{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T06:00:20Z","timestamp":1769925620872,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,17]]},"DOI":"10.1145\/3679240.3734608","type":"proceedings-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T13:13:42Z","timestamp":1750079622000},"page":"43-55","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Aging-aware CPU Core Management for Embodied Carbon Amortization in Cloud LLM Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6348-4602","authenticated-orcid":false,"given":"Tharindu B.","family":"Hewage","sequence":"first","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1178-6582","authenticated-orcid":false,"given":"Shashikant","family":"Ilager","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2831-8526","authenticated-orcid":false,"given":"Maria Rodriguez","family":"Read","sequence":"additional","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9754-6496","authenticated-orcid":false,"given":"Rajkumar","family":"Buyya","sequence":"additional","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS58335.2023.00025"},{"key":"e_1_3_3_1_3_2","unstructured":"AWS. 2025. Deploying Multiple Large Language Models with NVIDIA Triton Server and vLLM. Retrieved May 4 2025 from https:\/\/awslabs.github.io\/data-on-eks\/docs\/gen-ai\/inference\/GPUs\/vLLM-NVIDIATritonServer"},{"key":"e_1_3_3_1_4_2","unstructured":"Azure. 2024. NCads H100 v5-series. Retrieved May 4 2025 from https:\/\/learn.microsoft.com\/en-us\/azure\/virtual-machines\/ncads-h100-v5"},{"key":"e_1_3_3_1_5_2","unstructured":"Azure. 2024. NCasT4_v3 sizes series. Retrieved May 4 2025 from https:\/\/learn.microsoft.com\/en-us\/azure\/virtual-machines\/sizes\/gpu-accelerated\/ncast4v3-series?tabs=sizebasic"},{"key":"e_1_3_3_1_6_2","unstructured":"Sally Beatty. 2024. Microsoft builds first datacenters with wood to slash carbon emissions. Retrieved May 4 2025 from https:\/\/news.microsoft.com\/source\/features\/sustainability\/microsoft-builds-first-datacenters-with-wood-to-slash-carbon-emissions\/"},{"key":"e_1_3_3_1_7_2","volume-title":"Proceedings of the 1st Workshop on NetZero Carbon Computing (NetZero)","author":"Berger Daniel\u00a0S.","year":"2023","unstructured":"Daniel\u00a0S. Berger, Fiodar Kazhamiaka, Esha Choukse, \u00cd\u00f1igo Goiri, Celine Irvene, Pulkit Misra, Alok Kumbhare, Rodrigo Fonseca, and Ricardo Bianchini. 2023. Research Avenues Towards Net-Zero Cloud Platforms. In Proceedings of the 1st Workshop on NetZero Carbon Computing (NetZero)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Ricardo Bianchini Christian Belady and Anand Sivasubramaniam. 2024. Data Center Power and Energy Management: Past Present and Future. IEEE Micro 44 5 (2024) 30\u201336.","DOI":"10.1109\/MM.2024.3426478"},{"key":"e_1_3_3_1_9_2","unstructured":"Jairus Bowne. 2024. Using Large Language Models in Learning and Teaching. Retrieved May 4 2025 from https:\/\/biomedicalsciences.unimelb.edu.au\/study\/dlh\/assets\/documents\/large-language-models-in-education\/llms-in-education"},{"key":"e_1_3_3_1_10_2","unstructured":"Microsoft Corporation. 2022. The role of embodied carbon in cloud emissions. Retrieved May 4 2025 from https:\/\/go.microsoft.com\/fwlink\/p\/?linkid=2233506"},{"key":"e_1_3_3_1_11_2","unstructured":"Crusoe. 2023. How Together And Crusoe Are Reducing The Carbon Impact Of Generative AI. Retrieved May 4 2025 from https:\/\/crusoe.ai\/blog\/crusoe-together-reducing-carbon-impact-of-generative-ai\/"},{"key":"e_1_3_3_1_12_2","unstructured":"Crusoe. 2024. Crusoe to Build Initial 200 MW AI Data Center With Plans to Expand at 1.2 GW Lancium Clean Campus. Retrieved May 4 2025 from https:\/\/crusoe.ai\/newsroom\/crusoe-200mw-ai-data-center\/"},{"key":"e_1_3_3_1_13_2","unstructured":"Sheila Dang. 2024. Musk\u2019s xAI plans massive expansion of AI supercomputer in Memphis. Retrieved May 4 2025 from https:\/\/www.reuters.com\/technology\/artificial-intelligence\/musks-xai-plans-massive-expansion-ai-supercomputer-memphis-2024-12-04\/"},{"key":"e_1_3_3_1_14_2","unstructured":"Harish\u00a0Dattatraya Dixit Sneha Pendharkar Matt Beadon Chris Mason Tejasvi Chakravarthy Bharath Muthiah and Sriram Sankar. 