{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:33:58Z","timestamp":1772724838859,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T00:00:00Z","timestamp":1528675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006502","name":"Defense Sciences Office, DARPA","doi-asserted-by":"publisher","award":["D16PC00183"],"award-info":[{"award-number":["D16PC00183"]}],"id":[{"id":"10.13039\/100006502","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1404995,1513120,1629548,1645599,1747447"],"award-info":[{"award-number":["1404995,1513120,1629548,1645599,1747447"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,6,11]]},"DOI":"10.1145\/3208040.3208062","type":"proceedings-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T12:36:20Z","timestamp":1528720580000},"page":"66-79","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["Efficient sparse-matrix multi-vector product on GPUs"],"prefix":"10.1145","author":[{"given":"Changwan","family":"Hong","sequence":"first","affiliation":[{"name":"The Ohio State University"}]},{"given":"Aravind","family":"Sukumaran-Rajam","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"Bortik","family":"Bandyopadhyay","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"Jinsung","family":"Kim","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"S\u00fcreyya Emre","family":"Kurt","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"Israt","family":"Nisa","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"Shivani","family":"Sabhlok","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"\u00dcmit V.","family":"\u00c7ataly\u00fcrek","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology"}]},{"given":"Srinivasan","family":"Parthasarathy","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[{"name":"The Ohio State University"}]}],"member":"320","published-online":{"date-parts":[[2018,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"The API reference guide for cuSPARSE the CUDA sparse matrixlibrary.(v8.0 ed.). http:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html. (2018).  The API reference guide for cuSPARSE the CUDA sparse matrixlibrary.(v8.0 ed.). http:\/\/docs.nvidia.com\/cuda\/cusparse\/index.html. (2018)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.125"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Symposium on High Performance Computing. Society for Computer Simulation International, 75--82","author":"Anzt Hartwig","year":"2015","unstructured":"Hartwig Anzt , Stanimire Tomov , and Jack Dongarra . 2015 . Accelerating the LOBPCG method on GPUs using a blocked Sparse Matrix Vector Product . In Proceedings of the Symposium on High Performance Computing. Society for Computer Simulation International, 75--82 . Hartwig Anzt, Stanimire Tomov, and Jack Dongarra. 2015. Accelerating the LOBPCG method on GPUs using a blocked Sparse Matrix Vector Product. In Proceedings of the Symposium on High Performance Computing. Society for Computer Simulation International, 75--82."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.69"},{"key":"e_1_3_2_1_5_1","unstructured":"Zhaojun Bai James Demmel Jack Dongarra Axel Ruhe and Henk van der Vorst. 2000. Templates for the solution of algebraic eigenvalue problems: a practical guide. SIAM.   Zhaojun Bai James Demmel Jack Dongarra Axel Ruhe and Henk van der Vorst. 2000. Templates for the solution of algebraic eigenvalue problems: a practical guide. SIAM."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/040608088"},{"key":"e_1_3_2_1_7_1","volume-title":"Sparse Matrix Format Selection with Multiclass SVM for SpMV on GPU. In 2016 45th International Conference on Parallel Processing (ICPP). 496--505","author":"Benatia A.","unstructured":"A. Benatia , W. Ji , Y. Wang , and F. Shi . 2016 . Sparse Matrix Format Selection with Multiclass SVM for SpMV on GPU. In 2016 45th International Conference on Parallel Processing (ICPP). 496--505 . A. Benatia, W. Ji, Y. Wang, and F. Shi. 2016. Sparse Matrix Format Selection with Multiclass SVM for SpMV on GPU. In 2016 45th International Conference on Parallel Processing (ICPP). 496--505."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536313"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11075-012-9564-z"},{"key":"e_1_3_2_1_10_1","volume-title":"BigLearn workshop, NIPS.","author":"Canny John","year":"2013","unstructured":"John Canny and Huasha Zhao . 2013 . Bidmach: Large-scale learning with zero memory allocation . In BigLearn workshop, NIPS. John Canny and Huasha Zhao. 2013. Bidmach: Large-scale learning with zero memory allocation. In BigLearn workshop, NIPS."},{"key":"e_1_3_2_1_11_1","unstructured":"SuiteSparse Matrix Collection. 2011. https:\/\/sparse.tamu.edu. (2011).  SuiteSparse Matrix Collection. 2011. https:\/\/sparse.tamu.edu. (2011)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2015.55"},{"key":"e_1_3_2_1_13_1","volume-title":"Cusp: Generic parallel algorithms for sparse matrix and graph computations. URL: http:\/\/cusplibrarygithub.io\/(accessed: 01.02.2016)","author":"Dalton Steven","year":"2014","unstructured":"Steven Dalton , Nathan Bell , Luke Olson , and Michael Garland . 2014 . Cusp: Generic parallel algorithms for sparse matrix and graph computations. URL: http:\/\/cusplibrarygithub.io\/(accessed: 01.02.2016) (2014). Steven Dalton, Nathan Bell, Luke Olson, and Michael Garland. 