{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:10Z","timestamp":1740123550312,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2017,1,19]],"date-time":"2017-01-19T00:00:00Z","timestamp":1484784000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"NSF China","award":["91530323"],"award-info":[{"award-number":["91530323"]}]},{"name":"National Key Research and Development Plan of China","award":["2016YFB0200600"],"award-info":[{"award-number":["2016YFB0200600"]}]},{"name":"National Key Technology RD Program of China","award":["2012BAC22B01"],"award-info":[{"award-number":["2012BAC22B01"]}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["QYZDB-SSW-SYS006"],"award-info":[{"award-number":["QYZDB-SSW-SYS006"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s11227-017-1958-1","type":"journal-article","created":{"date-parts":[[2017,1,19]],"date-time":"2017-01-19T09:37:37Z","timestamp":1484818657000},"page":"2823-2842","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Development of a hybrid parallel MCV-based high-order global shallow-water model"],"prefix":"10.1007","volume":"73","author":[{"given":"Peng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chungang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingliang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueshun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,19]]},"reference":[{"issue":"2","key":"1958_CR1","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/0743-7315(90)90028-N","volume":"10","author":"HR Arabnia","year":"1990","unstructured":"Arabnia HR (1990) A parallel algorithm for the arbitrary rotation of digitized images using process-and-data-decomposition approach. J Parallel Distrib Comput 10(2):188\u2013192","journal-title":"J Parallel Distrib Comput"},{"issue":"3","key":"1958_CR2","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/BF00130109","volume":"10","author":"HR Arabnia","year":"1996","unstructured":"Arabnia HR, Bhandarkar SM (1996) Parallel stereocorrelation on a reconfigurable multi-ring network. J Supercomput 10(3):243\u2013269","journal-title":"J Supercomput"},{"issue":"3","key":"1958_CR3","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1467-8659.1986.tb00296.x","volume":"5","author":"HR Arabnia","year":"1986","unstructured":"Arabnia HR, Oliver MA (1986) Fast operations on raster images with SIMD machine architectures. Comput Graph Forum 5(3):179\u2013188","journal-title":"Comput Graph Forum"},{"issue":"5","key":"1958_CR4","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1093\/comjnl\/30.5.425","volume":"30","author":"HR Arabnia","year":"1987","unstructured":"Arabnia HR, Oliver MA (1987) A transputer network for the arbitrary rotation of digitised images. Comput J 30(5):425\u2013433","journal-title":"Comput J"},{"key":"1958_CR5","doi-asserted-by":"crossref","unstructured":"Arabnia HR, Oliver MA (1989) A transputer network for fast operations on digitised images. In: Computer graphics forum, vol\u00a08, p 312","DOI":"10.1111\/j.1467-8659.1989.tb00448.x"},{"key":"1958_CR6","doi-asserted-by":"crossref","unstructured":"Bernaschi M, Bisson M, Endo T, Matsuoka S, Fatica M, Melchionna S (2011) Petaflop biofluidics simulations on a two million-core system. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, p 4","DOI":"10.1145\/2063384.2063389"},{"issue":"1","key":"1958_CR7","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1006\/jpdc.1995.1011","volume":"24","author":"SM Bhandarkar","year":"1995","unstructured":"Bhandarkar SM, Arabnia HR (1995) The hough transform on a reconfigurable multi-ring network. J Parallel Distrib Comput 24(1):107\u2013114","journal-title":"J Parallel Distrib Comput"},{"issue":"11","key":"1958_CR8","doi-asserted-by":"crossref","first-page":"1783","DOI":"10.1016\/0167-8191(95)00032-9","volume":"21","author":"SM