{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T11:34:16Z","timestamp":1791891256256,"version":"4.3.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tc.2022.3222955","type":"journal-article","created":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T19:58:11Z","timestamp":1671134291000},"page":"1733-1746","source":"Crossref","is-referenced-by-count":13,"title":["High-Performance Tensor Learning Primitives Using GPU Tensor Cores"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9532-1709","authenticated-orcid":false,"given":"Xiao-Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3890-5388","authenticated-orcid":false,"given":"Zeliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3884-2487","authenticated-orcid":false,"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering and Science, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2945-9240","authenticated-orcid":false,"given":"Xiaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1992-6068","authenticated-orcid":false,"given":"Anwar","family":"Walid","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"278","article-title":"NVIDIA research: Tensors are the future of deep learning","author":"kossaifi","year":"2021","journal-title":"Nvidia developers'"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref15","first-page":"442","article-title":"Tensorizing neural networks","author":"novikov","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3064182"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004354"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2937876"},{"key":"ref10","first-page":"550","article-title":"A distributed graph-theoretic framework for automatic parallelization in multi-core systems","volume":"3","author":"ma","year":"2021","journal-title":"Proc Mach Learn Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3624"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3157733"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOAS1228"},{"key":"ref51","first-page":"1","article-title":"Parallel training of DNNs with natural gradient and parameter averaging","author":"povey","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2020.106848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IA3.2016.010"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3071507"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2018.07.018"},{"key":"ref47","first-page":"15:1","article-title":"TTC: A high-performance compiler for tensor transpositions","volume":"44","author":"springer","year":"2017","journal-title":"ACM Trans Math Softw"},{"key":"ref42","article-title":"NVIDIA cuTensor library","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479896305696"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"ref43","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2016.031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3028495"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683383"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5807"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1515\/9783110365832"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2006.08.026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413527"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/105\/38002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441599"},{"key":"ref34","article-title":"Accelerating sparse deep neural networks","author":"mishra","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.1c00726"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3172895"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref30","first-page":"925","article-title":"TensorLy: Tensor learning in python","volume":"20","author":"kossaifi","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/19M1289546"},{"key":"ref2","first-page":"1","article-title":"High-performance computing primitives for tensor networks learning operations on GPUs","author":"liu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop Quantum Tensor Netw Mach Learn"},{"key":"ref1","first-page":"1","article-title":"cuTensor-CP: High performance third-order CP tensor decompositions on GPUs","author":"liu","year":"2020","journal-title":"Proc Int Joint Conf Artif Intell Workshop Tensor Netw Represenations Mach Learn"},{"key":"ref39","article-title":"Mnist handwritten digit database","volume":"2","author":"lecun","year":"2010","journal-title":"ATT Labs"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2653"},{"key":"ref24","article-title":"High performance tensor decompositions for compressing and accelerating deep neural networks","author":"liu","year":"2021","journal-title":"Book Tensors for Data Processing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8913"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975196"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2940192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.07.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3022353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3010724"},{"key":"ref28","article-title":"Tensorlab 3.0","author":"vervliet","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.12.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.08.055"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/10122189\/09987675.pdf?arnumber=9987675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:00:31Z","timestamp":1686592831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9987675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":52,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tc.2022.3222955","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}