{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:15:58Z","timestamp":1763468158796},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642400469"},{"type":"electronic","value":"9783642400476"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","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":[[2013]]},"DOI":"10.1007\/978-3-642-40047-6_81","type":"book-chapter","created":{"date-parts":[[2013,7,20]],"date-time":"2013-07-20T12:18:02Z","timestamp":1374322682000},"page":"813-825","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Power\/Performance Trade-Offs of Small Batched LU Based Solvers on GPUs"],"prefix":"10.1007","author":[{"given":"Oreste","family":"Villa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Massimiliano","family":"Fatica","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nitin","family":"Gawande","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonino","family":"Tumeo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"81_CR1","doi-asserted-by":"crossref","unstructured":"Agullo, E., Augonnet, C., Dongarra, J., Faverge, M., Langou, J., Ltaief, H., Tomov, S.: Lu factorization for accelerator-based systems. In: AICCSA: 9th IEEE\/ACS International Conference on Computer Systems and Applications, pp. 217\u2013224 (December 2011)","DOI":"10.1109\/AICCSA.2011.6126599"},{"key":"81_CR2","unstructured":"Hammond, G., Lichtner, P., Lu, C., Mills, R.: Pflotran: Reactive flow and transport code for use on laptops to leadership-class supercomputers. In: Groundwater Reactive Transport Models. Bentham Sciene Publishers (2012)"},{"key":"81_CR3","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1002\/wics.164","volume":"3","author":"N. Higham","year":"2011","unstructured":"Higham, N.: Gaussian elimination. Computational Statistics\u00a03, 230\u2013238 (2011)","journal-title":"Computational Statistics"},{"key":"81_CR4","unstructured":"Nidia corporation. Nidia CUBLAS Library, Version 5.0 (2012)"},{"key":"81_CR5","unstructured":"Nidia corporation. Nvidia CUDA c Programming Guide, Version 5.0 (2012)"},{"key":"81_CR6","doi-asserted-by":"crossref","unstructured":"Song, F., Tomov, S., Dongarra, J.: Enabling and scaling matrix computations on heterogeneous multi-core and multi-GPU systems. In: ICS 2012: The 26th ACM International Conference on Supercomputing, pp. 365\u2013376 (2012)","DOI":"10.1145\/2304576.2304625"},{"key":"81_CR7","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1016\/j.cageo.2010.04.013","volume":"36","author":"G. Tang","year":"2010","unstructured":"Tang, G., D\u2019Azevedo, E.F., Zhang, F., Parker, J.C., Watson, D.B., Jardine, P.M.: Application of a hybrid MPI\/OPENMP approach for parallel groundwater model calibration using multi-core computers. Computers & Geosciences\u00a036, 1451\u20131460 (2010)","journal-title":"Computers & Geosciences"},{"key":"81_CR8","doi-asserted-by":"crossref","unstructured":"Tomov, S., Nath, R., Ltaief, H., Dongarra, J.: Dense linear algebra solvers for multicore with gpu accelerators. In: IPDPSW 2010: IEEE International Symposium on Parallel Distributed Processing, Workshops and Phd Forum, pp. 1\u20138 (2010)","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"81_CR9","doi-asserted-by":"crossref","unstructured":"White, M., Oostrom, M.: STOMP Subsurface Transport Over Multiple Phase: User\u2019s Guide. Technical report, Pacific Northwest National Laboratory, Richland, WA, USA, PNNL-15782 (2006)","DOI":"10.2172\/1012530"},{"key":"81_CR10","unstructured":"Yeh, G., Tripathi, V., Gwo, J., Cheng, H., Chend, J.-R.C., Salvage, K., Li, M., Fang, Y., Li, Y., Sun, J., Zhang, F., Siegel, M.: HYDROGEOCHEM: A coupled model of variably saturated flow, thermal transport, and reactive biogeochemical transport, on laptops to leadership-class supercomputers. In: Groundwater Reactive Transport Models. Bentham Science Publishers (2012)"},{"key":"81_CR11","unstructured":"Zhang, K., Wu, Y., Pruess, K.: User\u2019s Guide for TOUGH2-MP - A Massively Parallel Version of the TOUGH2 Code. Technical report, Lawrence Berkeley National Laboratory, Berkeley, CA, USA, LBNL-315E (2008)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2013 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40047-6_81","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T01:09:42Z","timestamp":1587344982000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40047-6_81"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642400469","9783642400476"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40047-6_81","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}