{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T22:28:36Z","timestamp":1782944916971,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"IBM"},{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2227609"],"award-info":[{"award-number":["ECCS-2227609"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,22]]},"DOI":"10.1145\/3642970.3655830","type":"proceedings-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T10:46:57Z","timestamp":1713523617000},"page":"47-55","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Characterizing Training Performance and Energy for Foundation Models and Image Classifiers on Multi-Instance GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8318-2596","authenticated-orcid":false,"given":"Connor","family":"Espenshade","sequence":"first","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2108-2156","authenticated-orcid":false,"given":"Rachel","family":"Peng","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7547-7132","authenticated-orcid":false,"given":"Eumin","family":"Hong","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3153-3600","authenticated-orcid":false,"given":"Max","family":"Calman","sequence":"additional","affiliation":[{"name":"IBM Research Yorktown Heights, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2207-1904","authenticated-orcid":false,"given":"Yue","family":"Zhu","sequence":"additional","affiliation":[{"name":"IBM Research Yorktown Heights, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4722-7854","authenticated-orcid":false,"given":"Pritish","family":"Parida","sequence":"additional","affiliation":[{"name":"IBM Research Yorktown Heights, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2335-4798","authenticated-orcid":false,"given":"Eun Kyung","family":"Lee","sequence":"additional","affiliation":[{"name":"IBM Research Yorktown Heights, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6243-5753","authenticated-orcid":false,"given":"Martha A.","family":"Kim","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2020. NVIDIA A100 Tensor Core GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_1_2_1","unstructured":"2021. NVIDIA A100 Tensor Core GPU | Data Sheet. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/a100\/pdf\/nvidia-a100-datasheet-us-nvidia-1758950-r4-web.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. NVIDIA H100 Tensor Core GPU. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2022. NVIDIA Multi-Instance GPU User Guide. https:\/\/docs.nvidia.com\/datacenter\/tesla\/mig-user-guide\/index.html"},{"key":"e_1_3_2_1_5_1","unstructured":"2023. Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html"},{"key":"e_1_3_2_1_6_1","first-page":"485","article-title":"Significance Of Epochs On Training A Neural Network","volume":"9","author":"Afaq Saahil","year":"2020","unstructured":"Saahil Afaq and Smitha Rao. 2020. Significance Of Epochs On Training A Neural Network. International Journal of Scientific & Technology Research 9 (2020), 485--488. https:\/\/api.semanticscholar.org\/CorpusID:225647672","journal-title":"International Journal of Scientific & Technology Research"},{"key":"e_1_3_2_1_7_1","unstructured":"Tom B. 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 M. 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. arXiv:2005.14165 [cs.CL]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_2_1_10_1","unstructured":"Aaron Gokaslan Vanya Cohen Ellie Pavlick and Stefanie Tellex. 2019. OpenWebText Corpus. http:\/\/Skylion007.github.io\/OpenWebTextCorpus."},{"key":"e_1_3_2_1_11_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs.CV]"},{"key":"e_1_3_2_1_12_1","volume-title":"Weinberger","author":"Huang Gao","year":"2018","unstructured":"Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2018. Densely Connected Convolutional Networks. http:\/\/arxiv.org\/abs\/1608.06993 arXiv:1608.06993 [cs]."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2020.04.010"},{"key":"e_1_3_2_1_14_1","unstructured":"Andrej Karpathy. 2023. NanoGPT. https:\/\/github.com\/karpathy\/nanoGPT"},{"key":"e_1_3_2_1_15_1","unstructured":"Donald Kinghorn. 2022. NVIDIA GPU Power Limit vs Performance. https:\/\/www.pugetsystems.com\/labs\/hpc\/nvidia-gpu-power-limit-vs-performance-2296\/"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.03.041"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00124"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.151"},{"key":"e_1_3_2_1_20_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arXiv:1609.07843 [cs.CL]"},{"key":"e_1_3_2_1_21_1","unstructured":"PyTorch. 2023. PyTorch Examples. https:\/\/github.com\/pytorch\/examples"},{"key":"e_1_3_2_1_22_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Ties Robroek Ehsan Yousefzadeh-Asl-Miandoab and Pinar T\u00f6z\u00fcn. 2023. An Analysis of Collocation on GPUs for Deep Learning Training. arXiv:2209.06018 [cs.LG]","DOI":"10.1145\/3642970.3655827"},{"key":"e_1_3_2_1_24_1","unstructured":"Dave Salvator. 2023. NVIDIA H100 GPUs Set Standard for Generative AI in Debut MLPerf Benchmark. https:\/\/blogs.nvidia.com\/blog\/2023\/06\/27\/generative-ai-debut-mlperf\/"},{"key":"e_1_3_2_1_25_1","unstructured":"Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jonathon Shlens and Zbigniew Wojna. 2015. Rethinking the Inception Architecture for Computer Vision. http:\/\/arxiv.org\/abs\/1512.00567 arXiv:1512.00567 [cs]."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.162"},{"key":"e_1_3_2_1_27_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_28_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL]"},{"key":"e_1_3_2_1_29_1","volume-title":"Chiew Tong Lau, and Yang You","author":"Luo Yong","year":"2023","unstructured":"Huaizheng Zhang, Yuanming Li, Wencong Xiao, Yizheng Huang, Xing Di, Jianxiong Yin, Simon See, Yong Luo, Chiew Tong Lau, and Yang You. 2023. MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs. arXiv:2301.00407 [cs.LG]"}],"event":{"name":"EuroSys '24: Nineteenth European Conference on Computer Systems","location":"Athens Greece","acronym":"EuroSys '24","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 4th Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642970.3655830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3642970.3655830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:15:43Z","timestamp":1755908143000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642970.3655830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":29,"alternative-id":["10.1145\/3642970.3655830","10.1145\/3642970"],"URL":"https:\/\/doi.org\/10.1145\/3642970.3655830","relation":{},"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"2024-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}