{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T08:22:29Z","timestamp":1779006149613,"version":"3.51.4"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030856649","type":"print"},{"value":"9783030856656","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-85665-6_13","type":"book-chapter","created":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T03:06:52Z","timestamp":1630120012000},"page":"201-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Efficient and Systematic Partitioning of Large and Deep Neural Networks for Parallelization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5828-5545","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thibaut","family":"Tachon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9bastien","family":"Limet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophie","family":"Robert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,25]]},"reference":[{"key":"13_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), Savannah, GA, November 2016, pp. 265\u2013283. USENIX Association (2016)"},{"key":"13_CR2","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8026\u20138037 (2019)"},{"key":"13_CR3","unstructured":"MindSpore. https:\/\/www.mindspore.cn\/"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR5","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, June 2019, vol. 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"13_CR6","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"13_CR7","unstructured":"Dean, J., Corrado, G.S., Monga, R., et al.: Large scale distributed deep networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - vol. 1, NIPS 2012, pp. 1223\u20131231, Red Hook, NY, USA. Curran Associates Inc (2012)"},{"key":"13_CR8","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997, 2014"},{"key":"13_CR9","unstructured":"Shazeer, N., Cheng, Y., Parmar, N., et al.: Mesh-tensorflow: deep learning for supercomputers. In: Advances in Neural Information Processing Systems, pp. 10414\u201310423 (2018)"},{"key":"13_CR10","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.), 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"13_CR11","unstructured":"Jia, Z., Lin, S., Qi, C.R., Aiken, A.: Exploring hidden dimensions in accelerating convolutional neural networks. In: Volume 80 of Proceedings of Machine Learning Research, PMLR, 10\u201315 Jul 2018, pp. 2274\u20132283 (2018)"},{"key":"13_CR12","unstructured":"Jia, Z., Zaharia, M., Aiken, A.: Beyond data and model parallelism for deep neural networks. In: Talwalkar, A., Smith, V., Zaharia, M. (eds.) Proceedings of Machine Learning and Systems, vol. 1, pp. 1\u201313 (2019)"},{"issue":"2","key":"13_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1504\/IJHPCN.2012.046371","volume":"7","author":"C Li","year":"2012","unstructured":"Li, C., Hains, G.: SGL: towards a bridging model for heterogeneous hierarchical platforms. Int. J. High Perform. Comput. Netw. 7(2), 139\u2013151 (2012)","journal-title":"Int. J. High Perform. Comput. Netw."},{"key":"13_CR14","unstructured":"Dongarra, J.: Report on the Fujitsu Fugaku system. University of Tennessee-Knoxville Innovative Computing Laboratory, Tech. Rep. ICLUT-20-06-2020 (2020)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Yuksel, A., et al.: Thermal and mechanical design of the fastest supercomputer of the world in cognitive systems: IBM POWER AC 922. In: ASME 2019 InterPACK (2019)","DOI":"10.1115\/IPACK2019-6444"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Liao, H., Tu, J., Xia, J., Zhou, X.: Davinci: a scalable architecture for neural network computing. In: 2019 IEEE Hot Chips 31 Symposium (HCS), pp. 1\u201344. IEEE (2019)","DOI":"10.1109\/HOTCHIPS.2019.8875654"},{"key":"13_CR17","unstructured":"Nvidia. NVIDIA DGX-1 System Architecture White Paper (2017)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Valiant, L.G.: A bridging model for multi-core computing. J. Comput. Syst. Sci. 77(1), 154\u2013166 (2011)","DOI":"10.1016\/j.jcss.2010.06.012"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Li, A., et al.: Evaluating modern GPU interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. IEEE TPDS 31(1), 94\u2013110 (2019)","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"13_CR20","unstructured":"Zhang, H., Zheng, Z., Xu, S., et al.: Poseidon: an efficient communication architecture for distributed deep learning on GPU clusters. In: 2017 USENIX Annual Technical Conference (USENIX ATC 17), pp. 181\u2013193 (2017)"},{"key":"13_CR21","unstructured":"Sergeev, A., Balso, M.D.: Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799 (2018)"},{"key":"13_CR22","unstructured":"Chilimbi, T., Suzue, Y., Apacible, J., Kalyanaraman, K.: Project adam: building an efficient and scalable deep learning training system. In Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, OSDI 2014, USA, pp. 571\u2013582. USENIX Association (2014)"},{"key":"13_CR23","unstructured":"Atlas900. https:\/\/e.huawei.com\/en\/products\/cloud-computing-dc\/atlas\/atlas-900-ai"},{"key":"13_CR24","unstructured":"Brown, T., Mann, B., Ryder, N.: et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901. Curran Associates Inc (2020)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2021: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85665-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T22:02:56Z","timestamp":1756332176000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85665-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030856649","9783030856656"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85665-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2021.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"136","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}