GANGR: GAN-Assisted Scalable and Efficient Global Routing Parallelization

2025-11-20

AI Summary

Traditional heuristic-based batched global routing approaches suffer from high computational overhead, poor batch quality, and redundant batching—severely limiting parallelization efficiency and scalability. To address these limitations, this work introduces, for the first time, a Wasserstein Generative Adversarial Network (WGAN) framework for optimizing batch assignment in global routing. Integrated with a Graph Neural Network (GNN), the model jointly learns topological and electrical characteristics of net groups to enable intelligent, high-quality, low-redundancy, and rapid batch generation. This data-driven approach eliminates reliance on hand-crafted heuristics and substantially enhances parallelization potential. Evaluated on the ISPD’24 benchmark suite, our method achieves up to 40% reduction in runtime while degrading routing quality by only 0.002%—demonstrating superior overall performance over state-of-the-art routers.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Global routing is a critical stage in electronic design automation (EDA) that enables early estimation and optimization of the routability of modern integrated circuits with respect to congestion, power dissipation, and design complexity. Batching is a primary concern in top-performing global routers, grouping nets into manageable sets to enable parallel processing and efficient resource usage. This process improves memory usage, scalable parallelization on modern hardware, and routing congestion by controlling net interactions within each batch. However, conventional batching methods typically depend on heuristics that are computationally expensive and can lead to suboptimal results (oversized batches with conflicting nets, excessive batch counts degrading parallelization, and longer batch generation times), ultimately limiting scalability and efficiency. To address these limitations, a novel batching algorithm enhanced with Wasserstein generative adversarial networks (WGANs) is introduced in this paper, enabling more effective parallelization by generating fewer higher-quality batches in less time. The proposed algorithm is tested on the latest ISPD'24 contest benchmarks, demonstrating up to 40% runtime reduction with only 0.002% degradation in routing quality as compared to state-of-the-art router.

Problem

• Optimizing global routing batching for parallel processing efficiency
• Reducing computational cost of heuristic-based net grouping methods
• Improving scalability through generative adversarial network enhanced algorithms

Innovation

• WGAN-enhanced batching algorithm for global routing
• Generates fewer high-quality batches in less time
• Reduces runtime by 40% with minimal quality loss