{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:25:29Z","timestamp":1764656729893,"version":"3.46.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"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":[[2025,10,28]]},"DOI":"10.1109\/sbac-padw69789.2025.00024","type":"proceedings-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:24:09Z","timestamp":1764613449000},"page":"116-123","source":"Crossref","is-referenced-by-count":0,"title":["Energy-Aware Deep Learning on GPUs through Parameter Sharing and Mixed Precision Training"],"prefix":"10.1109","author":[{"given":"Roblex Nana","family":"Tchakoute","sequence":"first","affiliation":[{"name":"Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claude","family":"Tadonki","sequence":"additional","affiliation":[{"name":"Mines Paris - PSL,Centre de Recherche en Informatique (CRI),Fontainebleau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Carbon emissions and large neural network training","volume":"abs\/2104.10350","author":"Patterson","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"article-title":"Quantifying the carbon emissions of machine learning","year":"2019","author":"Lacoste","key":"ref3"},{"key":"ref4","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume":"abs\/1909.11942","author":"Lan","year":"2019","journal-title":"CoRR"},{"article-title":"Mixed precision training","year":"2018","author":"Micikevicius","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"article-title":"Low-memory neural network training: A technical report","year":"2022","author":"Sohoni","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3467017"},{"key":"ref10","article-title":"Energy concerns with hpc systems and applications","volume":"abs\/2309.08615","author":"Nana","year":"2023"},{"article-title":"Codecarbon","year":"2020","author":"GAMM","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PADW64858.2024.00014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GREENCOMP.2010.5598316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-014-0264-x"},{"key":"ref16","first-page":"119","article-title":"Zeus: Understanding and optimizing GPU energy consumption of DNN training","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sustainlp-1.5"},{"key":"ref18","article-title":"Learning multiple layers of features from tiny images","volume-title":"Master\u2019s thesis","author":"Krizhevsky","year":"2009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"Merity","key":"ref21"},{"article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref24","article-title":"Tinyllama: An open-source small language model","volume":"abs\/2401.02385","author":"Zhang","year":"2024"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"ref25"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"Dosovitskiy","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e38137"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2592784.2592786"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3438264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-017-0897-1"}],"event":{"name":"2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)","start":{"date-parts":[[2025,10,28]]},"location":"Bonito, Brazil","end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11264603\/11264609\/11264704.pdf?arnumber=11264704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T06:23:19Z","timestamp":1764656599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/sbac-padw69789.2025.00024","relation":{},"subject":[],"published":{"date-parts":[[2025,10,28]]}}}