{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T10:33:46Z","timestamp":1756636426780,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030242886"},{"type":"electronic","value":"9783030242893"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-24289-3_49","type":"book-chapter","created":{"date-parts":[[2019,6,28]],"date-time":"2019-06-28T11:03:03Z","timestamp":1561719783000},"page":"665-676","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Towards a Learning-Based Performance Modeling for Accelerating Deep Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6815-6659","authenticated-orcid":false,"given":"Damiano","family":"Perri","sequence":"first","affiliation":[]},{"given":"Paolo","family":"Sylos Labini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4327-520X","authenticated-orcid":false,"given":"Osvaldo","family":"Gervasi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9174-9065","authenticated-orcid":false,"given":"Sergio","family":"Tasso","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5676-9228","authenticated-orcid":false,"given":"Flavio","family":"Vella","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,29]]},"reference":[{"issue":"3","key":"49_CR1","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1109\/TMSCS.2018.2797195","volume":"4","author":"M Bernaschi","year":"2018","unstructured":"Bernaschi, M., Bisson, M., Mastrostefano, E., Vella, F.: Multilevel parallelism for the exploration of large-scale graphs. IEEE Trans. Multi-scale Comput. Syst. 4(3), 204\u2013216 (2018)","journal-title":"IEEE Trans. Multi-scale Comput. Syst."},{"key":"49_CR2","unstructured":"Cho, M., Brand, D.: MEC: memory-efficient convolution for deep neural network. CoRR, abs\/1706.06873 (2017)"},{"key":"49_CR3","unstructured":"Cianfriglia, M., Vella, F., Nugteren, C., Lokhmotov, A., Fursin, G.: A model-driven approach for a new generation of adaptive libraries. arXiv preprint \n                      arXiv:1806.07060\n                      \n                     (2018)"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Cosenza, B., Durillo, J.J., Ermon, S., Juurlink, B.: Autotuning stencil computations with structural ordinal regression learning. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 287\u2013296. IEEE (2017)","DOI":"10.1109\/IPDPS.2017.102"},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Di Girolamo, S., Vella, F., Hoefler, T.: Transparent caching for RMA systems. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 1018\u20131027. IEEE (2017)","DOI":"10.1109\/IPDPS.2017.92"},{"key":"49_CR6","doi-asserted-by":"crossref","unstructured":"Falch, T.L., Elster, A.C.: Machine learning based auto-tuning for enhanced OpenCL performance portability. In: 2015 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW), pp. 1231\u20131240. IEEE (2015)","DOI":"10.1109\/IPDPSW.2015.85"},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Formisano, A., Gentilini, R., Vella, F.: Accelerating energy games solvers on modern architectures. In: Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms, p. 12. ACM (2017)","DOI":"10.1145\/3149704.3149771"},{"issue":"4","key":"49_CR8","first-page":"20","volume":"7","author":"G Fursin","year":"2010","unstructured":"Fursin, G., Temam, O.: Collective optimization: a practical collaborative approach. ACM Trans. Archit. Code Optim. (TACO) 7(4), 20 (2010)","journal-title":"ACM Trans. Archit. Code Optim. (TACO)"},{"issue":"1","key":"49_CR9","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10\u201318 (2009)","journal-title":"ACM SIGKDD Explor. Newslett."},{"key":"49_CR10","doi-asserted-by":"crossref","unstructured":"Hou, K., Feng, W.-c., Che, S.: Auto-tuning strategies for parallelizing sparse matrix-vector (SPMV) multiplication on multi-and many-core processors. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 713\u2013722. IEEE (2017)","DOI":"10.1109\/IPDPSW.2017.155"},{"key":"49_CR11","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1097\u20131105 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Lokhmotov, A., Chunosov, N., Vella, F., Fursin, G.: Multi-objective autotuning of mobilenets across the full software\/hardware stack. In: Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning, p. 6. ACM (2018)","DOI":"10.1145\/3229762.3229767"},{"issue":"3","key":"49_CR13","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1145\/321075.321084","volume":"8","author":"ME Maron","year":"1961","unstructured":"Maron, M.E.: Automatic indexing: an experimental inquiry. J. ACM (JACM) 8(3), 404\u2013417 (1961)","journal-title":"J. ACM (JACM)"},{"key":"49_CR14","doi-asserted-by":"crossref","unstructured":"Nugteren, C., Codreanu, V.: CLTune: a generic auto-tuner for OpenCL kernels. In: 2015 IEEE 9th International Symposium on Embedded Multicore\/Many-core Systems-on-Chip (MCSoC), pp. 195\u2013202 (2015)","DOI":"10.1109\/MCSoC.2015.10"},{"key":"49_CR15","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"49_CR16","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/21.97458","volume":"21","author":"SR Safavian","year":"1991","unstructured":"Safavian, S.R., Landgrebe, D.: A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybern. 21(3), 660\u2013674 (1991)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"49_CR17","unstructured":"Singer, B., Veloso, M.: Learning to predict performance from formula modeling and training data. In: ICML, pp. 887\u2013894 (2000)"},{"key":"49_CR18","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":"49_CR19","doi-asserted-by":"crossref","unstructured":"Tasso, S., Gervasi, O., Vella, F., Cuzzocrea, A.: A simulation framework for efficient resource management on hybrid systems. In: 2015 IEEE 18th International Conference on Computational Science and Engineering, pp. 216\u2013223. IEEE (2015)","DOI":"10.1109\/CSE.2015.51"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Vasudevan, A., Anderson, A., Gregg, D.: Parallel multi channel convolution using general matrix multiplication. CoRR, abs\/1704.04428 (2017)","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"49_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3182656","volume":"23","author":"F Vella","year":"2018","unstructured":"Vella, F., Bernaschi, M., Carbone, G.: Dynamic merging of frontiers for accelerating the evaluation of betweenness centrality. J. Exp. Algorithmics (JEA) 23, 1\u20134 (2018)","journal-title":"J. Exp. Algorithmics (JEA)"},{"key":"49_CR22","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chen, T.: Optimizing deep learning workloads on arm GPU with TVM. In: Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-Designing Pareto-Efficient Deep Learning, p. 3. ACM (2018)","DOI":"10.1145\/3229762.3229764"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-24289-3_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,28]],"date-time":"2019-06-28T15:22:01Z","timestamp":1561735321000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-24289-3_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030242886","9783030242893"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-24289-3_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Saint Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}