What question did this study set out to answer?

To develop a macro placement method that improves sample efficiency and exploration through advanced techniques in reinforcement learning.

March 26, 2026Open Access

Efficient Chip Macro Placement via Discrete Soft Actor-Critic with Enhanced Channel Attention

LFLingyan FanHangzhou Dianzi University CDCanming DINGHangzhou Dianzi University JDJie DengDalian Minzu University

Key Points

To develop a macro placement method that improves sample efficiency and exploration through advanced techniques in reinforcement learning.
Proposed DSPLACE integrates Discrete Soft Actor-Critic with Efficient Channel Attention.
Utilized a maximum-entropy framework to enhance exploration capabilities.
Implemented experiments on ISPD-2005 benchmarks to evaluate performance.
Achieved up to 14% reduction in wirelength compared to previous methods.
Demonstrated approximately 30.7% faster convergence than recent RL-based approaches.

Abstract

Macro placement is a critical step in modern IC design, where reinforcement learning (RL) has shown promise by treating it as a sequential decision process. However, existing RL-based methods often suffer from low sample efficiency and insufficient exploration. To address these issues, we propose DSPLACE (Discrete Soft Actor-Critic PLACE), a macro placement approach that integrates Discrete Soft Actor-Critic (DSAC) with Efficient Channel Attention (ECA). DSAC enhances exploration through its maximum-entropy framework, while ECA strengthens state representation by adaptively recalibrating features. Experimental results on ISPD-2005 benchmarks show that DSPLACE improves wirelength by up to 14% and converges about 30.7% faster compared to recent RL-based counterparts.

KI fragen

Bookmark

View Full Paper