用大模型自动优化电路映射代码，显著降低面积延迟开销。
MappingEvolve: LLM-Driven Code Evolution for Technology Mapping
- 分层代理架构驱动代码演化，抽象为可优化的操作符
- 在EPFL数据集上实现46.6%~96.0%的综合性能提升
- 适合芯片设计自动化与算法改进方向的研究者
技术映射是逻辑综合中关键但极具挑战性的阶段。尽管大型语言模型（LLMs）已被用于生成优化脚本，其在核心算法改进方面的潜力尚未被挖掘。我们提出MappingEvolve，一个开源框架，首次将LLMs应用于直接演化技术映射代码。该方法将映射过程抽象为独立的优化操作符，并采用分层代理架构——包含规划器（Planner）、演化器（Evolver）和评估器（Evaluator），以指导进化搜索。这一结构化方法实现了有策略且高效的代码修改。实验表明，该方法显著优于直接演化及强基线模型，在EPFL基准测试中相较ABC实现10.04%的面积减少，相较mockturtle实现7.93%的面积减少，整体综合性能（$S_{overall}$）提升46.6%至96.0%，同时明确权衡面积与延迟之间的关系。代码与数据已公开于https://github.com/Flians/MappingEvolve。
原文摘要 · Abstract (English)
Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimization scripts, their potential for core algorithm enhancement remains untapped. We introduce MappingEvolve, an open-source framework that pioneers the use of LLMs to directly evolve technology mapping code. Our method abstracts the mapping process into distinct optimization operators and employs a hierarchical agent-based architecture, comprising a Planner, Evolver, and Evaluator, to guide the evolutionary search. This structured approach enables strategic and effective code modifications. Experiments show our method significantly outperforms direct evolution and strong baselines, achieving 10.04\% area reduction versus ABC and 7.93\% versus mockturtle, with 46.6\%--96.0\% $S_{overall}$ improvement on EPFL benchmarks, while explicitly navigating the area--delay trade-off. Our code and data are available at https://github.com/Flians/MappingEvolve.
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。