Bhandarkar","year":"1995","unstructured":"Bhandarkar SM, Arabnia HR (1995) The refine multiprocessor: theoretical properties and algorithms. Parallel Comput 21(11):1783\u20131805","journal-title":"Parallel Comput"},{"issue":"2","key":"1958_CR9","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1142\/S0218001495000110","volume":"9","author":"SM Bhandarkar","year":"1995","unstructured":"Bhandarkar SM, Arabnia HR, Smith JW (1995) A reconfigurable architecture for image processing and computer vision. Int J Pattern Recognit Artif Intell 9(2):201\u2013229","journal-title":"Int J Pattern Recognit Artif Intell"},{"key":"1958_CR10","doi-asserted-by":"crossref","unstructured":"Carpenter I, Archibald RK, Evans KJ, Larkin J, Micikevicius P, Norman M, Rosinski J, Schwarzmeier J, Taylor MA (2013) Progress towards accelerating HOMME on hybrid multi-core systems. Int J High Perform Comput Appl 27(3):335\u2013347","DOI":"10.1177\/1094342012462751"},{"key":"1958_CR11","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.jcp.2013.10.026","volume":"271","author":"C Chen","year":"2014","unstructured":"Chen C, Li X, Shen X, Xiao F (2014) Global shallow water models based on multi-moment constrained finite volume method and three quasi-uniform spherical grids. J Comput Phys 271:191\u2013223","journal-title":"J Comput Phys"},{"issue":"10","key":"1958_CR12","doi-asserted-by":"crossref","first-page":"5019","DOI":"10.1016\/j.jcp.2008.01.033","volume":"227","author":"C Chen","year":"2008","unstructured":"Chen C, Xiao F (2008) Shallow water model on cubed-sphere by multi-moment finite volume method. J Comput Phys 227(10):5019\u20135044","journal-title":"J Comput Phys"},{"key":"1958_CR13","doi-asserted-by":"crossref","unstructured":"Cockburn B, Karniadakis G, Shu C, Griebel M (2000) Discontinuous Galerkin methods theory, computation and applications. Lectures notes in computational science and engineering, vol 11. Inc. Marzo del","DOI":"10.1007\/978-3-642-59721-3"},{"key":"1958_CR14","unstructured":"Cumming B, Osuna C, Gysi T, Bianco M, Lapillonne X, Fuhrer O, Schulthess TC (2013) A review of the challenges and results of refactoring the community climate code cosmo for hybrid cray hpc systems. In: Proceedings of Cray User Group"},{"key":"1958_CR15","unstructured":"Demeshko I, Maruyama N, Tomita H, Matsuoka S (2012) Multi-GPU implementation of the NICAM atmospheric model. In: European Conference on Parallel Processing. Springer, pp 175\u2013184"},{"key":"1958_CR16","doi-asserted-by":"publisher","unstructured":"Govett M, Middlecoff J, Henderson T (2014) Directive-based parallelization of the NIM weather model for GPUs. In: First Workshop on Accelerator Programming using Directives (WACCPD), pp 55\u201361. doi: 10.1109\/WACCPD.2014.9","DOI":"10.1109\/WACCPD.2014.9"},{"key":"1958_CR17","doi-asserted-by":"crossref","unstructured":"Hamada T, Narumi T, Yokota R, Yasuoka K, Nitadori K, Taiji M (2009) 42 Tflops hierarchical N-body simulations on GPUs with applications in both astrophysics and turbulence. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis. ACM, p 62","DOI":"10.1145\/1654059.1654123"},{"key":"1958_CR18","doi-asserted-by":"crossref","unstructured":"Hamada T, Nitadori K (2010) 190 Tflops astrophysical N-body simulation on a cluster of GPUs. