Splitting tasks for migrating real-time automotive applications to multi-core ECUs

Real-time automotive software becomes increasingly complex due to the integration of more functionalities. At the same time, the computation power of electronic control units grows by increasing the number of cores instead of the core performance. Thus, in the near future a single task will require more computation power than a single core can offer. We propose an approach that solves this problem by splitting a task into multiple parallel task partitions with minimal synchronization overhead while maintaining all data dependencies of the functionalities inside the original task. The approach is successfully validated on a real-world engine management system.