{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T23:11:17Z","timestamp":1784675477546,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2214272"],"award-info":[{"award-number":["CNS-2214272"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1815525"],"award-info":[{"award-number":["CNS-1815525"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1145\/3552326.3567505","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:33:02Z","timestamp":1683307982000},"page":"867-882","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1614-0601","authenticated-orcid":false,"given":"Zhuang","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Science Department, Rice University, Houston, Texas, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-5335","authenticated-orcid":false,"given":"Haibin","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Newark, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9113-2660","authenticated-orcid":false,"given":"Yibo","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Bellevue, Washington, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-0767","authenticated-orcid":false,"given":"T. S. Eugene","family":"Ng","sequence":"additional","affiliation":[{"name":"Rice University, Houston, Texas, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. NVIDIA NCCL. https:\/\/developer.nvidia.com\/NCCL."},{"key":"e_1_3_2_1_2_1","volume-title":"MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","unstructured":"2022. MLaaS in the Wild: Workload Analysis and Scheduling in Large-Scale Heterogeneous GPU Clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). USENIX Association, Renton, WA. https:\/\/www.usenix.org\/conference\/nsdi22\/presentation\/weng"},{"key":"e_1_3_2_1_3_1","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI). 265--283","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. Tensorflow: A system for large-scale machine learning. In USENIX Symposium on Operating Systems Design and Implementation (OSDI). 265--283."},{"key":"e_1_3_2_1_4_1","volume-title":"On the Utility of Gradient Compression in Distributed Training Systems. arXiv preprint arXiv:2103.00543","author":"Agarwal Saurabh","year":"2021","unstructured":"Saurabh Agarwal, Hongyi Wang, Shivaram Venkataraman, and Dimitris Papailiopoulos. 2021. On the Utility of Gradient Compression in Distributed Training Systems. arXiv preprint arXiv:2103.00543 (2021)."},{"key":"e_1_3_2_1_5_1","unstructured":"Alham Fikri Aji and Kenneth Heafield. 2017. Sparse communication for distributed gradient descent."},{"key":"e_1_3_2_1_6_1","volume-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems. 1709--1720.","author":"Alistarh Dan","year":"2017","unstructured":"Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, and Milan Vojnovic. 2017. QSGD: Communication-efficient SGD via gradient quantization and encoding. In Advances in Neural Information Processing Systems. 1709--1720."},{"key":"e_1_3_2_1_7_1","unstructured":"Amazon. 2021. Gradient Compression in MXNet. https:\/\/mxnet.apache.org\/versions\/1.9.0\/api\/faq\/gradient_compression.html."},{"key":"e_1_3_2_1_8_1","unstructured":"Amazon. 2022. Amazon EC2 pricing on demand. https:\/\/aws.amazon.com\/ec2\/pricing\/on-demand\/."},{"key":"e_1_3_2_1_9_1","volume-title":"Gradient Compression Supercharged High-Performance Data Parallel DNN Training. To appear in the proceedings of the 28th ACM Symposium on Operating Systems Principles","author":"Bai Youhui","year":"2021","unstructured":"Youhui Bai, Cheng Li, Quan Zhou, Jun Yi, Ping Gong, Feng Yan, Ruichuan Chen, and Yinlong Xu. 2021. Gradient Compression Supercharged High-Performance Data Parallel DNN Training. To appear in the proceedings of the 28th ACM Symposium on Operating Systems Principles (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"14th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 20). 499--514.","author":"Bai Zhihao","unstructured":"Zhihao Bai, Zhen Zhang, Yibo Zhu, and Xin Jin. 2020. PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In 14th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 20). 499--514."},{"key":"e_1_3_2_1_11_1","volume-title":"signSGD: Compressed optimisation for non-convex problems. arXiv preprint arXiv:1802.04434","author":"Bernstein Jeremy","year":"2018","unstructured":"Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, and Anima Anandkumar. 2018. signSGD: Compressed optimisation for non-convex problems. arXiv preprint arXiv:1802.04434 (2018)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"e_1_3_2_1_13_1","volume-title":"Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981","author":"Chen Jianmin","year":"2016","unstructured":"Jianmin Chen, Xinghao Pan, Rajat Monga, Samy Bengio, and Rafal Jozefowicz. 2016. Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981 (2016)."},{"key":"e_1_3_2_1_14_1","volume-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274","author":"Chen Tianqi","year":"2015","unstructured":"Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274 (2015)."},{"key":"e_1_3_2_1_15_1","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan Leyuan Wang Yuwei Hu Luis Ceze et al. 2018. {TVM}: An automated end-to-end optimizing compiler for deep learning. In 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18). 578--594."},{"key":"e_1_3_2_1_16_1","volume-title":"cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_19_1","volume-title":"8-bit approximations for parallelism in deep learning. arXiv preprint arXiv:1511.04561","author":"Dettmers Tim","year":"2015","unstructured":"Tim Dettmers. 2015. 8-bit approximations for parallelism in deep learning. arXiv preprint arXiv:1511.04561 (2015)."},{"key":"e_1_3_2_1_20_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_22_1","unstructured":"Google. 2021. Google Cloud. https:\/\/cloud.google.com\/compute\/docs\/gpus."},{"key":"e_1_3_2_1_23_1","volume-title":"Sangeetha Abdu Jyothi, and Roy H Campbell","author":"Hashemi Sayed Hadi","year":"2018","unstructured":"Sayed Hadi Hashemi, Sangeetha Abdu Jyothi, and Roy H Campbell. 2018. Tictac: Accelerating distributed deep learning with communication scheduling. arXiv preprint arXiv:1803.03288 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","volume-title":"Priority-based parameter propagation for distributed DNN training. arXiv preprint arXiv:1905.03960","author":"Jayarajan Anand","year":"2019","unstructured":"Anand Jayarajan, Jinliang Wei, Garth Gibson, Alexandra Fedorova, and Gennady Pekhimenko. 2019. Priority-based parameter propagation for distributed DNN training. arXiv preprint arXiv:1905.03960 (2019)."},{"key":"e_1_3_2_1_26_1","unstructured":"Peng Jiang and Gagan Agrawal. 2018. A linear speedup analysis of distributed deep learning with sparse and quantized communication. In Advances in Neural Information Processing Systems. 2525--2536."},{"key":"e_1_3_2_1_27_1","volume-title":"14th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 20). 463--479.","author":"Jiang Yimin","unstructured":"Yimin Jiang, Yibo Zhu, Chang Lan, Bairen Yi, Yong Cui, and Chuanxiong Guo. 2020. A Unified Architecture for Accelerating Distributed {DNN} Training in Heterogeneous GPU\/CPU Clusters. In 14th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 20). 463--479."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_29_1","volume-title":"Error feedback fixes signsgd and other gradient compression schemes. arXiv preprint arXiv:1901.09847","author":"Karimireddy Sai Praneeth","year":"2019","unstructured":"Sai Praneeth Karimireddy, Quentin Rebjock, Sebastian U Stich, and Martin Jaggi. 2019. Error feedback fixes signsgd and other gradient compression schemes. arXiv preprint arXiv:1901.09847 (2019)."},{"key":"e_1_3_2_1_30_1","volume-title":"U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. arXiv preprint arXiv:1907.10830","author":"Kim Junho","year":"2019","unstructured":"Junho Kim, Minjae Kim, Hyeonwoo Kang, and Kwanghee Lee. 2019. U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. arXiv preprint arXiv:1907.10830 (2019)."},{"key":"e_1_3_2_1_31_1","unstructured":"Ryan Kiros Yukun Zhu Russ R Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-thought vectors. In Advances in neural information processing systems. 3294--3302."},{"key":"e_1_3_2_1_32_1","volume-title":"CROSSBOW: scaling deep learning with small batch sizes on multi-gpu servers. arXiv preprint arXiv:1901.02244","author":"Koliousis Alexandros","year":"2019","unstructured":"Alexandros Koliousis, Pijika Watcharapichat, Matthias Weidlich, Luo Mai, Paolo Costa, and Peter Pietzuch. 2019. CROSSBOW: scaling deep learning with small batch sizes on multi-gpu servers. arXiv preprint arXiv:1901.02244 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"ATP: In-network Aggregation for Multi-tenant Learning.. In NSDI. 741--761.","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael M Swift. 2021. ATP: In-network Aggregation for Multi-tenant Learning.. In NSDI. 741--761."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"e_1_3_2_1_35_1","volume-title":"Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704","author":"Li Shen","year":"2020","unstructured":"Shen Li, Yanli Zhao, Rohan Varma, Omkar Salpekar, Pieter Noordhuis, Teng Li, Adam Paszke, Jeff Smith, Brian Vaughan, Pritam Damania, and Soumith Chintala. 2020. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704 (2020)."},{"key":"e_1_3_2_1_36_1","volume-title":"The International Conference on Learning Representations (ICLR)","author":"Lin Yujun","year":"2017","unstructured":"Yujun Lin, Song Han, Huizi Mao, Yu Wang, and William J Dally. 