{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:49:54Z","timestamp":1783036194394,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"XRAC","award":["NCR-130002"],"award-info":[{"award-number":["NCR-130002"]}]},{"DOI":"10.13039\/100014718","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1931537,1450440,1664137,1818253"],"award-info":[{"award-number":["1931537,1450440,1664137,1818253"]}],"id":[{"id":"10.13039\/100014718","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,6,29]]},"DOI":"10.1145\/3392717.3392771","type":"proceedings-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T18:49:02Z","timestamp":1593456542000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["NV-group"],"prefix":"10.1145","author":[{"given":"Ching-Hsiang","family":"Chu","sequence":"first","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pouya","family":"Kousha","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ammar Ahmad","family":"Awan","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kawthar Shafie","family":"Khorassani","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hari","family":"Subramoni","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhabaleswar K. (D K)","family":"Panda","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,6,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"ROCm Communication Collectives Library. https:\/\/github.com\/ROCmSoftwarePlatform\/rccl Accessed","author":"AMD.","year":"2020"},{"key":"e_1_3_2_1_2_1","volume-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin. CoRR abs\/1512.02595","author":"Amodei Dario","year":"2015"},{"key":"e_1_3_2_1_3_1","volume-title":"The 19th Annual IEEE\/ACM International Symposium in Cluster, Cloud, and Grid Computing (CCGRID","author":"Awan Ammar Ahmad","year":"2019"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2949986"},{"key":"e_1_3_2_1_6_1","volume-title":"Sourav Chakraborty, Hari Subramoni, Robert S Oakes, and Dhabaleswar K. Panda.","author":"Bayatpour Mohammadreza","year":"2018"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"e_1_3_2_1_8_1","volume-title":"2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing. 180--186","author":"Broquedis F."},{"key":"e_1_3_2_1_9_1","volume-title":"International Workshop on OpenPOWER for HPC (IWOPH\u00e2\u0102Ź19)","author":"Pearson Z. Sura W.","year":"2018"},{"key":"e_1_3_2_1_10_1","volume-title":"BlueConnect: Novel Hierarchical All-Reduce on Multi-tired Network for Deep Learning. In 32nd Conference on Neural Information Processing Systems (NeurIPS","author":"Cho Minsik","year":"2018"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2016.111"},{"key":"e_1_3_2_1_13_1","volume-title":"Neena Imam, and Chris J. Newburn.","author":"Chu Ching-Hsiang","year":"2019"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Z. Dong Y. L. Fang X. Huang H. Yan S. Ha W. Xu Y. S. Chu S. I. Campbell and M. Lin. 2018. High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs. In 2018 New York Scientific Data Summit (NYSDS). 1--5.  Z. Dong Y. L. Fang X. Huang H. Yan S. Ha W. Xu Y. S. Chu S. I. Campbell and M. Lin. 2018. High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs. In 2018 New York Scientific Data Summit (NYSDS). 1--5.","DOI":"10.1109\/NYSDS.2018.8538964"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.37"},{"key":"e_1_3_2_1_16_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Go Younghwan","year":"2017"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339596"},{"key":"e_1_3_2_1_18_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He Kaiming","year":"2016"},{"key":"e_1_3_2_1_19_1","volume-title":"IBM Spectrum MPI: Accelerating high-performance application parallelization. https:\/\/www.ibm.com\/us-en\/marketplace\/spectrum-mpi. Accessed","author":"IBM.","year":"2020"},{"key":"e_1_3_2_1_20_1","volume-title":"Panda","author":"Khorassani Kawthar Shafie","year":"2018"},{"key":"e_1_3_2_1_21_1","volume-title":"2019 IEEE 26th International Conference on High Performance Computing, Data, and Analytics (HiPC). 93--102","author":"Kousha Pouya"},{"key":"e_1_3_2_1_22_1","unstructured":"Nouamane Laanait Joshua Romero Junqi Yin M. Todd Young Sean Treichler Vitalii Starchenko Albina Borisevich Alex Sergeev and Michael Matheson. 2019. Exascale Deep Learning for Scientific Inverse Problems. arXiv:cs.LG\/1909.11150  Nouamane Laanait Joshua Romero Junqi Yin M. Todd Young Sean Treichler Vitalii Starchenko Albina Borisevich Alex Sergeev and Michael Matheson. 2019. Exascale Deep Learning for Scientific Inverse Problems. arXiv:cs.LG\/1909.11150"},{"key":"e_1_3_2_1_23_1","volume-title":"https:\/\/hpc.llnl.gov\/hardware\/platforms\/lassen. Accessed","author":"Lawrence Livermore National Laboratory. 