Physics-Guided Geometric Diffusion for Macro Placement Generation

TL;DR

MacroDiff+ is a physics-guided geometric diffusion framework for macro placement in VLSI design, combining topological and geometric modeling to improve wirelength and scalability.

Contribution

It introduces a dual-domain denoising architecture with physics-guided sampling, achieving better performance and stability over existing methods.

Findings

Reduces wirelength by 6.1-6.2% on benchmarks.

Outperforms state-of-the-art baselines.

Demonstrates superior scalability and convergence.

Abstract

Macro placement is a pivotal stage in VLSI physical design, fundamentally determining the overall chip performance. Recent data-driven placement methods have demonstrated significant potential, yet they often struggle to handle sequential dependencies and to balance topological connectivity with physical constraints. To bridge this gap, we propose MacroDiff+, a physics-guided geometric diffusion framework. Specifically, we design a dual-domain denoising architecture that couples topological connectivity encoded by heterogeneous GNNs with global geometric context modeled by a Transformer. Furthermore, we introduce Physics-Guided Sampling, an inference strategy that actively steers the generation using explicit gradients to ensure both statistical plausibility and physical validity. On the ISPD2005 MMS benchmarks, MacroDiff+ outperforms state-of-the-art baselines with a 6.1-6.2% reduction in wirelength. Notably, it exhibits superior stability and scalability on large-scale designs where prior methods fail to converge. The source code is available at https://github.com/jhy00n/MacroDiff-plus.