{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T02:00:27Z","timestamp":1782439227688,"version":"3.54.5"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,4,1]],"date-time":"2013-04-01T00:00:00Z","timestamp":1364774400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput. Visual Sci."],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1007\/s00791-014-0223-x","type":"journal-article","created":{"date-parts":[[2014,9,18]],"date-time":"2014-09-18T05:57:42Z","timestamp":1411019862000},"page":"41-58","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Matrix-free GPU implementation of a preconditioned conjugate gradient solver for anisotropic elliptic PDEs"],"prefix":"10.1007","volume":"16","author":[{"given":"Eike","family":"M\u00fcller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Scheichl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinan","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2014,9,19]]},"reference":[{"key":"223_CR1","doi-asserted-by":"crossref","unstructured":"Ament, M., Knittel, G., Weiskopf, D., Strasser, W.: A parallel preconditioned conjugate gradient solver for the poisson problem on a multi-GPU platform. In: 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp. 583\u2013592 (2010)","DOI":"10.1109\/PDP.2010.51"},{"key":"223_CR2","doi-asserted-by":"crossref","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughputoriented processors. In: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, ACM, New York, NY, USA, SC \u201909, pp 18:1\u201318:11 (2009)","DOI":"10.1145\/1654059.1654078"},{"key":"223_CR3","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1145\/882262.882364","volume":"22","author":"J Bolz","year":"2003","unstructured":"Bolz, J., Farmer, I., Grinspun, E., Schr\u00f6der, P.: Sparse matrix solvers on the GPU: conjugate gradients and multigrid. ACM Trans. Graphics 22, 917\u2013924 (2003)","journal-title":"ACM Trans. Graphics"},{"key":"223_CR4","first-page":"200","volume":"26","author":"S B\u00f6rm","year":"1999","unstructured":"B\u00f6rm, S., Hiptmair, R.: Analysis of tensor product multigrid. Numer. Algorithms 26, 200\u2013201 (1999)","journal-title":"Numer. Algorithms"},{"key":"223_CR5","doi-asserted-by":"crossref","unstructured":"Brannick, J., Chen, Y., Hu, X., Zikatanov, L.: Parallel unsmoothed aggregation algebraic multigrid algorithms on GPUs. arXiv preprint arXiv:1302.2547 (2013)","DOI":"10.1007\/978-1-4614-7172-1_5"},{"key":"223_CR6","doi-asserted-by":"crossref","unstructured":"Briggs, W., Henson, V., McCormick, S.: A Multigrid Tutorial. Society for Industrial and Applied Mathematics (2000)","DOI":"10.1137\/1.9780898719505"},{"key":"223_CR7","doi-asserted-by":"crossref","unstructured":"Cantwell, C., Sherwin, S., Kirby, R., Kelly, P.: From h to p efficiently: strategy selection for operator evaluation on hexahedral and tetrahedral elements. Comput. Fluids 43(1):23\u201328, Symposium on High Accuracy Flow Simulations. Special Issue Dedicated to Prof. Michel Deville (2011)","DOI":"10.1016\/j.compfluid.2010.08.012"},{"key":"223_CR8","unstructured":"Carvalho, R., Martins, C., Batalha, R., Camargos, A.: 3D parallel conjugate gradient solver optimized for GPUs. In: 14th Biennial IEEE Conference on Electromagnetic Field Computation (CEFC), 2010 , p. 1 (2010)"},{"key":"223_CR9","doi-asserted-by":"crossref","unstructured":"Cevahir, A., Nukada, A., Matsuoka, S.: Fast conjugate gradients with multiple GPUs. In: Allen, Gabrielle and Nabrzyski, Jaros\u0142aw and Seidel, Edward and Albada, GeertDick and Dongarra, Jack and Sloot, Peter M.A (eds) Lecture Notes in Computer Science, vol 5544. Springer, Berlin (2009)","DOI":"10.1007\/978-3-642-01970-8_90"},{"issue":"2","key":"223_CR10","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/0377-0427(89)90045-9","volume":"25","author":"A Chronopoulos","year":"1989","unstructured":"Chronopoulos, A., Gear, C.: s-Step iterative methods for symmetric linear systems. J. Comput. Appl. Math. 25(2), 153\u2013168 (1989)","journal-title":"J. Comput. Appl. Math."