{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:22:29Z","timestamp":1768029749561,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":50,"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":[{"DOI":"10.13039\/501100007601","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["754304"],"award-info":[{"award-number":["754304"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,23]]},"DOI":"10.1145\/3369583.3392674","type":"proceedings-article","created":{"date-parts":[[2020,6,22]],"date-time":"2020-06-22T03:27:27Z","timestamp":1592796447000},"page":"101-112","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["DCDB Wintermute: Enabling Online and Holistic Operational Data Analytics on HPC Systems"],"prefix":"10.1145","author":[{"given":"Alessio","family":"Netti","sequence":"first","affiliation":[{"name":"Leibniz Supercomputing Centre, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micha","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Leibniz Supercomputing Centre, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carla","family":"Guillen","sequence":"additional","affiliation":[{"name":"Leibniz Supercomputing Centre, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Ott","sequence":"additional","affiliation":[{"name":"Leibniz Supercomputing Centre, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Tafani","sequence":"additional","affiliation":[{"name":"Leibniz Supercomputing Centre, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gence","family":"Ozer","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Schulz","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,6,23]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.18"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00069"},{"key":"e_1_3_2_2_3_1","volume-title":"Taxonomist: Application Detection Through Rich Monitoring Data. In Proc. of Euro-Par","author":"Ates Emre","year":"2018","unstructured":"Emre Ates, Ozan Tuncer, Ata Turk, Vitus J. Leung, et al. 2018. Taxonomist: Application Detection Through Rich Monitoring Data. In Proc. of Euro-Par 2018. Springer."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07518-1_25"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00118"},{"key":"e_1_3_2_2_6_1","volume-title":"Proc. of USENIX","volume":"138","author":"Bash Cullen","year":"2007","unstructured":"Cullen Bash and George Forman. 2007. Cool Job Allocation: Measuring the Power Savings of Placing Jobs at Cooling-Efficient Locations in the Data Center.. In Proc. of USENIX 2007, Vol. 138. 140."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339186.3339213"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927143"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3339186.3339210"},{"key":"e_1_3_2_2_10_1","unstructured":"Norman Bourassa and Michael Ott. 2019. EEHPCWG Operational Data Analytics Survey. https:\/\/eehpcwg.llnl.gov\/assets\/sc19_11_425_525_operational_data_analytics_ott_bourassa.pdf"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Franck Cappello Al Geist William Gropp Sanjay Kale et al. 2014. Toward exascale resilience: 2014 update. Supercomputing frontiers and innovations Vol. 1 1 (2014) 5--28.","DOI":"10.14529\/jsfi140101"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2015.1100"},{"key":"e_1_3_2_2_13_1","volume-title":"Proc. of IPDPS","author":"Corbalan Julita","year":"2018","unstructured":"Julita Corbalan and Luigi Brochard. submitted. EAR: Energy management framework for supercomputers. In Proc. of IPDPS 2018. IEEE."},{"key":"e_1_3_2_2_14_1","volume-title":"The LINPACK benchmark: past, present and future. Concurrency and Computation: practice and experience","author":"Dongarra Jack J","year":"2003","unstructured":"Jack J Dongarra, Piotr Luszczek, and Antoine Petitet. 2003. The LINPACK benchmark: past, present and future. Concurrency and Computation: practice and experience, Vol. 15, 9 (2003), 803--820."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58667-0_21"},{"key":"e_1_3_2_2_16_1","volume-title":"Proc. of CLOUD","author":"Ejarque Jorge","year":"2010","unstructured":"Jorge Ejarque, Andras Micsik, Raul Sirvent, Peter Pallinger, et al. 2010. Semantic resource allocation with historical data based predictions. In Proc. of CLOUD 2010. IARIA."},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. of JSSPP","author":"Emeras Joseph","year":"2015","unstructured":"Joseph Emeras, S\u00e9bastien Varrette, Mateusz Guzek, and Pascal Bouvry. 2015. Evalix: Classification and Prediction of Job Resource Consumption on HPC Platforms. In Proc. of JSSPP 2015. Springer, 102--122."