{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:36Z","timestamp":1755993756048,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2119184, CNS-2027170"],"award-info":[{"award-number":["CCF-2119184, CNS-2027170"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1145\/3655038.3665947","type":"proceedings-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:19:48Z","timestamp":1719447588000},"page":"63-70","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Selective Preprocessing Offloading Framework for Reducing Data Traffic in DL Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0970-6558","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3673-2524","authenticated-orcid":false,"given":"Gus","family":"Waldspurger","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4468-3061","authenticated-orcid":false,"given":"Swaminathan","family":"Sundararaman","sequence":"additional","affiliation":[{"name":"IBM Research, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Jian Sun. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016."},{"key":"e_1_3_2_1_2_1","volume-title":"Geoffrey E Hinton. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 26th Conference on Neural Information Processing Systems (NIPS)","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the 26th Conference on Neural Information Processing Systems (NIPS), 2012."},{"key":"e_1_3_2_1_3_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. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_5_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. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_6_1","unstructured":"Google Cloud Deep Learning VM Images. https:\/\/cloud.google.com\/deep-learning-vm."},{"key":"e_1_3_2_1_7_1","unstructured":"Azure Machine Learning - ML as a Service. https:\/\/azure.microsoft.com\/en-us\/products\/machine-learning."},{"key":"e_1_3_2_1_8_1","unstructured":"Amazon SageMaker. https:\/\/aws.amazon.com\/sagemaker\/."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"e_1_3_2_1_10_1","volume-title":"Chuanxiong Guo. Optimus: An Efficient Dynamic Resource Scheduler for Deep Learning Clusters. In Proceedings of the 2018 EuroSys Conference (EuroSys)","author":"Peng Yanghua","year":"2018","unstructured":"Yanghua Peng, Yixin Bao, Yangrui Chen, Chuan Wu, and Chuanxiong Guo. Optimus: An Efficient Dynamic Resource Scheduler for Deep Learning Clusters. In Proceedings of the 2018 EuroSys Conference (EuroSys), 2018."},{"key":"e_1_3_2_1_11_1","volume-title":"Vijay Chidambaram. Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters. In Proceedings of the 16th Symposium on Operating Systems Design and Implementation (OSDI)","author":"Mohan Jayashree","year":"2022","unstructured":"Jayashree Mohan, Amar Phanishayee, Janardhan Kulkarni, and Vijay Chidambaram. Looking Beyond GPUs for DNN Scheduling on Multi-Tenant Clusters. In Proceedings of the 16th Symposium on Operating Systems Design and Implementation (OSDI), 2022."},{"key":"e_1_3_2_1_12_1","volume-title":"Yangqing Jia. AntMan: Dynamic Scaling on GPU Clusters for Deep Learning. In Proceedings of the 14th Symposium on Operating Systems Design and Implementation (OSDI)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. AntMan: Dynamic Scaling on GPU Clusters for Deep Learning. In Proceedings of the 14th Symposium on Operating Systems Design and Implementation (OSDI), 2020."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526150"},{"key":"e_1_3_2_1_14_1","volume-title":"Fan Yang and Lidong Zhou. Gandiva: Introspective Cluster Scheduling for Deep Learning. In Proceedings of the 13th Symposium on Operating Systems Design and Implementation (OSDI)","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. Gandiva: Introspective Cluster Scheduling for Deep Learning. In Proceedings of the 13th Symposium on Operating Systems Design and Implementation (OSDI), 2018."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387555"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01156"},{"key":"e_1_3_2_1_17_1","volume-title":"Vijay Chidambaram. Analyzing and Mitigating Data Stalls in DNN Training. In Proceedings of the 47th International Conference on Very Large Databases (VLDB)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, Ashish Raniwala, and Vijay Chidambaram. Analyzing and Mitigating Data Stalls in DNN Training. In Proceedings of the 47th International Conference on Very Large Databases (VLDB), 2021."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476181"},{"key":"e_1_3_2_1_19_1","volume-title":"Vijaya Kumar and Muthian Sivathanu. Quiver: An Informed Storage Cache for Deep Learning. In Proceedings of the 18th USENIX Symposium on File and Storage Technologies (FAST)","author":"Abhishek","year":"2020","unstructured":"Abhishek Vijaya Kumar and Muthian Sivathanu. Quiver: An Informed Storage Cache for Deep Learning. In Proceedings of the 18th USENIX Symposium on File and Storage Technologies (FAST), 2020."