A Function for Hard Real-Time System Search-Based Task Mapping Optimisation

Abstract

A task mapping is deemed feasible for a hard real-time embedded system if the end-to-end response times of all tasks, which include the computation and the communication delays, does not exceed their deadlines. In this paper, we propose a new fitness function based on the concept of breakdown frequency to address the task mapping optimisation problem of hard real-time embedded systems. As a property of task mapping, the breakdown frequency is the minimal operating frequency under which a task set and its messages are able to execute in any scenario without missing their deadlines. With the frequency, unschedulable tasks and messages can become schedulable without changing the task mapping itself. These advantages are difficult to find in the state-of-the-art optimisation techniques that use the number of unschedulable tasks or latency as the property of task mapping. Results from the case studies suggest that the proposed function enables a wider design space exploration, allowing designers to easily trade-off operating frequency and core count without sacrificing hard real-time schedulability.