{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T12:08:21Z","timestamp":1794571701150,"version":"4.9.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319969824","type":"print"},{"value":"9783319969831","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-96983-1_48","type":"book-chapter","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T11:50:06Z","timestamp":1533037806000},"page":"672-687","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":84,"title":["Design Principles for Sparse Matrix Multiplication on the GPU"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4357-0906","authenticated-orcid":false,"given":"Carl","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-9038","authenticated-orcid":false,"given":"Ayd\u0131n","family":"Bulu\u00e7","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6582-8237","authenticated-orcid":false,"given":"John D.","family":"Owens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,8,1]]},"reference":[{"key":"48_CR1","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"48_CR2","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.jpdc.2014.07.006","volume":"76","author":"AE Sar\u0131y\u00fcce","year":"2015","unstructured":"Sar\u0131y\u00fcce, A.E., Saule, E., Kaya, K., \u00c7ataly\u00fcrek, \u00dc.V.: Regularizing graph centrality computations. J. Parallel Distrib. Comput. 76, 106\u2013119 (2015)","journal-title":"J. Parallel Distrib. Comput."},{"key":"48_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/3-540-48224-5_15","volume-title":"Automata, Languages and Programming","author":"A Tiskin","year":"2001","unstructured":"Tiskin, A.: All-pairs shortest paths computation in the BSP model. In: Orejas, F., Spirakis, P.G., van Leeuwen, J. (eds.) ICALP 2001. LNCS, vol. 2076, pp. 178\u2013189. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-48224-5_15"},{"issue":"4","key":"48_CR4","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1137\/0916053","volume":"16","author":"V Simoncini","year":"1995","unstructured":"Simoncini, V., Gallopoulos, E.: An iterative method for nonsymmetric systems with multiple right-hand sides. SIAM J. Sci. Comput. 16(4), 917\u2013933 (1995)","journal-title":"SIAM J. Sci. Comput."},{"key":"48_CR5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719581","volume-title":"Templates for the Solution of Algebraic Eigenvalue Problems: A Practical Guide","author":"Z Bai","year":"2000","unstructured":"Bai, Z., Demmel, J., Dongarra, J., Ruhe, A., van der Vorst, H.: Templates for the Solution of Algebraic Eigenvalue Problems: A Practical Guide. SIAM, Philadelphia (2000)"},{"issue":"2","key":"48_CR6","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1137\/S1064827500366124","volume":"23","author":"AV Knyazev","year":"2001","unstructured":"Knyazev, A.V.: Toward the optimal preconditioned eigensolver: locally optimal block preconditioned conjugate gradient method. SIAM SISC 23(2), 517\u2013541 (2001)","journal-title":"SIAM SISC"},{"key":"48_CR7","unstructured":"Wang, H., Banerjee, A., Hsieh, C.J., Ravikumar, P.K., Dhillon, I.S.: Large scale distributed sparse precision estimation. In: NIPS, pp. 584\u2013592 (2013)"},{"key":"48_CR8","unstructured":"Si, S., Shin, D., Dhillon, I.S., Parlett, B.N.: Multi-scale spectral decomposition of massive graphs. In: NIPS, pp. 2798\u20132806 (2014)"},{"issue":"8","key":"48_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3016078.2851152","volume":"51","author":"Ramakrishnan Kannan","year":"2016","unstructured":"Kannan, R., Ballard, G., Park, H.: A high-performance parallel algorithm for nonnegative matrix factorization. In: ACM SIGPLAN, vol. 51. ACM (2016)","journal-title":"ACM SIGPLAN Notices"},{"issue":"1","key":"48_CR10","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.jsb.2010.01.021","volume":"170","author":"F Vazquez","year":"2010","unstructured":"Vazquez, F., Garzon, E.M., Fernandez, J.J.: A matrix approach to tomographic reconstruction and its implementation on GPUs. J. Struct. Biol. 170(1), 146\u2013151 (2010)","journal-title":"J. Struct. Biol."