Skip to content

Program

The program of the MLCAD Workshop 2022 is now available. Download the program!

Sept. 11, 2022, Snowbird, Utah

18:00 – 21:00 Welcome Reception


Sept. 12, 2022, Snowbird, Utah

08:00 – 08:45 Keynote: Engineering the Flywheel of AI for Electronic Design Automation: Present Challenges and Future Opportunities
Ruchir Puri – IBM
Moderator: Paul Franzon – North Carolina State University

08:45 – 10:00 Session 1: Physical Design and Optimization with ML
Session Chair: Ioannis Savidis – Drexel University

Placement Optimization via PPA-Directed Graph Clustering [best paper candidate]
Yi-Chen Lu – Georgia Institute of Technology, USA
Tian Yang – NVIDIA, USA
Sung Kyu Lim – Georgia Institute of Technology, USA
Haoxing Ren – NVIDIA, USA

From Global Route to Detailed Route: ML for Fast and Accurate Wire Parasitics and Timing Prediction
Vidya A. Chhabria, Wenjing Jiang – University of Minnesota, USA
Andrew B. Kahng – University of California, San Diego, USA
Sachin Sapatnekar – University of Minnesota, USA

Faster FPGA Routing by Forecasting and Pre-Loading Congestion Information
Umair Siddiqi – King Fahd University of Petroleum and Minerals, Saudi Arabia
Timothy Martin, Sam Van Den Eijnden, Ahmed Shamli, Gary Grewal – University of Guelph, Canada
Sadiq Sait – King Fahd University of Petroleum and Minerals, Saudi Arabia
Shawki Areibi – University of Guelph, Canada

10:00 – 10:20 Break

10:20 – 12:00 Session 2: Machine Learning for Analog Design
Session Chair: Tsung-Wei Huang – University of Utah

Deep Reinforcement Learning for Analog Circuit Sizing with an Electrical Design Space and Sparse Rewards
Yannick Uhlmann, Michael Essich, Lennart Bramlage, Jürgen Scheible, Cristóbal Curio – Reutlingen University, Germany

LinEasyBO: Scalable Bayesian Optimization Approach for Analog Circuit Synthesis via One-Dimensional Subspaces
Shuhan Zhang – Fudan University & The University of Texas at Austin
Fan Yang, Changhao Yan – Fudan University, China
Dian Zhou – The University of Texas at Dallas, USA
Xuan Zeng – Fudan University, China

RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL
Wei Shi – The University of Texas at Austin, USA
Hanrui Wang – Massachusetts Institute of Technology, USA
Jiaqi Gu, Mingjie Liu, David Z. Pan – The University of Texas at Austin, USA
Song Han – Massachusetts Institute of Technology, USA
Nan Sun – Tsinghua University, China & The University of Texas at Austin, USA

Automatic Analog Schematic Diagram Generation based on Building Block Classification and Reinforcement Learning
Hung-Yun Hsu, Mark Po-Hung Lin – National Yang Ming Chiao Tung University, Taiwan

12:00 – 13:00 Lunch

13:00 – 13:30 Plenary: The changing landscape of AI-driven System Optimization for Complex Combinatorial Optimization
Somdeb Majumdar, Intel AI labs
Moderator: Andrew Kahng – University of California at San Diego

13:30 – 14:30 Invited Session 1
Session Chair: Hai (Helen) Li – Duke University

AI Chips Built by AI – Promise or Reality? An Industry Perspective
Thomas Andersen, Synopsys

ML for Analog Design: Good Progress, but More to Do
Borivoje Nikolić – University of California, Berkeley

14:30 – 14:45 Break

14:45 – 16:00 Session 3: Circuit Evaluation and Simulation with ML
Session Chair: Hussam Amrouch – University of Stuttgart

SpeedER: A Supervised Encoder-Decoder Driven Engine for Effective Resistance Estimation of Power Delivery Networks [best paper candidate]
Bing-Yue Wu, Shao-Yun Fang – National Taiwan University of Science and Technology, Taiwan
Hsiang-Wen Chang, Peter Wei – Synopsys, Taiwan

XT-PRAGGMA: Crosstalk Pessimism Reduction Achieved with GPU Gate-level Simulations and Machine Learning
Vidya A. Chhabria – University of Minnesota, USA
Ben Keller, Yanqing Zhang, Sandeep Vollala, Sreedhar Pratty, Haoxing Ren, Brucek Khailany – NVIDIA, USA

Fast Prediction of Dynamic IR-Drop Using Recurrent U-Net Architecture
Yonghwi Kwon, Youngsoo Shin – Korea Advanced Institute of Science and Technology, South Korea

16:00 – 16:15 Break

16:15 – 17:30 Session 4: DRC, Test and Hotspot Detection using ML Methods
Session Chair: Hai (Helen) Li – Duke University

Efficient Design Rule Checking Script Generation via Key Information Extraction [best paper candidate]
Binwu Zhu, Xinyun Zhang – The Chinese University of Hong Kong, Hong Kong
Yibo Lin – Peking University, China
Bei Yu, Martin Wong – The Chinese University of Hong Kong, Hong Kong

