Machine Learning Applications in Electronic Design Automation

Introduction.- Analysis of Digital Design: Routability Optimization for Industrial Designs at Sub-14nm Process Nodes Using Machine Learning.- RouteNet: Routability Prediction for Mixed-size Designs Using Convolutional Neural Network.- High Performance Graph Convolutional networks with Applications in Testability Analysis.- MAVIREC: ML-Aided Vectored IR-Drop Estimation and Classification.- GRANNITE: Graph Neural Network Inference for Transferable Power Estimation.- Machine Learning-Enabled High-Frequency Low-Power Digital Design Implementation at Advanced Process Nodes.- Optimization of Digital Design: Chip Placement with Deep Reinforcement learning.- DREAMPlace: Deep Learning Toolkit-Enabled GPU Acceleration for Modern VLSI Placement.- TreeNet: Deep Point Cloud Embedding for Routing Tree Construction.- Asynchronous Reinforcement Learning Framework for Net Order Exploration in Detailed Routing.- Standard Cell Routing with Reinforcement Learning and Genetic Algorithm in Advanced Technology Nodes.- PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning.- GAN-CTS: A Generative Adversarial Framework for Clock Tree Prediction and Optimization.- Analysis and Optimization of Analog Design: Machine Learning Techniques in Analog Layout Automation.- Layout Symmetry Annotation for Analog Circuits with Graph Neural Networks.- ParaGraph: Layout parasitics and device parameter prediction using graph neural network.- GCN-RL circuit designer: Transferable transistor sizing with graph neural networks and reinforcement learn.- Parasitic-Aware Analog Circuit Sizing with Graph Neural Networks and Bayesian Optimization.- Logic and Physical Verification: Deep Predictive Coverage Collection/ Dynamically Optimized Test Generation Using Machine Learning.- Novelty-Driven Verification: Using Machine Learning to Identify Novel Stimuli and Close Coverage.- Using Machine Learning Clustering To Find Large Coverage Holes.- GAN-OPC: Mask optimization with

Haoxing Ren (Mark) was born in Nanchang, China in 1976. He received two BS degrees in Electrical Engineering and Finance, and MS degree in Electrical Engineering from Shanghai Jiao Tong University, China in 1996, and 1999, respectively; MS in Computer Engineering from Rensselaer Polytechnic Institute in 2000; and PhD in Computer Engineering from University of Texas at Austin in 2006. From 2000 to 2015, he worked at IBM Microelectronics and Thomas J. Watson Research Center (after 2006) developing physical design and logic synthesis tools and methodology for IBM microprocessor and ASIC designs. He received several IBM technical achievement awards including the IBM Corporate Award for his work on improving microprocessor design productivity. After his 15 years tenue at IBM, he had a brief stint as a technical executive at a chip design start-up developing server-class CPUs based on IBM OpenPOWER technology. In 2016, Mark joined NVIDIA Research where he currently leads theDesign Automation research group, whose mission is to improve the quality and productivity of chip design through machine learning and GPU accelerated tools. He published many papers in the field of design automation including several book chapters in logic synthesis and physical design. He also received the best paper awards at International Symposium on Physical Design (ISPD) in 2013, Design Automation Conference (DAC) in 2019 and IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems in 2021. Jiang Hu received the B.S. degree in optical engineering from Zhejiang University (China) in 1990, the M.S. degree in physics in 1997 and the Ph.D. degree in electrical engineering from the University of Minnesota in 2001. He worked with IBM Microelectronics from January 2001 to June 2002.