{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:35:26Z","timestamp":1777653326404,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["2023JJ40679"],"award-info":[{"award-number":["2023JJ40679"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004761","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["2024JJ6470"],"award-info":[{"award-number":["2024JJ6470"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tpds.2025.3616981","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:40:28Z","timestamp":1759340428000},"page":"2652-2667","source":"Crossref","is-referenced-by-count":1,"title":["SSpMM: Efficiently\n                    <u>S<\/u>\n                    calable\n                    <u>SpMM<\/u>\n                    Kernels Across Multiple Generations of Tensor Cores"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6374-2916","authenticated-orcid":false,"given":"Zeyu","family":"Xue","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5875-3297","authenticated-orcid":false,"given":"Mei","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7016-7672","authenticated-orcid":false,"given":"Jianchao","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7718-3085","authenticated-orcid":false,"given":"Minjin","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7120-9729","authenticated-orcid":false,"given":"Zhongdi","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3854-5336","authenticated-orcid":false,"given":"Jing","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5786-3171","authenticated-orcid":false,"given":"Yang","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1552-8396","authenticated-orcid":false,"given":"Zhaoyun","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6233-6800","authenticated-orcid":false,"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Langguth","sequence":"additional","affiliation":[{"name":"Simula Research Laboratory, Oslo, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626303"},{"key":"ref3","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00077"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3067825"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3154387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3324934"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530508"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00076"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3249110"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3177291"},{"key":"ref31","article-title":"Deep learning matrix collection (DLMC)","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref33","first-page":"149","article-title":"TC-GNN: Bridging sparse GNN computation and dense tensor cores on GPUs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3477746"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3288520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref38","first-page":"3299","article-title":"meProp: Sparsified back propagation for accelerated deep learning with reduced overfitting","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3098483"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref42","article-title":"Exploring the regularity of sparse structure in convolutional neural networks","author":"Mao","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref44","first-page":"1387","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00189"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2953852"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651378"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218644"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","article-title":"Long range arena: A benchmark for efficient transformers","author":"Tay","year":"2020"},{"key":"ref52","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96983-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040150"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3452478"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3225230"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208062"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00085"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00057"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569667"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00071"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2020.106848"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530588"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IA356718.2022.00009"},{"key":"ref66","first-page":"513","article-title":"Efficient GPU kernels for N:M-SPARSE weights in deep learning","volume-title":"Proc. Mach. Learn. Syst.","author":"Lin","year":"2023"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11205816\/11189050.pdf?arnumber=11189050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:51:28Z","timestamp":1763146288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11189050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":59,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3616981","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":[[2025,12]]}}}