{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T11:01:28Z","timestamp":1725793288526},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662434536"},{"type":"electronic","value":"9783662434543"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-662-43454-3_3","type":"book-chapter","created":{"date-parts":[[2014,4,30]],"date-time":"2014-04-30T08:22:20Z","timestamp":1398846140000},"page":"21-29","source":"Crossref","is-referenced-by-count":0,"title":["Optimization of Industrial Neural Network Simulators for GPGPUs"],"prefix":"10.1007","author":[{"given":"Mhd. Amer","family":"Wafai","sequence":"first","affiliation":[]},{"given":"Zaheer","family":"Ahmed","sequence":"additional","affiliation":[]},{"given":"Rainer","family":"Keller","sequence":"additional","affiliation":[]},{"given":"Sven","family":"Holzmann","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn","family":"Sander","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Resch","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","first-page":"207","volume-title":"CF 2009: Proceedings of the 6th ACM Conference on Computing Frontiers","author":"A.S. Amesfoort van","year":"2009","unstructured":"van Amesfoort, A.S., Varbanescu, A.L., Sips, H.J., van Nieuwpoort, R.V.: Evaluating multi-core platforms for hpc data-intensive kernels. In: CF 2009: Proceedings of the 6th ACM Conference on Computing Frontiers, pp. 207\u2013216. ACM, New York (2009)"},{"issue":"1","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/10943420020160010101","volume":"16","author":"J. Dongarra","year":"2002","unstructured":"Dongarra, J.: Basic linear algebra subprograms technical forum standard. Int. J. of High Performance Applications and Supercomputing\u00a016(1), 1\u2013111 (2002)","journal-title":"Int. J. of High Performance Applications and Supercomputing"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Flynn, M.J.: Some computer organizations and their effectiveness. IEEE Trans. Comput. C-21, 948 (1972)","DOI":"10.1109\/TC.1972.5009071"},{"key":"3_CR4","unstructured":"G\u00f6ddeke, D., Strzodka, R., Turek, S.: Accelerating double precision FEM simulations with GPUs. In: H\u00fclsemann, F., Kowarschik, M., R\u00fcde, U. (eds.) Frontiers in Simulation, pp. 139\u2013144 (2005)"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1970353.1970356","volume":"16","author":"Y. Han","year":"2011","unstructured":"Han, Y., Chakraborty, K., Roy, S., Kuntamukkala, V.: Design and implementation of a throughput-optimized gpu floorplanning algorithm. ACM Trans. Des. Autom. Electron. Syst.\u00a016, 1\u201323 (2011)","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"3_CR6","unstructured":"NVIDIA: CUDA basic linear algebra subroutines (cuBLAS), \n \n http:\/\/developer.nvidia.com\/cublas\n \n \n (2011)"},{"key":"3_CR7","unstructured":"NVIDIA: CUDA C programming guide version 4.0. Tech. rep. (2011), \n \n http:\/\/developer.download.nvidia.com\/compute\/cuda\/4_0\/toolkit\/docs\/CUDA_C_Programming_Guide.pdf"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Scanzio, S., Cumani, S., Gemello, R., Mana, F., Laface, P.: Parallel implementation of artificial neural network training. In: IEEE Int. Conf. on Acoustics Speech and Signal Processing (ICASSP), March 14-19, vol.\u00a01, pp. 4902\u20134905 (2010)","DOI":"10.1109\/ICASSP.2010.5495108"},{"key":"3_CR9","unstructured":"Siek, J., Lee, L.Q., Lumsdaine, A.: The Boost Graph Library. Addison-Wesley (2002)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Strigl, D., Kofler, K., Podlipnig, S.: Performance and scalability of GPU-based convolutional neural networks. In: 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), Pisa, Italy, February 17-19 (2010)","DOI":"10.1109\/PDP.2010.43"},{"key":"3_CR11","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.entcs.2008.12.087","volume":"225","author":"H. Takizawa","year":"2009","unstructured":"Takizawa, H., Chida, T., Kobayashi, H.: Evaluating computational performance of backpropagation learning on graphics hardware. Electr. Notes Theor. Comput. Sci.\u00a0225, 379\u2013389 (2009)","journal-title":"Electr. Notes Theor. Comput. Sci."},{"key":"3_CR12","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1145\/1543834.1543939","volume-title":"Proceedings of the First ACM\/SIGEVO Summit on Genetic and Evolutionary Computation, GEC 2009","author":"W. Zhu","year":"2009","unstructured":"Zhu, W.: A study of parallel evolution strategy: pattern search on a gpu computing platform. In: Proceedings of the First ACM\/SIGEVO Summit on Genetic and Evolutionary Computation, GEC 2009, pp. 765\u2013772. ACM, New York (2009)"}],"container-title":["Lecture Notes in Computer Science","New Horizons in Web Based Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-43454-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,26]],"date-time":"2019-05-26T14:29:33Z","timestamp":1558880973000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-43454-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783662434536","9783662434543"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-43454-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}