Latency Constrained Task Mapping to Improve Reliability of High Critical Tasks in Mixed Criticality Systems

In this paper, we focus on improving the reliability of high critical tasks in Mixed Criticality Systems (MCS) running on a Hardware/Software codesign environment. Assuming the system is operating in low criticality mode, we first find the minimum execution latency by mapping the tasks to the processing elements considering the reliability and execution latency values in the technology library. When the system switches to high criticality mode, the proposed algorithm maps high critical tasks to the highest reliable components, and then, schedules low critical tasks without exceeding the minimum latency. The results of the experimental evaluation clearly show the viability of the proposed approach.