{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T12:05:31Z","timestamp":1710590731084},"reference-count":67,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2014,4,1]],"date-time":"2014-04-01T00:00:00Z","timestamp":1396310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2018,4,16]],"date-time":"2018-04-16T00:00:00Z","timestamp":1523836800000},"content-version":"vor","delay-in-days":1476,"URL":"https:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100004281","name":"Polish National Science Centre","doi-asserted-by":"crossref","award":["DEC-2011\/01\/B\/ST6\/00674"],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Mathematics with Applications"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1016\/j.camwa.2014.01.021","type":"journal-article","created":{"date-parts":[[2014,2,17]],"date-time":"2014-02-17T14:23:22Z","timestamp":1392647002000},"page":"1319-1344","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":26,"title":["Numerical integration on GPUs for higher order finite elements"],"prefix":"10.1016","volume":"67","author":[{"given":"Krzysztof","family":"Bana\u015b","sequence":"first","affiliation":[]},{"given":"Przemys\u0142aw","family":"P\u0142aszewski","sequence":"additional","affiliation":[]},{"given":"Pawe\u0142","family":"Macio\u0142","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.camwa.2014.01.021_br000005","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1016\/j.simpat.2005.08.001","article-title":"Scientific computation for simulations on programmable graphics hardware","volume":"13","author":"Strzodka","year":"2005","journal-title":"Simulat. Model. Practice Theory"},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000010","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","article-title":"A survey of general-purpose computation on graphics hardware","volume":"26","author":"Owens","year":"2007","journal-title":"Comput. Graph. Forum"},{"issue":"3\u20134","key":"10.1016\/j.camwa.2014.01.021_br000015","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1002\/cav.24","article-title":"A hybrid condensed finite element model with GPU acceleration for interactive 3D soft tissue cutting","volume":"15","author":"Wu","year":"2004","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"5","key":"10.1016\/j.camwa.2014.01.021_br000020","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/j.jpdc.2009.01.006","article-title":"Porting a high-order finite-element earthquake modeling application to NVIDIA graphics cards using CUDA","volume":"69","author":"Komatitsch","year":"2009","journal-title":"J. Parallel Distrib. Comput."},{"key":"10.1016\/j.camwa.2014.01.021_br000025","doi-asserted-by":"crossref","first-page":"7863","DOI":"10.1016\/j.jcp.2009.06.041","article-title":"Nodal discontinuous Galerkin methods on graphics processors","volume":"228","author":"Kl\u00f6ckner","year":"2009","journal-title":"J. Comput. Phys."},{"issue":"4\u20135","key":"10.1016\/j.camwa.2014.01.021_br000030","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1002\/nme.1620020104","article-title":"A frontal solution scheme for finite element analysis","volume":"2","author":"Irons","year":"1970","journal-title":"Internat. J. Numer. Methods Engrg."},{"issue":"3","key":"10.1016\/j.camwa.2014.01.021_br000035","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1145\/356044.356047","article-title":"The multifrontal solution of indefinite sparse symmetric linear","volume":"9","author":"Duff","year":"1983","journal-title":"ACM Trans. Math. Softw."},{"key":"10.1016\/j.camwa.2014.01.021_br000040","first-page":"1788","article-title":"Out-of-core multi-frontal solver for multi-physics hp adaptive problems","volume":"4","author":"Paszynski","year":"2011","journal-title":"Procedia CS"},{"key":"10.1016\/j.camwa.2014.01.021_br000045","series-title":"Parallel Newton-Krylov-Schwarz Algorithms for the Transonic Full Potential Equation, Report TR 96-39, ICASE","author":"Cai","year":"1996"},{"key":"10.1016\/j.camwa.2014.01.021_br000050","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/0045-7825(91)90009-U","article-title":"A globally convergent matrix-free algorithm for implicit time-marching schemes arising in finite element analysis in fluids","volume":"87","author":"Johan","year":"1991","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.camwa.2014.01.021_br000055","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1002\/cnm.495","article-title":"A Newton\u2013Krylov solver with multiplicative Schwarz preconditioning for finite element compressible flow simulations","volume":"18","author":"Bana\u015b","year":"2002","journal-title":"Commun. Numer. Methods Eng."