集成电路与嵌入式系统2025，Vol.25Issue(8)：31-40,10.DOI:10.20193/j.ices2097-4191.2025.0043
基于大语言模型多智能体的端到端领域专用SoC设计
End-to-end domain-specific SoC design with LLM-based multi-agent
摘要
Abstract
As Moore's Law slows down,domain-specific SoC(DSSoC)has emerged as a promising energy-efficient design strategy by integrating domain-specific accelerator(DSA).However,the design process for DSSoC remains highly complex,leading to prolonged development cycles and significant labor effort.Recent advances in large language models(LLMs)have introduced new methodologies for agile chip design,demonstrating substantial potential in code and EDA script generation.In this work,an LLM-based multi-agent framework for DSSoC design is proposed,which consists of end-to-end design stages from architecture definition to code generation and EDA physical implementation.The approach is validated through two case studies involving 2-to 4-week SoC designs at process nodes of 22 nm and 7 nm.The evalautions show the generated SoCs achieve energy efficiency improvements of 4.84 × and 3.82×,compared to SoCs generated by the existing framework.关键词
敏捷设计/多智能体/端到端设计/领域专用片上系统/大语言模型Key words
agile design/multi-agent/end-to-end design/DSSoC/large language model分类
信息技术与安全科学引用本文复制引用
闫沛然,支沁喆,刘力峰,贾天宇..基于大语言模型多智能体的端到端领域专用SoC设计[J].集成电路与嵌入式系统,2025,25(8):31-40,10.基金项目
国家自然科学基金项目(U23A6007) （U23A6007）
北京市自然科学基金—小米创新联合基金项目(L243001) （L243001）