},{"issue":"608","key":"223_CR11","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.1256\/qj.04.101","volume":"131","author":"T Davies","year":"2005","unstructured":"Davies, T., Cullen, M.J.P., Malcolm, A.J., Mawson, M.H., Staniforth, A., White, A.A., Wood, N.: A new dynamical core for the Met Office\u2019s global and regional modelling of the atmosphere. Q. J. R. Meteorol. Soc. 131(608), 1759\u20131782 (2005)","journal-title":"Q. J. R. Meteorol. Soc."},{"issue":"1","key":"223_CR12","first-page":"1:1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1:1\u20131:25 (2011)","journal-title":"ACM Trans. Math. Softw."},{"key":"223_CR13","unstructured":"de Jong, M.: Developing a CUDA solver for large sparse matrices for MARIN. Master\u2019s thesis, Delft Institute of Applied Mathematics (2012)"},{"issue":"8","key":"223_CR14","doi-asserted-by":"crossref","first-page":"2982","DOI":"10.1109\/TMAG.2010.2043511","volume":"46","author":"M Dehnavi","year":"2010","unstructured":"Dehnavi, M., Fern\u00e1ndez, D., Giannacopoulos, D.: Finite-element sparse matrix vector multiplication on graphic processing units. IEEE Trans. Magn. 46(8), 2982\u20132985 (2010)","journal-title":"IEEE Trans. Magn."},{"issue":"5","key":"223_CR15","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1109\/TMAG.2010.2081662","volume":"47","author":"M Dehnavi","year":"2011","unstructured":"Dehnavi, M., Fern\u00e1ndez, D., Giannacopoulos, D.: Enhancing the performance of conjugate gradient solvers on graphic processing units. IEEE Trans. Magn. 47(5), 1162\u20131165 (2011)","journal-title":"IEEE Trans. Magn."},{"key":"223_CR16","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.ocemod.2006.03.006","volume":"14","author":"OB Fringer","year":"2006","unstructured":"Fringer, O.B., Gerritsen, M.: An unstructured-grid, finite-volume, nonhydrostatic, parallel coastal ocean simulator. Ocean Model. 14, 139\u2013173 (2006)","journal-title":"Ocean Model."},{"issue":"10\u201312","key":"223_CR17","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1002\/fld.2462","volume":"64","author":"S Georgescu","year":"2010","unstructured":"Georgescu, S., Okuda, H.: Conjugate gradients on multiple GPUs. Int. J. Numer. Methods Fluids 64(10\u201312), 1254\u20131273 (2010)","journal-title":"Int. J. Numer. Methods Fluids"},{"key":"223_CR18","unstructured":"Geveler, M., Ribbrock, D., G\u00f6ddeke, D., Zajac, P., Turek, S.: Efficient Finite Element Geometric Multigrid Solvers for Unstructured Grids on GPUs. Techn. Univ., Fak. f\u00fcr Mathematik (2011)"},{"key":"223_CR19","doi-asserted-by":"crossref","unstructured":"Goodnight, N., Woolley, C., Lewin, G., Luebke, D., Humphreys, G.: A multigrid solver for boundary value problems using programmable graphics hardware. In: ACM SIGGRAPH 2005 Courses, ACM, New York, NY, USA, SIGGRAPH \u201905 (2005)","DOI":"10.1145\/1198555.1198784"},{"key":"223_CR20","unstructured":"Helfenstein, R., Koko, J.: Parallel preconditioned conjugate gradient algorithm on GPU. J. Comput. Appl. Math. 236(15):3584\u20133590, Proceedings of the Fifteenth International Congress on Computational and Applied Mathematics (ICCAM-2010), Leuven, Belgium, 5\u20139 July, 2010 (2012)"},{"issue":"6","key":"223_CR21","doi-asserted-by":"crossref","first-page":"409","DOI":"10.6028\/jres.049.044","volume":"49","author":"MR Hestenes","year":"1952","unstructured":"Hestenes, M.R., Stiefel, E.: Methods of conjugate gradients for solving linear systems. J. Res. Natl. Bur. Stand. 49(6), 409\u2013436 (1952)","journal-title":"J. Res. Natl. Bur. Stand."},{"key":"223_CR22","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.cam.2011.07.021","volume":"236","author":"H Knibbe","year":"2011","unstructured":"Knibbe, H., Oosterlee, C., Vuik, C.: GPU implementation of a Helmholtz Krylov solver preconditioned by a shifted Laplace multigrid method. J. Comput. Appl. Math. 236, 281\u2013293 (2011)","journal-title":"J. Comput. Appl. Math."