{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:40:11Z","timestamp":1787510411600,"version":"build-2736575974"},"reference-count":14,"publisher":"Springer Science and Business Media LLC","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1007\/s11227-011-0626-0","type":"journal-article","created":{"date-parts":[[2011,6,6]],"date-time":"2011-06-06T11:02:29Z","timestamp":1307358149000},"page":"710-721","source":"Crossref","is-referenced-by-count":19,"title":["Performance modeling and optimization of sparse matrix-vector multiplication on NVIDIA CUDA platform"],"prefix":"10.1007","volume":"63","author":[{"given":"Shiming","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai Xiang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2011,6,7]]},"reference":[{"key":"626_CR1","unstructured":"Zone CUDA. http:\/\/www.nvidia.com\/cuda"},{"key":"626_CR2","unstructured":"decuda. http:\/\/wiki.github.com\/laanwj\/decuda"},{"key":"626_CR3","unstructured":"GPGPU.org. http:\/\/www.gpgpu.org"},{"issue":"1","key":"626_CR4","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s10766-010-0145-2","volume":"39","author":"M Belgin","year":"2011","unstructured":"Belgin M, Back G, Ribbens C (2011) A library for pattern-based sparse matrix vector multiply. Intl J Parallel Program 39(1):62\u201367","journal-title":"Intl J Parallel Program"},{"issue":"3","key":"626_CR5","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1080\/17445760802337010","volume":"24","author":"L Buatois","year":"2009","unstructured":"Buatois L, Caumon G, Levy B (2009) Concurrent number cruncher\u2014a GPU implementation of a general sparse linear solver. Intl J of Parallel, Emergent and Distributed Systems 24(3):205\u2013223","journal-title":"Intl J of Parallel, Emergent and Distributed Systems"},{"issue":"6","key":"626_CR6","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1109\/TITB.2010.2072963","volume":"14","author":"D Chen","year":"2010","unstructured":"Chen D, Li D, Xiong M, Bao H, Li X (2010) GPGPU-aided ensemble empirical mode decomposition for EEG analysis during anaesthesia. IEEE Trans Inf Technol BioMed 14(6):1417\u20131427","journal-title":"IEEE Trans Inf Technol BioMed"},{"issue":"5","key":"626_CR7","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1145\/1837853.1693471","volume":"45","author":"JW Choi","year":"2010","unstructured":"Choi JW, Singh A, Vuduc RW (2010) Model-driven autotuning of sparse matrix-vector multiply on CPUs. ACM SIGPLAN Not 45(5):115\u2013126","journal-title":"ACM SIGPLAN Not"},{"key":"626_CR8","first-page":"157","volume-title":"Proc 24th nat conf ACM","author":"E Cuthill","year":"1969","unstructured":"Cuthill E, McKee J (1969) Reducing the bandwidth of sparse symmetric matrices. In: Proc 24th nat conf ACM, pp 157\u2013172"},{"key":"626_CR9","doi-asserted-by":"crossref","unstructured":"Kourtis K, Goumas G, Koziris N (2008) Optimizing sparse matrix-vector multiplication using index and value compression, pp\u00a087\u201396","DOI":"10.1109\/ICPP.2008.62"},{"key":"626_CR10","volume-title":"Proc SC\u201909","author":"N Bell","year":"2009","unstructured":"Bell N, Garland M (2009) Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Proc SC\u201909"},{"key":"626_CR11","unstructured":"Vuduc RW (2002) Automatic performance tuning of sparse matrix kernels. PhD thesis, University of California, Berkeley, 2002"},{"key":"626_CR12","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1145\/1183401.1183444","volume-title":"Proc of the 20th annual intl conf on supercomputing, ICS \u201906","author":"J Willcock","year":"2006","unstructured":"Willcock J, Lumsdaine A (2006) Accelerating sparse matrix computations via data compression. In: Proc of the 20th annual intl conf on supercomputing, ICS \u201906. ACM, New York, pp 307\u2013316"},{"key":"626_CR13","first-page":"38:1","volume-title":"Proc 2007 ACM\/IEEE conference on supercomputing, SC \u201907","author":"S Williams","year":"2007","unstructured":"Williams S, Oliker L, Vuduc R, Shalf J, Yelick K, Demmel JW (2007) Optimization of sparse matrix-vector multiplication on emerging multicore platforms. In: Proc 2007 ACM\/IEEE conference on supercomputing, SC \u201907. ACM, New York, pp 38:1\u201338:12"},{"key":"626_CR14","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative methods for sparse linear systems","author":"Y Saad","year":"2003","unstructured":"Saad Y (2003) Iterative methods for sparse linear systems, 2nd edn. SIAM, Philadelphia","edition":"2"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-011-0626-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,11]],"date-time":"2019-06-11T08:55:12Z","timestamp":1560243312000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-011-0626-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6,7]]},"references-count":14,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["626"],"URL":"https:\/\/doi.org\/10.1007\/s11227-011-0626-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,6,7]]}}}