{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:44Z","timestamp":1740099044329,"version":"3.37.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319780238"},{"type":"electronic","value":"9783319780245"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-78024-5_5","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"47-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multilayer Approach for Joint Direct and Transposed Sparse Matrix Vector Multiplication for Multithreaded CPUs"],"prefix":"10.1007","author":[{"given":"Ivan","family":"\u0160ime\u010dek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Langr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Kotenkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Aktulga, H.M., Bulu\u00e7, A., Williams, S., Yang, C.: Optimizing sparse matrix-multiple vectors multiplication for nuclear configuration interaction calculations. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS 2014, pp. 1213\u20131222. IEEE Computer Society, Washington (2014). https:\/\/doi.org\/10.1109\/IPDPS.2014.125","DOI":"10.1109\/IPDPS.2014.125"},{"key":"5_CR2","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511624100","volume-title":"Iterative Solution Methods","author":"O Axelsson","year":"1994","unstructured":"Axelsson, O.: Iterative Solution Methods. Cambridge University Press, Cambridge (1994)"},{"key":"5_CR3","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971538","volume-title":"Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods","author":"R Barrett","year":"1994","unstructured":"Barrett, R., Berry, M., Chan, T.F., Demmel, J., Donato, J., Dongarra, J., Eijkhout, V., Pozo, R., Romine, C., der Vorst, H.V.: Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods, 2nd edn. SIAM, Philadelphia (1994)","edition":"2"},{"key":"5_CR4","unstructured":"Cotofana, M.S., Cotofana, S., Stathis, P., Vassiliadis, S.: Direct and transposed sparse matrix-vector. In: Proceedings of the 2002 Euromicro Conference on Massively-Parallel Computing Systems, MPCS-2002, pp. 1\u20139 (2002)"},{"issue":"1","key":"5_CR5","first-page":"1:1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.F.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1:1\u20131:25 (2011)","journal-title":"ACM Trans. Math. Softw."},{"key":"5_CR6","unstructured":"Intel\u00ae company: Intel\u00ae Math Kernel Library. https:\/\/software.intel.com\/en-us\/mkl , https:\/\/software.intel.com\/en-us\/mkl . Accessed 13 Aug 2017"},{"issue":"6","key":"5_CR7","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TPDS.2015.2453970","volume":"27","author":"MO Karsavuran","year":"2016","unstructured":"Karsavuran, M.O., Akbudak, K., Aykanat, C.: Locality-aware parallel sparse matrix-vector and matrix-transpose-vector multiplication on many-core processors. IEEE Trans. Parallel Distrib. Syst. 27(6), 1713\u20131726 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"5_CR8","unstructured":"Langr, D., \u0160ime\u010dek, I., Tvrd\u00edk, P.: Storing sparse matrices in the adaptive-blocking hierarchical storage format. In: Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS 2013), pp. 479\u2013486. IEEE Xplore Digital Library, September 2013"},{"key":"5_CR9","unstructured":"Langr, D., \u0160ime\u010dek, I., Tvrd\u00edk, P., Dytrych, T., Draayer, J.P.: Adaptive-blocking hierarchical storage format for sparse matrices. In: Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS 2012), pp. 545\u2013551. IEEE Xplore Digital Library (2012)"},{"issue":"2","key":"5_CR10","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/TPDS.2015.2401575","volume":"27","author":"D Langr","year":"2016","unstructured":"Langr, D., Tvrd\u00edk, P.: Evaluation criteria for sparse matrix storage formats. IEEE Trans. Parallel Distrib. Syst. 27(2), 428\u2013440 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"11","key":"5_CR11","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/MC.2012.363","volume":"45","author":"N Leavitt","year":"2012","unstructured":"Leavitt, N.: Big iron moves toward exascale computing. Computer 45(11), 14\u201317 (2012)","journal-title":"Computer"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Liu, W., Vinter, B.: CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS 2015, pp. 339\u2013350. ACM, New York (2015). https:\/\/doi.org\/10.1145\/2751205.2751209","DOI":"10.1145\/2751205.2751209"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Martone, M., Filippone, S., Paprzycki, M., Tucci, S.: On blas operations with recursively stored sparse matrices. In: 2010 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), pp. 49\u201356, September 2010","DOI":"10.1109\/SYNASC.2010.72"},{"issue":"7","key":"5_CR14","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.parco.2014.03.008","volume":"40","author":"M Martone","year":"2014","unstructured":"Martone, M.: Efficient multithreaded untransposed, transposed or symmetric sparse matrix-vector multiplication with the recursive sparse blocks format. Parallel Comput. 