2020 International Conference On Computer Aided Design

The Premier Conference Devoted to Technical Innovations in Electronic Design Automation

November 2-5, 2020VIRTUAL CONFERENCE

MP Associates, Inc.
MONDAY November 02, 8:00am - 8:30am | Slot 4
EVENT TYPE: SPECIAL SESSION
SESSION 1D
How Machine Leaning can Reshape Technology, Manufacturability, Performance and Power
Moderators:
Ertugrul Demircan - NXP Semiconductors
Mark Johnstone - NXP Semiconductor , TX
Organizers:
Sheldon Tan - University of California , CA
Hussam Amrouch - Karlsruhe Institute of Technology, Karlsruhe, Germany
Recently machine learning, especially deep learning is gaining much attention due to the breakthrough performance in various cognitive applications. Machine learning for electronic design automation (EDA) is also gaining significant traction as it provides new computing and optimization paradigms for many challenging design automation problems with complex nature. Today’s chip designer and EDA developers faces several many challenges in advanced technologies from technology and physical levels to the circuit and multi-core chip levels such as designing robust circuits with high manufacturability and yield, excessive voltage IR drops, thermally constrained multi-core processor design and runtime thermal/power/reliability management and excessive on-chip power density and efficiency limitations due to fundamental restrictions in voltage scaling etc. Given the complex nature of those EDA problems, this special session focuses on complicated lithography modeling, efficient IR drop estimation, fast full-chip thermal/power modeling, design-technology co-optimization in advanced technologies and demonstrates the potentials in using latest advances in machine learning to tackle those hard problems towards developing intelligent EDA algorithms. This special session consists of four presentations ranging from machine Learning for VLSI manufacturability and yield, fast machine learning based IR drop estimation, data-driven full-chip thermal/power modeling, machine learning for modeling emerging technologies.

1D.1Re-examining VLSI Manufacturing and Yield through the Lens of Deep Learning
 Speaker: David Z. Pan - Univ. of Texas at Austin, TX
 Authors: Mohamed Mohamed Baker Alawieh - University of Taxes at Austin, TX
Wei Ye - University of Taxes at Austin, TX
David Z. Pan - Univ. of Texas at Austin, TX
1D.2Fast IR Drop Estimation with Machine Learning
 Speaker: Hai Li - Duke Univ., Durham, NC
 Authors: Zhiyao Xie - Duke Univ., Durham, NC
Hai Li - Duke Univ., Durham, NC
Xiaoqing Xu - Arm, Ltd.
Jiang Hu - Texas A&M Univ., College Station, TX
Yiran Chen - Duke Univ., Durham, NC
1D.3Full-Chip Thermal Map Estimation for Commercial Multi-Core CPUs with Generative Adversarial Learning
 Speaker: Sheldon Tan - Univ. of California, Riverside, CA
 Authors: Wentian Jin - Univ. of California, Riverside
Sheriff Sadiqbatcha - University of California, Riverside, CA
Jinwei Zhang - Univ. of California, Riverside, CA
Sheldon Tan - Univ. of California, Riverside, CA
1D.4Modeling Emerging Technologies using Machine Learning: Challenges and Opportunities
 Speaker: Hussam Amrouch - Univ. of Stuttgart, Germany
 Authors: Florian Klemme - Karlsruhe Institute of Technology, Karlsruhe, Germany
Jannik Prinz - Karlsruhe Institute of Technology, Germany
Victor van Santen - Karlsruhe Institute of Technology, Germany
Joerg Henkel - Karlsruhe Institute of Technology (KIT), , Germany
Hussam Amrouch - Univ. of Stuttgart, Germany