{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:51:11Z","timestamp":1777063871222,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDA0500402"],"award-info":[{"award-number":["XDA0500402"]}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDB0500101"],"award-info":[{"award-number":["XDB0500101"]}]},{"name":"Major Key Project of PCL","award":["PCL2025A09"],"award-info":[{"award-number":["PCL2025A09"]}]},{"name":"Youth Fund of Computer Network Information Center of Chinese Academy of Sciences","award":["24YF07"],"award-info":[{"award-number":["24YF07"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803604","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"1181-1195","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["swKokkos: An Athread Backend for Enhanced Kokkos with the Sunway Heterogeneous Architecture"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3824-656X","authenticated-orcid":false,"given":"Junlin","family":"Wei","sequence":"first","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"Pengcheng Laboratory, Shenzhen, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4463-8666","authenticated-orcid":false,"given":"Jinrong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6216-5324","authenticated-orcid":false,"given":"Wu","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7244-3458","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4568-2549","authenticated-orcid":false,"given":"Yehong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9865-2212","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7451-1474","authenticated-orcid":false,"given":"Lian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2461-8135","authenticated-orcid":false,"given":"Xiang","family":"Han","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3770-7898","authenticated-orcid":false,"given":"Zhenjia","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1650-978X","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9089-1587","authenticated-orcid":false,"given":"Haoyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0778-3805","authenticated-orcid":false,"given":"Yidi","family":"Bai","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-4947","authenticated-orcid":false,"given":"Maoxue","family":"Yu","sequence":"additional","affiliation":[{"name":"Laoshan Laboratory, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0907-2671","authenticated-orcid":false,"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"Laoshan Laboratory, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-0398","authenticated-orcid":false,"given":"Hailong","family":"Liu","sequence":"additional","affiliation":[{"name":"Laoshan Laboratory, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0150-5815","authenticated-orcid":false,"given":"Xuebin","family":"Chi","sequence":"additional","affiliation":[{"name":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510454.3516827"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00023-0"},{"key":"e_1_3_2_1_3_1","unstructured":"Huanqi Cao and Jiajie Chen. 2022. Design and Implementation of ShenWei Universal C\/C++. arXiv:2208.00607 [cs.PL] https:\/\/arxiv.org\/abs\/2208.00607"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-74224-9_5"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710893"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.2172\/1398234"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/917630"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420211028940"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3847\/1538-4365\/ad9687"},{"key":"e_1_3_2_1_12_1","volume-title":"Towards Exascale Computation for Turbomachinery Flows. In SC23: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society, 1\u201312","author":"Fu Yuhang","year":"2023","unstructured":"Yuhang Fu, Weiqi Shen, Jiahuan Cui, Yao Zheng, Guangwen Yang, Zhao Liu, Jifa Zhang, Tingwei Ji, Fangfang Xie, Xiaojing Lv, et al. 2023. Towards Exascale Computation for Turbomachinery Flows. In SC23: International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society, 1\u201312."},{"key":"e_1_3_2_1_13_1","volume-title":"The Kokkos OpenMPTarget Backend: Implementation and Lessons Learned","author":"Gayatri Rahulkumar","unstructured":"Rahulkumar Gayatri, Stephen L. Olivier, Christian R. Trott, Johannes Doerfert, Jan Ciesko, and Damien Lebrun-Grandie. 2023. The Kokkos OpenMPTarget Backend: Implementation and Lessons Learned. In OpenMP: Advanced Task-Based, Device and Compiler Programming, Simon McIntosh-Smith, Michael Klemm, Bronis R. de Supinski, Tom Deakin, and Jannis Klinkenberg (Eds.). Springer Nature Switzerland, Cham, 99\u2013113."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC62374.2024.00035"},{"key":"e_1_3_2_1_15_1","volume-title":"Kokkos-Based Implementation of MPCD on Heterogeneous Nodes. In International Conference on Parallel Processing and Applied Mathematics. Springer, 3\u201313","author":"Halver Rene","year":"2022","unstructured":"Rene Halver, Christoph Junghans, and Godehard Sutmann. 2022. Kokkos-Based Implementation of MPCD on Heterogeneous Nodes. In International Conference on Parallel Processing and Applied Mathematics. Springer, 3\u201313."