2017. Deep gradient compression: Reducing the communication bandwidth for distributed training. The International Conference on Learning Representations (ICLR) (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"e_1_3_2_1_38_1","volume-title":"Proc. of MLSys","author":"Luo Liang","year":"2020","unstructured":"Liang Luo, Peter West, Arvind Krishnamurthy, Luis Ceze, and Jacob Nelson. 2020. PLink: Discovering and Exploiting Datacenter Network Locality for Efficient Cloud-based Distributed Training. Proc. of MLSys (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"e_1_3_2_1_40_1","unstructured":"Mellanox. 2022. Mellanox Corporate Update. https:\/\/www.mellanox.com\/related-docs\/company\/MLNX_Corporate_Deck.pdf."},{"key":"e_1_3_2_1_41_1","volume-title":"Nitish Shirish Keskar, and Richard Socher","author":"Merity Stephen","year":"2017","unstructured":"Stephen Merity, Nitish Shirish Keskar, and Richard Socher. 2017. Regularizing and optimizing LSTM language models. arXiv preprint arXiv:1708.02182 (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"Nitish Shirish Keskar, and Richard Socher","author":"Merity Stephen","year":"2017","unstructured":"Stephen Merity, Nitish Shirish Keskar, and Richard Socher. 2017. Regularizing and optimizing LSTM language models. arXiv preprint arXiv:1708.02182 (2017)."},{"key":"e_1_3_2_1_43_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)."},{"key":"e_1_3_2_1_44_1","unstructured":"Meta. 2022. Gradient Compression in Pytorch. https:\/\/pytorch.org\/docs\/stable\/ddp_comm_hooks.html."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_46_1","unstructured":"NVIDIA. 2021. A Timeline of Innovation for NVIDIA. https:\/\/www.nvidia.com\/en-us\/about-nvidia\/corporate-timeline\/."},{"key":"e_1_3_2_1_47_1","unstructured":"NVIDIA. 2021. BERT training time. https:\/\/github.com\/NVIDIA\/DeepLearningExamples\/blob\/master\/PyTorch\/LanguageModeling\/BERT\/."},{"key":"e_1_3_2_1_48_1","unstructured":"NVIDIA. 2021. Broadcast in NCCL. https:\/\/github.com\/NVIDIA\/nccl-tests\/blob\/master\/doc\/PERFORMANCE.md."},{"key":"e_1_3_2_1_49_1","unstructured":"OpenAI. 2021. AI and Compute. https:\/\/openai.com\/blog\/ai-andcompute\/."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_51_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_52_1","volume-title":"Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv:1806.03822","author":"Rajpurkar Pranav","year":"2018","unstructured":"Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don't know: Unanswerable questions for SQuAD. arXiv preprint arXiv:1806.03822 (2018)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480853"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356222"},{"key":"e_1_3_2_1_55_1","volume-title":"Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv:1805.00907","author":"Rotem Nadav","year":"2018","unstructured":"Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Garret Catron, Summer Deng, Roman Dzhabarov, Nick Gibson, James Hegeman, Meghan Lele, Roman Levenstein, et al. 2018. Glow: Graph lowering compiler techniques for neural networks. arXiv preprint arXiv:1805.00907 (2018)."},{"key":"e_1_3_2_1_56_1","unstructured":"Arnaud ROUGETET. 2022. selfie2anime in Kaggle. https:\/\/www.kaggle.com\/arnaud58\/selfie2anime."},{"key":"e_1_3_2_1_57_1","volume-title":"Dan RK Ports, and Peter Richt\u00e1rik","author":"Sapio Amedeo","year":"2019","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan RK Ports, and Peter Richt\u00e1rik. 2019. Scaling distributed machine learning with in-network aggregation. arXiv preprint arXiv:1903.06701 (2019)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"e_1_3_2_1_59_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799 (2018)."},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of Machine Learning and Systems 3","author":"Shi Shaohuai","year":"2021","unstructured":"Shaohuai Shi, Xianhao Zhou, Shutao Song, Xingyao Wang, Zilin Zhu, Xue Huang, Xinan Jiang, Feihu Zhou, Zhenyu Guo, Liqiang Xie, et al. 2021. Towards scalable distributed training of deep learning on public cloud clusters. Proceedings of Machine Learning and Systems 3 (2021)."},{"key":"e_1_3_2_1_61_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_62_1","unstructured":"Sebastian U Stich Jean-Baptiste Cordonnier and Martin Jaggi. 2018. Sparsified SGD with memory. