WISP: Image Segmentation-Based Whitespace Diagnosis for Optimal Rectilinear Floorplanning

2025-05-21

AI Summary

Modern chip designs featuring rectangular macro placements suffer from congestion corners, inaccurate HPWL wirelength estimation, and low whitespace utilization. To address these challenges, this work introduces the first whitespace diagnosis paradigm tailored for rectilinear layouts, integrating image-based semantic segmentation with orientation-aware macro repacking to identify and redistribute block-level idle regions. A lightweight probabilistic scoring mechanism and Gaussian Mixture Model (GMM)-based density estimation are further incorporated to enhance macro relocation accuracy. Experimental results on industrial benchmarks demonstrate that, compared to DREAMPlace 4.1, the proposed method achieves an average wirelength reduction of 5.4% (up to 11.4%), improves worst negative slack (WNS) and total negative slack (TNS) by 41.5% and 43.7%, respectively, and recovers 16.2% of block-level area—significantly enhancing physical design quality in rectangular macro placement scenarios.

Technology Category

• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements

Abstract

The increasing number of rectilinear floorplans in modern chip designs presents significant challenges for traditional macro placers due to the additional complexity introduced by blocked corners. Particularly, the widely adopted wirelength model Half-Perimeter Wirelength (HPWL) struggles to accurately handle rectilinear boundaries, highlighting the need for additional objectives tailored to rectilinear floorplan optimization. In this paper, we identify the necessity for whitespace diagnosis in rectilinear floorplanning, an aspect often overlooked in past research. We introduce WISP, a novel framework that analyzes and scores whitespace regions to guide placement optimization. WISP leverages image segmentation techniques for whitespace parsing, a lightweight probabilistic model to score whitespace regions based on macro distribution, a Gaussian Mixture Model (GMM) for whitespace density scoring and direction-aware macro relocation to iteratively refine macro placement, reduce wasted whitespace, and enhance design quality. The proposed diagnostic technique also enables the reclamation of block-level unused area and its return to the top level, maximizing overall area utilization. When compared against state-of-the-art academia placer DREAMPlace 4.1, our method achieves an average improvement of 5.4% in routing wirelength, with a maximum of 11.4% across widely-used benchmarks. This yields an average of 41.5% and 43.7% improvement in Worst Negative Slack (WNS) and Total Negative Slack (TNS), respectively. Additionally, WISP recycles an average of 16.2% area at the block level, contributing to more efficient top-level area distribution.

Problem

• Diagnose whitespace in rectilinear floorplans for optimization
• Improve wirelength accuracy with rectilinear boundary handling
• Reclaim unused block-level area for top-level utilization

Innovation

• Image segmentation for whitespace parsing
• Gaussian Mixture Model for density scoring
• Direction-aware macro relocation optimization