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society, pp 1\u20139","DOI":"10.1109\/SC.2010.1"},{"key":"1958_CR19","volume-title":"High resolution numerical modelling of the atmosphere and ocean","author":"K Hamilton","year":"2007","unstructured":"Hamilton K, Ohfuchi W (2007) High resolution numerical modelling of the atmosphere and ocean. Springer, Berlin"},{"issue":"9","key":"1958_CR20","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.5194\/gmd-8-2977-2015","volume":"8","author":"M Huang","year":"2015","unstructured":"Huang M, Mielikainen J, Huang B, Chen H, Huang HLA, Goldberg MD (2015) Development of efficient GPU parallelization of WRF Yonsei University planetary boundary layer scheme. Geosci Model Dev 8(9):2977\u20132990","journal-title":"Geosci Model Dev"},{"key":"1958_CR21","doi-asserted-by":"crossref","unstructured":"Huynh H (2007) A flux reconstruction approach to high-order schemes including discontinuous Galerkin methods. AIAA paper 4079","DOI":"10.2514\/6.2007-4079"},{"issue":"5","key":"1958_CR22","doi-asserted-by":"crossref","first-page":"1774","DOI":"10.1016\/j.jcp.2009.11.008","volume":"229","author":"S Ii","year":"2010","unstructured":"Ii S, Xiao F (2010) A global shallow water model using high order multi-moment constrained finite volume method and icosahedral grid. J Comput Phys 229(5):1774\u20131796","journal-title":"J Comput Phys"},{"key":"1958_CR23","doi-asserted-by":"crossref","unstructured":"Jameson A, Schmidt W, Turkel E et al (1981) Numerical solutions of the Euler equations by finite volume methods using Runge-Kutta time-stepping schemes. AIAA paper 1259","DOI":"10.2514\/6.1981-1259"},{"issue":"691","key":"1958_CR24","doi-asserted-by":"crossref","first-page":"2090","DOI":"10.1002\/qj.2504","volume":"141","author":"X Li","year":"2015","unstructured":"Li X, Chen C, Xiao F, Shen X (2015) A high-order multi-moment constrained finite-volume global shallow-water model on the Yin-Yang grid. Q J Royal Meteorol Soc 141(691):2090\u20132102","journal-title":"Q J Royal Meteorol Soc"},{"issue":"8","key":"1958_CR25","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1175\/2007MWR2206.1","volume":"136","author":"X Li","year":"2008","unstructured":"Li X, Chen D, Peng X, Takahashi K, Xiao F (2008) A multimoment finite-volume shallow-water model on the Yin-Yang overset spherical grid. Mon Weather Rev 136(8):3066\u20133086","journal-title":"Mon Weather Rev"},{"key":"1958_CR26","unstructured":"Message Passing Interface Forum. http:\/\/www.mpi-forum.org\/"},{"issue":"04","key":"1958_CR27","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1142\/S0129626408003557","volume":"18","author":"J Michalakes","year":"2008","unstructured":"Michalakes J, Vachharajani M (2008) GPU acceleration of numerical weather prediction. Parallel Process Lett 18(04):531\u2013548","journal-title":"Parallel Process Lett"},{"key":"1958_CR28","unstructured":"Mielikainen J, Huang B, Huang H-LA (2014) Intel Many Integrated Core (MIC) architecture optimization strategies for a memory-bound Weather Research and Forecasting (WRF) Goddard microphysics scheme. Proc SPIE Int Soc Opt Eng 9247(4):1\u20139"},{"issue":"8","key":"1958_CR29","doi-asserted-by":"crossref","first-page":"4106","DOI":"10.1109\/JSTARS.2015.2438638","volume":"8","author":"J Mielikainen","year":"2015","unstructured":"Mielikainen J, Huang B, Huang HA (2015) Optimizing total energy mass flux (TEMF) planetary boundary layer scheme for Intels many integrated core (MIC) architecture. IEEE J Sel Top Appl Earth Obs Remote Sens 8(8):4106\u20134119","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"issue":"12","key":"1958_CR30","doi-asserted-by":"crossref","first-page":"2896","DOI":"10.1175\/JTECH-D-12-00218.1","volume":"30","author":"J Mielikainen","year":"2013","unstructured":"Mielikainen J, Huang B, Huang HL, Goldberg M, Mehta A (2013) Speeding up the computation of WRF double-moment 6-class microphysics scheme with GPU. J Atmos Ocean Technol 30(12):2896\u20132906","journal-title":"J Atmos Ocean Technol"},{"issue":"1","key":"1958_CR31","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1109\/JSTARS.2015.2496583","volume":"9","author":"J Mielikainen","year":"2016","unstructured":"Mielikainen J, Huang B, Huang HLA (2016) Optimizing Purdue-Lin Microphysics Scheme for Intel Xeon Phi