{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T16:09:03Z","timestamp":1725466143754},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642314636"},{"type":"electronic","value":"9783642314643"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31464-3_63","type":"book-chapter","created":{"date-parts":[[2012,7,2]],"date-time":"2012-07-02T11:20:38Z","timestamp":1341228038000},"page":"619-629","source":"Crossref","is-referenced-by-count":8,"title":["Auto-tuning Dense Vector and Matrix-Vector Operations for Fermi GPUs"],"prefix":"10.1007","author":[{"given":"Hans Henrik Brandenborg","family":"S\u00f8rensen","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"63_CR1","unstructured":"NVIDIA Corp.: CUDA Toolkit Version 3.2. (2010)"},{"key":"63_CR2","unstructured":"Khronos Group: OpenCL Specification 1.1. (2010)"},{"key":"63_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"J.J. Dongarra","year":"1990","unstructured":"Dongarra, J.J., Du Croz, J., Hammarling, S., Duff, I.S.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw.\u00a016, 1\u201317 (1990)","journal-title":"ACM Trans. Math. Softw."},{"key":"63_CR4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604","volume-title":"LAPACK Users\u2019 guide","author":"E. Anderson","year":"1999","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, L.S., Demmel, J., Dongarra, J.J., Du Croz, J., Hammarling, S., Greenbaum, A., McKenney, A., Sorensen, D.: LAPACK Users\u2019 guide, 3rd edn. SIAM, Philadelphia (1999)","edition":"3"},{"key":"63_CR5","unstructured":"Tomov, S., Nath, R., Du, P., Dongarra, J.: MAGMA v0.2 Users\u2019 Guide (2009)"},{"key":"63_CR6","doi-asserted-by":"crossref","unstructured":"Humphrey, J.R., Price, D.K., Spagnoli, K.E., Paolini, A.L., Kelmelis, E.J.: CULA: hybrid GPU accelerated linear algebra routines. In: Proc. SPIE, vol. 7705 (2010)","DOI":"10.1117\/12.850538"},{"key":"63_CR7","doi-asserted-by":"crossref","unstructured":"Dongarra, J., Moore, S.: 12. In: Empirical Performance Tuning of Dense Linear Algebra Software, pp. 255\u2013272. CRC Press (2010)","DOI":"10.1201\/b10509-13"},{"key":"63_CR8","unstructured":"Whaley, R.C., Petitet, A., Clint, R., Antoine, W., Jack, P., Dongarra, J.J.: Automated Empirical Optimizations of Software and the ATLAS project (2000)"},{"key":"63_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Dongarra, J., Tomov, S.: A note on auto-tuning gemm for gpus (2009)","DOI":"10.1007\/978-3-642-01970-8_89"},{"key":"63_CR10","unstructured":"Micikevicius, P.: Analysis-driven performance opt. GTC, Recorded Session (2010)"},{"key":"63_CR11","unstructured":"Volkov, V.: Better performance at lower occupancy. GTC, Recorded Session (2010)"},{"key":"63_CR12","unstructured":"Harris, M.: Optimizing parallel reduction in cuda. NVIDIA Dev. Tech. (2008)"},{"key":"63_CR13","unstructured":"NVIDIA Corp.: CUDA C Programming Guide Version 3.2. (2010)"},{"key":"63_CR14","unstructured":"Kl\u00f6ckner, A., Pinto, N., Lee, Y., Catanzaro, B., Ivanov, P., Fasih, A.: PyCUDA: GPU Run-Time Code Generation for High-Performance Computing (2009)"},{"key":"63_CR15","unstructured":"NVIDIA Corp.: CUDA GPU Occupancy Calculator (2010)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31464-3_63.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T08:02:25Z","timestamp":1620115345000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31464-3_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642314636","9783642314643"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31464-3_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}