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-015-0418-x"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241271005"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571891"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3627045"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/PAWATM51920.2020.00011"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2979"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CISCE52179.2021.9445916"},{"key":"e_1_3_2_1_23_1","unstructured":"Haoran Lin Lifeng Yan Qixin Chang Haitian Lu Chenlin Li Quanjie He Zeyu Song Xiaohui Duan Zekun Yin Yuxuan Li et al. 2024. O2ath: An OpenMP offloading toolkit for the sunway heterogeneous manycore platform. CCF Transactions on High Performance Computing (2024) 1\u201313."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00376-019-9208-5"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13351-012-0305-y"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02916365"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3097276"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2018.06.005"},{"key":"e_1_3_2_1_29_1","first-page":"581","article-title":"The hybrid MPI and Openmp parallel scheme of GRAPES global model(in Chinese)","volume":"25","author":"J","year":"2014","unstructured":"J Qin-gu and J Zhi-yan. 2014. The hybrid MPI and Openmp parallel scheme of GRAPES global model(in Chinese). J. Appl. Meteorological Sci 25, 5 (2014), 581\u2013591.","journal-title":"J. Appl. Meteorological Sci"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49943-3_7"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.2514\/6.2024-0045"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2023.108973"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3615318.3615321"},{"key":"e_1_3_2_1_34_1","volume-title":"KEDM: A performance-portable implementation of empirical dynamic modeling using Kokkos. In Practice and Experience in Advanced Research Computing. 1\u20138.","author":"Takahashi Keichi","year":"2021","unstructured":"Keichi Takahashi, Wassapon Watanakeesuntorn, Kohei Ichikawa, Joseph Park, Ryousei Takano, Jason Haga, George Sugihara, and Gerald M Pao. 2021. KEDM: A performance-portable implementation of empirical dynamic modeling using Kokkos. In Practice and Experience in Advanced Research Computing. 1\u20138."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3627044"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3098509"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241261987"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589246.3595369"},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613209"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5194\/gmd-14-2781-2021"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00009"},{"key":"e_1_3_2_1_44_1","unstructured":"Junlin Wei Jinrong Jiang Hailong Liu Feng Zhang Pengfei Lin Pengfei Wang Yongqiang Yu Xuebin Chi Lian Zhao Mengrong Ding et al. 2023. LICOM3-CUDA: A GPU version of LASG\/IAP climate system ocean model version 3 based on CUDA. The Journal of Supercomputing (2023) 1\u201331."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.06.029"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.100843"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3771788"},{"key":"e_1_3_2_1_48_1","volume-title":"A numerical world ocean general circulation model. Advances in atmospheric sciences 6, 1","author":"Xuehong Zhang","year":"1989","unstructured":"Zhang Xuehong and Liang Xinzhong. 1989. A numerical world ocean general circulation model. Advances in atmospheric sciences 6, 1 (1989), 44\u201361."},{"key":"e_1_3_2_1_49_1","first-page":"1","article-title":"swNEMO_v4.0: an ocean model NEMO for the next generation Sunway supercomputer","volume":"2022","author":"Ye Yuejin","year":"2022","unstructured":"Yuejin Ye, Zhenya Song, Shengchang Zhou, Yao Liu, Qi Shu, Bingzhuo Wang, Weiguo Liu, Fangli Qiao, and Lanning Wang. 2022. swNEMO_v4.0: an ocean model NEMO for the next generation Sunway supercomputer. Geoscientific Model Development Discussions 2022 (2022), 1\u201329.","journal-title":"Geoscientific Model Development Discussions"},{"key":"e_1_3_2_1_50_1","volume-title":"swCUDA: Auto parallel code translation framework from CUDA to ATHREAD for new generation sunway supercomputer. CCF Transactions on High Performance Computing","author":"Yu Maoxue","year":"2024","unstructured":"Maoxue Yu, Guanghao Ma, Zhuoya Wang, Shuai Tang, Yuhu Chen, Yucheng Wang, Yuanyuan Liu, Dongning Jia, and Zhiqiang Wei. 2024. swCUDA: Auto parallel code translation framework from CUDA to ATHREAD for new generation sunway supercomputer. CCF Transactions on High Performance Computing (2024), 1\u201320."},{"key":"e_1_3_2_1_51_1","first-page":"877","article-title":"Development and evaluation of the dynamic framework of an ocean general circulation model with arbitrary orthogonal curvilinear coordinate","volume":"42","author":"Yu YQ","year":"2018","unstructured":"YQ Yu, SL Tang, HL Liu, PF Lin, and XL Li. 2018. Development and evaluation of the dynamic framework of an ocean general circulation model with arbitrary orthogonal curvilinear coordinate. Chinese Journal of Atmospheric Sciences 42, 4 (2018), 877\u2013889.","journal-title":"Chinese Journal of Atmospheric Sciences"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:21:33Z","timestamp":1777062093000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":51,"alternative-id":["10.1145\/3767295.3803604","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803604","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}