},{"key":"e_1_3_2_1_20_1","volume-title":"Lidong Zhou. SiloD: A Co-design of Caching and Scheduling for Deep Learning Clusters. In Proceedings of the 2023 EuroSys Conference (EuroSys)","author":"Zhao Hanyu","year":"2023","unstructured":"Hanyu Zhao, Zhenhua Han, Zhi Yang, Quanlu Zhang, Mingxia Li, Fan Yang, Qianxi Zhang, Binyang Li, Yuqing Yang, Lili Qiu, Lintao Zhang, and Lidong Zhou. SiloD: A Co-design of Caching and Scheduling for Deep Learning Clusters. In Proceedings of the 2023 EuroSys Conference (EuroSys), 2023."},{"key":"e_1_3_2_1_21_1","volume-title":"Qiong Luo. DIESEL: A Dataset-Based Distributed Storage and Caching System for Large-Scale Deep Learning Training. In 49st International Conference on Parallel Processing (ICPP)","author":"Wang Lipeng","year":"2020","unstructured":"Lipeng Wang, Songgao Ye, Baichen Yang, Youyou Lu, Hequan Zhang, Shengen Yan, and Qiong Luo. DIESEL: A Dataset-Based Distributed Storage and Caching System for Large-Scale Deep Learning Training. In 49st International Conference on Parallel Processing (ICPP), 2020."},{"key":"e_1_3_2_1_22_1","unstructured":"Open Images Dataset V7 and Extensions. https:\/\/storage.googleapis.com\/openimages\/web\/index.html."},{"key":"e_1_3_2_1_23_1","volume-title":"Robert Chansler. The Hadoop Distributed File System. In Proceedings of the 26th IEEE Symposium on Massive Storage Systems and Technologies (MSST)","author":"Shvachko Konstantin","year":"2010","unstructured":"Konstantin Shvachko, Hairong Kuang, Sanjay Radia, and Robert Chansler. The Hadoop Distributed File System. In Proceedings of the 26th IEEE Symposium on Massive Storage Systems and Technologies (MSST), 2010."},{"key":"e_1_3_2_1_24_1","unstructured":"GlusterFS. https:\/\/www.gluster.org."},{"key":"e_1_3_2_1_25_1","unstructured":"Azure Blob Storage. https:\/\/azure.microsoft.com\/en-us\/products\/storage\/blobs."},{"key":"e_1_3_2_1_26_1","unstructured":"Amazon S3. https:\/\/aws.amazon.com\/s3\/."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 47th International Conference on Very Large Databases (VLDB)","author":"Murray Derek G.","year":"2021","unstructured":"Derek G. Murray, Ji\u0159\u00ed \u0160im\u0161a, Ana Klimovic, and Ihor Indyk. tf.data: A Machine Learning Data Processing Framework. In Proceedings of the 47th International Conference on Very Large Databases (VLDB), 2021."},{"key":"e_1_3_2_1_28_1","volume-title":"Yang and Guojing Cong. Accelerating Data Loading in Deep Neural Network Training. In 2019 IEEE 26th International Conference on High Performance Computing, Data, and Analytics (HiPC)","author":"Chih-Chieh","year":"2019","unstructured":"Chih-Chieh Yang and Guojing Cong. Accelerating Data Loading in Deep Neural Network Training. In 2019 IEEE 26th International Conference on High Performance Computing, Data, and Analytics (HiPC), 2019."},{"key":"e_1_3_2_1_29_1","volume-title":"Hidden Trade-Offs in Deep Learning Preprocessing Pipelines. In Proceedings of the 2022 ACM SIGMOD International Conference on Management of Data (SIGMOD)","author":"Isenko Alexander","year":"2022","unstructured":"Alexander Isenko, Ruben Mayer, Jeffrey Jedele, and Hans-Arno Jacobsen. Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines. In Proceedings of the 2022 ACM SIGMOD International Conference on Management of Data (SIGMOD), 2022."},{"key":"e_1_3_2_1_30_1","volume-title":"Shivaram Venkataraman. The Case for Unifying Data Loading in Machine Learning Clusters. In The 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud)","author":"Kakaraparthy Aarati","year":"2019","unstructured":"Aarati Kakaraparthy, Abhay Venkatesh, Amar Phanishayee, and Shivaram Venkataraman. The Case for Unifying Data Loading in Machine Learning Clusters. In The 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud), 2019."},{"key":"e_1_3_2_1_31_1","volume-title":"Byung-Gon Chun. Refurbish Your Training Data: Reusing Partially Augmented Samples for Faster Deep Neural Network Training. In Proceedings of the 2021 USENIX Annual Technical Conference (ATC)","author":"Lee Gyewon","year":"2021","unstructured":"Gyewon Lee, Irene Lee, Hyeonmin Ha, Kyung-Geun Lee, Hwarim Hyun, Ahnjae Shin, and Byung-Gon Chun. Refurbish Your Training Data: Reusing Partially Augmented Samples for Faster Deep Neural Network Training. In Proceedings of the 2021 USENIX Annual Technical Conference (ATC), 2021."