摘要：In a parallel computer system with faulty processors, it is highly desirable to reconfigure the system by eliminating the faulty ones and thereby restore the system to some operational state. In the reconfiguration maintaining the maximum size fault-free subsystem is the main problem. In this paper, we propose an efficient scheme for identifying maximum size fault-free submeshes in a faulty torus-connected multicomputer system. For this, the relations between two submeshes have been defined. Then we take two-phase approach. In the first phase, an efficient algorithm for determining maximal faulty submeshes in a faulty torus has been introduced. In the second phase, we have introduced a procedure to identify the maximal fault-free submeshes by removing all faulty submeshes from a whole torus. The time complexity of the proposed scheme is O(Nf3) where Nf is the number of faulty processors in a 2D torus. The proposed scheme can be utilized to the task allocation in 2D tori in the presence of failed nodes.
