AN EFFICIENT ADAPTIVE FAULT-TOLERANT RUTING IN HYPERCUBES IN THE PRESENCE OF DYNAMIC FAULTS

摘要: This paper presents a new fault-tolerant routing algorithm in hypercube multicomputers based on the local-information of each node. In this algorithm, each node is only aware of its neighbors ‘status and makes routing decision using this information and the destination address of a message. This bounded local-information, whose values are numerable, causes the algorithm to be more adaptive with respect to the similar works, eg probability vector. Due to the low overhead of communications needed for constructing the local-information, dynamic faults are highly tolerable as well as static faults. Simulation results reveal that, in the case of static faults, the latency of messages is reduced up to 20 percent and in the presence of dynamic faults, the throughput of message delivery with wormhole switching is considerably improved.