{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T12:17:12Z","timestamp":1778156232771,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2313061"],"award-info":[{"award-number":["OAC-2313061"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767566","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:13:44Z","timestamp":1762532024000},"page":"2022-2031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["EMLIO: Minimizing I\/O Latency and Energy Consumption for Large-Scale AI Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7631-1487","authenticated-orcid":false,"given":"Md Hasibul","family":"Jamil","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University at Buffalo SUNY, Amherst, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6218-0199","authenticated-orcid":false,"given":"MD S. Q. Zulkar","family":"Nine","sequence":"additional","affiliation":[{"name":"Tennessee Technological University, Cookeville, TN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5600-6706","authenticated-orcid":false,"given":"Tevfik","family":"Kosar","sequence":"additional","affiliation":[{"name":"University at Buffalo (SUNY), Buffalo, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. perf: Performance Analysis Tools. https:\/\/www.kernel.org\/doc\/html\/latest\/admin-guide\/perf.html. Accessed: 2025-07-23."},{"key":"e_1_3_3_1_3_2","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg\u00a0S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/."},{"key":"e_1_3_3_1_4_2","volume-title":"17th IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"Abodo Franklin","year":"2018","unstructured":"Franklin Abodo, Robert Rittmuller, Brian Sumner, and Andrew Berthaume. 2018. Detecting Work Zones in SHRP\u00a02 NDS Videos Using Deep Learning Based Computer Vision. In 17th IEEE International Conference on Machine Learning and Applications (ICMLA)."},{"key":"e_1_3_3_1_5_2","unstructured":"Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Paul Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.08675."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Ammar\u00a0Ahmad Awan Karthik\u00a0Vadambacheri Manian Ching\u2011Hsiang Chu Hari Subramoni and Dhabaleswar\u00a0K Panda. 2019. Optimized large\u2011message broadcast for deep learning workloads: MPI MPI + NCCL or NCCL2? Parallel Comput. 85 (2019) 141\u2013152.","DOI":"10.1016\/j.parco.2019.03.005"},{"key":"e_1_3_3_1_8_2","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An end-to-end optimization stack for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)."},{"key":"e_1_3_3_1_9_2","unstructured":"Sharan Chetlur Cliff Woolley Philippe Vandermersch Jonathan Cohen John Tran Bryan Catanzaro and Evan Shelhamer. 2014. cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1410.0759."},{"key":"e_1_3_3_1_10_2","volume-title":"International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW\u2011DISCS)","author":"Chien Steven W.\u00a0D.","year":"2018","unstructured":"Steven W.\u00a0D. Chien, Stefano Markidis, Chaitanya\u00a0P. Sishtla, Luis Santos, Pawel Herman, Sai Narasimhamurthy, and Erwin Laure. 2018. Characterizing Deep\u2011Learning I\/O Workloads in TensorFlow. In International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW\u2011DISCS)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476181"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2018.8638639"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Adithya Gangidi and et al.2024. RDMA over Ethernet for Distributed Training at Meta Scale(ACM SIGCOMM \u201924). Association for Computing Machinery New York NY USA 57\u201370. 10.1145\/3651890.3672233","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_3_1_15_2","unstructured":"Google. 2020. XLA: Optimizing Compiler for Machine Learning. https:\/\/www.tensorflow.org\/xla."},{"key":"e_1_3_3_1_16_2","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2017. Accurate Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.02677."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_18_2","unstructured":"InfluxData. [n. d.]. InfluxDB\u2011Python Client Documentation. https:\/\/influxdb-python.readthedocs.io\/. Accessed: 2025-07-23."},{"key":"e_1_3_3_1_19_2","volume-title":"Proceedings of the Fourth Conference on Machine Learning and Systems (MLSys)","author":"Ivanov Andrei","year":"2021","unstructured":"Andrei Ivanov, Nikoli Dryden, Tal Ben-Nun, Shigang Li, and Torsten Hoefler. 2021. Data Movement Is All You Need: A Case Study on Optimizing Transformers. In Proceedings of the Fourth Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891012"},{"key":"e_1_3_3_1_21_2","unstructured":"Hasubil Jamil Jacob Goldverg Elvis Rodrigues MD\u00a0S Q\u00a0Zulkar Nine and Tevfik Kosar. 2025. Optimizing Data Transfer Performance and Energy Efficiency with Deep Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2503.13662\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2503.13662"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_1_23_2","volume-title":"Proceedings of USENIX ATC\u201920","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey, Jason Anderson, Zhuo Zhen, and et al.2020. Lessons Learned from the Chameleon Testbed. In Proceedings of USENIX ATC\u201920."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Guillaume Leclerc Andrew Ilyas Logan Engstrom Sung\u00a0Min Park Hadi Salman and Aleksander Madry. 2023. FFCV: Accelerating Training by Removing Data Bottlenecks. arxiv:https:\/\/arXiv.org\/abs\/2306.12517\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2306.12517","DOI":"10.1109\/CVPR52729.2023.01156"},{"key":"e_1_3_3_1_26_2","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie Lubomir Bourdev Ross Girshick James Hays Pietro Perona Deva Ramanan C.