},{"key":"223_CR23","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1175\/1520-0493(1971)099<0032:ASSFGP>2.3.CO;2","volume":"99","author":"M Kwizak","year":"1971","unstructured":"Kwizak, M., Robert, A.J.: A semi-implicit scheme for grid point atmospheric models of the primitive equations. Mon. Weather Rev. 99, 32 (1971)","journal-title":"Mon. Weather Rev."},{"issue":"3","key":"223_CR24","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1137\/S106482750240443X","volume":"25","author":"S Lacroix","year":"2003","unstructured":"Lacroix, S., Vassilevski, Y., Wheeler, J., Wheeler, M.: Iterative solution methods for modeling multiphase flow in porous media fully implicitly. SIAM J. Sci. Comput. 25(3), 905\u2013926 (2003)","journal-title":"SIAM J. Sci. Comput."},{"key":"223_CR25","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s11227-012-0825-3","volume":"63","author":"R Li","year":"2013","unstructured":"Li, R., Saad, Y.: GPU-accelerated preconditioned iterative linear solvers. J. Supercomput. 63, 443\u2013466 (2013)","journal-title":"J. Supercomput."},{"key":"223_CR26","doi-asserted-by":"crossref","unstructured":"Markall, G.R., Ham, D.A., Kelly, P.H.: Towards generating optimised finite element solvers for GPUs from high-level specifications. Procedia Comput. Sci. 1(1):1815\u20131823, iCCS 2010 (2010)","DOI":"10.1016\/j.procs.2010.04.203"},{"key":"223_CR27","doi-asserted-by":"crossref","first-page":"5753","DOI":"10.1029\/96JC02775","volume":"102","author":"J Marshall","year":"1997","unstructured":"Marshall, J., Adcroft, A., Hill, C., Perelman, L., Heisey, C.: A finite-volume, incompressible Navier Stokes model for studies of the ocean on parallel computers. J. Geophys. Res. 102, 5753\u20135766 (1997)","journal-title":"J. Geophys. Res."},{"issue":"648","key":"223_CR28","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1002\/qj.603","volume":"136","author":"T Melvin","year":"2010","unstructured":"Melvin, T., Dubal, M., Wood, N., Staniforth, A., Zerroukat, M.: An inherently mass-conserving iterative semi-implicit semi-Lagrangian discretization of the non-hydrostatic vertical-slice equations. Q. J. R. Meteorol. Soc. 136(648), 799\u2013814 (2010)","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"223_CR29","unstructured":"Menon, S., Perot, J.: Implementation of an efficient conjugate gradient algorithm for Poisson solutions on graphics processors. In: Proceedings of the 2007 Meeting of the Canadian CFD Society, Toronto Canada (2007)"},{"key":"223_CR30","unstructured":"Michels, D.: Sparse-matrix-cg-solver in cuda. In: Proceedings of the 15th Central European Seminar on Computer Graphics (2011)"},{"key":"223_CR31","doi-asserted-by":"crossref","unstructured":"M\u00fcller, E., Scheichl, R.: Massively parallel solvers for elliptic PDEs in numerical weather- and climate prediction. accepted for publication in Q. J. R. Meteorol. Soc. (2014)","DOI":"10.1002\/qj.2327"},{"key":"223_CR32","unstructured":"nVidia Corporation (2009) Fermi architecture whitepaper. http:\/\/www.nvidia.co.uk\/content\/PDF\/fermi_white_papers\/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf . Accessed 9 Feb 2013"},{"key":"223_CR33","unstructured":"nVidia Corporation (2012) CUDA programming guide. http:\/\/docs.nvidia.com\/cuda\/index.html . Accessed 9 Feb 2013"},{"key":"223_CR34","unstructured":"nVidia Corporation (2013) CuSPARSE Library. https:\/\/developer.nvidia.com\/cusparse"},{"key":"223_CR35","doi-asserted-by":"crossref","unstructured":"Piotrowski, Z.P., Wyszogrodzki, A.A., Smolarkiewicz, P.K.: Towards petascale simulation of atmospheric circulations with soundproof equations. Acta Geophys. 