{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:50:53Z","timestamp":1777063853841,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["01002047"],"award-info":[{"award-number":["01002047"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sapienza University","award":["ADAGIO"],"award-info":[{"award-number":["ADAGIO"]}]},{"name":"Sapienza University","award":["D2QNeT"],"award-info":[{"award-number":["D2QNeT"]}]},{"name":"European Union Commission\u2019s Horizon Europe","award":["101175702"],"award-info":[{"award-number":["101175702"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3769320","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"225-246","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2345-473X","authenticated-orcid":false,"given":"Tommaso","family":"Bonato","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"},{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7106-3824","authenticated-orcid":false,"given":"Abdul","family":"Kabbani","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4130-9948","authenticated-orcid":false,"given":"Ahmad","family":"Ghalayini","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9018-675X","authenticated-orcid":false,"given":"Michael","family":"Papamichael","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9513-1276","authenticated-orcid":false,"given":"Mohammad","family":"Dohadwala","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5975-4526","authenticated-orcid":false,"given":"Lukas","family":"Gianinazzi","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0862-4662","authenticated-orcid":false,"given":"Mikhail","family":"Khalilov","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7240-906X","authenticated-orcid":false,"given":"Elias","family":"Achermann","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7244-639X","authenticated-orcid":false,"given":"Daniele","family":"De Sensi","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome, Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"},{"name":"Microsoft, Redmond, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Infiniband Performance Review. In 2004 USENIX Annual Technical Conference (USENIX ATC 04)","year":"2004","unstructured":"2004. Infiniband Performance Review. In 2004 USENIX Annual Technical Conference (USENIX ATC 04). USENIX Association, Boston, MA. https:\/\/www.usenix.org\/conference\/2004-usenix-annual-technical-conference\/infiniband-performance-review"},{"key":"e_1_3_2_1_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Popa Adrian Dumitrescu Dragos Handley Mark Nikolaidis Georgios Lee Jeongkeun and Raiciu Costin. 2022. Implementing packet trimming support in hardware. (2022). arXiv:cs.NI\/2207.04967"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation (NSDI'10)","author":"Al-Fares Mohammad","year":"2010","unstructured":"Mohammad Al-Fares, Sivasankar Radhakrishnan, Barath Raghavan, Nelson Huang, and Amin Vahdat. 2010. Hedera: dynamic flow scheduling for data center networks. In Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation (NSDI'10). USENIX Association, USA, 19."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626316"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851275.1851192"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2021.10.033"},{"key":"e_1_3_2_1_8_1","volume-title":"Supplement to InfiniBand Architecture Specification","author":"Infiniband Trade Association","year":"2024","unstructured":"Infiniband Trade Association. 2024. Supplement to InfiniBand Architecture Specification Volume 1 Release 1.2.1 Annex A17: RoCEv2. (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/S00446-017-0320-4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2079296.2079304"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/S00453-018-0411-Z"},{"key":"e_1_3_2_1_12_1","volume-title":"https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm78900-series (accessed 01\/24)","author":"Switch Tomahawk","year":"2024","unstructured":"Broadcom. 2024. Tomahawk 5 Switch. (2024). https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm78900-series (accessed 01\/24)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1592681.1592693"},{"key":"e_1_3_2_1_14_1","volume-title":"11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14)","author":"Cheng Peng","year":"2014","unstructured":"Peng Cheng, Fengyuan Ren, Ran Shu, and Chuang Lin. 2014. Catch the Whole Lot in an Action: Rapid Precise Packet Loss Notification in Data Center. In 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI 14). USENIX Association, Seattle, WA, 17\u201328. https:\/\/www.usenix.org\/conference\/nsdi14\/technical-sessions\/presentation\/cheng"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2006.10129115"},{"key":"e_1_3_2_1_16_1","unstructured":"Ultra Ethernet Consortium. [n. d.]