{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T18:32:15Z","timestamp":1743100335240,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819628841"},{"type":"electronic","value":"9789819628858"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2885-8_19","type":"book-chapter","created":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T05:59:58Z","timestamp":1741586398000},"page":"188-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Training Feature-Awared GPU-Memory Allocation and\u00a0Management for\u00a0Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"Qintao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengchuang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"19_CR1","unstructured":"Lee, J., Toutanova, K.: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, vol.\u00a03, p.\u00a08 (2018)"},{"key":"19_CR2","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"19_CR3","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"19_CR4","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"19_CR5","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Tong, Z., Du, N., Song, X., Wang, X.: Study on mindspore deep learning framework. In: 2021 17th International Conference on Computational Intelligence and Security (CIS), pp. 183\u2013186. IEEE (2021)","DOI":"10.1109\/CIS54983.2021.00046"},{"issue":"6","key":"19_CR7","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1145\/359605.359626","volume":"20","author":"JL Peterson","year":"1977","unstructured":"Peterson, J.L., Norman, T.A.: Buddy systems. Commun. ACM 20(6), 421\u2013431 (1977)","journal-title":"Commun. ACM"},{"key":"19_CR8","unstructured":"Bonwick, J., et al.: The slab allocator: an object-caching kernel memory allocator. In: USENIX Summer, Boston, MA, USA, vol.\u00a016 (1994)"},{"issue":"6","key":"19_CR9","doi-asserted-by":"publisher","first-page":"2477","DOI":"10.1109\/TCSI.2022.3153288","volume":"69","author":"DT Nguyen","year":"2022","unstructured":"Nguyen, D.T., Je, H., Nguyen, T.N., Ryu, S., Lee, K., Lee, H.-J.: ShortcutFusion: from tensorflow to FPGA-based accelerator with a reuse-aware memory allocation for shortcut data. IEEE Trans. Circuits Syst. I Regul. Pap. 69(6), 2477\u20132489 (2022)","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with pagedattention. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Superneurons: dynamic GPU memory management for training deep neural networks. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 41\u201353 (2018)","DOI":"10.1145\/3178487.3178491"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: GMLake: efficient and transparent GPU memory defragmentation for large-scale DNN training with virtual memory stitching. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol. 2, pp. 450\u2013466 (2024)","DOI":"10.1145\/3620665.3640423"},{"issue":"3","key":"19_CR13","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TKDE.2006.48","volume":"18","author":"Y Tao","year":"2006","unstructured":"Tao, Y., Papadias, D.: Maintaining sliding window skylines on data streams. IEEE Trans. Knowl. Data Eng. 18(3), 377\u2013391 (2006)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"19_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"19_CR15","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"19_CR18","unstructured":"Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 34, pp. 770\u2013778 (2016)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"},{"key":"19_CR20","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"}],"container-title":["Lecture Notes in Computer Science","Advances in Brain Inspired Cognitive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2885-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T06:00:21Z","timestamp":1741586421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2885-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819628841","9789819628858"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2885-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"11 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Brain Inspired Cognitive Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bics2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bics2024.dobell.me\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}