{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T23:17:56Z","timestamp":1725837476362},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319271187"},{"type":"electronic","value":"9783319271194"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-27119-4_5","type":"book-chapter","created":{"date-parts":[[2015,11,15]],"date-time":"2015-11-15T23:39:29Z","timestamp":1447630769000},"page":"64-76","source":"Crossref","is-referenced-by-count":4,"title":["Unified Virtual Memory Support for Deep CNN Accelerator on SoC FPGA"],"prefix":"10.1007","author":[{"given":"Tao","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Yuran","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Qianming","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,12,16]]},"reference":[{"issue":"5","key":"5_CR1","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1147\/JRD.2010.2059721","volume":"54","author":"C Cascaval","year":"2010","unstructured":"Cascaval, C., Chatterjee, S., Franke, H., Gildea, K., Pattnaik, P.: A taxonomy of accelerator architectures and their programming models. IBM J. Res. Dev. 54(5), 473\u2013482 (2010)","journal-title":"IBM J. Res. Dev."},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Menychtas, K., Shen, K., Scott, M.L.: Disengaged scheduling for fair, protected access to fast computational accelerators. In: Proceedings of the 19th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS 2014), pp. 301\u2013316. ACM (2014)","DOI":"10.1145\/2541940.2541963"},{"key":"5_CR3","unstructured":"Abdelgawad, H.M., Safar, M., Wahba, A.M.: High level synthesis of canny edge detection algorithm on zynq platform"},{"key":"5_CR4","unstructured":"Vallina, F.M., Kohn, C., Joshi, P.: Zynq all programmable soc sobel filter implementation using the vivado hls tool, vol. XAPP890, pp. 1\u201316 (2012)"},{"key":"5_CR5","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 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 161\u2013170. ACM (2015)","DOI":"10.1145\/2684746.2689060"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Gokhale, V., Jin, J., Dundar, A., Martini, B., Culurciello, E.: A 240 g-ops\/s mobile coprocessor for deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 696\u2013701 (2014)","DOI":"10.1109\/CVPRW.2014.106"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"5_CR8","volume-title":"Linux Device Drivers","author":"J Corbet","year":"2005","unstructured":"Corbet, J., Rubini, A., Kroah-Hartman, G.: Linux Device Drivers. O\u2019Reilly Media Inc., Sebastopol (2005)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Sadri, M., Weis, C., Wehn, N., Benini, L.: Energy and performance exploration of accelerator coherency port using xilinx zynq. In: Proceedings of the 10th FPGAworld Conference, p. 5. ACM (2013)","DOI":"10.1145\/2513683.2513688"},{"key":"5_CR10","unstructured":"Zynq-7000 All Programmable SoC Technical Reference Manual (UG585), Xilinx. Inc., March 2013"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Farabet, C., Poulet, C., Han, J.Y., LeCun, Y.: Cnp: an fpga-based processor for convolutional networks. In: International Conference on Field Programmable Logic and Applications, FPL 2009, pp. 32\u201337. IEEE (2009)","DOI":"10.1109\/FPL.2009.5272559"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Sankaradas, M., Jakkula, V., Cadambi, S., Chakradhar, S., Durdanovic, I., Cosatto, E., Graf, H.P.: A massively parallel coprocessor for convolutional neural networks. In: 20th IEEE International Conference on Application-specific Systems, Architectures and Processors, ASAP 2009, pp. 53\u201360. IEEE (2009)","DOI":"10.1109\/ASAP.2009.25"},{"key":"5_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"5_CR14","unstructured":"PetaLinux Tools User Guide: Board Bringup Guide (UG980), Xilinx. Inc., June 2014"},{"key":"5_CR15","unstructured":"Rogers, P., Fellow, C.: Amd heterogeneous uniform memory access (2013)"},{"key":"5_CR16","unstructured":"Garg, I.C.: Amd kaveri review: A8-7600 and a10-7850k tested, January 2014. http:\/\/www.anandtech.com\/show\/7677\/amd-kaveri-review-a8-7600-a10-7850k\/6"},{"issue":"3","key":"5_CR17","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/MM.2009.44","volume":"29","author":"T Berg","year":"2009","unstructured":"Berg, T.: Maintaining I\/O data coherence in embedded multicore systems. IEEE Micro 29(3), 10\u201319 (2009)","journal-title":"IEEE Micro"},{"key":"5_CR18","unstructured":"Greenhalgh, P.: Big. little processing with arm cortex-a15 & cortex-a7. ARM White paper (2011)"},{"key":"5_CR19","unstructured":"Koutras, I., Bartzas, A., Soudris, D.: Efficient memory allocations on a many-core accelerator. In: ARCS Workshops (ARCS), pp. 1\u20136. IEEE (2012)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27119-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T11:24:41Z","timestamp":1567337081000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27119-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319271187","9783319271194"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27119-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]}}}