},{"issue":"4","key":"10.1016\/j.camwa.2014.01.021_br000060","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1504\/IJCSE.2009.029162","article-title":"Co-processor acceleration of an unmodified parallel solid mechanics code with FEASTGPU","volume":"4","author":"G\u00f6ddeke","year":"2009","journal-title":"Internat. J. Comput. Sci. Eng."},{"issue":"10\u201311","key":"10.1016\/j.camwa.2014.01.021_br000065","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.parco.2007.09.002","article-title":"Exploring weak scalability for FEM calculations on a GPU-enhanced cluster","volume":"33","author":"G\u00f6ddeke","year":"2007","journal-title":"Parallel Comput."},{"key":"10.1016\/j.camwa.2014.01.021_br000070","series-title":"Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, SC\u201908","first-page":"31:1","article-title":"Benchmarking GPUs to tune dense linear algebra","author":"Volkov","year":"2008"},{"key":"10.1016\/j.camwa.2014.01.021_br000075","doi-asserted-by":"crossref","unstructured":"N. Fujimoto, Faster matrix\u2013vector multiplication on GeForce 8800GTX, in: Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, IPDPS, April 2008, pp. 1\u20138.","DOI":"10.1109\/IPDPS.2008.4536350"},{"issue":"4","key":"10.1016\/j.camwa.2014.01.021_br000080","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/BF01060030","article-title":"Spectral methods on triangles and other domains","volume":"6","author":"Dubiner","year":"1991","journal-title":"J. Sci. Comput."},{"key":"10.1016\/j.camwa.2014.01.021_br000085","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1006\/jcph.1996.0042","article-title":"Tetrahedral hp finite elements: algorithms and flow simulations","volume":"124","author":"Sherwin","year":"1996","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.camwa.2014.01.021_br000090","doi-asserted-by":"crossref","first-page":"4339","DOI":"10.1016\/S0045-7825(00)00322-4","article-title":"Fully discrete hp-finite elements I: fast quadrature","volume":"190","author":"Melenk","year":"2001","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.camwa.2014.01.021_br000095","series-title":"Computing with hp-Adaptive Finite Elements","volume":"vol. 2","author":"Demkowicz","year":"2007"},{"key":"10.1016\/j.camwa.2014.01.021_br000100","doi-asserted-by":"crossref","first-page":"5161","DOI":"10.1016\/j.jcp.2010.03.031","article-title":"From h to p efficiently: implementing finite and spectral\/hp element methods to achieve optimal performance for low- and high-order discretisations","volume":"229","author":"Vos","year":"2010","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.camwa.2014.01.021_br000105","unstructured":"F.J. Filipovic, I. Peterlik, GPU acceleration of equations assembly in finite elements method \u2014 preliminary results, in: SAAHPC : Symposium on Application Accelerators in HPC, 2009."},{"key":"10.1016\/j.camwa.2014.01.021_br000110","doi-asserted-by":"crossref","first-page":"249","DOI":"10.2528\/PIER12040301","article-title":"Finite element matrix generation on a GPU","volume":"128","author":"Dziekonski","year":"2012","journal-title":"Prog. Electromagn. Res."