{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:39:33Z","timestamp":1767137973682,"version":"build-2238731810"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319969824","type":"print"},{"value":"9783319969831","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-96983-1_12","type":"book-chapter","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T11:50:06Z","timestamp":1533037806000},"page":"163-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Early Termination of Failed HPC Jobs Through Machine and Deep Learning"],"prefix":"10.1007","author":[{"given":"Micha\u0142","family":"Zasadzi\u0144ski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Munt\u00e9s-Mulero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Sol\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Carrera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Ludwig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,1]]},"reference":[{"issue":"3","key":"12_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00516ED2V01Y201306CAC024","volume":"8","author":"LA Barroso","year":"2013","unstructured":"Barroso, L.A., Clidaras, J., H\u00f6lzle, U.: The datacenter as a computer: an introduction to the design of warehouse-scale machines. Synth. Lect. Comput. Archit. 8(3), 1\u2013154 (2013)","journal-title":"Synth. Lect. Comput. Archit."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Gainaru, A., Perarnau, S., et al.: Reducing waste in extreme scale systems through introspective analysis. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 212\u2013221 (2016)","DOI":"10.1109\/IPDPS.2016.100"},{"issue":"Suppl. C","key":"12_CR3","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2017.06.005","volume":"67","author":"M Casas","year":"2017","unstructured":"Casas, M., Bronevetsky, G.: Prediction of the impact of network switch utilization on application performance via active measurement. Parallel Comput. 67(Suppl. C), 38\u201356 (2017)","journal-title":"Parallel Comput."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Clark, A.D., Tellez, L.M., Besse, S., et al.: Dynamic prediction and estimation of intentional failures in HPCs. In: International Conference on Advances in Social Networks Analysis and Mining, pp. 1244\u20131250 (2016)","DOI":"10.1109\/ASONAM.2016.7752397"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"El-Sayed, N., Schroeder, B.: Reading between the lines of failure logs: understanding how HPC systems fail. In: 43rd Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN), pp. 1\u201312 (2013)","DOI":"10.1109\/DSN.2013.6575356"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Fu, S., Xu, C.Z.: Exploring event correlation for failure prediction in coalitions of clusters. In: Proceedings of the Conference on Supercomputing, pp. 41:1\u201341:12 (2007)","DOI":"10.1145\/1362622.1362678"},{"key":"12_CR7","unstructured":"Gao, J.: Machine learning applications for data center optimization. Google White Paper (2014). https:\/\/research.google.com\/pubs\/archive\/42542.pdf"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Gu, J., Zheng, Z., Lan, Z., et al.: Dynamic meta-learning for failure prediction in large-scale systems: a case study. In: 37th International Conference on Parallel Processing (2008)","DOI":"10.1109\/ICPP.2008.17"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, S., Patel, T., Engelmann, C., et al.: Failures in large scale systems: long-term measurement, analysis, and implications. In: SC 2017, pp. 1\u201312 (2017)","DOI":"10.1145\/3126908.3126937"},{"key":"12_CR10","unstructured":"Jones, M.D., White, J.P., Innus, M., et al.: Workload analysis of blue waters. CoRR abs\/1703.00924 (2017). http:\/\/arxiv.org\/abs\/1703.00924"},{"issue":"7553","key":"12_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Nakka, N., Agrawal, A., Choudhary, A.: Predicting node failure in high performance computing systems from failure and usage logs. In: 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PhD Forum, pp. 1557\u20131566, May 2011","DOI":"10.1109\/IPDPS.2011.310"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Nie, B., Xue, J., Gupta, S., et al.: Characterizing temperature, power, and soft-error behaviors in data center systems: insights, challenges, and opportunities. In: IEEE 25th MASCOTS, pp. 22\u201331 (2017)","DOI":"10.1109\/MASCOTS.2017.12"},{"issue":"3","key":"12_CR14","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/21.97458","volume":"21","author":"SR Safavian","year":"1991","unstructured":"Safavian, S.R., Landgrebe, D.: A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybern. Syst. 21(3), 660\u2013674 (1991)","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"2","key":"12_CR15","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1007\/s10586-016-0564-y","volume":"19","author":"A S\u00eerbu","year":"2016","unstructured":"S\u00eerbu, A., Babaoglu, O.: Towards operator-less data centers through data-driven, predictive, proactive autonomics. J. Cluster Comput. 19(2), 865\u2013878 (2016)","journal-title":"J. Cluster Comput."},{"issue":"1","key":"12_CR16","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-319-58667-0_19","volume-title":"High Performance Computing","author":"O Tuncer","year":"2017","unstructured":"Tuncer, O., et al.: Diagnosing performance variations in HPC applications using machine learning. In: Kunkel, J.M., Yokota, R., Balaji, P., Keyes, D. (eds.) ISC 2017. LNCS, vol. 10266, pp. 355\u2013373. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58667-0_19"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Vishwanath, K.V., Nagappan, N.: Characterizing cloud computing hardware reliability. In: Proceedings of the 1st ACM Symposium on Cloud Computing, pp. 193\u2013204. ACM (2010)","DOI":"10.1145\/1807128.1807161"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.parco.2016.05.015","volume":"57","author":"S Wallace","year":"2016","unstructured":"Wallace, S., Zhou, Z., Vishwanath, V., et al.: Application power profiling on IBM Blue Gene\/Q. Parallel Comput. 57, 73\u201386 (2016)","journal-title":"Parallel Comput."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Xie, B., Huang, Y., Chase, J.S., et al.: Predicting output performance of a petascale supercomputer. In: Proceedings of the 26th International Symposium on High-Performance Parallel and Distributed Computing, pp. 181\u2013192 (2017)","DOI":"10.1145\/3078597.3078614"},{"issue":"Suppl. C","key":"12_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jpdc.2015.06.006","volume":"84","author":"L Yu","year":"2015","unstructured":"Yu, L., Zhou, Z., Wallace, S., et al.: Quantitative modeling of power performance tradeoffs on extreme scale systems. J. Parallel Distrib. Comput. 84(Suppl. C), 1\u201314 (2015)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"2","key":"12_CR22","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.camwa.2011.07.040","volume":"63","author":"Y Yuan","year":"2012","unstructured":"Yuan, Y., Wu, Y., Wang, Q., et al.: Job failures in high performance computing systems: a large-scale empirical study. Comput. Math. Appl. 63(2), 365\u2013377 (2012)","journal-title":"Comput. Math. Appl."},{"key":"12_CR23","unstructured":"Zasadzi\u0144ski, M., Munt\u00e9s-Mulero, V., S\u00f3le, M., Ludwig, T.: Mistral supercomputer job history analysis (2018). https:\/\/arxiv.org\/abs\/1801.07624"}],"updated-by":[{"DOI":"10.1007\/978-3-319-96983-1_58","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T00:00:00Z","timestamp":1537833600000}}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2018: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96983-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T22:25:43Z","timestamp":1693779943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-96983-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319969824","9783319969831"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96983-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"1 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"25 September 2018","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/europar2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}