{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:34:35Z","timestamp":1774449275477,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432003"],"award-info":[{"award-number":["62432003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B200"],"award-info":[{"award-number":["U22B200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liaoning Revitalization Talents Program","award":["LYC2403086"],"award-info":[{"award-number":["LYC2403086"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,8]]},"DOI":"10.1145\/3718958.3750514","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:54:11Z","timestamp":1756313651000},"page":"55-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ResCCL: Resource-Efficient Scheduling for Collective Communication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5722-4063","authenticated-orcid":false,"given":"Tongrui","family":"Liu","sequence":"first","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5010-1529","authenticated-orcid":false,"given":"Chenyang","family":"Hei","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9782-0053","authenticated-orcid":false,"given":"Fuliang","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1386-7394","authenticated-orcid":false,"given":"Chengxi","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5468-7366","authenticated-orcid":false,"given":"Jiamin","family":"Cao","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9602-8417","authenticated-orcid":false,"given":"Tianshu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4352-7497","authenticated-orcid":false,"given":"Ennan","family":"Zhai","sequence":"additional","affiliation":[{"name":"Alibaba Cloud, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8668-3524","authenticated-orcid":false,"given":"Xingwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Inc Advanced Micro Devices. 2024. ROCm Communication Collectives Library (RCCL). https:\/\/github.com\/ROCm\/rccl."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071117"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787480"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"e_1_3_2_1_7_1","unstructured":"Microsoft Corporation. 2022. Microsoft Collective Communication Libarary. https:\/\/github.com\/microsoft\/msccl."},{"key":"e_1_3_2_1_8_1","unstructured":"Microsoft Corporation. 2022. MSCCL Tools. https:\/\/github.com\/microsoft\/msccl-tools."},{"key":"e_1_3_2_1_9_1","unstructured":"NVIDIA Corporation. 2019. Megatron-LM. https:\/\/github.com\/NVIDIA\/Megatron-LM."},{"key":"e_1_3_2_1_10_1","unstructured":"NVIDIA Corporation. 2019. NCCL Tree Algorithm. https:\/\/developer.nvidia.com\/blog\/massively-scale-deep-learning-training-nccl-2-4."},{"key":"e_1_3_2_1_11_1","unstructured":"NVIDIA Corporation. 2020. CUDA Refresher: The CUDA Programming Model. https:\/\/developer.nvidia.com\/blog\/cuda-refresher-cuda-programming-model."},{"key":"e_1_3_2_1_12_1","unstructured":"NVIDIA Corporation. 2022. PTX ISA - Cache Operators. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html#cache-operators."},{"key":"e_1_3_2_1_13_1","unstructured":"NVIDIA Corporation. 2024. NVIDIA Collective Communications Library (NCCL). https:\/\/github.com\/NVIDIA\/nccl."},{"key":"e_1_3_2_1_14_1","unstructured":"NVIDIA Corporation. 2025. NVIDIA Inference Xfer Library. https:\/\/github.com\/ai-dynamo\/nixl."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575724"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/65.120719"},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. of USENIX NSDI. 1445\u20131462","author":"Sensi Daniele De","year":"2024","unstructured":"Daniele De Sensi, Tommaso Bonato, David Saam, and Torsten Hoefler. 2024. Swing: Short-cutting Rings for Higher Bandwidth Allreduce. In Proc. of USENIX NSDI. 1445\u20131462. https:\/\/www.usenix.org\/system\/files\/nsdi24-de-sensi.pdf."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472938"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486014"},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. of USENIX NSDI. 709\u2013729","author":"Hu Qinghao","year":"2024","unstructured":"Qinghao Hu, Zhisheng Ye, Zerui Wang, Guoteng Wang, Meng Zhang, Qiaoling Chen, Peng Sun, Dahua Lin, Xiaolin Wang, Yingwei Luo, et al. 2024. Characterization of large language model development in the datacenter. In Proc. of USENIX NSDI. 709\u2013729. https:\/\/www.usenix.org\/system\/files\/nsdi24-hu.pdf."},{"key":"e_1_3_2_1_21_1","unstructured":"Ltd Huawei Technologies Co. 2024. Huawei Collective Communication Library (HCCL). https:\/\/www.hiascend.com\/hccl."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. of USENIX NSDI. 87\u2013101","author":"Hwang Changho","year":"2023","unstructured":"Changho Hwang, KyoungSoo Park, Ran Shu, Xinyuan Qu, Peng Cheng, and Yongqiang Xiong. 2023. ARK: GPU-driven Code Execution for Distributed Deep Learning. In Proc. of USENIX NSDI. 87\u2013101. https:\/\/www.usenix.org\/system\/files\/nsdi23-hwang.pdf."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"e_1_3_2_1_24_1","volume-title":"Graph coloring problems","author":"Jensen Tommy R","unstructured":"Tommy R Jensen and Bjarne Toft. 2011. Graph coloring problems. John Wiley & Sons. Available: Graph coloring problems."},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. of USENIX NSDI. 745\u2013760","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 Proc. of USENIX NSDI. 745\u2013760. https:\/\/www.usenix.org\/system\/files\/nsdi24-jiang-ziheng.pdf."