{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:45:48Z","timestamp":1775231148338,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,3,3]],"date-time":"2012-03-03T00:00:00Z","timestamp":1330732800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["926688"],"award-info":[{"award-number":["926688"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DOE award DE-SC0002434"],"award-info":[{"award-number":["DOE award DE-SC0002434"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,3,3]]},"DOI":"10.1145\/2159430.2159436","type":"proceedings-article","created":{"date-parts":[[2012,3,6]],"date-time":"2012-03-06T13:18:26Z","timestamp":1331039906000},"page":"47-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["High-performance sparse matrix-vector multiplication on GPUs for structured grid computations"],"prefix":"10.1145","author":[{"given":"Jeswin","family":"Godwin","sequence":"first","affiliation":[{"name":"The Ohio State University, Columbus, OH"}]},{"given":"Justin","family":"Holewinski","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH"}]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, OH"}]}],"member":"320","published-online":{"date-parts":[[2012,3,3]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0376-0421(00)00005-1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_6_1","volume-title":"Cusp: Generic parallel algorithms for sparse matrix and graph computations","author":"Bell N.","year":"2010","unstructured":"Bell , N. , and Garland , M . Cusp: Generic parallel algorithms for sparse matrix and graph computations , 2010 . Version 0.1.0. Bell, N., and Garland, M. Cusp: Generic parallel algorithms for sparse matrix and graph computations, 2010. Version 0.1.0."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882364"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1693453.1693471"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11428831_13"},{"key":"e_1_3_2_1_10_1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-3-540-39737-3_25","volume-title":"Computer and Information Sciences - ISCIS","author":"Ekambaram A.","year":"2003","unstructured":"Ekambaram , A. , and Montagne , E . An alternative compressed storage format for sparse matrices . In Computer and Information Sciences - ISCIS 2003 , A. Yazici and C. Sener, Eds ., vol. 2869 of Lecture Notes in Computer Science . Springer Berlin\/Heidelberg , 2003, pp. 196 -- 203 . 10.1007\/978-3-540-39737-3_25. Ekambaram, A., and Montagne, E. An alternative compressed storage format for sparse matrices. In Computer and Information Sciences - ISCIS 2003, A. Yazici and C. Sener, Eds., vol. 2869 of Lecture Notes in Computer Science. Springer Berlin\/Heidelberg, 2003, pp. 196--203. 10.1007\/978-3-540-39737-3_25."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1391469.1391473"},{"key":"e_1_3_2_1_12_1","volume-title":"Efficient finite element geometric multigrid solvers for unstructured grids on GPUs. PARENG (April","author":"Geveler M.","year":"2011","unstructured":"Geveler , M. , Ribbrock , D. , G\u00f6ddeke , D. , Peter , Z. , and Stefan , T . Efficient finite element geometric multigrid solvers for unstructured grids on GPUs. PARENG (April 2011 ). Geveler, M., Ribbrock, D., G\u00f6ddeke, D., Peter, Z., and Stefan, T. Efficient finite element geometric multigrid solvers for unstructured grids on GPUs. PARENG (April 2011)."},{"key":"e_1_3_2_1_13_1","volume-title":"Towards a complete FEM-based simulation toolkit on GPUs: Geometric multigrid solvers. ParCFD (May","author":"Geveler M.","year":"2011","unstructured":"Geveler , M. , Ribbrock , D. , G\u00f6ddeke , D. , Peter , Z. , and Stefan , T . Towards a complete FEM-based simulation toolkit on GPUs: Geometric multigrid solvers. ParCFD (May 2011 ). Geveler, M., Ribbrock, D., G\u00f6ddeke, D., Peter, Z., and Stefan, T. Towards a complete FEM-based simulation toolkit on GPUs: Geometric multigrid solvers. ParCFD (May 2011)."},{"key":"e_1_3_2_1_14_1","series-title":"Lecture Notes in Computer Science (Berlin","volume-title":"Vector and Parallel Processing -- VECPAR'2002, 5th International Conference","author":"Goodale T.","year":"2003","unstructured":"Goodale , T. , Allen , G. , Lanfermann , G. , Mass\u00f3 , J. , Radke , T. , Seidel , E. , and Shalf , J . The Cactus framework and toolkit: Design and applications . In Vector and Parallel Processing -- VECPAR'2002, 5th International Conference , Lecture Notes in Computer Science (Berlin , 2003 ), Springer . Goodale, T., Allen, G., Lanfermann, G., Mass\u00f3, J., Radke, T., Seidel, E., and Shalf, J. The Cactus framework and toolkit: Design and applications. In Vector and Parallel Processing -- VECPAR'2002, 5th International Conference, Lecture Notes in Computer Science (Berlin, 2003), Springer."