Detecting Stimuli with Novel Temporal Patterns to Accelerate Functional Coverage Closure
Xuan Zheng, Tim Blackmore, James Buckingham, Kerstin Eder
TL;DR
The paper tackles the challenge of slow coverage closure in verification by addressing the inefficiency of random test selection and the lack of emphasis on novel temporal patterns in sequential stimuli. It introduces two DL-based test selectors—the transformer encoder and the LSTM autoencoder—that operate on sliding-window sequences of transactions to detect novelty and prioritize simulation. Empirical evaluation on a commercial SRI bus-bridge DUV shows substantial improvements over random selection, with the LSTM-based selector achieving up to 26.9% reduction in simulated tests to reach 98.5% coverage and saving up to ~$254.53$ hours on a single license, outperforming prior methods by factors of 13 and 2.68. The approach is automated, scalable to industrial designs, and integrates with existing CDV workflows, with potential enhancements via reinforcement learning to further accelerate coverage closure.
Abstract
Novel test selectors have demonstrated their effectiveness in accelerating the closure of functional coverage for various industrial digital designs in simulation-based verification. The primary advantages of these test selectors include performance that is not impacted by coverage holes, straightforward implementation, and relatively low computational expense. However, the detection of stimuli with novel temporal patterns remains largely unexplored. This paper introduces two novel test selectors designed to identify such stimuli. The experiments reveal that both test selectors can accelerate the functional coverage for a commercial bus bridge, compared to random test selection. Specifically, one selector achieves a 26.9\% reduction in the number of simulated tests required to reach 98.5\% coverage, outperforming the savings achieved by two previously published test selectors by factors of 13 and 2.68, respectively.