學院消息

HOT NEWS

COLLEGE OF COMPUTER SCIENCE NYCU

最新消息

Machine Learning to the Rescue of IC Design

Date2019/01/31 00:24:44

Title: Machine Learning to the Rescue of IC Design: Recent Results, and a Roadmap of Open Research Challenges

Time: 107/07/12 (Thu) 10:00-12:30

 

Location: EC 345

 

Speaker: Prof. Andrew B. Kahng

 

Talk Abstract:

Over the coming decade, the semiconductor industry will increasingly draw on three “last levers” - cost, quality, and schedule – to continue the Moore's-Law trajectory of value scaling. These levers will require the broad enablement and application of machine learning, both inside and “around” design tools and flows. This talk reviews recent results and near-term opportunities for machine learning, with emphasis on IC physical implementation. Example classes of applications include (1) removing unnecessary design and modeling margins through correlation mechanisms; (2) achieving faster design convergence through prediction of tool/flow outcomes from attributes of both tools and design instances; and (3) corollary applications such as optimizing the usage of available design resources and schedule. I will conclude with a “roadmap” of open research challenges for machine learning in IC physical implementation, and of the implied challenges for infrastructure and culture change across the IC design ecosystem.

 

Bio:

Andrew B. Kahng is Professor of CSE and ECE at UC San Diego, where he holds the endowed chair in High-Performance Computing. He has served as visiting scientist at Cadence (1995-1997) and as founder/CTO at Blaze DFM (2004-2006). He is the coauthor of 3 books and over 400 journal and conference papers, holds 34 issued U.S. patents, and is a fellow of ACM and IEEE. He has served as general chair of DAC, ISQED, ISPD and other conferences. He served as international chair/co-chair of the Design technology working group, and of the System Integration focus team, for the International Technology Roadmap for Semiconductors (ITRS) from 2000-2016. His research interests include IC physical design and performance analysis, the IC design- manufacturing interface, combinatorial algorithms and optimization, and the roadmapping of systems and technology.

    Share this