{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:40:13Z","timestamp":1755870013535,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3734528","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"221-235","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1738-886X","authenticated-orcid":false,"given":"Yuebo","family":"Luo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3046-0414","authenticated-orcid":false,"given":"Shiyang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA and Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8349-1194","authenticated-orcid":false,"given":"Junran","family":"Tao","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology, Hoboken, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9190-798X","authenticated-orcid":false,"given":"Kiran Gautam","family":"Thorat","sequence":"additional","affiliation":[{"name":"School of Computing, University of Connecticut, Storrs, CONNECTICUT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7489-2860","authenticated-orcid":false,"given":"Xi","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computing, University of Connecticut, Storrs, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2025-2195","authenticated-orcid":false,"given":"Hongwu","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computing, University of Connecticut, Storrs, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-2830","authenticated-orcid":false,"given":"Nuo","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0891-1231","authenticated-orcid":false,"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, Minneapolis, Minnesota, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-9798","authenticated-orcid":false,"given":"Shaoyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology, Hoboken, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"ACM\/SIGDA. 2012. DAC 2012 Contest. http:\/\/archive.sigda.org\/dac2012\/contest\/dac2012_contest.html Accessed: 2025-02-28."},{"key":"e_1_3_3_1_3_2","unstructured":"Abien\u00a0Fred Agarap. 2019. Deep Learning using Rectified Linear Units (ReLU). arxiv:https:\/\/arXiv.org\/abs\/1803.08375\u00a0[cs.NE] https:\/\/arxiv.org\/abs\/1803.08375"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC47756.2020.9045178"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Lilas Alrahis Abhrajit Sengupta Johann Knechtel Satwik Patnaik Hani Saleh Baker Mohammad Mahmoud Al-Qutayri and Ozgur Sinanoglu. 2021. GNN-RE: Graph neural networks for reverse engineering of gate-level netlists. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 8 (2021) 2435\u20132448.","DOI":"10.1109\/TCAD.2021.3110807"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2717764.2723572"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Zhuomin Chai Yuxiang Zhao Wei Liu Yibo Lin Runsheng Wang and Ru Huang. 2023. CircuitNet: An Open-Source Dataset for Machine Learning in VLSI CAD Applications With Improved Domain-Specific Evaluation Metric and Learning Strategies. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 42 12 (2023) 5034\u20135047. https:\/\/doi.org\/10.1109\/TCAD.2023.3287970","DOI":"10.1109\/TCAD.2023.3287970"},{"key":"e_1_3_3_1_8_2","unstructured":"Ruoyu Cheng and Junchi Yan. 2021. On joint learning for solving placement and routing in chip design. Advances in Neural Information Processing Systems 34 (2021) 16508\u201316519."},{"key":"e_1_3_3_1_9_2","unstructured":"Compute express link (CXL) specification [n. d.]. https:\/\/computeexpresslink.org\/cxl-specification\/ Accessed: 2025-02-25."},{"key":"e_1_3_3_1_10_2","unstructured":"cuSPARSE Documents [n. d.]. https:\/\/docs.nvidia.com\/cuda\/cusparse\/ Accessed: 2025-02-25."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"DEEP GRAPH LIBRARY [n. d.]. https:\/\/www.dgl.ai Accessed: 2025-02-25.","DOI":"10.70315\/uloap.ulete.2025.0201005"},{"key":"e_1_3_3_1_12_2","unstructured":"Stefan Elfwing Eiji Uchibe and Kenji Doya. 2017. Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/1702.03118\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1702.03118"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643446"},{"key":"e_1_3_3_1_15_2","first-page":"1263","volume-title":"International conference on machine learning","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel\u00a0S Schoenholz, Patrick\u00a0F Riley, Oriol Vinyals, and George\u00a0E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263\u20131272."},{"key":"e_1_3_3_1_16_2","volume-title":"Unified Memory for CUDA Beginners","author":"Harris Mark","year":"2021","unstructured":"Mark Harris. 2021. Unified Memory for CUDA Beginners. Accessed: 2025-2-25."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-SoC.2019.8920342"},{"key":"e_1_3_3_1_18_2","series-title":"(ICML\u201920)","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Kurtz Mark","year":"2020","unstructured":"Mark Kurtz, Justin Kopinsky, Rati Gelashvili, Alexander Matveev, John Carr, Michael Goin, William Leiserson, Sage Moore, Bill Nell, Nir Shavit, and Dan Alistarh. 