{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:56:02Z","timestamp":1781585762254,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Department of Sichuan Province","award":["25JBGS0053"],"award-info":[{"award-number":["25JBGS0053"]}]},{"DOI":"10.13039\/501100005408","name":"University of Electronic Science and Technology of China","doi-asserted-by":"publisher","award":["A1098531023601465"],"award-info":[{"award-number":["A1098531023601465"]}],"id":[{"id":"10.13039\/501100005408","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-SUMA Foundation","award":["CCF-GH OF 2024002"],"award-info":[{"award-number":["CCF-GH OF 2024002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpds.2026.3692274","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T19:50:53Z","timestamp":1778615453000},"page":"1790-1807","source":"Crossref","is-referenced-by-count":0,"title":["OSLA: A High Performance One-Sided Linear Algebra Library on GPU Architectures"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2481-0318","authenticated-orcid":false,"given":"Lu","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4231-3237","authenticated-orcid":false,"given":"Ruiyi","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaoyuan","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0035-2323","authenticated-orcid":false,"given":"Hansheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7721-7422","authenticated-orcid":false,"given":"Hancong","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9525-1659","authenticated-orcid":false,"given":"Shaoshuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Magma users\u2019 guide","author":"Tomov","year":"2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref5","first-page":"444","article-title":"Benchmarking the NVIDIA V100 GPUu and tensor cores","volume-title":"Proc. Eur. Conf. Parallel Process.","author":"Martineau"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241239588"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/nla.1680020208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/wics.18"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/1024100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2021.12.017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S0129053393000232"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/0909058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/0914063"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/080731992"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022326604210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0898-1221(95)00215-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/080731992"},{"key":"ref20","article-title":"Ozaki Scheme II: A GEMM-oriented emulation of floating-point matrix multiplication using an integer modular technique","author":"Ozaki","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038237"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718027.ch13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241239588"},{"key":"ref24","article-title":"TSQR on TensorCores","volume-title":"Proc. Int. Conf. High Perform. Computi. Netw. Storage Anal.","author":"Ootomo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3522776"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392685"},{"key":"ref27","first-page":"65","article-title":"Adaptive triangular system solving","volume-title":"Challenges in Symbolic Computation Software","author":"Dumas","year":"2006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/0908086"},{"key":"ref29","article-title":"SLATE users\u2019 guide no10","volume":"15","author":"Gates","year":"2020","journal-title":"Environments"},{"key":"ref30","article-title":"SLATE performance report: Updates to cholesky and LU factorizations","author":"YarKhan","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2011.6126599"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-385963-1.00034-4"},{"issue":"5","key":"ref34","first-page":"468","article-title":"Magma: Enabling exascale performance with accelerated blas and lapack for diverse GPU architectures","volume":"38","author":"Abdelfattah","year":"2024","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2818311"},{"key":"ref36","first-page":"70","article-title":"Matrix inversion using Cholesky decomposition","volume-title":"Proc. 2013 Signal Process.: Algorithms Architectures Arrangements Appl.","author":"Krishnamoorthy"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/18M1218212"},{"key":"ref38","first-page":"2408","article-title":"Optimizing neural networks with Kronecker-factored approximate curvature","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Martens"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2009.2017934"},{"key":"ref40","article-title":"Eigen","author":"Guennebaud","year":"2010"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3264491"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063393"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/14M0973773"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/18M1218212"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/16m1081270"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/13092157X"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.299"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11558584\/11516316.pdf?arnumber=11516316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:45:59Z","timestamp":1781585159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11516316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":48,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3692274","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":[[2026,8]]}}}