Output compression for IC fault detection using compressive sensing

The process of detecting logical faults in integrated circuits (ICs) due to manufacturing variations is bottlenecked by the I/O cost of scanning in test vectors and offloading test results. Traditionally, the output bottleneck is alleviated by reducing the number of bits in output responses using XOR networks, or computing signatures from the responses of multiple tests. However, these many-to-one computations reduce test time at the cost of higher detection failure rates, and lower test granularity. In this paper, we propose an output compression approach that uses compressive sensing to exploit the redundancy of correlated outputs from closely related tests, and of correlated faulty responses across many circuits. Compressive sensing's simple encoding method makes our approach attractive because it can be implemented on-chip using only a small number of accumulators. Through simulation, we show that our method can reduce the output I/O bottleneck without increasing failure rates, and can reconstruct higher granularity results off-chip than current compaction approaches.