Placement is a critical step in modern chip design, aiming to determine the positions of circuit modules on the chip canvas. Recent works have shown that reinforcement learning (RL) can improve human performance in chip placement. However, such an RL-based approach suffers from long training time and low transfer ability in unseen chip circuits. To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data. ChiPFormer has several advantages that prior arts do not have. First, ChiPFormer can exploit offline placement designs to learn transferable policies more efficiently in a multi-task setting. Second, ChiPFormer can promote effective finetuning for unseen chip circuits, reducing the placement runtime from hours to minutes. Third, extensive experiments on 32 chip circuits demonstrate that ChiPFormer achieves significantly better placement quality while reducing the runtime by 10x compared to recent state-of-the-art approaches in both public benchmarks and realistic industrial tasks. The deliverables are released at https://sites.google.com/view/chipformer/home.

翻译：布局是现代芯片设计中的关键步骤，旨在确定电路模块在芯片版图上的位置。近期研究表明，强化学习（RL）可以提升芯片布局的人工性能。然而，此类基于RL的方法存在训练时间长、对未见芯片电路的迁移能力低等问题。为解决这些挑战，我们将芯片布局问题转化为离线强化学习形式，并提出ChiPFormer——该方法能从固定离线数据中学习可迁移的布局策略。ChiPFormer具备现有技术所缺乏的多项优势。首先，ChiPFormer能利用离线布局设计，在多任务设置中更高效地学习可迁移策略。其次，ChiPFormer可促进对未见芯片电路的有效微调，将布局运行时间从数小时缩短至数分钟。第三，在32个芯片电路上的大量实验表明，相较于近期最先进方法，ChiPFormer在公开基准测试和实际工业任务中均能实现显著更优的布局质量，同时将运行时间降低10倍。相关成果已发布于https://sites.google.com/view/chipformer/home。