{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:58:27Z","timestamp":1778583507196,"version":"3.51.4"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:00:00Z","timestamp":1641772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","award":["TIN2017-82972-R"],"award-info":[{"award-number":["TIN2017-82972-R"]}]},{"name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","award":["TIN2017-82972-R"],"award-info":[{"award-number":["TIN2017-82972-R"]}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"crossref","award":["Prometeo\/2019\/109"],"award-info":[{"award-number":["Prometeo\/2019\/109"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003359","name":"Generalitat Valenciana","doi-asserted-by":"publisher","award":["CDEIGENT\/2018\/014"],"award-info":[{"award-number":["CDEIGENT\/2018\/014"]}],"id":[{"id":"10.13039\/501100003359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["FJC2019-039222-I"],"award-info":[{"award-number":["FJC2019-039222-I"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s00607-021-01029-2","type":"journal-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T00:03:16Z","timestamp":1641772996000},"page":"1101-1119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Analyzing the impact of the MPI allreduce in distributed training of convolutional neural networks"],"prefix":"10.1007","volume":"105","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8576-8451","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Castell\u00f3","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar","family":"Catal\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel F.","family":"Dolz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9","family":"Duato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,10]]},"reference":[{"key":"1029_CR1","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, Devin M, Ghemawat S, Irving G, Isard M, Kudlur M, Levenberg J, Monga R, Moore S, Murray DG, Steiner B, Tucker P, Vasudevan V, Warden P, Wicke M, Yu Y, Zheng X(2016) Tensorflow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), pp 265\u2013283, Savannah, GA, Nov. USENIX Association"},{"key":"1029_CR2","doi-asserted-by":"crossref","unstructured":"Ben-Nun T, Hoefler T (2019) Demystifying parallel and distributed deep learning: An in-depth concurrency analysis. ACM Computing Surveys, 52(4):65:1\u201365:43","DOI":"10.1145\/3320060"},{"key":"1029_CR3","doi-asserted-by":"crossref","unstructured":"Castell\u00f3 A, Dolz MF, Quintana-Ort\u00ed ES, Duato J (2019) Theoretical scalability analysis of distributed deep convolutional neural networks. In 2nd High Performance Machine Learning Workshop \u2013 HPML\u20192019, pp 534\u2013541","DOI":"10.1109\/CCGRID.2019.00068"},{"key":"1029_CR4","doi-asserted-by":"crossref","unstructured":"Castell\u00f3 A, Catal\u00e1n M, Dolz MF, Mestre JI, Quintana-Ort\u00ed ES, Duato J (2021) Evaluation of mpi allreduce for distributed training of convolutional neural networks. In 2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pages 109\u2013116","DOI":"10.1109\/PDP52278.2021.00025"},{"issue":"13","key":"1029_CR5","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1002\/cpe.1206","volume":"19","author":"E Chan","year":"2007","unstructured":"Chan E, Heimlich M, Purkayastha A, van de Geijn R (2007) Collective communication: Theory, practice, and experience. Concurr Comput: Practice Experience 19(13):1749\u20131783","journal-title":"Concurr Comput: Practice Experience"},{"key":"1029_CR6","doi-asserted-by":"crossref","unstructured":"Demmel J (2012) Communication avoiding algorithms. In Proceedings of the 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, SCC \u201912, pp 1942-2000, USA. IEEE Computer Society","DOI":"10.1109\/SC.Companion.2012.351"},{"issue":"2","key":"1029_CR7","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/s11227-016-1779-7","volume":"73","author":"K Hasanov","year":"2017","unstructured":"Hasanov K, Lastovetsky A (2017) Hierarchical redesign of classic MPI reduction algorithms. J Supercomput 73(2):713\u2013725","journal-title":"J