Using Fault Avoidance for Fault Tolerant Routing in Interconnection Networks

Next to the high performance, the most important feature of the multiprocessor systems is their fault tolerant capability. In this regard, fault tolerant interconnection networks and specially fault tolerant routing methods are important parts of these systems. Hypercube is a popular interconnection network that is used in many multiprocessors. There are a number of suggested methods for fault tolerant routing in these systems. In this paper a neural routing method is introduced which is named as Fault Avoidance Routing (FAR). This method keeps the message as far from the faulty nodes as possible. The proposed method applies the Hopfield neural network. In comparison with other neural routing methods, FAR requires a small number of neurons. The simulation results show that FAR has good performance in larger interconnection networks and in networks with high density of faulty nodes.