{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:54:52Z","timestamp":1775638492567,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Assistant Secretary of Defense for Research and Engineering","award":["FA8702-15-D-0001"],"award-info":[{"award-number":["FA8702-15-D-0001"]}]},{"name":"United States Air Force Research Laboratory","award":["FA8750-19-2-1000"],"award-info":[{"award-number":["FA8750-19-2-1000"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607034","type":"proceedings-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T21:47:06Z","timestamp":1699998426000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["Clover: Toward Sustainable AI with Carbon-Aware Machine Learning Inference Service"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9778-1023","authenticated-orcid":false,"given":"Baolin","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4937-6054","authenticated-orcid":false,"given":"Siddharth","family":"Samsi","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4598-2808","authenticated-orcid":false,"given":"Vijay","family":"Gadepally","sequence":"additional","affiliation":[{"name":"MIT Lincoln Laboratory, Lexington, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-2458","authenticated-orcid":false,"given":"Devesh","family":"Tiwari","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"World is on brink of catastrophic warming, u.n. climate change report says","author":"Post The Washington","year":"2023","unstructured":"The Washington Post . World is on brink of catastrophic warming, u.n. climate change report says , 2023 . URL https:\/\/www.washingtonpost.com\/climate-environment\/2023\/03\/20\/climate-change-ipcc-report-15\/. The Washington Post. World is on brink of catastrophic warming, u.n. climate change report says, 2023. URL https:\/\/www.washingtonpost.com\/climate-environment\/2023\/03\/20\/climate-change-ipcc-report-15\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527408"},{"key":"e_1_3_2_1_3_1","unstructured":"IEA. Data centres and data transmission networks 2022. URL https:\/\/www.iea.org\/reports\/data-centres-and-data-transmission-networks. IEA. Data centres and data transmission networks 2022. URL https:\/\/www.iea.org\/reports\/data-centres-and-data-transmission-networks."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/challe6010117"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3148714"},{"key":"e_1_3_2_1_6_1","first-page":"795","article-title":"Sustainable ai: Environmental implications, challenges and opportunities","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 , Sustainable ai: Environmental implications, challenges and opportunities . Proceedings of Machine Learning and Systems , 4 : 795 -- 813 , 2022 . Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga, Jinshi Huang, Charles Bai, et al. Sustainable ai: Environmental implications, challenges and opportunities. Proceedings of Machine Learning and Systems, 4:795--813, 2022.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Inf1 instances with aws inferentia chips for high performance cost-effective inferencing","author":"Service Amazon Web","year":"2019","unstructured":"Amazon Web Service . Inf1 instances with aws inferentia chips for high performance cost-effective inferencing , 2019 . URL https:\/\/aws.amazon.com\/blogs\/aws\/amazon-ec2-update-inf1-instances-with-aws-inferentia-chips-for-high-performance-cost-effective-inferencing\/. Amazon Web Service. Inf1 instances with aws inferentia chips for high performance cost-effective inferencing, 2019. URL https:\/\/aws.amazon.com\/blogs\/aws\/amazon-ec2-update-inf1-instances-with-aws-inferentia-chips-for-high-performance-cost-effective-inferencing\/."},{"key":"e_1_3_2_1_8_1","volume-title":"Aws to offer nvidia's t4 gpus for ai inferencing","author":"Wire HPC","year":"2019","unstructured":"HPC Wire . Aws to offer nvidia's t4 gpus for ai inferencing , 2019 . URL https:\/\/www.hpcwire.com\/2019\/03\/19\/aws-upgrades-its-gpu-backed-ai-inference-platform\/. HPC Wire. Aws to offer nvidia's t4 gpus for ai inferencing, 2019. URL https:\/\/www.hpcwire.com\/2019\/03\/19\/aws-upgrades-its-gpu-backed-ai-inference-platform\/."},{"key":"e_1_3_2_1_9_1","volume-title":"Energy-efficient advanced computing system operations","author":"National Renewable Energy Laboratory (NREL).","year":"2023","unstructured":"National Renewable Energy Laboratory (NREL). Energy-efficient advanced computing system operations , 2023 . URL https:\/\/www.nrel.gov\/computational-science\/hpc-systems-operations.html. National Renewable Energy Laboratory (NREL). Energy-efficient advanced computing system operations, 2023. URL https:\/\/www.nrel.gov\/computational-science\/hpc-systems-operations.html."