{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:47:18Z","timestamp":1783784838852,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T00:00:00Z","timestamp":1636761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["955513"],"award-info":[{"award-number":["955513"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["185778"],"award-info":[{"award-number":["185778"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,14]]},"DOI":"10.1145\/3458817.3476181","type":"proceedings-article","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T05:10:34Z","timestamp":1634793034000},"page":"1-15","source":"Crossref","is-referenced-by-count":50,"title":["Clairvoyant prefetching for distributed machine learning I\/O"],"prefix":"10.1145","author":[{"given":"Nikoli","family":"Dryden","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"B\u00f6hringer","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tal","family":"Ben-Nun","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,11,13]]},"reference":[{"key":"e_1_3_2_2_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\/  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\/"},{"key":"e_1_3_2_2_2_1","volume-title":"17th IEEE International Conference on Machine Learning and Applications (ICMLA).","author":"Abodo Franklin","year":"2018"},{"key":"e_1_3_2_2_3_1","volume-title":"YouTube-8M: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675","author":"Abu-El-Haija Sami","year":"2016"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms (SODA).","author":"Agrawal Kunal","year":"2021"},{"key":"e_1_3_2_2_5_1","volume-title":"Integrated prefetching and caching in single and parallel disk systems. Information and Computation 198, 1","author":"Albers Susanne","year":"2005"},{"key":"e_1_3_2_2_6_1","article-title":"Minimizing stall time in single and parallel disk systems","volume":"47","author":"Albers Susanne","year":"2000","journal-title":"Journal of the ACM (JACM)"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Susanne Albers and Carsten Witt. 2001. Minimizing stall time in single and parallel disk systems using multicommodity network flows. In Approximation Randomization and Combinatorial Optimization: Algorithms and Techniques.  Susanne Albers and Carsten Witt. 2001. Minimizing stall time in single and parallel disk systems using multicommodity network flows. In Approximation Randomization and Combinatorial Optimization: Algorithms and Techniques.","DOI":"10.1007\/3-540-44666-4_6"},{"key":"e_1_3_2_2_9_1","unstructured":"Argonne Leadership Compute Facility. 2021. Aurora. https:\/\/www.alcf.anl.gov\/aurora  Argonne Leadership Compute Facility. 2021. Aurora. https:\/\/www.alcf.anl.gov\/aurora"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.","author":"Awan Ammar Ahmad","year":"2017"},{"key":"e_1_3_2_2_11_1","volume-title":"Ching-Hsiang Chu, Hari Subramoni, and Dhabaleswar K Panda.","author":"Awan Ammar Ahmad","year":"2019"},{"key":"e_1_3_2_2_12_1","unstructured":"Jens Axboe. 2021. fio - Felxible I\/O tester. https:\/\/fio.readthedocs.io\/en\/latest\/fio_doc.html  Jens Axboe. 2021. fio - Felxible I\/O tester. https:\/\/fio.readthedocs.io\/en\/latest\/fio_doc.html"},{"key":"e_1_3_2_2_13_1","volume-title":"A study of replacement algorithms for a virtual-storage computer. IBM Systems journal 5, 2","author":"B\u00e9l\u00e1dy L\u00e1szl\u00f3 A.","year":"1966"},{"key":"e_1_3_2_2_14_1","volume-title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. ACM Comput. Surv. 52, 4","author":"Ben-Nun Tal","year":"2019"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the twenty-fifth annual ACM-SIAM symposium on Discrete algorithms.","author":"Bender Michael A","year":"2014"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of the IEEE International Conference on Computer Communications (INFOCOM).","author":"Borst