. Ultra Ethernet Specification Update - Ultra Ethernet Consortium \u2014 ultraethernet.org. https:\/\/ultraethernet.org\/ultra-ethernet-specification-update\/. ([n. d.]). [Accessed 16-09-2024]."},{"key":"e_1_3_2_1_17_1","volume-title":"https:\/\/ultraethernet.org\/","author":"Ultra Ethernet Consortium","year":"2024","unstructured":"Ultra Ethernet Consortium. 2024. Ultra Ethernet. (2024). https:\/\/ultraethernet.org\/."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00039"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567015"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29414-4_1"},{"key":"e_1_3_2_1_21_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.251892"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC3168"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098839"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242086"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098825"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:NACO.0000023417.31393.C7"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787507"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00016"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2022.3158437"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2023.3261184"},{"key":"e_1_3_2_1_33_1","unstructured":"Torsten Hoefler Karen Schramm Eric Spada Keith Underwood Cedell Alexander Bob Alverson Paul Bottorff Adrian Caulfield Mark Handley Cathy Huang Costin Raiciu Abdul Kabbani Eugene Opsasnick Rong Pan Adee Ran and Rip Sohan. 2025. Ultra Ethernet's Design Principles and Architectural Innovations. (2025). arXiv:cs.NI\/2508.08906 https:\/\/arxiv.org\/abs\/2508.08906"},{"key":"e_1_3_2_1_34_1","volume-title":"Analysis of an Equal-Cost Multi-Path Algorithm. RFC 2992. (Nov","author":"Hopps C.","year":"2009","unstructured":"C. Hopps. 2009. Analysis of an Equal-Cost Multi-Path Algorithm. RFC 2992. (Nov. 2009). https:\/\/www.ietf.org\/rfc\/rfc2992.txt"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355615"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR.2004.1303507"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2674005.2674985"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.19"},{"key":"e_1_3_2_1_39_1","unstructured":"Yanfang Le Rong Pan Peter Newman Jeremias Blendin Abdul Kabbani Vipin Jain Raghava Sivaramu and Francis Matus. 2024. STrack: A Reliable Multipath Transport for AI\/ML Clusters. (2024). arXiv:cs.NI\/2407.15266 https:\/\/arxiv.org\/abs\/2407.15266"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29414-4_2"},{"key":"e_1_3_2_1_41_1","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania et al. 2020. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704 (2020)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750480"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.4230\/LIPICS.STACS.2023.45"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3307441.3307472"},{"key":"e_1_3_2_1_45_1","unstructured":"Tesla Motors. 2024. Tesla Transport Protocol (TTPoE). (2024). https:\/\/github.com\/teslamotors\/ttpoe (accessed 09\/24)."},{"key":"e_1_3_2_1_46_1","volume-title":"Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al.","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2208917.2209336"},{"key":"e_1_3_2_1_48_1","unstructured":"Nvidia. 2024. Networking for the Era of AI: The Network Defines the Data Center. (2024). https:\/\/nvdam.widen.net\/s\/bvpmlkbgzt\/networking-overall-whitepaper-networking-for-ai-2911204 (accessed 01\/24)."},{"key":"e_1_3_2_1_49_1","unstructured":"NVIDIA. 2024. NVIDIA Spectrum-X Network Platform Architecture. (2024). https:\/\/resources.nvidia.com\/en-us-accelerated-networking-resource-library\/nvidia-spectrum-x."},{"key":"e_1_3_2_1_50_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Olteanu Vladimir","year":"2022","unstructured":"Vladimir Olteanu, Haggai Eran, Dragos Dumitrescu, Adrian Popa, Cristi Baciu, Mark Silberstein, Georgios Nikolaidis, Mark Handley, and Costin Raiciu. 2022. An edge-queued datagram service for all datacenter traffic. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA, 761\u2013777. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/olteanu"},{"key":"e_1_3_2_1_51_1","unstructured":"Christos Pelekis. 