Chip placement plays an important role in physical design. While generative models like diffusion models offer promising learning-based solutions, current methods have the following limitations: they use random synthetic data for pre-training, require long sampling times, and often result in overlaps due to their dependence on gradient-based solvers during the sampling process. To overcome these issues, we propose FlowPlace, which features mask-guided synthetic data generation, flow-based efficient training with flexible prior injection, and hard constraint sampling for overlap-free layouts. Experiments on OpenROAD and ICCAD 2015 benchmarks show FlowPlace achieves better PPA metrics, 10-50$\times$ faster sampling efficiency, and zero overlaps.

翻译：芯片布局在物理设计中起着重要作用。尽管扩散模型等生成模型提供了有前景的基于学习的解决方案，但现有方法存在以下局限性：使用随机合成数据进行预训练，需要较长的采样时间，并且由于在采样过程中依赖基于梯度的求解器，常常导致布局重叠。为解决这些问题，我们提出FlowPlace，其特点包括基于掩码引导的合成数据生成、具有灵活先验注入的基于流的有效训练以及用于无重叠布局的硬约束采样。在OpenROAD和ICCAD 2015基准测试上的实验表明，FlowPlace实现了更优的PPA指标、10-50倍的采样效率提升以及零重叠。