},{"key":"e_1_3_2_1_15_1","volume-title":"August","author":"Grimes R.","year":"1979","unstructured":"Grimes , R. , Kincaid , D. , and Young , D . ITPACK 2.0 user's guide , August 1979 . Grimes, R., Kincaid, D., and Young, D. ITPACK 2.0 user's guide, August 1979."},{"key":"e_1_3_2_1_16_1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/3-540-45545-0_22","volume-title":"Computational Science - ICCS","author":"Im E.-J.","year":"2001","unstructured":"Im , E.-J. , and Yelick , K . Optimizing sparse matrix computations for register reuse in sparsity . In Computational Science - ICCS 2001 , V. Alexandrov, J. Dongarra, B. Juliano, R. Renner, and C. Tan, Eds., vol. 2073 of Lecture Notes in Computer Science . Springer Berlin\/Heidelberg , 2001, pp. 127 -- 136 . 10.1007\/3-540-45545-0_22. Im, E.-J., and Yelick, K. Optimizing sparse matrix computations for register reuse in sparsity. In Computational Science - ICCS 2001, V. Alexandrov, J. Dongarra, B. Juliano, R. Renner, and C. Tan, Eds., vol. 2073 of Lecture Notes in Computer Science. Springer Berlin\/Heidelberg, 2001, pp. 127--136. 10.1007\/3-540-45545-0_22."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041296"},{"key":"e_1_3_2_1_18_1","unstructured":"Khronos OpenCL Working Group. The OpenCL specification - version 1.2.  Khronos OpenCL Working Group. The OpenCL specification - version 1.2."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1198555.1198795"},{"key":"e_1_3_2_1_20_1","unstructured":"Los Alamos National Laboratory. PFLOTRAN. http:\/\/ees.lanl.gov\/source\/orgs\/ees\/pflotran\/index.shtml.  Los Alamos National Laboratory. PFLOTRAN. http:\/\/ees.lanl.gov\/source\/orgs\/ees\/pflotran\/index.shtml."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_10"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/75.658652"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipl.2004.01.014"},{"key":"e_1_3_2_1_24_1","first-page":"1207","article-title":"Sensitivity analysis with the fdtd method on structured grids. Microwave Theory and Techniques","volume":"52","author":"Nikolova N.","unstructured":"Nikolova , N. , Tam , H. , and Bakr , M . Sensitivity analysis with the fdtd method on structured grids. Microwave Theory and Techniques , IEEE Transactions on 52 , 4 (april 2004), 1207 -- 1216 . Nikolova, N., Tam, H., and Bakr, M. Sensitivity analysis with the fdtd method on structured grids. Microwave Theory and Techniques, IEEE Transactions on 52, 4 (april 2004), 1207--1216.","journal-title":"IEEE Transactions on"},{"key":"e_1_3_2_1_25_1","unstructured":"NVIDIA Corporation. CUDA C programming guide - version 4.0.  NVIDIA Corporation. CUDA C programming guide - version 4.0."},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA Corporation. OpenCL programming guide for the CUDA architecture.  NVIDIA Corporation. OpenCL programming guide for the CUDA architecture."},{"key":"e_1_3_2_1_27_1","unstructured":"Saad Y. Sparskit: A basic toolkit for sparse matrix computations - version 2.  Saad Y. Sparskit: A basic toolkit for sparse matrix computations - version 2."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1658"}],"event":{"name":"GPGPU-5: The 5th Annual Workshop on General Purpose Processing with Graphics Processing Units","location":"London United Kingdom","acronym":"GPGPU-5","sponsor":["ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2159430.2159436","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2159430.2159436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:05:51Z","timestamp":1750241151000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2159430.2159436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3,3]]},"references-count":26,"alternative-id":["10.1145\/2159430.2159436","10.1145\/2159430"],"URL":"https:\/\/doi.org\/10.1145\/2159430.2159436","relation":{},"subject":[],"published":{"date-parts":[[2012,3,3]]},"assertion":[{"value":"2012-03-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}