40(7), 251\u2013270 (2014). https:\/\/doi.org\/10.1016\/j.parco.2014.03.008","journal-title":"Parallel Comput."},{"key":"5_CR15","unstructured":"Morton, G.M.: A computer oriented geodetic data base and a new technique in file sequencing. IBM Ltd. (1966)"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/978-0-387-09766-4_284","volume-title":"Encycl. Parallel Comput.","author":"R Nair","year":"2011","unstructured":"Nair, R.: Exascale computing. In: Padua, D. (ed.) Encycl. Parallel Comput., pp. 638\u2013644. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-0-387-09766-4_284"},{"key":"5_CR17","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.: Iterative Methods for Sparse Linear Systems, 2nd edn. Society for Industrial and Applied Mathematics, Philadelphia (2003)","edition":"2"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"\u0160ime\u010dek, I., Langr, D.: Space and execution efficient formats for modern processor architectures. In: Proceedings of the 17th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC 2015), pp. 98\u2013105. IEEE Computer Society (2015)","DOI":"10.1109\/SYNASC.2015.24"},{"issue":"14","key":"5_CR19","doi-asserted-by":"crossref","first-page":"3771","DOI":"10.1002\/cpe.3415","volume":"27","author":"Y Tao","year":"2015","unstructured":"Tao, Y., Deng, Y., Mu, S., Zhang, Z., Zhu, M., Xiao, L., Ruan, L.: GPU accelerated sparse matrix-vector multiplication and sparse matrix-transpose vector multiplication. Concurr. Comput. Pract. Exp. 27(14), 3771\u20133789 (2015)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"5_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/11752578_21","volume-title":"Parallel Processing and Applied Mathematics","author":"P Tvrd\u00edk","year":"2006","unstructured":"Tvrd\u00edk, P., \u0160ime\u010dek, I.: A new diagonal blocking format and model of cache behavior for sparse matrices. In: Wyrzykowski, R., Dongarra, J., Meyer, N., Wa\u015bniewski, J. (eds.) PPAM 2005. LNCS, vol. 3911, pp. 164\u2013171. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11752578_21 . http:\/\/dl.acm.org\/citation.cfm?id=2096870.2096894"},{"key":"5_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-540-68111-3_17","volume-title":"Parallel Processing and Applied Mathematics","author":"I \u0160ime\u010dek","year":"2008","unstructured":"\u0160ime\u010dek, I., Tvrd\u00edk, P.: Sparse matrix-vector multiplication - final solution? In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2007. LNCS, vol. 4967, pp. 156\u2013165. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-68111-3_17"},{"key":"5_CR22","unstructured":"\u0160ime\u010dek, I., Langr, D., Kotenkov, I.: Multilayer approach for joint direct and transposed sparse matrix vector multiplication for multithreaded CPUs (2017). https:\/\/bitbucket.org\/pctc\/parallel_spmmtv\/ . Accessed 13 Aug 2017"},{"issue":"1","key":"5_CR23","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/TPDS.2013.31","volume":"25","author":"AJ Yzelman","year":"2014","unstructured":"Yzelman, A.J., Roose, D.: High-level strategies for parallel shared-memory sparse matrix-vector multiplication. IEEE Trans. Parallel Distrib. Syst. 25(1), 116\u2013125 (2014)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"4","key":"5_CR24","doi-asserted-by":"crossref","first-page":"3128","DOI":"10.1137\/080733243","volume":"31","author":"AJ Yzelman","year":"2009","unstructured":"Yzelman, A.J., Bisseling, R.H.: Cache-oblivious sparse matrix-vector multiplication by using sparse matrix partitioning methods. SIAM J. Sci. Comput. 31(4), 3128\u20133154 (2009). https:\/\/lirias.kuleuven.be\/handle\/123456789\/319143","journal-title":"SIAM J. Sci. Comput."}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78024-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,13]],"date-time":"2019-10-13T03:54:39Z","timestamp":1570938879000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}