Reliability Evaluation of Hypercube Multicomputers

Performance evaluation and reliability prediction are two essential aspects of any study into the effectiveness of hypercube multicomputers. While performance models for hypercube systems have been reported extensively, reliability evaluation has not received much attention. This paper presents an analytic model for the reliability evaluation of hypercube multicomputers. The model is based on the decomposition principle, where a hypercube of a higher dimension is recursively decomposed into smaller hypercubes, until the reliability of the smallest cube is modeled exactly. The reliability of the large n-cube is then obtained from this smallest base model using a recursive equation. The reliability model used is task-based — it is assumed that the system is operational if a task can be executed on the system. Analytic results are given for n-dimensional hypercubes with up to 75% system degradation. The model is validated by comparing analytic results with simulation results.