{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:12:55Z","timestamp":1730297575275,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T00:00:00Z","timestamp":1662336000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T00:00:00Z","timestamp":1662336000000},"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":[],"published-print":{"date-parts":[[2022,9,5]]},"DOI":"10.1109\/socc56010.2022.9908120","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T16:23:18Z","timestamp":1665418998000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Cache-locality Based Adaptive Warp Scheduling for Neural Network Acceleration on GPGPUs"],"prefix":"10.1109","author":[{"given":"Weiming","family":"Hu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Glenfly Tech Co., Ltd.,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Quan","sequence":"additional","affiliation":[{"name":"Glenfly Tech Co., Ltd.,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Glenfly Tech Co., Ltd.,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056024"},{"key":"ref15","first-page":"230","article-title":"Dynamic selective warp scheduling for GPUs using L1 data cache locality information","author":"kim","year":"2018","journal-title":"Proceedings of the International Conference on Parallel and Distributed Computing Applications and Technologies (PDCAT)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2636225"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref19","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"journal-title":"CUDA Application Design and Development","year":"2011","author":"farber","key":"ref4"},{"article-title":"Parboil: A revised benchmark suite for scientific and commercial throughput computing","year":"2012","author":"stratton","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155656"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref21","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Rep"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3300053.3319418"},{"article-title":"Squeezenet: AlexNet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size","year":"2016","author":"iandola","key":"ref23"}],"event":{"name":"2022 IEEE 35th International System-on-Chip Conference (SOCC)","start":{"date-parts":[[2022,9,5]]},"location":"Belfast, United Kingdom","end":{"date-parts":[[2022,9,8]]}},"container-title":["2022 IEEE 35th International System-on-Chip Conference (SOCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9907764\/9908069\/09908120.pdf?arnumber=9908120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T15:02:34Z","timestamp":1675090954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9908120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/socc56010.2022.9908120","relation":{},"subject":[],"published":{"date-parts":[[2022,9,5]]}}}