Derivation of Parallel and Resilient Programs from Simulink Models

Abstract

Modern embedded applications often require high computational power and, on the other hand, fulfilment of real-time constraints and high level of resilience. Simulink is one widely used tool for model-based development of embedded software. In this paper, we focus on the derivation of parallel programs from Simulink models and real-time resilient execution of derived implementations on a many-core platform. The main contribution is a fault-tolerance (FT) mechanism that prevents data loss when the platform is dynamically reconfigured to mask failures of individual cores. Finally, we evaluate the proposed solutions on an industrial case study using a commercially available NoC-based platform. The evaluation shows that the proposed FT mechanism has a marginal overhead.