{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:14:03Z","timestamp":1772694843454,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2023YFB3001705"],"award-info":[{"award-number":["2023YFB3001705"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20461,62472160,62572180,2024JJ7375"],"award-info":[{"award-number":["U21A20461,62472160,62572180,2024JJ7375"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012269","name":"Aid Program for Science and Technology Innovative Research Team in Higher Educational Institutions of Hunan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006433","name":"Future of Computing, a Barcelona Supercomputing Center and IBM initiative","doi-asserted-by":"publisher","award":["PID2023-146511NB-I00"],"award-info":[{"award-number":["PID2023-146511NB-I00"]}],"id":[{"id":"10.13039\/501100006433","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Spanish Ministry of Science, Innovation and Universities","doi-asserted-by":"publisher","award":["MCIU \/AEI \/10.13039\/501100011033"],"award-info":[{"award-number":["MCIU \/AEI \/10.13039\/501100011033"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"EU ERDF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408479","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-16","source":"Crossref","is-referenced-by-count":0,"title":["Swift: High-Performance Sparse-Dense Matrix Multiplication on GPUs"],"prefix":"10.1109","author":[{"given":"Jinyu","family":"Hu","sequence":"first","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huizhang","family":"Luo","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Jiang","sequence":"additional","affiliation":[{"name":"UT Arlington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Casas","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chubo","family":"Liu","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"issue":"1","key":"ref2","first-page":"1959","article-title":"Sparse factor analysis for learning and content analytics","volume":"15","author":"Lan","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref3","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281714"},{"key":"ref6","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281719"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640427"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638470"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295727"},{"key":"ref12","article-title":"Gpu performance analysis and optimization","volume-title":"GPU technology conference","volume":"3","author":"Micikevicius","year":"2012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295704"},{"key":"ref14","first-page":"445","article-title":"Sparse matrix storage format","volume-title":"Proceedings of the 16th Annual workshop on circuits, systems and signal processing","author":"Smailbegovic","year":"2005"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2017.00039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/sc41405.2020.00076"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref21","article-title":"Cusparse library","volume-title":"GPU Technology Conference","volume":"12","author":"Naumov","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5121\/acij.2012.3109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2015.7054183"},{"issue":"4","key":"ref27","first-page":"1","article-title":"Evaluation of the performance of gpu global memory coalescing","volume":"4","author":"Kim","year":"2017","journal-title":"Evaluation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473837"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3177291"},{"key":"ref30","volume-title":"Scan primitives for gpu computing","author":"Sengupta","year":"2007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589054"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00081"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536313"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/sc.2014.68"},{"key":"ref35","first-page":"75","article-title":"Accelerating the lobpcg method on gpus using a blocked sparse matrix vector product","volume-title":"SpringSim (HPS)","author":"Anzt","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.73"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827595287997"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628087"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3688612"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3687480"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3665896"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CIC58953.2023.00012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxt038"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00076"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605632"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1145\/3489517.3530508","article-title":"Heuristic adaptability to input dynamics for spmm on gpus","volume-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference","author":"Dai","year":"2022"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408479.pdf?arnumber=11408479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:35:22Z","timestamp":1772692522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408479","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}