发表机构
Institute of Technology, Nirma University; Arizona State University（尼玛大学理工学院; 亚利桑那州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对VLSI全局路由这一NP难组合优化问题，传统方法失效。AlphaRoute将拆线重布重构为动态优化系统，引入基于SHAP的溢出分解等技术，用大语言模型作语义策略优化器，在基准测试中大幅减少溢出，证明优越算法可克服Python实现的延迟。
AI 中文摘要
超大规模集成电路（VLSI）全局路由是一个NP难组合优化问题，需在容量受限的3D网格上分配信号网络，同时最小化拥塞、线长和通孔转换。传统启发式方法因依赖静态惩罚策略在复杂拥塞拓扑中失效。为此提出AlphaRoute，将拆线重布（R&R）重新构建为动态优化系统，引入基于SHAP的溢出分解隔离每个网络的拥塞，通过3D Dijkstra迷宫路由和自适应PathFinder策略驱动目标子图提取。关键是，AlphaRoute使用大语言模型作为语义策略优化器，在确定性知识图的约束下，解释拥塞指标以动态调整惩罚参数。在ISPD 2025基准测试中，AlphaRoute在MEMPOOL上使溢出减少98.6%。在受限的ARIANE设计上，溢出为146,109（比现有技术减少29.8倍），惩罚分数S_orig = 0.0538，而现有技术为1.780。这些结果表明，优越的算法搜索几何结构可克服解释型Python实现的延迟问题。
英文摘要
Very Large Scale Integration (VLSI) global routing is an NP-hard combinatorial optimization problem requiring signal net assignment across capacity-constrained 3D grids while minimizing congestion, wirelength, and via transitions. Because traditional heuristics rely on static penalty schedules that fail on complex congestion topologies, we present AlphaRoute: a multi-objective adaptive search framework reformulating rip-up and reroute (R&R) into a dynamic optimization system. We introduce SHAP-based overflow decomposition to isolate per-net congestion, driving targeted subgraph extraction via 3D Dijkstra maze routing and an adaptive PathFinder policy. Crucially, AlphaRoute employs Large Language Models (LLMs) as semantic policy optimizers. Bounded by a deterministic knowledge graph, the LLMs interpret congestion metrics to dynamically adjust penalty parameters. Evaluated on ISPD 2025 benchmarks, AlphaRoute reduces overflow by 98.6% on MEMPOOL. On the constrained ARIANE design, we achieve an overflow of 146,109 (a 29.8x reduction in overflow over the state of the art), yielding a penalized score of S_orig = 0.0538 versus the State-of-the-art (SOTA) 1.780. These results demonstrate that superior algorithmic search geometry can overcome the latency of interpreted Python implementations.
Comments7 pages, 5 figures. Accepted for publication in the IEEE International Conference on LLM-Aided Design, 2026, Stanford University, Stanford, CA, USA. Code available at https://github.com/Kcbir/AlphaRoute
