Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2405.14918 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910463852281856 |
|---|---|
| author | Lai, Yao Lee, Sungyoung Chen, Guojin Poddar, Souradip Hu, Mengkang Pan, David Z. Luo, Ping |
| author_facet | Lai, Yao Lee, Sungyoung Chen, Guojin Poddar, Souradip Hu, Mengkang Pan, David Z. Luo, Ping |
| contents | Analog circuit design is a significant task in modern chip technology, focusing on the selection of component types, connectivity, and parameters to ensure proper circuit functionality. Despite advances made by Large Language Models (LLMs) in digital circuit design, the complexity and scarcity of data in analog circuitry pose significant challenges. To mitigate these issues, we introduce AnalogCoder, the first training-free LLM agent for designing analog circuits through Python code generation. Firstly, AnalogCoder incorporates a feedback-enhanced flow with tailored domain-specific prompts, enabling the automated and self-correcting design of analog circuits with a high success rate. Secondly, it proposes a circuit tool library to archive successful designs as reusable modular sub-circuits, simplifying composite circuit creation. Thirdly, extensive experiments on a benchmark designed to cover a wide range of analog circuit tasks show that AnalogCoder outperforms other LLM-based methods. It has successfully designed 20 circuits, 5 more than standard GPT-4o. We believe AnalogCoder can significantly improve the labor-intensive chip design process, enabling non-experts to design analog circuits efficiently. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14918 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnalogCoder: Analog Circuit Design via Training-Free Code Generation Lai, Yao Lee, Sungyoung Chen, Guojin Poddar, Souradip Hu, Mengkang Pan, David Z. Luo, Ping Machine Learning Emerging Technologies Analog circuit design is a significant task in modern chip technology, focusing on the selection of component types, connectivity, and parameters to ensure proper circuit functionality. Despite advances made by Large Language Models (LLMs) in digital circuit design, the complexity and scarcity of data in analog circuitry pose significant challenges. To mitigate these issues, we introduce AnalogCoder, the first training-free LLM agent for designing analog circuits through Python code generation. Firstly, AnalogCoder incorporates a feedback-enhanced flow with tailored domain-specific prompts, enabling the automated and self-correcting design of analog circuits with a high success rate. Secondly, it proposes a circuit tool library to archive successful designs as reusable modular sub-circuits, simplifying composite circuit creation. Thirdly, extensive experiments on a benchmark designed to cover a wide range of analog circuit tasks show that AnalogCoder outperforms other LLM-based methods. It has successfully designed 20 circuits, 5 more than standard GPT-4o. We believe AnalogCoder can significantly improve the labor-intensive chip design process, enabling non-experts to design analog circuits efficiently. |
| title | AnalogCoder: Analog Circuit Design via Training-Free Code Generation |
| topic | Machine Learning Emerging Technologies |
| url | https://arxiv.org/abs/2405.14918 |