2021. Silent Data Corruptions at Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.11245 (2021)."},{"key":"e_1_3_3_1_15_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Faiz Ahmad","year":"2024","unstructured":"Ahmad Faiz, Sotaro Kaneda, Ruhan Wang, Rita\u00a0Chukwunyere Osi, Prateek Sharma, Fan Chen, and Lei Jiang. 2024. LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_16_2","unstructured":"Zhenxiao Fu Fan Chen Shan Zhou Haitong Li and Lei Jiang. 2024. LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02950 (2024)."},{"key":"e_1_3_3_1_17_2","unstructured":"GitHub. 2021. Introducing GitHub Copilot: your AI pair programmer. Retrieved May 4 2025 from https:\/\/github.blog\/news-insights\/product-news\/introducing-github-copilot-ai-pair-programmer\/"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744849"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527408"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458336.3465297"},{"key":"e_1_3_3_1_21_2","unstructured":"IEA. 2023. International Energy Agency\u2019s report on Low-emissions sources of electricity. Retrieved May 4 2025 from https:\/\/www.iea.org\/reports\/low-emissions-sources-of-electricity"},{"key":"e_1_3_3_1_22_2","unstructured":"Intel. 2024. How to Find Compatible Motherboards for the Intel\u00ae Xeon\u00ae Processor Family?Retrieved May 4 2025 from https:\/\/www.intel.com\/content\/www\/us\/en\/support\/articles\/000057630\/processors.html"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI61997.2024.00095"},{"key":"e_1_3_3_1_24_2","unstructured":"Lenovo. 2025. ThinkSystem SR650 Maintenance Manual. Retrieved May 4 2025 from https:\/\/pubs.lenovo.com\/sr650\/sr650_maintenance_manual.pdf"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1215"},{"key":"e_1_3_3_1_26_2","unstructured":"Yueying Li Zhanqiu Hu Esha Choukse Rodrigo Fonseca G.\u00a0Edward Suh and Udit Gupta. 2025. EcoServe: Designing Carbon-Aware AI Inference Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05043 (2025)."},{"key":"e_1_3_3_1_27_2","volume-title":"Proceedings of the 3rd Workshop on Sustainable Computer Systems","author":"Li Yueying\u00a0Lisa","year":"2024","unstructured":"Yueying\u00a0Lisa Li, Omer Graif, and Udit Gupta. 2024. Towards Carbon-efficient LLM Life Cycle. In Proceedings of the 3rd Workshop on Sustainable Computer Systems."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI59464.2023.10238501"},{"key":"e_1_3_3_1_29_2","first-page":"287","volume-title":"Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Lyu Jialun","year":"2023","unstructured":"Jialun Lyu, Marisa You, Celine Irvene, Mark Jung, Tyler Narmore, Jacob Shapiro, Luke Marshall, Savyasachi Samal, Ioannis Manousakis, Lisa Hsu, Preetha Subbarayalu, Ashish Raniwala, Brijesh Warrier, Ricardo Bianchini, Bianca Schroeder, and Daniel\u00a0S. Berger. 2023. Hyrax: Fail-in-Place Server Operation in Cloud Platforms. In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 287\u2013304."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3662164"},{"key":"e_1_3_3_1_31_2","unstructured":"Kevin Mayo Sylvester Rajasekaran Igor Pasichnyk and Michael Senizaiz. 2018. High Performance Computing (HPC) Tuning Guide. Retrieved May 4 2025 from https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-technical-docs\/tuning-guides\/58479_amd-epyc-9005-tg-hpc.pdf"},{"key":"e_1_3_3_1_32_2","unstructured":"Rick Merritt. 2023. Why GPUs Are Great for AI. Retrieved May 4 2025 from https:\/\/blogs.nvidia.com\/blog\/why-gpus-are-great-for-ai\/"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Iraj Moghaddasi Arash Fouman Mostafa\u00a0E. Salehi and Mehdi Kargahi. 2019. Instruction-Level NBTI Stress Estimation and Its Application in Runtime Aging Prediction for Embedded Processors. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38 (2019) 1427\u20131437.","DOI":"10.1109\/TCAD.2018.2846629"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Sophia Nguyen Beihao Zhou Yi Ding and Sihang Liu. 2025. Towards Sustainable Large Language Model Serving. SIGENERGY Energy Inform. Rev. 4 5 (2025) 134\u2013140.","DOI":"10.1145\/3727200.3727220"},{"key":"e_1_3_3_1_35_2","unstructured":"LA Office of\u00a0the governor. 