{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:51:45Z","timestamp":1743072705432,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031226762"},{"type":"electronic","value":"9783031226779"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-22677-9_31","type":"book-chapter","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:04:32Z","timestamp":1673341472000},"page":"590-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PipeFB: An Optimized Pipeline Parallelism Scheme to\u00a0Reduce the\u00a0Peak Memory Usage"],"prefix":"10.1007","author":[{"given":"Wei","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"31_CR1","unstructured":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems (2016)"},{"key":"31_CR2","unstructured":"Abdollahi, B., Nasraoui, O.: Explainable restricted boltzmann machines for collaborative filtering (2016)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Athiwaratkun, B., Wilson, A.G.: Multimodal word distributions (2017)","DOI":"10.18653\/v1\/P17-1151"},{"issue":"4","key":"31_CR4","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1145\/2644865.2541967","volume":"49","author":"T Chen","year":"2014","unstructured":"Chen, T., et al.: DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. ACM Sigplan Notices 49(4), 269\u2013284 (2014)","journal-title":"ACM Sigplan Notices"},{"key":"31_CR5","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Shelhamer, E.: cuDNN: efficient primitives for deep learning. Computer ENCE (2014)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Chung, Y.A., Belinkov, Y., Glass, J.: Similarity analysis of self-supervised speech representations. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2021)","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"issue":"1","key":"31_CR7","first-page":"2493","volume":"12","author":"R Collobert","year":"2011","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12(1), 2493\u20132537 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5\u20136","key":"31_CR9","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5\u20136), 602\u2013610 (2005)","journal-title":"Neural Netw."},{"key":"31_CR10","unstructured":"Harlap, A., et al.: Pipedream: Fast and efficient pipeline parallel DNN training (2018)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"31_CR12","unstructured":"Huang, Y., et al.: GPipe: efficient training of giant neural networks using pipeline parallelism. arXiv (2018)"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Xu, R., Ma, S., Wang, Q., Hou, X., Lu, H.: A memory saving mechanism based on data transferring for pipeline parallelism. In: 2021 IEEE International Conference on Parallel Distributed Processing with Applications, Big Data Cloud Computing, Sustainable Computing Communications, Social Computing Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), pp. 1230\u20131235 (2021)","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00169"},{"issue":"3","key":"31_CR14","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2018.032271057","volume":"38","author":"N Jouppi","year":"2018","unstructured":"Jouppi, N., Young, C., Patil, N., Patterson, D.: Motivation for and evaluation of the first tensor processing unit. IEEE Micro 38(3), 10\u201319 (2018)","journal-title":"IEEE Micro"},{"key":"31_CR15","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Chintala, S.: PyTorch: an imperative style, high-performance deep learning library (2019)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Rhu, M., Gimelshein, N., Clemons, J., Zulfiqar, A., Keckler, S.W.: VDNN: virtualized deep neural networks for scalable, memory-efficient neural network design. ACM (2016)","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Rhu, M., O\u2019Connor, M., Chatterjee, N., Pool, J., Keckler, S.W.: Compressing DMA engine: Leveraging activation sparsity for training deep neural networks. IEEE Computer Society (2017)","DOI":"10.1109\/HPCA.2018.00017"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Sarwar, B.: Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International World Wide Web Conference (WWW10), Hong Kong, May 1\u20135 (2001) (2001)","DOI":"10.1145\/371920.372071"},{"key":"31_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. Computer Science (2014)"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Rabinovich, A.: Going deeper with convolutions. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"31_CR22","unstructured":"Ts\/Technicolor, and Sor Related. ImageNet classification with deep convolutional neural networks [50]"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Wang, L., Ye, J., Zhao, Y., Wei, W., Kraska, T.: Superneurons: dynamic GPU memory management for training deep neural networks (2018)","DOI":"10.1145\/3178487.3178491"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, Z., Demmel, J., Keutzer, K., Hsieh, C.J.: ImageNet training in 24 minutes (2017)","DOI":"10.1145\/3225058.3225069"},{"key":"31_CR25","unstructured":"Zeng, W., et al.: Pangu-$$\\alpha $$: Large-scale autoregressive pretrained Chinese language models with auto-parallel computation (2021)"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhan, J., Li, J., Jin, J., Qian, L.: Optimizing execution for pipelined-based distributed deep learning in a heterogeneously networked GPU cluster. Concurrency and Computation Practice and Experience (2020)","DOI":"10.1002\/cpe.5923"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22677-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:11:44Z","timestamp":1673341904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22677-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031226762","9783031226779"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22677-9_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2022","order":10,"name":"conference_id","label":"Conference ID","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":"91","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":"33","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":"10","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":"36% - 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","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":"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)"}}]}}