Routability-driven Global Routing with 3D Congestion Estimation Using a Customized Neural Network

Yuxuan Pan, Zhonghua Zhou, Andre Ivanov
the University of British Columbia


In global routing, one factor that affects routability is the routing congestion, which happens when the number of wires and vias in a region exceeds the capacity of that area. Such congestion may cause Design Rule Violations (DRVs) or incorrect routing solutions that ultimately lead to design failure. To improve routability, we propose a global routing congestion estimation algorithm based on a Convolutional Neural Network (CNN). This algorithm estimates the severity of congestion of designs in the global routing phase based on a design’s placement information only. Placement features are extracted and fed into the proposed network which produces congestion estimation results. The predicted congestion is taken as an input to our proposed XX-GR (The full name of XX-GR has been omitted for the purpose of blind review), a modified global router based on the state-of-the-art CU-GR. In comparison with CU-GR, this work achieved an average reduction of 15% in routing channel overflow and 3% in the number of vias, without increasing the total wire length. Moreover, XX-GR produced a routing solution for a previously unroutable design using CU-GR.