Toward Reinforcement Learning-based Rectilinear Macro Placement Under Human Constraints

TL;DR

This paper introduces a reinforcement learning-based macro placement method that incorporates human-like constraints, improving placement quality and reducing manual effort in chip design.

Contribution

It presents a novel learning-based macro placer supporting rectilinear macros with human-like constraints, demonstrating effectiveness and generalization in chip layout optimization.

Findings

Achieves competitive PPA metrics with minimal manual intervention

Supports diverse macro shapes and layout areas

Demonstrates high-quality placements comparable to human-designed solutions

Abstract

Macro placement is a critical phase in chip design, which becomes more intricate when involving general rectilinear macros and layout areas. Furthermore, macro placement that incorporates human-like constraints, such as design hierarchy and peripheral bias, has the potential to significantly reduce the amount of additional manual labor required from designers. This study proposes a methodology that leverages an approach suggested by Google's Circuit Training (G-CT) to provide a learning-based macro placer that not only supports placing rectilinear cases, but also adheres to crucial human-like design principles. Our experimental results demonstrate the effectiveness of our framework in achieving power-performance-area (PPA) metrics and in obtaining placements of high quality, comparable to those produced with human intervention. Additionally, our methodology shows potential as a generalized model to address diverse macro shapes and layout areas.