RL-Legalizer: Reinforcement Learning-based Mixed-Height Standard Cell Legalization
This project is implemented by Sung-Yun Lee and Seonghyeon Park (Advisor: Seokhyeong Kang).
CAD & SoC Design Lab., POSTECH, Rep. of Korea. (link)
Contact: [email protected]
Title: "RL-Legalizer: Reinforcement Learning-based Cell Priority Optimization in Mixed-Height Standard Cell Legalization"
Authors: S.-Y. Lee, S. Park, D. Kim, M. Kim, T. P. Le and S. Kang
Conference: 2023 26th IEEE/ACM Design, Automation and Test in Europe Conference & Exhibition (DATE 2023) (link)
OpenDP: Open Source Detailed Placement Engine
Reference paper: S. Do, M. Woo and S. Kang, "Fence-region-aware mixed-height standard cell legalization,” in IEEE/ACM Grate Lakes Symposium on VLSI (GLSVLSI) 2019 (link)
This legalizer has been embedded in OpenROAD
RLagent.py: PyTorch RL agent (including agent, model, train algorithms, environment, etc.)