AI 中文总结
研究针对CAD工具固定算法在不同电路设计效果不佳的问题，提出VPR-Evolve多智能体框架，通过进化VPR源代码优化布局布线。经实验，相比原始VPR和超参数调整基线，该框架在关键路径延迟、布线线长和工具运行时等方面有显著提升。
AI 中文摘要
CAD工具通常在具有广泛不同结构和时序特征的电路中应用相同的固定手工设计算法。将这些通用流程专门应用于目标设计的常见方法是调整CAD工具的超参数。然而，超参数调整只能在固定算法已实现的行为中进行选择，限制了结果质量，且需要多次昂贵的布局布线评估。我们提出了VPR-Evolve，这是一个多智能体框架，通过为每个设计进化其源代码来专门化通用布局布线（VPR），即Verilog到路由（VTR）流程中的开源FPGA布局-放置-布线引擎。VPR-Evolve使用大语言模型智能体来提出、实现和评估代码级修改，同时共享内存记录先前结果并指导后续进化。每个候选方案都通过完整的VPR构建和运行进行评估，直接优化作为关键路径延迟（CPD）、布线线长（WL）和工具运行时（RT）的加权函数测量的综合分数。在五个VTR-9基准电路上，VPR-Evolve比VTR-9中的原始VPR将综合分数提高了2.7%。相对于原始VPR，它将CPD降低了9.8%，布线WL降低了18.1%，工具RT降低了79.3%。与超参数调整基线相比，VPR-Evolve将CPD降低了6.0%，布线WL降低了2.2%，工具RT降低了7.8%。
英文摘要
CAD tools typically apply the same fixed, hand-designed algorithms across circuits with widely different structural and timing characteristics. A common way to specialize these one-size-fits-all flows to a target design is to tune the CAD tool's hyperparameters. However, hyperparameter tuning can only select among behaviors already implemented by the fixed algorithm, limiting the achievable quality of results while requiring many expensive place-and-route evaluations. We present VPR-Evolve, a multi-agent framework that specializes Versatile Place and Route (VPR), the open-source FPGA pack-place-and-route engine in the Verilog-to-Routing (VTR) flow, by evolving its source code for each design. VPR-Evolve uses LLM agents to propose, implement, and evaluate code-level modifications, while a shared memory records prior outcomes and guides subsequent evolution. Every candidate is evaluated through a complete VPR build and run, directly optimizing a composite score measured as a weighted function of critical-path delay (CPD), routed wirelength (WL), and tool runtime (RT). Across five VTR-9 benchmark circuits, VPR-Evolve improves the composite score by up to 2.7% over stock VPR in VTR-9. Relative to stock VPR, it reduces CPD by up to 9.8%, routed WL by up to 18.1%, and tool RT by up to 79.3%. VPR-Evolve reduces CPD by up to 6.0%, routed WL by up to 2.2%, and tool RT by up to 7.8% compared with a hyperparameter-tuning baseline.
