{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T22:59:03Z","timestamp":1725577143280},"reference-count":13,"publisher":"CRC Press","isbn-type":[{"type":"print","value":"9781439825365"},{"type":"electronic","value":"9781439825372"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12,7]]},"DOI":"10.1201\/b10376-6","type":"book-chapter","created":{"date-parts":[[2011,1,28]],"date-time":"2011-01-28T14:37:12Z","timestamp":1296225432000},"page":"57-80","source":"Crossref","is-referenced-by-count":2,"title":["BLAS for GPUs"],"prefix":"10.1201","author":[{"given":"Rajib","family":"Nath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"301","published-online":{"date-parts":[[2011,1,28]]},"reference":[{"volume-title":"Guide","year":"1992","author":"Anderson E.","key":"p_2"},{"volume-title":"Guide. http:\/\/icl.cs.utk.edu\/magma","year":"2009","author":"Tomov S.","key":"p_3"},{"key":"p_6","doi-asserted-by":"crossref","unstructured":"V. Volkov and J. Demmel. Benchmarking GPUs to tune dense linear algebra. InSC '08: Proceedings of the 2008 ACM\/IEEE conference on Supercomputing, pages1-11, Piscataway, NJ, 2008. IEEE Press.","DOI":"10.1109\/SC.2008.5214359"},{"key":"p_7","doi-asserted-by":"crossref","unstructured":"Y. Li, J. Dongarra, and S. Tomov. A note on auto-tuning GEMM for GPUs. InICCS '09: Proceedings of the 9th International Conference on Computational Science, pages884-892, Berlin, Heidelberg, 2009. Springer-Verlag.","DOI":"10.1007\/978-3-642-01970-8_89"},{"volume-title":"http:\/\/developer.download.nvidia.com","year":"2007","author":"Compute Unified Device NVIDIA CUDA","key":"p_8"},{"volume-title":"EECS Department","year":"1992","author":"Demmel James W.","key":"p_11"},{"key":"p_12","doi-asserted-by":"publisher","DOI":"10.1137\/0916025"},{"key":"p_13","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"p_14","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840848"},{"key":"p_15","doi-asserted-by":"crossref","unstructured":"Jeff Bilmes, Krste Asanovic, Chee-Whye Chin, and James Demmel. Optimizing Matrix Multiply Using PHiPAC: A Portable, High-Performance, ANSI C Coding Methodology. International Conference on Supercomputing, 1997, pp.340-347.","DOI":"10.1145\/263580.263662"},{"key":"p_16","unstructured":"Matteo Frigo and Steven G. Johnson. FFTW: An adaptive software architecture for the FFT. Proc. 1998 IEEE Intl. Conf. Acoustics Speech and Signal Processing, vol.3, IEEE,1998, pp.1381-1384."},{"key":"p_17","first-page":"884","volume-title":"ICCS '09","author":"Li Y.","year":"2009"},{"volume-title":"October","year":"2008","author":"Wolfe Michael","key":"p_18"}],"container-title":["Chapman & Hall\/CRC Computational Science","Scientific Computing with Multicore and Accelerators"],"original-title":[],"language":"en","deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T05:42:49Z","timestamp":1559972569000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.crcnetbase.com\/doi\/abs\/10.1201\/b10376-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12,7]]},"ISBN":["9781439825365","9781439825372"],"references-count":13,"alternative-id":["10.1201\/b10376-6","10.1201\/CHCOMPUTSCI","10.1201\/b10376"],"URL":"https:\/\/doi.org\/10.1201\/b10376-6","relation":{},"ISSN":["2154-4492"],"issn-type":[{"type":"print","value":"2154-4492"}],"subject":[],"published":{"date-parts":[[2010,12,7]]}}}