{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T02:04:30Z","timestamp":1761185070424,"version":"build-2065373602"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"crossref","award":["2023YFB3002204"],"award-info":[{"award-number":["2023YFB3002204"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s42514-025-00227-0","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T07:13:21Z","timestamp":1746170001000},"page":"447-464","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Practice and observation: live migration for MPI workload"],"prefix":"10.1007","volume":"7","author":[{"given":"Xiaoning","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yining","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Shasha","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Haili","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,2]]},"reference":[{"key":"227_CR1","doi-asserted-by":"crossref","unstructured":"Acun, B., Gupta, A., Jain, N., et al.: Parallel Programming with Migratable Objects: Charm++ in Practice. In: SC \u201914: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. pp 647\u2013658 (2014)","DOI":"10.1109\/SC.2014.58"},{"key":"227_CR2","doi-asserted-by":"crossref","unstructured":"Ansel, J., Arya, K., Cooperman, G.: DMTCP: Transparent checkpointing for cluster computations and the desktop. In: 2009 IEEE International Symposium on Parallel & Distributed Processing. pp 1\u201312 (2009)","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"227_CR3","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Tsuboi, S., Komatitsch, D., et al.: FTI: high performance fault tolerance interface for hybrid systems. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis. Association for Computing Machinery, New York, NY, USA, pp 1\u201332 (2011)","DOI":"10.1145\/2063384.2063427"},{"key":"227_CR4","doi-asserted-by":"crossref","unstructured":"Benjaponpitak, T., Karakate, M., Sripanidkulchai, K.: Enabling live migration of containerized applications across clouds. In: IEEE INFOCOM 2020\u2014IEEE Conference on Computer Communications. IEEE, Toronto, ON, Canada, pp 2529\u20132538 (2020)","DOI":"10.1109\/INFOCOM41043.2020.9155403"},{"key":"227_CR5","unstructured":"Bi K, Xie L, Zhang H, et al.: Pangu-weather: a 3D high-resolution model for fast and accurate global weather forecast (2022)"},{"key":"227_CR6","doi-asserted-by":"crossref","unstructured":"Garg, R., Price, G., Cooperman, G.: MANA for MPI: MPI-agnostic network-agnostic transparent checkpointing. In: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing. Association for Computing Machinery, New York, pp 49\u201360 (2019)","DOI":"10.1145\/3307681.3325962"},{"key":"227_CR7","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1088\/1742-6596\/46\/1\/067","volume":"46","author":"PH Hargrove","year":"2006","unstructured":"Hargrove, P.H., Duell, J.C.: Berkeley lab checkpoint\/restart (BLCR) for Linux clusters. J. Phys. Conf. Ser. 46, 494 (2006). https:\/\/doi.org\/10.1088\/1742-6596\/46\/1\/067","journal-title":"J. Phys. Conf. Ser."},{"key":"227_CR8","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1007\/978-3-540-24644-2_20","volume-title":"Languages and compilers for parallel computing","author":"C Huang","year":"2004","unstructured":"Huang, C., Lawlor, O., Kal\u00e9, L.V.: Adaptive MPI. In: Rauchwerger, L. (ed.) Languages and compilers for parallel computing, pp. 306\u2013322. Springer, Berlin, Heidelberg (2004)"},{"key":"227_CR9","doi-asserted-by":"crossref","unstructured":"Jia, W., Wang, H., Chen, M., et al.: Pushing the limit of molecular dynamics with Ab initio accuracy to 100 million atoms with machine learning. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis. pp 1\u201314 (2020)","DOI":"10.1109\/SC41405.2020.00009"},{"key":"227_CR10","doi-asserted-by":"crossref","unstructured":"Keller, K., Kestelman, A.C., Bautista-Gomez, L.: Towards zero-waste recovery and zero-overhead checkpointing in ensemble data assimilation. In: 2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC). pp 131\u2013140 (2021)","DOI":"10.1109\/HiPC53243.2021.00027"},{"key":"227_CR11","doi-asserted-by":"crossref","unstructured":"Kumar, R., Thangaraju, B.: Performance analysis between RunC and kata container runtime. In: 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). pp 1\u20134 (2020)","DOI":"10.1109\/CONECCT50063.2020.9198653"},{"key":"227_CR12","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4890","volume":"32","author":"S Levy","year":"2020","unstructured":"Levy, S., Ferreira, K.B., Widener, P.: The unexpected virtue of almost: Exploiting MPI collective operations to approximately coordinate checkpoints. Concurr. Comput. 