{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:27:00Z","timestamp":1750220820273,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,9,7]]},"DOI":"10.1145\/3386263.3406925","type":"proceedings-article","created":{"date-parts":[[2020,9,4]],"date-time":"2020-09-04T21:34:23Z","timestamp":1599255263000},"page":"21-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["On-chip Memory Optimized CNN Accelerator with Efficient Partial-sum Accumulation"],"prefix":"10.1145","author":[{"given":"Hongjie","family":"Xu","sequence":"first","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Shiomi","sequence":"additional","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hidetoshi","family":"Onodera","sequence":"additional","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,7]]},"reference":[{"issue":"1","key":"e_1_3_2_2_1_1","first-page":"436","article-title":"Deep learning","volume":"521","author":"Yann L.","year":"2015","unstructured":"L. Yann , B. Yoshua , and H. Geoffrey , \" Deep learning ,\" Nature , vol. 521 , no. 1 , pp. 436 -- 444 , May 2015 . L. Yann, B. Yoshua, and H. Geoffrey, \"Deep learning,\" Nature, vol. 521, no. 1, pp. 436--444, May 2015.","journal-title":"Nature"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3294007"},{"volume-title":"Neural compute stick 2. [Online]. Available: https:\/\/software.intel.com\/en-us\/articles\/OpenVINO-RelNotes","year":"2019","key":"e_1_3_2_2_3_1","unstructured":"Intel. ( 2019 ) Neural compute stick 2. [Online]. Available: https:\/\/software.intel.com\/en-us\/articles\/OpenVINO-RelNotes Intel. (2019) Neural compute stick 2. [Online]. Available: https:\/\/software.intel.com\/en-us\/articles\/OpenVINO-RelNotes"},{"volume-title":"Edge tpu. [Online]. Available: https:\/\/cloud.google.com\/edge-tpu\/","year":"2019","key":"e_1_3_2_2_4_1","unstructured":"Google. ( 2019 ) Edge tpu. [Online]. Available: https:\/\/cloud.google.com\/edge-tpu\/ Google. (2019) Edge tpu. [Online]. Available: https:\/\/cloud.google.com\/edge-tpu\/"},{"issue":"484","key":"e_1_3_2_2_5_1","first-page":"484","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"S. D. H. A.","year":"2016","unstructured":"S. D. H. A. et al , \" Mastering the game of go with deep neural networks and tree search ,\" Nature , vol. 529 , no. 484 , p. 484 -- 489 , Jan 2016 . S. D. H. A. et al, \"Mastering the game of go with deep neural networks and tree search,\" Nature, vol. 529, no. 484, p. 484--489, Jan 2016.","journal-title":"Nature"},{"key":"e_1_3_2_2_6_1","first-page":"04861","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","volume":"1704","author":"Howard A. G.","year":"2017","unstructured":"A. G. Howard , M. Zhu , B. Chen , D. Kalenichenko , W. Wang , T. Weyand , M. Andreetto , and H. Adam , \" Mobilenets: Efficient convolutional neural networks for mobile vision applications ,\" CoRR , vol. abs\/ 1704 . 04861 , 2017 . [Online]. Available: http:\/\/arxiv.org\/abs\/1704.04861 A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, \"Mobilenets: Efficient convolutional neural networks for mobile vision applications,\" CoRR, vol. abs\/1704.04861, 2017. [Online]. Available: http:\/\/arxiv.org\/abs\/1704.04861","journal-title":"CoRR"},{"key":"e_1_3_2_2_7_1","first-page":"1","volume-title":"June 2015","author":"Szegedy C.","unstructured":"C. Szegedy , Wei Liu , Yangqing Jia , P. Sermanet , S. Reed , D. Anguelov , D. Erhan , V. Vanhoucke , and A. Rabinovich , \" Going deeper with convolutions,\" in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , June 2015 , pp. 1 -- 9 . C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, \"Going deeper with convolutions,\" in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015, pp. 1--9."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_2_9_1","first-page":"281","volume-title":"Minimizing computation in convolutional neural networks,\" in Artificial Neural Networks and Machine Learning -- ICANN","author":"Cong J.","year":"2014","unstructured":"J. Cong and B. Xiao , \" Minimizing computation in convolutional neural networks,\" in Artificial Neural Networks and Machine Learning -- ICANN 2014 . Cham : Springer International Publishing , 2014, pp. 281 -- 290 . J. Cong and B. Xiao, \"Minimizing computation in convolutional neural networks,\" in Artificial Neural Networks and Machine Learning -- ICANN 2014. Cham: Springer International Publishing, 2014, pp. 281--290."