{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:13:39Z","timestamp":1780326819176,"version":"3.54.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T00:00:00Z","timestamp":1615852800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T00:00:00Z","timestamp":1615852800000},"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":["CCF Trans. HPC"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s42514-021-00065-w","type":"journal-article","created":{"date-parts":[[2021,3,16]],"date-time":"2021-03-16T11:17:36Z","timestamp":1615893456000},"page":"157-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deployment and verification of machine learning tool-chain based on kubernetes distributed clusters"],"prefix":"10.1007","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5010-3396","authenticated-orcid":false,"given":"Haoyu","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,16]]},"reference":[{"key":"65_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., et al.: Tensorflow: a system for largescale machine learning. In: 12thUSENIX Symposium on Operating Systems Design and Implementation (OSDI16), pp. 265\u2013283 (2016)"},{"key":"65_CR2","doi-asserted-by":"crossref","unstructured":"Awan, A.A., Hamidouche, K., Venkatesh, A., et al.: Efficient large message broadcast using NCCL and CUDA-aware MPI for deep learning. Proceedings of the 23rd European MPI Users\u2019 Group Meeting. pp. 5\u201322 (2016)","DOI":"10.1145\/2966884.2966912"},{"issue":"3","key":"65_CR3","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/MS.2016.64","volume":"33","author":"A Balalaie","year":"2016","unstructured":"Balalaie, A., Heydarnoori, A., Jamshidi, P.: Microservices architecture enables devops: migration to a cloud-native architecture. IEEE Softw. 33(3), 42\u201352 (2016)","journal-title":"IEEE Softw."},{"issue":"3","key":"65_CR4","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1109\/MCC.2014.51","volume":"1","author":"D Bernstein","year":"2014","unstructured":"Bernstein, D.: Containers and cloud: from lxc to docker to kubernetes. IEEE Cloud Comput 1(3), 81\u201384 (2014)","journal-title":"IEEE Cloud Comput"},{"key":"65_CR5","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/978-1-4842-4470-8","volume-title":"Kubeflow and Kubeflow Pipelines[M]\/\/Building Machine Learning and Deep Learning Models on Google Cloud Platform","author":"E Bisong","year":"2019","unstructured":"Bisong, E.: Kubeflow and Kubeflow Pipelines[M]\/\/Building Machine Learning and Deep Learning Models on Google Cloud Platform, pp. 671\u2013685. Apress, Berkeley (2019)"},{"key":"65_CR6","doi-asserted-by":"crossref","unstructured":"Bisong, E.: Kubeflow and Kubeflow pipelines. Building Machine Learning and Deep Learning Models on Google Cloud Platform. Springer, New York, pp. 671\u2013685 (2019)","DOI":"10.1007\/978-1-4842-4470-8_46"},{"key":"65_CR7","unstructured":"Chen, T., Li, M., Li, Y., et al.: Mxnet: a flexible and efficient machine learning library for heterogeneous distributed systems. (2015). arXiv:1512.01274"},{"key":"65_CR8","doi-asserted-by":"crossref","unstructured":"Gabriel, E., Fagg, G.E., Bosilca, G., et al.: Open MPI: Goals, concept, and design of a next generation MPI implementation. European Parallel Virtual Machine\/Message Passing Interface Users\u2019 Group Meeting, pp. 97\u2013104. Springer, Berlin (2004)","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"65_CR9","unstructured":"Hindman, B., Konwinski, A., Zaharia, M., et al.: Mesos: a platform for finegrained resource sharing in the data center. NSDI: volume 11:22\u201322 (2011)"},{"key":"65_CR10","doi-asserted-by":"crossref","unstructured":"Ketkar, N.:Introduction to pytorch. Deep learning with python. Springer, New York, pp. 95\u2013208 (2017)","DOI":"10.1007\/978-1-4842-2766-4_12"},{"key":"65_CR11","unstructured":"Kluyver, T., Ragankelley, B., P\u00c9REZ, F., et al.: Jupyter notebooks a publishing format for reproducible computational workflows. ELPUB, pp. 87\u201390 (2016)"},{"key":"65_CR12","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/TSE.1987.232562","volume":"1","author":"R Koo","year":"1987","unstructured":"Koo, R., Toueg, S.: Checkpointing and rollback-recovery for distributed systems. IEEE Trans. Softw. Eng. 1, 23\u201331 (1987)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"65_CR13","doi-asserted-by":"crossref","unstructured":"Kramer, O.: Scikitlearn. Machine learning for evolution strategies. Springer, New York, pp. 45\u201353 (2016)","DOI":"10.1007\/978-3-319-33383-0_5"},{"key":"65_CR14","doi-asserted-by":"crossref","unstructured":"Luksa, M.: Kubernetes in action. Manning Publications (2017)","DOI":"10.3139\/9783446456020"},{"key":"65_CR15","unstructured":"Man\u00e9 D.: TensorBoard: TensorFlow\u2019s visualization toolkit (2015)"},{"issue":"239","key":"65_CR16","first-page":"2","volume":"2014","author":"D Merkel","year":"2014","unstructured":"Merkel, D.: Docker: lightweight linux containers for consistent development and deployment. Linux J. 2014(239), 2 (2014)","journal-title":"Linux J."},{"key":"65_CR17","unstructured":"Nadareishvili, I., Mitra, R., McLarty, M., et al.: Microservice architecture: aligning principles, practices, and culture[M]. O\u2019Reilly Media, Inc. (2016)"},{"issue":"3","key":"65_CR18","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/MCC.2015.51","volume":"2","author":"C Pahl","year":"2015","unstructured":"Pahl, C.: Containerization and the paas cloud. IEEE Cloud Comput. 2(3), 24\u201331 (2015)","journal-title":"IEEE Cloud Comput."},{"key":"65_CR19","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv:1804.02767 (2018)"},{"key":"65_CR20","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H. et al.: Generalized intersection over union: A metric and a loss for bounding box regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"65_CR21","unstructured":"Sandberg, R., Goldberg, D., Kleiman, S., et al.: Design and implementation of the sun network filesystem. In: Proceedings of the Summer USENIX conference, pp. 119\u2013130 (1985)"},{"key":"65_CR22","unstructured":"Vitux.com. Install nfs server and client on ubuntu 18.04 lts[EB\/OL] . (2020). http:\/\/vitux.com\/installNFSserverandclientonubuntu\/"},{"key":"65_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yin, G., Wang, T., et al.: An insight into the impact of dockerfile evolutionary trajectories on quality and latency[C]. In: 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC). IEEE 1, 138\u2013143 (2018)","DOI":"10.1109\/COMPSAC.2018.00026"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-021-00065-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-021-00065-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-021-00065-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T08:41:45Z","timestamp":1625042505000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-021-00065-w"}},"subtitle":["This paper is submitted for possible publication in the special issue on high performance distributed computing"],"short-title":[],"issued":{"date-parts":[[2021,3,16]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["65"],"URL":"https:\/\/doi.org\/10.1007\/s42514-021-00065-w","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,16]]},"assertion":[{"value":"30 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2021","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"}}]}}