{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T07:39:52Z","timestamp":1725521992306},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540898931"},{"type":"electronic","value":"9783540898948"}],"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\/978-3-540-89894-8_7","type":"book-chapter","created":{"date-parts":[[2008,12,16]],"date-time":"2008-12-16T10:22:24Z","timestamp":1229422944000},"page":"30-41","source":"Crossref","is-referenced-by-count":1,"title":["Fine Tuning Matrix Multiplications on Multicore"],"prefix":"10.1007","author":[{"given":"St\u00e9phane","family":"Zuckerman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"P\u00e9rache","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Jalby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"7_CR1","unstructured":"Asanovic, K., Bodik, R., Catanzaro, B.C., Gebis, J.J., Husbands, P., Keutzer, K., Patterson, D.A., Plishker, W.L., Shalf, J., Williams, S.W., Yelick, K.A.: The landscape of parallel computing research: A view from berkeley. Technical report, EECS Department, Univ. of California, Berkeley (December 2006)"},{"key":"7_CR2","unstructured":"Cannon, L.E.: A cellular computer to implement the kalman filter algorithm. Ph.D thesis (1969)"},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1145\/1248377.1248397","volume-title":"SPAA 2007: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures","author":"E. Chan","year":"2007","unstructured":"Chan, E., Quintana-Orti, E.S., Quintana-Orti, G., van de Geijn, R.: Supermatrix out-of-order scheduling of matrix operations for smp and multi-core architectures. In: SPAA 2007: Proceedings of the nineteenth annual ACM symposium on Parallel algorithms and architectures, pp. 116\u2013125. ACM, New York (2007)"},{"key":"7_CR4","doi-asserted-by":"publisher","DOI":"10.1145\/63047","volume-title":"Proceedings of the 3rd conference on Hypercube concurrent computers and applications","author":"G.C. Fox","year":"1988","unstructured":"Fox, G.C., Furmanski, W., Walker, D.W.: Optimal matrix algorithms on homogeneous hypercubes. In: Proceedings of the 3rd conference on Hypercube concurrent computers and applications. ACM, New York (1988)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Goto, K., van de Geijn, R.: High performance implementation of the level-3. Transactions on Mathematical Software\u00a035(1) (2008)","DOI":"10.1145\/1377603.1377607"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Goto, K., van de Geijn, R.A.: Anatomy of a high-performance matrix multiplication. Transactions on Mathematical Software\u00a034(3) (2008)","DOI":"10.1145\/1356052.1356053"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Krishnan, M., Nieplocha, J.: Srumma: A matrix multiplication algorithm suitable for clusters and scalable shared memory systems. In: IPDPS (2004)","DOI":"10.1109\/IPDPS.2004.1303000"},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-540-85451-7_9","volume-title":"Euro-Par 2008 \u2013 Parallel Processing","author":"H.J. Marc P\u00e9rache","year":"2008","unstructured":"Marc P\u00e9rache, H.J., Namyst, R.: Mpc: a unified parallel runtime for clusters of numa machines. In: Luque, E., Margalef, T., Ben\u00edtez, D. (eds.) Euro-Par 2008. LNCS, vol.\u00a05168, pp. 78\u201388. Springer, Heidelberg (2008)"},{"key":"7_CR9","unstructured":"Matthias Christen, O.S., Burkhart, H.: Graphical processing units as co-processors for hardware-oriented numerical solvers. In: Workshop PARS 2007 (2006)"},{"key":"7_CR10","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the ATLAS project. In: Parallel Computing (2001)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing - HiPC 2008"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-89894-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T05:42:12Z","timestamp":1557985332000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-89894-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540898931","9783540898948"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-89894-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2008]]}}}