{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:47:07Z","timestamp":1743007627877,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819708338"},{"type":"electronic","value":"9789819708345"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0834-5_23","type":"book-chapter","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T02:02:48Z","timestamp":1710208968000},"page":"401-418","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance Comparison of\u00a0Distributed DNN Training on\u00a0Optical Versus Electrical Interconnect Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-3320","authenticated-orcid":false,"given":"Fei","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7006-2459","authenticated-orcid":false,"given":"Yawen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8561-2556","authenticated-orcid":false,"given":"Zhiyi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3752-0806","authenticated-orcid":false,"given":"Haibo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7952-571X","authenticated-orcid":false,"given":"Hui","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,12]]},"reference":[{"key":"23_CR1","first-page":"1","volume":"2022","author":"AR Khan","year":"2022","unstructured":"Khan, A.R., Kashif, M., Jhaveri, R.H., Raut, R., Saba, T., Bahaj, S.A.: Deep learning for intrusion detection and security of Internet of Things (IoT): current analysis, challenges, and possible solutions. Secur. Commun. Netw. 2022, 1\u201313 (2022)","journal-title":"Secur. Commun. Netw."},{"key":"23_CR2","first-page":"82","volume":"2","author":"L Luo","year":"2020","unstructured":"Luo, L., West, P., Nelson, J., Krishnamurthy, A., Ceze, L.: PLink: discovering and exploiting locality for accelerated distributed training on the public cloud. Proc. Mach. Learn. Syst. 2, 82\u201397 (2020)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"23_CR3","first-page":"172","volume":"2","author":"G Wang","year":"2020","unstructured":"Wang, G., Venkataraman, S., Phanishayee, A., Devanur, N., Thelin, J., Stoica, I.: Blink: Fast and generic collectives for distributed ML. Proc. Mach. Learn. Syst. 2, 172\u2013186 (2020)","journal-title":"Proc. Mach. Learn. Syst."},{"unstructured":"Yuichiro, U., Yokota, R.: Exhaustive study of hierarchical allreduce patterns for large messages between GPUs. In: 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), pp. 430\u2013439 (2019)","key":"23_CR4"},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"183488","DOI":"10.1109\/ACCESS.2020.3028367","volume":"8","author":"Y Jiang","year":"2020","unstructured":"Jiang, Y., Gu, H., Lu, Y., Yu, X.: 2D-HRA: two-dimensional hierarchical ring-based all-reduce algorithm in large-scale distributed machine learning. IEEE Access 8, 183488\u2013183494 (2020)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Cho, M., Finkler, U., Serrano, M., Kung, D., Hunter, H.: BlueConnect: decomposing all-reduce for deep learning on heterogeneous network hierarchy. IBM J. Res. Dev. 63(6), 1:1\u20131:11 (2019)","key":"23_CR6","DOI":"10.1147\/JRD.2019.2947013"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Takano, R.: On the feasibility of hybrid electrical\/optical switch architecture for large-scale training of distributed deep learning. In: 2019 IEEE\/ACM Workshop on Photonics-Optics Technology Oriented Networking, Information and Computing Systems (PHOTONICS), pp. 7\u201314 (2019)","key":"23_CR7","DOI":"10.1109\/PHOTONICS49561.2019.00007"},{"doi-asserted-by":"crossref","unstructured":"Khani, M., et al.: SIP-ML: high-bandwidth optical network interconnects for machine learning training. In: Proceedings of the 2021 ACM SIGCOMM 2021 Conference, pp. 657\u2013675 (2021)","key":"23_CR8","DOI":"10.1145\/3452296.3472900"},{"doi-asserted-by":"crossref","unstructured":"Gu, R., Qiao, Y., Ji, Y.: Optical or electrical interconnects: quantitative comparison from parallel computing performance view. In: 2008 IEEE Global Telecommunications Conference, IEEE GLOBECOM 2008, pp. 1\u20135 (2008)","key":"23_CR9","DOI":"10.1109\/GLOCOM.2008.ECP.534"},{"unstructured":"Shin, J., Seo, C.S., Chellappa, A., Brooke, M., Chatterjee, A., Jokerst, N.M.: Comparison of electrical and optical interconnect. In: IEEE Electronic Components and Technology Conference, pp. 1067\u20131072 (1999)","key":"23_CR10"},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"113648","DOI":"10.1016\/j.microrel.2020.113648","volume":"110","author":"J Wei","year":"2020","unstructured":"Wei, J., et al.: Analyzing the impact of soft errors in VGG networks implemented on GPUs. Microelectron. Reliab. 