{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:16:08Z","timestamp":1743088568365,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031478420"},{"type":"electronic","value":"9783031478437"}],"license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-47843-7_11","type":"book-chapter","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T21:27:25Z","timestamp":1699306045000},"page":"150-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-level Storage Optimization for\u00a0Intermediate Data in\u00a0AI Model Training"],"prefix":"10.1007","author":[{"given":"Junfeng","family":"Fu","sequence":"first","affiliation":[]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xianqiang","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"issue":"2","key":"11_CR1","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1147\/sj.52.0078","volume":"5","author":"LA Belady","year":"1966","unstructured":"Belady, L.A.: A study of replacement algorithms for virtual-storage computer. IBM Syst. J. 5(2), 78\u2013101 (1966)","journal-title":"IBM Syst. J."},{"key":"11_CR2","unstructured":"Bian, Z., et al.: Colossal-AI: a unified deep learning system for large-scale parallel training. CoRR abs\/2110.14883 (2021)"},{"key":"11_CR3","unstructured":"Bian, Z., Xu, Q., Wang, B., You, Y.: Maximizing parallelism in distributed training for huge neural networks. CoRR abs\/2105.14450 (2021)"},{"key":"11_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, NeurIPS (2020)"},{"key":"11_CR5","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. CoRR abs\/1604.06174 (2016)"},{"key":"11_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, vol. 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"11_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021 (2021)"},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/TPDS.2022.3219819","volume":"34","author":"J Fang","year":"2023","unstructured":"Fang, J., et al.: Parallel training of pre-trained models via chunk-based dynamic memory management. IEEE Trans. Parallel Distrib. Syst. 34(1), 304\u2013315 (2023)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"11_CR9","unstructured":"Gokaslan, A., Cohen, V., Pavlick, E., Tellex, S.: (2019). https:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Hildebrand, M., Khan, J., Trika, S., Lowe-Power, J., Akella, V.: Autotm: automatic tensor movement in heterogeneous memory systems using integer linear programming. In: ASPLOS \u201920: Architectural Support for Programming Languages and Operating Systems, Lausanne, pp. 875\u2013890 (2020)","DOI":"10.1145\/3373376.3378465"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Huang, C., Jin, G., Li, J.: Swapadvisor: pushing deep learning beyond the GPU memory limit via smart swapping. In: ASPLOS \u201920: Architectural Support for Programming Languages and Operating Systems, pp. 1341\u20131355 (2020)","DOI":"10.1145\/3373376.3378530"},{"key":"11_CR12","unstructured":"Huang, Y., et al.: Efficient training of giant neural networks using pipeline parallelism. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems, NeurIPS 2019, pp. 103\u2013112 (2019)"},{"key":"11_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings (2015)"},{"key":"11_CR14","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, B.: Deep gradient compression: reducing the communication bandwidth for distributed training. In: 6th International Conference on Learning Representations, ICLR 2018, Conference Track Proceedings (2018)"},{"key":"11_CR15","unstructured":"Liu, E.Z., Hashemi, M., Swersky, K., Ranganathan, P., Ahn, J.: An imitation learning approach for cache replacement. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, pp. 6237\u20136247 (2020)"},{"issue":"2","key":"11_CR16","doi-asserted-by":"publisher","first-page":"312","DOI":"10.14778\/3489496.3489511","volume":"15","author":"X Miao","year":"2021","unstructured":"Miao, X., et al.: HET: scaling out huge embedding model training via cache-enabled distributed framework. Proc. VLDB Endow. 15(2), 312\u2013320 (2021)","journal-title":"Proc. VLDB Endow."},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Pipedream: generalized pipeline parallelism for DNN training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, SOSP 2019, pp. 1\u201315 (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Nie, X., Miao, X., Yang, Z., Cui, B.: TSPLIT: fine-grained GPU memory management for efficient DNN training via tensor splitting. In: 38th IEEE International Conference on Data Engineering, ICDE 2022, pp. 2615\u20132628 (2022)","DOI":"10.1109\/ICDE53745.2022.00241"},{"key":"11_CR19","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training. OpenAI (2018)"},{"key":"11_CR20","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI (2019)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020, p. 20 (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Ruwase, O., Rasley, J., Smith, S., He, Y.: Zero-infinity: breaking the GPU memory wall for extreme scale deep learning. In: International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2021, p. 59 (2021)","DOI":"10.1145\/3458817.3476205"},{"key":"11_CR23","unstructured":"Ren, J., et al.: Zero-offload: democratizing billion-scale model training. In: 2021 USENIX Annual Technical Conference, USENIX ATC 2021, pp. 551\u2013564 (2021)"},{"key":"11_CR24","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-LM: training multi-billion parameter language models using model parallelism. CoRR abs\/1909.08053 (2019)"},{"key":"11_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, NeurIPS 2017, pp. 5998\u20136008 (2017)"},{"key":"11_CR26","unstructured":"Wang, B., Xu, Q., Bian, Z., You, Y.: 2.5-dimensional distributed model training. CoRR abs\/2105.14500 (2021)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Q., You, Y.: An efficient 2D method for training super-large deep learning models. In: IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023, pp. 222\u2013232 (2023)","DOI":"10.1109\/IPDPS54959.2023.00031"},{"key":"11_CR28","unstructured":"Zeng, W., et al.: PanGu-$$\\alpha $$: large-scale autoregressive pretrained Chinese language models with auto-parallel computation. CoRR abs\/2104.12369 (2021)"}],"container-title":["Lecture Notes in Computer Science","Databases Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47843-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T21:33:21Z","timestamp":1699306401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47843-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"ISBN":["9783031478420","9783031478437"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47843-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,7]]},"assertion":[{"value":"7 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Database Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"63% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}