2020. Inducing and exploiting activation sparsity for fast neural network inference. In Proceedings of the 37th International Conference on Machine Learning(ICML\u201920). JMLR.org, Article 513, 11\u00a0pages."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650951"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Shiyang Li Ruiqi Tang Jingyu Zhu Ziyi Zhao Xiaoli Gong Wenwen Wang Jin Zhang and Pen-Chung Yew. 2023. Liberator: A Data Reuse Framework for Out-of-Memory Graph Computing on GPUs. IEEE Transactions on Parallel and Distributed Systems 34 6 (2023) 1954\u20131967. https:\/\/doi.org\/10.1109\/TPDS.2023.3268662","DOI":"10.1109\/TPDS.2023.3268662"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD52597.2021.9531070"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Seung\u00a0Won Min Vikram\u00a0Sharma Mailthody Zaid Qureshi Jinjun Xiong Eiman Ebrahimi and Wen-mei Hwu. 2020. EMOGI: efficient memory-access for out-of-memory graph-traversal in GPUs. Proc. VLDB Endow. 14 2 (Oct. 2020) 114\u2013127. https:\/\/doi.org\/10.14778\/3425879.3425883","DOI":"10.14778\/3425879.3425883"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Azalia Mirhoseini Anna Goldie Mustafa Yazgan Joe\u00a0Wenjie Jiang Ebrahim Songhori Shen Wang Young-Joon Lee Eric Johnson Omkar Pathak Azade Nazi et\u00a0al. 2021. A graph placement methodology for fast chip design. Nature 594 7862 (2021) 207\u2013212.","DOI":"10.1038\/s41586-021-03544-w"},{"key":"e_1_3_3_1_25_2","volume-title":"GPU Technology Conference","volume":"12","author":"Naumov Maxim","year":"2010","unstructured":"Maxim Naumov, L Chien, Philippe Vandermersch, and Ujval Kapasi. 2010. Cusparse library. In GPU Technology Conference , Vol.\u00a012."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Amir Hossein\u00a0Nodehi Sabet Zhijia Zhao and Rajiv Gupta. 2020. Subway: minimizing data transfer during out-of-GPU-memory graph processing(EuroSys \u201920). Association for Computing Machinery New York NY USA Article 12 16\u00a0pages. https:\/\/doi.org\/10.1145\/3342195.3387537","DOI":"10.1145\/3342195.3387537"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"e_1_3_3_1_28_2","unstructured":"Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio Yoshua Bengio et\u00a0al. 2017. Graph attention networks. stat 1050 20 (2017) 10\u201348550."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530675"},{"key":"e_1_3_3_1_30_2","first-page":"515","volume-title":"15th USENIX symposium on operating systems design and implementation (OSDI 21)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. { GNNAdvisor} : An adaptive and efficient runtime system for { GNN} acceleration on { GPUs}. In 15th USENIX symposium on operating systems design and implementation (OSDI 21). 515\u2013531."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Zhiyao Xie Rongjian Liang Xiaoqing Xu Jiang Hu Chen-Chia Chang Jingyu Pan and Yiran Chen. 2022. Preplacement net length and timing estimation by customized graph neural network. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 11 (2022) 4667\u20134680.","DOI":"10.1109\/TCAD.2022.3149977"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Runzhen Xue Dengke Han Mingyu Yan Mo Zou Xiaocheng Yang Duo Wang Wenming Li Zhimin Tang John Kim Xiaochun Ye and Dongrui Fan. 2024. HiHGNN: Accelerating HGNNs Through Parallelism and Data Reusability Exploitation. IEEE Transactions on Parallel and Distributed Systems 35 7 (2024) 1122\u20131138. https:\/\/doi.org\/10.1109\/TPDS.2024.3394841","DOI":"10.1109\/TPDS.2024.3394841"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656540"},{"key":"e_1_3_3_1_34_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xun Jiang","year":"2024","unstructured":"Jiang Xun, Zhuomin Chai, Yuxiang Zhao, Yibo Lin, Runsheng Wang, and Ru Huang. 2024. CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nMFSUjxMIl"},{"key":"e_1_3_3_1_35_2","volume-title":"Advances in Neural Information Processing Systems","author":"Yang Shuwen","year":"2022","unstructured":"Shuwen Yang, Zhihao Yang, Dong Li, Yingxue Zhang, Zhanguang Zhang, Guojie Song, and Jianye HAO. 2022. Versatile Multi-stage Graph Neural Network for Circuit Representation. In Advances in Neural Information Processing Systems, Alice\u00a0H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=nax3ATLrovW"},{"key":"e_1_3_3_1_36_2","series-title":"Proceedings of Machine Learning Research","first-page":"7364","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Zhang Guo","year":"2019","unstructured":"Guo Zhang, Hao He, and Dina Katabi. 2019. Circuit-GNN: Graph Neural Networks for Distributed Circuit Design. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 7364\u20137373. https:\/\/proceedings.mlr.press\/v97\/zhang19e.html"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549361"}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3734528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:02:16Z","timestamp":1755867736000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3734528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":36,"alternative-id":["10.1145\/3721145.3734528","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3734528","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}