{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:32:22Z","timestamp":1780356742281,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpds.2022.3177291","type":"journal-article","created":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T19:41:29Z","timestamp":1654285289000},"page":"3977-3989","source":"Crossref","is-referenced-by-count":15,"title":["VCSR: An Efficient GPU Memory-Aware Sparse Format"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3849-4918","authenticated-orcid":false,"given":"Elmira","family":"Karimi","sequence":"first","affiliation":[{"name":"ECE Department, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas Bohm","family":"Agostini","sequence":"additional","affiliation":[{"name":"ECE Department, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7144-7190","authenticated-orcid":false,"given":"Shi","family":"Dong","sequence":"additional","affiliation":[{"name":"ECE Department, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5692-0151","authenticated-orcid":false,"given":"David","family":"Kaeli","sequence":"additional","affiliation":[{"name":"ECE Department, Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830830"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446081"},{"key":"ref33","article-title":"Sparse matrix vector processing formats","author":"stathis","year":"2004"},{"key":"ref32","first-page":"214","article-title":"A sparse matrix library in C$++$++ for high performance architectures","author":"dongarraxz","year":"1994","journal-title":"Proc 2nd Object Oriented Numerics Conf"},{"key":"ref31","article-title":"SPARSKIT: A basic toolkit for sparse matrix computations","author":"saad","year":"1990","journal-title":"NASA Tech Rep Server"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.07.002"},{"key":"ref37","article-title":"NVIDIA Tesla V100 GPU Architecture","year":"2017"},{"key":"ref36","article-title":"Toolkit Documentation v7. 0","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2015.7054183"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/62038.62043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.211"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref12","article-title":"NVIDIA's next generation CUDA compute architecture: Kepler Gk110","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/275323.275327"},{"key":"ref14","article-title":"ITPACKV 2D user's guide","author":"kincaid","year":"1989","journal-title":"Center for Numerical Analysis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3017994"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.271"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2011.08.003"},{"key":"ref18","article-title":"Implementing a sparse matrix vector product for the SELL-C\/SELL-C-$\\sigma$? formats on NVIDIA GPUs","author":"anzt","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2528\/PIER11031607"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3226228"},{"key":"ref4","article-title":"Efficient sparse matrix-vector multiplication on CUDA","author":"bell","year":"2008"},{"key":"ref27","article-title":"cuSPARSE Library","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1094342004041296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.68"},{"key":"ref5","first-page":"211","article-title":"Optimization of sparse matrix-vector multiplication for CSR format on NVIDIA Kepler architecture GPUs","author":"mukunoki","year":"2013","journal-title":"Proc Int Conf Comput Sci Appl"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03138-0_32"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1658"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/130930352"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2010.02.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079086"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1837853.1693471"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.57"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2009.21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SNPD.2012.20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/17445760802337010"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9790018\/09787804.pdf?arnumber=9787804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T19:57:04Z","timestamp":1663617424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9787804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3177291","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}