用扩散模型快速生成物理设计热力图，加速机器学习研究
DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design
- 基于扩散模型生成多样布局热力图，推理仅需数秒
- 构建超2万组配置数据集，涵盖功率、IR压降等多类热力图
- 生成数据逼近真实布局，显著提升下游预测任务精度
机器学习在物理设计（PD）中展现出巨大潜力，但模型泛化能力受限于高质量、大规模训练数据的缺乏。构建此类数据通常计算成本高且受知识产权限制。目前公开数据集极少，且多为静态、生成缓慢，需频繁更新。为此，我们提出DALI-PD——一种可扩展的合成布局热力图生成框架，用于加速PD领域的机器学习研究。DALI-PD利用扩散模型，在数秒内完成快速推理，生成包括功耗、IR压降、拥塞、宏单元布局与单元密度在内的多种热力图。通过该框架，我们构建了包含超过20,000个不同宏单元数量与布局配置的数据集。生成的热力图与真实布局高度相似，并在下游任务如IR压降或拥塞预测中显著提升了机器学习模型的准确率。
原文摘要 · Abstract (English)
Machine learning (ML) has demonstrated significant promise in various physical design (PD) tasks. However, model generalizability remains limited by the availability of high-quality, large-scale training datasets. Creating such datasets is often computationally expensive and constrained by IP. While very few public datasets are available, they are typically static, slow to generate, and require frequent updates. To address these limitations, we present DALI-PD, a scalable framework for generating synthetic layout heatmaps to accelerate ML in PD research. DALI-PD uses a diffusion model to generate diverse layout heatmaps via fast inference in seconds. The heatmaps include power, IR drop, congestion, macro placement, and cell density maps. Using DALI-PD, we created a dataset comprising over 20,000 layout configurations with varying macro counts and placements. These heatmaps closely resemble real layouts and improve ML accuracy on downstream ML tasks such as IR drop or congestion prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。