},{"key":"e_1_3_2_2_10_1","first-page":"218","volume-title":"et al, \"Unpu: A 50.6tops\/w unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision,\" 2018 IEEE International Solid - State Circuits Conference - (ISSCC)","author":"J.","year":"2018","unstructured":"J. L. et al, \"Unpu: A 50.6tops\/w unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision,\" 2018 IEEE International Solid - State Circuits Conference - (ISSCC) , pp. 218 -- 220 , 2018 . J. L. et al, \"Unpu: A 50.6tops\/w unified deep neural network accelerator with 1b-to-16b fully-variable weight bit-precision,\" 2018 IEEE International Solid - State Circuits Conference - (ISSCC), pp. 218--220, 2018."},{"key":"e_1_3_2_2_11_1","first-page":"1","volume-title":"June 2017","author":"N. P. J.","unstructured":"N. P. J. et al, \"In-datacenter performance analysis of a tensor processing unit,\" in 2017 ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA) , June 2017 , pp. 1 -- 12 . N. P. J. et al, \"In-datacenter performance analysis of a tensor processing unit,\" in 2017 ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), June 2017, pp. 1--12."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2018.2840092"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2636225"},{"key":"e_1_3_2_2_14_1","first-page":"07928","article-title":"Eyeriss v2: A flexible and high-performance accelerator for emerging deep neural networks","volume":"1807","author":"Chen Y.","year":"2018","unstructured":"Y. Chen , J. S. Emer , and V. Sze , \" Eyeriss v2: A flexible and high-performance accelerator for emerging deep neural networks ,\" CoRR , vol. abs\/ 1807 . 07928 , 2018 . [Online]. Available: http:\/\/arxiv.org\/abs\/1807.07928 Y. Chen, J. S. Emer, and V. Sze, \"Eyeriss v2: A flexible and high-performance accelerator for emerging deep neural networks,\" CoRR, vol. abs\/1807.07928, 2018. [Online]. Available: http:\/\/arxiv.org\/abs\/1807.07928","journal-title":"CoRR"},{"key":"e_1_3_2_2_15_1","first-page":"1","volume-title":"June 2016","author":"Albericio J.","unstructured":"J. Albericio , P. Judd , T. Hetherington , T. Aamodt , N. E. Jerger , and A. Moshovos , \" Cnvlutin: Ineffectual-neuron-free deep neural network computing,\" in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) , June 2016 , pp. 1 -- 13 . J. Albericio, P. Judd, T. Hetherington, T. Aamodt, N. E. Jerger, and A. Moshovos, \"Cnvlutin: Ineffectual-neuron-free deep neural network computing,\" in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), June 2016, pp. 1--13."},{"key":"e_1_3_2_2_16_1","first-page":"92","volume-title":"June 2015","author":"Du Z.","unstructured":"Z. Du , R. Fasthuber , T. Chen , P. Ienne , L. Li , T. Luo , X. Feng , Y. Chen , and O. Temam , \" Shidiannao: Shifting vision processing closer to the sensor,\" in 2015 ACM\/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA) , June 2015 , pp. 92 -- 104 . Z. Du, R. Fasthuber, T. Chen, P. Ienne, L. Li, T. Luo, X. Feng, Y. Chen, and O. Temam, \"Shidiannao: Shifting vision processing closer to the sensor,\" in 2015 ACM\/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA), June 2015, pp. 92--104."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2017.2757036"},{"key":"e_1_3_2_2_18_1","first-page":"1","volume-title":"Feb","author":"Park S.","year":"2015","unstructured":"S. Park , K. Bong , D. Shin , J. Lee , S. Choi , and H. Yoo , \" 4.6 a1.93tops\/w scalable deep learning\/inference processor with tetra-parallel mimd architecture for big-data applications,\" in 2015 IEEE International Solid-State Circuits Conference - (ISSCC) Digest of Technical Papers , Feb 2015 , pp. 1 -- 3 . S. Park, K. Bong, D. Shin, J. Lee, S. Choi, and H. Yoo, \"4.6 a1.93tops\/w scalable deep learning\/inference processor with tetra-parallel mimd architecture for big-data applications,\" in 2015 IEEE International Solid-State Circuits Conference - (ISSCC) Digest of Technical Papers, Feb 2015, pp. 1--3."