{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:52:23Z","timestamp":1764834743979,"version":"3.46.0"},"reference-count":58,"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-pad66369.2025.00028","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:39:34Z","timestamp":1764787174000},"page":"215-226","source":"Crossref","is-referenced-by-count":0,"title":["A Framework for Analytical Performance and Energy Prediction of DL Training on GPUs"],"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"}]},{"given":"Petr","family":"Dokladal","sequence":"additional","affiliation":[{"name":"Mines Paris - PSL,Centre de Morphologie Mathématique (CMM),Fontainebleau,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youssef","family":"Mesri","sequence":"additional","affiliation":[{"name":"Mines Paris - PSL,Centre de Mise en Forme de Matériaux (CEMEF),Sophia Antipolis,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sustainable ai: Environmental implications, challenges and opportunities","volume":"abs\/2111.00364","author":"Wu","year":"2021","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3148714"},{"issue":"09","key":"ref3","first-page":"13 693","article-title":"Energy and policy considerations for modern deep learning research","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"34","author":"Strubell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"issue":"9","key":"ref5","first-page":"100340","article-title":"The real climate and transformative impact of ict: A critique of estimates, trends, and regulations","volume-title":"Patterns","volume":"2","author":"Freitag","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658542"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/1094342015597083"},{"key":"ref8","article-title":"High performance computing as a combination of machines and methods and programming","volume-title":"Ph.D. dissertation","author":"Tadonki","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-80126-7_35"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS49563.2019.00007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/a:1008202821328"},{"key":"ref13","article-title":"Learning multiple layers of features from tiny images","volume-title":"Master\u2019s thesis","author":"Krizhevsky","year":"2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"Merity","key":"ref16"},{"key":"ref17","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"CoRR","volume":"abs\/1909.11942","author":"Lan","year":"2019"},{"key":"ref18","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"ArXiv:1910.01108"},{"article-title":"Deep residual learning for image recognition","year":"2015","author":"He","key":"ref19"},{"article-title":"Tinyllama: An open-source small language model","year":"2024","author":"Zhang","key":"ref20"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"ref21"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"Dosovitskiy","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PADW64858.2024.00014"},{"year":"2008","key":"ref24","article-title":"scipy.optimize.differential_evolution"},{"year":"2022","key":"ref25","article-title":"Running average power limit energy reporting \/ cve-2020-8694 , cve-2020-8695 \/ intel-sa-00389"},{"year":"2023","key":"ref26","article-title":"Energy estimates"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2014.6968672"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2010.38"},{"volume-title":"Welcome to pyjoules\u2019s documentation","year":"2019","key":"ref29"},{"year":"2020","key":"ref30","article-title":"Codecarbon"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1134\/s1064562422060230"},{"issue":"3","key":"ref32","article-title":"Towards an energy consumption index for deep learning models: A comparative analysis of architectures, gpus, and measurement tools","volume-title":"Sensors","volume":"25","author":"Aquino-Br\u00edtez","year":"2025"},{"issue":"11","key":"ref33","article-title":"Openzmeter: An efficient low-cost energy smart meter and power quality analyzer","volume-title":"Sustainability","volume":"10","author":"Viciana","year":"2018"},{"article-title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models","volume-title":"ICML Workshop on Challenges in Deploying and monitoring Machine Learning Systems","author":"Anthony","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.13630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref37","article-title":"Deep residual learning for image recognition","volume-title":"CoRR","volume":"abs\/1512.03385","author":"He","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-66146-4_3"},{"key":"ref39","first-page":"819","article-title":"Batchsizer: Power-performance trade-off for dnn inference","volume-title":"2021 26th Asia and South Pacific Design Automation Conference (ASP-DAC)","author":"Nabavinejad"},{"key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3192515"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.70777\/si.v2i3.15155","article-title":"Trends in frontier ai model count: A forecast to 2028","author":"Kumar","year":"2025"},{"article-title":"Training compute-optimal large language models","year":"2022","author":"Hoffmann","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC56579.2022.00008"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/DLS51937.2020.00007"},{"article-title":"Paleo: A performance model for deep neural networks","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Qi","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707265"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/GREENCOMP.2010.5598316"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810108"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.05.211"},{"key":"ref51","first-page":"12","article-title":"Evaluating the effectiveness of model-based power characterization","volume-title":"Proceedings of the 2011 USENIX Conference on USENIX Annual Technical Conference","author":"McCullough"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-015-0298-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-014-0264-x"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00125"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD60044.2023.00017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.23919\/WiOpt56218.2022.9930584"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ccgrid49817.2020.00-45"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-021-03428-8"}],"event":{"name":"2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","start":{"date-parts":[[2025,10,28]]},"location":"Bonito, Mato Grosso do Sul, Brazil","end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 IEEE\/SBC 37th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11264602\/11264604\/11264638.pdf?arnumber=11264638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:50:15Z","timestamp":1764834615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/sbac-pad66369.2025.00028","relation":{},"subject":[],"published":{"date-parts":[[2025,10,28]]}}}