Lightning Talk - ML for EDA: Hype or Reality?
DescriptionThere is buzz around a new generation of EDA/CAD tools based on machine learning that could drastically reduce time to market and achieve superhuman performance. Is this hype warranted? In this talk, I will discuss the why, what, and how of ML for EDA using two problems as case studies: (1) large language model-based automatic Verilog code generation from natural language specifications; and (2) reinforcement learning for logic synthesis. I will highlight encouraging preliminary results that demonstrate the massive potential to substantially improve design quality and/or time-to-market, as well as roadblocks to achieving this potential including the (non)-availability of large and high-quality datasets. I will conclude with some directions for future research.
TimeWednesday, July 12th1:30pm - 1:40pm PDT
Location3004, 3rd Floor