Fault tolerant wormhole routing in hypercube multicomputers

The communication latency between nodes of the distributed memory multicomputers (DMMPs) is a vital factor to the performance of whole the system. Up to date, researches have been proposed to show that wormhole routing always takes the least time latency for data communication in a DMMPs. Unlike store-and-forward and virtual cut-through routing strategies, wormhole routing is sensitive to deadlocks. No efficient methods for deadlock free, fault tolerant and adaptive wormhole routing in an hypercube multicomputers have been proposed yet. In this paper, two distributed fault tolerant wormhole routing strategies is proposed. One is deterministic and the other is adaptive. Both can tolerate n-1 faults and are shown to be deadlock free. The routing algorithm and examples which demonstrate the routing procedures are also given.