Adaptive voting for fault (VFF) node scheme for distributed self-diagnosis

Distributed self-diagnosis has long been proposed to efficiently test multiprocessor and array based systems. Such an approach is also now being considered for testing integrated circuit wafers containing identical circuits. Here the testing is based on a majority voting on the test results from neighboring nodes. The authors identify that the voting for faulty node (VFF) always performs better than the voting for good node (VFG), irrespective of the number of voting cells and fault rate. Based on the VFF approach, an approach to find the optimal number of tests allowing the most accurate test results is proposed. The authors also introduce an adaptive voting scheme by which the time overhead of the traditional voting schemes can be significantly reduced.