},{"issue":"3","key":"10.1016\/j.camwa.2014.01.021_br000115","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1137\/040607824","article-title":"Optimizing the evaluation of finite element matrices","volume":"27","author":"Kirby","year":"2005","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"10.1016\/j.camwa.2014.01.021_br000120","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1145\/1163641.1163644","article-title":"A compiler for variational forms","volume":"32","author":"Kirby","year":"2006","journal-title":"ACM Trans. Math. Software"},{"issue":"2","key":"10.1016\/j.camwa.2014.01.021_br000125","doi-asserted-by":"crossref","first-page":"20:1","DOI":"10.1145\/1731022.1731030","article-title":"Dolfin: automated finite element computing","volume":"37","author":"Logg","year":"2010","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.camwa.2014.01.021_br000130","series-title":"Automated Solution of Differential Equations by the Finite Element Method","author":"Logg","year":"2012"},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000135","doi-asserted-by":"crossref","first-page":"1815","DOI":"10.1016\/j.procs.2010.04.203","article-title":"Towards generating optimised finite element solvers for GPUs from high-level specifications","volume":"1","author":"Markall","year":"2010","journal-title":"Procedia Comput. Sci."},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000140","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1002\/fld.3648","article-title":"Finite element assembly strategies on multi-core and many-core architectures","volume":"71","author":"Markall","year":"2013","journal-title":"Internat. J. Numer. Methods Fluids"},{"issue":"2","key":"10.1016\/j.camwa.2014.01.021_br000145","doi-asserted-by":"crossref","first-page":"10:1","DOI":"10.1145\/2427023.2427027","article-title":"Finite element integration on GPUs","volume":"39","author":"Knepley","year":"2013","journal-title":"ACM Trans. Math. Software"},{"key":"10.1016\/j.camwa.2014.01.021_br000150","unstructured":"S. Rul, H. Vandierendonck, J. D\u2019Haene, K. De Bosschere, An experimental study on performance portability of OpenCL kernels, in: Application Accelerators in High Performance Computing, 2010 Symposium, Papers, Knoxville, TN, USA, 2010, p. 3."},{"issue":"5","key":"10.1016\/j.camwa.2014.01.021_br000155","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1002\/nme.2989","article-title":"Assembly of finite element methods on graphics processors","volume":"85","author":"Cecka","year":"2011","journal-title":"International Journal for Numerical Methods in Engineering"},{"key":"10.1016\/j.camwa.2014.01.021_br000160","series-title":"GPU Computing Gems","first-page":"187","article-title":"Application of assembly of finite element methods on graphics processors for real-time elastodynamics","author":"Cecka","year":"2011"},{"key":"10.1016\/j.camwa.2014.01.021_br000165","series-title":"Numerical Solution of Partial Differential Equations on Parallel Computers","first-page":"89","article-title":"Graphics processor units: new prospects for parallel computing","volume":"vol. 51","author":"Rumpf","year":"2005"},{"issue":"7","key":"10.1016\/j.camwa.2014.01.021_br000170","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1002\/nme.2101","article-title":"A scalable multilevel preconditioner for matrix-free \u03bc-finite element analysis of human bone structures","volume":"73","author":"Arbenz","year":"2008","journal-title":"Internat. J. Numer. Methods Engrg."},{"key":"10.1016\/j.camwa.2014.01.021_br000175","first-page":"1","article-title":"Finite element algorithms and data structures on graphical processing units","author":"Reguly","year":"2013","journal-title":"Int. J. Parallel Program."},{"key":"10.1016\/j.camwa.2014.01.021_br000180","unstructured":"P. P\u0142aszewski, K. Bana\u015b, Performance analysis of iterative solvers of linear equations for hp-adaptive finite element method, Procedia CS."},{"key":"10.1016\/j.camwa.2014.01.021_br000185","article-title":"Generation of large finite-element matrices on multiple graphics processors","author":"Dziekonski","year":"2012","journal-title":"Internat. J. Numer. Methods Engrg."},{"issue":"4","key":"10.1016\/j.camwa.2014.01.021_br000190","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1080\/17445760601122076","article-title":"Performance and accuracy of hardware-oriented native-, emulated- and mixed-precision solvers in FEM simulations","volume":"22","author":"G\u00f6ddeke","year":"2007","journal-title":"Int. J. Parallel Emergent Distrib. Syst."