},{"key":"e_1_3_2_2_19_1","volume-title":"A 1.06-to-5.09 tops\/w reconfigurable hybrid-neural-network processor for deep learning applications,\" 2017 Symposium on VLSI Circuits","author":"Yin S.","year":"2017","unstructured":"S. Yin , P. Ouyang , S. Tang , F. Tu , X. Li , L. Liu , and S. Wei , \" A 1.06-to-5.09 tops\/w reconfigurable hybrid-neural-network processor for deep learning applications,\" 2017 Symposium on VLSI Circuits , pp. C26--C27, 2017 . S. Yin, P. Ouyang, S. Tang, F. Tu, X. Li, L. Liu, and S. Wei, \"A 1.06-to-5.09 tops\/w reconfigurable hybrid-neural-network processor for deep learning applications,\" 2017 Symposium on VLSI Circuits, pp. C26--C27, 2017."},{"key":"e_1_3_2_2_20_1","first-page":"06873","article-title":"MEC: memory-efficient convolution for deep neural network","volume":"1706","author":"Cho M.","year":"2017","unstructured":"M. Cho and D. Brand , \" MEC: memory-efficient convolution for deep neural network ,\" CoRR , vol. abs\/ 1706 . 06873 , 2017 . [Online]. Available: http:\/\/arxiv.org\/abs\/1706.06873 M. Cho and D. Brand, \"MEC: memory-efficient convolution for deep neural network,\" CoRR, vol. abs\/1706.06873, 2017. [Online]. Available: http:\/\/arxiv.org\/abs\/1706.06873","journal-title":"CoRR"},{"key":"e_1_3_2_2_21_1","first-page":"237","volume-title":"Optimization and Simulation (PATMOS). IEEE","author":"Xu H.","year":"2018","unstructured":"H. Xu , J. Shiomi , T. Ishihara , and H. Onodera , \" Maximizing Energy Efficiency of on-Chip Caches Exploiting Hybrid Memory Structure,\" in 2018 28th International Symposium on Power and Timing Modeling , Optimization and Simulation (PATMOS). IEEE , July 2018 , pp. 237 -- 242 . H. Xu, J. Shiomi, T. Ishihara, and H. Onodera, \"Maximizing Energy Efficiency of on-Chip Caches Exploiting Hybrid Memory Structure,\" in 2018 28th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS). IEEE, July 2018, pp. 237--242."},{"key":"e_1_3_2_2_22_1","first-page":"1097","volume-title":"Imagenet classification with deep convolutional neural networks,\" in Advances in Neural Information Processing Systems 25","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky , I. Sutskever , and G. E. Hinton , \" Imagenet classification with deep convolutional neural networks,\" in Advances in Neural Information Processing Systems 25 , F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds. Curran Associates, Inc. , 2012 , pp. 1097 -- 1105 . A. Krizhevsky, I. Sutskever, and G. E. Hinton, \"Imagenet classification with deep convolutional neural networks,\" in Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2012, pp. 1097--1105."},{"key":"e_1_3_2_2_23_1","first-page":"770","volume-title":"June 2016","author":"He K.","unstructured":"K. He , X. Zhang , S. Ren , and J. Sun , \" Deep residual learning for image recognition,\" in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , June 2016 , pp. 770 -- 778 . K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016, pp. 770--778."},{"key":"e_1_3_2_2_24_1","volume-title":"Very deep convolutional networks for large-scale image recognition,\" arXiv 1409.1556, 09","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman , \" Very deep convolutional networks for large-scale image recognition,\" arXiv 1409.1556, 09 2014 . K. Simonyan and A. Zisserman, \"Very deep convolutional networks for large-scale image recognition,\" arXiv 1409.1556, 09 2014."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/4.509850"}],"event":{"name":"GLSVLSI '20: Great Lakes Symposium on VLSI 2020","acronym":"GLSVLSI '20","location":"Virtual Event China"},"container-title":["Proceedings of the 2020 on Great Lakes Symposium on VLSI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386263.3406925","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3386263.3406925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:13Z","timestamp":1750201993000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3386263.3406925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,7]]},"references-count":25,"alternative-id":["10.1145\/3386263.3406925","10.1145\/3386263"],"URL":"https:\/\/doi.org\/10.1145\/3386263.3406925","relation":{},"subject":[],"published":{"date-parts":[[2020,9,7]]},"assertion":[{"value":"2020-09-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}