{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:18:05Z","timestamp":1758709085867},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,11,26]],"date-time":"2013-11-26T00:00:00Z","timestamp":1385424000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sci Comput"],"published-print":{"date-parts":[[2014,8]]},"DOI":"10.1007\/s10915-013-9805-x","type":"journal-article","created":{"date-parts":[[2013,11,25]],"date-time":"2013-11-25T03:27:02Z","timestamp":1385350022000},"page":"457-482","source":"Crossref","is-referenced-by-count":5,"title":["Exploiting Batch Processing on Streaming Architectures to Solve 2D Elliptic Finite Element Problems: A Hybridized Discontinuous Galerkin (HDG) Case Study"],"prefix":"10.1007","volume":"60","author":[{"given":"James","family":"King","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Yakovlev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert M.","family":"Kirby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spencer J.","family":"Sherwin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,26]]},"reference":[{"key":"9805_CR1","doi-asserted-by":"crossref","unstructured":"Buck, I.: GPU computing: programming a massively parallel processor. In: Proceedings of the International Symposium on Code Generation and Optimization, CGO \u201907, p. 17. IEEE Computer Society, Washington, DC, USA (2007)","DOI":"10.1109\/CGO.2007.13"},{"key":"9805_CR2","doi-asserted-by":"crossref","unstructured":"Bell, N., Yu, Y., Mucha, P.J.: Particle-based simulation of granular materials. In: Proceedings of the 2005 ACM SIGGRAPH\/Eurographics Symposium on Computer Animation, SCA \u201905, pp. 77\u201386. ACM, New York, NY, USA (2005)","DOI":"10.1145\/1073368.1073379"},{"issue":"5","key":"9805_CR3","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"JD Owens","year":"2008","unstructured":"Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., Phillips, J.C.: GPU computing. Proceedings of the IEEE 96(5), 879\u2013899 (2008)","journal-title":"Proceedings of the IEEE"},{"key":"9805_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-72067-8","volume-title":"Nodal Discontinuous Galerkin Methods: Algorithms, Analysis and Applications","author":"JS Hesthaven","year":"2008","unstructured":"Hesthaven, J.S., Warburton, T.: Nodal Discontinuous Galerkin Methods: Algorithms, Analysis and Applications. Springer, New York (2008)"},{"key":"9805_CR5","doi-asserted-by":"crossref","unstructured":"Ali, A., Syed, K.S., Ishaq, M., Hassan, A., Luo, Hong.: A communication-efficient, distributed memory parallel code using discontinuous Galerkin method for compressible flows. In: Emerging Technologies (ICET), 2010 6th International Conference on, pp. 331\u2013336, oct 2010","DOI":"10.1109\/ICET.2010.5638464"},{"key":"9805_CR6","doi-asserted-by":"crossref","unstructured":"Eskilsson, C., El-Khamra, Y., Rideout, D., Allen, G., Jim Chen Q., Tyagi, M.: A parallel High-Order Discontinuous Galerkin Shallow Water Model. In: Proceedings of the 9th International Conference on Computational Science: Part I, ICCS \u201909, pp. 63\u201372. Springer-Verlag, Berlin, Heidelberg (2009)","DOI":"10.1007\/978-3-642-01970-8_7"},{"issue":"8","key":"9805_CR7","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1109\/TMAG.2010.2043655","volume":"46","author":"N Goedel","year":"2010","unstructured":"Goedel, N., Schomann, S., Warburton, T., Clemens, M.: GPU accelerated Adams-Bashforth multirate discontinuous Galerkin FEM simulation of high-frequency electromagnetic fields. IEEE Trans. Magn. 46(8), 2735\u20132738 (2010)","journal-title":"IEEE Trans. Magn."},{"key":"9805_CR8","unstructured":"Goedel, N., Warburton, T., Clemens, M.: GPU accelerated Discontinuous Galerkin FEM for electromagnetic radio frequency problems. In: Antennas and Propagation Society International Symposium, 2009. APSURSI \u201909. IEEE, pp. 1\u20134, June 2009"},{"key":"9805_CR9","doi-asserted-by":"crossref","unstructured":"Kl\u00f6ckner, A., Warburton, T., Hesthaven, J.S.: High-Order Discontinuous Galerkin Methods by GPU Metaprogramming. In: GPU Solutions to Multi-scale Problems in Science and Engineering, pp. 353\u2013374. Springer (2013)","DOI":"10.1007\/978-3-642-16405-7_23"},{"key":"9805_CR10","doi-asserted-by":"crossref","unstructured":"Cockburn, B., Karniadakis, G.E., Shu, C.