发表机构
The Chinese University of Hong Kong; Peking University（香港中文大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MacroAgent是结合LLM智能体设计轮廓算法的四阶段宏合法化框架，在TILOS、Chipyard等基准及Cadence Innovus工具上，实现布局规则性、布线长度等指标的显著提升与更好鲁棒性。
AI 中文摘要
宏是现代超大规模集成电路（VLSI）设计核心区域的重要组成部分，宏的位置对最终结果质量（QoR）有显著影响，宏合法化是确定宏位置的典型最终步骤。然而，现有宏合法化方法要么缺乏鲁棒性，要么产生大量计算成本，要么忽略宏之间的规则性。为解决这些局限，我们提出MacroAgent，该新颖框架是一个四阶段方法：聚类、轮廓生成、模板匹配和簇间优化。我们建议利用大语言模型（LLMs）发现多种有效的感知规则性轮廓启发式算法。该框架成功为宏合法化生成鲁棒且有效的算法解决方案。与最先进的宏合法化工作相比，在TILOS和Chipyard基准上的实验结果表明，布局规则性提升2至8倍，全局布线后布线长度减少3%至5%且拥塞相当，且在可接受的运行时间内实现显著更好的鲁棒性。此外，通过Cadence Innovus布局布线的端到端评估证实，规则性提升转化为切实的PPA收益，包括与DREAMPlace宏合法化基线相比，布线长度降低2.9%，总负延迟数（TNS）提升68.3%；当集成到Innovus宏布局流程时，还实现布线长度降低1.8%。
英文摘要
Macros constitute a large part of the core area in modern very large-scale integration (VLSI) designs. Moreover, macro positions have a significant impact on the final quality of result (QoR), and macro legalization is typically the final step in determining the macro positions. However, existing approaches related to macro legalization either lack robustness or incur substantial computational costs or neglect the regularity between macros. To address these limitations, we introduce MacroAgent. The novel framework is a four-stage approach: clustering, contour generation, template matching, and inter-cluster refinement. We propose leveraging Large Language Models (LLMs) to discover multiple, effective heuristic regularity-aware contour algorithms. This framework successfully generates robust and effective algorithmic solutions for macro legalization. Compared with state-of-the-art macro legalization works, experimental results on TILOS and Chipyard benchmarks demonstrate a 2 to 8 fold improvement in layout regularity, a 3% to 5% reduction in routed wirelength with comparable congestion after global routing, and significantly better robustness with an acceptable runtime. Furthermore, end-to-end evaluation through Cadence Innovus place-and-route confirms that the regularity improvements translate into tangible PPA gains, including 2.9% lower routed wirelength and 68.3% TNS improvement over the DREAMPlace macro legalization baseline; it also achieves 1.8% lower routed wirelength when integrated into the Innovus macro placement flow.