Scan Chain Clustering and Optimization with Constrained Clustering and Reinforcement Learning
Naiju Karim Abdul, George Antony, Rahul M. Rao, Suriya T. Skariah – IBM, India

Autoencoder-Based Data Sampling for Machine Learning-Based Lithography Hotspot Detection
Mohamed Tarek Ismail – Siemens EDA & American University in Cairo, Egypt
Hossam Sharara – American University in Cairo, Egypt
Kareem Madkour – Siemens EDA, Egypt
Karim Seddik – American University in Cairo, Egypt

18:00 – 20:00 Dinner and PanelTop 5 Opportunities for ML Disruption
Brucek Khailany – NVIDIA
Ming Zhang – Synopsys
Rajeev Jain – Qualcomm
Ulf Schlichtmann – TU Munich
Andrew Kahng – UC San Diego
Moderator: Marilyn Wolf – University of Nebraska-Lincoln


Sept. 13, 2022, Snowbird, Utah

08:30 – 09:15 Keynote: AI/ML and Semiconductor research at NSF
Sankar Basu – NSF
Moderator: Andrew Kahng – University of California at San Diego

09:15 – 10:30 Session 5: Power and Thermal Evaluation with ML
Session Chair: Ulf Schlichtmann – Technical University of Munich

Driving Early Physical Synthesis Exploration through End-of-Flow Total Power Prediction
Yi-Chen Lu – Georgia Institute of Technology, USA
Wei-Ting Chan, Vishal Khandelwal – Synopsys, USA
Sung Kyu Lim – Georgia Institute of Technology, USA

Towards Neural Hardware Search: Power Estimation of CNNs for GPGPUs with Dynamic Frequency Scaling
Christopher A. Metz – University Bremen, Germany
Mehran Goli, Rolf Drechsler – University Bremen/DFKI, Germany

A Thermal Machine Learning Solver for Chip Simulation
Rishikesh Ranade, Haiyang He, Jay Pathak, Norman Chang, Akhilesh Kumar, Jimin Wen – Ansys Inc, USA

10:30 – 10:45 Break

10:45 – 12:00 Session 6: Performance Prediction with ML Models and Algorithms
Session Chair: Cunxi Yu – University of Utah

Physically Accurate Learning-based Performance Prediction of Hardware-accelerated ML Algorithms
Hadi Esmaeilzadeh, Soroush Ghodrati, Andrew B. Kahng, Joon Kyung Kim, Sean Kinzer, Sayak Kundu, Rohan Mahapatra – University of California, San Diego, USA
Susmita Dey Manasi, Sachin S. Sapatnekar – University of Minnesota, USA
Zhiang Wang – University of California, San Diego, USA
Ziqing Zeng – University of Minnesota, USA

Graph Representation Learning for Gate Level Arrival Time Prediction
Pratik Shrestha, Saran Phatharodom, Ioannis Savidis – Drexel University, USA

A Tale of EDA’s Long Tail: Long-Tailed Distribution Learning for Electronic Design Automation
Zixuan Jiang, Mingjie Liu – The University of Texas at Austin, USA
Zizheng Guo – Peking University, China
Shuhan Zhang – The University of Texas at Austin, USA
Yibo Lin – Peking University, China
David Z. Pan – The University of Texas at Austin, USA

12:00 – 13:00 Lunch

13:00 – 13:30 Plenary: Industrial Experience with Open-Source EDA Tools
Christian Lück, Daniela Sánchez Lopera – Infineon Technologies AG, Germany
Sven Wenzek – EPOS Embedded Core & Power Systems
Wolfgang Ecker – Infineon Technologies AG, Germany
Moderator: Ulf Schlichtmann – Technical University of Munich

13:30 – 14:30 Invited Session 2
Session Chair: Paul Franzon – North Carolina State University

Machine Learning for the Design of Microelectronic Systems
Madhavan Swaminathan, Gaeorgia Institute of Technology

MLCAD Algorithms & Solutions to Redefine the Design Process of Complex SoCs
Venu Sanaka, Qualcomm

14:30 – 16:10 Session 7: ML Models for Analog Design and Optimization
Session Chair: Hussam Amrouch – University of Stuttgart

Invertible Neural Networks for Design of Broadband Active Mixers
Oluwaseyi Akinwande, Osama Waqar Bhatti, Xingchen Li, Madhavan Swaminathan – Georgia Institute of Technology, USA

High Dimensional Optimization for Electronic Design
Yuejiang Wen, Jacob Dean, Brian A. Floyd, Paul Franzon – North Carolina State University, USA

Transfer of Performance Models Across Analog Circuit Topologies with Graph Neural Networks
Zhengfeng Wu, Ioannis Savidis – Drexel University, USA

RxGAN: Modeling High-Speed Receiver through Generative Adversarial Networks
Priyank Kashyap, Archit Gajjar – North Carolina State University, USA
Yongjin Choi – Hewlett Packard Enterprise, USA
Chau-Wai Wong, Dror Baron, Tianfu Wu – North Carolina State University, USA
Chris Cheng – Hewlett Packard Enterprise, USA
Paul Franzon – North Carolina State University, USA

16:10 – Social Event: Half day activity pass (included) and dinner https://www.snowbird.com/summer-activities/