{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T04:24:16Z","timestamp":1787372656810,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819510207","type":"print"},{"value":"9789819510214","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-1021-4_23","type":"book-chapter","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T10:29:29Z","timestamp":1762165769000},"page":"308-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding Data Preprocessing for\u00a0Effective End-to-End Training of\u00a0DNN"],"prefix":"10.1007","author":[{"given":"Ping","family":"Gong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaosong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam H.","family":"Noh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"23_CR1","unstructured":"Aarati, K., Abhay, V., Amar, P., Shivaram, V.: The case for unifying data loading in machine learning clusters. In: 11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 19). USENIX Association, Renton, WA (2019). https:\/\/www.usenix.org\/conference\/hotcloud19\/presentation\/kakaraparthy"},{"key":"23_CR2","doi-asserted-by":"publisher","unstructured":"Agrawal, P., et\u00a0al.: Data platform for machine learning. In: Proceedings of the 2019 International Conference on Management of Data, pp. 1803\u20131816. SIGMOD 2019, Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3299869.3314050","DOI":"10.1145\/3299869.3314050"},{"key":"23_CR3","unstructured":"Amazon elastic block store - easy to use, high performance block storage at any scale (2020). https:\/\/aws.amazon.com\/ebs\/"},{"key":"23_CR4","unstructured":"Dedrick, J.: The need for disaggregated cloud infrastructures (2019). https:\/\/www.sdwanresource.com\/articles\/441334-need-disaggregated-cloud-infrastructures.htm"},{"key":"23_CR5","unstructured":"Virtual Machine series at AWS EC2 (2020). https:\/\/aws.amazon.com\/ec2\/instance-types\/"},{"key":"23_CR6","unstructured":"Gao, P.X., et al.: Network Requirements for Resource Disaggregation. In: Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, pp. 249\u2013264. OSDI2016, USENIX Association, USA (2016)"},{"key":"23_CR7","unstructured":"Virtual Machine series at Google Cloud (2020). https:\/\/cloud.google.com\/compute\/docs\/gpus"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Han, S., Egi, N., Panda, A., Ratnasamy, S., Shi, G., Shenker, S.: Network support for resource disaggregation in next-generation datacenters. In: Proceedings of the Twelfth ACM Workshop on Hot Topics in Networks, p.\u00a010. ACM (2013)","DOI":"10.1145\/2535771.2535778"},{"key":"23_CR9","doi-asserted-by":"publisher","unstructured":"Jia, D., Wei, D., Richard, S., Li-Jia, L., Kai, L., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009).https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"23_CR10","unstructured":"Joaquin\u00a0Anton, G., et al.: Fast AI data preprocessing with NVIDIA DALI (2019). https:\/\/devblogs.nvidia.com\/fast-ai-data-preprocessing-with-nvidia-dali\/"},{"key":"23_CR11","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Klimovic, A., Kozyrakis, C., Thereska, E., John, B., Kumar, S.: Flash storage disaggregation. In: Proceedings of the Eleventh European Conference on Computer Systems, p.\u00a029. ACM (2016)","DOI":"10.1145\/2901318.2901337"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Koliousis, A., Watcharapichat, P., Weidlich, M., Mai, L., Costa, P., Pietzuch, P.: Crossbow: scaling deep learning with small batch sizes on Multi-GPU servers. Proc. VLDB Endow. 12(11), 1399\u20131412 (2019). https:\/\/doi.org\/10.14778\/3342263.3342276","DOI":"10.14778\/3342263.3342276"},{"issue":"6","key":"23_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"key":"23_CR15","unstructured":"Luitjens, P.: NVIDIA DALI: speeding up PyTorch (2020). https:\/\/www.private-ai.com\/en\/2020\/01\/21\/nvidia-dali-speeding-up-pytorch\/"},{"issue":"2","key":"23_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2440-7","volume":"18","author":"M Li","year":"2024","unstructured":"Li, M., et al.: Towards optimized tensor code generation for deep learning on sunway many-core processor. Front. Comp. Sci. 18(2), 182101 (2024). https:\/\/doi.org\/10.1007\/s11704-022-2440-7","journal-title":"Front. Comp. Sci."},{"key":"23_CR17","unstructured":"MXNet: A Scalable Deep Learning Framework (2020). https:\/\/mxnet.incubator.apache.org\/"},{"key":"23_CR18","unstructured":"NVIDIA: Training script specifying various data loading methods enabled by DALI (2019). https:\/\/github.com\/NVIDIA\/DALI\/blob\/master\/docs\/examples\/use_cases\/pytorch\/resnet50\/main.py. Accessed April 2025"},{"key":"23_CR19","unstructured":"Pytorch official website (2020). https:\/\/pytorch.org\/"},{"key":"23_CR20","unstructured":"Xu, Q., Awasthi, M., Malladi, K.T., Bhimani, J., Yang, J., Annavaram, M.: Performance analysis of containerized applications on local and remote storage. In: Proceedings of the 33rd International Conference on Massive Storage Systems and Technology. MSST\u201917 (2017)"},{"key":"23_CR21","unstructured":"Robbie, G., Owen, C., Yevgeni, L.: Introducing Petastorm: Uber ATG\u2019s Data Access Library for Deep Learning (2018). https:\/\/eng.uber.com\/petastorm\/"},{"key":"23_CR22","unstructured":"TensorFlow (2020). https:\/\/www.tensorflow.org\/"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"issue":"4","key":"23_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1749-6","volume":"17","author":"X Liu","year":"2023","unstructured":"Liu, X., Liu, Y., Yin, B., Yang, H., Luan, Z., Qian, D.: swspamm: optimizing large-scale sparse approximate matrix multiplication on sunway taihulight. Front. Comp. Sci. 17(4), 174104 (2023). https:\/\/doi.org\/10.1007\/s11704-022-1749-6","journal-title":"Front. Comp. Sci."},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Xiuhong, L., Yun, L., Shengen, Y., Liancheng, J., Yinghan, L.: A coordinated tiling and batching framework for efficient GEMM on GPUs. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, pp. 229\u2013241 (2019)","DOI":"10.1145\/3293883.3295734"},{"key":"23_CR26","doi-asserted-by":"publisher","unstructured":"Yang, C.C., Cong, G.: Accelerating data loading in deep neural network training. In: 2019 IEEE 26th International Conference on High Performance Computing, Data, and Analytics (HiPC) (2019).https:\/\/doi.org\/10.1109\/hipc.2019.00037","DOI":"10.1109\/hipc.2019.00037"},{"key":"23_CR27","unstructured":"Yizhou, S., Yutong, H., Yilun, C., Yiying, Z.: LegoOS: a disseminated, distributed OS for hardware resource disaggregation. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pp. 69\u201387. USENIX Association, Carlsbad, CA (2018). https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/shan"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-1021-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:43:15Z","timestamp":1787370195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-1021-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"ISBN":["9789819510207","9789819510214"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-1021-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,4]]},"assertion":[{"value":"4 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}