Why high-quality verification data is impeding research into machine learning in functional verification.
Functional verification is computationally and data-intensive by nature, making it a natural target of machine learning applications. This paper provides a comprehensive and up-to-date analysis of FV problems addressable by ML.
Among the various ML techniques and algorithms, several emerging ones have demonstrated outstanding potential in FV. Yet despite the promising research results, critical challenges remain for applying ML in the industrial EDA environment. As well, the unavailability of high-quality verification data is impeding the research of ML in FV, so the authors call for further contributions to open verification datasets.
Read more in the white paper.
 |
 |
 |
 |
 |
 |
 |
 |
 |
Leave a Reply