2014. Cusp: Generic parallel algorithms for sparse matrix and graph computations. URL: http:\/\/cusplibrarygithub.io\/(accessed: 01.02.2016) (2014)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1656274.1656278"},{"key":"e_1_3_2_1_16_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv.1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han , HuiziMao, and William J Dally . 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv.1510.00149 ( 2015 ). Song Han, HuiziMao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv.1510.00149 (2015)."},{"key":"e_1_3_2_1_17_1","volume-title":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking. arXiv preprint arXiv","author":"Jia Zhe","year":"1804","unstructured":"Zhe Jia , Marco Maggioni , Benjamin Staiger , and Daniele P Scarpazza . 2018. Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking. arXiv preprint arXiv : 1804 .06826 (2018). Zhe Jia, Marco Maggioni, Benjamin Staiger, and Daniele P Scarpazza. 2018. Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking. arXiv preprint arXiv: 1804.06826 (2018)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2010.05.034"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827500366124"},{"key":"e_1_3_2_1_20_1","volume-title":"2016 24th Euromicro International Conference on. IEEE, 448--455","author":"Konstantinidis Elias","year":"2016","unstructured":"Elias Konstantinidis and Yiannis Cotronis . 2016 . A quantitative performance evaluation of fast on-chip memories of GPUs. In Parallel, Distributed, and Network-Based Processing (PDP) , 2016 24th Euromicro International Conference on. IEEE, 448--455 . Elias Konstantinidis and Yiannis Cotronis. 2016. A quantitative performance evaluation of fast on-chip memories of GPUs. In Parallel, Distributed, and Network-Based Processing (PDP), 2016 24th Euromicro International Conference on. IEEE, 448--455."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038037.1941587"},{"key":"e_1_3_2_1_22_1","volume-title":"CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. CoRR abs\/1503.05032","author":"Liu Weifeng","year":"2015","unstructured":"Weifeng Liu and Brian Vinter . 2015. CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. CoRR abs\/1503.05032 ( 2015 ). http:\/\/arxiv.org\/abs\/1503.05032 Weifeng Liu and Brian Vinter. 2015. CSR5: an efficient storage format for cross-platform sparse matrix-vector multiplication. CoRR abs\/1503.05032 (2015). http:\/\/arxiv.org\/abs\/1503.05032"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2015.06.010"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2011.07.020"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851190"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1137\/100799265"},{"key":"e_1_3_2_1_27_1","first-page":"31","article-title":"Cublas library. NVIDIA Corporation, Santa Clara","volume":"15","author":"Nvidia CUDA","year":"2008","unstructured":"CUDA Nvidia . 2008 . Cublas library. NVIDIA Corporation, Santa Clara , California 15 , 27 (2008), 31 . CUDA Nvidia. 2008. Cublas library. NVIDIA Corporation, Santa Clara, California 15, 27 (2008), 31.","journal-title":"California"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt038"},{"key":"e_1_3_2_1_29_1","volume-title":"Hai Li, Yiran Chen, and Pradeep Dubey. Faster CNNs with Direct Sparse Convolutions and Guided Pruning.","author":"Park Jongsoo","year":"2016","unstructured":"Jongsoo Park , Sheng Li , Wei Wen , Ping Tak Peter Tang , Hai Li, Yiran Chen, and Pradeep Dubey. Faster CNNs with Direct Sparse Convolutions and Guided Pruning. ( 2016 ). arXiv:1608.01409 arXiv:1608.01409v5. Jongsoo Park, Sheng Li, Wei Wen, Ping Tak Peter Tang, Hai Li, Yiran Chen, and Pradeep Dubey. Faster CNNs with Direct Sparse Convolutions and Guided Pruning. (2016). arXiv:1608.01409 arXiv:1608.01409v5."},{"key":"e_1_3_2_1_30_1","volume-title":"Block Krylov methods to solve adjoint problems in aerodynamic design optimization. AIAA journal","author":"Pinel Xavier","year":"2013","unstructured":"Xavier Pinel and Marc Montagnac . 2013. Block Krylov methods to solve adjoint problems in aerodynamic design optimization. AIAA journal ( 2013 ). Xavier Pinel and Marc Montagnac. 2013. Block Krylov methods to solve adjoint problems in aerodynamic design optimization. AIAA journal (2013)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079086"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130281"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2010.208"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.99"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2010.17"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3152"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.04.001"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2692916.2555255"}],"event":{"name":"HPDC '18: The 27th International Symposium on High-Performance Parallel and Distributed Computing","location":"Tempe Arizona","acronym":"HPDC '18","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3208040.3208062","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3208040.3208062","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3208040.3208062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:08:06Z","timestamp":1750212486000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3208040.3208062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,11]]},"references-count":39,"alternative-id":["10.1145\/3208040.3208062","10.1145\/3208040"],"URL":"https:\/\/doi.org\/10.1145\/3208040.3208062","relation":{},"subject":[],"published":{"date-parts":[[2018,6,11]]},"assertion":[{"value":"2018-06-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}