At DAC56 in Las Vegas we talked a lot about automatic debug powered by machine learning, both with engineers at our booth and with Sanjay Gangal, EDACafé. For the first time at DAC we presented real cases of features we use to predict bugs using machine learning. This was well received and gave engineers a better understanding how it all works.

The local industry in Las Vegas does not have any local ASIC industry which led to fewer engineers attending the show, but on the other hand more Elvis impersonators

 

We presented at a completely new show focused on innovation within the verification space - Verification 3.0 Innovation Summit. All the verification technology leaders were there: Breker, OneSpin, Imperas, Vayavya, Agnisys, Methodics, Vtool, Verifyter and many more.

Verification 3.0 was held at the Levi's Stadium Auditorium. After some welcoming words by Jim Hogan the show started with the keynote speech from Joe Costello. It ended many interesting presentations later with Verifyter's talk about predicting bugs (see picture below) expanding on our DVCon poster we presented recently, digging deeper into what we actually mean with "features". The day finished off with a reception in the Oak Room situated high up in the stadium with an amazing view.

We presented the poster "Predicting Bad Commits" at DVCon, Feb 26 2019, San Jose, CA , where we explored the feasibility of using machine learning to predict bugs. Bug prediction occurs before tests are launched. At this time there is not even a test failure to analyze.

The idea is that the better you can predict bugs the better you can control the verification flow. This means that you can control whether to run a large/small test suite depending on how risky the recent changes are. Also debugging of bugs takes less time as you know the most likely culprits before you start.

We also participated in a round table discussion on AI and EDA, which will end up as an article series by Brian Baily in semiengineering.com

Larry Melling (Cadence), Harry Foster (Mentor), Daniel Hansson (Verifyter), Manish Pandey (Carnegie Mellon), Doug Letcher (Metrics), Raik Brinkmann (OneSpin) 

At our booth we talked about bug prediction and automatic debug at our booth, which had quite a few visitors. According to our scientific studies machine learning attracts more engineers than candy these days :-)