{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T22:56:20Z","timestamp":1768431380749,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T00:00:00Z","timestamp":1652745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"US DOE","award":["DE-AC05-76RL01830"],"award-info":[{"award-number":["DE-AC05-76RL01830"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,17]]},"DOI":"10.1145\/3528416.3530242","type":"proceedings-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T02:16:59Z","timestamp":1651717019000},"page":"159-168","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Workload characterization of a time-series prediction system for spatio-temporal data"],"prefix":"10.1145","author":[{"given":"Milan","family":"Jain","sequence":"first","affiliation":[{"name":"Pacific Northwest National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sayan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai Pushpak","family":"Nandanoori","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dandelion Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. https:\/\/www.tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 92--101","author":"Agarwal Ashish","year":"2019","unstructured":"Ashish Agarwal. 2019. Static automatic batching in TensorFlow. In International Conference on Machine Learning. PMLR, 92--101."},{"key":"e_1_3_2_1_4_1","volume-title":"Optimizing Performance of Recurrent Neural Networks on GPUs. arXiv preprint arXiv:1604.01946 (apr","author":"Appleyard Jeremy","year":"2016","unstructured":"Jeremy Appleyard, Tomas Kocisky, and Phil Blunsom. 2016. Optimizing Performance of Recurrent Neural Networks on GPUs. arXiv preprint arXiv:1604.01946 (apr 2016). https:\/\/arxiv.org\/abs\/1604.01946v1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557153"},{"key":"e_1_3_2_1_6_1","unstructured":"Chainer Blog. 2017. Performance comparison of LSTM with and without cuDNN(v5) in Chainer. https:\/\/chainer.org\/general\/2017\/03\/15\/Performance-of-LSTM-Using-CuDNN-v5.html. Accessed: 2022-02-13."},{"key":"e_1_3_2_1_7_1","volume-title":"LSTM benchmarks for deep learning frameworks. arXiv preprint arXiv:1806.01818","author":"Braun Stefan","year":"2018","unstructured":"Stefan Braun. 2018. LSTM benchmarks for deep learning frameworks. arXiv preprint arXiv:1806.01818 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIGDATA.2015.7364089"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402898"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00011"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_2_1_12_1","first-page":"102","article-title":"Dawn-bench: An end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman Cody","year":"2017","unstructured":"Cody Coleman, Deepak Narayanan, Daniel Kang, Tian Zhao, Jian Zhang, Luigi Nardi, Peter Bailis, Kunle Olukotun, Chris R\u00e9, and Matei Zaharia. 2017. Dawn-bench: An end-to-end deep learning benchmark and competition. Training 100, 101 (2017), 102.","journal-title":"Training"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330896"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038228.3038239"},{"key":"e_1_3_2_1_17_1","volume-title":"A guide to deep learning in healthcare. Nature medicine 25, 1","author":"Esteva Andre","year":"2019","unstructured":"Andre Esteva, Alexandre Robicquet, Bharath Ramsundar, Volodymyr Kuleshov, Mark DePristo, Katherine Chou, Claire Cui, Greg Corrado, Sebastian Thrun, and Jeff Dean. 2019. A guide to deep learning in healthcare. Nature medicine 25, 1 (2019), 24--29."