{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:37:56Z","timestamp":1783784276354,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,23]],"date-time":"2020-06-23T00:00:00Z","timestamp":1592870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Office of Advanced Scientific Computing Research, Office of Science, of the U.S. Department of Energy under Contract","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]},{"name":"the National Research Foundation of Korea (NRF)","award":["2016M3C4A7952587, 2018R1C1B5085640, 21A20151113068"],"award-info":[{"award-number":["2016M3C4A7952587, 2018R1C1B5085640, 21A20151113068"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,23]]},"DOI":"10.1145\/3369583.3392678","type":"proceedings-article","created":{"date-parts":[[2020,6,22]],"date-time":"2020-06-22T03:27:27Z","timestamp":1592796447000},"page":"77-88","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Towards HPC I\/O Performance Prediction through Large-scale Log Analysis"],"prefix":"10.1145","author":[{"given":"Sunggon","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Sim","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kesheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suren","family":"Byna","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongseok","family":"Son","sequence":"additional","affiliation":[{"name":"Chung-Ang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeonsang","family":"Eom","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,6,23]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation ( OSDI 16). 265-- 283."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2834976.2834977"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600708"},{"key":"e_1_3_2_2_4_1","volume-title":"https:\/\/asc. llnl. gov\/sequoia\/benchmarks\/IOR summary v1. 0. pdf. Accessed January 5","author":"Benchmark IOR","year":"2020","unstructured":"IOR Benchmark. 2020. https:\/\/asc. llnl. gov\/sequoia\/benchmarks\/IOR summary v1. 0. pdf. Accessed January 5 (2020)."},{"key":"e_1_3_2_2_5_1","volume-title":"Noise reduction in speech processing","author":"Benesty Jacob","unstructured":"Jacob Benesty, Jingdong Chen, Yiteng Huang, and Israel Cohen. 2009. Pearson correlation coefficient. In Noise reduction in speech processing. Springer, 1--4."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289150"},{"key":"e_1_3_2_2_7_1","unstructured":"Fran\u00e7ois Chollet et al. 2015. Keras. https:\/\/keras.io."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1976.5408784"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00049"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/141975.142034"},{"key":"e_1_3_2_2_11_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classifica- tion with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/822076.822448"},{"key":"e_1_3_2_2_13_1","volume-title":"Pro- ceedings of the Conference on High Performance Computing Networking, Storage and Analysis","author":"Lang Samuel","unstructured":"Samuel Lang, Philip Carns, Robert Latham, Robert Ross, Kevin Harms, and William Allcock. 2009. I\/O performance challenges at leadership scale. In Pro- ceedings of the Conference on High Performance Computing Networking, Storage and Analysis. IEEE, 1--12."},{"key":"e_1_3_2_2_14_1","volume-title":"Matthew Wiener, et al","author":"Liaw Andy","year":"2002","unstructured":"Andy Liaw, Matthew Wiener, et al. 2002. Classification and regression by ran- domForest. R news 2, 3 (2002), 18--22."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00077"},{"key":"e_1_3_2_2_16_1","unstructured":"Glenn K Lockwood Nicholas J Wright Shane Snyder Philip Carns George Brown and Kevin Harms. 2018. TOKIO on ClusterStor: connecting standard tools to enable holistic I\/O performance analysis. (2018)."},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the High Performance Computing Symposium. Society for Computer Simulation International, 8.","author":"Lux Thomas CH","year":"2018","unstructured":"Thomas CH Lux, Layne T Watson, Tyler H Chang, Jon Bernard, Bo Li, Li Xu, Godmar Back, Ali R Butt, Kirk W Cameron, and Yili Hong. 2018. Predictive modeling of I\/O characteristics in high performance computing systems. In Proceedings of the High Performance Computing Symposium. Society for Computer Simulation International, 8."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.98"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.58"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-92bf1922-00a"},{"key":"e_1_3_2_2_21_1","first-page":"1","article-title":"SFS: random write considered harmful in solid state drives","volume":"12","author":"Min Changwoo","year":"2012","unstructured":"Changwoo Min, Kangnyeon Kim, Hyunjin Cho, Sang-Won Lee, and Young Ik Eom. 2012. SFS: random write considered harmful in solid state drives.. In FAST, Vol. 12. 