{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:44Z","timestamp":1740099044695,"version":"3.37.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319780238"},{"type":"electronic","value":"9783319780245"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-78024-5_49","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"565-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance Evaluation of DBN Learning on Intel Multi- and Manycore Architectures"],"prefix":"10.1007","author":[{"given":"Tomasz","family":"Olas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wojciech K.","family":"Mleczko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcin","family":"Wozniak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert K.","family":"Nowicki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawel","family":"Gepner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"issue":"3","key":"49_CR1","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/MCSE.2017.48","volume":"19","author":"J Dongarra","year":"2017","unstructured":"Dongarra, J., Tomov, S., Luszczek, P., Kurzak, J., Gates, M., Yamazaki, I., Anzt, H., Haidar, A., Abdelfattah, A.: With extreme computing, the rules have changed. Comput. Sci. Eng. 19(3), 52\u201362 (2017)","journal-title":"Comput. Sci. Eng."},{"key":"49_CR2","unstructured":"Fang, J., Varbanescu, A.L., Sips, H.: Benchmarking Intel Xeon Phi to guide kernel design. Delft University of Technology Parallel and Distributed Systems Report Series. No. PDS-2013-005, pp. 1\u201322 (2013)"},{"issue":"7","key":"49_CR3","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"G Hinton","year":"2006","unstructured":"Hinton, G., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"key":"49_CR4","unstructured":"Intel Math Kernel Library: Reference Manual. Intel Corporation, Santa Clara (2009)"},{"key":"49_CR5","volume-title":"Intel Xeon Phi Coprocessor High Performance Programming","author":"J Jeffers","year":"2013","unstructured":"Jeffers, J., Reinders, J.: Intel Xeon Phi Coprocessor High Performance Programming, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco (2013)","edition":"1"},{"key":"49_CR6","volume-title":"Intel Xeon Phi Processor High Performance Programming: Knights Landing Edition","author":"J Jeffers","year":"2016","unstructured":"Jeffers, J., Reinders, J., Sodani, A.: Intel Xeon Phi Processor High Performance Programming: Knights Landing Edition. Elsevier Science, Cambridge (2016)"},{"issue":"4","key":"49_CR7","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2017","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 664\u2013676 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"49_CR8","unstructured":"Karpathy, A., Joulin, A., Li, F.F.F.: Deep fragment embeddings for bidirectional image sentence mapping. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, pp. 1889\u20131897 (2014)"},{"key":"49_CR9","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Department of Computer Science, University of Toronto (2009)"},{"key":"49_CR10","doi-asserted-by":"crossref","DOI":"10.1201\/9781315155944","volume-title":"Programming for Hybrid Multi\/Manycore MPP Systems","author":"J Levesque","year":"2017","unstructured":"Levesque, J., Vose, A.: Programming for Hybrid Multi\/Manycore MPP Systems, 1st edn. Taylor & Francis Ltd, London (2017)","edition":"1"},{"issue":"3","key":"49_CR11","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1109\/TPDS.2016.2599527","volume":"28","author":"A Lastovetsky","year":"2017","unstructured":"Lastovetsky, A., Szustak, L., Wyrzykowski, R.: Model-based optimization of EULAG kernel on Intel Xeon Phi through load imbalancing. IEEE Trans. Parallel Distrib. Syst. 28(3), 787\u2013797 (2017). https:\/\/doi.org\/10.1109\/TPDS.2016.2599527","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"49_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-319-32149-3_43","volume-title":"Parallel Processing and Applied Mathematics","author":"T Olas","year":"2016","unstructured":"Olas, T., Mleczko, W.K., Nowicki, R.K., Wyrzykowski, R.: Adaptation of deep belief networks to modern multicore architectures. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015. LNCS, vol. 9573, pp. 459\u2013472. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-32149-3_43"},{"key":"49_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1007\/978-3-319-19324-3_9","volume-title":"Artificial Intelligence and Soft Computing","author":"T Olas","year":"2015","unstructured":"Olas, T., Mleczko, W.K., Nowicki, R.K., Wyrzykowski, R., Krzyzak, A.: Adaptation of RBM learning for Intel MIC architecture. