{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:26:59Z","timestamp":1767166019208,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819958368"},{"type":"electronic","value":"9789819958375"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-5837-5_30","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T01:01:29Z","timestamp":1693789289000},"page":"363-374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Scheduling Deep Learning Training in\u00a0GPU Cluster Using the\u00a0Model-Similarity-Based Policy"],"prefix":"10.1007","author":[{"given":"Panissara","family":"Thanapol","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kittichai","family":"Lavangnananda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franck","family":"Lepr\u00e9vost","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julien","family":"Schleich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Bouvry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","unstructured":"Albahar, H., Dongare, S., Du, Y., Zhao, N., Paul, A.K., Butt, A.R.: Schedtune: a heterogeneity-aware gpu scheduler for deep learning. In: 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pp. 695\u2013705 (2022). https:\/\/doi.org\/10.1109\/CCGrid54584.2022.00079","DOI":"10.1109\/CCGrid54584.2022.00079"},{"key":"30_CR2","unstructured":"Amazon web services inc.: deep learning AMI: Developer guide. Technical Report (2022)"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Chaudhary, S., Ramjee, R., Sivathanu, M., Kwatra, N., Viswanatha, S.: Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning. In: The Fifteenth European Conference on Computer Systems, pp. 1\u201316 (2020)","DOI":"10.1145\/3342195.3387555"},{"key":"30_CR4","unstructured":"Chollet, F.: Deep learning with Python. Manning Publications, Shelter Island (2017)"},{"key":"30_CR5","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"30_CR6","unstructured":"Goyal, P., et al.: Accurate, large minibatch sgd: Training imagenet in 1 hour. Technical Report (2017)"},{"key":"30_CR7","unstructured":"Gu, J., et al.: Tiresias: A GPU cluster manager for distributed deep learning. In: 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19), pp. 485\u2013500 (2019)"},{"key":"30_CR8","doi-asserted-by":"publisher","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining, pp. 39\u201382. The Morgan Kaufmann Series in Data Management Systems, Morgan Kaufmann, Boston, 3 edn. (2012). https:\/\/doi.org\/10.1016\/B978-0-12-381479-1.00002-2","DOI":"10.1016\/B978-0-12-381479-1.00002-2"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR10","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, 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":"30_CR12","unstructured":"Karen, S., Andrew, Z.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"30_CR13","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical Report (2009)"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Margery, D., Morel, E., Nussbaum, L., Richard, O., Rohr, C.: Resources description, selection, reservation and verification on a large-scale testbed. In: TRIDENTCOM - 9th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities (2014)","DOI":"10.1007\/978-3-319-13326-3_23"},{"key":"30_CR15","first-page":"336","volume":"2","author":"P Mattson","year":"2020","unstructured":"Mattson, P., et al.: Mlperf training benchmark. Proc. Mach. Learn. Syst. 2, 336\u2013349 (2020)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"30_CR16","unstructured":"Narayanan, D., Santhanam, K., Kazhamiaka, F., Phanishayee, A., Zaharia, M.: Heterogeneity-aware cluster scheduling policies for deep learning workloads. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp. 481\u2013498. USENIX Association (2020)"},{"key":"30_CR17","doi-asserted-by":"publisher","unstructured":"Peng, Y., Bao, Y., Chen, Y., Wu, C., Guo, C.: Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: The Thirteenth EuroSys Conference, pp. 1\u201314 (2018). https:\/\/doi.org\/10.1145\/3190508.3190517","DOI":"10.1145\/3190508.3190517"},{"issue":"8","key":"30_CR18","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPDS.2021.3052895","volume":"32","author":"Y Peng","year":"2021","unstructured":"Peng, Y., Bao, Y., Chen, Y., Wu, C., Meng, C., Lin, W.: Dl2: A deep learning-driven scheduler for deep learning clusters. IEEE Trans. Parallel Distrib. Syst. 32(8), 1947\u20131960 (2021)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"30_CR19","doi-asserted-by":"publisher","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: Inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"30_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)"},{"key":"30_CR21","unstructured":"Torres, J.: Train a neural network on multi-gpu with tensorflow - supercomputing for artificial intelligence, March 2023. https:\/\/towardsdatascience.com\/train-a-neural-network-on-multi-gpu-with-tensorflow-42fa5f51b8af"},{"issue":"23","key":"30_CR22","first-page":"495","volume":"5","author":"J Wu","year":"2017","unstructured":"Wu, J.: Introduction to convolutional neural networks. Natl Key Lab Novel Softw. Technol. 5(23), 495 (2017)","journal-title":"Natl Key Lab Novel Softw. Technol."},{"key":"30_CR23","unstructured":"Xiao, W., et al.: Gandiva: introspective cluster scheduling for deep learning. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pp. 595\u2013610 (2018)"},{"key":"30_CR24","unstructured":"Xiao, W., et al.: Antman: Dynamic scaling on GPU clusters for deep learning. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp. 533\u2013548. USENIX Association, November 2020. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/xiao"},{"issue":"1","key":"30_CR25","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/TPDS.2021.3079202","volume":"33","author":"G Yeung","year":"2022","unstructured":"Yeung, G., Borowiec, D., Yang, R., Friday, A., Harper, R., Garraghan, P.: Horus: Interference-aware and prediction-based scheduling in deep learning systems. IEEE Trans. Parallel Distrib. Syst. 33(1), 88\u2013100 (2022). https:\/\/doi.org\/10.1109\/TPDS.2021.3079202","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"30_CR26","unstructured":"Yu, G.X., Gao, Y., Golikov, P., Pekhimenko, G.: Habitat: a runtime-based computational performance predictor for deep neural network training. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp. 503\u2013521. USENIX Association (2021)"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Stafman, L., Or, A., Freedman, M.J.: Slaq: quality-driven scheduling for distributed machine learning. In: The 2017 Symposium on Cloud Computing, pp. 390\u2013404 (2017)","DOI":"10.1145\/3127479.3127490"}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-5837-5_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T07:22:47Z","timestamp":1767165767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-5837-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819958368","9789819958375"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-5837-5_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phuket","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"24 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}