{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T03:40:04Z","timestamp":1751859604186,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811324222"},{"type":"electronic","value":"9789811324239"}],"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\/978-981-13-2423-9_2","type":"book-chapter","created":{"date-parts":[[2018,9,12]],"date-time":"2018-09-12T11:37:42Z","timestamp":1536752262000},"page":"15-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory Bandwidth and Energy Efficiency Optimization of Deep Convolutional Neural Network Accelerators"],"prefix":"10.1007","author":[{"given":"Zikai","family":"Nie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shasha","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,13]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Albericio, J., et al.: Bit-pragmatic deep neural network computing. In: Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 382\u2013394. ACM (2017)","DOI":"10.1145\/3123939.3123982"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Alwani, M., Chen, H., Ferdman, M., Milder, P.: Fused-layer CNN accelerators. In: 2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 1\u201312. IEEE (2016)","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bastoul, C.: Code generation in the polyhedral model is easier than you think. In: Proceedings of the 13th International Conference on Parallel Architectures and Compilation Techniques, pp. 7\u201316. IEEE Computer Society (2004)","DOI":"10.1109\/PACT.2004.1342537"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., et al.: Diannao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. In: ACM Sigplan Notices, vol. 49, pp. 269\u2013284. ACM (2014)","DOI":"10.1145\/2644865.2541967"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Emer, J., Sze, V.: Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks. In: 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp. 367\u2013379. IEEE (2016)","DOI":"10.1109\/ISCA.2016.40"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., 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"},{"issue":"12","key":"2_CR7","doi-asserted-by":"publisher","first-page":"3207","DOI":"10.1162\/NECO_a_00052","volume":"22","author":"DC Cire\u015fan","year":"2010","unstructured":"Cire\u015fan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep, big, simple neural nets for handwritten digit recognition. Neural Comput. 22(12), 3207\u20133220 (2010)","journal-title":"Neural Comput."},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of the 25th International Conference on Machine Learning, pp. 160\u2013167. ACM (2008)","DOI":"10.1145\/1390156.1390177"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Deng, L., et al.: Recent advances in deep learning for speech research at microsoft. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8604\u20138608. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Ding, C., et al.: C IR CNN: accelerating and compressing deep neural networks using block-circulant weight matrices. In: Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 395\u2013408. ACM (2017)","DOI":"10.1145\/3123939.3124552"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fowers, J., Brown, G., Cooke, P., Stitt, G.: A performance and energy comparison of FPGAs, GPUS, and multicores for sliding-window applications. In: Proceedings of the ACM\/SIGDA International Symposium on Field Programmable Gate Arrays, pp. 47\u201356. ACM (2012)","DOI":"10.1145\/2145694.2145704"},{"key":"2_CR12","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., Narayanan, P.: Deep learning with limited numerical precision. In: Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pp. 1737\u20131746 (2015)"},{"key":"2_CR13","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)"},{"key":"2_CR14","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)"},{"issue":"11","key":"2_CR15","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., Yang, Y., Feng, M., Chakradhar, S., Zhou, H.: Optimizing memory efficiency for deep convolutional neural networks on GPUS. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 633\u2013644. IEEE (2016)","DOI":"10.1109\/SC.2016.53"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Laius: an 8-bit fixed-point CNN hardware inference engine. In: 2017 15th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), pp. 143\u2013150. IEEE (2017)","DOI":"10.1109\/ISPA\/IUCC.2017.00030"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Reagen, B., et al.: Minerva: enabling low-power, highly-accurate deep neural network accelerators. In: Proceedings of the 43rd International Symposium on Computer Architecture, pp. 267\u2013278. IEEE Press (2016)","DOI":"10.1109\/ISCA.2016.32"},{"issue":"1","key":"2_CR19","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/L-CA.2011.4","volume":"10","author":"P Rosenfeld","year":"2011","unstructured":"Rosenfeld, P., Cooper-Balis, E., Jacob, B.: Dramsim2: a cycle accurate memory system simulator. IEEE Comput. Arch. Lett. 10(1), 16\u201319 (2011)","journal-title":"IEEE Comput. Arch. Lett."},{"key":"2_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"3","key":"2_CR21","first-page":"513","volume":"36","author":"C Wang","year":"2017","unstructured":"Wang, C., Gong, L., Qi, Y., Li, X., Xie, Y., Zhou, X.: Dlau: a scalable deep learning accelerator unit on FPGA. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 36(3), 513\u2013517 (2017)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Wei, X., et al.: Automated systolic array architecture synthesis for high throughput CNN inference on FPGAs. In: 2017 54th ACM\/EDAC\/IEEE Design Automation Conference (DAC), pp. 1\u20136. IEEE (2017)","DOI":"10.1145\/3061639.3062207"}],"container-title":["Communications in Computer and Information Science","Advanced Computer Architecture"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-2423-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T03:11:47Z","timestamp":1751857907000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-13-2423-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9789811324222","9789811324239"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-2423-9_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"ACA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Conference on Advanced Computer Architecture","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aca2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/aca2018.tcarch.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}