{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:43:55Z","timestamp":1782999835615,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CSSI-2411386"],"award-info":[{"award-number":["CSSI-2411386"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CSSI-2514056"],"award-info":[{"award-number":["CSSI-2514056"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3807872","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"1014-1026","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["StreamGuard: Low-Overhead Resilience for Real-time HPC Data Streams"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4177-0493","authenticated-orcid":false,"given":"Hai Duc","family":"Nguyen","sequence":"first","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA and University of Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-7509","authenticated-orcid":false,"given":"Bogdan","family":"Nicolae","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8428-5159","authenticated-orcid":false,"given":"Tekin","family":"Bicer","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4830-3139","authenticated-orcid":false,"given":"Amal","family":"Gueroudji","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9293-2021","authenticated-orcid":false,"given":"Matthieu","family":"Dorier","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7370-4805","authenticated-orcid":false,"given":"Kyle","family":"Chard","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-5269","authenticated-orcid":false,"given":"Ian","family":"Foster","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA and Argonne National Lab, Lemont, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"9th USENIX Symposium on Operating Systems Design and Implementation (OSDI 10)","author":"Ananthanarayanan Ganesh","year":"2010","unstructured":"Ganesh Ananthanarayanan, Srikanth Kandula, Albert Greenberg, Ion Stoica, Yi Lu, Bikas Saha, and Edward Harris. 2010. Reining in the outliers in { Map-Reduce} clusters using mantri. In 9th USENIX Symposium on Operating Systems Design and Implementation (OSDI 10)."},{"key":"e_1_3_3_1_3_2","unstructured":"Apache Flink. [n. d.]. Checkpoints. https:\/\/nightlies.apache.org\/flink\/flink-docs-stable\/docs\/ops\/state\/checkpoints\/. Apache Flink Documentation accessed: 2026-02-09."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3190664"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Anakha\u00a0V Babu Tao Zhou Saugat Kandel Tekin Bicer Zhengchun Liu William Judge Daniel\u00a0J Ching Yi Jiang Sinisa Veseli Steven Henke et\u00a0al. 2023. Deep learning at the edge enables real-time streaming ptychographic imaging. Nature Communications 14 1 (2023) 7059.","DOI":"10.1038\/s41467-023-41496-z"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3325400"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"GAUDI& Barrand I Belyaev P Binko M Cattaneo R Chytracek G Corti M Frank G Gracia J Harvey Eric Van\u00a0Herwijnen et\u00a0al. 2001. GAUDI\u2014A software architecture and framework for building HEP data processing applications. Computer physics communications 140 1-2 (2001) 45\u201355.","DOI":"10.1016\/S0010-4655(01)00254-5"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063427"},{"key":"e_1_3_3_1_9_2","first-page":"701","volume-title":"14th International Conference on Contemporary Computing","author":"Benoit Anne","year":"2022","unstructured":"Anne Benoit, Yishu Du, Thomas Herault, Loris Marchal, Guillaume Pallez, Lucas Perotin, Yves Robert, Hongyang Sun, and Fr\u00e9d\u00e9ric Vivien. 2022. Checkpointing \u00e0 la Young\/Daly: An overview. In 14th International Conference on Contemporary Computing. 701\u2013710."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Anne Benoit Lucas Perotin Yves Robert and Fr\u00e9d\u00e9ric Vivien. 2024. Checkpointing Strategies to Tolerate Non-Memoryless Failures on HPC Platforms. ACM Trans. Parallel Comput. 11 1 Article 1 (2024) 26\u00a0pages.","DOI":"10.1145\/3624560"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Tekin Bicer Do\u011fa G\u00fcrsoy Vincent\u00a0De Andrade Rajkumar Kettimuthu William Scullin Francesco\u00a0De Carlo and Ian\u00a0T Foster. 2017. Trace: A high-throughput tomographic reconstruction engine for large-scale datasets. Advanced Structural and Chemical Imaging 3 (2017) 1\u201310.","DOI":"10.1186\/s40679-017-0040-7"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470462"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/XLOOP51963.2020.00007"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Franck Cappello Al Geist William Gropp Sanjay Kale Bill Kramer and Marc Snir. 2014. Toward exascale resilience: 2014 update. Supercomputing Frontiers and Innovations: An International Journal 1 1 (2014) 5\u201328.","DOI":"10.14529\/jsfi140101"},{"key":"e_1_3_3_1_15_2","unstructured":"Paris Carbone Asterios Katsifodimos Stephan Ewen Volker Markl Seif Haridi and Kostas Tzoumas. 2015. Apache flink: Stream and batch processing in a single engine. The Bulletin of the Technical Committee on Data Engineering 38 4 (2015)."