{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:46:54Z","timestamp":1760014014899,"version":"3.37.3"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T00:00:00Z","timestamp":1566518400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T00:00:00Z","timestamp":1566518400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2019R1H1A2039658","2015M3C4A7065646"],"award-info":[{"award-number":["2019R1H1A2039658","2015M3C4A7065646"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013173","name":"GRRC","doi-asserted-by":"crossref","award":["GRRC-KAU-2018-B01"],"award-info":[{"award-number":["GRRC-KAU-2018-B01"]}],"id":[{"id":"10.13039\/501100013173","id-type":"DOI","asserted-by":"crossref"}]},{"name":"MOTIE\/KEIT","award":["10076476"],"award-info":[{"award-number":["10076476"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s10586-019-02974-6","type":"journal-article","created":{"date-parts":[[2019,8,23]],"date-time":"2019-08-23T10:02:34Z","timestamp":1566554554000},"page":"2193-2204","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Comprehensive techniques of multi-GPU memory optimization for deep learning acceleration"],"prefix":"10.1007","volume":"23","author":[{"given":"Youngrang","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6248-9567","authenticated-orcid":false,"given":"Jaehwan","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jik-Soo","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Hyunseung","family":"Jei","sequence":"additional","affiliation":[]},{"given":"Hongchan","family":"Roh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,23]]},"reference":[{"key":"2974_CR1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates Inc., Red Hook (2012)"},{"key":"2974_CR2","doi-asserted-by":"crossref","unstructured":"Rhu, M., Gimelshein, N., Clemons, J., Zulfiqar, A., Keckler, S.W.: vdnn: virtualized deep neural networks for scalable, memory-efficient neural network design. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) (2016)","DOI":"10.1109\/MICRO.2016.7783721"},{"key":"2974_CR3","unstructured":"TensorFlow: an open source machine learning library for research and production. \nhttps:\/\/www.tensorflow.org\/\n\n (2019)"},{"key":"2974_CR4","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"2974_CR5","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.-S., Jei, H., Roh, H.: Efficient multi-GPU memory management for deep learning acceleration. In: 6th International Workshop on Autonomic Management of High Performance Grid and Cloud Computing (AMGCC\u201918) (2018)","DOI":"10.1109\/FAS-W.2018.00023"},{"key":"2974_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. \narxiv.org\n\n (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2974_CR7","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2974_CR8","doi-asserted-by":"crossref","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (1998)","DOI":"10.1109\/5.726791"},{"key":"2974_CR9","unstructured":"NVIDIA DGX-1 system architecture. White Paper, NVIDIA"},{"key":"2974_CR10","unstructured":"Duc, T.L.: Ibmcaffe: the harmony of CPU and GPU in training deep neural networks. IBM Research, Technical Reports"},{"key":"2974_CR11","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. \narxiv.org\n\n (2014)"},{"key":"2974_CR12","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., He, K.: Accurate, large minibatch SGD: training imagenet in 1 hour. \narxiv.org\n\n (2018)"},{"key":"2974_CR13","unstructured":"NVIDIA: Unified memory in cuda 6"},{"key":"2974_CR14","unstructured":"XLA: \nhttps:\/\/www.tensorflow.org\/performance\/xla\n\n (2019)"},{"key":"2974_CR15","unstructured":"NNVM: \nhttps:\/\/github.com\/dmlc\/nnvm-fusion\n\n (2019)"},{"key":"2974_CR16","unstructured":"MXNet\u2019s Optimizing Memory Consumption in Deep Learning. \nhttp:\/\/mxnet.incubator.apache.org\/architecture\/note-memory.html\n\n (2019)"},{"key":"2974_CR17","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. \narxiv.org\n\n (2016)"},{"key":"2974_CR18","doi-asserted-by":"crossref","unstructured":"Kehne, J., Metter, J., Bellosa, F.: Gpuswap: enabling oversubscription of GPU memory through transparent swapping. In: Proceedings of the 11th ACM SIGPLAN\/SIGOPS International Conference on Virtual Execution Environments, pp. 65\u201377","DOI":"10.1145\/2817817.2731192"},{"key":"2974_CR19","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, W.: Deep gradient compression: reducing the communication bandwidth for distributed training. In: Sixth International Conference on Learning Representations (ICLR) (2018)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02974-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-02974-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02974-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T18:18:03Z","timestamp":1600366683000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-02974-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,23]]},"references-count":19,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["2974"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-02974-6","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2019,8,23]]},"assertion":[{"value":"28 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}