ClusterNet: Routing Congestion Prediction and Optimization Using Netlist Clustering and Graph Neural Networks
- Title
- ClusterNet: Routing Congestion Prediction and Optimization Using Netlist Clustering and Graph Neural Networks
- Authors
- KANG, SEOKHYEONG; Min, Kyungjun; Kwon, Seongbin; Lee, Sung-Yun; Kim, Dohun; Park, Sunghye
- Date Issued
- 2023-10-28
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- Accurately predicting routing congestion caused by netlist topology is essential as circuit designs become increasingly complex. To correctly predict routing congestion, the use of graph neural networks (GNNs) has gained great attention. However, existing GNN-based methods have limitations in capturing crucial netlist information and effectively representing complex topologies. In this work, we propose a novel approach, ClusterNet, to predict routing congestion caused by netlist topology. Our approach leverages netlist clustering to overcome these limitations. We first divide the netlist into highly connected clusters using the Leiden algorithm, enabling an analysis of the local netlist topology. We then predict routing congestion by exploiting GNNs to generate cluster embeddings that capture the detailed netlist topology. In addition, we introduce a cluster padding method that utilizes the trained model to mitigate routing congestion. By applying the proposed ClusterNet, we can accurately predict and optimize routing congestion from specific cluster topologies. Our experimental results demonstrated improved prediction performance, with a mean absolute error of 0.056 and an R2 score of 0.669. Furthermore, routing congestion optimization significantly improved the total negative slack and reduced the number of failing endpoints by 14.5% and 9.9%, respectively.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/121887
- Article Type
- Conference
- Citation
- 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023, 2023-10-28
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.