},{"key":"e_1_3_3_1_16_2","unstructured":"K\u00a0Mani Chandy and Leslie Lamport. 1985. Distributed snapshots: Determining global states of distributed systems. ACM Transactions on Computer Systems (TOCS) 3 1 (1985) 63\u201375."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"John\u00a0T Daly. 2006. A higher order estimate of the optimum checkpoint interval for restart dumps. Future Generation Computer Systems 22 3 (2006) 303\u2013312.","DOI":"10.1016\/j.future.2004.11.016"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Dean and Luiz\u00a0Andr\u00e9 Barroso. 2013. The tail at scale. Commun. ACM 56 2 (2013) 74\u201380.","DOI":"10.1145\/2408776.2408794"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Dean and Sanjay Ghemawat. 2008. MapReduce: simplified data processing on large clusters. Commun. ACM 51 1 (2008) 107\u2013113.","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Martin Dierolf Andreas Menzel Pierre Thibault Philipp Schneider Cameron\u00a0M Kewish Roger Wepf Oliver Bunk and Franz Pfeiffer. 2010. Ptychographic X-ray computed tomography at the nanoscale. Nature 467 7314 (2010) 436\u2013439.","DOI":"10.1038\/nature09419"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20943-2_1"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Matthieu Dorier Amal Gueroudji Val\u00e9rie Hayot-Sasson Hai\u00a0Duc Nguyen Seth Ockerman Renan Souza Tekin Bicer Haochen Pan Philip Carns Kyle Chard et\u00a0al. 2025. Toward a persistent event-streaming system for high-performance computing applications. Frontiers in High Performance Computing 3 (2025) 1638203.","DOI":"10.3389\/fhpcp.2025.1638203"},{"key":"e_1_3_3_1_23_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The Llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063443"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Michael Goodrich Carl Timmer Vardan Gyurjyan David Lawrence Graham Heyes Yatish Kumar and Stacey Sheldon. 2023. ESnet\/JLab FPGA Accelerated Transport. IEEE Transactions on Nuclear Science 70 6 (2023) 1096\u20131101.","DOI":"10.1109\/TNS.2023.3243871"},{"key":"e_1_3_3_1_26_2","unstructured":"Google Cloud. 2026. Google Cloud Dataflow. https:\/\/cloud.google.com\/products\/dataflow. Accessed: 2026-02-09."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Mikaila\u00a0J. Gossman Bogdan Nicolae and Jon\u00a0C. Calhoun. 2024. Scalable I\/O aggregation for asynchronous multi-level checkpointing. Future Generation Computer Systems 160 (2024) 420\u2013432. 10.1016\/j.future.2024.06.003","DOI":"10.1016\/j.future.2024.06.003"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767575"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2504566"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3102980.3103005"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Eliu\u00a0Antonio Huerta Gabrielle Allen Igor Andreoni Javier\u00a0M Antelis Etienne Bachelet G\u00a0Bruce Berriman Federica\u00a0B Bianco Rahul Biswas Matias Carrasco\u00a0Kind Kyle Chard et\u00a0al. 2019. Enabling real-time multi-messenger astrophysics discoveries with deep learning. Nature Reviews Physics 1 10 (2019) 600\u2013608.","DOI":"10.1038\/s42254-019-0097-4"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Yongho Kim Seongha Park Sean Shahkarami Rajesh Sankaran Nicola Ferrier and Pete Beckman. 2022. Goal-driven scheduling model in edge computing for smart city applications. J. Parallel and Distrib. Comput. 167 (2022) 97\u2013108.","DOI":"10.1016\/j.jpdc.2022.04.024"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742788"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00027"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Gang Liu Zeting Wang Amelie\u00a0Chi Zhou and Rui Mao. 2024. Adaptive key partitioning in distributed stream processing. CCF Transactions on High Performance Computing 6 2 (2024) 164\u2013178.","DOI":"10.1007\/s42514-023-00179-3"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Zhengchun Liu Tekin Bicer Rajkumar Kettimuthu Doga Gursoy Francesco De\u00a0Carlo and Ian Foster. 2020. TomoGAN: Low-dose synchrotron x-ray tomography with generative adversarial networks. JOSA A 37 3 (2020) 422\u2013434.","DOI":"10.1364\/JOSAA.375595"},{"key":"e_1_3_3_1_37_2","first-page":"133","volume-title":"International Conference on Algorithms and Architectures for Parallel Processing","author":"Lu Pengqi","year":"2021","unstructured":"Pengqi Lu, Yue Yue, Liang Yuan, and Yunquan Zhang. 2021. AutoFlow: hotspot-aware, dynamic load balancing for distributed stream processing. In International Conference on Algorithms and Architectures for Parallel Processing. Springer, 133\u2013151."},{"key":"e_1_3_3_1_38_2","unstructured":"Nicolau Manubens Johann Lombardi Simon\u00a0D. Smart Emanuele Danovaro Tiago Quintino Dean Hildebrand and Adrian Jackson. 2024. Exploring DAOS Interfaces and Performance. arxiv:https:\/\/arXiv.org\/abs\/2409.18682\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2409.18682"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC58850.2023.00043"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"K. Mohror A. Moody G. Bronevetsky and B.