{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:36:11Z","timestamp":1791390971208,"version":"4.3.3"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:00:00Z","timestamp":1642118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["777154"],"award-info":[{"award-number":["777154"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10586-021-03428-8","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T00:03:28Z","timestamp":1642118608000},"page":"1279-1302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Performance prediction of deep learning applications training in GPU as a service systems"],"prefix":"10.1007","volume":"25","author":[{"given":"Marco","family":"Lattuada","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugenio","family":"Gianniti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4224-927X","authenticated-orcid":false,"given":"Danilo","family":"Ardagna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,14]]},"reference":[{"key":"3428_CR1","doi-asserted-by":"crossref","unstructured":"Jun, T.J., Kang, D., Kim, D., Kim, D.: GPU enabled serverless computing framework. In: 26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP 2018), Cambridge, 21\u201323 March 2018, pp. 533\u2013540 (2018)","DOI":"10.1109\/PDP2018.2018.00090"},{"key":"3428_CR2","unstructured":"Global Market Insights (2019) GPU as a service market size by product. www.gminsights.com\/industry-analysis\/gpu-as-a-service-market"},{"key":"3428_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of 25th International Conference on Neural Information Processing Systems (NIPS 12), vol.\u00a01, pp 1097\u20131105 (2012)"},{"key":"3428_CR4","doi-asserted-by":"crossref","unstructured":"Khomenko, V., Shyshkov, O., Radyvonenko, O., Bokhan, K.: Accelerating recurrent neural network training using sequence bucketing and multi-gpu data parallelization. CoRR abs\/1708.05604, (2017) arXiv:1708.05604","DOI":"10.1109\/DSMP.2016.7583516"},{"key":"3428_CR5","unstructured":"PyTorch: Tensors and dynamic neural networks in Python with strong GPU acceleration (2018). https:\/\/pytorch.org"},{"key":"3428_CR6","unstructured":"TensorFlow: An open source machine learning framework for everyone (2018). www.tensorflow.org"},{"key":"3428_CR7","unstructured":"Amazon (2018) Amazon EC2 elastic GPUs. https:\/\/aws.amazon.com\/ec2\/elastic-gpus\/"},{"key":"3428_CR8","unstructured":"Google: GPUs on Compute Engine (2018). https:\/\/cloud.google.com\/compute\/docs\/gpus\/"},{"key":"3428_CR9","unstructured":"Microsoft: GPU optimized virtual machine sizes (2018). https:\/\/docs.microsoft.com\/en-us\/azure\/virtual-machines\/windows\/sizes-gpu"},{"key":"3428_CR10","unstructured":"Hadjis, S., Zhang, C., Mitliagkas, I., R\u00e9, C.: Omnivore: an optimizer for multi-device deep learning on CPUs and GPUs. Arxiv Preprint (2016). arXiv:1606.04487"},{"issue":"3","key":"3428_CR11","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1007\/s10586-021-03240-4","volume":"24","author":"RE Shawi","year":"2021","unstructured":"Shawi, R.E., Wahab, A., Barnawi, A., Sakr, S.: Dlbench: a comprehensive experimental evaluation of deep learning frameworks. Clust. Comput. 24(3), 2017\u20132038 (2021)","journal-title":"Cluster Computing"},{"key":"3428_CR12","volume-title":"Applied Regression Analysis","author":"NR Draper","year":"1966","unstructured":"Draper, N.R., Smith, H.: Applied Regression Analysis. Wiley, New York (1966)"},{"issue":"1","key":"3428_CR13","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J Machine Learning Research"},{"key":"3428_CR14","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: 2nd International Conference on Learning Representations (ICLR 2014). arXiv preprint (2013). arXiv:1312.4400"},{"key":"3428_CR15","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)","journal-title":"J Machine Learning Research"},{"key":"3428_CR16","doi-asserted-by":"publisher","unstructured":"Jia, W., Shaw, K.A., Martonosi, M.: Stargazer: automated regression-based GPU design space exploration. In: International Symposium on Performance Analysis of Systems & Software (ISPASS 12). IEEE (2012) https:\/\/doi.org\/10.1109\/ISPASS.2012.6189201","DOI":"10.1109\/ISPASS.2012.6189201"},{"issue":"2","key":"3428_CR17","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1007\/s10586-019-03011-2","volume":"23","author":"MH Shafiabadi","year":"2020","unstructured":"Shafiabadi, M.H., Pedram, H., Reshadi, M., Reza, A.: Comprehensive regression-based model to predict performance of general-purpose graphics processing unit. Clust. Comput. 