{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T20:00:16Z","timestamp":1766088016389,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"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_39","type":"book-chapter","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:04:32Z","timestamp":1673341472000},"page":"722-736","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DNNEmu: A Lightweight Performance Emulator for\u00a0Distributed DNN Training"],"prefix":"10.1007","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enda","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengbin","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI), pp. 265\u2013283 (2016)","key":"39_CR1"},{"unstructured":"Cai, E., Juan, D.C., Stamoulis, D., Marculescu, D.: Neuralpower: predict and deploy energy-efficient convolutional neural networks. In: Asian Conference on Machine Learning, pp. 622\u2013637. PMLR (2017)","key":"39_CR2"},{"unstructured":"Chen, T., et al.: MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. CoRR abs\/1512.01274 (2015). http:\/\/arxiv.org\/abs\/1512.01274","key":"39_CR3"},{"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)","key":"39_CR4","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"crossref","unstructured":"Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 1189\u20131232 (2001)","key":"39_CR5","DOI":"10.1214\/aos\/1013203451"},{"unstructured":"Geoffrey, X.Y., Gao, Y., Golikov, P., Pekhimenko, G.: Habitat: a runtime-based computational performance predictor for deep neural network training. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 503\u2013521 (2021)","key":"39_CR6"},{"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)","key":"39_CR7","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Justus, D., Brennan, J., Bonner, S., McGough, A.S.: Predicting the computational cost of deep learning models. In: 2018 IEEE International Conference on Big Data (Big Data), pp. 3873\u20133882. IEEE (2018)","key":"39_CR8","DOI":"10.1109\/BigData.2018.8622396"},{"key":"39_CR9","first-page":"3146","volume":"30","author":"G Ke","year":"2017","unstructured":"Ke, G., et al.: Lightgbm: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30, 3146\u20133154 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"LeCun, Y.: The mnist database of handwritten digits (1998). http:\/\/yann.lecun.com\/exdb\/mnist\/","key":"39_CR10"},{"issue":"4","key":"39_CR11","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"unstructured":"Mattson, P., et al.: Mlperf training benchmark. arXiv preprint arXiv:1910.01500 (2019)","key":"39_CR12"},{"unstructured":"NVIDIA: NVIDIA Nsight. https:\/\/developer.nvidia.com\/tools-overview","key":"39_CR13"},{"unstructured":"NVIDIA: NVIDIA Profiler. docs.nvidia.com\/cuda\/profiler-users-guide\/index.html","key":"39_CR14"},{"key":"39_CR15","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8026\u20138037 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Qi, H., Sparks, E.R., Talwalkar, A.: Paleo: a performance model for deep neural networks. In: Proceedings of the International Conference on Learning Representations (2017)","key":"39_CR16"},{"doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","key":"39_CR17","DOI":"10.1109\/CVPR.2018.00474"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)","key":"39_CR18"},{"unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical bayesian optimization of machine learning algorithms. Adv. Neural Inf. Process. Syst. 25 (2012)","key":"39_CR19"},{"doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","key":"39_CR20","DOI":"10.1109\/CVPR.2015.7298594"},{"doi-asserted-by":"crossref","unstructured":"Tang, F., et al.: Aibench training: balanced industry-standard AI training benchmarking. In: 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 24\u201335. IEEE (2021)","key":"39_CR21","DOI":"10.1109\/ISPASS51385.2021.00014"},{"unstructured":"Wong, A.W.: TorchProf. https:\/\/github.com\/awwong1\/torchprof","key":"39_CR22"},{"doi-asserted-by":"crossref","unstructured":"Yu, E., Dong, D., Xu, Y., Ouyang, S., Liao, X.: CD-SGD: distributed stochastic gradient descent with compression and delay compensation. In: 50th International Conference on Parallel Processing, pp. 1\u201310 (2021)","key":"39_CR23","DOI":"10.1145\/3472456.3472508"},{"unstructured":"Zhu, H., Phanishayee, A., Pekhimenko, G.: Daydream: accurately estimating the efficacy of optimizations for DNN training. In: 2020 USENIX Annual Technical Conference (USENIX ATC 20), pp. 337\u2013352 (2020)","key":"39_CR24"}],"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_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:13:41Z","timestamp":1673342021000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22677-9_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031226762","9783031226779"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22677-9_39","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)"}}]}}