FAE: Autoencoder-Based Failure Binning of RTL Designs for Verification and Debugging

As the Register Transfer Level (RTL) designs are more complicated, debugging becomes a major bottleneck in the design process. To make debugging more efficient, failure binning aims at grouping failure traces caused by the same error source together so that designers can focus on one bug at one time. However, as there are multiple bugs in a design, behaviors exhibited by failure traces are diverse and severely confuse designers. One error source may result in different appearances subject to different activation conditions. In addition, different error sources may also exhibit similar appearances among the limited number of failure traces. In this work, we propose an autoencoder-based failure binning engine name FAE for debugging RTL designs more efficiently. The autoencoders extract meaningful representations from the sparse and high-dimensional feature space to the latent space with good properties for clustering. Superior to prior works, FAE provides confidence ranks between bins and in a bin to clearly guide designers during debugging. Experimental results show that FAE can drive bins of higher purity under an acceptable number of bins than prior works, dropping only few less-informative failures. Evaluated by three common metrics for clustering, FAE also achieves averagely 13.1% improvement in purity, 25.0% improvement in NMI and 18.2% improvement in ARI, respectively. As a result, the proposed autoencoder-based engine, FAE, applies machine learning to extract useful information from diverse failure traces and is effective on failure binning with more focused debugging.