Sem","year":"2010"},{"key":"e_1_3_2_2_17_1","article-title":"Optimization methods for large-scale machine learning","volume":"60","author":"Bottou L\u00e9on","year":"2018","journal-title":"Siam Review"},{"key":"e_1_3_2_2_18_1","volume-title":"The OpenCV Library. Dr. Dobb's Journal of Software Tools","author":"Bradski G.","year":"2000"},{"key":"e_1_3_2_2_19_1","article-title":"A study of integrated prefetching and caching strategies","volume":"23","author":"Cao Pei","year":"1995","journal-title":"ACM SIGMETRICS Performance Evaluation Review"},{"key":"e_1_3_2_2_20_1","unstructured":"Pei Cao Edward W Felten and Kai Li. 1994. Application-Controlled File Caching Policies. In USENIX Summer.  Pei Cao Edward W Felten and Kai Li. 1994. Application-Controlled File Caching Policies. In USENIX Summer."},{"key":"e_1_3_2_2_21_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI).","author":"Chen Tianqi","year":"2018"},{"key":"e_1_3_2_2_22_1","volume-title":"cuDNN: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014"},{"key":"e_1_3_2_2_23_1","volume-title":"International Workshop on Parallel Data Storage & Data Intensive Scalable Computing Systems (PDSW-DISCS).","author":"Chien Steven WD","year":"2018"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 48th International Conference on Parallel Processing.","author":"Chowdhury Fahim","year":"2019"},{"key":"e_1_3_2_2_25_1","unstructured":"CSCS. 2020. Piz Daint. https:\/\/www.cscs.ch\/computers\/piz-daint\/  CSCS. 2020. Piz Daint. https:\/\/www.cscs.ch\/computers\/piz-daint\/"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Deng Jia","year":"2009"},{"key":"e_1_3_2_2_27_1","volume-title":"GPU-Aware Communication Library Optimized for Large-Scale Training of Deep Neural Networks on HPC Systems. In Workshop on Machine Learning in HPC Environments (MLHPC).","author":"Dryden Nikoli","year":"2018"},{"key":"e_1_3_2_2_28_1","volume-title":"2017 17th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID).","author":"Fu Huansong","year":"2017"},{"key":"e_1_3_2_2_29_1","volume-title":"XLA: Optimizing Compiler for Machine Learning. https:\/\/www.tensorflow.org\/xla","year":"2020"},{"key":"e_1_3_2_2_30_1","volume-title":"large minibatch SGD: Training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677","author":"Goyal Priya","year":"2017"},{"key":"e_1_3_2_2_31_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Gu Juncheng","year":"2017"},{"key":"e_1_3_2_2_32_1","volume-title":"Why random reshuffling beats stochastic gradient descent. Mathematical Programming","author":"G\u00fcrb\u00fczbalaban Mert","year":"2019"},{"key":"e_1_3_2_2_33_1","unstructured":"Avinatan Hassidim. 2010. Cache Replacement Policies for Multicore Processors. In Innovations in Computer Science.  Avinatan Hassidim. 2010. Cache Replacement Policies for Multicore Processors. In Innovations in Computer Science."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"He Kaiming","year":"2016"},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Hoefler Torsten","year":"2010"},{"key":"e_1_3_2_2_36_1","volume-title":"Workshop on Interfaces and Abstractions for Scientific Data Storage.","author":"Howison Mark","year":"2010"},{"key":"e_1_3_2_2_37_1","unstructured":"IOR team. 2021. HPC IO benchmark repository. https:\/\/github.com\/hpc\/ior  IOR team. 2021. HPC IO benchmark repository. https:\/\/github.com\/hpc\/ior"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of the 2016 International Conference on Supercomputing.","author":"Islam Nusrat Sharmin","year":"2016"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the Fourth Conference on Machine Learning and Systems (MLSys).","author":"Ivanov Andrei","year":"2021"},{"key":"e_1_3_2_2_40_1","volume-title":"IEEE International Conference on Cluster Computing (CLUSTER).","author":"Jacobs Sam