110, 113648 (2020)","journal-title":"Microelectron. Reliab."},{"doi-asserted-by":"crossref","unstructured":"Casanova, H., Legrand, A., Quinson, M.: SimGrid: a generic framework for large-scale distributed experiments. In: Tenth IEEE International Conference on Computer Modeling and Simulation, UKSim2008, pp. 126\u2013131 (2008)","key":"23_CR12","DOI":"10.1109\/UKSIM.2008.28"},{"key":"23_CR13","first-page":"1","volume":"2022","author":"SD Alotaibi","year":"2022","unstructured":"Alotaibi, S.D., et al.: Deep Neural Network - based intrusion detection system through PCA. Math. Prob. Eng. 2022, 1\u20139 (2022)","journal-title":"Math. Prob. Eng."},{"doi-asserted-by":"crossref","unstructured":"Huang, J., Majumder, P., Kim, S., Muzahid, A., Yum, K.H., Kim, E.J.: Communication algorithm-architecture co-design for distributed deep learning. In: 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), pp. 181\u2013194. IEEE (2021)","key":"23_CR14","DOI":"10.1109\/ISCA52012.2021.00023"},{"doi-asserted-by":"crossref","unstructured":"Ghobadi, M.: Emerging optical interconnects for AI systems. In: IEEE 2022 Optical Fiber Communications Conference and Exhibition (OFC), pp. 1\u20133 (2022)","key":"23_CR15","DOI":"10.1364\/OFC.2022.Th1G.1"},{"doi-asserted-by":"crossref","unstructured":"Dai, F., Chen, Y., Huang, Z., Zhang, H., Zhang, F.: Efficient all-reduce for distributed DNN training in optical interconnect systems. In: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, pp. 422\u2013424 (2023)","key":"23_CR16","DOI":"10.1145\/3572848.3577391"},{"unstructured":"TensorFlow: Optimize TensorFlow performance using the Profiler (n.d.). https:\/\/www.tensorflow.org\/guide\/profiler. Accessed 2 Sept 2023","key":"23_CR17"},{"unstructured":"Wang, W., et al.: TopoOpt: co-optimizing network topology and parallelization strategy for distributed training jobs. In: 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023, pp. 739\u2013767 (2023)","key":"23_CR18"},{"unstructured":"Zhang, H., et al.: Poseidon: an efficient communication architecture for distributed deep learning on GPU clusters. In: 2017 USENIX Annual Technical Conference, USENIX ATC 2017, pp. 181\u2013193 (2017)","key":"23_CR19"},{"issue":"10","key":"23_CR20","doi-asserted-by":"publisher","first-page":"10725","DOI":"10.1007\/s11227-022-04945-y","volume":"79","author":"F Dai","year":"2023","unstructured":"Dai, F., Chen, Y., Huang, Z., Zhang, H., Zhang, H., Xia, C.: Comparing the performance of multi-layer perceptron training on electrical and optical network-on-chips. J. Supercomput. 79(10), 10725\u201310746 (2023)","journal-title":"J. Supercomput."},{"key":"23_CR21","doi-asserted-by":"publisher","first-page":"100761","DOI":"10.1016\/j.osn.2023.100761","volume":"51","author":"A Ottino","year":"2023","unstructured":"Ottino, A., Benjamin, J., Zervas, G.: RAMP: a flat nanosecond optical network and MPI operations for distributed deep learning systems. Opt. Switching Netw. 51, 100761 (2023)","journal-title":"Opt. Switching Netw."},{"unstructured":"Dai, F., Chen, Y., Zhang, H., Huang, Z.: Accelerating fully connected neural network on optical network-on-chip (ONoC). arXiv preprint arXiv:2109.14878 (2021)","key":"23_CR22"},{"issue":"1","key":"23_CR23","doi-asserted-by":"publisher","first-page":"513","DOI":"10.2298\/CSIS220131066X","volume":"20","author":"C Xia","year":"2023","unstructured":"Xia, C., Chen, Y., Zhang, H., Zhang, H., Dai, F., Wu, J.: Efficient neural network accelerators with optical computing and communication. Comput. Sci. Inf. Syst. 20(1), 513\u2013535 (2023)","journal-title":"Comput. Sci. Inf. Syst."}],"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\/978-981-97-0834-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T02:08:09Z","timestamp":1710209289000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0834-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819708338","9789819708345"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0834-5_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 March 2024","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":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tjutanklab.com\/ica3pp2023\/","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":"Online submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"439","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":"145","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":"33% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}