{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T19:09:21Z","timestamp":1763665761703,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","funder":[{"name":"Hong Kong RGC Theme-based Research Scheme (TRS)","award":["T41-603\\\/20R"],"award-info":[{"award-number":["T41-603\\\/20R"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,7]]},"DOI":"10.1145\/3735358.3735378","type":"proceedings-article","created":{"date-parts":[[2025,7,17]],"date-time":"2025-07-17T23:08:27Z","timestamp":1752793707000},"page":"59-65","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Congestion Control for AI Workloads with Message-Level Signaling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9042-7285","authenticated-orcid":false,"given":"Yuxuan","family":"Li","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8779-4768","authenticated-orcid":false,"given":"Zhenghang","family":"Ren","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8228-2552","authenticated-orcid":false,"given":"Wenxue","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2156-9683","authenticated-orcid":false,"given":"Xiangzhou","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2025. NVIDIA Collective Communications Library (NCCL) | NVIDIA Developer. https:\/\/developer.nvidia.com\/nccl. (2025)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626316"},{"key":"e_1_3_3_1_4_2","unstructured":"Wei An Xiao Bi Guanting Chen Shanhuang Chen Chengqi Deng Honghui Ding Kai Dong Qiushi Du Wenjun Gao Kang Guan Jianzhong Guo Yongqiang Guo Zhe Fu Ying He Panpan Huang Jiashi Li Wenfeng Liang Xiaodong Liu Xin Liu Yiyuan Liu Yuxuan Liu Shanghao Lu Xuan Lu Xiaotao Nie Tian Pei Junjie Qiu Hui Qu Zehui Ren Zhangli Sha Xuecheng Su Xiaowen Sun Yixuan Tan Minghui Tang Shiyu Wang Yaohui Wang Yongji Wang Ziwei Xie Yiliang Xiong Yanhong Xu Shengfeng Ye Shuiping Yu Yukun Zha Liyue Zhang Haowei Zhang Mingchuan Zhang Wentao Zhang Yichao Zhang Chenggang Zhao Yao Zhao Shangyan Zhou Shunfeng Zhou and Yuheng Zou. 2024. Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning. (2024). arxiv:cs.DC\/2408.14158https:\/\/arxiv.org\/abs\/2408.14158"},{"key":"e_1_3_3_1_5_2","first-page":"49","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Bai Wei","year":"2023","unstructured":"Wei Bai, Shanim\u00a0Sainul Abdeen, Ankit Agrawal, Krishan\u00a0Kumar Attre, Paramvir Bahl, Ameya Bhagat, Gowri Bhaskara, Tanya Brokhman, Lei Cao, Ahmad Cheema, et\u00a0al. 2023. Empowering azure storage with { RDMA}. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 49\u201367."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2535372.2535375"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672198.3673794"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Vinton Cerf and Robert Kahn. 1974. A protocol for packet network intercommunication. IEEE Transactions on communications 22 5 (1974) 637\u2013648.","DOI":"10.1109\/TCOM.1974.1092259"},{"key":"e_1_3_3_1_9_2","first-page":"17","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). 17\u201328."},{"key":"e_1_3_3_1_10_2","first-page":"19","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Cheng Wenxue","year":"2020","unstructured":"Wenxue Cheng, Kun Qian, Wanchun Jiang, Tong Zhang, and Fengyuan Ren. 2020. Re-architecting congestion management in lossless ethernet. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 19\u201336."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018477"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"e_1_3_3_1_14_2","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.15266 (2024)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267826"},{"key":"e_1_3_3_1_16_2","first-page":"931","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Li Qiang","year":"2023","unstructured":"Qiang Li, Yixiao Gao, Xiaoliang Wang, Haonan Qiu, Yanfang Le, Derui Liu, Qiao Xiang, Fei Feng, Peng Zhang, Bo Li, et\u00a0al. 2023. Flor: An open high performance { RDMA} framework over heterogeneous { RNICs}. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 931\u2013948."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"e_1_3_3_1_18_2","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et\u00a0al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19437 (2024)."},{"key":"e_1_3_3_1_19_2","first-page":"357","volume-title":"15th USENIX symposium on networked systems design and implementation (NSDI 18)","author":"Lu Yuanwei","year":"2018","unstructured":"Yuanwei Lu, Guo Chen, Bojie Li, Kun Tan, Yongqiang Xiong, Peng Cheng, Jiansong Zhang, Enhong Chen, and Thomas Moscibroda. 2018. { Multi-Path} transport for { RDMA} in datacenters. In 15th USENIX symposium on networked systems design and implementation (NSDI 18). 357\u2013371."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544226"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2535372.2535397"},{"key":"e_1_3_3_1_24_2","first-page":"407","volume-title":"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). 407\u2013420."},{"key":"e_1_3_3_1_25_2","first-page":"999","volume-title":"22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Xu Kaiqiang","year":"2025","unstructured":"Kaiqiang Xu, Decang Sun, Han Tian, Junxue Zhang, and Kai Chen. 2025. { GREEN} : Carbon-efficient Resource Scheduling for Machine Learning Clusters. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). 999\u20131014."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707266"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342390"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592803"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Yibo Zhu Haggai Eran Daniel Firestone Chuanxiong Guo Marina Lipshteyn Yehonatan Liron Jitendra Padhye Shachar Raindel Mohamad\u00a0Haj Yahia and Ming Zhang. 2015. Congestion control for large-scale RDMA deployments. ACM SIGCOMM Computer Communication Review 45 4 (2015) 523\u2013536.","DOI":"10.1145\/2829988.2787484"}],"event":{"name":"APNET 2025: The 9th Asia-Pacific Workshop on Networking","acronym":"APNET 2025","location":"Shang Hai China"},"container-title":["Proceedings of the 9th Asia-Pacific Workshop on Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3735358.3735378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T05:10:28Z","timestamp":1753161028000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3735358.3735378"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":28,"alternative-id":["10.1145\/3735358.3735378","10.1145\/3735358"],"URL":"https:\/\/doi.org\/10.1145\/3735358.3735378","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}