{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T10:42:26Z","timestamp":1786099346990,"version":"3.56.0"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"am","delay-in-days":353,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Performance Evaluation"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1016\/j.peva.2022.102318","type":"journal-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T17:51:55Z","timestamp":1662400315000},"page":"102318","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":5,"special_numbering":"C","title":["I\/O performance analysis of machine learning workloads on leadership scale supercomputer"],"prefix":"10.1016","volume":"157-158","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7270-8847","authenticated-orcid":false,"given":"Ahmad Maroof","family":"Karimi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnab K.","family":"Paul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.peva.2022.102318_b1","series-title":"International Symposium on Cluster Computing and the Grid","first-page":"783","article-title":"Reliability-aware approach: An incremental checkpoint\/restart model in HPC environments","author":"Naksinehaboon","year":"2008"},{"key":"10.1016\/j.peva.2022.102318_b2","series-title":"Workshop on Big Data Benchmarks, Performance Optimization, and Emerging Hardware","first-page":"85","article-title":"I\/O characterization of big data workloads in data centers","author":"Pan","year":"2014"},{"issue":"3","key":"10.1016\/j.peva.2022.102318_b3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2027066.2027068","article-title":"Understanding and improving computational science storage access through continuous characterization","volume":"7","author":"Carns","year":"2011","journal-title":"ACM Trans. Storage (TOS)"},{"key":"10.1016\/j.peva.2022.102318_b4","doi-asserted-by":"crossref","unstructured":"B.K. Pasquale, G.C. Polyzos, Dynamic I\/O Characterization of I\/O Intensive Scientific Applications, in: ACM\/IEEE Conference on Supercomputing, 1994, pp. 660\u2013669.","DOI":"10.1109\/SUPERC.1994.344330"},{"key":"10.1016\/j.peva.2022.102318_b5","series-title":"International Symposium on Performance Evaluation of Computer & Telecommunication Systems","first-page":"133","article-title":"I\/O characterization on a parallel file system","author":"Narayan","year":"2010"},{"key":"10.1016\/j.peva.2022.102318_b6","doi-asserted-by":"crossref","unstructured":"F. Chowdhury, Y. Zhu, T. Heer, S. Paredes, A. Moody, R. Goldstone, K. Mohror, W. Yu, I\/O Characterization and Performance Evaluation of BeeGFS for Deep Learning, in: International Conference on Parallel Processing, ICPP, 2019, pp. 1\u201310.","DOI":"10.1145\/3337821.3337902"},{"key":"10.1016\/j.peva.2022.102318_b7","series-title":"International Conference on Cluster Computing","first-page":"359","article-title":"tf-Darshan: Understanding fine-grained I\/O performance in machine learning workloads","author":"Chien","year":"2020"},{"key":"10.1016\/j.peva.2022.102318_b8","doi-asserted-by":"crossref","unstructured":"G.K. Lockwood, S. Snyder, S. Byna, P. Carns, N.J. Wright, Understanding Data Motion in the Modern HPC Data Center, in: IEEE\/ACM International Parallel Data Systems Workshop, PDSW, 2019, pp. 74\u201383.","DOI":"10.1109\/PDSW49588.2019.00012"},{"key":"10.1016\/j.peva.2022.102318_b9","series-title":"International Conference on High Performance Computing, Data, and Analytics","first-page":"202","article-title":"Understanding HPC application I\/O behavior using system level statistics","author":"Paul","year":"2020"},{"key":"10.1016\/j.peva.2022.102318_b10","doi-asserted-by":"crossref","unstructured":"H. Luu, B. Behzad, R. Aydt, M. Winslett, A Multi-level Approach for Understanding I\/O Activity in HPC Applications, in: IEEE International Conference on Cluster Computing, CLUSTER, 2013, pp. 1\u20135.","DOI":"10.1109\/CLUSTER.2013.6702690"},{"issue":"2","key":"10.1016\/j.peva.2022.102318_b11","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1093\/comjnl\/bxs044","article-title":"Parallel file system analysis through application I\/O tracing","volume":"56","author":"Wright","year":"2012","journal-title":"Comput. J.","ISSN":"https:\/\/id.crossref.org\/issn\/0010-4620","issn-type":"print"},{"key":"10.1016\/j.peva.2022.102318_b12","series-title":"Darshan - HPC I\/O characterization tool","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b13","series-title":"Workshop on Extreme-Scale Programming Tools","first-page":"9","article-title":"Modular HPC I\/O characterization with