{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:07:23Z","timestamp":1778760443806,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"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":[[2026,4,23]]},"DOI":"10.1145\/3746467.3801513","type":"proceedings-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:32Z","timestamp":1778756792000},"page":"270-275","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Identifying the Optimal Number of DataLoader Workers for CPU-GPU Concurrency in Asynchronous Deep Training Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7019-1979","authenticated-orcid":false,"given":"Michael","family":"Seavers","sequence":"first","affiliation":[{"name":"Western Kentucky University, Bowling Green, KY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5554-5647","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"SEAS, Western Kentucky University, Bowling Green, KY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Corrado Alessio. [n. d.]. Animal-10. https:\/\/www.kaggle.com\/datasets\/alessiocorrado99\/animals10\/discussion\/117317"},{"key":"e_1_3_2_1_2_1","unstructured":"Amazon. [n. d.]. Amazon EC2 P3dn Instances. https:\/\/aws.amazon.com\/ec2\/instance-types\/p3\/"},{"key":"e_1_3_2_1_3_1","first-page":"397","article-title":"Using Confidence Bounds for Exploitation-Exploration Trade-Offs","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using Confidence Bounds for Exploitation-Exploration Trade-Offs. Journal of Machine Learning Research 3, Nov (2002), 397\u2013422.","journal-title":"Journal of Machine Learning Research 3"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639232"},{"key":"e_1_3_2_1_5_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep Learning. Vol. 1. MIT Press Cambridge."},{"key":"e_1_3_2_1_6_1","volume-title":"Pipedream: Fast and Efficient Pipeline Parallel DNN Training. https:\/\/arxiv.org\/abs","author":"Harlap Aaron","year":"2018","unstructured":"Aaron Harlap, Deepak Narayanan, Amar Phanishayee, Vivek Seshadri, Nikhil Devanur, Greg Ganger, and Phil Gibbons. 2018. Pipedream: Fast and Efficient Pipeline Parallel DNN Training. https:\/\/arxiv.org\/abs"},{"key":"e_1_3_2_1_7_1","volume-title":"Jiquan Ngiam, Quoc V Le, Yonghui Wu, et al.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, et al. 2019. Gpipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Advances in Neural Information Processing Systems 32."},{"key":"e_1_3_2_1_8_1","volume-title":"The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems. arXiv preprint arXiv:2012.04210","author":"Inci Ahmet","year":"2020","unstructured":"Ahmet Inci, Evgeny Bolotin, Yaosheng Fu, Gal Dalal, Shie Mannor, David Nellans, and Diana Marculescu. 2020. The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems. arXiv preprint arXiv:2012.04210 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 93\u2013105","author":"Jangda Abhinav","year":"2024","unstructured":"Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi. 2024. A Framework for Fine-Grained Synchronization of Dependent GPU Kernels. In 2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 93\u2013105."},{"key":"e_1_3_2_1_10_1","volume-title":"Bpipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models. In International Conference on Machine Learning. PMLR, 16639\u201316653","author":"Kim Taebum","year":"2023","unstructured":"Taebum Kim, Hyoungjoo Kim, Gyeong-In Yu, and Byung-Gon Chun. 2023. Bpipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models. In International Conference on Machine Learning. PMLR, 16639\u201316653."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"High-Performance Data Loader for Large-Scale Data Processing","volume":"36","author":"Martinez-Noriega Edgar Josafat","year":"2024","unstructured":"Edgar Josafat Martinez-Noriega, Chen Peng, and Rio Yokota. 2024. High-Performance Data Loader for Large-Scale Data Processing. Electronic Imaging 36 (2024), 1\u20136.","journal-title":"Electronic Imaging"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2788396"},{"key":"e_1_3_2_1_13_1","volume-title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 360\u2013367","author":"Ofeidis Iason","year":"2024","unstructured":"Iason Ofeidis, Diego Kiedanski, and Leandros Tassiulas. 2024. An Overview of the Data-Loader Landscape: Comparative Performance Analysis. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 360\u2013367."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2018.07.010"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3749185"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587451"},{"key":"e_1_3_2_1_17_1","first-page":"17146","article-title":"A Deep Learning DataLoader with Shared Data Preparation","volume":"35","author":"Xu Jingwei","year":"2022","unstructured":"Jingwei Xu, Guochang Wang, Yuan Yao, Zenan Li, Chun Cao, Hanghang Tong, et al. 2022. A Deep Learning DataLoader with Shared Data Preparation. Advances in Neural Information Processing Systems 35 (2022), 17146\u201317156.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","volume-title":"Large Batch Training of Convolutional Networks. arXiv preprint arXiv:1708.03888","author":"You Yang","year":"2017","unstructured":"Yang You, Igor Gitman, and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arXiv preprint arXiv:1708.03888 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Scaling SGD Batch Size to 32k for ImageNet Training. arXiv preprint arXiv:1708.03888 6, 12","author":"You Yang","year":"2017","unstructured":"Yang You, Igor Gitman, and Boris Ginsburg. 2017. Scaling SGD Batch Size to 32k for ImageNet Training. arXiv preprint arXiv:1708.03888 6, 12 (2017), 6."},{"key":"e_1_3_2_1_20_1","volume-title":"Importance of Data Loading Pipeline in Training Deep Neural Networks. arXiv preprint arXiv:2005.02130","author":"Zolnouri Mahdi","year":"2020","unstructured":"Mahdi Zolnouri, Xinlin Li, and Vahid Partovi Nia. 2020. Importance of Data Loading Pipeline in Training Deep Neural Networks. arXiv preprint arXiv:2005.02130 (2020)."}],"event":{"name":"ACMSE 2026: 2026 ACM Southeast Conference","location":"Troy University Troy AL USA","acronym":"ACMSE 2026"},"container-title":["Proceedings of the 2026 ACM Southeast Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746467.3801513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:09:02Z","timestamp":1778756942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746467.3801513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":20,"alternative-id":["10.1145\/3746467.3801513","10.1145\/3746467"],"URL":"https:\/\/doi.org\/10.1145\/3746467.3801513","relation":{},"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"2026-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}