{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:39Z","timestamp":1740099039483,"version":"3.37.3"},"publisher-location":"Cham","reference-count":14,"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_22","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"243-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["NVIDIA GPUs Scalability to Solve Multiple (Batch) Tridiagonal Systems Implementation of cuThomasBatch"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1479-4310","authenticated-orcid":false,"given":"Pedro","family":"Valero-Lara","sequence":"first","affiliation":[]},{"given":"Ivan","family":"Mart\u00ednez-P\u00e9rez","sequence":"additional","affiliation":[]},{"given":"Ra\u00fcl","family":"Sirvent","sequence":"additional","affiliation":[]},{"given":"Xavier","family":"Martorell","sequence":"additional","affiliation":[]},{"given":"Antonio J.","family":"Pe\u00f1a","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Davidson, A., Zhang, Y., Owens, J.D.: An auto-tuned method for solving large tridiagonal systems on the GPU. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium, May 2011","DOI":"10.1109\/IPDPS.2011.92"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Dongarra, J.J., Hammarling, S., Higham, N.J., Relton, S.D., Valero-Lara, P., Zounon, M.: The design and performance of batched BLAS on modern high-performance computing systems. In: International Conference on Computational Science, ICCS 2017, 12\u201314 June 2017, Zurich, Switzerland, pp. 495\u2013504 (2017)","DOI":"10.1016\/j.procs.2017.05.138"},{"key":"22_CR3","doi-asserted-by":"publisher","unstructured":"Greenbaum, A.: Iterative methods for solving linear systems. Society for Industrial and Applied Mathematics (1997). \nhttps:\/\/doi.org\/10.1137\/1.9781611970937","DOI":"10.1137\/1.9781611970937"},{"issue":"34","key":"22_CR4","first-page":"285","volume":"7","author":"R George","year":"2004","unstructured":"George, R.: Evaluation of vertical coordinate and vertical mixing algorithms in the Hybrid-Coordinate Ocean Model (HYCOM). Ocean Model. 7(34), 285\u2013322 (2004)","journal-title":"Ocean Model."},{"issue":"3","key":"22_CR5","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1137\/0911032","volume":"11","author":"CT Ho","year":"1990","unstructured":"Ho, C.T., Johnsson, S.L.: Optimizing tridiagonal solvers for alternating direction methods on Boolean cube multiprocessors. SIAM J. Sci. Stat. Comput. 11(3), 563\u2013592 (1990)","journal-title":"SIAM J. Sci. Stat. Comput."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Kim, H.-S., Wu, S., Chang, L., Hwu, W.W.: A scalable tridiagonal solver for GPUs. In: Proceedings of the 2013 42nd International Conference on Parallel Processing, pp. 444\u2013453 (2011)","DOI":"10.1109\/ICPP.2011.41"},{"key":"22_CR7","unstructured":"NVIDIA. cuSPARSE. CUDA Toolkit Documentation (2018)"},{"key":"22_CR8","unstructured":"Sakharnykh, N.: Efficient tridiagonal solvers for ADI methods and fluid simulation. In: Proceedings of the NVIDIA GPU Technology Conference, September 2010"},{"key":"22_CR9","volume-title":"Elementary Numerical Analysis","author":"C Boor de","year":"1976","unstructured":"de Boor, C., Conte, S.D.: Elementary Numerical Analysis, vol. 1. McGraw-Hill, New York (1976)"},{"key":"22_CR10","unstructured":"Valero-Lara, P., Mart\u00ednez-Perez, I., Pe\u00f1a, A.J., Martorell, X., Sirvent, R., Labarta, J.: cuHinesBatch: solving multiple Hines systems on GPUs human brain \n            $${\\text{project}}^{\\text{* }}$$\n          . In: International Conference on Computational Science, ICCS 2017, 12\u201314 June 2017, Zurich, Switzerland, pp. 566\u2013575 (2017)"},{"issue":"1","key":"22_CR11","first-page":"32","volume":"17","author":"P Valero-Lara","year":"2016","unstructured":"Valero-Lara, P., Nookala, P., Pelayo, F.L., Jansson, J., Dimitropoulos, S., Raicu, I.: Many-task computing on many-core architectures. Scalable Comput.: Pract. Exp. 17(1), 32\u201346 (2016)","journal-title":"Scalable Comput.: Pract. Exp."},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Valero-Lara, P., Pinelli, A., Favier, J., Matias, M.P.: Block tridiagonal solvers on heterogeneous architectures. In: Proceedings of the IEEE 10th International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012, pp. 609\u2013616 (2012)","DOI":"10.1109\/ISPA.2012.91"},{"issue":"4","key":"22_CR13","doi-asserted-by":"crossref","first-page":"1265","DOI":"10.1016\/j.cpc.2013.12.026","volume":"185","author":"P Valero-Lara","year":"2014","unstructured":"Valero-Lara, P., Pinelli, A., Prieto-Matias, M.: Fast finite difference poisson solvers on heterogeneous architectures. Comput. Phys. Commun. 185(4), 1265\u20131272 (2014)","journal-title":"Comput. Phys. Commun."},{"issue":"5","key":"22_CR14","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1145\/1837853.1693472","volume":"45","author":"Y Zhang","year":"2010","unstructured":"Zhang, Y., Cohen, J., Owens, J.D.: Fast tridiagonal solvers on the GPU. SIGPLAN Not. 45(5), 127\u2013136 (2010)","journal-title":"SIGPLAN Not."}],"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_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:36:21Z","timestamp":1521707781000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}