Machine Learning… Everywhere!

Over the years, the EDA industry has offered many solutions in the modeling and design creation of complex systems. Most design problems in EDA are NP-hard; there are simply no polynomial-time algorithms to solve these problems and hence an optimal solution cannot be identified analytically. Furthermore, the interdependence of design requirements exacerbates these problems, requiring concurrent optimization across multiple design cycle stages.

 

Self-Optimizing Design Tools

New, ML-driven capabilities can be embedded in different design engines, giving EDA developers a new arsenal of solutions for today’s demanding semiconductor design environment. With an abundance of data and a rich set of heuristics, new classes of ML models can be created using ensemble methods (e.g., linear regression, support vector machines, neural networks) to exploit opportunities throughout the design cycle.

Machine learning-driven chip design represents a paradigm shift which delivers a significant QoR and productivity leap. We are extremely impressed with Synopsys for making the ML vision a reality in IC Compiler II and delivering exceptional QoR results."

Youngmin Shin

|

Vice President, Samsung Electronics

Machine Learning Resources

International Symposium on Physical Design - Best Paper Award 2021

Synopsys wins for Machine Learning-Enabled High-Frequency Low-Power Digital Design Implementation at Advanced Process Nodes by Siddhartha Nath and Vishal Khandelwal, Synopsys