Reliable broadcasting in faulty hypercube computers

Abstract

A nonredundant broadcasting algorithm for faulty hypercube computers is proposed. The concept of unsafe nodes is introduced to identify those nonfaulty nodes that will cause a detour or backtracking because of their proximity to faulty nodes. It is assumed that each healthy node, safe or unsafe, knows the status of all the neighboring nodes. The broadcasting is optimal, meaning that a message is sent to each node via a Hamming distance path if the broadcasting is initiated from a safe node. It is also shown that when the source node is unsafe and there is an adjacent safe node, then the broadcasting can be achieved with only one more time step than the fault-free case.<>