{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:25:30Z","timestamp":1743078330328,"version":"3.40.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319682099"},{"type":"electronic","value":"9783319682105"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-68210-5_9","type":"book-chapter","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T05:58:09Z","timestamp":1505714289000},"page":"100-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing OpenCL Implementation of Deep Convolutional Neural Network on FPGA"],"prefix":"10.1007","author":[{"given":"Yuran","family":"Qiao","sequence":"first","affiliation":[]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Dafei","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qianming","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Chunyuan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,19]]},"reference":[{"key":"9_CR1","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., Shelhamer, E.: cuDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Luo, T., Liu, S., Zhang, S., He, L., Wang, J., Li, L., Chen, T., Xu, Z., Sun, N., et al.: DaDianNao: a machine-learning supercomputer. In: Proceedings of the 47th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 609\u2013622. IEEE Computer Society (2014)","DOI":"10.1109\/MICRO.2014.58"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., Cong, J.: Optimizing FPGA-based accelerator design for deep convolutional neural networks. In: Proceedings of the 23rd ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA), pp. 161\u2013170. ACM (2015)","DOI":"10.1145\/2684746.2689060"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S., et al.: Going deeper with embedded FPGA platform for convolutional neural network. In: Proceedings of the 24th ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA), pp. 26\u201335. ACM (2016)","DOI":"10.1145\/2847263.2847265"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Czajkowski, T.S., Aydonat, U., Denisenko, D., Freeman, J., Kinsner, M., Neto, D., Wong, J., Yiannacouras, P., Singh, D.P.: From OpenCL to high-performance hardware on FPGAs. In: 22nd International Conference on Field Programmable Logic and Applications (FPL), pp. 531\u2013534. IEEE (2012)","DOI":"10.1109\/FPL.2012.6339272"},{"key":"9_CR6","unstructured":"Lin, D., Talathi, S., Annapureddy, S.: Fixed point quantization of deep convolutional networks. In: International Conference on Machine Learning, pp. 2849\u20132858 (2016)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Gu, J., Liu, Y., Gao, Y., Zhu, M.: OpenCL caffe: accelerating and enabling a cross platform machine learning framework. In: Proceedings of the 4th International Workshop on OpenCL, p. 8. ACM (2016)","DOI":"10.1145\/2909437.2909443"},{"key":"9_CR8","unstructured":"Altera: Altera opencl design examples. https:\/\/www.altera.com\/support\/support-resources\/design-examples\/design-software\/opencl\/matrix-multiplication.html"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Suda, N., Chandra, V., Dasika, G., Mohanty, A., Ma, Y., Vrudhula, S., Seo, J.s., Cao, Y.: Throughput-optimized OpenCL-based FPGA accelerator for large-scale convolutional neural networks. In: Proceedings of the 24th ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA), pp. 16\u201325. ACM (2016)","DOI":"10.1145\/2847263.2847276"},{"key":"9_CR10","unstructured":"Zhu, M., Liu, L., Wang, C., Xie, Y.: CNNLab: a novel parallel framework for neural networks using GPU and FPGA-a practical study with trade-off analysis. arXiv preprint arXiv:1606.06234 (2016)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, J.: Improving the performance of OpenCL-based FPGA accelerator for convolutional neural network. In: FPGA, pp. 25\u201334 (2017)","DOI":"10.1145\/3020078.3021698"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68210-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T05:38:28Z","timestamp":1633930708000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-68210-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319682099","9783319682105"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68210-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"19 September 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/npc-china2017.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}