-W. (eds.): The Development of Discontinuous Galerkin Methods. In: Discontinuous Galerkin Methods: Theory, Computation and Applications, pp. 135\u2013146. Springer-Verlag, Berlin (2000)","DOI":"10.1007\/978-3-642-59721-3_1"},{"key":"9805_CR11","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1137\/070706616","volume":"47","author":"B Cockburn","year":"2009","unstructured":"Cockburn, B., Gopalakrishnan, J., Lazarov, R.: Unified hybridization of discontinuous Galerkin mixed and continuous Galerkin methods for second order elliptic problems. SIAM J. Numer. Anal. 47, 1319\u20131365 (2009)","journal-title":"SIAM J. Numer. Anal."},{"key":"9805_CR12","doi-asserted-by":"crossref","first-page":"7863","DOI":"10.1016\/j.jcp.2009.06.041","volume":"228","author":"A Kl\u00f6ckner","year":"2009","unstructured":"Kl\u00f6ckner, A., Warburton, T., Bridge, J., Hesthaven, J.S.: Nodal discontinuous Galerkin methods on graphics processors. J. Comput. Phys 228, 7863\u20137882 (2009)","journal-title":"J. Comput. Phys"},{"key":"9805_CR13","unstructured":"Lanteri, S., Perrussel, R.: An implicit hybridized discontinuous Galerkin method for time-domain Maxwell\u2019s equations. Rapport de recherche RR-7578, INRIA, March (2011)"},{"key":"9805_CR14","unstructured":"NVIDIA Corporation. CUDA Programming Guide 4.2, April 2012"},{"key":"9805_CR15","unstructured":"AMD Corporation. AMD Accelerated Parallel Processing Math Libraries, Jan 2011"},{"key":"9805_CR16","unstructured":"ATI. AMD Accelerated Parallel Processing OpenGL Programming Guide, Jan 2011"},{"key":"9805_CR17","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Proceedings of the 2008 ACM\/IEEE conference on Supercomputing, SC \u201908, pp. 31:1\u201331:11. IEEE Press, Piscataway, NJ, USA (2008)","DOI":"10.1109\/SC.2008.5214359"},{"key":"9805_CR18","unstructured":"Agullo, E., Augonnet, C., Dongarra, J., Ltaief, H., Namyst, R., Thibault, S., Tomov, S.: A Hybridization Methodology for High-Performance Linear Algebra Software for GPUs. In: GPU Computing Gems, Jade Edition 2, 473\u2013484 (2011)"},{"key":"9805_CR19","doi-asserted-by":"crossref","unstructured":"Song, F., Tomov, S., Dongarra, J.: Efficient Support for Matrix Computations on Heterogeneous Multi-core and Multi-GPU Architectures. University of Tennessee, Computer Science Technical, Report UT-CS-11-668 (2011)","DOI":"10.2172\/1173287"},{"key":"9805_CR20","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780198528692.001.0001","volume-title":"Spectral\/HP Element Methods for CFD","author":"GE Karniadakis","year":"2005","unstructured":"Karniadakis, G.E., Sherwin, S.J.: Spectral\/HP Element Methods for CFD, 2nd edn. Oxford University Press, UK (2005)","edition":"2"},{"key":"9805_CR21","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/0045-7825(94)00745-9","volume":"123","author":"SJ Sherwin","year":"1995","unstructured":"Sherwin, S.J., Karniadakis, G.E.: A triangular spectral element method. Applications to the incompressible Navier\u2013Stokes equations. Comput. Methods Appl. Mech. Eng. 123, 189\u2013229 (1995)","journal-title":"Comput. Methods Appl. Mech. Eng."},{"issue":"264","key":"9805_CR22","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1090\/S0025-5718-08-02123-6","volume":"77","author":"B Cockburn","year":"2007","unstructured":"Cockburn, B., Dong, B., Guzm\u00e1n, J.: A superconvergent LDG-Hybridizable Galerkin method for second-order elliptic problems. Math. Comput. 77(264), 1887\u20131916 (2007)","journal-title":"Math. Comput."},{"key":"9805_CR23","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1090\/S0025-5718-10-02334-3","volume":"79","author":"B Cockburn","year":"2010","unstructured":"Cockburn, B., Gopalakrishnan, J., Sayas, F.-J.: A projection-based error analysis of HDG methods. Math. Comput. 79, 1351\u20131367 (2010)","journal-title":"Math. Comput."},{"key":"9805_CR24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1090\/S0025-5718-08-02146-7","volume":"78","author":"B Cockburn","year":"2009","unstructured":"Cockburn, B., Guzm\u00e1n, J., Wang, H.: Superconvergent discontinuous Galerkin methods for second-order elliptic problems. Math. Comput. 