{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:22:32Z","timestamp":1774596152596,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031408427","type":"print"},{"value":"9783031408434","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40843-4_6","type":"book-chapter","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T12:02:32Z","timestamp":1692878552000},"page":"68-81","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Smarter Schedulers: Molding Jobs into\u00a0the\u00a0Right Shape via\u00a0Monitoring and\u00a0Modeling"],"prefix":"10.1007","author":[{"given":"Jean-Baptiste","family":"Besnard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Tarraf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cl\u00e9ment","family":"Barth\u00e9lemy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Cascajo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Jeannot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sameer","family":"Shende","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, D.H., Garlick, J., Grondona, M., Lipari, D., Springmeyer, B., Schulz, M.: Flux: a next-generation resource management framework for large HPC centers. In: 2014 43rd International Conference on Parallel Processing Workshops, pp. 9\u201317. IEEE (2014)","DOI":"10.1109\/ICPPW.2014.15"},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-031-23220-6_14","volume-title":"High Performance Computing","author":"E Arima","year":"2023","unstructured":"Arima, E., Compr\u00e9s, A.I., Schulz, M.: On the convergence of malleability and the HPC PowerStack: exploiting dynamism in over-provisioned and power-constrained HPC systems. In: Anzt, H., Bienz, A., Luszczek, P., Baboulin, M. (eds.) ISC High Performance 2022. LNCS, vol. 13387, pp. 206\u2013217. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-23220-6_14"},{"issue":"11","key":"6_CR3","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.1109\/JPROC.2018.2841200","volume":"106","author":"P Balaprakash","year":"2018","unstructured":"Balaprakash, P., et al.: Autotuning in high-performance computing applications. Proc. IEEE 106(11), 2068\u20132083 (2018)","journal-title":"Proc. IEEE"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Besnard, J.B., Malony, A.D., Shende, S., P\u00e9rache, M., Carribault, P., Jaeger, J.: Towards a better expressiveness of the speedup metric in MPI context. In: 2017 46th International Conference on Parallel Processing Workshops (ICPPW), pp. 251\u2013260. IEEE (2017)","DOI":"10.1109\/ICPPW.2017.45"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Calotoiu, A., Hoefler, T., Poke, M., Wolf, F.: Using automated performance modeling to find scalability bugs in complex codes. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 45 (2013). tex.organization: ACM Citation Key: CA13","DOI":"10.1145\/2503210.2503277"},{"key":"6_CR6","unstructured":"Cantalupo, C., et al.: A strawman for an HPC PowerStack. Technical report, Intel Corporation, United States; Lawrence Livermore National Lab. (LLNL) (2018)"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Carns, P.H., et al.: Understanding and improving computational science storage access through continuous characterization. ACM Trans. Storage 7(3), 8:1\u20138:26 (2011). https:\/\/doi.org\/10.1145\/2027066.2027068","DOI":"10.1145\/2027066.2027068"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Carretero, J., Jeannot, E., Pallez, G., Singh, D.E., Vidal, N.: Mapping and scheduling HPC applications for optimizing I\/O. In: Proceedings of the 34th ACM International Conference on Supercomputing, pp. 1\u201312 (2020)","DOI":"10.1145\/3392717.3392764"},{"key":"6_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2022.104586","volume":"93","author":"A Cascajo","year":"2022","unstructured":"Cascajo, A., Singh, D.E., Carretero, J.: LIMITLESS-light-weight monitoring tool for large scale systems. Microprocess. Microsyst. 93, 104586 (2022)","journal-title":"Microprocess. Microsyst."},{"key":"6_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/978-3-642-11322-2_26","volume-title":"Distributed Computing and Networking","author":"MC Cera","year":"2010","unstructured":"Cera, M.C., Georgiou, Y., Richard, O., Maillard, N., Navaux, P.O.A.: Supporting malleability in parallel architectures with dynamic CPUSETs mapping and dynamic MPI. In: Kant, K., Pemmaraju, S.V., Sivalingam, K.M., Wu, J. (eds.) ICDCN 2010. LNCS, vol. 5935, pp. 242\u2013257. