{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:16:34Z","timestamp":1781021794538,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"AMD"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,10,1]]},"DOI":"10.1109\/tpds.2021.3067825","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T19:57:35Z","timestamp":1616443055000},"page":"2448-2463","source":"Crossref","is-referenced-by-count":10,"title":["Spartan: A Sparsity-Adaptive Framework to Accelerate Deep Neural Network Training on GPUs"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7144-7190","authenticated-orcid":false,"given":"Shi","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3532-6521","authenticated-orcid":false,"given":"Yifan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1855-3810","authenticated-orcid":false,"given":"Nicolas Bohm","family":"Agostini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elmira","family":"Karimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Lowell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2243-389X","authenticated-orcid":false,"given":"Jose","family":"Cano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3550-720X","authenticated-orcid":false,"given":"Jose L.","family":"Abellan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5692-0151","authenticated-orcid":false,"given":"David","family":"Kaeli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref38","article-title":"Nvidia tesla V100 GPU architecture","year":"2017"},{"key":"ref33","article-title":"Mixed precision training","author":"micikevicius","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"MIOpen: An open source library for deep learning primitives","author":"khan","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/0613024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2018.00034"},{"key":"ref37","article-title":"Radeon(TM) RX Vega56 Graphics","year":"2017"},{"key":"ref36","article-title":"AMD GCN3 ISA architecture manual","year":"2016"},{"key":"ref35","first-page":"2","article-title":"The design space of data-parallel memory systems","author":"ahn","year":"2006","journal-title":"Proc ACM\/IEEE Conf Supercomputing"},{"key":"ref34","author":"gaster","year":"2013","journal-title":"Heterogeneous Computing with OpenCL Revised OpenCL 2nd ed"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref2","first-page":"1","author":"ouyang","year":"2014","journal-title":"Proc IEEE Hot Chips 26 Symp"},{"key":"ref1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref20","article-title":"rocSPARSE","year":"2019"},{"key":"ref22","first-page":"1146","article-title":"Improving the performance of the sparse matrix vector product with GPUS","author":"vuez","year":"2010","journal-title":"Proc 10th IEEE Int Conf Comput Inf Technol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3184407.3184423"},{"key":"ref24","article-title":"clSPARSE","year":"2016"},{"key":"ref23","article-title":"A systematic survey of general sparse matrix-matrix multiplication","author":"gao","year":"2020"},{"key":"ref26","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00908"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00070"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00017"},{"key":"ref40","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322271"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS.2019.8771562"},{"key":"ref16","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","article-title":"cuBLAS","year":"2019"},{"key":"ref18","article-title":"rocBLAS","year":"2019"},{"key":"ref19","article-title":"cuSPARSE","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"ref6","article-title":"Nvidia DGX-2 the world most powerful deep learning system for the most complex AI challenges","year":"2019"},{"key":"ref5","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref7","article-title":"Radeon instinct (TM) MI60 accelerator","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080215"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910864"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038239"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573503"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293898"},{"key":"ref42","article-title":"Amd radeon instinct mi6 accelerator","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"ref44","article-title":"AMD app SDK 3.0 getting started","year":"2017"},{"key":"ref43","article-title":"A guide to convolution arithmetic for deep learning","author":"dumoulin","year":"2016"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9399068\/09382871.pdf?arnumber=9382871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:24Z","timestamp":1652194224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9382871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,1]]},"references-count":53,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3067825","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":[[2021,10,1]]}}}