},{"key":"e_1_3_2_1_10_1","unstructured":"Google. 24\/7 carbon-free energy by 2030 2023. URL https:\/\/www.google.com\/about\/datacenters\/cleanenergy\/. Google. 24\/7 carbon-free energy by 2030 2023. URL https:\/\/www.google.com\/about\/datacenters\/cleanenergy\/."},{"key":"e_1_3_2_1_11_1","volume-title":"Made to measure: Sustainability commitment progress and updates","year":"2021","unstructured":"Microsoft. Made to measure: Sustainability commitment progress and updates , 2021 . URL https:\/\/blogs.microsoft.com\/blog\/2021\/07\/14\/made-to-measure-sustainability-commitment-progress-and-updates\/. Microsoft. Made to measure: Sustainability commitment progress and updates, 2021. URL https:\/\/blogs.microsoft.com\/blog\/2021\/07\/14\/made-to-measure-sustainability-commitment-progress-and-updates\/."},{"key":"e_1_3_2_1_12_1","volume-title":"About sustainable energy for all","year":"2023","unstructured":"GoCarbonFree247. About sustainable energy for all , 2023 . URL https:\/\/gocarbonfree247.com\/about\/. GoCarbonFree247. About sustainable energy for all, 2023. URL https:\/\/gocarbonfree247.com\/about\/."},{"key":"e_1_3_2_1_13_1","volume-title":"Sustainable hpc: Modeling, characterization, and implications of carbon footprint in modern hpc systems. arXiv preprint arXiv:2306.13177","author":"Li Baolin","year":"2023","unstructured":"Baolin Li , Siddharth Samsi , Vijay Gadepally , and Devesh Tiwari . Sustainable hpc: Modeling, characterization, and implications of carbon footprint in modern hpc systems. arXiv preprint arXiv:2306.13177 , 2023 . Baolin Li, Siddharth Samsi, Vijay Gadepally, and Devesh Tiwari. Sustainable hpc: Modeling, characterization, and implications of carbon footprint in modern hpc systems. arXiv preprint arXiv:2306.13177, 2023."},{"key":"e_1_3_2_1_14_1","volume-title":"Data center hardware refresh cutback by microsoft --- what's next?","author":"Knowledge Datacenter","year":"2022","unstructured":"Datacenter Knowledge . Data center hardware refresh cutback by microsoft --- what's next? , 2022 . URL https:\/\/www.datacenterknowledge.com\/microsoft\/data-center-hardware-refresh-cutback-microsoft-what-s-next. Datacenter Knowledge. Data center hardware refresh cutback by microsoft --- what's next?, 2022. URL https:\/\/www.datacenterknowledge.com\/microsoft\/data-center-hardware-refresh-cutback-microsoft-what-s-next."},{"key":"e_1_3_2_1_15_1","volume-title":"Frontier's architecture","author":"Oak Ridge National Laboratory.","year":"2022","unstructured":"Oak Ridge National Laboratory. Frontier's architecture , 2022 . URL https:\/\/olcf.ornl.gov\/wp-content\/uploads\/Frontiers-Architecture-Frontier-Training-Series-final.pdf. Oak Ridge National Laboratory. Frontier's architecture, 2022. URL https:\/\/olcf.ornl.gov\/wp-content\/uploads\/Frontiers-Architecture-Frontier-Training-Series-final.pdf."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476188"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.12.014"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447555.3466582"},{"key":"e_1_3_2_1_19_1","volume-title":"Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700","author":"Lacoste Alexandre","year":"2019","unstructured":"Alexandre Lacoste , Alexandra Luccioni , Victor Schmidt , and Thomas Dandres . Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700 , 2019 . Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt, and Thomas Dandres. Quantifying the carbon emissions of machine learning. arXiv preprint arXiv:1910.09700, 2019."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"e_1_3_2_1_21_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , and Radu Soricut . Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 , 2019 . Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942, 2019."},{"key":"e_1_3_2_1_22_1","first-page":"6105","volume-title":"International conference on machine learning","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. Efficientnet : Rethinking model scaling for convolutional neural networks . In International conference on machine learning , pages 6105 -- 6114 . PMLR, 2019 . Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105--6114. PMLR, 2019."