{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T11:29:20Z","timestamp":1782386960131,"version":"3.54.5"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2024,1,7]],"date-time":"2024-01-07T00:00:00Z","timestamp":1704585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,7]],"date-time":"2024-01-07T00:00:00Z","timestamp":1704585600000},"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":["CCF Trans. HPC"],"DOI":"10.1007\/s42514-023-00178-4","type":"journal-article","created":{"date-parts":[[2024,1,7]],"date-time":"2024-01-07T20:01:36Z","timestamp":1704657696000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["DCU-CHK: checkpointing for large-scale CPU-DCU heterogeneous computing systems"],"prefix":"10.1007","author":[{"given":"Jie","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,7]]},"reference":[{"key":"178_CR1","doi-asserted-by":"crossref","unstructured":"Ansel, J., Arya, K., Cooperman, G.: DMTCP: transparent checkpointing for cluster computations and the desktop. In: IPDPS 2009\u2014Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium. IEEE, 2009, pp. 1\u201312","DOI":"10.1109\/IPDPS.2009.5161063"},{"issue":"3","key":"178_CR2","first-page":"63","volume":"5","author":"DH Bailey","year":"1991","unstructured":"Bailey, D.H., Barszcz, E., Barton, J.T., et al.: The NAS parallel benchmarks. Int. J. Supercomput. Appl. 5(3), 63\u201373 (1991)","journal-title":"Int. J. Supercomput. Appl."},{"key":"178_CR3","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Komatitsch, D., Maruyama, N., et al.: FTI: high performance fault tolerance interface for hybrid systems. In: Proceedings of 2011 SC\u2014International Conference for High Performance Computing, Networking, Storage and Analysis, IEEE, 2011, pp. 1\u201312","DOI":"10.1145\/2063384.2063427"},{"key":"178_CR4","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: 2009 IEEE International Symposium on Workload Characterization (IISWC). Ieee, 2009, pp. 44\u201354","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"178_CR5","unstructured":"CRIU [EB\/OL] (2023). https:\/\/criu.org\/Main_Page. Accessed 15 June 2023"},{"key":"178_CR6","doi-asserted-by":"crossref","unstructured":"Egevang, K., Francis, P.: The IP network address translator (NAT) (1994)","DOI":"10.17487\/rfc1631"},{"key":"178_CR7","doi-asserted-by":"crossref","unstructured":"Garg, R., Mohan, A., Sullivan, M., et al.: CRUM: checkpoint-restart support for CUDA\u2019s unified memory. In: Proceedings\u2014IEEE International Conference on Cluster Computing, ICCC, Institute of Electrical and Electronics Engineers Inc., 2018, 2018-Septe, pp. 302\u2013313","DOI":"10.1109\/CLUSTER.2018.00047"},{"issue":"1","key":"178_CR8","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(1), 494\u2013499 (2006)","journal-title":"J. Phys. Conf. Ser."},{"key":"178_CR9","unstructured":"HeCBench\/gibbs-hip at master \u00b7 zjin-lcf\/HeCBench[EB\/OL] (2022). https:\/\/github.com\/zjin-lcf\/HeCBench\/tree\/master\/gibbs-hip. Accessed 23 Dec 2022"},{"key":"178_CR10","unstructured":"HeCBench\/qtclustering-hip at master \u00b7 zjin-lcf\/HeCBench[EB\/OL] (2022). https:\/\/github.com\/zjin-lcf\/HeCBench\/tree\/master\/qtclustering-hip. Accessed 23 Dec 2022"},{"key":"178_CR11","doi-asserted-by":"crossref","unstructured":"Jain, T., Cooperman, G. Crac: checkpoint-restart architecture for cuda with streams and uvm. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC. IEEE, 2020, 2020-Novem, pp. 1\u201315","DOI":"10.1109\/SC41405.2020.00081"},{"key":"178_CR12","doi-asserted-by":"crossref","unstructured":"Martino, C.D., Kramer, W., Kalbarczyk, Z., et al.: Measuring and understanding extreme-scale application resilience: a field study of 5,000,000 HPC application runs. In: Proceedings of the International Conference on Dependable Systems and Networks. IEEE, 2015, 2015-Septe, pp. 25\u201336","DOI":"10.1109\/DSN.2015.50"},{"key":"178_CR13","unstructured":"Mantevo\/miniFE: MiniFE Finite Element Mini-Application[EB\/OL] (2022). https:\/\/github.com\/Mantevo\/miniFE. Accessed 23 Dec 2022"},{"key":"178_CR14","doi-asserted-by":"crossref","unstructured":"Pourghassemi, B., Chandramowlishwaran, A.: cudacr: an in-kernel application-level checkpoint\/restart scheme for cuda-enabled gpus. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 2017, pp. 725\u2013732","DOI":"10.1109\/CLUSTER.2017.100"},{"key":"178_CR15","unstructured":"RadeonOpenCompute\/ROCm: ROCm - Open Software Platform for GPU Compute[EB\/OL] (2022). https:\/\/github.com\/RadeonOpenCompute\/ROCm. Accessed 21 Dec 2022"},{"key":"178_CR16","unstructured":"ROCm-Developer-Tools\/HIP: HIP: C++ Heterogeneous-Compute Interface for Portability[EB\/OL] (2022). https:\/\/github.com\/ROCm-Developer-Tools\/HIP. Accessed 21 Dec 2022"},{"key":"178_CR17","unstructured":"Slurm Workload Manager - Overview [EB\/OL]. Slurm (2020). https:\/\/slurm.schedmd.com\/overview.html. Accessed 1 Dec 2020"},{"key":"178_CR18","doi-asserted-by":"crossref","unstructured":"Takizawa, H., Sato, K., Komatsut, K., et al.: CheCUDA: a checkpoint\/restart tool for CUDA applications. In: Parallel and Distributed Computing, Applications and Technologies, PDCAT Proceedings. IEEE, 2009, pp. 408\u2013413","DOI":"10.1109\/PDCAT.2009.78"},{"key":"178_CR19","doi-asserted-by":"crossref","unstructured":"Takizawa, H., Koyama, K., Sato, K., et al. CheCL: transparent checkpointing and process migration of OpenCL applications. In: 2011 IEEE International Parallel & Distributed Processing Symposium. IEEE, 2011, pp. 864\u2013876","DOI":"10.1109\/IPDPS.2011.85"},{"key":"178_CR20","unstructured":"Top500 | Top500 [EB\/OL] (2023). https:\/\/www.top500.org\/lists\/top500\/. Accessed 15 June 2023"},{"issue":"9","key":"178_CR21","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1360\/SSI-2020-0099","volume":"50","author":"R Wang","year":"2020","unstructured":"Wang, R., Qian, D.: Key issues in exascale computing. Scientia Sinica Informationis 50(9), 1303 (2020)","journal-title":"Scientia Sinica Informationis"},{"key":"178_CR22","unstructured":"Zhou, S.: Lsf: load sharing in large heterogeneous distributed systems. In: I Workshop on Cluster Computing, p. 136 (1992)"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00178-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-023-00178-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00178-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,7]],"date-time":"2024-01-07T20:04:28Z","timestamp":1704657868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-023-00178-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,7]]},"references-count":22,"alternative-id":["178"],"URL":"https:\/\/doi.org\/10.1007\/s42514-023-00178-4","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,7]]},"assertion":[{"value":"16 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest, financial or otherwise. 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"}}]}}