Electronic Design Automation

Electronic Design Automation #

Electronic Design Automation (EDA) involves computational tools for designing and verifying electronic circuits and systems. ML approaches optimize placement, routing, timing, and other design parameters.

Recent Literature #

1. Machine Learning for Electronic Design Automation: A Survey ACM Transactions on Design Automation of Electronic Systems, 2021. paper

   Guyue Huang, Jingbo Hu, Yifan He, Jialong Liu, Mingjie Liu, Zhaoyang Shen, Jian Shi, Yuanfeng Peng, Chenxi Wang, Bin He, Young-Joon Lee, Haoxing Ren

2. Chip Placement with Deep Reinforcement Learning ICLR, 2021. paper, code

   Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, Joe Jiang, Ebrahim Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Olivier Bastien, Joe Bobba, Naveen Bobbili, Paul N. Chen, Mike Compt, Paul H. Huang, Abe Kahng, Seunggeun Lee, Megan Li, Lukasz Lew, Mark Marson, Peilin Song, Sameer Vora, Jeff Weinberg, Zihan Ye, Hailong Yun

3. RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN NSDI, 2019. paper, code

   Gerardo Ferrando, Eduard Almendares, Miquel Ferriol, Albert López, David Cordobés, Sergi Abadal, Eduard Alarcón, Albert Cabellos-Aparicio, Jordi Suñé

4. Learning Heuristics over Large Graphs via Deep Reinforcement Learning ICLR, 2018. paper

   Guyue Huang, Zemin Wang, Haoxing Ren

5. GCN-RL Circuit Designer: Transferable Transductive Boundary Search for Analog Circuit Optimization ICLR, 2022. paper, code

   Keren Zhu, Mingjie Liu, Yaguang Li, Yisong Yue, Haoxing Ren

6. RL4RewriteRules: Generating Rewrite Rules from Offline Reinforcement Learning Trajectories NeurIPS, 2024. paper, code

   Kaiyuan Hu, Runpeng Guo, Changlin Yan, Jianye Hao, Ping Zhang