{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:38:06Z","timestamp":1767339486520,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030576745"},{"type":"electronic","value":"9783030576752"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-57675-2_10","type":"book-chapter","created":{"date-parts":[[2020,8,17]],"date-time":"2020-08-17T23:12:33Z","timestamp":1597705953000},"page":"151-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Optimal GPU-CPU Offloading Strategies for Deep Neural Network Training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2741-6228","authenticated-orcid":false,"given":"Olivier","family":"Beaumont","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2475-3309","authenticated-orcid":false,"given":"Lionel","family":"Eyraud-Dubois","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1795-8421","authenticated-orcid":false,"given":"Alena","family":"Shilova","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,8,18]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Shriram, S.B., Garg, A., Kulkarni, P.: Dynamic memory management for GPU-based training of deep neural networks. In: IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE Press (2019). https:\/\/doi.org\/10.1109\/IPDPS.2019.00030","DOI":"10.1109\/IPDPS.2019.00030"},{"key":"10_CR2","unstructured":"Beaumont, O., Eyraud-Dubois, L., Herrmann, J., Joly, A., Shilova, A.: Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory. Research Report RR-9302, Inria Bordeaux Sud-Ouest, November 2019. https:\/\/hal.inria.fr\/hal-02352969"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Beaumont, O., Eyraud-Dubois, L., Shilova, A.: Optimal GPU-CPU Offloading Strategies for Deep Neural Network Training, October 2019. https:\/\/hal.inria.fr\/hal-02316266, working paper or preprint","DOI":"10.1007\/978-3-030-57675-2_10"},{"issue":"1","key":"10_CR4","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1186\/s12862-017-1014-z","volume":"17","author":"J Carranza-Rojas","year":"2017","unstructured":"Carranza-Rojas, J., Goeau, H., Bonnet, P., Mata-Montero, E., Joly, A.: Going deeper in the automated identification of herbarium specimens. BMC Evol. Biol. 17(1), 181 (2017). https:\/\/doi.org\/10.1186\/s12862-017-1014-z","journal-title":"BMC Evol. Biol."},{"key":"10_CR5","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Feng, Y., Zhang, Z., Zhao, X., Ji, R., Gao, Y.: GVCNN: group-view convolutional neural networks for 3D shape recognition. In: IEEE CVPR, pp. 264\u2013272. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00035","DOI":"10.1109\/CVPR.2018.00035"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Gruslys, A., Munos, R., Danihelka, I., Lanctot, M., Graves, A.: Memory-efficient backpropagation through time. In: Advances in Neural Information Processing Systems, pp. 4125\u20134133 (2016). https:\/\/doi.org\/10.5555\/3157382.3157559","DOI":"10.5555\/3157382.3157559"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet? In: IEEE CVPR, pp. 6546\u20136555. IEEE (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00685","DOI":"10.1109\/CVPR.2018.00685"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE CVPR. IEEE (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE CVPR. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"10_CR11","unstructured":"Kumar, R., Purohit, M., Svitkina, Z., Vee, E., Wang, J.: Efficient rematerialization for deep networks. In: Advances in Neural Information Processing Systems, pp. 15146\u201315155 (2019)"},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"Kwon, Y., Rhu, M.: Beyond the memory wall: a case for memory-centric HPC system for deep learning. In: 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 148\u2013161. IEEE (2018). https:\/\/doi.org\/10.1109\/MICRO.2018.00021","DOI":"10.1109\/MICRO.2018.00021"},{"key":"10_CR13","unstructured":"Le, T.D., Imai, H., Negishi, Y., Kawachiya, K.: TFLMS: large model support in tensorflow by graph rewriting. arXiv preprint arXiv:1807.02037 (2018)"},{"key":"10_CR14","unstructured":"Meng, C., Sun, M., Yang, J., Qiu, M., Gu, Y.: Training deeper models by GPU memory optimization on tensorflow. In: Proceedings of ML Systems Workshop in NIPS (2017)"},{"key":"10_CR15","unstructured":"Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., Weinberger, K.Q.: Memory-efficient implementation of densenets. arXiv preprint arXiv:1707.06990 (2017)"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Rhu, M., Gimelshein, N., Clemons, J., Zulfiqar, A., Keckler, S.W.: VDNN: virtualized deep neural networks for scalable, memory-efficient neural network design. In: The 49th Annual IEEE\/ACM International Symposium on Microarchitecture, p. 18. IEEE Press (2016). https:\/\/doi.org\/10.1109\/MICRO.2016.7783721","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Rhu, M., O\u2019Connor, M., Chatterjee, N., Pool, J., Kwon, Y., Keckler, S.W.: Compressing DMA engine: leveraging activation sparsity for training deep neural networks. In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 78\u201391. IEEE (2018). https:\/\/doi.org\/10.1109\/HPCA.2018.00017","DOI":"10.1109\/HPCA.2018.00017"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Rota Bul\u00f2, S., Porzi, L., Kontschieder, P.: In-place activated batchnorm for memory-optimized training of DNNs. In: IEEE CVPR, pp. 5639\u20135647. IEEE (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00591","DOI":"10.1109\/cvpr.2018.00591"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Shou, Z., Chan, J., Zareian, A., Miyazawa, K., Chang, S.F.: CDC: convolutional-de-convolutional networks for precise temporal action localization in untrimmed videos. In: IEEE CVPR, pp. 5734\u20135743. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.155","DOI":"10.1109\/CVPR.2017.155"},{"issue":"1","key":"10_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/3200691.3178491","volume":"53","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: SuperNeurons: dynamic GPU memory management for training deep neural networks. SIGPLAN Not. 53(1), 41\u201353 (2018). https:\/\/doi.org\/10.1145\/3200691.3178491","journal-title":"SIGPLAN Not."},{"key":"10_CR21","unstructured":"Zhang, J., Yeung, S.H., Shu, Y., He, B., Wang, W.: Efficient memory management for GPU-based deep learning systems. arXiv preprint arXiv:1903.06631 (2019)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2020: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-57675-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T00:03:18Z","timestamp":1723939398000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-57675-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030576745","9783030576752"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-57675-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 August 2020","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":"Warsaw","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2020.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":"158","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":"39","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":"25% - 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":"2.5","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 coronavirus 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}