{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:41:53Z","timestamp":1775122913689,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540290315","type":"print"},{"value":"9783540320791","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11557654_91","type":"book-chapter","created":{"date-parts":[[2005,10,4]],"date-time":"2005-10-04T13:59:18Z","timestamp":1128434358000},"page":"807-816","source":"Crossref","is-referenced-by-count":72,"title":["Fast Sparse Matrix-Vector Multiplication by Exploiting Variable Block Structure"],"prefix":"10.1007","author":[{"given":"Richard W.","family":"Vuduc","sequence":"first","affiliation":[]},{"given":"Hyun-Jin","family":"Moon","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"91_CR1","unstructured":"Baker, A.H., Jessup, E.R., Manteuffel, T.: A technique for accelerating the convergence of restarted GMRES. Technical Report CU-CS-045-03, University of Colorado, Dept. of Computer Science (January 2003)"},{"key":"91_CR2","unstructured":"Buttari, A., Eijkhout, V., Langou, J., Filippone, S.: Performance optimization and modeling of blocked sparse kernels. Technical Report ICL-UT-04-05, Innovative Computing Laboratory, University of Tennessee, Knoxville (2005)"},{"key":"91_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/11428831_13","volume-title":"Computational Science \u2013 ICCS 2005","author":"E. D\u2019Azevedo","year":"2005","unstructured":"D\u2019Azevedo, E., Fahey, M.R., Mills, R.T.: Vectorized sparse matrix multiply for compressed sparse row storage. In: Sunderam, V.S., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2005. LNCS, vol.\u00a03514, pp. 99\u2013106. Springer, Heidelberg (2005)"},{"key":"91_CR4","first-page":"308","volume-title":"Proceedings of the International Conference on Parallel Computing (ParCo)","author":"R. Geus","year":"1999","unstructured":"Geus, R., R\u00f6llin, S.: Towards a fast parallel sparse matrix-vector multiplication. In: D\u2019Hollander, E.H., Joubert, J.R., Peters, F.J., Sips, H. (eds.) Proceedings of the International Conference on Parallel Computing (ParCo), pp. 308\u2013315. Imperial College Press, London (1999)"},{"key":"91_CR5","unstructured":"Im, E.-J.: Optimizing the performance of sparse matrix-vector multiplication. PhD thesis, University of California, Berkeley (May 2000)"},{"issue":"1","key":"91_CR6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1177\/1094342004041296","volume":"18","author":"E.-J. Im","year":"2004","unstructured":"Im, E.-J., Yelick, K., Vuduc, R.: Sparsity: Optimization framework for sparse matrix kernels. International Journal of High Performance Computing Applications\u00a018(1), 135\u2013158 (2004)","journal-title":"International Journal of High Performance Computing Applications"},{"key":"91_CR7","doi-asserted-by":"crossref","unstructured":"Lee, B.C., Vuduc, R., Demmel, J., Yelick, K.: Performance models for evaluation and automatic tuning of symmetric sparse matrix-vector multiply. In: Proceedings of the International Conference on Parallel Processing, Montreal, Canada (August 2004)","DOI":"10.1109\/ICPP.2004.1327917"},{"key":"91_CR8","unstructured":"Mellor-Crummey, J., Garvin, J.: Optimizing sparse matrix vector multiply using unroll-and-jam. In: Proceedings of the Los Alamos Computer Science Institute Third Annual Symposium, Santa Fe, NM, USA (October 2002)"},{"key":"91_CR9","unstructured":"Nishtala, R., Vuduc, R., Demmel, J., Yelick, K.: When cache blocking sparse matrix vector multiply works and why. In: Proceedings of the PARA 2004 Workshop on the State-of-the-art in Scientific Computing, Copenhagen, Denmark (June 2004)"},{"key":"91_CR10","doi-asserted-by":"crossref","unstructured":"Pinar, A., Heath, M.: Improving performance of sparse matrix-vector multiplication. In: Proceedings of Supercomputing (1999)","DOI":"10.1145\/331532.331562"},{"key":"91_CR11","unstructured":"Remington, K., Pozo, R.: NIST Sparse BLAS: User\u2019s Guide. Technical report, NIST (1996) http:\/\/www.gams.nist.gov\/spblas"},{"key":"91_CR12","unstructured":"Saad, Y.: SPARSKIT: A basic toolkit for sparse matrix computations (1994), http:\/\/www.cs.umn.edu\/Research\/arpa\/SPARSKIT\/sparskit.html"},{"key":"91_CR13","doi-asserted-by":"crossref","unstructured":"Temam, O., Jalby, W.: Characterizing the behavior of sparse algorithms on caches. In: Proceedings of Supercomputing (1992)","DOI":"10.1109\/SUPERC.1992.236646"},{"key":"91_CR14","doi-asserted-by":"crossref","unstructured":"Toledo, S.: Improving memory-system performance of sparse matrix-vector multiplication. In: Proceedings of the 8th SIAM Conference on Parallel Processing for Scientific Computing (March 1997)","DOI":"10.1147\/rd.416.0711"},{"key":"91_CR15","unstructured":"Vassilevska, V., Pinar, A.: Finding nonoverlapping dense blocks of a sparse matrix. Technical Report LBNL-54498, Lawrence Berkeley National Laboratory, Berkeley, CA, USA (2004)"},{"key":"91_CR16","unstructured":"Vuduc, R.: Automatic performance tuning of sparse matrix kernels. PhD thesis, University of California, Berkeley, Berkeley, CA, USA (December 2003)"},{"key":"91_CR17","unstructured":"Vuduc, R., Demmel, J., Yelick, K.: OSKI: An interface for a self-optimizing library of sparse matrix kernels (2005) http:\/\/www.bebop.cs.berkeley.edu\/oski"},{"key":"91_CR18","doi-asserted-by":"crossref","unstructured":"Vuduc, R., Demmel, J.W., Yelick, K.A., Kamil, S., Nishtala, R., Lee, B.: Performance optimizations and bounds for sparse matrix-vector multiply. In: Proceedings of Supercomputing, Baltimore, MD, USA (November 2002)","DOI":"10.1109\/SC.2002.10025"},{"key":"91_CR19","doi-asserted-by":"crossref","unstructured":"Vuduc, R., Moon, H.-J.: Fast sparse matrix-vector multiplication by exploiting variable blocks structure. Technical Report UCRL-TR-213454, Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, Livermore, CA, USA (July 2005)","DOI":"10.2172\/891708"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing and Communications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11557654_91","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,10]],"date-time":"2020-04-10T01:12:57Z","timestamp":1586481177000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11557654_91"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540290315","9783540320791"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/11557654_91","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005]]}}}