},{"key":"e_1_3_2_1_23_1","first-page":"434","article-title":"A fast and lightweight automl library","volume":"3","author":"Wang Chi","year":"2021","unstructured":"Chi Wang , Qingyun Wu , Markus Weimer , and Erkang Zhu . Flaml : A fast and lightweight automl library . Proceedings of Machine Learning and Systems , 3 : 434 -- 447 , 2021 . Chi Wang, Qingyun Wu, Markus Weimer, and Erkang Zhu. Flaml: A fast and lightweight automl library. Proceedings of Machine Learning and Systems, 3: 434--447, 2021.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_24_1","first-page":"230","article-title":"A system for massively parallel hyperparameter tuning","volume":"2","author":"Li Liam","year":"2020","unstructured":"Liam Li , Kevin Jamieson , Afshin Rostamizadeh , Ekaterina Gonina , Jonathan Ben-Tzur , Moritz Hardt , Benjamin Recht , and Ameet Talwalkar . A system for massively parallel hyperparameter tuning . Proceedings of Machine Learning and Systems , 2 : 230 -- 246 , 2020 . Liam Li, Kevin Jamieson, Afshin Rostamizadeh, Ekaterina Gonina, Jonathan Ben-Tzur, Moritz Hardt, Benjamin Recht, and Ameet Talwalkar. A system for massively parallel hyperparameter tuning. Proceedings of Machine Learning and Systems, 2:230--246, 2020.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9041955"},{"key":"e_1_3_2_1_26_1","volume-title":"Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Computing Surveys (CSUR), 53(4):1--37","author":"Chen Yanjiao","year":"2020","unstructured":"Yanjiao Chen , Baolin Zheng , Zihan Zhang , Qian Wang , Chao Shen , and Qian Zhang . Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Computing Surveys (CSUR), 53(4):1--37 , 2020 . Yanjiao Chen, Baolin Zheng, Zihan Zhang, Qian Wang, Chao Shen, and Qian Zhang. Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Computing Surveys (CSUR), 53(4):1--37, 2020."},{"key":"e_1_3_2_1_27_1","first-page":"353","volume-title":"Proceedings of the 2020 USENIX Conference on Usenix Annual Technical Conference","author":"Wan Chengcheng","year":"2020","unstructured":"Chengcheng Wan , Muhammad Santriaji , Eri Rogers , Henry Hoffmann , Michael Maire , and Shan Lu. Alert : Accurate learning for energy and timeliness . In Proceedings of the 2020 USENIX Conference on Usenix Annual Technical Conference , pages 353 -- 369 , 2020 . Chengcheng Wan, Muhammad Santriaji, Eri Rogers, Henry Hoffmann, Michael Maire, and Shan Lu. Alert: Accurate learning for energy and timeliness. In Proceedings of the 2020 USENIX Conference on Usenix Annual Technical Conference, pages 353--369, 2020."},{"key":"e_1_3_2_1_28_1","volume-title":"NVIDIA Multi-Instance GPU User Guide","author":"MIG.","year":"2023","unstructured":"MIG. NVIDIA Multi-Instance GPU User Guide , 2023 . URL https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/. MIG. NVIDIA Multi-Instance GPU User Guide, 2023. URL https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/."},{"key":"e_1_3_2_1_29_1","volume-title":"NVIDIA Multi-Process Service","author":"MPS.","year":"2023","unstructured":"MPS. NVIDIA Multi-Process Service , 2023 . URL https:\/\/docs.nvidia.com\/deploy\/mps\/. MPS. NVIDIA Multi-Process Service, 2023. URL https:\/\/docs.nvidia.com\/deploy\/mps\/."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00124"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488793"},{"key":"e_1_3_2_1_34_1","volume-title":"Carbon intensity of electricity consumed","author":"Maps Electricity","year":"2023","unstructured":"Electricity Maps . Carbon intensity of electricity consumed , 2023 . URL https:\/\/app.electricitymaps.com\/map. Electricity Maps. Carbon intensity of electricity consumed, 2023. URL https:\/\/app.electricitymaps.com\/map."},{"key":"e_1_3_2_1_35_1","volume-title":"Carbon intensity dashboard","author":"UK National Grid.","year":"2023","unstructured":"UK National Grid. Carbon intensity dashboard , 2023 . URL https:\/\/www.nationalgrideso.com\/future-energy\/our-progress\/carbon-intensity-dashboard. UK National Grid. Carbon intensity dashboard, 2023. URL https:\/\/www.nationalgrideso.com\/future-energy\/our-progress\/carbon-intensity-dashboard."