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624666"},{"key":"e_1_3_2_1_33_1","volume-title":"Woo-Yeon Lee. FastFlow: Accelerating Deep Learning Model Training with Smart Offloading of Input Data Pipeline. In Proceedings of the 49th International Conference on Very Large Databases (VLDB)","author":"Um Taegeon","year":"2023","unstructured":"Taegeon Um, Byungsoo Oh, Byeongchan Seo, Minhyeok Kweun, Goeun Kim, and Woo-Yeon Lee. FastFlow: Accelerating Deep Learning Model Training with Smart Offloading of Input Data Pipeline. In Proceedings of the 49th International Conference on Very Large Databases (VLDB), 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"Wei Lin. GoldMiner: Elastic Scaling of Training Data Pre-Processing Pipelines for Deep Learning. In Proceedings of the 2023 ACM SIGMOD International Conference on Management of Data (SIGMOD)","author":"Zhao Hanyu","year":"2023","unstructured":"Hanyu Zhao, Zhi Yang, Yu Cheng, Chao Tian, Shiru Ren, Wencong Xiao, Man Yuan, Langshi Chen, Kaibo Liu, Yang Zhang, Yong Li, and Wei Lin. GoldMiner: Elastic Scaling of Training Data Pre-Processing Pipelines for Deep Learning. In Proceedings of the 2023 ACM SIGMOD International Conference on Management of Data (SIGMOD), 2023."},{"key":"e_1_3_2_1_35_1","volume-title":"cedar: Composable and optimized machine learning input data pipelines. arXiv preprint arXiv:2401.08895","author":"Zhao Mark","year":"2024","unstructured":"Mark Zhao, Emanuel Adamiak, and Christos Kozyrakis. cedar: Composable and optimized machine learning input data pipelines. arXiv preprint arXiv:2401.08895, 2024."},{"key":"e_1_3_2_1_36_1","volume-title":"Parik Po. Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training. In Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA)","author":"Zhao Mark","year":"2022","unstructured":"Mark Zhao, Niket Agarwal, Aarti Basant, Bu\u011fra Gedik, Satadru Pan, Mustafa Ozdal, Rakesh Komuravelli, Jerry Pan, Tianshu Bao, Haowei Lu, Sundaram Narayanan, Jack Langman, Kevin Wilfong, Harsha Rastogi, Carole-Jean Wu, Christos Kozyrakis, and Parik Po. Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training. In Proceedings of the 49th Annual International Symposium on Computer Architecture (ISCA), 2022."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12289"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2017.8277979"},{"key":"e_1_3_2_1_39_1","volume-title":"Wei Chen. Exploiting Combined Locality for Wide-Stripe Erasure Coding in Distributed Storage. In Proceedings of the 19th USENIX Symposium on File and Storage Technologies (FAST)","author":"Hu Yuchong","year":"2021","unstructured":"Yuchong Hu, Liangfeng Cheng, Qiaori Yao, Patrick P. C. Lee, Weichun Wang, and Wei Chen. Exploiting Combined Locality for Wide-Stripe Erasure Coding in Distributed Storage. In Proceedings of the 19th USENIX Symposium on File and Storage Technologies (FAST), 2021."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of International Conference on High Performance Computing, Networking","author":"Wang Meng","year":"2023","unstructured":"Meng Wang, Jiajun Mao, Rajdeep Rana, John Bent, Serkay Olmez, Anjus George, Garrett Wilson Ransom, Jun Li and Haryadi S. Gunawi. Design Considerations and Analysis of Multi-Level Erasure Coding in Large-Scale Data Centers. In Proceedings of International Conference on High Performance Computing, Networking, Storage and Analysis (SC), 2023."},{"key":"e_1_3_2_1_41_1","unstructured":"PyTorch ImageNet example training script. ImageNet training in PyTorch. https:\/\/github.com\/pytorch\/examples\/tree\/main\/imagenet."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_43_1","unstructured":"Open Images Dataset Github. https:\/\/github.com\/cvdfoundation\/open-images-dataset."},{"key":"e_1_3_2_1_44_1","unstructured":"Scalability and performance targets for standard storage accounts. https:\/\/learn.microsoft.com\/en-us\/azure\/storage\/common\/scalability-targets-standard-account."},{"key":"e_1_3_2_1_45_1","first-page":"16","volume-title":"Proceedings of the Lua Workshop","author":"Watkins Noah","year":"2017","unstructured":"Noah Watkins and Michael Sevilla. Using lua in the ceph distributed storage system. In Proceedings of the Lua Workshop, pages 16--17, 2017."},{"key":"e_1_3_2_1_46_1","unstructured":"Amazon S3 Object Lambda. https:\/\/aws.amazon.com\/s3\/features\/object-lambda\/."},{"key":"e_1_3_2_1_47_1","unstructured":"NVIDIA DALI. https:\/\/developer.nvidia.com\/dali."}],"event":{"name":"HOTSTORAGE '24: 16th ACM Workshop on Hot Topics in Storage and File Systems","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"],"location":"Santa Clara CA USA","acronym":"HOTSTORAGE '24"},"container-title":["Proceedings of the 16th ACM Workshop on Hot Topics in Storage and File Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655038.3665947","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3655038.3665947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:09:39Z","timestamp":1755914979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3655038.3665947"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":47,"alternative-id":["10.1145\/3655038.3665947","10.1145\/3655038"],"URL":"https:\/\/doi.org\/10.1145\/3655038.3665947","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]},"assertion":[{"value":"2024-07-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}