{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:41:55Z","timestamp":1763811715525,"version":"3.41.2"},"reference-count":30,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"Guangdong S&T Programme","award":["2022B0701180001"],"award-info":[{"award-number":["2022B0701180001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23A20361"],"award-info":[{"award-number":["U23A20361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Planning Project of Guangzhou","award":["2023B01J0007"],"award-info":[{"award-number":["2023B01J0007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Traditional supervised single-task learning models are used in timing-driven placement exploration to improve both effectiveness and efficiency by predicting wire length, wire delay, and cell delay separately. However, these metrics are interdependent, with the two delays being timing-based and wire length non-timing, which makes it difficult for single-task models to capture their complex relationships. Moreover, the limited existing multi-task learning methods can only predict either multiple timing or non-timing metrics. To address these limitations, this article introduces DLGNN, a novel multi-task graph learning model that simultaneously predicts these three metrics through an embedder-predictor architecture featuring two residual connections, a combination of both soft and hard parameter sharing, and a geometric loss strategy. Cross-design experimental results on the Nangate 45nm library demonstrate that DLGNN outperforms baseline models in terms of both predictive performance and time efficiency. Additionally, ablation studies emphasize the critical roles of the residual connections, the combination of soft and hard parameter sharing, and the geometric loss strategy in improving DLGNN\u2019s predictive performance. The generalization experiment on the ASAP 7nm library further confirms DLGNN\u2019s advantages for more advanced technology nodes.<\/jats:p>","DOI":"10.1145\/3747181","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T07:07:11Z","timestamp":1751440031000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Concurrent Prediction of Timing and wire Length Using A Multi-Task Graph Neural Network"],"prefix":"10.1145","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7651-5287","authenticated-orcid":false,"given":"Yan","family":"Xing","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4834-3020","authenticated-orcid":false,"given":"Hongtao","family":"Hu","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology, School of Integrated Circuits and School of Automation","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1","volume-title":"Proceedings of the 56th ACM\/EDAC\/IEEE Design Automation Conference (DAC)","author":"Barboza E. C.","year":"2019","unstructured":"E. C. Barboza et\u00a0al. 2019. Machine learning-based pre-routing timing prediction with reduced pessimism. In Proceedings of the 56th ACM\/EDAC\/IEEE Design Automation Conference (DAC). Long Beach, CA, USA, 1\u20136."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3216752"},{"key":"e_1_3_2_4_2","first-page":"428","volume-title":"Proceedings of the 23th International Symposium on Quality Electronic Design (ISQED)","author":"Chen L.","year":"2022","unstructured":"L. Chen et\u00a0al. 2022. Path-based pre-routing timing prediction for modern very large-scale integration designs. In Proceedings of the 23th International Symposium on Quality Electronic Design (ISQED). Santa Jose, CA, 428\u2013433."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/3437539.3437768"},{"key":"e_1_3_2_6_2","first-page":"1200","volume-title":"Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Chennupati S.","year":"2019","unstructured":"S. Chennupati et\u00a0al. 2019. MultiNet++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning. In Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Long Beach, CA, USA, 1200\u20131210."},{"key":"e_1_3_2_7_2","first-page":"7","volume-title":"Proceedings of the 4th ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD)","author":"Chhabria V. A.","year":"2022","unstructured":"V. A. Chhabria et\u00a0al. 2022. From global route to detailed route: ML for fast and accurate wire parasitics and timing prediction. In Proceedings of the 4th ACM\/IEEE Workshop on Machine Learning for CAD (MLCAD). Snowbird, UT, 7\u201314."},{"key":"e_1_3_2_8_2","first-page":"229","volume-title":"Proceedings of the 2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","author":"Fu C.","year":"2023","unstructured":"C. Fu et\u00a0al. 2023. Machine learning techniques for pre-CTS identification of timing critical flip-flops. In Proceedings of the 2023 IEEE Computer Society Annual Symposium on VLSI (ISVLSI). Foz do Iguacu, BRAZIL, 229\u2013234."