{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:32:31Z","timestamp":1768030351568,"version":"3.49.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030633929","type":"print"},{"value":"9783030633936","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-63393-6_27","type":"book-chapter","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T09:04:28Z","timestamp":1608627868000},"page":"408-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ALAMO: Autonomous Lightweight Allocation, Management, and Optimization"],"prefix":"10.1007","author":[{"given":"Ron","family":"Brightwell","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt B.","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan E.","family":"Grant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Lofstead","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen L.","family":"Olivier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin T.","family":"Pedretti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew J.","family":"Younge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Gentile","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jim","family":"Brandt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,12,18]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Agelastos, A., et al.: The lightweight distributed metric service: A scalable infrastructure for continuous monitoring of large scale computing systems and applications. In: SC 2014 Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 154\u2013165 (2014)","DOI":"10.1109\/SC.2014.18"},{"key":"27_CR2","unstructured":"Barrett, B.W., et al.: The Portals 4.2 networking programming interface. Technical Report, Technical report SAND2018-12790, Sandia National Laboratories (SNL-NM) (2018)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: Expressing locality and independence with logical regions. In: SC 2012 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311. IEEE (2012)","DOI":"10.1109\/SC.2012.71"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Zyulkyarov, F., Unsal, O., McIntosh-Smith, S.: Unprotected computing: A large-scale study of DRAM raw error rate on a supercomputer. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC 2016, pp. 55:1\u201355:11 (2016)","DOI":"10.1109\/SC.2016.54"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Bouguerra, M.S., Gainaru, A., Gomez, L.B., Cappello, F., Matsuoka, S., Maruyam, N.: Improving the computing efficiency of HPC systems using a combination of proactive and preventive checkpointing. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp. 501\u2013512. IEEE (2013)","DOI":"10.1109\/IPDPS.2013.74"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Brandt, J., et al.: Quantifying effectiveness of failure prediction and response in HPC systems: Methodology and example. In: 2010 International Conference on Dependable Systems and Networks Workshops (DSN-W), pp. 2\u20137 (2010)","DOI":"10.1109\/DSNW.2010.5542629"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Brandt, J., Devine, K., Gentile, A., Pedretti, K.: Demonstrating improved application performance using dynamic monitoring and task mapping. In: 2014 IEEE International Conference on Cluster Computing (CLUSTER), pp. 408\u2013415 (2014)","DOI":"10.1109\/CLUSTER.2014.6968670"},{"issue":"3","key":"27_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1177\/1094342007078442","volume":"21","author":"B Chamberlain","year":"2007","unstructured":"Chamberlain, B., Callahan, D., Zima, H.: Parallel programmability and the Chapel language. Int. J. High Perform. Comput. Appli. 21(3), 291\u2013312 (2007). https:\/\/doi.org\/10.1177\/1094342007078442","journal-title":"Int. J. High Perform. Comput. Appli."},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Di Martino, C., Kalbarczyk, Z., Iyer, R.K., Baccanico, F., Fullop, J., Kramer, W.: Lessons learned from the analysis of system failures at petascale: The case of Blue Waters. In: International Conference on Dependable Systems and Networks (2014)","DOI":"10.1109\/DSN.2014.62"},{"key":"27_CR10","unstructured":"Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: Enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput., 74(12), 3202\u20133216 (2014). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0743731514001257"},{"key":"27_CR11","doi-asserted-by":"publisher","unstructured":"El-Sayed, N., Stefanovici, I.A., Amvrosiadis, G., Hwang, A.A., Schroeder, B.: Temperature management in data centers: Why some (might) like it hot. In: Proceedings of the 12th ACM SIGMETRICS\/PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems. SIGMETRICS 2012, pp. 163\u2013174. ACM (2012). https:\/\/doi.org\/10.1145\/2254756.2254778","DOI":"10.1145\/2254756.2254778"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Engelmann, C., Vallee, G.R., Naughton, T., Scott, S.L.: Proactive fault tolerance using preemptive migration. In: 2009 17th Euromicro International Conference on Parallel, Distributed and Network-based Processing, pp. 252\u2013257. IEEE (2009)","DOI":"10.1109\/PDP.2009.31"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Ferreira, K.B., Widener, P., Levy, S., Arnold, D., Hoefler, T.: Understanding the effects of communication and coordination on checkpointing at scale. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. SC 2014, pp. 883\u2013894 (2014)","DOI":"10.1109\/SC.2014.77"},{"issue":"10","key":"27_CR14","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MC.2016.308","volume":"49","author":"RE Grant","year":"2016","unstructured":"Grant, R.E., Levenhagen, M., Olivier, S.L., DeBonis, D., Pedretti, K.T., Laros III, J.H.: Standardizing power monitoring and control at exascale. Computer 49(10), 38\u201346 (2016)","journal-title":"Computer"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Grant, R.E., Rashti, M.J., Afsahi, A.: An analysis of QOS provisioning for sockets direct protocol vs. IPOIB over modern InfiniBand networks. In: 2008 International Conference on Parallel Processing-Workshops, pp. 79\u201386. IEEE (2008)","DOI":"10.1109\/ICPP-W.2008.25"},{"issue":"4","key":"27_CR16","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1145\/2248487.2150989","volume":"47","author":"AA Hwang","year":"2012","unstructured":"Hwang, A.A., Stefanovici, I.A., Schroeder, B.: Cosmic rays don\u2019t strike twice: Understanding the nature of DRAM errors and the implications for system design. ACM SIGPLAN Notices 