{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:14:46Z","timestamp":1781194486192,"version":"3.54.1"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","license":[{"start":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T00:00:00Z","timestamp":1743984000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"abstract":"<jats:p>In FPGA routing, machine learning-based optimization methods have achieved improved routing solutions by integrating traditional heuristics with predictive capabilities. However, these approaches mostly relied on single-task learning models with black-box nature and often neglected the complex trade-offs and inter-dependencies between routing metrics. To address these limitations, this paper introduces a novel multi-task learning-based routing optimization method. In the congestion-wirelength co-learning stage, the simultaneous prediction of congestion and wirelength is formulated as a multi-task learning problem. A multi-task learning model, named CWNet, is proposed to tackle this challenge effectively. During the congestion-wirelength impact interpretation, the contribution of congestion to wirelength is quantified using an XAI technique known as DeepSHAP, producing a congestion-wirelength impact map. In the congestion-wirelength co-guided routing optimization (CWRO) stage, the VTR router\u2019s lookahead map is enhanced based on the impact map, guiding the router to avoid locations where congestion significantly affect wirelength. Experimental results demonstrate that CWNet outperforms most baseline learning models in terms of both prediction performance and computational efficiency. Additionally, the impact map visually illustrates the complex and nonlinear relationship between congestion and wirelength. Ultimately, CWRO significantly reduces congestion, wirelength, and critical path delay, while maintaining a competitive runtime compared to baseline routers.<\/jats:p>","DOI":"10.1145\/3728467","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T11:24:44Z","timestamp":1744025084000},"update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Optimizing FPGA Routing with Explainable Co-Learning of Congestion and Wirelength"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5816-0099","authenticated-orcid":false,"given":"Wenhao","family":"Liu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7651-5287","authenticated-orcid":false,"given":"Yan","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2842-6439","authenticated-orcid":false,"given":"Shuting","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1227-0791","authenticated-orcid":false,"given":"Weijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2421-7621","authenticated-orcid":false,"given":"Xiaoming","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"High-Definition Routing Congestion Prediction for Large-Scale FPGAs. In the 25th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE","author":"Alawieh Mohamed\u00a0Baker","year":"2020","unstructured":"Mohamed\u00a0Baker Alawieh, Wuxi Li, Yibo Lin, Love Singhal, Mahesh\u00a0A. Iyer, and David\u00a0Z. Pan. 2020. High-Definition Routing Congestion Prediction for Large-Scale FPGAs. In the 25th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE, Beijing, China, 26\u201331."},{"key":"e_1_2_1_2_1","first-page":"1","article-title":"Explainable Artificial Intelligence (XAI): What We Know and What Is Left to Attain Trustworthy Artificial Intelligence","volume":"99","author":"Ali Sajid","year":"2023","unstructured":"Sajid Ali, Tamer Abuhmed, Shaker El-Sappagh, Khan Muhammad, Jose\u00a0M. Alonso-Moral, Roberto Confalonieri, Riccardo Guidotti, Javier Del Ser, Natalia D\u00edaz-Rodr\u00edguez, and Francisco Herrera. 2023. Explainable Artificial Intelligence (XAI): What We Know and What Is Left to Attain Trustworthy Artificial Intelligence. Information Fusion 99(2023), 1\u201352.","journal-title":"Information Fusion"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3272582"},{"key":"e_1_2_1_4_1","volume-title":"Explaining Models by Propagating Shapley Values of Local Components","author":"Chen Hugh","unstructured":"Hugh Chen, Scott Lundberg, and Su-In Lee. 2021. Explaining Models by Propagating Shapley Values of Local Components. Springer International Publishing, Cham, 261\u2013270."},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/TCAD.2022.3168259","article-title":"PROS 2.0: A Plug-in for Routability Optimization and Routed Wirelength Estimation Using Deep Learning","volume":"42","author":"Chen Jingsong","year":"2022","unstructured":"Jingsong Chen, Jian Kuang, Guowei Zhao, Dennis J-H Huang, and Evangeline\u00a0FY Young. 2022. PROS 2.0: A Plug-in for Routability Optimization and Routed Wirelength Estimation Using Deep Learning. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 42, 1(2022), 164\u2013177.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_2_1_6_1","volume-title":"FPGA Placement and Routing. In 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). IEEE","author":"Chen Shih-Chun","year":"2017","unstructured":"Shih-Chun Chen and Yao-Wen Chang. 2017. FPGA Placement and Routing. In 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). IEEE, Irvine, CA, USA, 914\u2013921."