},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Mattson, T., McMillan, S., Moreira, J., Yang, C.: Design of the GraphBLAS API for C. In: IEEE Workshop on Graph Algorithm Building Blocks, IPDPSW (2017)","DOI":"10.1109\/IPDPSW.2017.117"},{"key":"48_CR12","unstructured":"Baxter, S.: Modern GPU library (2015). http:\/\/nvlabs.github.io\/moderngpu\/"},{"issue":"4","key":"48_CR13","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/2699470","volume":"41","author":"S Dalton","year":"2015","unstructured":"Dalton, S., Olson, L., Bell, N.: Optimizing sparse matrix-matrix multiplication for the GPU. ACM TOMS 41(4), 25 (2015)","journal-title":"ACM TOMS"},{"key":"48_CR14","doi-asserted-by":"crossref","unstructured":"Merrill, D., Garland, M.: Merge-based parallel sparse matrix-vector multiplication. In: Supercomputing 2016, pp. 678\u2013689. IEEE, November 2016","DOI":"10.1109\/SC.2016.57"},{"issue":"1","key":"48_CR15","first-page":"1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM TOMS 38(1), 1 (2011)","journal-title":"ACM TOMS"},{"issue":"7","key":"48_CR16","first-page":"968","volume":"57","author":"G Ortega","year":"2014","unstructured":"Ortega, G., V\u00e1zquez, F., Garc\u00eda, I., Garz\u00f3n, E.M.: FastSpMM: an efficient library for sparse matrix matrix product on GPUs. Computer 57(7), 968\u2013979 (2014)","journal-title":"Computer"},{"key":"48_CR17","unstructured":"Anzt, H., Tomov, S., Dongarra, J.: Accelerating the LOBPCG method on GPUs using a blocked sparse matrix vector product. In: Proceedings of the Symposium on High Performance Computing, pp. 75\u201382 (2015)"},{"key":"48_CR18","doi-asserted-by":"crossref","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 IPDPS. IEEE Computer Society (2014)","DOI":"10.1109\/IPDPS.2014.125"},{"issue":"4","key":"48_CR19","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/3017994","volume":"43","author":"S Filippone","year":"2017","unstructured":"Filippone, S., Cardellini, V., Barbieri, D., Fanfarillo, A.: Sparse matrix-vector multiplication on GPGPUs. ACM TOMS 43(4), 30 (2017)","journal-title":"ACM TOMS"},{"key":"48_CR20","unstructured":"Naumov, M., Chien, L.S., Vandermersch, P., Kapasi, U.: CUSPARSE library: a set of basic linear algebra subroutines for sparse matrices. In: GTC (2010)"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Hong, C., et al.: Efficient sparse-matrix multi-vector product on GPUs. In: Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing. HPDC 2018, pp. 66\u201379. ACM, New York (2018)","DOI":"10.1145\/3208040.3208062"},{"key":"48_CR22","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking GPUs to tune dense linear algebra. In: Supercomputing 2008, pp. 31:1\u201331:11, November 2008","DOI":"10.1109\/SC.2008.5214359"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Jablin, J.A., Jablin, T.B., Mutlu, O., Herlihy, M.: Warp-aware trace scheduling for GPUs. In: ACM PACT 2014, pp. 163\u2013174 (2014)","DOI":"10.1145\/2628071.2628101"},{"key":"48_CR24","doi-asserted-by":"crossref","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: Supercomputing 2009, pp. 18:1\u201318:11, November 2009","DOI":"10.1145\/1654059.1654078"},{"key":"48_CR25","doi-asserted-by":"crossref","unstructured":"Yang, C., Buluc, A., Owens, J.D.: Supporting data for design principles for sparse matrix multiplication on the GPU paper at euro-par 2018 (2018). https:\/\/doi.org\/10.6084\/m9.figshare.6378764","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"48_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-12200-2_14","volume-title":"LATIN 2010: Theoretical Informatics","author":"G Greiner","year":"2010","unstructured":"Greiner, G., Jacob, R.: The I\/O complexity of sparse matrix dense matrix multiplication. In: L\u00f3pez-Ortiz, A. (ed.) LATIN 2010. LNCS, vol. 6034, pp. 143\u2013156. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12200-2_14"},{"key":"48_CR27","doi-asserted-by":"crossref","unstructured":"Bulu\u00e7, A., Fineman, J.T., Frigo, M., Gilbert, J.R., Leiserson, C.E.: Parallel sparse matrix-vector and matrix-transpose-vector multiplication using compressed sparse blocks. In: Proceedings of SPAA (2009)","DOI":"10.1145\/1583991.1584053"},{"key":"48_CR28","unstructured":"Merrill, D.: CUB library (2015). http:\/\/nvlabs.github.io\/cub"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2018: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96983-1_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T21:09:47Z","timestamp":1659301787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-96983-1_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319969824","9783319969831"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96983-1_48","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-319-96983-1","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"1 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}