{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:46:24Z","timestamp":1773153984856,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,20]]},"DOI":"10.1145\/3698038.3698515","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:32:43Z","timestamp":1731565963000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Hops: Fine-grained heterogeneous sensing, efficient and fair Deep Learning cluster scheduling system"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2892-4115","authenticated-orcid":false,"given":"Qinghe","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4181-8485","authenticated-orcid":false,"given":"Futian","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9466-2256","authenticated-orcid":false,"given":"Xinwei","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National, Science Center, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33 (2020), 12449--12460."},{"key":"e_1_3_2_1_2_1","volume-title":"Zurich","author":"Bossard Lukas","year":"2014","unstructured":"Lukas Bossard, Matthieu Guillaumin, and Luc Van Gool. 2014. Food-101-mining discriminative components with random forests. In Computer Vision-ECCV 2014:13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13. Springer, Springer, Zurich, Switzerland, 446--461."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2015.7143328"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2019.123208"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.2009.11920908"},{"key":"e_1_3_2_1_10_1","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2017. Accurate large minibatch sgd: Training imagenet in 1 hour."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026884"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation","author":"Grandl Robert","year":"2016","unstructured":"Robert Grandl, Srikanth Kandula, Sriram Rao, Aditya Akella, and Janardhan Kulkarni. 2016. Graphene: packing and dependency-aware scheduling for data-parallel clusters. In Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (Savannah, GA, USA) (OSDI'16). USENIX Association, USA, 81--97."},{"key":"e_1_3_2_1_13_1","volume-title":"Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Gu Juncheng","year":"2019","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang G. Shin, Yibo Zhu, Myeongjae Jeon, Junjie Qian, Hongqiang Liu, and Chuanxiong Guo. 2019. Tiresias: A GPU Cluster Manager for Distributed Deep Learning. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). USENIX Association, Boston, MA, 485--500. https:\/\/www.usenix.org\/conference\/nsdi19\/presentation\/gu"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575705"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"e_1_3_2_1_18_1","unstructured":"Sylvain Jeaugey. 2019. Massively Scale Your Deep Learning Training with NCCL 2.4. NVIDIA Developer Blog. https:\/\/developer.nvidia.com\/blog\/massively-scale-deep-learning-training-nccl-2-4"},{"key":"e_1_3_2_1_19_1","unstructured":"Myeongjae Jeon Shivaram Venkataraman Amar Phanishayee Junjie Qian Wencong Xiao and Fan Yang. 2018. Multi-tenant GPU Clusters for Deep Learning Workloads: Analysis and Implications (TR). Technical Report MSR-TR-2018-13. Microsoft."},{"key":"e_1_3_2_1_20_1","unstructured":"Xianyan Jia Shutao Song Wei He Yangzihao Wang Haidong Rong Feihu Zhou Liqiang Xie Zhenyu Guo Yuanzhou Yang Liwei Yu et al. 2018. Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes."},{"key":"e_1_3_2_1_21_1","first-page":"75","article-title":"Research and Design of 2D-Mesh Network-on-Chip Based on Multi-core System","volume":"32","author":"Shi Kong","year":"2015","unstructured":"De-chun Kong and Hui-bin Shi. 2015. Research and Design of 2D-Mesh Network-on-Chip Based on Multi-core System. Microelectronics & Computer 32, 4 (2015), 75--78.","journal-title":"Microelectronics & Computer"},{"key":"e_1_3_2_1_22_1","unstructured":"Alex Krizhevsky. 2012. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto. https:\/\/www.cs.toronto.edu\/~kriz\/learning-features- 2009-TR.pdf"},{"key":"e_1_3_2_1_23_1","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks."},{"key":"e_1_3_2_1_24_1","volume-title":"Paulson","author":"Li Wenda","year":"2021","unstructured":"Wenda Li, Lei Yu, Yuhuai Wu, and Lawrence C. Paulson. 2021. IsarStep: a Benchmark for High-level Mathematical Reasoning. arXiv:2006.09265 [cs.LO]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_27_1","volume-title":"Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and Efficient GPU Cluster Scheduling. