{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:17:03Z","timestamp":1730225823306,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"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":[[2023,9,25]]},"DOI":"10.1109\/hpec58863.2023.10363476","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T14:39:57Z","timestamp":1703515197000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Build Energy-Efficient GPU Computing Environment for Machine Learning Algorithms with Register File Packing Technique"],"prefix":"10.1109","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[{"name":"Virginia Commonwealth University,Department of Electrical and Computer Engineering,Richmond,VA,23284"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Louisville,Department of Electrical and Computer Engineering,Louisville,KY,40292"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1400181.1400197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.05.014"},{"key":"ref3","article-title":"Gpgpu: General purpose computing on graphics hardware","volume-title":"Pushpaks Home Page","author":"Karnick","year":"2008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref5","first-page":"63","article-title":"Nvidias next generation cuda compute architecture: Fermi","volume":"26","year":"2009","journal-title":"Comput. Syst"},{"article-title":"Nvidias next generation cuda compute architecture: Kepler gk110","volume-title":"Technical report","year":"2012","key":"ref6"},{"volume-title":"Pascal gpu architecture","year":"2016","key":"ref7"},{"article-title":"V100 gpu architecture http:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper-v1.O.pdf","volume-title":"NVIDIA","year":"2017","key":"ref8"},{"journal-title":"NVIDIA","article-title":"Nvidia turing gpu architecture whitepaper","year":"2018","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1815998"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485964"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2611758"},{"key":"ref13","first-page":"1379","article-title":"Dynamic network surgery for efficient dnns","author":"Guo","year":"2016","journal-title":"Advances In Neural Information Processing Systems"},{"key":"ref14","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.31"},{"key":"ref16","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv preprint"},{"journal-title":"Training skinny deep neural networks with iterative hard thresholding methods","year":"2016","author":"Jin","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286215"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2004.10007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.1999.744314"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2011.6105405"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref25","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and\u00a1 0.5 mb model size","author":"Iandola","year":"2016","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547526"}],"event":{"name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2023,9,25]]},"location":"Boston, MA, USA","end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10363430\/10363422\/10363476.pdf?arnumber=10363476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T16:16:31Z","timestamp":1705076191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10363476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/hpec58863.2023.10363476","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}