A Novel Heuristic Algorithm for Mapping AUTOSAR Runnables to Tasks

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.