},{"key":"e_1_3_2_2_18_1","volume-title":"Proc. of MOD","author":"Galleguillos Cristian","year":"2017","unstructured":"Cristian Galleguillos, Alina Sirbu, Zeynep Kiziltan, Ozalp Babaoglu, et al. 2017. Data-driven job dispatching in HPC systems. In Proc. of MOD 2017. Springer, 449--461."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2015.114"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126935"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2831129.2831133"},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of REPARA Workshop","author":"Griebler Dalvan","year":"2018","unstructured":"Dalvan Griebler, Daniele De Sensi, Adriano Vogel, Marco Danelutto, et al. 2018. Service Level Objectives via C+ 11 Attributes. In Proc. of REPARA Workshop 2018. Springer."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2013.29"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14313-2_31"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225088"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225086"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00072"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322236"},{"key":"e_1_3_2_2_29_1","volume-title":"Proc. of LCI","author":"Knapp Rashawn L","year":"2007","unstructured":"Rashawn L Knapp, Kathryn Mohror, Aaron Amauba, Karen L Karavanic, et al. 2007. PerfTrack: Scalable application performance diagnosis for linux clusters. In Proc. of LCI 2007. Citeseer, 15--17."},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. of IC2E","author":"Lin X.","year":"2016","unstructured":"X. Lin, Y. Wang, and M. Pedram. 2016. A Reinforcement Learning-Based Power Management Framework for Green Computing Data Centers. In Proc. of IC2E 2016. IEEE, 135--138."},{"key":"e_1_3_2_2_31_1","volume-title":"Mq telemetry transport (mqtt) v3. 1 protocol specification. IBM developerWorks Technical Library","author":"Locke Dave","year":"2010","unstructured":"Dave Locke. 2010. Mq telemetry transport (mqtt) v3. 1 protocol specification. IBM developerWorks Technical Library (2010), 15."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2004.04.001"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.98"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2016.58"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2018.00104"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356191"},{"key":"e_1_3_2_2_37_1","volume-title":"Proc. of PMACS Workshop","author":"Ozer Gence","year":"2019","unstructured":"Gence Ozer, Sarthak Garg, Neda Davoudi, Gabrielle Poerwawinata, et al. 2019. Towards a Predictive Energy Model for HPC Runtime Systems Using Supervised Learning. In Proc. of PMACS Workshop 2019. Springer."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730550"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.08.235"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_9"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-016-0564-y"},{"key":"e_1_3_2_2_42_1","unstructured":"Ozan Tuncer Emre Ates Yijia Zhang Ata Turk et al. 2018. Online Diagnosis of Performance Variation in HPC Systems Using Machine Learning. IEEE Transactions on Parallel and Distributed Systems (2018)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126946"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375555"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.73"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2017.7858403"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_2_48_1","volume-title":"Proc. of ICPP","author":"Michael R","year":"2018","unstructured":"Michael R Wyatt II, Stephen Herbein, Todd Gamblin, Adam Moody, et al. 2018. PRIONN: Predicting Runtime and IO using Neural Networks. In Proc. of ICPP 2018. ACM, 46."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CNSM.2015.7367348"},{"key":"e_1_3_2_2_50_1","volume-title":"Proc. of PDPTA","author":"Zhang Hao","year":"2012","unstructured":"Hao Zhang, Haihang You, Bilel Hadri, and Mark Fahey. 2012. HPC usage behavior analysis and performance estimation with machine learning techniques. In Proc. of PDPTA 2012. 1."}],"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\/3369583.3392674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3369583.3392674","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\/3369583.3392674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,23]]},"references-count":50,"alternative-id":["10.1145\/3369583.3392674","10.1145\/3369583"],"URL":"https:\/\/doi.org\/10.1145\/3369583.3392674","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"}}]}}