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11322-2_26"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"D\u2019Amico, M., Jokanovic, A., Corbalan, J.: Holistic slowdown driven scheduling and resource management for malleable jobs. In: ACM International Conference Proceeding Series (2019). https:\/\/doi.org\/10.1145\/3337821.3337909","DOI":"10.1145\/3337821.3337909"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-319-72971-8_5","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation","author":"N Denoyelle","year":"2018","unstructured":"Denoyelle, N., Goglin, B., Ilic, A., Jeannot, E., Sousa, L.: Modeling large compute nodes with\u00a0heterogeneous memories with\u00a0cache-aware roofline model. In: Jarvis, S., Wright, S., Hammond, S. (eds.) PMBS 2017. LNCS, vol. 10724, pp. 91\u2013113. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-72971-8_5"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Dorier, M., Dreher, M., Peterka, T., Wozniak, J.M., Antoniu, G., Raffin, B.: Lessons learned from building in situ coupling frameworks. In: Proceedings of the First Workshop on In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization, pp. 19\u201324 (2015)","DOI":"10.1145\/2828612.2828622"},{"key":"6_CR14","unstructured":"Duro, F.R., Blas, J.G., Isaila, F., Carretero, J., Wozniak, J., Ross, R.: Exploiting data locality in Swift\/T workflows using Hercules. In: Proceedings of NESUS Workshop (2014)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Goglin, B., Moreaud, S.: Dodging non-uniform I\/O access in hierarchical collective operations for multicore clusters. In: 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum, pp. 788\u2013794. IEEE (2011)","DOI":"10.1109\/IPDPS.2011.222"},{"key":"6_CR16","unstructured":"Gupta, R., Laguna, I., Ahn, D., Gamblin, T., Bagchi, S., Lin, F.: STATuner: efficient tuning of CUDA kernels parameters. In: Supercomputing Conference (SC 2015), Poster (2015)"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Hoefler, T., Gropp, W., Kramer, W., Snir, M.: Performance modeling for systematic performance tuning. In: State of the Practice Reports, SC 2011, pp. 1\u201312. Association for Computing Machinery, New York (2011). https:\/\/doi.org\/10.1145\/2063348.2063356","DOI":"10.1145\/2063348.2063356"},{"issue":"11","key":"6_CR18","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1631\/FITEE.1601336","volume":"17","author":"W Hu","year":"2016","unstructured":"Hu, W., Liu, G., Li, Q., Jiang, Y., Cai, G.: Storage wall for exascale supercomputing. Front. Inf. Technol. Electron. Eng. 17(11), 1154\u20131175 (2016). https:\/\/doi.org\/10.1631\/FITEE.1601336","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Huber, D., Streubel, M., Compr\u00e9s, I., Schulz, M., Schreiber, M., Pritchard, H.: Towards dynamic resource management with MPI sessions and PMIx. In: Proceedings of the 29th European MPI Users\u2019 Group Meeting, pp. 57\u201367 (2022)","DOI":"10.1145\/3555819.3555856"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Klein, C., P\u00e9rez, C.: An RMS for non-predictably evolving applications. In: Proceedings - IEEE International Conference on Cluster Computing, ICCC, pp. 326\u2013334 (2011). https:\/\/doi.org\/10.1109\/CLUSTER.2011.56","DOI":"10.1109\/CLUSTER.2011.56"},{"key":"6_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-642-35867-8_11","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"R Kumar","year":"2013","unstructured":"Kumar, R., Vadhiyar, S.: Identifying quick starters: towards an integrated framework for efficient predictions of queue waiting times of batch parallel jobs. In: Cirne, W., Desai, N., Frachtenberg, E., Schwiegelshohn, U. (eds.) JSSPP 2012. LNCS, vol. 7698, pp. 196\u2013215. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-35867-8_11"},{"key":"6_CR22","unstructured":"Mart\u00ed Fraiz, J.: dataClay: next generation object storage (2017)"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Miranda, A., Jackson, A., Tocci, T., Panourgias, I., Nou, R.: NORNS: extending Slurm to support data-driven workflows through asynchronous data staging. In: 2019 IEEE International Conference on Cluster Computing (CLUSTER), USA, pp. 1\u201312. IEEE (2019). https:\/\/doi.org\/10.1109\/CLUSTER.2019.8891014","DOI":"10.1109\/CLUSTER.2019.8891014"},{"issue":"6","key":"6_CR24","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1109\/71.932708","volume":"12","author":"AW Mu\u2019alem","year":"2001","unstructured":"Mu\u2019alem, A.W., Feitelson, D.G.: Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans. Parallel Distrib. Syst. 12(6), 529\u2013543 (2001). https:\/\/doi.org\/10.1109\/71.932708","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Netti, A., et al.: DCDB wintermute: enabling online and holistic operational data analytics on HPC systems. In: Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, pp. 101\u2013112 (2020)","DOI":"10.1145\/3369583.3392674"},{"issue":"7","key":"6_CR26","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1134\/S1995080221070192","volume":"42","author":"DA Nikitenko","year":"2021","unstructured":"Nikitenko, D.A., et al.: Influence of noisy environments on behavior of HPC applications. Lobachevskii J. Math. 42(7), 1560\u20131570 (2021). https:\/\/doi.org\/10.1134\/S1995080221070192","journal-title":"Lobachevskii J. Math."