{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:29:37Z","timestamp":1771882177689,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB3001503"],"award-info":[{"award-number":["2023YFB3001503"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62421002"],"award-info":[{"award-number":["62421002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302505"],"award-info":[{"award-number":["62302505"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpds.2026.3664114","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:01:28Z","timestamp":1770930088000},"page":"905-919","source":"Crossref","is-referenced-by-count":0,"title":["mtGEMM: An Efficient GEMM Library for Modern Multi-Core DSPs"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3542-4869","authenticated-orcid":false,"given":"Jianbin","family":"Fang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kainan","family":"Yu","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\/0000-0001-8364-9793","authenticated-orcid":false,"given":"Peng","family":"Zhang","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\/0000-0001-6243-8479","authenticated-orcid":false,"given":"Dezun","family":"Dong","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\/0000-0001-8316-2934","authenticated-orcid":false,"given":"Xinxin","family":"Qi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Hou","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\/0000-0001-7952-3784","authenticated-orcid":false,"given":"Ruibo","family":"Wang","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\/0000-0003-2284-7897","authenticated-orcid":false,"given":"Kai","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"ref2","first-page":"1","article-title":"High performance convolutional neural networks for document processing","volume-title":"Proc. 10th Int. Workshop Front. Handwriting Recognit.","author":"Chellapilla"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icpp.2015.29"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/9781119086383.ch12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-015-1613-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063392"},{"key":"ref10","first-page":"70","article-title":"TSM2X: High-performance tall-and-skinny matrix\u2013matrix multiplication on GPUs","volume-title":"J. Parallel Distrib. Comput.","volume":"151","author":"Rivera","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/sc.2012.109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s42514-020-00057-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cluster51413.2022.00055"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00090"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2019.2906891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2905302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2200359"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1147\/rd.386.0673"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icpads.2012.97"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2017.19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.51"},{"key":"ref27","article-title":"NVIDIA CUTLASS: CUDA templates for linear algebra subroutines"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11454-5_15"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11396400\/11394784.pdf?arnumber=11394784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:49:48Z","timestamp":1771879788000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11394784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":28,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3664114","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":[[2026,4]]}}}