{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:14:53Z","timestamp":1769829293615,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the U.S. Department of Energy (DOE)","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]},{"name":"Exascale Computing Project","award":["17-SC-20-SC"],"award-info":[{"award-number":["17-SC-20-SC"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3588195.3592986","type":"proceedings-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T20:47:00Z","timestamp":1691441220000},"page":"155-167","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AIIO: Using Artificial Intelligence for Job-Level and Automatic I\/O Performance Bottleneck Diagnosis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0725-0833","authenticated-orcid":false,"given":"Bin","family":"Dong","sequence":"first","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3915-1135","authenticated-orcid":false,"given":"Jean Luca","family":"Bez","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3048-3448","authenticated-orcid":false,"given":"Suren","family":"Byna","sequence":"additional","affiliation":[{"name":"The Ohio State University & Lawrence Berkeley National Laboratory, Columbus, OH, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"TabNet: Attentive Interpretable Tabular Learning. CoRR","author":"Arik Sercan","year":"2019","unstructured":"Sercan \u00d6 mer Arik and Tomas Pfister. 2019. TabNet: Attentive Interpretable Tabular Learning. CoRR, Vol. abs\/1908.07442 (2019). showeprint[arXiv]1908.07442 http:\/\/arxiv.org\/abs\/1908.07442"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Dorian C. Arnold Dong H. Ahn Bronis R. de Supinski Gregory L. Lee Barton P. Miller and Martin Schulz. 2007. Stack Trace Analysis for Large Scale Debugging. In IPDPS. 1--10. https:\/\/doi.org\/10.1109\/IPDPS.2007.370254","DOI":"10.1109\/IPDPS.2007.370254"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Jiwoo Bang Chungyong Kim Kesheng Wu Alex Sim Suren Byna Hanul Sung and Hyeonsang Eom. 2021. An In-Depth I\/O Pattern Analysis in HPC Systems. In HiPC. 400--405. https:\/\/doi.org\/10.1109\/HiPC53243.2021.00056","DOI":"10.1109\/HiPC53243.2021.00056"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW56643.2022.00006"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531461"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW54622.2021.00008"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Neural Networks and Tabular Data: A Survey. CoRR","author":"Borisov Vadim","year":"1889","unstructured":"Vadim Borisov, Tobias Leemann, Kathrin Se\u00dfler, Johannes Haug, Martin Pawelczyk, and Gjergji Kasneci. 2021. Deep Neural Networks and Tabular Data: A Survey. CoRR, Vol. abs\/2110.01889 (2021). showeprint[arXiv]2110.01889 https:\/\/arxiv.org\/abs\/2110.01889"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-9822-9"},{"key":"e_1_3_2_1_9_1","volume-title":"Tuning HDF5 subfiling performance on parallel file systems. (5","author":"Byna Suren","year":"2017","unstructured":"Suren Byna, Mohamad Chaarawi, Quincey Koziol, John Mainzer, and Frank Willmore. 2017. Tuning HDF5 subfiling performance on parallel file systems. (5 2017). https:\/\/www.osti.gov\/biblio\/1398484"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.92"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289150"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_14_1","volume-title":"Lessons From Examining Repetitive Job Behavior and I\/O Performance Variability on a Production HPC System Emily Costa Northeastern University","author":"Costa Emily","year":"2021","unstructured":"Emily Costa, Tirthak Patel, Benjamin Schwaller, James Brandt, and Devesh Tiwari. 2021a. Lessons From Examining Repetitive Job Behavior and I\/O Performance Variability on a Production HPC System Emily Costa Northeastern University, USA Tirthak Patel Northeastern University, USA Benjamin Schwaller. \"OSTI\" (8 2021). https:\/\/www.osti.gov\/biblio\/1884199"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476186"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW51947.2020.00008"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/Grid.2012.11"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00035"},{"key":"e_1_3_2_1_19_1","volume-title":"Liudmila Ostroumova Prokhorenkova, and Aleksandr Vorobev","author":"Dorogush Anna Veronika","year":"2017","unstructured":"Anna Veronika Dorogush, Andrey Gulin, Gleb Gusev, Nikita Kazeev, Liudmila Ostroumova Prokhorenkova, and Aleksandr Vorobev. 2017. Fighting biases with dynamic boosting. CoRR, Vol. abs\/1706.09516 (2017). showeprint[arXiv]1706.09516 http:\/\/arxiv.org\/abs\/1706.09516"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos"},{"key":"e_1_3_2_1_21_1","volume-title":"The Elements of Statistical Learning","author":"Hastie Trevor","unstructured":"Trevor Hastie, Robert Tibshirani, and Jerome Friedman. 2001. The Elements of Statistical Learning. Springer New York Inc., New York, NY, USA."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1713072.1713082"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Axel Huebl R\u00e9mi Lehe Jean-Luc Vay David P. Grote Ivo F. Sbalzarini Stephan Kuschel and Michael Bussmann. 2017. Open Science with openPMD. https:\/\/doi.org\/10.5281\/zenodo.822396","DOI":"10.5281\/zenodo.822396"},{"key":"e_1_3_2_1_24_1","volume-title":"2022 SC22: International Conference for High Performance Computing, Networking, Storage and Analysis (SC) (SC). IEEE Computer Society","author":"Isakov M.","unstructured":"M. Isakov, M. Currier, E. Rosario, S. Madireddy, P. Balaprakash, P. Carns, R. B. Ross, G. K. Lockwood, and M. A. Kinsy. 