ChipMind: Retrieval-Augmented Reasoning for Long-Context Circuit Design Specifications

While Large Language Models (LLMs) demonstrate immense potential for automating integrated circuit (IC) development, their practical deployment is fundamentally limited by restricted context windows. Existing context-extension methods struggle to achieve effective semantic modeling and thorough multi-hop reasoning over extensive, intricate circuit specifications. To address this, we introduce ChipMind, a novel knowledge graph-augmented reasoning framework specifically designed for lengthy IC specifications. ChipMind first transforms circuit specifications into a domain-specific knowledge graph (ChipKG) through the Circuit Semantic-Aware Knowledge Graph Construction methodology. It then leverages the ChipKG-Augmented Reasoning mechanism, combining information-theoretic adaptive retrieval to dynamically trace logical dependencies with intent-aware semantic filtering to prune irrelevant noise, effectively balancing retrieval completeness and precision. Evaluated on an industrial-scale specification reasoning benchmark, ChipMind significantly outperforms state-of-the-art baselines, achieving an average improvement of 34.59% (up to 72.73%). Our framework bridges a critical gap between academic research and practical industrial deployment of LLM-aided Hardware Design (LAD).

Authors

• Changwen Xing School of Integrated Circuits, Southeast University, Nanjing, China National Center of Technology Innovation for EDA, Nanjing, China
• SamZaak Wong School of Integrated Circuits, Southeast University, Nanjing, China National Center of Technology Innovation for EDA, Nanjing, China
• Xinlai Wan National Center of Technology Innovation for EDA, Nanjing, China
• Yanfeng Lu National Center of Technology Innovation for EDA, Nanjing, China
• Mengli Zhang National Center of Technology Innovation for EDA, Nanjing, China
• Zebin Ma National Center of Technology Innovation for EDA, Nanjing, China
• Lei Qi School of Computer Science and Engineering, Southeast University, China
• Zhengxiong Li Department of Computer Science and Engineering, University of Colorado Denver, USA
• Nan Guan Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China
• Zhe Jiang University of Florida
• Xi Wang
• Jun Yang Department of Automation, Tsinghua University

Keywords

No keywords are indexed for this paper.