richard Olejnik. Automated runnable to task mapping. 2013. ⟨hal-00827798v1⟩