Online fault detection in a hardware/software co-design environment: system partitioning

System reliability aspects are receiving a lot of attention in the design of systems for critical application fields. Often these issues are approached at low abstraction levels, toward the end of the design process, introducing significant overheads. By introducing fault detection requirements at system level, when a hardware/software co-design process is to be carried out, it is possible to evaluate the overheads and benefits of different solutions. The traditional partitioning phase has been modified in order to take into account the reliability issues for selecting, among the several identified reliable solutions, the one that best responds to the user's requirements. The paper presents the partitioning for a co-design flow aimed at providing fault detection properties to the final system, selecting the hardware tasks and the software tasks for implementing both the system functionality and the checking capabilities.