Coprocessor. IEEE J Sel Top Appl Earth Obs Remote Sens 9(1):425\u2013438","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"issue":"4","key":"1958_CR32","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1109\/JSTARS.2012.2188780","volume":"5","author":"J Mielikainen","year":"2012","unstructured":"Mielikainen J, Huang B, Huang HLA, Goldberg MD (2012) Improved GPU\/CUDA based parallel weather and research forecast (WRF) single moment 5-class (WSM5) cloud microphysics. IEEE J Sel Top Appl Earth Obs Remote Sens 5(4):1256\u20131265","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"1958_CR33","doi-asserted-by":"crossref","unstructured":"Price E, Mielikainen J, Huang B, Huang H-LA, Lee T (2013) GPU acceleration experience with RRTMG long wave radiation model. Proc SPIE Int Soc Opt Eng 8895(H):1\u201312","DOI":"10.1117\/12.2031450"},{"key":"1958_CR34","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/j.cageo.2012.10.006","volume":"52","author":"J Mielikainen","year":"2013","unstructured":"Mielikainen J, Huang B, Wang J, Huang HLA, Goldberg MD (2013) Compute unified device architecture (CUDA)-based parallelization of WRF Kessler cloud microphysics scheme. Comput Geosci 52:292\u2013299","journal-title":"Comput Geosci"},{"key":"1958_CR35","unstructured":"Mielikainen J, Price E, Huang B, Huang HLA (2015) GPU compute unified device architecture (CUDA)-based parallelization of the RRTMG shortwave rapid radiative transfer model. IEEE J Sel Top Appl Earth Obs Remote Sens 9(2):1\u201311"},{"issue":"5857","key":"1958_CR36","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1126\/science.1148443","volume":"318","author":"H Miura","year":"2007","unstructured":"Miura H, Satoh M, Nasuno T, Noda AT, Oouchi K (2007) A Madden-Julian oscillation event realistically simulated by a global cloud-resolving model. Science 318(5857):1763\u20131765","journal-title":"Science"},{"key":"1958_CR37","unstructured":"PAPI: performance application programming interface. http:\/\/icl.cs.utk.edu\/papi\/index.html"},{"issue":"3","key":"1958_CR38","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/0021-9991(84)90128-1","volume":"54","author":"AT Patera","year":"1984","unstructured":"Patera AT (1984) A spectral element method for fluid dynamics: laminar flow in a channel expansion. J Comput Phys 54(3):468\u2013488","journal-title":"J Comput Phys"},{"key":"1958_CR39","doi-asserted-by":"crossref","unstructured":"Putman WM, Suarez M (2011) Cloud-system resolving simulations with the NASA Goddard Earth Observing System global atmospheric model (GEOS-5). Geophys Res Lett 38(16):239\u2013255","DOI":"10.1029\/2011GL048438"},{"issue":"1","key":"1958_CR40","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1006\/jcph.1996.0047","volume":"124","author":"C Ronchi","year":"1996","unstructured":"Ronchi C, Iacono R, Paolucci PS (1996) The cubed sphere: a new method for the solution of partial differential equations in spherical geometry. J Comput Phys 124(1):93\u2013114","journal-title":"J Comput Phys"},{"issue":"2","key":"1958_CR41","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1175\/1520-0493(1972)100<0136:CFAOTP>2.3.CO;2","volume":"100","author":"R Sadourny","year":"1972","unstructured":"Sadourny R (1972) Conservative finite-difference approximations of the primitive equations on quasi-uniform spherical grids. Mon Weather Rev 100(2):136\u2013144","journal-title":"Mon Weather Rev"},{"key":"1958_CR42","doi-asserted-by":"crossref","first-page":"1535","DOI":"10.1016\/j.procs.2011.04.166","volume":"4","author":"T Shimokawabe","year":"2011","unstructured":"Shimokawabe T, Aoki T, Ishida J, Kawano K, Muroi C (2011) 145 TFlops performance on 3990\u00a0GPUs of TSUBAME 2.0 supercomputer for an operational weather prediction. Proced Comput Sci 4:1535\u20131544","journal-title":"Proced