\u00a0R. de Supinski. 2014. Detailed Modeling and Evaluation of a Scalable Multilevel Checkpointing System. IEEE Transactions on Parallel and Distributed Systems 25 09 (sep 2014) 2255\u20132263. 10.1109\/TPDS.2013.100","DOI":"10.1109\/TPDS.2013.100"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Hai\u00a0Duc Nguyen Tekin Bicer Bogdan Nicolae Rajkumar Kettimuthu Eliu\u00a0A Huerta and Ian\u00a0T Foster. 2025. Resilient execution of distributed X-ray image analysis workflows. Frontiers in High Performance Computing 3 (2025) 1550855.","DOI":"10.3389\/fhpcp.2025.1550855"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3452413.3464786"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00099"},{"key":"e_1_3_3_1_44_2","volume-title":"SuperCheck\u201921: The First International Symposium on Checkpointing for Supercomputing","author":"Nicolae Bogdan","year":"2021","unstructured":"Bogdan Nicolae, Adam Moody, Greg Kosinovsky, Kathryn Mohror, and Franck Cappello. 2021. VELOC: VEry Low Overhead Checkpointing in the Age of Exascale. In SuperCheck\u201921: The First International Symposium on Checkpointing for Supercomputing. Virtual Event. https:\/\/arxiv.org\/pdf\/2103.02131.pdf"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science62913.2024.10678669"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Shadi\u00a0A Noghabi Kartik Paramasivam Yi Pan Navina Ramesh Jon Bringhurst Indranil Gupta and Roy\u00a0H Campbell. 2017. Samza: stateful scalable stream processing at LinkedIn. Proceedings of the VLDB Endowment 10 12 (2017) 1634\u20131645.","DOI":"10.14778\/3137765.3137770"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Norbert Podhorszki et\u00a0al. 2020. ADIOS 2: The Adaptable Input Output System. A framework for high-performance data management. SoftwareX 12 (2020). 10.1016\/j.softx.2020.100529","DOI":"10.1016\/j.softx.2020.100529"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624613"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391236"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0D Schlichting and Fred\u00a0B Schneider. 1983. Fail-stop processors: An approach to designing fault-tolerant computing systems. ACM Transactions on Computer Systems 1 3 (1983) 222\u2013238.","DOI":"10.1145\/357369.357371"},{"key":"e_1_3_3_1_51_2","first-page":"301","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Song Won\u00a0Wook","year":"2023","unstructured":"Won\u00a0Wook Song, Taegeon Um, Sameh Elnikety, Myeongjae Jeon, and Byung-Gon Chun. 2023. Sponge: Fast reactive scaling for stream processing with serverless frameworks. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 301\u2013314."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Sebastian Steiner Jakob Wolf Stefan Glatzel Anna Andreou Jaros\u0142aw\u00a0M Granda Graham Keenan Trevor Hinkley Gerardo Aragon-Camarasa Philip\u00a0J Kitson Davide Angelone et\u00a0al. 2019. Organic synthesis in a modular robotic system driven by a chemical programming language. Science 363 6423 (2019) eaav2211.","DOI":"10.1126\/science.aav2211"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Dawei Sun Chunlin Zhang Shang Gao and Rajkumar Buyya. 2024. An adaptive load balancing strategy for stateful join operator in skewed data stream environments. Future generation computer systems 152 (2024) 138\u2013151.","DOI":"10.1016\/j.future.2023.11.002"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"P Thibault M Dierolf A Menzel O Bunk C David and F Pfeiffer. 2008. High-resolution scanning x-ray diffraction microscopy. Science 321 5887 (2008) 379\u2013382.","DOI":"10.1126\/science.1158573"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2595641"},{"key":"e_1_3_3_1_56_2","unstructured":"Xiaoli Yan Nathaniel Hudson Hyun Park Daniel Grzenda J\u00a0Gregory Pauloski Marcus Schwarting Haochen Pan Hassan Harb Samuel Foreman Chris Knight et\u00a0al. 2025. MOFA: Discovering Materials for Carbon Capture with a GenAI-and Simulation-Based Workflow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.10651 (2025)."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"John\u00a0W Young. 1974. A first order approximation to the optimum checkpoint interval. Commun. ACM 17 9 (1974) 530\u2013531.","DOI":"10.1145\/361147.361115"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522737"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","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 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3807872","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:54:03Z","timestamp":1782996843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3807872"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":57,"alternative-id":["10.1145\/3797905.3807872","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3807872","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}