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00009"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/YAC.2016.7804912"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573475"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"e_1_3_2_1_22_1","volume-title":"DeepProf: Performance Analysis for Deep Learning Applications via Mining GPU Execution Patterns. arXiv preprint arXiv:1707.03750 (jul","author":"Gu Jiazhen","year":"2017","unstructured":"Jiazhen Gu, Huan Liu, Yangfan Zhou, and Xin Wang. 2017. DeepProf: Performance Analysis for Deep Learning Applications via Mining GPU Execution Patterns. arXiv preprint arXiv:1707.03750 (jul 2017). arXiv:1707.03750 https:\/\/arxiv.org\/abs\/1707.03750v1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2923982"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/NECO.1997.9.8.1735"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1073\/PNAS.81.10.3088"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.ESWA.2019.03.029"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC50251.2020.00024"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005496"},{"key":"e_1_3_2_1_30_1","unstructured":"B Jacob G Guennebaud et al. 2012. Eigen is a C++ template library for linear algebra: matrices vectors numerical solvers and related algorithms."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891042"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314401"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3090079"},{"key":"e_1_3_2_1_34_1","volume-title":"International Symposium on Benchmarking, Measuring and Optimization. Springer, 10--22","author":"Jiang Zihan","year":"2018","unstructured":"Zihan Jiang, Wanling Gao, Lei Wang, Xingwang Xiong, Yuchen Zhang, Xu Wen, Chunjie Luo, Hainan Ye, Xiaoyi Lu, Yunquan Zhang, et al. 2018. HPC AI500: a benchmark suite for HPC AI systems. In International Symposium on Benchmarking, Measuring and Optimization. Springer, 10--22."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2753802"},{"key":"e_1_3_2_1_36_1","unstructured":"Lambda Labs. 2021. A 100 vs V100 Deep Learning Benchmarks. https:\/\/lambdalabs.com\/blog\/nvidia-a100-vs-v100--benchmarks\/. Accessed: 2022-02-13."},{"key":"e_1_3_2_1_37_1","unstructured":"Rasmus Munk Larsen and Tatiana Shpeisman. 2019. TensorFlow Graph Optimizations."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Da Li Xinbo Chen Michela Becchi and Ziliang Zong. 2016. Evaluating the energy efficiency of deep convolutional neural networks on CPUs and GPUs. In 2016 IEEE international conferences on big data and cloud computing (BDCloud) social computing and networking (SocialCom) sustainable computing and communications (SustainCom)(BDCloud-SocialCom-SustainCom). IEEE 477--484.","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.76"},{"key":"e_1_3_2_1_40_1","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania et al. 2020. Pytorch distributed: Experiences on accelerating data parallel training. arXiv preprint arXiv:2006.15704 (2020)."},{"key":"e_1_3_2_1_41_1","article-title":"Time-series forecasting with deep learning: a survey","volume":"379","author":"Lim Bryan","year":"2021","unstructured":"Bryan Lim and Stefan Zohren. 2021. Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A 379, 2194 (2021), 20200209.","journal-title":"Philosophical Transactions of the Royal Society A"},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-node Bert-pretraining: Cost-efficient approach. arXiv preprint arXiv:2008.00177","author":"Lin Jiahuang","year":"2020","unstructured":"Jiahuang Lin, Xin Li, and Gennady Pekhimenko. 2020. Multi-node Bert-pretraining: Cost-efficient approach. arXiv preprint arXiv:2008.00177 (2020)."},{"key":"e_1_3_2_1_43_1","volume-title":"4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings (nov","author":"Lipton Zachary C.","year":"2015","unstructured":"Zachary C. Lipton, David C. Kale, Charles Elkan, and Randall Wetzel. 2015. Learning to Diagnose with LSTM Recurrent Neural Networks. 4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings (nov 2015). https:\/\/arxiv.org\/abs\/1511.03677v7"},{"key":"e_1_3_2_1_44_1","volume-title":"Taylor Robie, Tom St. John, Tsuguchika Tabaru, Carole-Jean Wu, Lingjie Xu, Masafumi Yamazaki, Cliff Young, and Matei Zaharia.","author":"Mattson Peter","year":"2019","unstructured":"Peter Mattson, Christine Cheng, Cody Coleman, Greg Diamos, Paulius Micikevicius, David Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen, Debojyoti Dutta, Udit Gupta, Kim Hazelwood, Andrew Hock, Xinyuan Huang, Atsushi Ike, Bill Jia, Daniel Kang, David Kanter, Naveen Kumar, Jeffery Liao, Guokai Ma, Deepak Narayanan, Tayo Oguntebi, Gennady Pekhimenko, Lillian Pentecost, Vijay Janapa Reddi, Taylor Robie, Tom St. John, Tsuguchika Tabaru, Carole-Jean Wu, Lingjie Xu, Masafumi Yamazaki, Cliff Young, and Matei Zaharia. 