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507752"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313167"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-008-0141-y"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01606"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981735"},{"key":"e_1_3_2_1_43_1","volume-title":"C Daniel Gelatt Jr, and Mario P Vecchi. Optimization by simulated annealing. science, 220(4598):671--680","author":"Kirkpatrick Scott","year":"1983","unstructured":"Scott Kirkpatrick , C Daniel Gelatt Jr, and Mario P Vecchi. Optimization by simulated annealing. science, 220(4598):671--680 , 1983 . Scott Kirkpatrick, C Daniel Gelatt Jr, and Mario P Vecchi. Optimization by simulated annealing. science, 220(4598):671--680, 1983."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-018-0098-8"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2015.02.005"},{"key":"e_1_3_2_1_47_1","volume-title":"Carbon-tracker: Tracking and predicting the carbon footprint of training deep learning models. arXiv preprint arXiv:2007.03051","author":"Wolff Anthony Lasse F","year":"2020","unstructured":"Lasse F Wolff Anthony , Benjamin Kanding , and Raghavendra Selvan . Carbon-tracker: Tracking and predicting the carbon footprint of training deep learning models. arXiv preprint arXiv:2007.03051 , 2020 . Lasse F Wolff Anthony, Benjamin Kanding, and Raghavendra Selvan. Carbon-tracker: Tracking and predicting the carbon footprint of training deep learning models. arXiv preprint arXiv:2007.03051, 2020."},{"key":"e_1_3_2_1_48_1","volume-title":"Los Alamos National Lab.(LANL)","author":"Hagberg Aric","year":"2008","unstructured":"Aric Hagberg , Pieter Swart , and Daniel S Chult . Exploring network structure, dynamics, and function using networkx. Technical report , Los Alamos National Lab.(LANL) , Los Alamos, NM ( United States) , 2008 . Aric Hagberg, Pieter Swart, and Daniel S Chult. Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Lab.(LANL), Los Alamos, NM (United States), 2008."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.25080\/TCWV9851","volume-title":"Proceedings of the 7th Python in Science Conference","author":"Hagberg Aric A.","year":"2008","unstructured":"Aric A. Hagberg , Daniel A. Schult , and Pieter J. Swart . Exploring network structure, dynamics, and function using networkx. In Ga\u00ebl Varoquaux, Travis Vaught, and Jarrod Millman, editors , Proceedings of the 7th Python in Science Conference , pages 11 -- 15 , Pasadena, CA USA , 2008 . Aric A. Hagberg, Daniel A. Schult, and Pieter J. Swart. Exploring network structure, dynamics, and function using networkx. In Ga\u00ebl Varoquaux, Travis Vaught, and Jarrod Millman, editors, Proceedings of the 7th Python in Science Conference, pages 11 -- 15, Pasadena, CA USA, 2008."},{"key":"e_1_3_2_1_50_1","first-page":"740","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin , Michael Maire , Serge Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1r , and C Lawrence Zitnick . Microsoft coco : Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014 , Proceedings, Part V 13 , pages 740 -- 755 . Springer , 2014 . Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13, pages 740--755. Springer, 2014."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_52_1","volume-title":"Know what you don't know: Unanswerable questions for squad. arXiv preprint arXiv:1806.03822","author":"Rajpurkar Pranav","year":"2018","unstructured":"Pranav Rajpurkar , Robin Jia , and Percy Liang . Know what you don't know: Unanswerable questions for squad. arXiv preprint arXiv:1806.03822 , 2018 . Pranav Rajpurkar, Robin Jia, and Percy Liang. Know what you don't know: Unanswerable questions for squad. arXiv preprint arXiv:1806.03822, 2018."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"e_1_3_2_1_56_1","first-page":"967","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Wang Zeke","year":"2022","unstructured":"Zeke Wang , Hongjing Huang , Jie Zhang , Fei Wu , and Gustavo Alonso . {FpgaNIC} : An {FPGA-based} versatile 100gb {SmartNIC} for {GPUs} . In 2022 USENIX Annual Technical Conference (USENIX ATC 22) , pages 967 -- 986 , 2022 . Zeke Wang, Hongjing Huang, Jie Zhang, Fei Wu, and Gustavo Alonso. {FpgaNIC}: An {FPGA-based} versatile 100gb {SmartNIC} for {GPUs}. In 2022 USENIX Annual Technical Conference (USENIX ATC 22), pages 967--986, 2022."},{"key":"e_1_3_2_1_57_1","unstructured":"ALBERT : A Lite BERT for Self-supervised Learning of Language Representations . URL https:\/\/github.com\/google-research\/albert. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations . URL https:\/\/github.com\/google-research\/albert."},{"key":"e_1_3_2_1_58_1","unstructured":"A PyTorch implementation of EfficientNet . URL https:\/\/github.com\/lukemelas\/EfficientNet-PyTorch. A PyTorch implementation of EfficientNet . URL https:\/\/github.com\/lukemelas\/EfficientNet-PyTorch."