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530597"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473937"},{"key":"e_1_3_2_11_2","first-page":"1","volume-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference (DAC)","author":"He X.","year":"2022","unstructured":"X. He et\u00a0al. 2022. Accurate timing prediction at placement stage with look-ahead RC network. In Proceedings of the 59th ACM\/IEEE Design Automation Conference (DAC). San Francisco, CA, 1\u20136."},{"key":"e_1_3_2_12_2","first-page":"1","volume-title":"Advances in Neural Information Processing Systems 36 (NEURIPS 2023)","author":"Hu Yuting","year":"2023","unstructured":"Yuting Hu, Jiajie Li, Florian Klemme, Gi-Joon Nam, Tengfei Ma, Hussam Amrouch, and Jinjun Xiong. 2023. SyncTREE: Fast timing analysis for integrated circuit design through a physics-informed tree-based graph neural network. In Advances in Neural Information Processing Systems 36 (NEURIPS 2023). New Orleans, LA, 1\u201313."},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3587817"},{"key":"e_1_3_2_14_2","unstructured":"The Silicon Integration Initiative Inc.2024. Open Cell and Free PDK Libraries. Retrieved from https:\/\/si2.org\/open-cell-library\/"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-96415-3","volume-title":"VLSI Physical Design: From Graph Partitioning to Timing Closure (2nd ed.)","author":"Kahng A. B.","year":"2022","unstructured":"A. B. Kahng et\u00a0al. 2022. VLSI Physical Design: From Graph Partitioning to Timing Closure (2nd ed.). Springer."},{"key":"e_1_3_2_16_2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-031-13074-8_1","volume-title":"Machine Learning Applications in Electronic Design Automation","author":"Kahng A. B.","year":"2022","unstructured":"A. B. Kahng and Z. Wang. 2022. ML for design QoR prediction. In Machine Learning Applications in Electronic Design Automation. Haoxing Ren and Jiang Hu (Eds.). Springer, 3\u201333."},{"key":"e_1_3_2_17_2","unstructured":"UC San Diego VLSI CAD Laboratory. 2024. The OpenROAD Project. Retrieved from https:\/\/theopenroadproject.org\/"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2004.834234"},{"key":"e_1_3_2_19_2","unstructured":"The Special Session on Sequential Test Generation. 1989. ISCAS89 Sequential Benchmark Circuits. Retrieved from https:\/\/filebox.ece.vt.edu\/mhsiao\/iscas89.html"},{"key":"e_1_3_2_20_2","unstructured":"OpenCores.org. 2024. OpenCores. Retrieved from https:\/\/www.opencores.org\/"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3124762"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626959"},{"issue":"7","key":"e_1_3_2_23_2","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 Gansbeke, Marc Proesmans, Dengxin Dai, and Luc Van Gool. 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_3_2_24_2","first-page":"1","volume-title":"Proceedings of the 60th ACM\/IEEE Design Automation Conference (DAC)","author":"Wang Z.","year":"2023","unstructured":"Z. Wang et\u00a0al. 2023. Restructure-tolerant timing prediction via multimodal fusion. In Proceedings of the 60th ACM\/IEEE Design Automation Conference (DAC). San Francisco, CA, 1\u20136."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2005.855885"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656170"},{"key":"e_1_3_2_27_2","first-page":"1","volume-title":"Proceedings of the 2023 Design, Automation and Test in Europe Conference and Exhibition (DATE)","author":"Ye Y.","year":"2023","unstructured":"Y. Ye et\u00a0al. 2023. Fast and accurate wire timing estimation based on graph learning. In Proceedings of the 2023 Design, Automation and Test in Europe Conference and Exhibition (DATE). Antwerp, BELGIUM, 1\u20136."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712484"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567904"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_31_2","first-page":"17087","volume-title":"Proceedings of the Thirty-Eight AAAI Conference on Artificial Intelligence","author":"Zhong Ruizhe","year":"2024","unstructured":"Ruizhe Zhong, Junjie Ye, Zhentao Tang, Shixiong Kai, Mingxuan Yuan, Jianye Hao, and Junchi Yan. 2024. PreRoutGNN for timing prediction with order preserving partition: Global circuit pre-training, local delay learning and attentional cell modeling. In Proceedings of the Thirty-Eight AAAI Conference on Artificial Intelligence, M Wooldridge, J Dy, and S Natarajan (Eds.). Vancouver, CANADA, 17087\u201317095."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3747181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T08:28:17Z","timestamp":1752827297000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3747181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3747181"],"URL":"https:\/\/doi.org\/10.1145\/3747181","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"type":"print","value":"1084-4309"},{"type":"electronic","value":"1557-7309"}],"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2024-11-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}