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05553-0"},{"key":"e_1_2_1_8_1","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE","author":"Chennupati Sumanth","year":"2019","unstructured":"Sumanth Chennupati, Ganesh Sistu, Senthil Yogamani, and Samir\u00a0A Rawashdeh. 2019. MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, Long Beach, CA, USA, 1200\u20131210."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3322358"},{"key":"e_1_2_1_10_1","volume-title":"Automatic Flow Selection and Quality-of-Result Estimation for FPGA Placement. In 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","author":"Grewal Gary","unstructured":"Gary Grewal, Shawki Areibi, Matthew Westrik, Ziad Abuowaimer, and Betty Zhao. 2017. Automatic Flow Selection and Quality-of-Result Estimation for FPGA Placement. In 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, Lake Buena Vista, FL, USA, 115\u2013123."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451179"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3587817"},{"key":"e_1_2_1_13_1","volume-title":"A Robust FPGA Router with Optimization of High-Fanout Nets and Intra-CLB Connections","author":"Jiang Xun","year":"2025","unstructured":"Xun Jiang, Jing Mai, Zhixiong Di, and Yibo Lin. 2025. A Robust FPGA Router with Optimization of High-Fanout Nets and Intra-CLB Connections. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems Early Access(2025), 1\u201314."},{"key":"e_1_2_1_14_1","volume-title":"A Survey on Machine Learning-based Routing for VLSI Physical Design. Integration, the VLSI Journal 86","author":"Li Lin","year":"2022","unstructured":"Lin Li, Yici Cai, and Qiang Zhou. 2022. A Survey on Machine Learning-based Routing for VLSI Physical Design. Integration, the VLSI Journal 86 (2022), 51\u201356."},{"key":"e_1_2_1_15_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. arxiv:1608.03983 \u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1608.03983","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. SGDR: Stochastic Gradient Descent with Warm Restarts. arxiv:1608.03983 \u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1608.03983"},{"key":"e_1_2_1_16_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. arxiv:1711.05101 \u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_2_1_17_1","unstructured":"Scott\u00a0M. Lundberg Gabriel\u00a0G. Erion and Su-In Lee. 2019. Consistent Individualized Feature Attribution for Tree Ensembles. arxiv:1802.03888 \u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1802.03888"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"M.","unstructured":"Scott\u00a0M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA). Curran Associates Inc., Red Hook, NY, USA, 4768\u20134777."},{"key":"e_1_2_1_19_1","volume-title":"Machine-Learning Based Congestion Estimation for Modern FPGAs. In the 28th International Conference on Field Programmable Logic and Applications (FPL). IEEE, IEEE, Dublin, IRELAND, 427\u2013434","author":"Maarouf Dani","year":"2018","unstructured":"Dani Maarouf, Abeer Alhyari, Ziad Abuowaimer, Timothy Martin, Andrew Gunter, Gary Grewal, Shawki Areibi, and Anthony Vannelli. 2018. Machine-Learning Based Congestion Estimation for Modern FPGAs. In the 28th International Conference on Field Programmable Logic and Applications (FPL). IEEE, IEEE, Dublin, IRELAND, 427\u2013434."},{"key":"e_1_2_1_20_1","volume-title":"the 30th International Conference on Field-Programmable Logic and Applications (FPL). IEEE","author":"Maarouff Dani","year":"2020","unstructured":"Dani Maarouff, Ahmed Shamli, Timothy Martin, Gary Grewal, and Shawki Areibi. 2020. A Deep-Learning Framework for Predicting Congestion During FPGA Placement. In the 30th International Conference on Field-Programmable Logic and Applications (FPL). IEEE, Gothenburg, Sweden, 138\u2013144."},{"key":"e_1_2_1_21_1","volume-title":"Integrating Machine-Learning Probes in FPGA CAD: Why and How?IEEE Design & Test 40, 5","author":"Martin Timothy","year":"2023","unstructured":"Timothy Martin, Charlotte Barnes, Gary Grewal, and Shawki Areibi. 2023. Integrating Machine-Learning Probes in FPGA CAD: Why and How?IEEE Design & Test 40, 5 (2023), 7\u201314."},{"key":"e_1_2_1_22_1","volume-title":"2023 International Conference on Field Programmable Technology (ICFPT). ACM, Yokohama, JAPAN, 7\u201315","author":"Martin T.","unstructured":"T. Martin, Q. Li, C. Barnes, G. Grewal, and S. Areibi. 2023. A Deep-Learning Data-Driven Approach for Reducing FPGA Routing Runtimes. In 2023 International Conference on Field Programmable Technology (ICFPT). ACM, Yokohama, JAPAN, 7\u201315."},{"key":"e_1_2_1_23_1","volume-title":"Proceedings of the ACM third International Symposium on Field-programmable Gate Arrays. ACM","author":"McMurchie Larry","year":"1995","unstructured":"Larry McMurchie and Carl Ebeling. 1995. PathFinder: A Negotiation-Based Performance-Driven Router for FPGAs. In Proceedings of the ACM third International Symposium on Field-programmable Gate Arrays. ACM, Monterey, CA, USA, 111\u2013117."},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3388617","article-title":"VTR 8: High-performance CAD and Customizable FPGA Architecture Modelling","volume":"13","author":"Murray E.","year":"2020","unstructured":"Kevin\u00a0E. Murray, Oleg Petelin, Sheng Zhong, Jia\u00a0Min Wang, Mohamed Eldafrawy, Jean-Philippe Legault, Eugene Sha, Aaron\u00a0G. Graham, Jean Wu, Matthew J.