Variability has emerged as a fundamental challenge to IC design in scaled CMOS technology; and it has profound impact on nearly all aspects of circuit performance. While some of the negative effects of variability can be handled via improvements in the manufacturing process, comprehensive methods are necessary to assess and manage the negative effects of variability, which in turn requires accurate and tractable variability models. The goal of the VMC workshop is to provide a forum for theoreticians and practitioners to freely exchange opinions on current practices as well as future research needs in variability modeling and characterization. In this year's edition of the VMC workshop, particular emphasis will be placed on the applications of machine-learning techniques to the variability topics listed below.
The workshop organizers strongly encourage the submission of early results in the related topics. The submissions will be promptly evaluated and the author(s) of the accepted submissions are expected to present the results in a poster format preceded by a brief introductory presentation at the workshop. Distribution of Workshop Proceedings is limited to attendees.
Key Topics
Fundamental physics of device variability
Compact variability modeling development and applications
Statistical extraction of variability
Variability test structure design and calibration
Design interface with manufacturing and solutions for variability
Variability issues in emerging semiconductor technology
Temporal variability issues
Reliability considerations that may be closely related to variability
Variability in computing and systems
Agenda
1:00 – 1:10pm
Welcome Note and Opening Remarks: Abe Elfadel (Khalifa U., UAE)
1:10 – 1:50pm
Yiorgos Makris (UT Dallas, USA)
Machine Learning in Semiconductor Manufacturing
and Test: Can Deep Learning Save The Day?
1:50 – 2:30pm
Zheng Zhang (UC Santa Barbara, USA)
Data-Efficient Machine Learning for Variation-Aware
Design Automation: A Tensor Perspective
2:30 – 3:10pm
Youngsoo Shin (KAIST, Korea)
Lithography Optimizations through Machine Learning
3:10 – 3:50pm
Poster Pitches/Coffee Break/Poster Viewing
3:50 – 4:30pm
Mehdi Tahoori (Karlsruhe Institute of Technology, Germany)
Machine Learning for Variability Modeling and
Mitigation of Energy-constrained Systems
4:30 – 5:10pm
Victor Kravets (IBM Research, USA)
Application of Boolean Sampling and Learning to the
Error Localization and Correction in Semiconductor Designs
5:10 – 5:40pm
Panel: Machine Learning and VMC
5:40 – 6:00pm
Wrap-up and Closing Remarks:
Abe Elfadel (Khalifa U., UAE)
|