{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:54:19Z","timestamp":1773510859965,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825421","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"360-367","source":"Crossref","is-referenced-by-count":1,"title":["An Overview of the Data-Loader Landscape: Comparative Performance Analysis"],"prefix":"10.1109","author":[{"given":"Iason","family":"Ofeidis","sequence":"first","affiliation":[{"name":"Yale University,New Haven,CT,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Kiedanski","sequence":"additional","affiliation":[{"name":"Tryolabs,Montevideo,Uruguay"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leandros","family":"Tassiulas","sequence":"additional","affiliation":[{"name":"Yale University,New Haven,CT,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref2","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912200"},{"issue":"4","key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3320060","article-title":"Demystifying parallel and distributed deep learning: An in-depth concurrency analysis","volume":"52","author":"Ben-Nun","year":"2019","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref6","article-title":"Analyzing and mitigating data stalls in dnn training","author":"Mohan","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3331526"},{"key":"ref8","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01156"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref12","article-title":"Amazon s3: Object storage built to retrieve any amount of data from anywhere","year":"2022"},{"key":"ref13","article-title":"Azure blob storage: Massively scalable and secure object storage for cloud-native workloads, archives, data lakes, high-performance computing, and machine learning","year":"2024"},{"key":"ref14","article-title":"Profiling and improving the pytorch dataloader for high-latency storage: A technical report","author":"Svogor","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2019.00037"},{"key":"ref16","first-page":"33","article-title":"Plumber: Diagnosing and removing performance bottlenecks in machine learning data pipelines","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Kuchnik"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00018"},{"key":"ref18","article-title":"Aibench: An agile domain-specific benchmarking methodology and an ai benchmark suite","author":"Gao","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3352020.3352024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2019.2928551"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref22","first-page":"623","article-title":"dpro: A generic performance diagnosis and optimization toolkit for expediting distributed dnn training","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Hu"},{"key":"ref23","article-title":"DLBench","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00127"},{"issue":"8","key":"ref25","first-page":"2","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"Hinton","year":"2012","journal-title":"Cited on"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08453-9"},{"key":"ref27","article-title":"Guidelines for assigning num_workers to dataloader","author":"Forums","year":"2017"},{"key":"ref28","article-title":"Nvidia data loading library (dali)","year":"2024"},{"key":"ref29","article-title":"Torchdata: A prototype library of common modular data loading primitives for easily constructing flexible and performant data pipelines","year":"2021"},{"key":"ref30","article-title":"Deep lake: a lakehouse for deep learning","author":"Hambardzumyan","year":"2022"},{"key":"ref31","article-title":"Squirrel: A python library that enables ml teams to share, load, and transform data in a collaborative, flexible, and efficient way","volume-title":"GitHub","author":"Team","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005703"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Torchvision: Pytorch\u2019s computer vision library","author":"Contributors","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/DLS49591.2019.00015"},{"key":"ref38","article-title":"Blink: A fast nvlink-based collective communication library","volume-title":"Proc. Conf. Syst. Mach. Learn","author":"Wang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825421.pdf?arnumber=10825421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:14:36Z","timestamp":1737101676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825421","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}