{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T04:09:09Z","timestamp":1750910949429,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811063848"},{"type":"electronic","value":"9789811063855"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-981-10-6385-5_50","type":"book-chapter","created":{"date-parts":[[2017,9,15]],"date-time":"2017-09-15T14:03:52Z","timestamp":1505484232000},"page":"594-604","source":"Crossref","is-referenced-by-count":0,"title":["An Implementation and Improvement of Convolutional Neural Networks on HSA Platform"],"prefix":"10.1007","author":[{"given":"Zhenshan","family":"Bao","sequence":"first","affiliation":[]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Wenbo","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,16]]},"reference":[{"issue":"1","key":"50_CR1","doi-asserted-by":"crossref","first-page":"53","DOI":"10.5815\/ijigsp.2010.01.07","volume":"2","author":"C Yang","year":"2010","unstructured":"Yang, C., Wu, L.: GPU-based volume rendering for 3D electromagnetic environment on virtual globe. Int. J. Image Graph. Sig. Process. 2(1), 53 (2010)","journal-title":"Int. J. Image Graph. Sig. Process."},{"issue":"1","key":"50_CR2","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/s10686-008-9114-9","volume":"22","author":"C Harris","year":"2008","unstructured":"Harris, C.: GPU accelerated radio astronomy signal convolution. Exp. Astron. 22(1), 129\u2013141 (2008)","journal-title":"Exp. Astron."},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Michel, P., Chestnutt, J., Kagami, S., Nishiwaki, K.: GPU-accelerated real-time 3D tracking for humanoid locomotion and stair climbing. IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 463\u2013469. IEEE (2007)","DOI":"10.1109\/IROS.2007.4399104"},{"issue":"5","key":"50_CR4","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"JD Owens","year":"2008","unstructured":"Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., Phillips, J.C.: GPU computing. Proc. IEEE 96(5), 879\u2013899 (2008)","journal-title":"Proc. IEEE"},{"issue":"8","key":"50_CR5","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.parco.2011.10.002","volume":"38","author":"P Du","year":"2012","unstructured":"Du, P., Weber, R., Luszczek, P., Tomov, S., Peterson, G., Dongarra, J.: From CUDA to OpenCL: towards a performance-portable solution for multi-platform GPU programming \u2606, \u2606\u2606. Parallel Comput. 38(8), 391\u2013407 (2012)","journal-title":"Parallel Comput."},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Blinzer, P.: The heterogeneous system architecture: it\u2019s beyond the GPU. In: International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, p. iii. IEEE (2014). (Maxwell, J.C.: A Treatise on Electricity and Magnetism, 3rd edn., vol. 2, pp. 68\u201373. Clarendon, Oxford (1892))","DOI":"10.1109\/SAMOS.2014.6893187"},{"key":"50_CR7","doi-asserted-by":"crossref","unstructured":"Dan, C.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Convolutional neural network committees for handwritten character classification. In: International Conference on Document Analysis and Recognition, pp. 1135\u20131139. IEEE Computer Society (2011)","DOI":"10.1109\/ICDAR.2011.229"},{"key":"50_CR8","unstructured":"Lecun, B.Y., et al.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (2010)"},{"key":"50_CR9","doi-asserted-by":"crossref","unstructured":"Ubal, R., Jang, B., Mistry, P., Schaa, D., Kaeli, D.: Multi2Sim: a simulation framework for CPU-GPU computing. In: International Conference on Parallel Architectures and Compilation Techniques, pp. 335\u2013344. ACM (2012)","DOI":"10.1145\/2370816.2370865"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Ma, K., Li, X., Chen, W., Zhang, C.: GreenGPU: a holistic approach to energy efficiency in GPU-CPU heterogeneous architectures. In: International Conference on Parallel Processing, pp. 48\u201357. IEEE (2012)","DOI":"10.1109\/ICPP.2012.31"},{"key":"50_CR11","doi-asserted-by":"crossref","unstructured":"Ding, J.H., Hsu, W.C., Jeng, B.C., Hung, S.H., Chung, Y.C.: HSAemu: a full system emulator for HSA platforms. In: International Conference on Hardware\/Software Codesign and System Synthesis, p. 26. ACM (2014)","DOI":"10.1145\/2656075.2656088"},{"key":"50_CR12","unstructured":"Luo, Z., Liu, H., Wu, X.: Artificial neural network computation on graphic process unit. In: IEEE International Joint Conference on Neural Networks, vol. 1, pp. 622\u2013626. IEEE (2005)"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Strigl, D., Kofler, K., Podlipnig, S.: Performance and scalability of GPU-based convolutional neural networks. In: Euromicro International Conference on Parallel, Distributed and Network-Based Processing, pp. 317\u2013324. IEEE (2010)","DOI":"10.1109\/PDP.2010.43"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Gadea, R., Cerd\u00e1, J., Ballester, F., Mochol\u00ed, A.: Artificial neural network implementation on a single FPGA of a pipelined on-line backpropagation, pp. 225\u2013230 (2000)","DOI":"10.1109\/ISSS.2000.874054"},{"issue":"3","key":"50_CR15","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1109\/TNN.2007.891626","volume":"18","author":"S Himavathi","year":"2007","unstructured":"Himavathi, S., Anitha, D., Muthuramalingam, A.: Feedforward neural network implementation in FPGA using layer multiplexing for effective resource utilization. IEEE Trans. Neural Netw. 18(3), 880 (2007)","journal-title":"IEEE Trans. Neural Netw."}],"container-title":["Communications in Computer and Information Science","Data Science"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-6385-5_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T19:27:03Z","timestamp":1750879623000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-10-6385-5_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9789811063848","9789811063855"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-6385-5_50","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]}}}