{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:57:00Z","timestamp":1774162620371,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030507428","type":"print"},{"value":"9783030507435","type":"electronic"}],"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\/978-3-030-50743-5_5","type":"book-chapter","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T19:03:45Z","timestamp":1592247825000},"page":"83-103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["HyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training with TensorFlow"],"prefix":"10.1007","author":[{"given":"Ammar Ahmad","family":"Awan","sequence":"first","affiliation":[]},{"given":"Arpan","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Quentin","family":"Anthony","sequence":"additional","affiliation":[]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"key":"5_CR1","unstructured":"Keras (2019). https:\/\/keras.io\/"},{"key":"5_CR2","unstructured":"Model parallelism in MXNet (2019). https:\/\/mxnet.apache.org\/api\/faq\/model_parallel_lstm"},{"key":"5_CR3","unstructured":"Akiba, T., Suzuki, S., Fukuda, K.: Extremely large minibatch SGD: training resnet-50 on ImageNet in 15 minutes (2017). CoRR abs\/1711.04325. http:\/\/arxiv.org\/abs\/1711.04325"},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Awan, A.A., Chu, C., Subramoni, H., Lu, X., Panda, D.K.: OC-DNN: exploiting advanced unified memory capabilities in CUDA 9 and volta GPUs for out-of-core DNN training. In: 2018 IEEE 25th International Conference on High Performance Computing (HiPC), pp. 143\u2013152, December 2018. https:\/\/doi.org\/10.1109\/HiPC.2018.00024","DOI":"10.1109\/HiPC.2018.00024"},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Awan, A.A., Hamidouche, K., Hashmi, J.M., Panda, D.K.: S-Caffe: co-designing MPI runtimes and caffe for scalable deep learning on modern GPU Clusters. In: Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming PPoPP 2017, pp. 193\u2013205. ACM, New York (2017). https:\/\/doi.org\/10.1145\/3018743.3018769","DOI":"10.1145\/3018743.3018769"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Bauer, M., Treichler, S., Slaughter, E., Aiken, A.: Legion: expressing locality and independence with logical regions. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis SC 2012, pp. 66:1\u201366:11. IEEE Computer Society Press, Los Alamitos (2012). http:\/\/dl.acm.org\/citation.cfm?id=2388996.2389086","DOI":"10.1109\/SC.2012.71"},{"key":"5_CR7","unstructured":"Ben-Nun, T., Hoefler, T.: Demystifying parallel and distributed deep learning: an in-depth concurrency analysis (2018). CoRR abs\/1802.09941. http:\/\/arxiv.org\/abs\/1802.09941"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Dryden, N., Maruyama, N., Benson, T., Moon, T., Snir, M., Essen, B.V.: Improving strong-scaling of CNN training by exploiting finer-grained parallelism (2019). CoRR abs\/1903.06681. http:\/\/arxiv.org\/abs\/1903.06681","DOI":"10.1109\/IPDPS.2019.00031"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Gholami, A., Azad, A., Jin, P., Keutzer, K., Buluc, A.: Integrated model, batch, and domain parallelism in training neural networks. In: Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures SPAA 2018, pp. 77\u201386. ACM, New York (2018). https:\/\/doi.org\/10.1145\/3210377.3210394","DOI":"10.1145\/3210377.3210394"},{"key":"5_CR10","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour (2017). CoRR abs\/1706.02677. http:\/\/arxiv.org\/abs\/1706.02677"},{"key":"5_CR11","unstructured":"Harlap, A., et al.: PipeDream: fast and efficient pipeline parallel DNN training (2018). CoRR abs\/1806.03377. http:\/\/arxiv.org\/abs\/1806.03377"},{"key":"5_CR12","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks (2016). CoRR absscaffe,\/1603.05027. http:\/\/arxiv.org\/abs\/1603.05027"},{"key":"5_CR13","unstructured":"Huang, Y., et al.: GPipe: efficient training of giant neural networks using pipeline parallelism (2018). CoRR abs\/1811.06965. http:\/\/arxiv.org\/abs\/1811.06965"},{"key":"5_CR14","unstructured":"Jia, Z., Zaharia, M., Aiken, A.: Beyond data and model parallelism for deep neural networks (2018). CoRR abs\/1807.05358. http:\/\/arxiv.org\/abs\/1807.05358"},{"key":"5_CR15","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks (2014). CoRR abs\/1404.5997. http:\/\/arxiv.org\/abs\/1404.5997"},{"key":"5_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012). http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf"},{"key":"5_CR17","unstructured":"Markthub, P., Belviranli, M.E., Lee, S., Vetter, J.S., Matsuoka, S.: DRAGON: breaking GPU memory capacity limits with direct NVM access. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis SC 2018, pp. 32:1\u201332:13. IEEE Press, Piscataway (2018). http:\/\/dl.acm.org\/citation.cfm?id=3291656.3291699"},{"key":"5_CR18","unstructured":"Mikami, H., Suganuma, H., Chupala, U.-P., Tanaka, Y., Kageyama, Y.: Imagenet\/resnet-50 training in 224 seconds (2018). CoRR abs\/1811.05233. http:\/\/arxiv.org\/abs\/1811.05233"},{"key":"5_CR19","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search (2018). CoRR abs\/1802.01548. http:\/\/arxiv.org\/abs\/1802.01548"},{"key":"5_CR20","unstructured":"Shazeer et al.: Mesh-TensorFlow: deep learning for supercomputers. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 10414\u201310423. Curran Associates, Inc. (2018). http:\/\/papers.nips.cc\/paper\/8242-mesh-tensorflow-deep-learning-for-supercomputers.pdf"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Sun, P., Feng, W., Han, R., Yan, S., Wen, Y.: Optimizing network performance for distributed DNN training on GPU clusters: Imagenet\/alexnet training in 1.5 minutes (2019). CoRR abs\/1902.06855. http:\/\/arxiv.org\/abs\/1902.06855","DOI":"10.1109\/TBDATA.2019.2957478"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-50743-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:02:56Z","timestamp":1702929776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-50743-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030507428","9783030507435"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-50743-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"15 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt am Main","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"22 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","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":"27","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":"31% - 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":"3.73","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":"4.33","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":"No","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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}