{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:05:43Z","timestamp":1791479143505,"version":"4.3.4"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030787127","type":"print"},{"value":"9783030787134","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\/978-3-030-78713-4_5","type":"book-chapter","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T23:06:15Z","timestamp":1623884775000},"page":"79-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Auto-Precision Scaling for Distributed Deep Learning"],"prefix":"10.1007","author":[{"given":"Ruobing","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Demmel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,6,17]]},"reference":[{"key":"5_CR1","unstructured":"Davidnet. https:\/\/github.com\/davidcpage\/cifar10-fast"},{"key":"5_CR2","unstructured":"Mmsegmentation. https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"5_CR3","unstructured":"torchvision. https:\/\/github.com\/pytorch\/vision"},{"key":"5_CR4","unstructured":"Alistarh, D., Grubic, D., Li, J., Tomioka, R., Vojnovic, M.: QSGD: communication-efficient SGD via gradient quantization and encoding. In: Advances in Neural Information Processing Systems, pp. 1709\u20131720 (2017)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"5_CR6","unstructured":"Courbariaux, M., Bengio, Y., David, J.P.: Training deep neural networks with low precision multiplications. arXiv preprint arXiv:1412.7024 (2014)"},{"key":"5_CR7","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"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Dryden, N., Moon, T., Jacobs, S.A., Van Essen, B.: Communication quantization for data-parallel training of deep neural networks. In: 2016 2nd Workshop on Machine Learning in HPC Environments (MLHPC), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/MLHPC.2016.004"},{"key":"5_CR9","unstructured":"Gibiansky, A.: Bringing HPC techniques to deep learning. Technical report, Baidu Research (2017)"},{"key":"5_CR10","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: The IEEE International Conference on Computer Vision (ICCV), December 2015","DOI":"10.1109\/ICCV.2015.123"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Higham, N.J.: Accuracy and Stability of Numerical Algorithms, vol. 80. SIAM (2002)","DOI":"10.1137\/1.9780898718027"},{"key":"5_CR14","unstructured":"Jia, X., et al.: Highly scalable deep learning training system with mixed-precision: training ImageNet in four minutes. arXiv preprint arXiv:1807.11205 (2018)"},{"key":"5_CR15","unstructured":"Johnson, J.: Rethinking floating point for deep learning. arXiv preprint arXiv:1811.01721 (2018)"},{"key":"5_CR16","unstructured":"K\u00f6ster, U., et al.: Flexpoint: an adaptive numerical format for efficient training of deep neural networks. In: Advances in Neural Information Processing Systems, pp. 1742\u20131752 (2017)"},{"key":"5_CR17","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, W.J.: Deep gradient compression: reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887 (2017)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5_CR19","unstructured":"Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Sun, P., Wen, Y., Han, R., Feng, W., Yan, S.: GradientFlow: optimizing network performance for large-scale distributed DNN training. IEEE Trans. Big Data (2019)","DOI":"10.1109\/TBDATA.2019.2957478"},{"key":"5_CR21","unstructured":"Wang, N., Choi, J., Brand, D., Chen, C.Y., Gopalakrishnan, K.: Training deep neural networks with 8-bit floating point numbers. In: Advances in Neural Information Processing Systems, pp. 7675\u20137684 (2018)"},{"key":"5_CR22","unstructured":"Wangni, J., Wang, J., Liu, J., Zhang, T.: Gradient sparsification for communication-efficient distributed optimization. arXiv preprint arXiv:1710.09854 (2017)"},{"key":"5_CR23","unstructured":"Wen, W., Xu, C., Yan, F., Wu, C., Wang, Y., Chen, Y., Li, H.: TernGrad: ternary gradients to reduce communication in distributed deep learning. In: Advances in Neural Information Processing Systems, pp. 1509\u20131519 (2017)"},{"key":"5_CR24","unstructured":"Ying, C., Kumar, S., Chen, D., Wang, T., Cheng, Y.: Image classification at supercomputer scale. arXiv preprint arXiv:1811.06992 (2018)"},{"key":"5_CR25","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Scaling SGD batch size to 32k for ImageNet training. arXiv preprint arXiv:1708.03888, 6 2017"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, Z., Hsieh, C.J., Demmel, J., Keutzer, K.: ImageNet training in minutes. In: Proceedings of the 47th International Conference on Parallel Processing, p. 1. ACM (2018)","DOI":"10.1145\/3225058.3225069"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, T., Lin, Z., Yang, G., Sa, C.D.: QPyTorch: a low-precision arithmetic simulation framework (2019)","DOI":"10.1109\/EMC2-NIPS53020.2019.00010"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78713-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,29]],"date-time":"2023-03-29T07:04:52Z","timestamp":1680073492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78713-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030787127","9783030787134"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78713-4_5","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":"17 June 2021","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2021","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":"74","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":"24","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":"32% - 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":"4.28","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":"4.13","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":"In the ISC High Performance Workshop, there were 49 submissions, out of which 35  were accepted.","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)"}}]}}