ChipXplore:硬件设计与库的自然语言探索
ChipXplore: Natural Language Exploration of Hardware Designs and Libraries
AI总结:
提出多智能体框架ChipXplore,利用大语言模型和定制text-to-SQL/Cypher工作流,支持自然语言查询硬件设计与PDK,显著提升检索准确率与效率,奠定自主物理设计智能体基础。
摘要:
硬件设计工作流依赖来自不同工艺节点的Process Design Kits (PDKs),每个包含针对速度、功耗或密度优化的标准单元库。工程师通常在设计与目标PDK之间切换以做出明智决策,例如为面积优化选择门电路或提升关键路径的速度。然而,此过程通常是手动的、耗时的且易出错。为解决此问题,我们提出ChipXplore,一个由大语言模型驱动的多智能体协作框架,使工程师能使用自然语言查询硬件设计与PDK。通过利用PDK与硬件设计数据的结构化特性,ChipXplore通过定制的text-to-SQL和text-to-Cypher工作流检索相关信息。该框架在复杂自然语言查询中达到97.39%的执行准确率,并在用户研究中将检索速度提升5.63倍,同时将错误减少5.25倍,从而提高生产力。与通用工作流相比,ChipXplore的定制工作流能在多个数据库上编排推理与规划,将准确率提升29.78%。ChipXplore为构建能够处理需要PDK与硬件设计感知的各类物理设计任务的自主智能体奠定了基础。
英文摘要:
Hardware design workflows rely on Process Design Kits (PDKs) from different fabrication nodes, each containing standard cell libraries optimized for speed, power, or density. Engineers typically navigate between the design and target PDK to make informed decisions, such as selecting gates for area optimization or enhancing the speed of the critical path. However, this process is often manual, time-consuming, and prone to errors. To address this, we present ChipXplore, a multi-agent collaborative framework powered by large language models that enables engineers to query hardware designs and PDKs using natural language. By exploiting the structured nature of PDK and hardware design data, ChipXplore retrieves relevant information through text-to-SQL and text-to-Cypher customized workflows. The framework achieves an execution accuracy of 97.39\% in complex natural language queries and improves productivity by making retrieval 5.63x faster while reducing errors by 5.25x in user studies. Compared to generic workflows, ChipXplore's customized workflow is capable of orchestrating reasoning and planning over multiple databases, improving accuracy by 29.78\%. ChipXplore lays the foundation for building autonomous agents capable of tackling diverse physical design tasks that require PDK and hardware design awareness.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。