D2D-GPT: Leveraging Incremental Learning GPT for Seamless Design Rule Conversion Across EDA Tools
This paper investigates the use of fine-tuned ChatGPT, in Electronic Design Automation (EDA) for Design Rule Checking (DRC). As integrated circuits grow in complexity, so do the design rules, exacerbated by the diversity of EDA tools with unique DRC specifications. We introduce D2D-GPT, a unified tool leveraging ChatGPT’s language capabilities to translate DRC specifications across different EDA platforms. This research focuses on optimizing input datasets - native DRC rules - to improve ChatGPT’s translation accuracy and efficiency. Our objective is to streamline the EDA workflow, bridge gaps between various tools, and pave the way for more cohesive design processes in the semiconductor industry.
Authors
- Wangzilu Lu (ORCID: https://orcid.org/0000-0003-0046-9004)
- Minghui Yin (ORCID: https://orcid.org/0000-0001-9966-9879)
- Jiajie Huang (ORCID: https://orcid.org/0000-0001-9209-9754)
- Qing Zhang (ORCID: https://orcid.org/0000-0002-2940-7440)
- Yuhang Zhang (ORCID: https://orcid.org/0000-0002-4101-6207)
- Yongfu Li (ORCID: https://orcid.org/0000-0002-6322-8614)
- Yunxiang Zhang (ORCID: https://orcid.org/0000-0002-8886-975X)
- Zhiqiang Li (ORCID: https://orcid.org/0009-0003-7463-8576)
- Chao Wang (ORCID: https://orcid.org/0000-0001-7885-9673)
Institutions
- Shanghai Jiao Tong University (CN)
- Chinese Academy of Sciences (CN)
- Institute of Microelectronics (CN)
Publication Details
- Published
- 2024-11-07
- DOI
- https://doi.org/10.1109/apccas62602.2024.10808537
- Citations
- 4
- Primary Topic
- Machine Learning and Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 1.39
Funders
- National Science Foundation
- Ministry of Education
- Shanghai Jiao Tong University