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_63_1","volume-title":"Optimizing network performance for distributed dnn training on gpu clusters: Imagenet\/alexnet training in 1.5 minutes. arXiv preprint arXiv:1902.06855","author":"Sun Peng","year":"2019","unstructured":"Peng Sun, Wansen Feng, Ruobing Han, Shengen Yan, and Yonggang Wen. 2019. Optimizing network performance for distributed dnn training on gpu clusters: Imagenet\/alexnet training in 1.5 minutes. arXiv preprint arXiv:1902.06855 (2019)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_66_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_67_1","first-page":"513","article-title":"DLAU: A scalable deep learning accelerator unit on FPGA","volume":"36","author":"Wang Chao","year":"2016","unstructured":"Chao Wang, Lei Gong, Qi Yu, Xi Li, Yuan Xie, and Xuehai Zhou. 2016. DLAU: A scalable deep learning accelerator unit on FPGA. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 36, 3 (2016), 513--517.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_1_68_1","volume-title":"Blink: Fast and generic collectives for distributed ML. arXiv preprint arXiv:1910.04940","author":"Wang Guanhua","year":"2019","unstructured":"Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Jorgen Thelin, Nikhil Devanur, and Ion Stoica. 2019. Blink: Fast and generic collectives for distributed ML. arXiv preprint arXiv:1910.04940 (2019)."},{"key":"e_1_3_2_1_69_1","volume-title":"MergeComp: A Compression Scheduler for Scalable Communication-Efficient Distributed Training. arXiv preprint arXiv:2103.15195","author":"Wang Zhuang","year":"2021","unstructured":"Zhuang Wang, Xinyu Wu, and TS Ng. 2021. MergeComp: A Compression Scheduler for Scalable Communication-Efficient Distributed Training. arXiv preprint arXiv:2103.15195 (2021)."},{"key":"e_1_3_2_1_70_1","unstructured":"Jianqiao Wangni Jialei Wang Ji Liu and Tong Zhang. 2018. Gradient sparsification for communication-efficient distributed optimization. In Advances in Neural Information Processing Systems. 1299--1309."},{"key":"e_1_3_2_1_71_1","volume-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in neural information processing systems. 1509--1519.","author":"Wen Wei","year":"2017","unstructured":"Wei Wen, Cong Xu, Feng Yan, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2017. Terngrad: Ternary gradients to reduce communication in distributed deep learning. In Advances in neural information processing systems. 1509--1519."},{"key":"e_1_3_2_1_72_1","volume-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization. arXiv preprint arXiv:1806.08054","author":"Wu Jiaxiang","year":"2018","unstructured":"Jiaxiang Wu, Weidong Huang, Junzhou Huang, and Tong Zhang. 2018. Error compensated quantized SGD and its applications to large-scale distributed optimization. arXiv preprint arXiv:1806.08054 (2018)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00060"},{"key":"e_1_3_2_1_74_1","volume-title":"2017 USENIX Annual Technical Conference (ATC). 181--193","author":"Zhang Hao","year":"2017","unstructured":"Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, and Eric P Xing. 2017. Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters. In 2017 USENIX Annual Technical Conference (ATC). 181--193."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3405671.3405810"},{"key":"e_1_3_2_1_76_1","volume-title":"Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, et al.","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, et al. 2020. Ansor: Generating high-performance tensor programs for deep learning. In 14th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 20). 863--879."},{"key":"e_1_3_2_1_77_1","unstructured":"Shuai Zheng Ziyue Huang and James Kwok. 2019. Communication-efficient distributed blockwise momentum SGD with error-feedback. In Advances in Neural Information Processing Systems. 11450--11460."},{"key":"e_1_3_2_1_78_1","volume-title":"Compressed Communication for Distributed Training: Adaptive Methods and System. arXiv preprint arXiv:2105.07829","author":"Zhong Yuchen","year":"2021","unstructured":"Yuchen Zhong, Cong Xie, Shuai Zheng, and Haibin Lin. 2021. Compressed Communication for Distributed Training: Adaptive Methods and System. arXiv preprint arXiv:2105.07829 (2021)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2956779"}],"event":{"name":"EuroSys '23: Eighteenth European Conference on Computer Systems","location":"Rome Italy","acronym":"EuroSys '23","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Eighteenth European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3567505","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552326.3567505","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552326.3567505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:39Z","timestamp":1750178859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3567505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":79,"alternative-id":["10.1145\/3552326.3567505","10.1145\/3552326"],"URL":"https:\/\/doi.org\/10.1145\/3552326.3567505","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]},"assertion":[{"value":"2023-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}