},{"key":"e_1_3_2_1_59_1","unstructured":"Yolov5 . URL https:\/\/github.com\/ultralytics\/yolov5. Yolov5 . URL https:\/\/github.com\/ultralytics\/yolov5."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303958"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_3_2_1_62_1","volume-title":"Uptime institute global data center survey","author":"Uptime Institute","year":"2022","unstructured":"Uptime Institute . Uptime institute global data center survey , 2022 . URL https:\/\/uptimeinstitute.com\/uptime_assets\/6768eca6a75d792c8eeede827d76de0d0380dee6b5ced20fde45787dd3688bfe-2022-data-center-industry-survey-en.pdf. Uptime Institute. Uptime institute global data center survey, 2022. URL https:\/\/uptimeinstitute.com\/uptime_assets\/6768eca6a75d792c8eeede827d76de0d0380dee6b5ced20fde45787dd3688bfe-2022-data-center-industry-survey-en.pdf."},{"key":"e_1_3_2_1_63_1","unstructured":"EPA. Greenhouse Gases Equivalencies Calculator - Calculations and References 2023. URL https:\/\/www.epa.gov\/energy\/greenhouse-gases-equivalencies-calculator-calculations-and-references. EPA. Greenhouse Gases Equivalencies Calculator - Calculations and References 2023. URL https:\/\/www.epa.gov\/energy\/greenhouse-gases-equivalencies-calculator-calculations-and-references."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/2248487.2150980"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2022.3163226"},{"key":"e_1_3_2_1_66_1","first-page":"118","volume-title":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"2","author":"Acun Bilge","year":"2023","unstructured":"Bilge Acun , Benjamin Lee , Fiodar Kazhamiaka , Kiwan Maeng , Udit Gupta , Manoj Chakkaravarthy , David Brooks , and Carole-Jean Wu. Carbon explorer : A holistic framework for designing carbon aware datacenters . In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems , Volume 2 , pages 118 -- 132 , 2023 . Bilge Acun, Benjamin Lee, Fiodar Kazhamiaka, Kiwan Maeng, Udit Gupta, Manoj Chakkaravarthy, David Brooks, and Carole-Jean Wu. Carbon explorer: A holistic framework for designing carbon aware datacenters. In Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, pages 118--132, 2023."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3173250"},{"key":"e_1_3_2_1_68_1","volume-title":"Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350","author":"Patterson David","year":"2021","unstructured":"David Patterson , Joseph Gonzalez , Quoc Le , Chen Liang , Lluis-Miquel Munguia , Daniel Rothchild , David So , Maud Texier , and Jeff Dean . Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350 , 2021 . David Patterson, Joseph Gonzalez, Quoc Le, Chen Liang, Lluis-Miquel Munguia, Daniel Rothchild, David So, Maud Texier, and Jeff Dean. Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350, 2021."},{"key":"e_1_3_2_1_69_1","volume-title":"Treehouse: A case for carbon-aware datacenter software. arXiv preprint arXiv:2201.02120","author":"Anderson Thomas","year":"2022","unstructured":"Thomas Anderson , Adam Belay , Mosharaf Chowdhury , Asaf Cidon , and Irene Zhang . Treehouse: A case for carbon-aware datacenter software. arXiv preprint arXiv:2201.02120 , 2022 . Thomas Anderson, Adam Belay, Mosharaf Chowdhury, Asaf Cidon, and Irene Zhang. Treehouse: A case for carbon-aware datacenter software. arXiv preprint arXiv:2201.02120, 2022."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533234"},{"key":"e_1_3_2_1_71_1","first-page":"443","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati , Reza Karimi , Safya Alzayat , Wei Hao , Antoine Kaufmann , Ymir Vigfusson , and Jonathan Mace . Serving DNNs like clockwork: Performance predictability from the bottom up . In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20) , pages 443 -- 462 . USENIX Association , November 2020 . ISBN 978-1-939133-19-9. URL https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/gujarati. Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. Serving DNNs like clockwork: Performance predictability from the bottom up. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pages 443--462. USENIX Association, November 2020. ISBN 978-1-939133-19-9. URL https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/gujarati."