用RAG技术打造开源芯片设计对话助手，让新手也能轻松上手OpenROAD流程。
ORAssistant: A Custom RAG-based Conversational Assistant for OpenROAD
- 基于RAG架构，结合文档与代码库构建上下文感知问答系统。
- 使用Gemini模型测试，相比普通LLM在准确率和性能上有显著提升。
- 支持OpenROAD等工具链，适合芯片设计初学者与开源开发者使用。
开源电子设计自动化（EDA）工具正迅速改变芯片设计格局，克服商业EDA工具在复杂性、成本和可访问性方面的障碍。大型语言模型（LLMs）的进展进一步提升了设计效率，可在设置、决策和流程自动化等任务中提供用户协助。本文提出ORAssistant，一个基于检索增强生成（RAG）的OpenROAD对话助手，旨在改善从RTL到GDSII全流程的用户体验。它能针对安装、命令使用、流程配置与执行等常见问题，提供自然语言格式的上下文相关回答。目前，ORAssistant集成了OpenROAD、OpenROAD-flow-scripts、Yosys、OpenSTA和KLayout。其数据模型来自公开文档与GitHub资源。该架构具有可扩展性，支持接入其他开源工具、运行模式及不同LLM模型。我们以Google Gemini为基础模型进行构建与测试，初步评估显示，相较于未微调的LLM，RAG模型在性能与准确性方面均有显著提升。
原文摘要 · Abstract (English)
Open-source Electronic Design Automation (EDA) tools are rapidly transforming chip design by addressing key barriers of commercial EDA tools such as complexity, costs, and access. Recent advancements in Large Language Models (LLMs) have further enhanced efficiency in chip design by providing user assistance across a range of tasks like setup, decision-making, and flow automation. This paper introduces ORAssistant, a conversational assistant for OpenROAD, based on Retrieval-Augmented Generation (RAG). ORAssistant aims to improve the user experience for the OpenROAD flow, from RTL-GDSII by providing context-specific responses to common user queries, including installation, command usage, flow setup, and execution, in prose format. Currently, ORAssistant integrates OpenROAD, OpenROAD-flow-scripts, Yosys, OpenSTA, and KLayout. The data model is built from publicly available documentation and GitHub resources. The proposed architecture is scalable, supporting extensions to other open-source tools, operating modes, and LLM models. We use Google Gemini as the base LLM model to build and test ORAssistant. Early evaluation results of the RAG-based model show notable improvements in performance and accuracy compared to non-fine-tuned LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。