},{"issue":"12","key":"10.1016\/j.camwa.2014.01.021_br000195","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1016\/j.cpc.2008.11.005","article-title":"Accelerating scientific computations with mixed precision algorithms","volume":"180","author":"Baboulin","year":"2009","journal-title":"Comput. Phys. Comm."},{"issue":"20","key":"10.1016\/j.camwa.2014.01.021_br000200","doi-asserted-by":"crossref","first-page":"7692","DOI":"10.1016\/j.jcp.2010.06.024","article-title":"High-order finite-element seismic wave propagation modeling with MPI on a large GPU cluster","volume":"229","author":"Komatitsch","year":"2010","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.camwa.2014.01.021_br000205","series-title":"The Finite Element Method for Elliptic Problems","author":"Ciarlet","year":"1978"},{"key":"10.1016\/j.camwa.2014.01.021_br000210","series-title":"One And Two Dimensional Elliptic And Maxwell Problems","volume":"vol. 1","author":"Demkowicz","year":"2006"},{"key":"10.1016\/j.camwa.2014.01.021_br000215","doi-asserted-by":"crossref","unstructured":"P. P\u0142aszewski, K. Bana\u015b, P. Macio\u0142, Higher order FEM numerical integration on GPUs with OpenCL, in: IMCSIT, 2010, pp. 337\u2013342.","DOI":"10.1109\/IMCSIT.2010.5679646"},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000220","first-page":"3","article-title":"ModFEM \u2014 a computational framework for parallel adaptive finite element simulations","volume":"13","author":"Michalik","year":"2013","journal-title":"Comput. Methods Mater. Sci."},{"key":"10.1016\/j.camwa.2014.01.021_br000225","series-title":"Computational Science \u2014 ICCS 2004, 4th International Conference, Krak\u00f3w, Poland, June 2004, Proceedings, Part II","first-page":"155","article-title":"A modular design for parallel adaptive finite element computational kernels","volume":"vol. 3037","author":"Bana\u015b","year":"2004"},{"key":"10.1016\/j.camwa.2014.01.021_br000230","series-title":"Domain Decomposition Methods in Science and Engineering","first-page":"159","article-title":"A model for parallel adaptive finite element software","volume":"vol. 40","author":"Bana\u015b","year":"2004"},{"key":"10.1016\/j.camwa.2014.01.021_br000235","series-title":"Computational Science \u2014 ICCS 2006, 6th International Conference, Reading, UK, May 28\u201331, 2006, Proceedings, Part III","first-page":"743","article-title":"Agent architecture for mesh based simulation systems","volume":"vol. 3993","author":"Bana\u015b","year":"2006"},{"key":"10.1016\/j.camwa.2014.01.021_br000240","series-title":"Parallel Processing and Applied Mathematics, Proceedings of Vth International Conference, PPAM 2003, Cz\u0229stochowa, Poland, 2003","first-page":"431","article-title":"Parallelization of large scale adaptive finite element computations","volume":"vol. 3019","author":"Bana\u015b","year":"2004"},{"key":"10.1016\/j.camwa.2014.01.021_br000245","series-title":"PPAM\u201909: Proceedings of the 8th International Conference on Parallel Processing and Applied Mathematics","first-page":"517","article-title":"Finite element numerical integration on PowerXCell processors","author":"Kru zel","year":"2010"},{"key":"10.1016\/j.camwa.2014.01.021_br000250","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s00791-004-0145-0","article-title":"On a modular architecture for finite element systems. I. Sequential codes","volume":"8","author":"Bana\u015b","year":"2005","journal-title":"Comput. Vis. Sci."},{"key":"10.1016\/j.camwa.2014.01.021_br000255","first-page":"43","article-title":"Architecture of iterative solvers for hp-adaptive finite element codes","volume":"20","author":"P\u0142aszewski","year":"2013","journal-title":"Comput. Assis. Methods Eng. Sci."},{"key":"10.1016\/j.camwa.2014.01.021_br000260","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1006\/jcph.1996.0129","article-title":"Entropy controlled adaptive finite element simulations for compressible gas flow","volume":"126","author":"Bana\u015b","year":"1996","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.camwa.2014.01.021_br000265","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1023\/A:1011546411957","article-title":"Discontinuous Galerkin method applied to a single phase flow in porous media","volume":"4","author":"Rivi\u00e8re","year":"2000","journal-title":"Comput. Geosci."