{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:59Z","timestamp":1786476479089,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3829133","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"396-414","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PReCCL: Performant and Resilient Collective Communication via Integrated Inband Telemetry and Workload Reallocation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0773-722X","authenticated-orcid":false,"given":"Zhiyong","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9013-5993","authenticated-orcid":false,"given":"Kaihui","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4228-7885","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8632-2017","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8736-8876","authenticated-orcid":false,"given":"Zihan","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6808-3242","authenticated-orcid":false,"given":"Fei","family":"Gui","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7581-8865","authenticated-orcid":false,"given":"Dan","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5468-7366","authenticated-orcid":false,"given":"Jiamin","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3548-2030","authenticated-orcid":false,"given":"Jiaqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626316"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference. 1\u201315","author":"Cao J","unstructured":"J Cao, Y Guan, K Qian, and et al. 2024. Crux: GPU-efficient communication scheduling for deep learning training. In Proceedings of the ACM SIGCOMM 2024 Conference. 1\u201315."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750499"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3009824"},{"key":"e_1_3_2_1_6_1","unstructured":"NVIDIA Corporation. 2025. NVIDIA Collective Communications Library (NCCL). https:\/\/github.com\/NVIDIA\/nccl. (2025)."},{"key":"e_1_3_2_1_7_1","unstructured":"DeepSeek-AI. 2024. DeepEP: An efficient expert-parallel communication library. https:\/\/github.com\/deepseek-ai\/DeepEP. (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Minder: Faulty Machine Detection for Large-scale Distributed Model Training. arXiv preprint arXiv.2411.01791","author":"Deng Yangtao","year":"2024","unstructured":"Yangtao Deng, Xiang Shi, Zhuo Jiang, Xingjian Zhang, Lei Zhang, Zhang Zhang, Bo Li, Zuquan Song, Hang Zhu, Gaohong Liu, Fuliang Li, Shuguang Wang, Haibin Lin, Jianxi Ye, and Minlan Yu. 2024. Minder: Faulty Machine Detection for Large-scale Distributed Model Training. arXiv preprint arXiv.2411.01791 (2024). https:\/\/arxiv.org\/abs\/2411.01791"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567015"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098839"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3767955.3767980"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098825"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787507"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2945863"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691864"},{"key":"e_1_3_2_1_16_1","volume-title":"Supplement to InfiniBand Architecture Specification","author":"InfiniBand Trade Association (IBTA). 2014.","unstructured":"InfiniBand Trade Association (IBTA). 2014. Supplement to InfiniBand Architecture Specification Volume 1 Release 1.2.1, Annex A17: RoCE. InfiniBand Trade Association, Beaverton, OR, USA. Available at: https:\/\/www.infinibandta.org."},{"key":"e_1_3_2_1_17_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, et al. 2024. {MegaScale}: Scaling large language model training to more than 10,000 {GPUs}. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 745\u2013760."},{"key":"e_1_3_2_1_18_1","volume-title":"Megascale-moe: Large-scale communication-efficient training of mixture-of-experts models in production. arXiv preprint arXiv.2505.11432","author":"Jin Chao","year":"2025","unstructured":"Chao Jin, Ziheng Jiang, Zhihao Bai, Zheng Zhong, Juncai Liu, Xiang Li, Ningxin Zheng, Xi Wang, Cong Xie, Qi Huang, et al. 2025. Megascale-moe: Large-scale communication-efficient training of mixture-of-experts models in production. arXiv preprint arXiv.2505.11432 (2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1090191.1080122"},{"key":"e_1_3_2_1_20_1","volume-title":"Multipath transport and packet spraying for efficient data delivery in data centres. Computer networks 162","author":"Kheirkhah Morteza","year":"2019","unstructured":"Morteza Kheirkhah, Ian Wakeman, and George Parisis. 2019. Multipath transport and packet spraying for efficient data delivery in data centres. Computer networks 162 (2019), 106852."},{"key":"e_1_3_2_1_21_1","volume-title":"Mohammad Azar Khan, et al","author":"Kim Changhoon","year":"2015","unstructured":"Changhoon Kim, Bilal Anwer, Anirudh Gupta, Mohammad Azar Khan, et al. 2015. In-band network telemetry via programmable dataplanes. In ACM SIGCOMM Industrial Demo."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"e_1_3_2_1_23_1","unstructured":"Heng Liao Bingyang Liu Xianping Chen Zhigang Guo Chuanning Cheng Jianbing Wang Xiangyu Chen Peng Dong Rui Meng Wenjie Liu et al. 2025. UB-Mesh: a Hierarchically Localized nD-FullMesh Datacenter Network Architecture. arXiv preprint arXiv 2503.20377 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference. 