59(6), 1294\u20131311 (2011)","DOI":"10.2478\/s11600-011-0049-6"},{"key":"223_CR36","volume-title":"Numerical Recipes 3rd Edition: The Art of Scientific Computing","author":"WH Press","year":"2007","unstructured":"Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes 3rd Edition: The Art of Scientific Computing, 3rd edn. Cambridge University Press, New York, NY (2007)","edition":"3"},{"key":"223_CR37","unstructured":"Reguly, I., Giles, M.: Efficient sparse matrix-vector multiplication on cache-based GPUs. In: Innovative Parallel Computing (InPar), 2012, pp. 1\u201312 (2012)"},{"key":"223_CR38","doi-asserted-by":"crossref","unstructured":"Robert, A.: A stable numerical integration scheme for the primitive meteorological equations. Atmosphere-Ocean 19(1), 35\u201346 (1981)","DOI":"10.1080\/07055900.1981.9649098"},{"key":"223_CR39","doi-asserted-by":"crossref","unstructured":"Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. Society for Industrial and Applied Mathematics (2003)","DOI":"10.1137\/1.9780898718003"},{"issue":"4","key":"223_CR40","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1175\/1520-0493(1997)125<0587:PCRSFH>2.0.CO;2","volume":"125","author":"WC Skamarock","year":"1997","unstructured":"Skamarock, W.C., Smolarkiewicz, P.K., Klemp, J.B.: Preconditioned conjugate-residual solvers for Helmholtz equations in nonhydrostatic models. Mon. Weather Rev. 125(4), 587\u2013599 (1997)","journal-title":"Mon. Weather Rev."},{"key":"223_CR41","unstructured":"Smolarkiewicz, P.K., Margolin, L.G.: Variational solver for elliptic problems in atmospheric flows. Appl. Math. Comput. Sci. 4, 101\u2013125 (1994)"},{"issue":"1","key":"223_CR42","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1080\/07055900.1997.9687345","volume":"45","author":"PK Smolarkiewicz","year":"1997","unstructured":"Smolarkiewicz, P.K., Margolin, L.G.: On forward-in-time differencing in fluids: an Eulerian\/semi-Lagrangian nonhydrostatic model for stratified flows. Atmosphere-Ocean 45(1), 127\u2013152 (1997)","journal-title":"Atmosphere-Ocean"},{"key":"223_CR43","doi-asserted-by":"crossref","unstructured":"Thomas, S.J., Malevsky, A.V., Desgagne, M., Benoit, R., Pellerin, P., Valin, M.: Massively parallel implementation of the mesoscale compressible community model. Span pp. 1\u201319 (1997)","DOI":"10.1016\/S0167-8191(97)00105-1"},{"key":"223_CR44","doi-asserted-by":"crossref","DOI":"10.1007\/b137868","volume-title":"Domain Decomposition Methods: Algorithms and Theory, Springer Series in Computational Mathematics","author":"A Toselli","year":"2005","unstructured":"Toselli, A., Widlund, O.: Domain Decomposition Methods: Algorithms and Theory, Springer Series in Computational Mathematics. Springer, Berlin (2005)"},{"key":"223_CR45","unstructured":"Trottenberg, U., Oosterlee, C.W., Sch\u00fcller, A.: Multigrid. Academic Press, London (2001)"},{"issue":"10\u201311","key":"223_CR46","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.parco.2012.07.002","volume":"38","author":"M Verschoor","year":"2012","unstructured":"Verschoor, M., Jalba, A.C.: Analysis and performance estimation of the Conjugate Gradient method on multiple GPUs. Parallel. Comput. 38(10\u201311), 552\u2013575 (2012)","journal-title":"Parallel. Comput."},{"key":"223_CR47","unstructured":"Wood, N., Staniforth, A., White, A., Allen, T., Diamantakis, M., Gross, M., Melvin, T., Smith, C., Vosper, S., Zerroukat, M., Thuburn, J.: An inherently mass-conserving semi-implicit semi-Lagrangian discretisation of the deep-atmosphere global nonhydrostatic equations. Q. J. R. Meteorol. Soc. 140(682), 1505\u20131520 (2013)"},{"key":"223_CR48","unstructured":"Zhang Xianyi, Z.C., Wang, Q.: OpenBLAS. http:\/\/xianyi.github.com\/OpenBLAS\/ . Accessed 9 Feb 2013 (2012)"}],"container-title":["Computing and Visualization in Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00791-014-0223-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00791-014-0223-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00791-014-0223-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T17:12:21Z","timestamp":1717348341000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00791-014-0223-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,4]]}},"alternative-id":["223"],"URL":"https:\/\/doi.org\/10.1007\/s00791-014-0223-x","relation":{},"ISSN":["1432-9360","1433-0369"],"issn-type":[{"value":"1432-9360","type":"print"},{"value":"1433-0369","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4]]}}}