78, 1\u201324 (2009)","journal-title":"Math. Comput."},{"key":"9805_CR25","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1137\/S0036142901384162","volume":"39","author":"DN Arnold","year":"2002","unstructured":"Arnold, D.N., Brezzi, F., Cockburn, B., Marini, D.: Unified analysis of discontinuous Galerkin methods for elliptic problems. SIAM J. Numer. Anal. 39, 1749\u20131779 (2002)","journal-title":"SIAM J. Numer. Anal."},{"key":"9805_CR26","doi-asserted-by":"crossref","unstructured":"Kirby, Robert M., Sherwin, Spencer J., Cockburn, Bernardo: To CG or to HDG: a comparative study. J. Sci. Comput. 51(1), 183\u2013212 (Apr 2012)","DOI":"10.1007\/s10915-011-9501-7"},{"key":"9805_CR27","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/BF01060030","volume":"6","author":"M Dubiner","year":"1991","unstructured":"Dubiner, M.: Spectral methods on triangles and other domains. J. Sci. Comput. 6, 345\u2013390 (1991)","journal-title":"J. Sci. Comput."},{"key":"9805_CR28","unstructured":"Bell, N., Garland, M.: Efficient Sparse Matrix-Vector Multiplication on CUDA. NVIDIA Technical Report NVR-2008-004, NVIDIA Corporation, Dec 2008"},{"key":"9805_CR29","unstructured":"Vos P.E.J.: From h to p efficiently : optimising the implementation of spectral \/ hp element methods. PhD thesis, University of London, 2011"},{"issue":"1","key":"9805_CR30","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1504\/IJCSE.2008.021111","volume":"4","author":"Dominik G\u00f6ddeke","year":"2008","unstructured":"G\u00f6ddeke, Dominik, Strzodka, Robert, Mohd-Yusof, Jamaludin, McCormick, Patrick S., Wobker, Hilmar, Becker, Christian, Turek, Stefan: Using GPUs to improve multigrid solver performance on a cluster. Int. J. Comput. Sci. Eng. 4(1), 36\u201355 (2008)","journal-title":"Int. J. Comput. Sci. Eng."},{"issue":"4","key":"9805_CR31","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1504\/IJCSE.2009.029162","volume":"4","author":"Dominik G\u00f6ddeke","year":"2009","unstructured":"G\u00f6ddeke, Dominik, Wobker, Hilmar, Strzodka, Robert, Mohd-Yusof, Jamaludin, McCormick, Patrick S., Turek, Stefan: Co-processor acceleration of an unmodified parallel solid mechanics code with FEASTGPU. Int. J. Comput. Sci. Eng. 4(4), 254\u2013269 (2009)","journal-title":"Int. J. Comput. Sci. Eng."},{"key":"9805_CR32","unstructured":"Kirby, R.M., Sherwin, S.J.: Nektar++ finite element library. http:\/\/www.nektar.info\/"},{"key":"9805_CR33","unstructured":"Bell, N., Garland, M.: Cusp: Generic Parallel Algorithms for Sparse Matrix and Graph Computations, 2012. Version 0.3.0"},{"key":"9805_CR34","unstructured":"Hoberock, J., Bell, N.: Thrust: A Parallel Template Library, 2010. Version 1.7.0"},{"key":"9805_CR35","unstructured":"Ha, L.K., King, J., Fu, Z., Kirby, R.M.: A High-Performance Multi-Element Processing Framework on GPUs. SCI Technical Report UUSCI-2013-005, SCI Institute, University of Utah (2013)"},{"key":"9805_CR36","doi-asserted-by":"crossref","unstructured":"Roca, X., Nguyen N.C., Peraire, J.: GPU-accelerated sparse matrix-vector product for a hybridizable discontinuous Galerkin method. Aerospace Sciences Meetings. American Institute of Aeronautics and Astronautics, Jan 2011. doi: 10.2514\/6.2011-687","DOI":"10.2514\/6.2011-687"}],"container-title":["Journal of Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-013-9805-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10915-013-9805-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-013-9805-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,4]],"date-time":"2019-08-04T01:19:02Z","timestamp":1564881542000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10915-013-9805-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,26]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,8]]}},"alternative-id":["9805"],"URL":"https:\/\/doi.org\/10.1007\/s10915-013-9805-x","relation":{},"ISSN":["0885-7474","1573-7691"],"issn-type":[{"value":"0885-7474","type":"print"},{"value":"1573-7691","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,26]]}}}