{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:39:50Z","timestamp":1725727190119},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387173"},{"type":"electronic","value":"9783642387180"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38718-0_9","type":"book-chapter","created":{"date-parts":[[2013,5,23]],"date-time":"2013-05-23T20:57:50Z","timestamp":1369342670000},"page":"59-71","source":"Crossref","is-referenced-by-count":1,"title":["A High Performance SYMV Kernel on a Fermi-core GPU"],"prefix":"10.1007","author":[{"given":"Toshiyuki","family":"Imamura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susumu","family":"Yamada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiko","family":"Machida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"9_CR1","doi-asserted-by":"crossref","first-page":"643","DOI":"10.15669\/pnst.2.643","volume":"2","author":"T. Imamura","year":"2011","unstructured":"Imamura, T., Yamada, S., Machida, M.: Development of a High Performance Eigensolver on the Peta-Scale Next Generation Supercomputer System, the Atomic Energy Society of Japan. Progress in Nuclear Science and Technology\u00a02, 643\u2013650 (2011)","journal-title":"Progress in Nuclear Science and Technology"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Nath, R., Tomov, S., et al.: Optimizing symmetric dense matrix-vector multiplication on GPUs. In: Proc. of the Intl. Conf. High Performance Computing, Networking, Storage and Analysis, SC 2011 (2011)","DOI":"10.1145\/2063384.2063392"},{"issue":"4","key":"9_CR3","first-page":"158","volume":"4","author":"T. Imamura","year":"2011","unstructured":"Imamura, T.: Performance-stabilization and automatic performance tuning for DGEMV routines on a CUDA environment. IPSJ Journal, Transaction of Advanced Computing Systems, ACS\u00a04(4), 158\u2013168 (2011) (in Japanese)","journal-title":"IPSJ Journal, Transaction of Advanced Computing Systems, ACS"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, A., Fey, D.: High Performance Stencil Code Algorithm for GPGPUs. In: Proc. of ICCS 2011, Procedia Computer Science, vol.\u00a04, pp. 2077\u20132036 (2011)","DOI":"10.1016\/j.procs.2011.04.221"},{"key":"9_CR5","unstructured":"Hwu, W.W. (ed.): GPU Computing Gems Jade Edition (Applications of GPU Computing Series). Morgan Kaufmann (2011)"},{"key":"9_CR6","unstructured":"NVIDIA: whitepaper NVIDIA\u2019s Next Generation CUDA Compute Architecture: Fermi, \n                    \n                      http:\/\/www.nvidia.com\/content\/PDF\/fermi_white_papers\/NVIDIAFermiComputeArchitectureWhitepaper.pdf"},{"key":"9_CR7","unstructured":"NVIDIA: CUDA CUBLAS Library, \n                    \n                      http:\/\/developer.download.nvidia.com"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Agullo, E., Demmel, J., et al.: Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects. J. of Physics: Conference Series\u00a0180 (2009)","DOI":"10.1088\/1742-6596\/180\/1\/012037"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Humphrey, J.R., Price, D.K., et al.: CULA: Hybrid GPU Accelerated Linear Algebra Routines. In: SPIE Defense and Security Symposium (DSS) (2010)","DOI":"10.1117\/12.850538"},{"key":"9_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/978-3-642-31464-3_63","volume-title":"Parallel Processing and Applied Mathematics","author":"H.H.B. S\u00f8rensen","year":"2012","unstructured":"S\u00f8rensen, H.H.B.: Auto-tuning Dense Vector and Matrix-Vector Operations for Fermi GPUs. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2011, Part I. LNCS, vol.\u00a07203, pp. 619\u2013629. Springer, Heidelberg (2012)"},{"key":"9_CR11","unstructured":"GPUlab: GLAS library version 0.0.2, \n                    \n                      http:\/\/gpulab.imm.dtu.dk\/docs\/glas_v0.0.2_C2050_cuda_4.0_linux.tar.gz"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science - VECPAR 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38718-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T01:49:00Z","timestamp":1557712140000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-38718-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387173","9783642387180"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38718-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}