{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T02:02:38Z","timestamp":1782439358991,"version":"3.54.5"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,6,13]],"date-time":"2016-06-13T00:00:00Z","timestamp":1465776000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004281","name":"Narodowe Centrum Nauki","doi-asserted-by":"publisher","award":["UMO- 2015\/17\/D\/ST6\/04059"],"award-info":[{"award-number":["UMO- 2015\/17\/D\/ST6\/04059"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,2]]},"DOI":"10.1007\/s11227-016-1774-z","type":"journal-article","created":{"date-parts":[[2016,6,13]],"date-time":"2016-06-13T09:44:39Z","timestamp":1465811079000},"page":"664-675","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Performance modeling of 3D MPDATA simulations on GPU cluster"],"prefix":"10.1007","volume":"73","author":[{"given":"Krzysztof","family":"Rojek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,6,13]]},"reference":[{"issue":"4","key":"1774_CR1","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.simpat.2006.11.014","volume":"15","author":"L Adhianto","year":"2007","unstructured":"Adhianto L, Chapman B (2007) Performance modeling of communication and computation in hybrid MPI and OpenMP applications. Simul Model Pract Theory 15(4):481\u2013491","journal-title":"Simul Model Pract Theory"},{"issue":"2","key":"1774_CR2","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1006\/jpdc.2000.1677","volume":"61","author":"K Al-Tawil","year":"2001","unstructured":"Al-Tawil K, Moritz C (2001) Performance modeling and evaluation of MPI. J Parallel Distrib Comput 61(2):202\u2013223","journal-title":"J Parallel Distrib Comput"},{"issue":"11","key":"1774_CR3","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MC.2009.372","volume":"42","author":"K Barker","year":"2009","unstructured":"Barker K, Davis K, Hoisie A, Kerbyson D, Lang M, Scott P, Sancho J (2009) Using performance modeling to design large-scale systems. Computer 42(11):42\u201349","journal-title":"Computer"},{"key":"1774_CR4","doi-asserted-by":"crossref","unstructured":"Cai J, Rendell A, Strazdins P (2008) Performance models for cluster-enabled OpenMP implementations. Comput Syst Archit Conf, pp 1\u20138","DOI":"10.1109\/APCSAC.2008.4625433"},{"key":"1774_CR5","doi-asserted-by":"crossref","unstructured":"Ciznicki M et al (2014) Elliptic solver performance evaluation on modern hardware architectures. In: Proceedings of the PPAM 2013, Lecture notes in computer science 8384:155\u2013165","DOI":"10.1007\/978-3-642-55224-3_16"},{"issue":"1","key":"1774_CR6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1137\/070693199","volume":"51","author":"K Datta","year":"2009","unstructured":"Datta K, Kamil S, Williams S, Oliker L, Shalf J, Yelick K (2009) Optimization and performance modeling of stencil computations on modern microprocessors. SIAM Rev 51(1):129\u2013159","journal-title":"SIAM Rev"},{"key":"1774_CR7","volume-title":"Introduction to high performance computing for scienceand engineers","author":"G Hager","year":"2011","unstructured":"Hager G, Wellein G (2011) Introduction to high performance computing for scienceand engineers. CRC Press, London"},{"key":"1774_CR8","doi-asserted-by":"crossref","unstructured":"Hoefler T, Gropp W, Thakur R, Traff J (2010) Toward performance models of MPI implementations for understanding application scaling issues. In: 17th European MPI Users Group Meeting, EuroMPI 2010, Lecture notes in computer science 6305:21\u201330","DOI":"10.1007\/978-3-642-15646-5_3"},{"key":"1774_CR9","doi-asserted-by":"crossref","unstructured":"Kamil S, Husbands P, Oliker L, Shalf J, Yelick K (2005) Impact of modern memory subsystems on cache optimizations for stencil computations. In: Proceedings of the 2005 workshop on memory system performance, pp 36\u201343","DOI":"10.1145\/1111583.1111589"},{"issue":"3","key":"1774_CR10","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/MCSE.2011.117","volume":"14","author":"A Khajeh-Saeed","year":"2012","unstructured":"Khajeh-Saeed A, Perot JB (2012) Computational fluid dynamics simulations using many graphics processors. Comput Sci Eng 14(3):10\u201319","journal-title":"Comput Sci Eng"},{"key":"1774_CR11","unstructured":"PizDaint & PizDora. http:\/\/www.cscs.ch\/computers\/piz_daint\/index.html"},{"key":"1774_CR12","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1016\/j.compfluid.2007.12.001","volume":"37","author":"JM Prusa","year":"2008","unstructured":"Prusa JM, Smolarkiewicz PK, Wyszogrodzki AA (2008) EULAG, a computational model for multiscale flows. Comput Fluids 37:1193\u20131207","journal-title":"Comput Fluids"},{"key":"1774_CR13","first-page":"145","volume":"8384","author":"K Rojek","year":"2014","unstructured":"Rojek K, Szustak L, Wyrzykowski R (2014) Performance analysis for stencil-based 3D MPDATA algorithm on GPU architecture. Proc PPAM 2013 8384:145\u2013154","journal-title":"Proc PPAM 2013"},{"issue":"4","key":"1774_CR14","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1002\/cpe.3417","volume":"27","author":"K Rojek et al","year":"2015","unstructured":"Rojek et al K (2015) Adaptation of fluid model EULAG to graphics processing unit architecture. Concurr Comput Pract Exp 27(4):937\u2013957","journal-title":"Concurr Comput Pract Exp"},{"key":"1774_CR15","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/978-3-319-21909-7_43","volume":"9251","author":"K Rojek","year":"2015","unstructured":"Rojek K, Wyrzykowski R (2015) Parallelization of 3D MPDATA algorithm using many graphics processors, parallel computing technologies. Lect Notes Comp Sci 9251:445\u2013457","journal-title":"Lect Notes Comp Sci"},{"key":"1774_CR16","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1002\/fld.1071","volume":"50","author":"P Smolarkiewicz","year":"2006","unstructured":"Smolarkiewicz P (2006) Multidimensional positive definite advection transport algorithm: an overview. Int J Numer Methods Fluids 50:1123\u20131144","journal-title":"Int J Numer Methods Fluids"},{"key":"1774_CR17","doi-asserted-by":"publisher","unstructured":"Szustak L et al (2015) Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci Program 2015. doi: 10.1155\/2015\/642705","DOI":"10.1155\/2015\/642705"},{"key":"1774_CR18","unstructured":"Wojcik D et al (2012) A study on paralllel performance of the EULAG F90\/F95 Code. In: Proceedings of the PPAM 2011, Lecture notes in computer Science 7204:419\u2013427"},{"key":"1774_CR19","unstructured":"Wyrzykowski R, Szustak L, Rojek K, Tomas A (2013) Towards efficient decomposition and parallelization of MPDATA on hybrid CPU-GPU cluster. In: Proceedings of the LSSC 2013, lecture notes in computer science 8353:457\u2013464"},{"issue":"8","key":"1774_CR20","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.parco.2014.04.009","volume":"40","author":"R Wyrzykowski","year":"2014","unstructured":"Wyrzykowski R, Rojek K, Szustak L (2014) Parallelization of 2D MPDATA EULAG algorithm on hybrid architectures with GPU accelerators. Parallel Comput 40(8):425\u2013447","journal-title":"Parallel Comput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1774-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1774-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1774-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1774-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T12:17:03Z","timestamp":1498306623000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1774-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,13]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,2]]}},"alternative-id":["1774"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1774-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,6,13]]}}}