47(4), 111\u2013122 (2012)","journal-title":"ACM SIGPLAN Notices"},{"key":"27_CR17","unstructured":"Jha, S., et al.: Measuring congestion in high-performance datacenter interconnects. In: 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20), Santa Clara, CA, pp. 37\u201357. USENIX Association, Feburary 2020"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Kaiser, H., Brodowicz, M., Sterling, T.: ParalleX: An advanced parallel execution model for scaling-impaired applications. In: 2009 International Conference on Parallel Processing Workshops, pp. 394\u2013401. IEEE (2009)","DOI":"10.1109\/ICPPW.2009.14"},{"key":"27_CR19","unstructured":"Kepner, J., et al.: TabulaROSA: Tabular operating system architecture for massively parallel heterogeneous compute engines. CoRR abs\/1807.05308 (2018). http:\/\/arxiv.org\/abs\/1807.05308"},{"key":"27_CR20","unstructured":"Sandia National Laboratories: Darma (2019). https:\/\/darma.sandia.gov"},{"key":"27_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5007-7","volume-title":"Autonomic Computing","author":"P Lalanda","year":"2013","unstructured":"Lalanda, P., McCann, J.A., Diaconescu, A.: Autonomic Computing. Springer-Verlag, London (2013)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Lange, J., et al.: Palacios and Kitten: New high performance operating systems for scalable virtualized and native supercomputing. In: 2010 IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470482"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Levy, S., Ferreira, K.B., DeBardeleben, N., Siddiqua, T., Sridharan, V., Baseman, E.: Lessons learned from memory errors observed over the lifetime of Cielo. In: SC\u20192018 International Conference for High Performance Computing, Networking, Storage and Analysis, November 2018","DOI":"10.1109\/SC.2018.00046"},{"key":"27_CR24","unstructured":"Li, X., Huang, M.C., Shen, K., Chu, L.: A realistic evaluation of memory hardware errors and software system susceptibility. In: Proceedings USENIX Annual Technical Conference (ATC 2010), pp. 75\u201388 (2010)"},{"key":"27_CR25","unstructured":"Li, X., Shen, K., Huang, M.C., Chu, L.: A memory soft error measurement on production systems. In: 2007 USENIX Annual Technical Conference on Proceedings of the USENIX Annual Technical Conference. ATC 2007, pp. 21:1\u201321:6 (2007). http:\/\/dl.acm.org\/citation.cfm?id=1364385.1364406"},{"key":"27_CR26","volume-title":"Autonomic Computing: Concepts, Infrastructure, and Applications","year":"2007","unstructured":"Parashar, M., Hariri, S. (eds.): Autonomic Computing: Concepts, Infrastructure, and Applications. Taylor & Francis, Inc., New York (2007)"},{"key":"27_CR27","unstructured":"Schroeder, B., Gibson, G.A.: A large-scale study of failures in high-performance computing systems. In: Dependable Systems and Networks (DSN 2006), June 2006"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Schroeder, B., Pinheiro, E., Weber, W.D.: DRAM errors in the wild: A large-scale field study. Commun. ACM, 54(2), 100\u2013107 (2011)","DOI":"10.1145\/1897816.1897844"},{"key":"27_CR29","unstructured":"Siddiqua, T., Papathanasiou, A., Biswas, A., Gurumurthi, S.: Analysis of memory errors from large-scale field data collection. In: 2013 IEEE Workshop on Silicon Errors in Logic-System Effects (SELSE) (2013)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Sridharan, V., et al.: Memory errors in modern systems: The good, the bad, and the ugly. In: Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems. ASPLOS 2015, pp. 297\u2013310 (2015)","DOI":"10.1145\/2694344.2694348"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Sridharan, V., Liberty, D.: A study of DRAM failures in the field. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. SC 2012, pp. 76:1\u201376:11 (2012)","DOI":"10.1109\/SC.2012.13"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Sridharan, V., Stearley, J., DeBardeleben, N., Blanchard, S., Gurumurthi, S.: Feng shui of supercomputer memory: Positional effects in DRAM and SRAM faults. In: Proceedings of SC13 International Conference for High Performance Computing, Networking, Storage and Analysis. SC 2013, pp. 22:1\u201322:11. ACM (2013)","DOI":"10.1145\/2503210.2503257"},{"key":"27_CR33","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":"27_CR34","doi-asserted-by":"crossref","unstructured":"Wheeler, K.B., Murphy, R.C., Thain, D.: Qthreads: An API for programming with millions of lightweight threads. In: 2008 IEEE International Symposium on Parallel and Distributed Processing Workshops, pp. 1\u20138, April 2008","DOI":"10.1109\/IPDPS.2008.4536359"},{"key":"27_CR35","unstructured":"Wilke, J.J., et al.: The DARMA approach to asynchronous many-task programming. Technical Report, Sandia National Lab. (SNL-CA), Livermore, CA (United States) (2016)"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Younge, A.J., Pedretti, K., Grant, R.E., Brightwell, R.: A tale of two systems: Using containers to deploy HPC applications on supercomputers and clouds. In: 2017 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), pp. 74\u201381. IEEE (2017)","DOI":"10.1109\/CloudCom.2017.40"}],"container-title":["Communications in Computer and Information Science","Driving Scientific and Engineering Discoveries Through the Convergence of HPC, Big Data and AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63393-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T22:09:24Z","timestamp":1619302164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63393-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030633929","9783030633936"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63393-6_27","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SMC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Smoky Mountains Computational Sciences and Engineering Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Oak Ridge, TN","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"smc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/smc.ornl.gov\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","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":"36","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":"1","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":"38% - 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":"3.75","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":"3","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}