{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:27:17Z","timestamp":1765254437190,"version":"3.34.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":"NSF CAREER","award":["2146509"],"award-info":[{"award-number":["2146509"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpds.2024.3522776","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:39:04Z","timestamp":1735155544000},"page":"422-436","source":"Crossref","is-referenced-by-count":1,"title":["High Performance Householder QR Factorization on Emerging GPU Architectures Using Tensor Cores"],"prefix":"10.1109","volume":"36","author":[{"given":"Yuhan","family":"Leng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Gaoyuan","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1859-3580","authenticated-orcid":false,"given":"Panruo","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Univeristy of Houston, Houston, TX, USA"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3369583.3392685"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.15"},{"year":"2017","key":"ref5","article-title":"Nvidia tesla v100 GPU architecture"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2971677"},{"year":"2023","key":"ref7","article-title":"Nvidia h100 tensor core GPU architecture"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00071"},{"article-title":"Dissecting the NVIDIA volta GPU architecture via microbenchmarking","year":"2018","author":"Jia","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508408"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221136848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HiPCW.2018.8634417"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3331057"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532392"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392770"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/10943420221090256"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241239588"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/0908009"},{"article-title":"Magma users\u2019 guide","year":"2011","author":"Tomov","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3061709"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.91"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2017.10.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/14M0973773"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/18M1218212"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/16m1081270"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/13092157X"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1504\/ijris.2017.10009618"},{"article-title":"TSQR on tensor cores","volume-title":"Proc. 29th Int. Conf. High Perform. Comput., Netw., Storage, Anal.","author":"Ootomo","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48311-X_158"},{"article-title":"An overview of block gram-schmidt methods and their stability properties","year":"2020","author":"Carson","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00211-005-0615-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.14708\/ma.v2i2.1048"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF01934122"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"article-title":"Analysis of randomized householder-cholesky QR factorization with multisketching","year":"2023","author":"Higgins","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.120"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926256"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/22M1514817"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/19M1289546"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3473522"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/10850501\/10816084-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10850501\/10816084.pdf?arnumber=10816084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:10:43Z","timestamp":1738177843000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":48,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3522776","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}