Ade","year":"2019"},{"key":"e_1_3_2_2_41_1","volume-title":"Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093","author":"Jia Yangqing","year":"2014"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the International Conference on Dependable Systems and Networks.","author":"Jin Wei","year":"2002"},{"key":"e_1_3_2_2_43_1","volume-title":"2011 International Conference on Parallel Processing.","author":"Jose Jithin","year":"2011"},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA).","author":"Jouppi Norman P","year":"2017"},{"key":"e_1_3_2_2_45_1","volume-title":"Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures (SPAA).","author":"Kamali Shahin","year":"2020"},{"key":"e_1_3_2_2_46_1","volume-title":"Symposium on Algorithmic Principles of Computer Systems (APOCS).","author":"Kamali Shahin","year":"2021"},{"key":"e_1_3_2_2_47_1","volume-title":"International Parallel and Distributed Processing Symposium (IPDPS).","author":"Katti Anil Kumar","year":"2012"},{"key":"e_1_3_2_2_48_1","series-title":"SIAM Journal on computing 29, 4","volume-title":"Near-optimal parallel prefetching and caching","author":"Kimbrel Tracy","year":"2000"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 9th ACM Multimedia Systems Conference (MMSys).","author":"Koch Christian","year":"2018"},{"key":"e_1_3_2_2_50_1","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Kurth Thorsten","year":"2018"},{"key":"e_1_3_2_2_51_1","unstructured":"Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Tom Duerig etal 2018. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018).  Alina Kuznetsova Hassan Rom Neil Alldrin Jasper Uijlings Ivan Krasin Jordi Pont-Tuset Shahab Kamali Stefan Popov Matteo Malloci Tom Duerig et al. 2018. The open images dataset v4: Unified image classification object detection and visual relationship detection at scale. arXiv preprint arXiv:1811.00982 (2018)."},{"key":"e_1_3_2_2_52_1","volume-title":"Proc. IEEE 86","author":"LeCun Yann","year":"1998"},{"key":"e_1_3_2_2_53_1","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Li Jianwei","year":"2003"},{"key":"e_1_3_2_2_54_1","unstructured":"Livermore Computing. 2020. Lassen. https:\/\/hpc.llnl.gov\/hardware\/platforms\/lassen  Livermore Computing. 2020. Lassen. https:\/\/hpc.llnl.gov\/hardware\/platforms\/lassen"},{"key":"e_1_3_2_2_55_1","volume-title":"Proceedings of the 3rd Innovations in Theoretical Computer Science Conference.","author":"L\u00f3pez-Ortiz Alejandro","year":"2012"},{"key":"e_1_3_2_2_56_1","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Lu Youyou","year":"2017"},{"key":"e_1_3_2_2_57_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Mahajan Dhruv"},{"key":"e_1_3_2_2_58_1","volume-title":"2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).","author":"Markidis Stefano","year":"2018"},{"key":"e_1_3_2_2_59_1","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Mathuriya Amrita","year":"2018"},{"key":"e_1_3_2_2_60_1","unstructured":"John D McCalpin etal 1995. Memory bandwidth and machine balance in current high performance computers. IEEE computer society technical committee on computer architecture (TCCA) newsletter 2 19--25 (1995).  John D McCalpin et al. 1995. Memory bandwidth and machine balance in current high performance computers. IEEE computer society technical committee on computer architecture (TCCA) newsletter 2 19--25 (1995)."},{"key":"e_1_3_2_2_61_1","unstructured":"MLCommons. 2020. MLPerf HPC Training Rules. https:\/\/github.com\/mlperf-hpc\/training_policies\/blob\/hpc-0.5.0\/hpc_training_rules.adoc  MLCommons. 2020. MLPerf HPC Training Rules. https:\/\/github.com\/mlperf-hpc\/training_policies\/blob\/hpc-0.5.0\/hpc_training_rules.adoc"},{"key":"e_1_3_2_2_62_1","unstructured":"Timothy Prickett Morgan. 