{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:40:12Z","timestamp":1755870012103,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,17]]},"DOI":"10.1145\/3626203.3670597","type":"proceedings-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T20:12:20Z","timestamp":1721247140000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Research Dataset-Sharing Strategies for Concurrent AI Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2411-3314","authenticated-orcid":false,"given":"Yongnuo","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3383-2191","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7601-0702","authenticated-orcid":false,"given":"Michael D.","family":"Weiner","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4302-4227","authenticated-orcid":false,"given":"Aaron","family":"Jezghani","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6710-9244","authenticated-orcid":false,"given":"J. Eric","family":"Coulter","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7258-8665","authenticated-orcid":false,"given":"Ruben","family":"Lara","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8917-8934","authenticated-orcid":false,"given":"Ronald","family":"Rahaman","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2770-0192","authenticated-orcid":false,"given":"Kenneth J.","family":"Suda","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1407-7741","authenticated-orcid":false,"given":"Jeffrey","family":"Valdez","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2018-3966","authenticated-orcid":false,"given":"Dee","family":"Womack","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1665-4837","authenticated-orcid":false,"given":"Dan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Partnership for an Advanced Computing Environment, Georgia Institute of Technology, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1109\/BigData47090.2019.9005703"},{"unstructured":"ML Commons. 2024. Croissant Working Group. https:\/\/mlcommons.org\/working-groups\/data\/croissant\/.","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1145\/3624062.3624131"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1101\/2021.10.04.463034"},{"unstructured":"Google. 2024. ArrayRecord. https:\/\/github.com\/google\/array_record.","key":"e_1_3_2_1_5_1"},{"unstructured":"Google. 2024. Riegeli. https:\/\/github.com\/google\/riegeli.","key":"e_1_3_2_1_6_1"},{"unstructured":"Jeremy Howard. [n. d.]. imagenette. https:\/\/github.com\/fastai\/imagenette\/","key":"e_1_3_2_1_7_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1038\/s41586-021-03819-2"},{"unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Technical Report.","key":"e_1_3_2_1_9_1"},{"unstructured":"Lustre. 2024. An open-source high performance parallel file system. https:\/\/www.lustre.org\/.","key":"e_1_3_2_1_10_1"},{"unstructured":"NVIDIA. [n. d.]. NVIDIA\/nccl: Optimized primitives for collective multi-GPU communication. https:\/\/github.com\/NVIDIA\/nccl. (Accessed on 04\/23\/2024).","key":"e_1_3_2_1_11_1"},{"unstructured":"Georgia Tech\u00a0College of Engineering. 2024. Georgia Tech AI Makerspace. https:\/\/coe.gatech.edu\/academics\/ai-for-engineering\/ai-makerspace.","key":"e_1_3_2_1_12_1"},{"unstructured":"Pytorch. 2024. DataLoader. https:\/\/pytorch.org\/tutorials\/beginner\/basics\/data_tutorial.html.","key":"e_1_3_2_1_13_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.1007\/s11263-015-0816-y"},{"unstructured":"Tensorflow. [n. d.]. Better performance with the tf.data API - TensorFlow Core. https:\/\/www.tensorflow.org\/guide\/data_performance#parallelizing_data_extraction. (Accessed on 04\/21\/2024).","key":"e_1_3_2_1_15_1"},{"unstructured":"Tensorflow. 2024. Tensorflow Dataset. https:\/\/www.tensorflow.org\/datasets\/tfless_tfds.","key":"e_1_3_2_1_16_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1109\/CVPR.2017.634"}],"event":{"sponsor":["SIGAPP ACM Special Interest Group on Applied Computing","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"acronym":"PEARC '24","name":"PEARC '24: Practice and Experience in Advanced Research Computing","location":"Providence RI USA"},"container-title":["Practice and Experience in Advanced Research Computing 2024: Human Powered Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670597","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626203.3670597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:58:57Z","timestamp":1755867537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626203.3670597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":17,"alternative-id":["10.1145\/3626203.3670597","10.1145\/3626203"],"URL":"https:\/\/doi.org\/10.1145\/3626203.3670597","relation":{},"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"2024-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}