Fault recovery and adaptation in time-triggered Networks-on-Chips for mixed-criticality systems

Adaptivity in terms of fault recovery and energy efficiency alongside with mixed-criticality support are demanded in today's embedded systems. Safety-critical systems are desired to switch between precomputed resource allocations at runtime based on the monitored information from the platform. In addition, those systems are desired to adjust their internal behavior with regard to a change in the environment, while operating at a desired safety level. At the same time, resource requests in such systems can be highly dynamic and data dependent. Aiming at meeting a superset of all worst case demands leads to unaffordable overheads in terms of resource utilization. Hence, efficient resource management mechanisms are required to provide fault recovery and to make the system adaptive to the changes in the environmental or the resource requests, while keeping the system at a safe state. This paper introduces a solution for supporting resource management in networks-on-chips that fulfills the requirements of adaptive mixed-criticality systems and proposes an architecture that establishes fault recovery by switching between precomputed resource allocations based on the statistical and diagnostic information.