On fault tolerant structure, distributed fault-diagnosis, reconfiguration, and recovery of the array processors

摘要

The design of fault-tolerant array structures from non-fault-tolerant array structures is studied. It is shown how hardware redundancy can be used in existing structures to make them capable of withstanding the failure of some of the array elements. Then distributed fault-tolerance schemes are introduced for the diagnosis of the fault elements, reconfiguration, and recovery of the array after failure of some of the elements.