16\u201337","author":"Liu X","unstructured":"X Liu, B Arzani, S K R Kakarla, and et al. 2024. Rethinking machine learning collective communication as a multi-commodity flow problem. In Proceedings of the ACM SIGCOMM 2024 Conference. 16\u201337."},{"key":"e_1_3_2_1_25_1","volume-title":"Doubling all2all Performance with NVIDIA Collective Communication Library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/. (Feb","author":"Mandakolathur Karthik","year":"2022","unstructured":"Karthik Mandakolathur and Sylvain Jeaugey. 2022. Doubling all2all Performance with NVIDIA Collective Communication Library 2.12. https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/. (Feb. 2022). https:\/\/developer.nvidia.com\/blog\/doubling-all2all-performance-with-nvidia-collective-communication-library-2-12\/ NVIDIA Developer Blog."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750521"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787510"},{"key":"e_1_3_2_1_28_1","volume-title":"n.d","author":"AMD.","year":"2025","unstructured":"AMD. n.d. 2025. ROCm Communication Collectives Library (RCCL). https:\/\/github.com\/ROCm\/rccl. (2025)."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA Corporation. 2014. NVIDIA NVLink High-Speed Interconnect: Technology Overview. Technical Report. NVIDIA White Paper. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/ White Paper."},{"key":"e_1_3_2_1_30_1","unstructured":"P4.org Applications Working Group. 2020. In-band Network Telemetry (INT) Dataplane Specification Version 2.0. Technical Report. P4.org. https:\/\/p4.org\/wp-content\/uploads\/sites\/53\/p4-spec\/docs\/INT_v2_0.pdf"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference (ACM SIGCOMM '24). Association for Computing Machinery, 691\u2013706","author":"Qian Kun","unstructured":"Kun Qian, Yongqing Xi, Jiamin Cao, Jiaqi Gao, Yichi Xu, Yu Guan, Binzhang Fu, Xuemei Shi, Fangbo Zhu, Rui Miao, and et al. 2024. Alibaba HPN: A data center network for large language model training. In Proceedings of the ACM SIGCOMM 2024 Conference (ACM SIGCOMM '24). Association for Computing Machinery, 691\u2013706."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Rajasekaran S","year":"2024","unstructured":"S Rajasekaran, M Ghobadi, and A Akella. 2024. CASSINI: Network-Aware job scheduling in machine learning clusters. In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 1403\u20131420."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)","author":"Ren Z","unstructured":"Z Ren, Y Li, Z Wang, and et al. 2025. Enabling Efficient GPU Communication over Multiple NICs with FuseLink. In Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25). 91\u2013108."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI). 593\u2013612","author":"Shah Aashaka","year":"2023","unstructured":"Aashaka Shah, Vijay Chidambaram, Meghan Cowan, Saeed Maleki, Madan Musuvathi, Todd Mytkowicz, Jacob Nelson, Olli Saarikivi, and Rachee Singh. 2023. TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches. In Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI). 593\u2013612. https:\/\/www.usenix.org\/system\/files\/nsdi23-shah.pdf"},{"key":"e_1_3_2_1_35_1","unstructured":"Base Specification. 2002. PCI Express\u00ae Base Specification Revision 3.0. (2002)."},{"key":"e_1_3_2_1_36_1","first-page":"127","article-title":"In-band Network Telemetry: A Survey","volume":"144","author":"Tan Lin","year":"2018","unstructured":"Lin Tan, Wei Su, Wenpeng Zhang, Boon Thau Loo, and Yifei Liu. 2018. In-band Network Telemetry: A Survey. Computer Networks 144 (2018),127\u2013147.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Shuai Wang Kaihui Gao Kun Qian Dan Li Rui Miao Bo Li Yu Zhou Ennan Zhai Chen Sun Jiaqi Gao et al. 2022. Predictable vFabric on informative data plane. In ACM SIGCOMM. 615\u2013632.","DOI":"10.1145\/3544216.3544241"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the ACM SIGCOMM 2024 Conference. 679\u2013690","author":"Wu Y","unstructured":"Y Wu, Y Xu, J Chen, and et al. 2024. MCCS: A Service-based Approach to Collective Communication for Multi-Tenant Cloud. In Proceedings of the ACM SIGCOMM 2024 Conference. 679\u2013690."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592803"},{"key":"e_1_3_2_1_40_1","unstructured":"Y Zhou Z Chen Z Mao and et al. 2025. An Extensible Software Transport Layer for GPU Networking. arXiv preprint arXiv 2504.17307 (2025). https:\/\/arxiv.org\/abs\/2504.17307 Accessed: 2025-09-18."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787484"},{"key":"e_1_3_2_1_42_1","unstructured":"Pengfei Zuo Huimin Lin Junbo Deng Nan Zou Xingkun Yang Yingyu Diao Weifeng Gao Ke Xu Zhangyu Chen Shirui Lu et al. 2025. Serving Large Language Models on Huawei CloudMatrix384. arXiv preprint arXiv:2506.12708 (2025)."}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3829133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:41:44Z","timestamp":1786473704000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3829133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":42,"alternative-id":["10.1145\/3789240.3829133","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3829133","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}