2019. MLPerf Training Benchmark. arXiv:1910.01500 [cs.LG]"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.EARSCIREV.2018.12.005"},{"key":"e_1_3_2_1_46_1","unstructured":"Sai Pushpak Nandanoori Soumya Kundu Seemita Pal Sutanay Choudhury and Khushbu Agarwal. 2021. Nominal and adversarial synthetic PMU data for standard IEEE test systems. https:\/\/data.pnl.gov\/publication\/grid_prediction. Accessed: 2021-07-01."},{"key":"e_1_3_2_1_47_1","unstructured":"NVIDIA. 2022. NVIDIA Deep Learning Examples for Tensor Cores. https:\/\/github.com\/NVIDIA\/DeepLearningExamples. Accessed: 2022-02-13."},{"key":"e_1_3_2_1_48_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch."},{"key":"e_1_3_2_1_49_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 8024--8035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_2_1_50_1","volume-title":"Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou.","author":"Reddi Vijay Janapa","year":"2019","unstructured":"Vijay Janapa Reddi, Christine Cheng, David Kanter, Peter Mattson, Guenther Schmuelling, Carole-Jean Wu, Brian Anderson, Maximilien Breughe, Mark Charlebois, William Chou, Ramesh Chukka, Cody Coleman, Sam Davis, Pan Deng, Greg Diamos, Jared Duke, Dave Fick, J. Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B. Jablin, Jeff Jiao, Tom St. John, Pankaj Kanwar, David Lee, Jeffery Liao, Anton Lokhmotov, Francisco Massa, Peng Meng, Paulius Micikevicius, Colin Osborne, Gennady Pekhimenko, Arun Tejusve Raghunath Rajan, Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou. 2019. MLPerf Inference Benchmark. arXiv:1911.02549 [cs.LG]"},{"key":"e_1_3_2_1_51_1","unstructured":"Baidu Research. 2017. DeepBench. https:\/\/github.com\/baidu-research\/DeepBench. Accessed: 2021-08-02."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision 115 3 (2015) 211--252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_53_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_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.ASOC.2020.106181"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-018-1805-8"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2014.6983043"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUCOM.2019.05.023"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9042047"},{"key":"e_1_3_2_1_60_1","volume-title":"arXiv preprint arXiv:1907.10701 (jul","author":"Wang Yu","year":"2019","unstructured":"Yu Wang, Gu-Yeon Wei, David Brooks, and John A Paulson. 2019. Benchmarking TPU, GPU, and CPU Platforms for Deep Learning. arXiv preprint arXiv:1907.10701 (jul 2019). https:\/\/arxiv.org\/abs\/1907.10701v4"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337905"},{"key":"e_1_3_2_1_62_1","volume-title":"Tbd: Benchmarking and analyzing deep neural network training. arXiv preprint arXiv:1803.06905","author":"Zhu Hongyu","year":"2018","unstructured":"Hongyu Zhu, Mohamed Akrout, Bojian Zheng, Andrew Pelegris, Amar Phanishayee, Bianca Schroeder, and Gennady Pekhimenko. 2018. Tbd: Benchmarking and analyzing deep neural network training. arXiv preprint arXiv:1803.06905 (2018)."}],"event":{"name":"CF '22: 19th ACM International Conference on Computing Frontiers","location":"Turin Italy","acronym":"CF '22","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 19th ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530242","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3528416.3530242","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528416.3530242","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3528416.3530242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:42Z","timestamp":1750186962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3528416.3530242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,17]]},"references-count":61,"alternative-id":["10.1145\/3528416.3530242","10.1145\/3528416"],"URL":"https:\/\/doi.org\/10.1145\/3528416.3530242","relation":{},"subject":[],"published":{"date-parts":[[2022,5,17]]},"assertion":[{"value":"2022-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}