A reconfigurable modular fault-tolerant hypercube architecture

摘要

We propose a new fault-tolerant design of a hypercube system. We first build the fault-tolerant modules (FTM's), then we interconnect these FTM's as the modular hypercube. Finally, we obtain our proposed system by augmenting links, called the spare-sharing links (SSL's), in the modular hypercube, which forms a ring connection in our architecture. The characteristic of our system is that the spare nodes in an FTM can be used as local spares to replace the faulty nodes in the FTM, or as remote spares to replace the faulty nodes in other FTM's via the spare-sharing links in the architecture. Thus, the use of spare nodes in any FTM will increase, and the proposed system reliability will improve. In the system, the switch and link failures are also considered. The modular diagnosis and modular reconfiguration are proposed to identify and reconfigure the failure of nodes, switches, and links.