23(2), 1505\u20131516 (2020)","journal-title":"Cluster Computing"},{"key":"3428_CR18","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Owens, J.D.: A quantitative performance analysis model for GPU architectures. In: 17th International Symposium on High Performance Computer Architecture (HPCA 11). IEEE (2011). https:\/\/doi.org\/10.1109\/HPCA.2011.5749745","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"3428_CR19","doi-asserted-by":"publisher","unstructured":"Song, S., Su, C., Rountree, B., Cameron, K.W.: A simplified and accurate model of power-performance efficiency on emergent GPU architectures. In: 27th International Symposium on Parallel and Distributed Processing (IPDPS 13). IEEE (2013) https:\/\/doi.org\/10.1109\/IPDPS.2013.73","DOI":"10.1109\/IPDPS.2013.73"},{"issue":"7","key":"3428_CR20","first-page":"1800","volume":"26","author":"TT Dao","year":"2015","unstructured":"Dao, T.T., Kim, J., Seo, S., Egger, B., Lee, J.: A performance model for GPUs with caches. IEEE Trans. Parallel Distrib. Syst. 26(7), 1800\u20131813 (2015)","journal-title":"IEEE TPDS"},{"key":"3428_CR21","doi-asserted-by":"publisher","unstructured":"Lu, Z., Rallapalli, S., Chan, K., La\u00a0Porta, T.: Modeling the resource requirements of convolutional neural networks on mobile devices. In: Proceedings of Conference on Multimedia (MM 17). ACM, New York (2017). https:\/\/doi.org\/10.1145\/3123266.3123389","DOI":"10.1145\/3123266.3123389"},{"key":"3428_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2840710","author":"U Gupta","year":"2018","unstructured":"Gupta, U., Babu, M., Ayoub, R., Kishinevsky, M., Paterna, F., Gumussoy, S., Ogras, U.Y.: An misc learning methodology for performance modeling of graphics processors. IEEE Trans. Comput. (2018). https:\/\/doi.org\/10.1109\/TC.2018.2840710","journal-title":"IEEE Transactions on Computer"},{"key":"3428_CR23","unstructured":"Peng, Y., Bao, Y., Chen, Y., Wu, C., Guo, C.: Optimus: an efficient dynamic resource scheduler for deep learning clusters. In: Proceedings of the Thirteenth EuroSys Conference (EuroSys 2018), Porto, Portugal, 23\u201326 April 2018. ACM, New York, pp. 3:1\u20133:14 (2018)"},{"key":"3428_CR24","doi-asserted-by":"publisher","unstructured":"Dube, P., Suk, T., Wang, C.: AI gauge: Runtime estimation for deep learning in the cloud. In: 31st International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 2019), Campo Grande, Brazil, 15\u201318 October 2019, pp. 160\u2013167. IEEE (2019) https:\/\/doi.org\/10.1109\/SBAC-PAD.2019.00035","DOI":"10.1109\/SBAC-PAD.2019.00035"},{"key":"3428_CR25","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.parco.2016.04.002","volume":"56","author":"S Madougou","year":"2016","unstructured":"Madougou, S., Varbanescu, A., de Laat, C., van Nieuwpoort, R.: The landscape of GPGPU performance modeling tools. J. Parallel Comput. 56, 18\u201333 (2016)","journal-title":"J Parallel Computing"},{"key":"3428_CR26","doi-asserted-by":"publisher","unstructured":"Kerr, A., Diamos, G., Yalamanchili, S.: Modeling GPU-CPU workloads and systems. In: Proceedings of 3rd Workshop General-Purpose Computation on Graphics Processing Units (GPGPU-3). ACM, New York (2010). https:\/\/doi.org\/10.1145\/1735688.1735696","DOI":"10.1145\/1735688.1735696"},{"key":"3428_CR27","doi-asserted-by":"publisher","unstructured":"Diamos, G.F., Kerr, A., Yalamanchili, S., Clark, N.: Ocelot: a dynamic optimization framework for bulk-synchronous applications in heterogeneous systems. In: 19th International Conference on Parallel Architecture and Compilation Techniques (PACT 10). IEEE, pp. 353\u2013364 (2010). https:\/\/doi.org\/10.1145\/1854273.1854318","DOI":"10.1145\/1854273.1854318"},{"key":"3428_CR28","doi-asserted-by":"crossref","unstructured":"Gianniti, E., Zhang, L., Ardagna, D.: Performance prediction of GPU-based deep learning applications. In: 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD 18) (2018)","DOI":"10.1109\/CAHPC.2018.8645908"},{"key":"3428_CR29","doi-asserted-by":"crossref","unstructured":"Gianniti, E., Zhang, L., Ardagna, D.: Performance prediction of gpu-based deep learning applications. In: Proceedings of the 9th International Conference on Cloud Computing and Services Science, CLOSER 2019, Heraklion, Crete, Greece, May 2-4, 2019, SciTePress, pp 279\u2013286 (2019)","DOI":"10.5220\/0007681802790286"},{"key":"3428_CR30","doi-asserted-by":"crossref","unstructured":"Mendoza, D., Romero, F., Li, Q., Yadwadkar, N.J., Kozyrakis, C.: Interference-aware scheduling for inference serving. In: Proceedings of the 1st Workshop on Machine Learning and Systemsg Virtual Event (EuroMLSys@EuroSys 2021), Edinburgh, Scotland, UK, 26 April 2021. ACM, New York, pp. 80\u201388 (2021)","DOI":"10.1145\/3437984.3458837"},{"issue":"1","key":"3428_CR31","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)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"3428_CR32","doi-asserted-by":"publisher","unstructured":"Lee, B.C., Brooks, D.M., de\u00a0Supinski, B.R., Schulz, M., Singh, K., McKee, S.A.: Methods of inference and learning for performance modeling of parallel applications. In: Proceedings of 12th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP 07) (2007). https:\/\/doi.org\/10.1145\/1229428.1229479","DOI":"10.1145\/1229428.1229479"},{"key":"3428_CR33","doi-asserted-by":"crossref","unstructured":"Didona, D., Romano, P.: On bootstrapping machine learning performance predictors via analytical models. CoRR (2014). arXiv:1410.5102v1","DOI":"10.1109\/ICPADS.2015.58"},{"key":"3428_CR34","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint (2014). arXiv:1409.1556"},{"key":"3428_CR35","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR 16). IEEE (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3428_CR36","unstructured":"Foundation, M.: Project deepspeech (2019b). https:\/\/github.com\/mozilla\/DeepSpeech"},{"key":"3428_CR37","unstructured":"Csurka, G.: Domain adaptation for visual applications: a comprehensive survey. Arxiv Preprint (2017). arXiv:1702.05374"},{"key":"3428_CR38","unstructured":"Hannun, A.Y., Case, C., Casper, J., Catanzaro, B., Diamos, G., Elsen, E., Prenger, R., Satheesh, S., Sengupta, S., Coates, A., Ng, A.Y.: Deep speech: Scaling up end-to-end speech recognition. CoRR (2014). arXiv:1412.5567"},{"key":"3428_CR39","unstructured":"Amodei, D., Anubhai, R., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Chen, J., Chrzanowski, M., Coates, A., Diamos, G., Elsen, E., Engel, J., Fan, L., Fougner, C., Han, T., Hannun, A.Y., Jun, B., LeGresley, P., Lin, L., Narang, S., Ng, A.Y., Ozair, S., Prenger, R., Raiman, J., Satheesh, S., Seetapun, D., Sengupta, S., Wang, Y., Wang, Z., Wang, C., Xiao, B., Yogatama, D., Zhan, J., Zhu, Z.: Deep speech 2: End-to-end speech recognition in english and mandarin. CoRR (2015). arXiv:1512.02595"},{"key":"3428_CR40","unstructured":"Morais, R.: A journey to <10% word error rate (2019). https:\/\/voice.mozilla.org\/"},{"key":"3428_CR41","unstructured":"Maas, A.L., Hannun, A.Y., Jurafsky, D., Ng, A.Y.: First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs. CoRR (2014). arXiv:1408.2873"},{"key":"3428_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2874944","author":"E Gianniti","year":"2018","unstructured":"Gianniti, E., Ciavotta, M., Ardagna, D.: Optimizing quality-aware big data applications in the cloud. IEEE Trans. Cloud Comput. (2018). https:\/\/doi.org\/10.1109\/TCC.2018.2874944","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"3428_CR43","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch. In: 31st Conference on Neural Information Processing Systems (NIPS 17) (2017)"},{"key":"3428_CR44","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I.J., Harp, A., Irving, G., Isard, M., Jia, Y., J\u00f3zefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D.G., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.A., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F.B., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. Arxiv Preprint (2016). arXiv:1603.04467"},{"key":"3428_CR45","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Arxiv Preprint (2015). arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"3428_CR46","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., L.-J. Li, K. Li, L. Fei-Fei: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 248\u2013255 (2009) https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3428_CR47","unstructured":"Foundation, M.: Common voice (2019a). https:\/\/voice.mozilla.org\/"},{"key":"3428_CR48","volume-title":"Quantitative System Performance","author":"ED Lazowska","year":"1984","unstructured":"Lazowska, E.D., Zahorjan, J., Graham, G.S., Sevcik, K.C.: Quantitative System Performance. Prentice-Hall, Hoboken (1984)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03428-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-021-03428-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03428-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T07:36:10Z","timestamp":1726472170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-021-03428-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,14]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["3428"],"URL":"https:\/\/doi.org\/10.1007\/s10586-021-03428-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,14]]},"assertion":[{"value":"10 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}