AI 中文总结
研究针对工业物理设计流程中宏布局需大量人工优化的问题，提出MAGE框架。该框架通过多模态多智能体实现宏布局优化，结合多种规则与检查，引入量化类人性指标。实验表明其相比商业工具及基线有显著提升，且能转移到新布局设置。
AI 中文摘要
在工业物理设计流程中，宏布局仍需大量人工优化。我们提出了MAGE（宏布局智能引擎），这是一个用于宏布局优化的多模态多智能体框架。MAGE将宏布局任务分解为六个阶段的工作流程，结合了结构化的布局规划规则、视觉检查和迭代优化。专家布局规划知识通过自然语言指令和验证标准进行编码，而非从标记的布局数据中学习。一种锦标赛式的优化模式评估多个候选布局，并传播来自更高质量解决方案的反馈。我们还引入了四个指标来量化宏布局中的类人性：缺口分数、空白分数、口袋分数和对齐分数。这些指标捕捉了专家设计师使用的结构属性，但传统的PPA指标无法直接测量。在NanGate45和GlobalFoundries 12nm工艺的九个设计中，与商业宏布局工具相比，MAGE在WNS方面实现了11.1%-19.3%的几何平均提升，在TNS方面实现了70.0%-74.0%的提升。在有人类专家和Hier-RTLMP基线的三个NanGate45设计中，MAGE在WNS和TNS方面比人类专家分别提高了18.3%和72.5%，比Hier-RTLMP分别提高了47.0%和80.4%，同时线长和功耗相当。在类人性指标上，MAGE比所有基线的总体分数提高了6%-48%。对匿名网表、未见设计、密集直线布局和高利用率设置的额外案例研究表明，该框架无需特定设计的再训练即可转移到新的布局设置中。
英文摘要
Macro placement still requires substantial manual refinement in industrial physical design flows. We present MAGE (Macro Placement Agentic Engine), a multimodal multi-agent framework for macro placement refinement. MAGE decomposes the macro placement task into a six-phase workflow that combines structured floorplanning rules, visual checks, and iterative refinement. Expert floorplanning knowledge is encoded through natural-language directives and validation criteria, rather than learned from labeled placement data. A tournament-style refinement mode evaluates multiple candidate placements and propagates feedback from higher-quality solutions. We also introduce four metrics for quantifying human-likeness in macro placement: notch score, whitespace score, pocket score, and alignment score. These metrics capture structural properties used by expert designers but not directly measured by conventional PPA metrics. Across nine designs in NanGate45 and GlobalFoundries 12nm enablements, MAGE achieves geometric-mean improvements of 11.1%-19.3% in WNS and 70.0%-74.0% in TNS over commercial macro placers. On the three NanGate45 designs, for which human-expert and Hier-RTLMP baselines are available, MAGE improves WNS and TNS by 18.3% and 72.5% over the human expert, and by 47.0% and 80.4% over Hier-RTLMP, with comparable wirelength and power. On human-likeness metrics, MAGE improves the overall score by 6%-48% over all baselines. Additional case studies on anonymized netlists, unseen designs, dense rectilinear floorplans, and high-utilization settings show that the framework transfers to new placement settings without design-specific retraining.
Comments16 pages