\u00a0P. Walker, Hanqing Zeng, Panagiotis Patros, Jason Luu, Kenneth\u00a0B. Kent, and Vaughn Betz. 2020. VTR 8: High-performance CAD and Customizable FPGA Architecture Modelling. ACM Transactions on Reconfigurable Technology and Systems 13, 2(2020), 1\u201355.","journal-title":"ACM Transactions on Reconfigurable Technology and Systems"},{"key":"e_1_2_1_25_1","volume-title":"AIR: A Fast But Lazy Timing-Driven FPGA Router. In The 25th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE","author":"Murray E","year":"2020","unstructured":"Kevin\u00a0E Murray, Sheng Zhong, and Vaughn Betz. 2020. AIR: A Fast But Lazy Timing-Driven FPGA Router. In The 25th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE, Beijing, PEOPLES R CHINA, 338\u2013344."},{"key":"e_1_2_1_26_1","volume-title":"Routability Prediction and Optimization Using Explainable AI. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE","author":"Park Seonghyeon","year":"2023","unstructured":"Seonghyeon Park, Daeyeon Kim, Seongbin Kwon, and Seokhyeong Kang. 2023. Routability Prediction and Optimization Using Explainable AI. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, San Francisco, CA, USA, 1\u20138."},{"key":"e_1_2_1_27_1","volume-title":"Clock-Aware Ultrascale FPGA Placement with Machine Learning Routability Prediction: Invited Paper. In 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). IEEE","author":"Pui Chak-Wa","year":"2017","unstructured":"Chak-Wa Pui, Gengjie Chen, Yuzhe Ma, Evangeline F.\u00a0Y. Young, and Bei Yu. 2017. Clock-Aware Ultrascale FPGA Placement with Machine Learning Routability Prediction: Invited Paper. In 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD). IEEE, Irvine, CA, 929\u2013936."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3124762"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551901.3556492"},{"key":"e_1_2_1_30_1","first-page":"935","article-title":"Towards Machine Learning-Based FPGA Backend Flow","volume":"12","author":"Taj Imran","year":"2023","unstructured":"Imran Taj and Umer Farooq. 2023. Towards Machine Learning-Based FPGA Backend Flow: Challenges and Opportunities. Electronics 12, 4 (2023), 935.","journal-title":"Challenges and Opportunities. Electronics"},{"key":"e_1_2_1_31_1","first-page":"3614","article-title":"Multi-Task Learning for Dense Prediction Tasks: A Survey","volume":"44","author":"Vandenhende Simon","year":"2022","unstructured":"Simon Vandenhende, Stamatios Georgoulis, Wouter Van\u00a0Gansbeke, Marc Proesmans, Dengxin Dai, and Luc Van\u00a0Gool. 2022. Multi-Task Learning for Dense Prediction Tasks: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 7(2022), 3614\u20133633.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3274950"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3188964"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656170"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the 56th Annual Design Automation Conference 2019 (DAC\u201919)","author":"Yu Cunxi","year":"2019","unstructured":"Cunxi Yu and Zhiru Zhang. 2019. Painting on Placement: Forecasting Routing Congestion Using Conditional Generative Adversarial Nets. In Proceedings of the 56th Annual Design Automation Conference 2019 (DAC\u201919). Association for Computing Machinery, New York, NY, USA, 1\u20136."},{"key":"e_1_2_1_36_1","volume-title":"Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE 2020) (Design Automation and Test in Europe Conference and Exhibition). IEEE, Grenoble, FRANCE, 1151\u20131156","author":"Zeng Wei","year":"2020","unstructured":"Wei Zeng, Azadeh Davoodi, and Rasit\u00a0Onur Topaloglu. 2020. Explainable DRC Hotspot Prediction with Random Forest and SHAP Tree Explainer. In Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE 2020) (Design Automation and Test in Europe Conference and Exhibition). IEEE, Grenoble, FRANCE, 1151\u20131156."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502356"},{"key":"e_1_2_1_38_1","doi-asserted-by":"crossref","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A Survey on Multi-Task Learning","volume":"34","author":"Zhang Yu","year":"2021","unstructured":"Yu Zhang and Qiang Yang. 2021. A Survey on Multi-Task Learning. IEEE Transactions on Knowledge Data Engineering 34, 12(2021), 5586\u20135609.","journal-title":"IEEE Transactions on Knowledge Data Engineering"},{"key":"e_1_2_1_39_1","first-page":"1","article-title":"RWRoute: An Open-source Timing-driven Router for Commercial FPGAs","volume":"15","author":"Zhou Yun","year":"2021","unstructured":"Yun Zhou, Pongstorn Maidee, Chris Lavin, Alireza Kaviani, and Dirk Stroobandt. 2021. RWRoute: An Open-source Timing-driven Router for Commercial FPGAs. ACM Transactions on Reconfigurable Technology and Systems (TRETS) 15, 1(2021), 1\u201327.","journal-title":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3590768"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728467","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:36Z","timestamp":1750295916000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,7]]},"references-count":40,"alternative-id":["10.1145\/3728467"],"URL":"https:\/\/doi.org\/10.1145\/3728467","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,7]]},"assertion":[{"value":"2024-10-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3728467"}}