{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:31:51Z","timestamp":1740169911142,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Electronics Co., Ltd"},{"name":"Ministry of Science and ICT","award":["IITP-2021-2018-0-01433"],"award-info":[{"award-number":["IITP-2021-2018-0-01433"]}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["2017M3A9G8084463"],"award-info":[{"award-number":["2017M3A9G8084463"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2022,7,1]]},"DOI":"10.1109\/tetc.2021.3089848","type":"journal-article","created":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T19:58:35Z","timestamp":1624046315000},"page":"1428-1442","source":"Crossref","is-referenced-by-count":3,"title":["AutoRelax: HW-SW Co-Optimization for Efficient SpGEMM Operations With Automated Relaxation in Deep Learning"],"prefix":"10.1109","volume":"10","author":[{"given":"Sehun","family":"Park","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5175-8258","authenticated-orcid":false,"given":"Jae-Joon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Creative Engineering, Pohang University of Science & Technology (POSTECH), Pohang, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2027-8531","authenticated-orcid":false,"given":"Jaeha","family":"Kung","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu, South Korea"}]}],"member":"263","reference":[{"year":"2017","key":"ref1","article-title":"Volta GPU architecture"},{"key":"ref2","first-page":"9:1","article-title":"Scaling deep learning on GPU and knights landing clusters","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"You"},{"key":"ref3","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","volume":"abs\/1609.08144","author":"Wu","year":"2016","journal-title":"CoRR"},{"key":"ref4","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"article-title":"cuDNN: Efficient primitives for deep learning","year":"2014","author":"Chetlur","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"article-title":"Learning semantic image representations at a large scale","year":"2014","author":"Jia","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref11","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding","volume":"abs\/1510.00149","author":"Han","year":"2015","journal-title":"CoRR"},{"key":"ref12","first-page":"4860","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref13","first-page":"13681","article-title":"AutoPrune: Automatic network pruning by regularizing auxiliary parameters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref14","article-title":"Fast training of sparse graph neural networks on dense hardware","volume":"abs\/1906.11786","author":"Balog","year":"2019","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8341971"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref20","first-page":"1387","article-title":"Dynamic network surgery for efficient dnns","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref21","article-title":"Pruning filters for efficient Convnets","volume":"abs\/1608.08710","author":"Li","year":"2016","journal-title":"CoRR"},{"key":"ref22","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","volume":"abs\/1607.03250","author":"Hu","year":"2016","journal-title":"CoRR"},{"article-title":"Learned threshold pruning","year":"2020","author":"Azarian","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref25","first-page":"1","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai"},{"key":"ref26","first-page":"363","article-title":"OPTIMUS: Optimized matrix multiplication structure for transformer neural network accelerator","volume-title":"Proc. Mach. Learn. Syst.","author":"Park"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00030"},{"key":"ref30","article-title":"WRPN: wide reduced-precision networks","volume":"abs\/1709.01134","author":"Mishra","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2016.2573586"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317879"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"article-title":"TIMIT acoustic-phonetic continuous speech corpus","year":"1993","author":"Garofolo","key":"ref34"},{"article-title":"CIFAR-10 (Canadian Institute for Advanced Research)","year":"2010","author":"Krizhevsky","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","article-title":"Deep residual learning for image recognition","volume":"abs\/1512.03385","author":"He","year":"2015","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836233"},{"key":"ref39","article-title":"Language models are few-shot learners","volume":"abs\/2005.14165","author":"Brown","year":"2020","journal-title":"CoRR"},{"key":"ref40","first-page":"1","article-title":"Regularizing and optimizing LSTM language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Merity"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/30.320814"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714765"},{"key":"ref44","first-page":"602","article-title":"HitNet: Hybrid ternary recurrent neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"article-title":"Learning recurrent binary\/ternary weights","year":"2018","author":"Ardakani","key":"ref45"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245516\/9874959\/09460798.pdf?arnumber=9460798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:09:52Z","timestamp":1705014592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9460798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,1]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2021.3089848","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"type":"electronic","value":"2168-6750"},{"type":"electronic","value":"2376-4562"}],"subject":[],"published":{"date-parts":[[2022,7,1]]}}}