darshan","author":"Snyder","year":"2016"},{"key":"10.1016\/j.peva.2022.102318_b14","doi-asserted-by":"crossref","unstructured":"P. Carns, R. Latham, R. Ross, K. Iskra, S. Lang, K. Riley, 24\/7 Characterization of Petascale I\/O Workloads, in: IEEE International Conference on Cluster Computing and Workshop, 2009, pp. 1\u201310.","DOI":"10.1109\/CLUSTR.2009.5289150"},{"key":"10.1016\/j.peva.2022.102318_b15","series-title":"The International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"807","article-title":"An ephemeral burst-buffer file system for scientific applications","author":"Wang","year":"2016"},{"key":"10.1016\/j.peva.2022.102318_b16","series-title":"IBM spectrum scale (GPFS)","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b17","series-title":"Summit","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b18","series-title":"Top 500 - june 2021","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b19","series-title":"2021 29th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems","first-page":"1","article-title":"Characterizing machine learning I\/O workloads on leadership scale HPC systems","author":"Paul","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b20","unstructured":"T. Patel, S. Byna, G.K. Lockwood, N.J. Wright, P. Carns, R. Ross, D. Tiwari, Uncovering Access, Reuse, and Sharing Characteristics of I\/O-Intensive Files on Large-Scale Production HPC Systems, in: 18th USENIX Conference on File and Storage Technologies, FAST 20, 2020, pp. 91\u2013101."},{"key":"10.1016\/j.peva.2022.102318_b21","doi-asserted-by":"crossref","unstructured":"W. Shin, V. Oles, A.M. Karimi, J.A. Ellis, F. Wang, Revealing Power, Energy and Thermal Dynamics of a 200PF Pre-exascale Supercomputer, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC, 2021, pp. 1\u201314.","DOI":"10.1145\/3458817.3476188"},{"key":"10.1016\/j.peva.2022.102318_b22","series-title":"Summit scheduling policy","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b23","doi-asserted-by":"crossref","unstructured":"A. Kougkas, H. Devarajan, X.-H. Sun, Hermes: A Heterogeneous-aware Multi-tiered Distributed I\/O Buffering System, in: International Symposium on High-Performance Parallel and Distributed Computing, HPDC, 2018, pp. 219\u2013230.","DOI":"10.1145\/3208040.3208059"},{"issue":"1","key":"10.1016\/j.peva.2022.102318_b24","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s11390-020-9781-1","article-title":"I\/O acceleration via multi-tiered data buffering and prefetching","volume":"35","author":"Kougkas","year":"2020","journal-title":"J. Comput. Sci. Tech."},{"key":"10.1016\/j.peva.2022.102318_b25","series-title":"Burst buffer on summit","year":"2021"},{"key":"10.1016\/j.peva.2022.102318_b26","series-title":"Density Estimation for Statistics and Data Analysis","author":"Silverman","year":"2018"},{"key":"10.1016\/j.peva.2022.102318_b27","doi-asserted-by":"crossref","unstructured":"J.L. Bez, A.M. Karimi, A.K. Paul, B. Xie, S. Byna, P. Carns, S. Oral, F. Wang, J. Hanley, Access Patterns and Performance Behaviors of Multi-layer Supercomputer I\/O Subsystems under Production Load, in: Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, HPDC, 2022, pp. 43\u201355.","DOI":"10.1145\/3502181.3531461"},{"key":"10.1016\/j.peva.2022.102318_b28","doi-asserted-by":"crossref","unstructured":"A.K. Paul, J.Y. Choi, A.M. Karimi, F. Wang, Machine Learning Assisted HPC Workload Trace Generation for Leadership Scale Storage Systems, in: Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, HPDC, 2022, pp. 199\u2013212.","DOI":"10.1145\/3502181.3531457"}],"container-title":["Performance Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0166531622000268?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0166531622000268?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T14:58:19Z","timestamp":1759071499000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0166531622000268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":28,"alternative-id":["S0166531622000268"],"URL":"https:\/\/doi.org\/10.1016\/j.peva.2022.102318","relation":{},"ISSN":["0166-5316"],"issn-type":[{"value":"0166-5316","type":"print"}],"subject":[],"published":{"date-parts":[[2022,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"I\/O performance analysis of machine learning workloads on leadership scale supercomputer","name":"articletitle","label":"Article Title"},{"value":"Performance Evaluation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.peva.2022.102318","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102318"}}