2021. Livermore Converges a Slew of New Ideas for Exascale Storage. https:\/\/www.nextplatform.com\/2021\/03\/09\/livermore-converges-a-slew-of-new-ideas-for-exascale-storage\/  Timothy Prickett Morgan. 2021. Livermore Converges a Slew of New Ideas for Exascale Storage. https:\/\/www.nextplatform.com\/2021\/03\/09\/livermore-converges-a-slew-of-new-ideas-for-exascale-storage\/"},{"key":"e_1_3_2_2_63_1","volume-title":"tf.data: A Machine Learning Data Processing Framework. arXiv preprint arXiv:2101.12127","author":"Murray Derek G","year":"2021"},{"key":"e_1_3_2_2_64_1","unstructured":"Nvidia. 2020. NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl  Nvidia. 2020. NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl"},{"key":"e_1_3_2_2_65_1","unstructured":"Nvidia. 2020. NVIDIA Data Loading Library. https:\/\/developer.nvidia.com\/DALI  Nvidia. 2020. NVIDIA Data Loading Library. https:\/\/developer.nvidia.com\/DALI"},{"key":"e_1_3_2_2_66_1","unstructured":"OpenAI. 2018. AI and Compute. https:\/\/openai.com\/blog\/ai-and-compute\/  OpenAI. 2018. AI and Compute. https:\/\/openai.com\/blog\/ai-and-compute\/"},{"key":"e_1_3_2_2_67_1","volume-title":"The case for strong scaling in deep learning: Training large 3D CNNs with hybrid parallelism","author":"Oyama Yosuke","year":"2020"},{"key":"e_1_3_2_2_68_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga etal 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS).  Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems (NeurIPS) ."},{"key":"e_1_3_2_2_69_1","volume-title":"Proceedings of the 2003 ACM\/IEEE conference on Supercomputing (SC).","author":"Petrini Fabrizio","year":"2003"},{"key":"e_1_3_2_2_70_1","article-title":"Scalable Deep Learning via I\/O Analysis and Optimization","volume":"6","author":"Pumma Sarunya","year":"2019","journal-title":"ACM Transactions on Parallel Computing (TOPC)"},{"key":"e_1_3_2_2_71_1","unstructured":"RIKEN Center for Computational Science. 2021. About Fugaku. https:\/\/www.r-ccs.riken.jp\/en\/fugaku\/about\/  RIKEN Center for Computational Science. 2021. About Fugaku. https:\/\/www.r-ccs.riken.jp\/en\/fugaku\/about\/"},{"key":"e_1_3_2_2_72_1","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky Olga","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"e_1_3_2_2_73_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018"},{"key":"e_1_3_2_2_74_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL).","author":"Strubell Emma","year":"2019"},{"key":"e_1_3_2_2_75_1","volume-title":"Crail: A High-Performance I\/O Architecture for Distributed Data Processing","author":"Stuedi Patrick","year":"2017"},{"key":"e_1_3_2_2_76_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV).","author":"Sun Chen","year":"2017"},{"key":"e_1_3_2_2_77_1","volume-title":"Seventh Symposium on the Frontiers of Massively Parallel Computation.","author":"Thakur Rajeev","year":"1999"},{"key":"e_1_3_2_2_78_1","volume-title":"Accelerating Data Loading in Deep Neural Network Training. In International Conference on High Performance Computing, Data, and Analytics (HiPC).","author":"Yang Chih-Chieh","year":"2019"},{"key":"e_1_3_2_2_79_1","volume-title":"International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS).","author":"Zhu Yue","year":"2018"}],"event":{"name":"SC '21: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis Missouri","acronym":"SC '21","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458817.3476181","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458817.3476181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:21Z","timestamp":1750191141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458817.3476181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,13]]},"references-count":78,"alternative-id":["10.1145\/3458817.3476181","10.1145\/3458817"],"URL":"https:\/\/doi.org\/10.1145\/3458817.3476181","relation":{},"subject":[],"published":{"date-parts":[[2021,11,13]]}}}