2017. Lower bounds on binomial and Poisson tails: an approach via tail conditional expectations. (2017). arXiv:math.PR\/1609.06651 https:\/\/arxiv.org\/abs\/1609.06651"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465434"},{"key":"e_1_3_2_1_53_1","volume-title":"Rui Miao, Chao Wang, Peng Wang, Pengcheng Zhang, Xianlong Zeng Zhiping Yao, Ennan Zhai, and Dennis Cai.","author":"Qian Kun","year":"2024","unstructured":"Kun Qian, Yongqing Xi, Jiamin Cao, Jiaqi Gao, Yichi Xu, Yu Guan, Binzhang Fu, Xuemei Shi Fangbo Zhu, Rui Miao, Chao Wang, Peng Wang, Pengcheng Zhang, Xianlong Zeng Zhiping Yao, Ennan Zhai, and Dennis Cai. 2024. Alibaba HPN: A Data Center Network for Large Language Model Training. (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544226"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49543-6_13"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2043164.2018467"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3016891"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787508"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCCN51052.2020.9362921"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3464994.3464996"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3754353"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604849"},{"key":"e_1_3_2_1_63_1","volume-title":"Ultra Ethernet Specification Version 1.0. (2025). https:\/\/ultraethernet.org\/uec-1-0-spec Accessed on","author":"Ultra Ethernet Consortium","year":"2025","unstructured":"Ultra Ethernet Consortium. 2025. Ultra Ethernet Specification Version 1.0. (2025). https:\/\/ultraethernet.org\/uec-1-0-spec Accessed on August 29, 2025."},{"key":"e_1_3_2_1_64_1","volume-title":"Let It Flow: Resilient Asymmetric Load Balancing with Flowlet Switching. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Vanini Erico","year":"2017","unstructured":"Erico Vanini, Rong Pan, Mohammad Alizadeh, Parvin Taheri, and Tom Edsall. 2017. Let It Flow: Resilient Asymmetric Load Balancing with Flowlet Switching. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 407\u2013420. https:\/\/www.usenix.org\/conference\/nsdi17\/technical-sessions\/presentation\/vanini"},{"key":"e_1_3_2_1_65_1","volume-title":"Poseidon: An Efficient Congestion Control using Deployable INT for Data Center Networks. https:\/\/www.usenix.org\/system\/files\/nsdi23-wang-weitao.pdf","author":"Wang Weitao","year":"2023","unstructured":"Weitao Wang, Masoud Moshref, Yuliang Li, Gautam Kumar, T. S. Eugene Ng, Neal Cardwell, and Nandita Dukkipati. 2023. Poseidon: An Efficient Congestion Control using Deployable INT for Data Center Networks. https:\/\/www.usenix.org\/system\/files\/nsdi23-wang-weitao.pdf"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2019.8847013"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098841"},{"key":"e_1_3_2_1_68_1","volume-title":"Modeling and understanding TCP incast in data center networks. 2011 Proceedings IEEE INFOCOM","author":"Zhang Jiao","year":"2011","unstructured":"Jiao Zhang, Fengyuan Ren, and Chuang Lin. 2011. Modeling and understanding TCP incast in data center networks. 2011 Proceedings IEEE INFOCOM (2011), 1377\u20131385. https:\/\/api.semanticscholar.org\/CorpusID:16461175"},{"key":"e_1_3_2_1_69_1","volume-title":"Hashing Linearity Enables Relative Path Control in Data Centers. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Zhang Zhehui","year":"2021","unstructured":"Zhehui Zhang, Haiyang Zheng, Jiayao Hu, Xiangning Yu, Chenchen Qi, Xuemei Shi, and Guohui Wang. 2021. Hashing Linearity Enables Relative Path Control in Data Centers. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 855\u2013862. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/zhang-zhehui"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Yanli Zhao Andrew Gu Rohan Varma Liang Luo Chien-Chin Huang Min Xu Less Wright Hamid Shojanazeri Myle Ott Sam Shleifer et al. 2023. Pytorch fsdp: experiences on scaling fully sharded data parallel. arXiv preprint arXiv:2304.11277 (2023).","DOI":"10.14778\/3611540.3611569"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592803"},{"key":"e_1_3_2_1_72_1","volume-title":"Ming Zhang, and Jitu Padhye.","author":"Zhu Yibo","year":"2015","unstructured":"Yibo Zhu, Yibo Zhu, Haggai Eran, Daniel Firestone, Chuanxiong Guo, Marina Lipshteyn, Yehonatan Liron, Jitendra Padhye, Shachar Raindel, Mohamad Haj Yahia, Ming Zhang, and Jitu Padhye. 2015. Congestion Control for Large-Scale RDMA Deployments. In SIGCOMM (sigcomm ed.). ACM - Association for Computing Machinery. https:\/\/www.microsoft.com\/en-us\/research\/publication\/congestion-control-for-large-scale-rdma-deployments\/"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:44Z","timestamp":1777062044000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3769320"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":72,"alternative-id":["10.1145\/3767295.3769320","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3769320","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}