Microprocessor fault-tolerance via on-the-fly partial reconfiguration

This paper presents a novel approach to exploit FPGA dynamic partial reconfiguration to improve the fault tolerance of complex microprocessor-based systems, with no need to statically reserve area to host redundant components. The proposed method not only improves the survivability of the system by allowing the online replacement of defective key parts of the processor, but also provides performance graceful degradation by executing in software the tasks that were executed in hardware before a fault and the subsequent reconfiguration happened. The advantage of the proposed approach is that thanks to a hardware hypervisor, the CPU is totally unaware of the reconfiguration happening in real-time, and there´s no dependency on the CPU to perform it. As proof of concept a design using this idea has been developed, using the LEON3 open-source processor, synthesized on a Virtex 4 FPGA.