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651362"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098842"},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. of USENIX NSDI. 741\u2013761","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael Swift. 2021. ATP: In-network aggregation for multi-tenant learning. In Proc. of USENIX NSDI. 741\u2013761. https:\/\/www.usenix.org\/system\/files\/nsdi21-lao.pdf."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of USENIX NSDI. 809\u2013824","author":"Mahajan Kshiteej","year":"2023","unstructured":"Kshiteej Mahajan, Ching-Hsiang Chu, Srinivas Sridharan, and Aditya Akella. 2023. Better Together: Jointly Optimizing ML Collective Scheduling and Execution Planning using SYNDICATE. In Proc. of USENIX NSDI. 809\u2013824. https:\/\/www.usenix.org\/system\/files\/nsdi23-mahajan.pdf."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. of USENIX NSDI. 1403\u20131420","author":"Rajasekaran Sudarsanan","year":"2024","unstructured":"Sudarsanan Rajasekaran, Manya Ghobadi, and Aditya Akella. 2024. CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters. In Proc. of USENIX NSDI. 1403\u20131420. https:\/\/www.usenix.org\/system\/files\/nsdi24-rajasekaran.pdf."},{"key":"e_1_3_2_1_32_1","volume-title":"Proc. of USENIX NSDI. 1027\u20131040","author":"Romero Joshua","year":"2022","unstructured":"Joshua Romero, Junqi Yin, Nouamane Laanait, Bing Xie, M Todd Young, Sean Treichler, Vitalii Starchenko, Albina Borisevich, Alex Sergeev, and Michael Matheson. 2022. Accelerating collective communication in data parallel training across deep learning frameworks. In Proc. of USENIX NSDI. 1027\u20131040. https:\/\/www.usenix.org\/system\/files\/nsdi22-paper-romero.pdf."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. of USENIX 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 Proc. of USENIX NSDI. 593\u2013612. https:\/\/www.usenix.org\/system\/files\/nsdi23-shah.pdf."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672221"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656896"},{"key":"e_1_3_2_1_36_1","volume-title":"Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping. arXiv preprint arXiv:2409.15241","author":"Wang Guanhua","year":"2024","unstructured":"Guanhua Wang, Chengming Zhang, Zheyu Shen, Ang Li, and Olatunji Ruwase. 2024. Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping. arXiv preprint arXiv:2409.15241 (2024). https:\/\/arxiv.org\/pdf\/2409.15241."},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of USENIX NSDI. 1421\u20131443","author":"Wang Hao","year":"2024","unstructured":"Hao Wang, Han Tian, Jingrong Chen, Xinchen Wan, Jiacheng Xia, Gaoxiong Zeng, Wei Bai, Junchen Jiang, Yong Wang, and Kai Chen. 2024. Towards Domain-Specific Network Transport for Distributed DNN Training. In Proc. of USENIX NSDI. 1421\u20131443. https:\/\/www.usenix.org\/system\/files\/nsdi24-wang-hao.pdf."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544241"},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. of USENIX NSDI. 739\u2013767","author":"Wang Weiyang","year":"2023","unstructured":"Weiyang Wang, Moein Khazraee, Zhizhen Zhong, Manya Ghobadi, Zhihao Jia, Dheevatsa Mudigere, Ying Zhang, and Anthony Kewitsch. 2023. TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs. In Proc. of USENIX NSDI. 739\u2013767. https:\/\/www.usenix.org\/system\/files\/nsdi23-wang-weiyang.pdf."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00068"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672252"},{"key":"e_1_3_2_1_42_1","volume-title":"Proc. of USENIX NSDI. 199\u2013217","author":"Zhao Bohan","year":"2023","unstructured":"Bohan Zhao, Wenfei Wu, and Wei Xu. 2023. NetRPC: Enabling In-Network computation in remote procedure calls. In Proc. of USENIX NSDI. 199\u2013217. https:\/\/www.usenix.org\/system\/files\/nsdi23-zhao-bohan.pdf."},{"key":"e_1_3_2_1_43_1","volume-title":"Proc. of USENIX NSDI. 705\u2013737","author":"Zhao Liangyu","year":"2025","unstructured":"Liangyu Zhao, Siddharth Pal, Tapan Chugh, Weiyang Wang, Jason Fantl, Prithwish Basu, Joud Khoury, and Arvind Krishnamurthy. 2025. Efficient Direct-Connect Topologies for Collective Communications. In Proc. of USENIX NSDI. 705\u2013737. https:\/\/www.usenix.org\/system\/files\/nsdi25-zhao-liangyu.pdf."},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. of USENIX NSDI. 761\u2013774","author":"Zu Yazhou","year":"2024","unstructured":"Yazhou Zu, Alireza Ghaffarkhah, Hoang-Vu Dang, Brian Towles, Steven Hand, Safeen Huda, Adekunle Bello, Alexander Kolbasov, Arash Rezaei, Dayou Du, et al. 2024. Resiliency at Scale: Managing Google's TPUv4 Machine Learning Supercomputer. In Proc. of USENIX NSDI. 761\u2013774. https:\/\/www.usenix.org\/system\/files\/nsdi24-zu.pdf."}],"event":{"name":"SIGCOMM '25: ACM SIGCOMM 2025 Conference","location":"S\u00e3o Francisco Convent Coimbra Portugal","acronym":"SIGCOMM '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2025 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718958.3750514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:57:29Z","timestamp":1756313849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718958.3750514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":44,"alternative-id":["10.1145\/3718958.3750514","10.1145\/3718958"],"URL":"https:\/\/doi.org\/10.1145\/3718958.3750514","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}