Spare sharing network enhancement for scalable systems

Future systems based on nano-scale devices will provide great potentials for scaling up in system complexity, yet at the same time be highly susceptible to operational faults. While spare units can be used to enhance reliability through the repair-based approaches, redundancy is most effectively utilized if any spare unit can be used to replace any faulty unit. However, such a scheme demands a fully connected network of spare sharing, and will be dreadfully expensive when system size and complexity scale up. In this paper, we focus on scalable systems with spare units shared under interconnect constraints in a limited way. Particularly, we propose an approach to add a small number of connections in the “spare sharing network” to boost system reliability. The proposed methodology identifies and connects the vulnerable units to the exploitable spares, thus strengthening the entire system at low cost. Simulation results confirm that the proposed methodology boosts reliability at the small cost of a few additional interconnections.