{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:08Z","timestamp":1740123548047,"version":"3.37.3"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T00:00:00Z","timestamp":1696636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T00:00:00Z","timestamp":1696636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272474,61561146395","62272474,61561146395","62272474,61561146395"],"award-info":[{"award-number":["62272474,61561146395","62272474,61561146395","62272474,61561146395"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s11227-023-05679-1","type":"journal-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T05:01:49Z","timestamp":1696654909000},"page":"5832-5846","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving CUDA performance of an unstructured high-order CFD application under OP2 framework"],"prefix":"10.1007","volume":"80","author":[{"given":"Kangjin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonggang","family":"Che","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanfu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,7]]},"reference":[{"key":"5679_CR1","doi-asserted-by":"crossref","unstructured":"Mullowney P, Li R, Thomas S, Ananthan S, Sharma A, Rood JS, Williams AB, Sprague MA (2021) Preparing an incompressible-flow fluid dynamics code for exascale-class wind energy simulations. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201316","DOI":"10.1145\/3458817.3476185"},{"key":"5679_CR2","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1631\/FITEE.1800494","volume":"19","author":"X-K Liao","year":"2018","unstructured":"Liao X-K, Lu K, Yang C-Q, Li J-W, Yuan Y, Lai M-C, Huang L-B, Lu P-J, Fang J-B, Ren J et al (2018) Moving from exascale to zettascale computing: challenges and techniques. Front Inf Technol Electron Eng 19:1236\u20131244","journal-title":"Front Inf Technol Electron Eng"},{"key":"5679_CR3","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/s42514-020-00039-4","volume":"2","author":"J Fang","year":"2020","unstructured":"Fang J, Huang C, Tang T, Wang Z (2020) Parallel programming models for heterogeneous many-cores: a comprehensive survey. CCF Trans High Perform Comput 2:382\u2013400","journal-title":"CCF Trans High Perform Comput"},{"key":"5679_CR4","doi-asserted-by":"crossref","unstructured":"Dai Z, Wang Y, Wang F, Ming L, Zhang J, et al. (2022) Performance optimization and analysis of the unstructured discontinuous galerkin solver on multi-core and many-core architectures. arXiv preprint arXiv:2209.01877","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys57074.2022.00158"},{"key":"5679_CR5","doi-asserted-by":"crossref","unstructured":"Mudalige GR, Giles MB, Reguly I, Bertolli C, Kelly PH (2012) Op2: an active library framework for solving unstructured mesh-based applications on multi-core and many-core architectures. In: 2012 Innovative Parallel Computing (InPar), pp 1\u201312. IEEE","DOI":"10.1109\/InPar.2012.6339594"},{"key":"5679_CR6","doi-asserted-by":"crossref","unstructured":"Reguly IZ, Owenson AM, Powell A, Jarvis SA, Mudalige GR (2021) Under the hood of sycl\u2013an initial performance analysis with an unstructured-mesh cfd application. In: High Performance Computing: 36th International Conference, ISC High Performance 2021, Virtual Event, June 24\u2013July 2, 2021, Proceedings 36, pp 391\u2013410. Springer","DOI":"10.1007\/978-3-030-78713-4_21"},{"key":"5679_CR7","doi-asserted-by":"crossref","unstructured":"Mudalige GR, Giles MB, Thiyagalingam J, Reguly IZ, Bertolli C, Kelly PHJ, Trefethen AE (2013) Design and initial performance of a high-level unstructured mesh framework on heterogeneous parallel systems. In: Elsevier B.V., pp 669\u2013692","DOI":"10.1016\/j.parco.2013.09.004"},{"key":"5679_CR8","doi-asserted-by":"crossref","unstructured":"Reguly IZ, L\u00e1szl\u00f3 E, Mudalige GR, Giles MB (2014) Vectorizing unstructured mesh computations for many-core architectures. In: Proceedings of Programming Models and Applications on Multicores and Manycores, pp 39\u201350","DOI":"10.1145\/2560683.2560686"},{"key":"5679_CR9","doi-asserted-by":"crossref","unstructured":"Reguly IZ, Mudalige GR, Giles MB (2015) Design and development of domain specific active libraries with proxy applications. In: 2015 IEEE International Conference on Cluster Computing, pp 738\u2013745. IEEE","DOI":"10.1109\/CLUSTER.2015.128"},{"issue":"5","key":"5679_CR10","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1109\/TPDS.2015.2453972","volume":"27","author":"IZ Reguly","year":"2015","unstructured":"Reguly IZ, Mudalige GR, Bertolli C, Giles MB, Betts A, Kelly PH, Radford D (2015) Acceleration of a full-scale industrial cfd application with op2. IEEE Trans Parallel Distrib Syst 27(5):1265\u20131278","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"5679_CR11","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1093\/comjnl\/bxr062","volume":"55","author":"MB Giles","year":"2012","unstructured":"Giles MB, Mudalige GR, Sharif Z, Markall G, Kelly PH (2012) Performance analysis and optimization of the op2 framework on many-core architectures. Comput J 55(2):168\u2013180","journal-title":"Comput J"},{"key":"5679_CR12","doi-asserted-by":"crossref","unstructured":"Reguly IZ, Mudalige GR (2020) Modernising an industrial cfd application. In: 2020 Eighth International Symposium on Computing and Networking Workshops (CANDARW), pp 191\u2013196. IEEE","DOI":"10.1109\/CANDARW51189.2020.00046"},{"issue":"11","key":"5679_CR13","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1016\/j.jpdc.2012.07.008","volume":"73","author":"MB Giles","year":"2013","unstructured":"Giles MB, Mudalige GR, Spencer B, Bertolli C, Reguly I (2013) Designing op2 for gpu architectures. J Parallel Distrib Comput 73(11):1451\u20131460","journal-title":"J Parallel Distrib Comput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05679-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-023-05679-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05679-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T20:09:10Z","timestamp":1710274150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-023-05679-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,7]]},"references-count":13,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["5679"],"URL":"https:\/\/doi.org\/10.1007\/s11227-023-05679-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2023,10,7]]},"assertion":[{"value":"19 September 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No competing of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}