{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:40:10Z","timestamp":1738820410617,"version":"3.37.0"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540928584"},{"type":"electronic","value":"9783540928591"}],"license":[{"start":{"date-parts":[[2008,1,1]],"date-time":"2008-01-01T00:00:00Z","timestamp":1199145600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-92859-1_37","type":"book-chapter","created":{"date-parts":[[2008,12,15]],"date-time":"2008-12-15T09:45:28Z","timestamp":1229334328000},"page":"406-419","source":"Crossref","is-referenced-by-count":3,"title":["Attaining High Performance in General-Purpose Computations on Current Graphics Processors"],"prefix":"10.1007","author":[{"given":"Francisco D.","family":"Igual","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Barrachina, S., Castillo, M., Igual, F.D., Mayo, R., Quintana-Ort\u00ed, E.S.: Evaluation and tuning of the level 3 CUBLAS for graphics processors. In: Workshop on Multithreaded Architectures and Applications, MTAAP 2008 (2008)","DOI":"10.1109\/IPDPS.2008.4536485"},{"key":"37_CR2","unstructured":"NVIDIA Corp. NVIDIA CUBLAS Library (2007)"},{"key":"37_CR3","unstructured":"NVIDIA Corp. NVIDIA CUDA Compute Unified Device Architecture. Programming Guide (2007)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"Fatahalian, K., Sugerman, J., Hanrahan, P.: Understanding the efficiency of GPU algorithms for matrix-matrix multiplication. Graphics Hardware (2004)","DOI":"10.1145\/1058129.1058148"},{"key":"37_CR5","unstructured":"Basic Linear Algebra Subprograms Technical\u00a0(BLAST) Forum. Basic Linear Algebra Subprograms Technical (BLAST) Forum Standard (2001)"},{"key":"37_CR6","unstructured":"Galoppo, N., Govindaraju, N., Henson, M., Monocha, D.: LU-GPU: Efficient algorithms for solving dense linear systems on graphics hardware. In: ACM\/IEEE SC 2005 Conference (2005)"},{"key":"37_CR7","unstructured":"Goto, K., Van de Geijn, R.: High-performance implementation of the level-3 BLAS. ACM Transactions on Mathematical Software"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Govindaraju, N., Lloyd, B., Wang, W., Lin, M., Manocha, D.: Fast computation of database operations using graphics processors. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data, pp. 215\u2013226 (June 2004)","DOI":"10.1145\/1007568.1007594"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Hong, J.Y., Wang, M.D.: High speed processing of biomedical images using programmable GPU. In: 2004 International Conference on Image Processing, ICIP 2004, 24-27 October 2004, vol.\u00a04, pp. 2455\u20132458 (2004)","DOI":"10.1109\/ICIP.2004.1421599"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Larsen, E.S., McAllister, D.: Fast matrix multiplies using graphics hardware. In: Supercomputing, ACM\/IEEE 2001 Conference, p. 43 (November 2001)","DOI":"10.1145\/582034.582089"},{"key":"37_CR11","unstructured":"Morav\u00e1nszky, A.: Dense matrix algebra on the GPU (2003)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Ruiz, A., Sertel, O., Ujaldon, M., Catalyurek, U., Saltz, J., Gurcan, M.: Pathological image analysis using the GPU: Stroma classification for neuroblastoma. In: Proceedings IEEE Intl. Conference on BioInformation and Bio Medicine (2007)","DOI":"10.1109\/BIBM.2007.15"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science - VECPAR 2008"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-92859-1_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T05:20:39Z","timestamp":1738819239000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-92859-1_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540928584","9783540928591"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-92859-1_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}