{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:50Z","timestamp":1740099050283,"version":"3.37.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319780238"},{"type":"electronic","value":"9783319780245"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-78024-5_21","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"232-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Comparison of Performance Tuning Process for Different Generations of\u00a0NVIDIA GPUs and an Example Scientific Computing Algorithm"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-1530","authenticated-orcid":false,"given":"Krzysztof","family":"Bana\u015b","sequence":"first","affiliation":[]},{"given":"Filip","family":"Kru\u017cel","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Biela\u0144ski","sequence":"additional","affiliation":[]},{"given":"Kazimierz","family":"Ch\u0142o\u0144","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"issue":"6","key":"21_CR1","doi-asserted-by":"crossref","first-page":"1319","DOI":"10.1016\/j.camwa.2014.01.021","volume":"67","author":"K Bana\u015b","year":"2014","unstructured":"Bana\u015b, K., P\u0142aszewski, P., Macio\u0142, P.: Numerical integration on GPUs for higher order finite elements. Comput. Math. Appl. 67(6), 1319\u20131344 (2014)","journal-title":"Comput. Math. Appl."},{"key":"21_CR2","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/j.cma.2016.03.038","volume":"305","author":"K Bana\u015b","year":"2016","unstructured":"Bana\u015b, K., Kru\u017cel, F., Biela\u0144ski, J.: Finite element numerical integration for first order approximations on multi- and many-core architectures. Comput. Methods Appl. Mech. Eng. 305, 827\u2013848 (2016)","journal-title":"Comput. Methods Appl. Mech. Eng."},{"issue":"5","key":"21_CR3","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1002\/nme.2989","volume":"85","author":"C Cecka","year":"2011","unstructured":"Cecka, C., Lew, A.J., Darve, E.: Assembly of finite element methods on graphics processors. Int. J. Numer. Methods Eng. 85(5), 640\u2013669 (2011)","journal-title":"Int. J. Numer. Methods Eng."},{"key":"21_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/978-3-642-28145-7_11","volume-title":"Applied Parallel and Scientific Computing","author":"A Davidson","year":"2012","unstructured":"Davidson, A., Owens, J.: Toward techniques for auto-tuning GPU algorithms. In: J\u00f3nasson, K. (ed.) PARA 2010. LNCS, vol. 7134, pp. 110\u2013119. Springer, Heidelberg (2012). \nhttps:\/\/doi.org\/10.1007\/978-3-642-28145-7_11"},{"issue":"2","key":"21_CR5","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1002\/nme.4452","volume":"94","author":"A Dziekonski","year":"2013","unstructured":"Dziekonski, A., Sypek, P., Lamecki, A., Mrozowski, M.: Generation of large finite-element matrices on multiple graphics processors. Int. J. Numer. Methods Eng. 94(2), 204\u2013220 (2013)","journal-title":"Int. J. Numer. Methods Eng."},{"key":"21_CR6","unstructured":"Group, K.O.W.: The OpenCL Specification, version 1.1 (2010). \nhttp:\/\/www.khronos.org\/registry\/cl\/specs\/opencl-1.1.pdf"},{"key":"21_CR7","volume-title":"Computer Architecture, Fifth Edition: A Quantitative Approach","author":"JL Hennessy","year":"2011","unstructured":"Hennessy, J.L., Patterson, D.A.: Computer Architecture, Fifth Edition: A Quantitative Approach, 5th edn. Morgan Kaufmann Publishers Inc., San Francisco (2011)","edition":"5"},{"key":"21_CR8","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/MM.2008.31","volume":"28","author":"E Lindholm","year":"2008","unstructured":"Lindholm, E., Nickolls, J., Oberman, S., Montrym, J.: NVIDIA Tesla: a unified graphics and computing architecture. IEEE Micro 28, 39\u201355 (2008)","journal-title":"IEEE Micro"},{"issue":"1","key":"21_CR9","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1002\/fld.3648","volume":"71","author":"GR Markall","year":"2013","unstructured":"Markall, G.R., Slemmer, A., Ham, D.A., Kelly, P.H.J., Cantwell, C.D., Sherwin, S.J.: Finite element assembly strategies on multi-core and many-core architectures. Int. J. Numer. Methods Fluids 71(1), 80\u201397 (2013)","journal-title":"Int. J. Numer. Methods Fluids"},{"key":"21_CR10","unstructured":"NVIDIA: NVIDIA CUDA C Programming Guide Version 5.0 (2012)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Whaley, R.C., Dongarra, J.J.: Automatically tuned linear algebra software. In: Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing, SC 1998, pp. 1\u201327. IEEE Computer Society, Washington (1998)","DOI":"10.1109\/SC.1998.10004"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78024-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:36:04Z","timestamp":1521707764000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}