2024. Landry Announces Meta Selects North Louisiana as Site of $10 Billion Artificial Intelligence Optimized Data Center. Retrieved May 4 2025 from https:\/\/gov.louisiana.gov\/news\/4697"},{"key":"e_1_3_3_1_36_2","unstructured":"OpenAI. 2022. Introducing ChatGPT. Retrieved May 4 2025 from https:\/\/openai.com\/index\/chatgpt\/"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_1_38_2","unstructured":"GHG Protocol. 2024. Greenhouse Gas Protocol. Retrieved May 4 2025 from https:\/\/ghgprotocol.org\/about-us"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2013.023"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Faezeh\u00a0Sadat Saadatmand Nezam Rohbani Farshad Baharvand and Hamed Farbeh. 2021. TAMER: an adaptive task allocation method for aging reduction in multi-core embedded real-time systems. The Journal of Supercomputing 77 (2021) 1939\u20131957.","DOI":"10.1007\/s11227-020-03326-7"},{"key":"e_1_3_3_1_41_2","unstructured":"Philipp Schmid Omar Sanseviero Pedro Cuenca and Lewis Tunstall. 2023. Llama 2 is here - get it on Hugging Face. Retrieved May 4 2025 from https:\/\/huggingface.co\/blog\/llama2"},{"key":"e_1_3_3_1_42_2","unstructured":"Tianyao Shi Yanran Wu Sihang Liu and Yi Ding. 2024. GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.20322 (2024)."},{"key":"e_1_3_3_1_43_2","unstructured":"Fumiyoshi Shoji Shuji Matsui Mitsuo Okamoto Fumichika Sueyasu Toshiyuki Tsukamoto Atsuya Uno and Keiji Yamamoto. 2015. Long term failure analysis of 10 peta-scale supercomputer. HPC in Asia Poster ISC (2015)."},{"key":"e_1_3_3_1_44_2","unstructured":"The\u00a0Financial Times. 2024. OpenAI targets 1bn users in next phase of growth. Retrieved May 4 2025 from https:\/\/www.ft.com\/content\/e91cb018-873c-4388-84c0-46e9f82146b4"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771785"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Amanda Tomlinson and George Porter. 2023. Something Old Something New: Extending the Life of CPUs in Datacenters. SIGENERGY Energy Informatics Review 3 3 (2023) 59\u201363.","DOI":"10.1145\/3630614.3630625"},{"key":"e_1_3_3_1_47_2","unstructured":"Shashank Verma and Neal Vaidya. 2023. Mastering LLM Techniques: Inference Optimization. Retrieved May 4 2025 from https:\/\/developer.nvidia.com\/blog\/mastering-llm-techniques-inference-optimization\/"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3662830"},{"key":"e_1_3_3_1_49_2","unstructured":"Rafael\u00a0J. Wysocki. 2018. CPU Idle Time Management. Retrieved May 4 2025 from https:\/\/www.kernel.org\/doc\/html\/v5.4\/admin-guide\/pm\/cpuidle.html"},{"key":"e_1_3_3_1_50_2","unstructured":"Rafael\u00a0J. Wysocki. 2018. CPU Idle Time Management. Retrieved May 4 2025 from https:\/\/docs.kernel.org\/admin-guide\/pm\/cpuidle.html"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00089"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00063"},{"key":"e_1_3_3_1_53_2","first-page":"521","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo\u00a0Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 521\u2013538."},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3661939"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604930.3605706"}],"event":{"name":"E-Energy '25: The 16th ACM International Conference on Future and Sustainable Energy Systems","location":"Rotterdam Netherlands","acronym":"E-Energy '25","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3679240.3734608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T14:01:32Z","timestamp":1750082492000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3679240.3734608"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":54,"alternative-id":["10.1145\/3679240.3734608","10.1145\/3679240"],"URL":"https:\/\/doi.org\/10.1145\/3679240.3734608","relation":{},"subject":[],"published":{"date-parts":[[2025,6,16]]},"assertion":[{"value":"2025-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}