Simultaneous Optimisation of Task Mapping and Priority Assignment for Real-Time Embedded NoCs

Abstract

In a hard real-time embedded system based on a fixed priority pre-emptive Networks-On-Chip (NoC), the provision of guaranteed services may require pre-emption of some tasks and messages based on their priorities. In a worst case scenario, the interference imposed to low priority tasks can cause substantial computation and communication delays that can exceed their deadlines, leading to an unschedulable system. In a task mapping optimisation process, changing task mappings does not always produce a schedulable task mapping. In this paper, we propose an approach that simultaneously optimises task mapping and priority assignment, aiming to find a configuration that can completely satisfy the timing constraints of the system. Differing to the state-of-the-art, our approach takes into account the overall schedulability of the system by considering the worst-case end-to-end response time of all mapped tasks. As a result, we are able to increase the quality of task mappings at the same time improving the convergence of the optimisation algorithm, better than the previous approaches that solely focus on the task mapping optimisation to make the system schedulable.