32, e4890 (2020). https:\/\/doi.org\/10.1002\/cpe.4890","journal-title":"Concurr. Comput."},{"key":"227_CR13","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s42514-019-00010-y","volume":"1","author":"Y Lu","year":"2019","unstructured":"Lu, Y.: Paving the way for China exascale computing. CCF Trans. HPC 1, 63\u201372 (2019). https:\/\/doi.org\/10.1007\/s42514-019-00010-y","journal-title":"CCF Trans. HPC"},{"key":"227_CR14","doi-asserted-by":"crossref","unstructured":"Mangkhangcharoen, S., Haga, J., Rattanatamrong, P.: Migrating deep learning data and applications among kubernetes edge nodes. In: 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys). IEEE, Haikou, Hainan, China, pp 2004\u20132010 (2021)","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys53884.2021.00299"},{"key":"227_CR15","doi-asserted-by":"publisher","DOI":"10.1177\/10943420231166608","author":"S Matsuoka","year":"2023","unstructured":"Matsuoka, S., Domke, J., Wahib, M., et al.: Myths and legends in high-performance computing. Int. J. High Perform. Comput. Appl. (2023). https:\/\/doi.org\/10.1177\/10943420231166608","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"227_CR16","doi-asserted-by":"crossref","unstructured":"Nicolae B, Moody A, Gonsiorowski E, et al (2019) VeloC: Towards High Performance Adaptive Asynchronous Checkpointing at Large Scale. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). pp 911\u2013920","DOI":"10.1109\/IPDPS.2019.00099"},{"key":"227_CR17","doi-asserted-by":"crossref","unstructured":"Parasyris, K., Georgakoudis, G., Bautista-Gomez, L., Laguna, I.: Co-designing multi-level checkpoint restart for MPI applications. In: 2021 IEEE\/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid). pp 103\u2013112 (2021)","DOI":"10.1109\/CCGrid51090.2021.00020"},{"key":"227_CR18","doi-asserted-by":"crossref","unstructured":"Ren, F., Chen, K., Wu, Y.: Libcrpm: improving the checkpoint performance of NVM. In: Proceedings of the 59th ACM\/IEEE Design Automation Conference. Association for Computing Machinery, New York, pp 811\u2013816 (2022)","DOI":"10.1145\/3489517.3530536"},{"key":"227_CR19","first-page":"264","volume-title":"Encyclopedia of Parallel Computing","author":"M Schulz","year":"2011","unstructured":"Schulz, M.: Checkpointing. In: Padua, D. (ed.) Encyclopedia of Parallel Computing, pp. 264\u2013273. Springer US, Boston (2011)"},{"key":"227_CR20","first-page":"1","volume-title":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","author":"M Sindi","year":"2019","unstructured":"Sindi, M., Williams, J.R.: Using container migration for HPC workloads resilience. In: 2019 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u201310. IEEE, Waltham (2019)"},{"key":"227_CR21","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1109\/IPDPSW55747.2022.00085","volume-title":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","author":"S White","year":"2022","unstructured":"White, S., Kale, L.V.: Optimizing Non-commutative Allreduce Over Virtualized, Migratable MPI Ranks. In: 2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 467\u2013475. IEEE, Lyon (2022)"},{"key":"227_CR22","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1109\/TPDS.2020.3015615","volume":"32","author":"A Wong","year":"2021","unstructured":"Wong, A., Heymann, E., Rexachs, D., Luque, E.: Middleware to manage fault tolerance using semi-coordinated checkpoints. IEEE Trans. Parallel Distrib. Syst. 32, 254\u2013268 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3015615","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"227_CR23","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhao, Z., Garg, R., et al.: MANA-2.0: a future-proof design for transparent checkpointing of MPI at scale. In: 2021 SC Workshops Supplementary Proceedings (SCWS). pp 68\u201378 (2021)","DOI":"10.1109\/SCWS55283.2021.00019"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00227-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00227-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00227-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:03:33Z","timestamp":1761174213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00227-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,2]]},"references-count":23,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["227"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00227-0","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"type":"print","value":"2524-4922"},{"type":"electronic","value":"2524-4930"}],"subject":[],"published":{"date-parts":[[2025,5,2]]},"assertion":[{"value":"10 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}