RTL regression test selection using Machine Learning
TimeWednesday, December 8th6:00pm - 7:00pm PST
LocationLevel 2 - Lobby
DescriptionWe address the problem of minimizing the validation cost of iterative changes in RTL design cycles. Our approach learns characteristics of both RTL code and tests during the verification process to generate estimated likelihoods that a test will expose a latent bug introduced by incremental design modifications. This paper describes our online machine learning approach to the problem and its implementation. We also present experiments on several real-world designs of various types with different types of test-suites that demonstrate significant time and resource savings while maintaining validation quality.