发表机构
National Tsing Hua University; Kohaku Lab; Karolinska Institutet; Stockholm University; National Taiwan University（国立清华大学; Kohaku 实验室; 卡罗林斯卡学院; 斯德哥尔摩大学; 国立台湾大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出Trinity流匹配布局规划器，用六个可微分函数统一训练、精炼和评分，无需引导，显著降低软硬成本并加速精炼。
AI 中文摘要
布局规划（Floorplanning）安排芯片的模块并决定其形状，其目标是将模块压紧、缩短线长和缩小轮廓，同时满足保持模块分离、不重叠、聚类、MIB形状和边界模块等约束。最近的扩散布局器仅基于参考布局进行训练，而将这一耦合系统留给引导（guidance）、事后循环和合法化器（legalizer）处理，并且只报告最终结果，这掩盖了生成器本身的贡献。我们在FloorSet数据集上，用统一的配方重新实现了其中四种方法，在一个尺度上对原始、精炼和合法化后的布局进行评分，并提出了Trinity——一种流匹配（flow-matching）布局规划器，其针对约束和目标设计的六个可微分函数分别用作训练损失项、采样后闭式精炼器的能量函数以及每个阶段软成本的基函数。因此，网络学习了先前布局器在其采样器中应用的修正先验，采样过程无需引导。逐阶段来看，训练项将普通Transformer的原始软成本降低了26%，且在短预算下效果最为显著；共享精炼器对最终成本的贡献大于生成器，并以少16至660倍的步数匹配了移植布局器的循环；Trinity的精炼软成本比最佳移植流水线低36%；软成本对设置的排序与竞赛中的硬成本排序一致；在FloorSet验证集上，该流水线达到平均硬成本1.014，每案例耗时1.63秒。
英文摘要
Floorplanning arranges the blocks of a chip and decides their shapes under objectives that press blocks together, short wirelength and a small outline, and constraints that hold them apart, non-overlap, clusters, MIB shapes and boundary blocks. Recent diffusion placers train on reference layouts alone and leave this coupled system to guidance, post-hoc loops and a legalizer, reporting only the endpoint, which hides what the generator contributes. We re-implement four of them under one recipe on FloorSet, score raw, refined and legalized layouts on one scale, and propose Trinity, a flow-matching floorplanner whose six differentiable functions for the constraints and objectives are its training loss term, the energy of a closed-form refiner after sampling and the base of a soft cost for every stage. The network thus learns the correction prior placers apply in their samplers, and sampling needs no guidance. Stage by stage, the training term lowers a plain transformer's raw soft cost by 26% and matters most at short budgets, the shared refiner decides more of the final cost than the generator and matches a ported placer's loop in 16 to 660 times fewer steps, Trinity's refined soft cost is 36% below the best ported pipeline, the soft cost ranks settings as the contest's hard cost does, and on the FloorSet val set the pipeline reaches a mean hard cost of 1.014 in 1.63 s per case.
CommentsShih-Ying Yeh and Tzu-Sian Wang contributed equally. 85 pages, 65 figures, 67 tables. Project page: https://kohaku-lab.github.io/Trinity/ Code: https://github.com/Kohaku-Lab/Trinity Models: https://huggingface.co/KBlueLeaf/Trinity