},{"key":"e_1_3_2_1_72_1","article-title":"Interference-aware gpu resource provisioning for predictable dnn inference in the cloud","author":"Xu Fei","year":"2022","unstructured":"Fei Xu , Jianian Xu , Jiabin Chen , Li Chen , Ruitao Shang , Zhi Zhou , and Fangming Liu . igniter : Interference-aware gpu resource provisioning for predictable dnn inference in the cloud . IEEE Transactions on Parallel and Distributed Systems , 2022 . Fei Xu, Jianian Xu, Jiabin Chen, Li Chen, Ruitao Shang, Zhi Zhou, and Fangming Liu. igniter: Interference-aware gpu resource provisioning for predictable dnn inference in the cloud. IEEE Transactions on Parallel and Distributed Systems, 2022.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486972"},{"key":"e_1_3_2_1_74_1","first-page":"1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Li Baolin","year":"2021","unstructured":"Baolin Li , Rohan Basu Roy , Tirthak Patel , Vijay Gadepally , Karen Gettings , and Devesh Tiwari . Ribbon : cost-effective and qos-aware deep learning model inference using a diverse pool of cloud computing instances . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis , pages 1 -- 13 , 2021 . Baolin Li, Rohan Basu Roy, Tirthak Patel, Vijay Gadepally, Karen Gettings, and Devesh Tiwari. Ribbon: cost-effective and qos-aware deep learning model inference using a diverse pool of cloud computing instances. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1--13, 2021."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486993"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467146"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3592997"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00074"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00049"},{"key":"e_1_3_2_1_80_1","first-page":"613","volume-title":"NSDI","volume":"17","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw , Xin Wang , Giulio Zhou , Michael J Franklin , Joseph E Gonzalez , and Ion Stoica . Clipper : A low-latency online prediction serving system . In NSDI , volume 17 , pages 613 -- 627 , 2017 . Daniel Crankshaw, Xin Wang, Giulio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. Clipper: A low-latency online prediction serving system. In NSDI, volume 17, pages 613--627, 2017."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.3390\/en15020474"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2013.6657064"},{"key":"e_1_3_2_1_83_1","first-page":"819","volume-title":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","author":"Nabavinejad Seyed Morteza","year":"2021","unstructured":"Seyed Morteza Nabavinejad , Sherief Reda , and Masoumeh Ebrahimi . Batchsizer : Power-performance trade-off for dnn inference . In Proceedings of the 26th Asia and South Pacific Design Automation Conference , pages 819 -- 824 , 2021 . Seyed Morteza Nabavinejad, Sherief Reda, and Masoumeh Ebrahimi. Batchsizer: Power-performance trade-off for dnn inference. In Proceedings of the 26th Asia and South Pacific Design Automation Conference, pages 819--824, 2021."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388948"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS52030.2021.00020"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"e_1_3_2_1_87_1","first-page":"397","volume-title":"USENIX Annual Technical Conference","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero , Qian Li , Neeraja J Yadwadkar , and Christos Kozyrakis . Infaas : Automated model-less inference serving . In USENIX Annual Technical Conference , pages 397 -- 411 , 2021 . Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. Infaas: Automated model-less inference serving. In USENIX Annual Technical Conference, pages 397--411, 2021."},{"key":"e_1_3_2_1_88_1","first-page":"199","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi , Sunho Lee , Yeonjae Kim , Jongse Park , Youngjin Kwon , and Jaehyuk Huh . Serving heterogeneous machine learning models on {Multi-GPU} servers with {Spatio-Temporal} sharing . In 2022 USENIX Annual Technical Conference (USENIX ATC 22) , pages 199 -- 216 , 2022 . Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. Serving heterogeneous machine learning models on {Multi-GPU} servers with {Spatio-Temporal} sharing. In 2022 USENIX Annual Technical Conference (USENIX ATC 22), pages 199--216, 2022."}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607034","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:22Z","timestamp":1750178182000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":88,"alternative-id":["10.1145\/3581784.3607034","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607034","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}