2018. Lassen | High Performance Computing.","year":"2020"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208054"},{"key":"e_1_3_2_1_25_1","volume-title":"Cooperative Groups: Flexible CUDA Thread Programming. https:\/\/devblogs.nvidia.com\/cooperative-groups\/ Accessed","author":"Harris Mark","year":"2017"},{"key":"e_1_3_2_1_26_1","volume-title":"http:\/\/www.mpi-forum.org\/ Accessed","author":"Interface Forum Message Passing","year":"2020"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573521"},{"key":"e_1_3_2_1_28_1","volume-title":"MVAPICH: MPI over InfiniBand, Omni-Path, Ethernet\/iWARP, and RoCE","author":"Computing Laboratory Network-Based","year":"2001"},{"key":"e_1_3_2_1_29_1","volume-title":"NVIDIA Management Library (NVML). https:\/\/developer.nvidia.com\/nvidia-management-library-nvml Accessed","author":"NVIDIA.","year":"2020"},{"key":"e_1_3_2_1_30_1","volume-title":"https:\/\/developer.nvidia.com\/gpudirect Accessed","author":"Direct NVIDIA.","year":"2020"},{"key":"e_1_3_2_1_31_1","volume-title":"https:\/\/github.com\/NVIDIA\/nccl. Accessed","author":"NVIDIA.","year":"2020"},{"key":"e_1_3_2_1_32_1","volume-title":"https:\/\/github.com\/NVIDIA\/nccl-tests Accessed","author":"Tests NVIDIA.","year":"2020"},{"key":"e_1_3_2_1_33_1","volume-title":"Summit: America's Newest and Smartest Supercomputer. https:\/\/www.olcf.ornl.gov\/summit\/. Accessed","author":"Oak Ridge National Laboratory.","year":"2018"},{"key":"e_1_3_2_1_34_1","volume-title":"Cloud and Grid Computing (CCGrid), 2014 14th IEEE\/ACM International Symposium on. 483--492","author":"Oden L."},{"key":"e_1_3_2_1_35_1","volume-title":"Open MPI: Open Source High Performance Computing. https:\/\/www.open-mpi.org\/. Accessed","author":"Open MPI.","year":"2020"},{"key":"e_1_3_2_1_36_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.17"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2009.09.001"},{"key":"e_1_3_2_1_41_1","volume-title":"Deep Learning in Neural Networks: An Overview. Neural networks 61","author":"Schmidhuber J\u00fcrgen","year":"2015"},{"key":"e_1_3_2_1_42_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. CoRR abs\/1802.05799","author":"Sergeev Alexander","year":"2018"},{"key":"e_1_3_2_1_43_1","volume-title":"Designing Efficient Small Message Transfer Mechanism for Inter-node MPI Communication on InfiniBand GPU Clusters. In 2014 21st International Conference on High Performance Computing (HiPC). 1--10","author":"Shi R."},{"key":"e_1_3_2_1_44_1","unstructured":"Erich Strohmaier Jack Dongarra Horst Simon and Martin Meuer. 1993. TOP 500 Supercomputer Sites. http:\/\/www.top500.org. Accessed: May 1 2020.  Erich Strohmaier Jack Dongarra Horst Simon and Martin Meuer. 1993. TOP 500 Supercomputer Sites. http:\/\/www.top500.org. Accessed: May 1 2020."},{"key":"e_1_3_2_1_45_1","volume-title":"Massively Scale Your Deep Learning Training with NCCL 2.4. https:\/\/devblogs.nvidia.com\/massively-scale-deep-learning-training-nccl-2-4\/. Accessed","author":"Jeaugey Sylvain","year":"2020"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CANDARW.2018.00048"},{"key":"e_1_3_2_1_48_1","volume-title":"https:\/\/www.hpcwire.com\/2017\/02\/17\/tsubame3-0-points-future-hpe-pascal-nvlink-opa-server\/ Accessed","author":"Trader Tiffany","year":"2020"},{"key":"e_1_3_2_1_49_1","volume-title":"Exhaustive Study of Hierarchical AllReduce Patterns for Large Messages Between GPUs. In 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 430--439","author":"Ueno Y."},{"key":"e_1_3_2_1_50_1","volume-title":"Blink: A fast NV Link-based collective communication library.","author":"Wangt Guanhua","year":"2018"},{"key":"e_1_3_2_1_51_1","volume-title":"A Survey of Methods for Collective Communication Optimization and Tuning. CoRR abs\/1611.06334","author":"Wickramasinghe Udayanga","year":"2016"},{"key":"e_1_3_2_1_52_1","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"Zhu Hao"}],"event":{"name":"ICS '20: 2020 International Conference on Supercomputing","location":"Barcelona Spain","acronym":"ICS '20","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 34th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392771","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3392717.3392771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:15Z","timestamp":1750200075000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3392717.3392771"}},"subtitle":["link-efficient reduction for distributed deep learning on modern dense GPU systems"],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":52,"alternative-id":["10.1145\/3392717.3392771","10.1145\/3392717"],"URL":"https:\/\/doi.org\/10.1145\/3392717.3392771","relation":{},"subject":[],"published":{"date-parts":[[2020,6,29]]},"assertion":[{"value":"2020-06-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}