},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000270","first-page":"181","article-title":"Modeling of Inconel 625 TIG welding process","volume":"13","author":"Siwek","year":"2013","journal-title":"Comput. Methods Mater. Sci."},{"key":"10.1016\/j.camwa.2014.01.021_br000275","series-title":"PPAM\u201909: Proceedings of the 8th International Conference on Parallel Processing and Applied Mathematics","first-page":"411","article-title":"Finite element numerical integration on GPUs","author":"P\u0142aszewski","year":"2010"},{"issue":"1","key":"10.1016\/j.camwa.2014.01.021_br000280","first-page":"1093","article-title":"3D finite element numerical integration on GPUs","volume":"1","author":"Macio\u0142","year":"2010","journal-title":"Procedia CS"},{"issue":"10","key":"10.1016\/j.camwa.2014.01.021_br000285","doi-asserted-by":"crossref","first-page":"2030","DOI":"10.1016\/j.camwa.2013.08.026","article-title":"Vectorized OpenCL implementation of numerical integration for higher order finite elements","volume":"66","author":"Kru\u017cel","year":"2013","journal-title":"Comput. Math. Appl."},{"key":"10.1016\/j.camwa.2014.01.021_br000290","article-title":"Higher-order finite element methods","volume":"vol. 1","author":"\u0160ol\u00edn","year":"2004"},{"key":"10.1016\/j.camwa.2014.01.021_br000295","series-title":"Isogeometric Analysis: Toward Integration of CAD and FEA","author":"Cottrell","year":"2009"},{"key":"10.1016\/j.camwa.2014.01.021_br000300","unstructured":"NVIDIA, NVIDIA CUDA C Programming Guide Version 5.0, 2012."},{"key":"10.1016\/j.camwa.2014.01.021_br000305","unstructured":"K.O.W. Group, The OpenCL Specification, version 1.1, 2010."},{"key":"10.1016\/j.camwa.2014.01.021_br000310","series-title":"Heterogeneous Computing With OpenCL","author":"Gaster","year":"2011"},{"key":"10.1016\/j.camwa.2014.01.021_br000315","unstructured":"AMD, AMD Accelerated Parallel Processing. OpenCL Programming Guide, 2012."},{"key":"10.1016\/j.camwa.2014.01.021_br000320","series-title":"IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2010, 28\u201330 March 2010, White Plains, NY, USA","first-page":"235","article-title":"Demystifying gpu microarchitecture through microbenchmarking","author":"Wong","year":"2010"},{"key":"10.1016\/j.camwa.2014.01.021_br000325","doi-asserted-by":"crossref","unstructured":"M. Harris, Optimizing CUDA, SC07, High Performance Computing on GPUs with CUDA presentation, 2007.","DOI":"10.1145\/1281500.1281650"},{"key":"10.1016\/j.camwa.2014.01.021_br000330","series-title":"Using OpenMP: Portable Shared Memory Parallel Programming (Scientific and Engineering Computation)","author":"Chapman","year":"2007"},{"key":"10.1016\/j.camwa.2014.01.021_br000335","series-title":"NVIDIA\u2019s Next Generation CUDA Compute Architecture: Fermi, Tech. Rep.","year":"2009"}],"container-title":["Computers & Mathematics with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0898122114000455?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0898122114000455?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,5,11]],"date-time":"2020-05-11T19:55:34Z","timestamp":1589226934000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0898122114000455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4]]},"references-count":67,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["S0898122114000455"],"URL":"https:\/\/doi.org\/10.1016\/j.camwa.2014.01.021","relation":{},"ISSN":["0898-1221"],"issn-type":[{"value":"0898-1221","type":"print"}],"subject":[],"published":{"date-parts":[[2014,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Numerical integration on GPUs for higher order finite elements","name":"articletitle","label":"Article Title"},{"value":"Computers & Mathematics with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.camwa.2014.01.021","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2014 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}