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). USENIX Association, Santa Clara, CA, 289--304. https:\/\/www.usenix.org\/conference\/nsdi20\/presentation\/mahajan"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"e_1_3_2_1_29_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arXiv:1609.07843 [cs.CL]"},{"key":"e_1_3_2_1_30_1","unstructured":"Hiroaki Mikami Hisahiro Suganuma Yoshiki Tanaka Yuichi Kageyama et al. 2018. Imagenet\/resnet-50 training in 224 seconds. 770--778 pages."},{"key":"e_1_3_2_1_31_1","unstructured":"Volodymyr Mnih Koray Kavukcuoglu David Silver Alex Graves Ioannis Antonoglou Daan Wierstra and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488793"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning","author":"Ngiam Jiquan","unstructured":"Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee, and Andrew Y. Ng. 2011. Multimodal deep learning. In Proceedings of the 28th International Conference on International Conference on Machine Learning (Bellevue, Washington, USA) (ICML'11). Omnipress, Madison, WI, USA, 689--696."},{"key":"e_1_3_2_1_35_1","volume-title":"The foreground-background queue: a survey. Performance evaluation 65, 3--4","author":"Nuyens Misja","year":"2008","unstructured":"Misja Nuyens and Adam Wierman. 2008. The foreground-background queue: a survey. Performance evaluation 65, 3--4 (2008), 286--307."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_37_1","volume-title":"Operating System Concepts","author":"Peterson James L","unstructured":"James L Peterson and Abraham Silberschatz. 1985. Operating System Concepts. Addison-Wesley Longman Publishing Co., Inc., Reading, MA, USA."},{"key":"e_1_3_2_1_38_1","volume-title":"Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Qiao Aurick","unstructured":"Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, and Eric P. Xing. 2021. Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, Santa Clara, CA, USA, 1--18. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/qiao"},{"key":"e_1_3_2_1_39_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_42_1","volume-title":"2020 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, IEEE","author":"Rodoshi Rehenuma Tasnim","year":"2020","unstructured":"Rehenuma Tasnim Rodoshi, Taewoon Kim, and Wooyeol Choi. 2020. Deep reinforcement learning based dynamic resource allocation in cloud radio access networks. In 2020 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, IEEE, Jeju Island, South Korea, 618--623."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_44_1","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter."},{"key":"e_1_3_2_1_45_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484--489."},{"key":"e_1_3_2_1_46_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_48_1","volume-title":"Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation Gradient Descent. In 2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Weng Qizhen","year":"2023","unstructured":"Qizhen Weng, Lingyun Yang, Yinghao Yu, Wei Wang, Xiaochuan Tang, Guodong Yang, and Liping Zhang. 2023. Beware of Fragmentation: Scheduling GPU-Sharing Workloads with Fragmentation Gradient Descent. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). USENIX Association, Boston, MA, 995--1008. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/weng"},{"key":"e_1_3_2_1_49_1","volume-title":"Gandiva: Introspective Cluster Scheduling for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, and Lidong Zhou. 2018. Gandiva: Introspective Cluster Scheduling for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 595--610. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/xiao"},{"key":"e_1_3_2_1_50_1","volume-title":"Muxflow: Efficient and safe gpu sharing in large-scale production deep learning clusters.","author":"Zhao Yihao","year":"2023","unstructured":"Yihao Zhao, Xin Liu, Shufan Liu, Xiang Li, Yibo Zhu, Gang Huang, Xuanzhe Liu, and Xin Jin. 2023. Muxflow: Efficient and safe gpu sharing in large-scale production deep learning clusters."}],"event":{"name":"SoCC '24: ACM Symposium on Cloud Computing","location":"Redmond WA USA","acronym":"SoCC '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698515","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698038.3698515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:01:47Z","timestamp":1755889307000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698515"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":50,"alternative-id":["10.1145\/3698038.3698515","10.1145\/3698038"],"URL":"https:\/\/doi.org\/10.1145\/3698038.3698515","relation":{},"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}