2022. A Taxonomy of Error Sources in HPC I\/O Machine Learning Models. In 2022 SC22: International Conference for High Performance Computing, Networking, Storage and Analysis (SC) (SC). IEEE Computer Society, Los Alamitos, CA, USA, 205--218. https:\/\/doi.ieeecomputersociety.org\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROSS51935.2020.00010"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00037"},{"key":"e_1_3_2_1_27_1","volume-title":"Garnett (Eds.)","volume":"30","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/166955.166994"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of Cray User Group Meeting, CUG","author":"Li Tonglin","year":"2021","unstructured":"Tonglin Li, Suren Byna, Quincey Koziol, Houjun Tang, Jean Luca Bez, and Qiao Kang. 2021. h5bench: HDF5 I\/O Kernel Suite for Exercising HPC I\/O Patterns. In Proceedings of Cray User Group Meeting, CUG 2021."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00077"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1996130.1996139"},{"key":"e_1_3_2_1_32_1","volume-title":"Explainable AI for Trees: From Local Explanations to Global Understanding. CoRR","author":"Lundberg Scott M.","year":"2019","unstructured":"Scott M. Lundberg, Gabriel G. Erion, Hugh Chen, Alex J. DeGrave, Jordan M. Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. 2019. Explainable AI for Trees: From Local Explanations to Global Understanding. CoRR, Vol. abs\/1905.04610 (2019). showeprint[arXiv]1905.04610 http:\/\/arxiv.org\/abs\/1905.04610"},{"key":"e_1_3_2_1_33_1","first-page":"I","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.). Curran Associates, Inc., 4765--4774. http:\/\/papers.nips.cc\/paper\/7062-a-unified-approach-to-interpreting-model-predictions.pdf","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2002.1028437"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.539739"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS53633.2021.9614303"},{"key":"e_1_3_2_1_37_1","volume-title":"Approximation theory of the MLP model in neural networks. Acta numerica","author":"Pinkus Allan","year":"1999","unstructured":"Allan Pinkus. 1999. Approximation theory of the MLP model in neural networks. Acta numerica, Vol. 8 (1999), 143--195."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1374596.1374609"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050053"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","unstructured":"Seetharami Seelam I-Hsin Chung Ding-Yong Hong Hui-Fang Wen and Hao Yu. 2008. Early experiences in application level I\/O tracing on blue gene systems. In IPDPS. 1--8. https:\/\/doi.org\/10.1109\/IPDPS.2008.4536550","DOI":"10.1109\/IPDPS.2008.4536550"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_2_1_43_1","volume-title":"Learning Important Features Through Propagating Activation Differences. CoRR","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning Important Features Through Propagating Activation Differences. CoRR, Vol. abs\/1704.02685 (2017). showeprint[arXiv]1704.02685 http:\/\/arxiv.org\/abs\/1704.02685"},{"key":"e_1_3_2_1_44_1","volume-title":"Tabular Data: Deep Learning is Not All You Need. CoRR","author":"Shwartz-Ziv Ravid","year":"2021","unstructured":"Ravid Shwartz-Ziv and Amitai Armon. 2021. Tabular Data: Deep Learning is Not All You Need. CoRR, Vol. abs\/2106.03253 (2021). showeprint[arXiv]2106.03253 https:\/\/arxiv.org\/abs\/2106.03253"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2021.07.021"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/568014.379590"},{"key":"e_1_3_2_1_47_1","unstructured":"Feng Wang Qin Xin Bo Hong Scott A Brandt Ethan L Miller and Darrell Long. 2004. File system workload analysis for large scale scientific computing applications. (2004)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00021"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00062"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","unstructured":"Bing Xie Zilong Tan Philip Carns Jeff Chase Kevin Harms Jay Lofstead Sarp Oral Sudharshan S. Vazhkudai and Feiyi Wang. 2019. Applying Machine Learning to Understand Write Performance of Large-scale Parallel Filesystems. In PDSW. 30--39. https:\/\/doi.org\/10.1109\/PDSW49588.2019.00008","DOI":"10.1109\/PDSW49588.2019.00008"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00064"},{"key":"e_1_3_2_1_52_1","unstructured":"Izzet Yildirim Hariharan Devarajan Anthony Kougkas Xian-He Sun and Kathryn Mohror. 2022. A Multifaceted Approach to Automated I\/O Bottleneck Detection for HPC Workloads. https:\/\/sc22.supercomputing.org\/proceedings\/tech_poster\/tech_poster_pages\/rpost186.html"}],"event":{"name":"HPDC '23: The 32nd International Symposium on High-Performance Parallel and Distributed Computing","location":"Orlando FL USA","acronym":"HPDC '23","sponsor":["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 32nd International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592986","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3588195.3592986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:25Z","timestamp":1750178845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3588195.3592986"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":51,"alternative-id":["10.1145\/3588195.3592986","10.1145\/3588195"],"URL":"https:\/\/doi.org\/10.1145\/3588195.3592986","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}