{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:07Z","timestamp":1782546427898,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3801822","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"90-100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Much Energy Is Wasted in LLM operations? Evidence from Kernel-Level DVFS"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5475-9594","authenticated-orcid":false,"given":"Jeffrey","family":"Spaan","sequence":"first","affiliation":[{"name":"University of Twente, Enschede, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7110-921X","authenticated-orcid":false,"given":"Kuan-Hsun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Twente, Enschede, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4932-1900","authenticated-orcid":false,"given":"Ana-Lucia","family":"Varbanescu","sequence":"additional","affiliation":[{"name":"University of Twente, Enschede, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926317"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Ghazanfar Ali Mert Side Sridutt Bhalachandra Nicholas\u00a0J. Wright and Yong Chen. 2023. An automated and portable method for selecting an optimal GPU frequency. Future Generation Computer Systems 149 (2023) 71\u201388. 10.1016\/j.future.2023.07.011","DOI":"10.1016\/j.future.2023.07.011"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624756"},{"key":"e_1_3_3_2_5_2","volume-title":"AMD Raven Ridge APU: Delivering a new level of visual performance in an SoC","author":"Bouvier Dan","year":"2018","unstructured":"Dan Bouvier, Jim Gibney, Alex Branover, and Sonu Arora. 2018. AMD Raven Ridge APU: Delivering a new level of visual performance in an SoC. https:\/\/old.hotchips.org\/hc30\/1conf\/1.05_AMD_APU_AMD_Raven_HotChips30_Final.pdf"},{"key":"e_1_3_3_2_6_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 159, 25\u00a0pages."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"K.W. Cameron Rong Ge and Xizhou Feng. 2005. High-performance power-aware distributed computing for scientific applications. Computer 38 11 (2005) 40\u201347. 10.1109\/MC.2005.380","DOI":"10.1109\/MC.2005.380"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00078"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695970"},{"key":"e_1_3_3_2_10_2","unstructured":"Aaron\u00a0Grattafiori et al.2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Stijn Eyerman and Lieven Eeckhout. 2011. Fine-grained DVFS using on-chip regulators. ACM Trans. Archit. Code Optim. 8 1 Article 1 (Feb. 2011) 24\u00a0pages. 10.1145\/1952998.1952999","DOI":"10.1145\/1952998.1952999"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607055"},{"key":"e_1_3_3_2_13_2","unstructured":"Marius Hobbhahn Lennart Heim and G\u00f6k\u00e7e Aydos. 2023. Trends in machine learning hardware. https:\/\/epoch.ai\/blog\/trends-in-machine-learning-hardware"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/LPE.1994.573184"},{"key":"e_1_3_3_2_15_2","volume-title":"GTC March 2024 Keynote with NVIDIA CEO Jensen Huang","author":"Huang Jensen","year":"2024","unstructured":"Jensen Huang. 2024. GTC March 2024 Keynote with NVIDIA CEO Jensen Huang. Nvidia. https:\/\/www.youtube.com\/live\/Y2F8yisiS6E?t=1246s"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Andreas\u00a0Kosmas Kakolyris Dimosthenis Masouros Sotirios Xydis and Dimitrios Soudris. 2024. SLO-Aware GPU DVFS for Energy-Efficient LLM Inference Serving. IEEE Computer Architecture Letters 23 2 (2024) 150\u2013153. 10.1109\/LCA.2024.3406038","DOI":"10.1109\/LCA.2024.3406038"},{"key":"e_1_3_3_2_17_2","unstructured":"Nitish\u00a0Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak\u00a0Peter Tang. 2017. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arxiv:https:\/\/arXiv.org\/abs\/1609.04836\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1609.04836"},{"key":"e_1_3_3_2_18_2","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv:https:\/\/arXiv.org\/abs\/1412.6980\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4492-2_8"},{"key":"e_1_3_3_2_20_2","series-title":"(HotPower\u201910)","first-page":"1","volume-title":"Proceedings of the 2010 International Conference on Power Aware Computing and Systems","author":"Le\u00a0Sueur Etienne","year":"2010","unstructured":"Etienne Le\u00a0Sueur and Gernot Heiser. 2010. Dynamic voltage and frequency scaling: the laws of diminishing returns. In Proceedings of the 2010 International Conference on Power Aware Computing and Systems (Vancouver, BC, Canada) (HotPower\u201910). USENIX Association, USA, 1\u20138."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2025.11018306"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD49847.2020.00012"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Seyed\u00a0Morteza Nabavinejad Sherief Reda and Masoumeh Ebrahimi. 2022. Coordinated Batching and DVFS for DNN Inference on GPU Accelerators. IEEE Transactions on Parallel and Distributed Systems 33 10 (2022) 2496\u20132508. 10.1109\/TPDS.2022.3144614","DOI":"10.1109\/TPDS.2022.3144614"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3629526.3645040"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS56514.2022.00010"},{"key":"e_1_3_3_2_26_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arxiv:https:\/\/arXiv.org\/abs\/1909.08053\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS64960.2025.00028"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Ben van Werkhoven. 2019. Kernel Tuner: A search-optimizing GPU code auto-tuner. Future Generation Computer Systems 90 (2019) 347\u2013358. 10.1016\/j.future.2018.08.004","DOI":"10.1016\/j.future.2018.08.004"},{"key":"e_1_3_3_2_30_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arxiv:https:\/\/arXiv.org\/abs\/1706.03762\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW66978.2025.00133"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707231"},{"key":"e_1_3_3_2_33_2","first-page":"795","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Wu Carole-Jean","year":"2022","unstructured":"Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga, Jinshi Huang, Charles Bai, Michael Gschwind, Anurag Gupta, Myle Ott, Anastasia Melnikov, Salvatore Candido, David Brooks, Geeta Chauhan, Benjamin Lee, Hsien-Hsin Lee, Bugra Akyildiz, Maximilian Balandat, Joe Spisak, Ravi Jain, Mike Rabbat, and Kim Hazelwood. 2022. Sustainable AI: Environmental Implications, Challenges and Opportunities. In Proceedings of Machine Learning and Systems , D.\u00a0Marculescu, Y.\u00a0Chi, and C.\u00a0Wu (Eds.), Vol.\u00a04. 795\u2013813."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00028"},{"key":"e_1_3_3_2_35_2","unstructured":"Joshua You David Owen David Porter and Tom Wilson. 2025. Scaling Intelligence: The Exponential Growth of AI\u2019s Power Needs. https:\/\/www.epri.com\/research\/products\/000000003002033669"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3801822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:09:44Z","timestamp":1782544184000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3801822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":34,"alternative-id":["10.1145\/3801487.3801822","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3801822","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}