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015. LNCS (LNAI), vol. 9119, pp. 90\u2013101. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-19324-3_9"},{"key":"49_CR14","doi-asserted-by":"publisher","unstructured":"Raina, R., Madhavan, A., Ng, A.Y.: Large-scale deep unsupervised learning using graphics processors. In: Proceeding of 26th Annual International Conference on Machine Learning, ICML 2009, pp. 873\u2013880. ACM (2009). https:\/\/doi.org\/10.1145\/1553374.1553486","DOI":"10.1145\/1553374.1553486"},{"key":"49_CR15","unstructured":"Reinders, J.: An overview of programming for Intel Xeon processors and Intel Xeon Phi coprocessors. Technical report, Intel Corporation (2012)"},{"issue":"4","key":"49_CR16","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1109\/TASLP.2014.2303296","volume":"22","author":"R Sarikaya","year":"2014","unstructured":"Sarikaya, R., Hinton, G.E., Deoras, A.: Application of deep belief networks for natural language understanding. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(4), 778\u2013784 (2014). https:\/\/doi.org\/10.1109\/TASLP.2014.2303296","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"49_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/978-3-642-55224-3_52","volume-title":"Parallel Processing and Applied Mathematics","author":"E Saule","year":"2014","unstructured":"Saule, E., Kaya, K., \u00c7ataly\u00fcrek, \u00dc.V.: Performance evaluation of sparse matrix multiplication kernels on Intel Xeon Phi. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2013. LNCS, vol. 8384, pp. 559\u2013570. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-642-55224-3_52"},{"key":"49_CR18","doi-asserted-by":"publisher","unstructured":"Song, K., Liu, Y., Wang, R., Zhao, M., Hao, Z., Qian, D.: Restricted Boltzmann machines and deep belief networks on sunway cluster. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications, pp. 245\u2013252 (2016). https:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS.2016.0044","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0044"},{"key":"49_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/978-3-642-55224-3_54","volume-title":"Parallel Processing and Applied Mathematics","author":"L Szustak","year":"2014","unstructured":"Szustak, L., Rojek, K., Gepner, P.: Using Intel Xeon Phi coprocessor to accelerate computations in MPDATA algorithm. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) PPAM 2013. LNCS, vol. 8384, pp. 582\u2013592. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-642-55224-3_54"},{"key":"49_CR20","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1155\/2015\/642705","volume":"2015","author":"L Szustak","year":"2015","unstructured":"Szustak, L., Rojek, K., Olas, T., Kuczynski, L., Halbiniak, K., Gepner, P.: Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci. Program. 2015, 14 (2015). https:\/\/doi.org\/10.1155\/2015\/642705","journal-title":"Sci. Program."},{"key":"49_CR21","unstructured":"Ueyoshi, K., Marukame, T., Asai, T., Motomura, M., Schmid, A.: FPGA implementation of a scalable and highly parallel architecture for restricted Boltzmann machines, 07, 2132\u20132141 (2016)"},{"issue":"6","key":"49_CR22","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/113446.113449","volume":"26","author":"ME Wolf","year":"1991","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. SIGPLAN Not. 26(6), 30\u201344 (1991). https:\/\/doi.org\/10.1145\/113446.113449","journal-title":"SIGPLAN Not."},{"key":"49_CR23","doi-asserted-by":"publisher","unstructured":"Wolfe, M.: More iteration space tiling. In: Proceedings of the 1989 ACM\/IEEE Conference on Supercomputing, Supercomputing 1989, pp. 655\u2013664. ACM, New York (1989). https:\/\/doi.org\/10.1145\/76263.76337","DOI":"10.1145\/76263.76337"},{"issue":"4","key":"49_CR24","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/TASL.2012.2229986","volume":"21","author":"XL Zhang","year":"2013","unstructured":"Zhang, X.L., Wu, J.: Deep belief networks based voice activity detection. IEEE Trans. Audio Speech Lang. Process. 21(4), 697\u2013710 (2013). https:\/\/doi.org\/10.1109\/TASL.2012.2229986","journal-title":"IEEE Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78024-5_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,13]],"date-time":"2019-10-13T03:56:46Z","timestamp":1570939006000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}