Supercomput"},{"key":"1029_CR8","doi-asserted-by":"crossref","unstructured":"Hazelwood K, Bird S, Brooks D, Chintala S, Diril U, Dzhulgakov D, Fawzy M, Jia B, Jia Y, Kalro A, Law J, Lee K, Lu J, Noordhuis P, Smelyanskiy M, Xiong L, Wang X (2018) Applied machine learning at Facebook: A datacenter infrastructure perspective. In 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp 620\u2013629","DOI":"10.1109\/HPCA.2018.00059"},{"key":"1029_CR9","unstructured":"Ivanov A, Dryden N, Ben-Nun T, Li S, Torsten H (2020) A case study on optimizing transformers, Data movement is all you need"},{"key":"1029_CR10","doi-asserted-by":"crossref","unstructured":"Ketkar N (2017) Introduction to pytorch. In Deep learning with python, pages 195\u2013208. Springer","DOI":"10.1007\/978-1-4842-2766-4_12"},{"key":"1029_CR11","unstructured":"attson P, Cheng C, Coleman C, Diamos G, Micikevicius P, Patterson D, Tang H, Wei GY, Bailis P, Bittorf V, Brooks D, Chen D, Dutta D, Gupta U, Hazelwood KM, Hock A, Huang X, Jia B, Kang D, Kanter D, Kumar N, Liao J, Ma G, Narayanan D, Oguntebi T, Pekhimenko G, Pentecost L, Reddi VJ, Robie T, John TS, Wu C-J, Xu L, Young C, Zaharia M (2019) Mlperf training benchmark. CoRR, arXiv:1910.01500"},{"key":"1029_CR12","doi-asserted-by":"crossref","unstructured":"Nuriyev E, Lastovetsky A (2021) A new model-based approach to performance comparison of mpi collective algorithms. In Victor Malyshkin, editor, Parallel Computing Technologies, pp 11\u201325, Cham, Springer International Publishing","DOI":"10.1007\/978-3-030-86359-3_2"},{"key":"1029_CR13","unstructured":"Sergeev A, Balso MD (2018) Horovod: fast and easy distributed deep learning in TensorFlow. arXiv:1802.05799"},{"key":"1029_CR14","doi-asserted-by":"crossref","unstructured":"Shalf J (2019) HPC Interconnects at the End of Moore\u2019s Law. In 2019 Optical Fiber Communications Conference and Exhibition (OFC), pp 1\u20133","DOI":"10.1364\/OFC.2019.Th3A.1"},{"key":"1029_CR15","unstructured":"Snir M, Otto SW, Steven HL, Walker DW, Dongarra J (1996) The Complete Reference. The MIT Press, MPI"},{"issue":"1","key":"1029_CR16","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R Thakur","year":"2005","unstructured":"Thakur R, Rabenseifner R, Gropp W (2005) Optimization of collective communication operations in MPICH. Int J High Performance Comput Appl 19(1):49\u201366","journal-title":"Int J High Performance Comput Appl"},{"key":"1029_CR17","doi-asserted-by":"crossref","unstructured":"Turchenko V, Bosilca G, Bouteiller A, Dongarra J (2013) Efficient parallelization of batch pattern training algorithm on many-core and cluster architectures. In 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), vol.\u00a02, pp 692\u2013698. IEEE","DOI":"10.1109\/IDAACS.2013.6663014"},{"key":"1029_CR18","doi-asserted-by":"crossref","unstructured":"Turchenko V, Grandinetti L, Bosilca G, Dongarra JJ (2010) Improvement of parallelization efficiency of batch pattern bp training algorithm using open mpi. Procedia Computer Science 1(1):525\u2013533","DOI":"10.1016\/j.procs.2010.04.056"},{"key":"1029_CR19","unstructured":"You Y, Gitman I, Ginsburg B (2017) Scaling SGD batch size to 32k for ImageNet training, arXiv:1708.03888"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-021-01029-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-021-01029-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-021-01029-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T15:06:27Z","timestamp":1682348787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-021-01029-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,10]]},"references-count":19,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["1029"],"URL":"https:\/\/doi.org\/10.1007\/s00607-021-01029-2","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,10]]},"assertion":[{"value":"30 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"To be used for non-life science journals"}},{"value":"The allreduce test codes can be found at .","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}