Detecting Stimuli with Novel Temporal Patterns to Accelerate Functional Coverage Closure
Detecting Stimuli with Novel Temporal Patterns to Accelerate Functional Coverage Closure
Novel test selectors have proven effective in accelerating the closure of functional coverage for various industrial digital designs in simulation-based verification. However, detecting stimuli with novel temporal patterns is largely unexplored. This presentation introduces two novel test selectors aimed at identifying such stimuli. Experiments show both selectors accelerate functional coverage for a commercial bus bridge compared to random test selection. One selector achieves a 26.9% reduction in the number of simulated tests needed to reach 98.5% coverage, outperforming two previously published selectors by factors of 13 and 2.68, respectively.
Xuan Zheng is a final-year PhD student at the University of Bristol, specializing in automating Design Verification through Machine Learning. Over the past few years, he has collaborated with Infineon, Bristol, and successfully demonstrated the effectiveness of several novel test selectors in accelerating the convergence of functional coverage.