1--16.","journal-title":"FAST"},{"key":"e_1_3_2_2_22_1","volume-title":"International Statistical and Optimization Perspectives Workshop\" Subspace, Latent Structure and Feature Selection\". Springer, 127--138","author":"Navot Amir","year":"2005","unstructured":"Amir Navot, Ran Gilad-Bachrach, Yiftah Navot, and Naftali Tishby. 2005. Is feature selection still necessary?. In International Statistical and Optimization Perspectives Workshop\" Subspace, Latent Structure and Feature Selection\". Springer, 127--138."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.159058"},{"key":"e_1_3_2_2_24_1","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. Journal of machine learning research 12, Oct (2011), 2825--2830.","journal-title":"Journal of machine learning research 12"},{"key":"e_1_3_2_2_25_1","first-page":"617","article-title":"An introduction to the infiniband architecture","volume":"42","author":"Pfister Gregory F","year":"2001","unstructured":"Gregory F Pfister. 2001. An introduction to the infiniband architecture. High Performance Mass Storage and Parallel I\/O 42 (2001), 617--632.","journal-title":"High Performance Mass Storage and Parallel I\/O"},{"key":"e_1_3_2_2_26_1","volume-title":"Andrei Socoliuc, Olaf Weiser, et al.","author":"Quintero Dino","year":"2017","unstructured":"Dino Quintero, Luis Bolinches, Puneet Chaudhary, Willard Davis, Steve Duersch, Carlos Henrique Fachim, Andrei Socoliuc, Olaf Weiser, et al. 2017. IBM Spectrum Scale (formerly GPFS). IBM Redbooks."},{"key":"e_1_3_2_2_27_1","volume-title":"Mathematischer Statistiker, Calyampudi Radhakrishna Rao, and Calyampudi Radhakrishna Rao.","author":"Rao Calyampudi Radhakrishna","year":"1973","unstructured":"Calyampudi Radhakrishna Rao, Calyampudi Radhakrishna Rao, Mathematischer Statistiker, Calyampudi Radhakrishna Rao, and Calyampudi Radhakrishna Rao. 1973. Linear statistical inference and its applications. Vol. 2. Wiley New York."},{"key":"e_1_3_2_2_28_1","first-page":"19","article-title":"Predicting I\/O performance in HPC using artificial neural networks","volume":"3","author":"Schmidt Jan F","year":"2016","unstructured":"Jan F Schmidt and Julian M Kunkel. 2016. Predicting I\/O performance in HPC using artificial neural networks. Supercomputing Frontiers and Innovations 3, 3 (2016), 19--33.","journal-title":"Supercomputing Frontiers and Innovations"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the 2003 Linux symposium","volume":"2003","author":"Philip","unstructured":"Philip Schwan et al. 2003. Lustre: Building a file system for 1000-node clusters. In Proceedings of the 2003 Linux symposium, Vol. 2003. 380--386."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413413"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESPT.2016.006"},{"key":"e_1_3_2_2_32_1","volume-title":"13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16)","author":"Venkataraman Shivaram","year":"2016","unstructured":"Shivaram Venkataraman, Zongheng Yang, Michael Franklin, Benjamin Recht, and Ion Stoica. 2016. Ernest: efficient performance prediction for large-scale advanced analytics. In 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16). 363--378."},{"key":"e_1_3_2_2_33_1","volume-title":"Efficient greedy learning of Gaussian mixture models. Neural computation 15, 2","author":"Verbeek Jakob J","year":"2003","unstructured":"Jakob J Verbeek, Nikos Vlassis, and Ben Kr\u00f6se. 2003. Efficient greedy learning of Gaussian mixture models. Neural computation 15, 2 (2003), 469--485."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00062"},{"key":"e_1_3_2_2_35_1","unstructured":"CM Herb Wartens and Jim Garlick. 2010. LMT-The Lustre Monitoring Tool."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078614"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/10968987_3"}],"event":{"name":"HPDC '20: The 29th International Symposium on High-Performance Parallel and Distributed Computing","location":"Stockholm Sweden","acronym":"HPDC '20","sponsor":["University of Arizona University of Arizona","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369583.3392678","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369583.3392678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:58Z","timestamp":1750203898000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3369583.3392678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,23]]},"references-count":37,"alternative-id":["10.1145\/3369583.3392678","10.1145\/3369583"],"URL":"https:\/\/doi.org\/10.1145\/3369583.3392678","relation":{},"subject":[],"published":{"date-parts":[[2020,6,23]]},"assertion":[{"value":"2020-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}