Comput Sci"},{"key":"1958_CR43","doi-asserted-by":"crossref","unstructured":"Shimokawabe T, Aoki T, Muroi C, Ishida J, Kawano K, Endo T, Nukada A, Maruyama N, Matsuoka S (2010) An 80-fold speedup, 15.0 TFlops full GPU acceleration of non-hydrostatic weather model ASUCA production code. In: 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, IEEE, pp 1\u201311","DOI":"10.1109\/SC.2010.9"},{"key":"1958_CR44","doi-asserted-by":"crossref","unstructured":"Shimokawabe T, Aoki T, Takaki T, Yamanaka A, Nukada A, Endo T, Maruyama N, Matsuoka S (2011) Peta-scale phase-field simulation for dendritic solidification on the TSUBAME 2.0 supercomputer. In: 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), IEEE, pp 1\u201311","DOI":"10.1145\/2063384.2063388"},{"issue":"10","key":"1958_CR45","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1002\/cpe.2951","volume":"25","author":"VT Vu","year":"2013","unstructured":"Vu VT, Cats G, Wolters L (2013) Graphics processing unit optimizations for the dynamics of the HIRLAM weather forecast model. Concurr Comput Pract Exp 25(10):1376\u20131393","journal-title":"Concurr Comput Pract Exp"},{"issue":"1","key":"1958_CR46","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1023\/A:1022804606389","volume":"25","author":"MA Wani","year":"2003","unstructured":"Wani MA, Arabnia HR (2003) Parallel edge-region-based segmentation algorithm targeted at reconfigurable multiring network. J Supercomput 25(1):43\u201362","journal-title":"J Supercomput"},{"issue":"1","key":"1958_CR47","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0021-9991(05)80016-6","volume":"102","author":"DL Williamson","year":"1992","unstructured":"Williamson DL, Drake JB, Hack JJ, Jakob R, Swarztrauber PN (1992) A standard test set for numerical approximations to the shallow water equations in spherical geometry. J Comput Phys 102(1):211\u2013224","journal-title":"J Comput Phys"},{"key":"1958_CR48","doi-asserted-by":"crossref","unstructured":"Xu S, Huang X, Zhang Y, Hu Y, Fu H, Yang G (2014) Porting the Princeton ocean model to GPUs. In: Algorithms and Architectures for Parallel Processing. Springer, pp 1\u201314","DOI":"10.1007\/978-3-319-11197-1_1"},{"key":"1958_CR49","doi-asserted-by":"crossref","unstructured":"Xue W, Yang C, Fu H, Wang X, Xu Y, Gan L, Lu Y, Zhu X (2014) Enabling and scaling a global shallow-water atmospheric model on Tianhe-2. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Proceeding Symposium (IPDPS\u201914), pp 745\u2013754","DOI":"10.1109\/IPDPS.2014.82"},{"key":"1958_CR50","doi-asserted-by":"crossref","unstructured":"Yang C, Xue W, Fu H, Gan L, Li L, Xu Y, Lu Y, Sun J, Yang G, Zheng W (2013) A Peta-scalable CPU-GPU Algorithm for Global Atmospheric Simulations. In: Proceedings of the 18th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP \u201913ACM, New York, pp 1\u201312","DOI":"10.1145\/2442516.2442518"},{"key":"1958_CR51","doi-asserted-by":"crossref","unstructured":"Zhang P, Ao Y, Yang C, Liu Y, Liu F, Wu C, Zhao H (2015) Pattern-driven hybrid multi-and many-core acceleration in the MPAS shallow-water model. In: 2015 44th International Conference on Parallel Processing (ICPP), IEEE, pp 71\u201380","DOI":"10.1109\/ICPP.2015.16"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-017-1958-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-1958-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-1958-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T15:03:20Z","timestamp":1568732600000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-017-1958-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,19]]},"references-count":51,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["1958"],"URL":"https:\/\/doi.org\/10.1007\/s11227-017-1958-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2017,1,19]]}}}