DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
Chen-Chia Chang, Chia-Tung Ho, Yaguang Li, Yiran Chen, Haoxing Ren

TL;DR
DRC-Coder is an innovative multi-agent framework that leverages vision and language models to automate the generation and debugging of DRC code, significantly reducing time and human effort in advanced technology node design workflows.
Contribution
It introduces a novel multi-agent system integrating vision and large language models for automated DRC code generation and debugging, outperforming standard prompting methods.
Findings
Achieves perfect F1 score of 1.000 in code generation for a 3nm node.
Generates DRC code within four minutes per rule.
Outperforms standard prompting techniques with F1=0.631.
Abstract
In the advanced technology nodes, the integrated design rule checker (DRC) is often utilized in place and route tools for fast optimization loops for power-performance-area. Implementing integrated DRC checkers to meet the standard of commercial DRC tools demands extensive human expertise to interpret foundry specifications, analyze layouts, and debug code iteratively. However, this labor-intensive process, requiring to be repeated by every update of technology nodes, prolongs the turnaround time of designing circuits. In this paper, we present DRC-Coder, a multi-agent framework with vision capabilities for automated DRC code generation. By incorporating vision language models and large language models (LLM), DRC-Coder can effectively process textual, visual, and layout information to perform rule interpretation and coding by two specialized LLMs. We also design an auto-evaluation…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