\u00a0Lawrence Zitnick and Piotr Doll\u00e1r. 2015. Microsoft COCO: Common Objects in Context. arxiv:https:\/\/arXiv.org\/abs\/1405.0312\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545090"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Eric Masanet Arman Shehabi Nuoa Lei Sarah Smith and Jonathan Koomey. 2020. Recalibrating Global Data Center Energy\u2011Use Estimates. Science 367 6481 (Feb. 2020) 984\u2013986. 10.1126\/science.aba3758","DOI":"10.1126\/science.aba3758"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00068"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Jayashree Mohan and et al.2021. Analyzing and Mitigating Data Stalls in DNN Training. Proceedings of the VLDB Endowment 14 5 (2021) 771\u2013784. 10.14778\/3446095.3446100","DOI":"10.14778\/3446095.3446100"},{"key":"e_1_3_3_1_33_2","unstructured":"Derek\u00a0G. Murray Jiri Simsa Ana Klimovic and Ihor Indyk. 2021. tf.data: A Machine Learning Data Processing Framework. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.12127."},{"key":"e_1_3_3_1_34_2","unstructured":"NVIDIA. 2018. DALI: NVIDIA Data Loading Library. https:\/\/developer.nvidia.com\/dali."},{"key":"e_1_3_3_1_35_2","unstructured":"NVIDIA. 2020. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_3_1_36_2","unstructured":"NVIDIA Corporation. [n. d.]. NVIDIA Management Library (NVML). https:\/\/developer.nvidia.com\/nvidia-management-library-nvml. Accessed: 2025-07-23."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Yosuke Oyama Naoya Maruyama Nikoli Dryden Erin McCarthy Peter Harrington Jan Balewski Satoshi Matsuoka Peter Nugent and Brian\u00a0Van Essen. 2020. The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism. arxiv:https:\/\/arXiv.org\/abs\/2007.12856\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2007.12856","DOI":"10.1109\/TPDS.2020.3047974"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Yosuke Oyama Naoya Maruyama Nikoli Dryden Erin McCarthy Peter Harrington Jan Balewski Satoshi Matsuoka Peter Nugent and Brian Van\u00a0Essen. 2020. The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism. IEEE Transactions on Parallel and Distributed Systems (2020).","DOI":"10.1109\/TPDS.2020.3047974"},{"key":"e_1_3_3_1_39_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, and et al.2019. PyTorch: An Imperative Style, High\u2011Performance Deep Learning Library. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345451"},{"key":"e_1_3_3_1_41_2","unstructured":"David Patterson Joseph Gonzalez Quoc Le Chen Liang Lluis-Miquel Munguia Daniel Rothchild David So Maud Texier and Jeff Dean. 2021. Carbon Emissions and Large Neural Network Training. arxiv:https:\/\/arXiv.org\/abs\/2104.10350\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2104.10350"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Sarunya Pumma Min Si Wu-Chun Feng and Pavan Balaji. 2019. Scalable Deep Learning via I\/O Analysis and Optimization. ACM Transactions on Parallel Computing (TOPC) 6 2 (2019).","DOI":"10.1145\/3331526"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Kun Qian and et al.2024. Alibaba HPN: A Data Center Network for Large Language Model Training(ACM SIGCOMM \u201924). Association for Computing Machinery New York NY USA 691\u2013706. 10.1145\/3651890.3672265","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Saurabhsingh Rajput Tim Widmayer Ziyuan Shang Maria Kechagia Federica Sarro and Tushar Sharma. 2024. Enhancing Energy-Awareness in Deep Learning through Fine-Grained Energy Measurement. ACM Trans. Softw. Eng. Methodol. 33 8 Article 211 (Dec. 2024) 34\u00a0pages. 10.1145\/3680470","DOI":"10.1145\/3680470"},{"key":"e_1_3_3_1_45_2","unstructured":"Alexander Sergeev and Mike Del\u00a0Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1802.05799."},{"key":"e_1_3_3_1_46_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:https:\/\/arXiv.org\/abs\/1409.1556\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_1_47_2","unstructured":"Emma Strubell Ananya Ganesh and Andrew McCallum. 2019. Energy and Policy Considerations for Deep Learning in NLP. arxiv:https:\/\/arXiv.org\/abs\/1906.02243\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1906.02243"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"e_1_3_3_1_49_2","unstructured":"TensorFlow Project. [n. d.]. TFRecord and tf.train.Example. https:\/\/www.tensorflow.org\/tutorials\/load_data\/tfrecord. Accessed: 2025-07-23."},{"key":"e_1_3_3_1_50_2","unstructured":"Francesco Versaci and Giovanni Busonera. 2025. Hiding Latencies in Network-Based Image Loading for Deep Learning. arxiv:https:\/\/arXiv.org\/abs\/2503.22643\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2503.22643"},{"key":"e_1_3_3_1_51_2","first-page":"213","volume-title":"Proceedings of the 2018 USENIX Annual Technical Conference (ATC \u201918)","author":"Wang Xiaoyun","year":"2018","unstructured":"Xiaoyun Wang and Ian Goldberg. 2018. GreenTCP: Energy\u2011Aware TCP with Dynamic Congestion Window Adaptation. In Proceedings of the 2018 USENIX Annual Technical Conference (ATC \u201918). USENIX Association, 213\u2013225. https:\/\/www.usenix.org\/conference\/atc18\/presentation\/wang"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2019.00037"},{"key":"e_1_3_3_1_53_2","volume-title":"International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","author":"Zhu Yue","year":"2018","unstructured":"Yue Zhu, Fahim Chowdhury, Huansong Fu, Adam Moody, Kathryn Mohror, Kento Sato, and Weikuan Yu. 2018. Entropy\u2011Aware I\/O Pipelining for Large\u2011Scale Deep Learning on HPC Systems. In International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767566","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:30:31Z","timestamp":1767987031000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":52,"alternative-id":["10.1145\/3731599.3767566","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767566","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}