{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:48:48Z","timestamp":1776678528079,"version":"3.51.2"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104588","type":"print"},{"value":"9783032104595","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10459-5_17","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:06:53Z","timestamp":1763190413000},"page":"208-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DPS: A Congestion-Aware Allreduce Job Placement for\u00a0In-Network Aggregation"],"prefix":"10.1007","author":[{"given":"Yanrong","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guannan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Zhao, H., Canny, J.: Kylix: a sparse allreduce for commodity clusters. In: Proceedings International Conference Parallel Process, pp. 273-282 (2014)","DOI":"10.1109\/ICPP.2014.36"},{"key":"17_CR2","unstructured":"Zhao, H., Canny, J.: Sparse allreduce: efficient scalable communication for power-law data. arXiv preprint arXiv:1312.3020 (2013)"},{"issue":"8","key":"17_CR3","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1103\/PhysRevD.35.2531","volume":"35","author":"S Gottlieb","year":"1987","unstructured":"Gottlieb, S., et al.: Hybrid-molecular-dynamics algorithms for the numerical simulation of quantum chromodynamics. Phys. Rev. D 35(8), 2531 (1987)","journal-title":"Phys. Rev. D"},{"issue":"1","key":"17_CR4","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"17_CR5","unstructured":"Sapio, A., et al.: Scaling distributed machine learning with in-network aggregation. In: Proceedings USENIX NSDI, pp. 785-808 (2021)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Roar: a router microarchitecture for in-network allreduce. In: Proceedings International Conference Supercomput, pp. 423-436 (2023)","DOI":"10.1145\/3577193.3593711"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, G., et al.: Libra: high-precision congestion control for datacenter networks with in-network allreduce. Computer Networks, p. 111407 (2025)","DOI":"10.1016\/j.comnet.2025.111407"},{"key":"17_CR8","unstructured":"Lao, C.L., et al.: ATP: In-network aggregation for multi-tenant learning. In: Proceedings USENIX NSDI, pp. 741-761 (2021)"},{"key":"17_CR9","first-page":"829","volume":"3","author":"N Gebara","year":"2021","unstructured":"Gebara, N., Ghobadi, M., Costa, P.: In-network aggregation for shared machine learning clusters. Proc. Mach. Learn. Syst. 3, 829\u2013844 (2021)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"17_CR10","unstructured":"Liu, S., et al.: NetReduce: RDMA-compatible in-network reduction for distributed DNN training acceleration. arXiv preprint arXiv:2009.09736 (2020)"},{"key":"17_CR11","unstructured":"Hwang, C., et al.: Elastic resource sharing for distributed deep learning. In: Proceeding USENIX NSDI, pp. 721-739 (2021)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Peng, Y., et al.: Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: Proceeding EuroSys Conference, pp. 1-14 (2018)","DOI":"10.1145\/3190508.3190517"},{"key":"17_CR13","unstructured":"\u201cNomad,\u201d HashiCorp. https:\/\/developer.hashicorp.com\/nomad\/docs"},{"key":"17_CR14","unstructured":"NVIDIA H100 Tensor Core GPU. NVIDIA. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/"},{"issue":"2","key":"17_CR15","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/MM.2024.3360081","volume":"44","author":"L Dai","year":"2024","unstructured":"Dai, L., et al.: High-speed data communication with advanced networks in large language model training. IEEE Micro 44(2), 31\u201340 (2024)","journal-title":"IEEE Micro"},{"issue":"5439","key":"17_CR16","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1126\/science.286.5439.509","volume":"286","author":"AL Barab\u00e1si","year":"1999","unstructured":"Barab\u00e1si, A.L., Albert, R.: Emergence of scaling in random networks. Science 286(5439), 509\u2013512 (1999)","journal-title":"Science"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Luo, X., et al.: Han: a hierarchical autotuned collective communication framework. In: Proceeding IEEE CLUSTER, pp. 23-34 (2020)","DOI":"10.1109\/CLUSTER49012.2020.00013"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Dorier, M., et al.: Evaluation of topology-aware broadcast algorithms for dragonfly networks. In: Proceeding IEEE CLUSTER, pp. 40-49 (2016)","DOI":"10.1109\/CLUSTER.2016.26"},{"key":"17_CR19","unstructured":"Wang, S., et al.: BML: a high-performance, low-cost gradient synchronization algorithm for DML training. In: Advanced Neural International Process System, vol. 31 (2018)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Eflops: algorithm and system co-design for a high performance distributed training platform. In: Proceeding IEEE HPCA, pp. 610-622 (2020)","DOI":"10.1109\/HPCA47549.2020.00056"},{"issue":"5","key":"17_CR21","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/MM.2021.3091475","volume":"41","author":"J Dong","year":"2021","unstructured":"Dong, J., et al.: ACCL: architecting highly scalable distributed training systems with highly efficient collective communication library. IEEE Micro 41(5), 85\u201392 (2021)","journal-title":"IEEE Micro"},{"key":"17_CR22","unstructured":"\u201cOMNeT++ Simulator\u201d. https:\/\/omnetpp.org\/"},{"key":"17_CR23","unstructured":"\u201cINET Framework\u201d. https:\/\/inet.omnetpp.org\/"},{"key":"17_CR24","unstructured":"\u201cNVLink,\u201d NVIDIA. https:\/\/www.nvidia.cn\/data-center\/nvlink\/"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10459-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T08:54:47Z","timestamp":1776675287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10459-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104588","9783032104595"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10459-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}