},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Patki, T., Thiagarajan, J.J., Ayala, A., Islam, T.Z.: Performance optimality or reproducibility: that is the question. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, Denver Colorado, pp. 1\u201330. ACM (2019). https:\/\/doi.org\/10.1145\/3295500.3356217","DOI":"10.1145\/3295500.3356217"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Petrini, F., Kerbyson, D., Pakin, S.: The case of the missing supercomputer performance: achieving optimal performance on the 8,192 processors of ASCI Q. In: SC 2003: Proceedings of the 2003 ACM\/IEEE Conference on Supercomputing, p. 55 (2003). https:\/\/doi.org\/10.1145\/1048935.1050204","DOI":"10.1145\/1048935.1050204"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Prabhakaran, S., Neumann, M., Rinke, S., Wolf, F., Gupta, A., Kale, L.V.: A batch system with efficient adaptive scheduling for malleable and evolving applications. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp. 429\u2013438. IEEE (2015)","DOI":"10.1109\/IPDPS.2015.34"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Ritter, M., Calotoiu, A., Rinke, S., Reimann, T., Hoefler, T., Wolf, F.: Learning cost-effective sampling strategies for empirical performance modeling. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 884\u2013895 (2020). https:\/\/doi.org\/10.1109\/IPDPS47924.2020.00095","DOI":"10.1109\/IPDPS47924.2020.00095"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Ritter, M., et al.: Noise-resilient empirical performance modeling with deep neural networks. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 23\u201334 (2021). https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00012","DOI":"10.1109\/IPDPS49936.2021.00012"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Schulz, M., Kranzlm\u00fcller, D., Schulz, L.B., Trinitis, C., Weidendorfer, J.: On the inevitability of integrated HPC systems and how they will change HPC system operations. In: Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies, pp. 1\u20136 (2021)","DOI":"10.1145\/3468044.3468046"},{"key":"6_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/3-540-47954-6_11","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"W Smith","year":"1999","unstructured":"Smith, W., Taylor, V., Foster, I.: Using run-time predictions to estimate queue wait times and improve scheduler performance. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1999. LNCS, vol. 1659, pp. 202\u2013219. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-47954-6_11"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Sudarsan, R., Ribbens, C.J.: ReSHAPE: a framework for dynamic resizing and scheduling of homogeneous applications in a parallel environment. In: Proceedings of the International Conference on Parallel Processing (2007). https:\/\/doi.org\/10.1109\/ICPP.2007.73","DOI":"10.1109\/ICPP.2007.73"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Vef, M.A., et al.: GekkoFS-a temporary distributed file system for HPC applications. In: 2018 IEEE International Conference on Cluster Computing (CLUSTER), pp. 319\u2013324. IEEE (2018)","DOI":"10.1109\/CLUSTER.2018.00049"},{"issue":"4","key":"6_CR36","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun. ACM"},{"key":"6_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/978-3-030-78713-4_24","volume-title":"High Performance Computing","author":"C Wood","year":"2021","unstructured":"Wood, C., et al.: Artemis: automatic runtime tuning of\u00a0parallel execution parameters using\u00a0machine learning. In: Chamberlain, B.L., Varbanescu, A.-L., Ltaief, H., Luszczek, P. (eds.) ISC High Performance 2021. LNCS, vol. 12728, pp. 453\u2013472. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-78713-4_24"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Toward an end-to-end auto-tuning framework in HPC PowerStack. In: 2020 IEEE International Conference on Cluster Computing (CLUSTER), pp. 473\u2013483. IEEE (2020)","DOI":"10.1109\/CLUSTER49012.2020.00068"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40843-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T12:03:07Z","timestamp":1692878587000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40843-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408427","9783031408434"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40843-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"25 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}