{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:37:42Z","timestamp":1783060662886,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":96,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,14]],"date-time":"2017-10-14T00:00:00Z","timestamp":1507939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0013553"],"award-info":[{"award-number":["DE-SC0013553"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Samsung Semiconductor Inc."},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1719160"],"award-info":[{"award-number":["1719160"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,14]]},"DOI":"10.1145\/3123939.3123977","type":"proceedings-article","created":{"date-parts":[[2017,11,20]],"date-time":"2017-11-20T14:31:12Z","timestamp":1511188272000},"page":"288-301","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":277,"title":["DRISA"],"prefix":"10.1145","author":[{"given":"Shuangchen","family":"Li","sequence":"first","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimin","family":"Niu","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krishna T.","family":"Malladi","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bob","family":"Brennan","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,10,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Revision 1506, IC Knowledge LLC.","year":"2015","unstructured":"2015. IC Cost and Price Model , Revision 1506, IC Knowledge LLC. ( 2015 ). http:\/\/www.icknowledge.com\/ 2015. IC Cost and Price Model, Revision 1506, IC Knowledge LLC. (2015). http:\/\/www.icknowledge.com\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2016. 8Gb B-die DDR4 SDRAM. (2016). http:\/\/ww.samsung.corn\/semiconductor\/global\/file\/product\/2016\/06\/DS_K4A8G085WB-B_Rev1_61-0.pdf  2016. 8Gb B-die DDR4 SDRAM. (2016). http:\/\/ww.samsung.corn\/semiconductor\/global\/file\/product\/2016\/06\/DS_K4A8G085WB-B_Rev1_61-0.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"2016. NVIDIA TITAN X (pascal). (2016). http:\/\/www.geforce.com\/hardware\/10series\/titan-x-pascal  2016. NVIDIA TITAN X (pascal). (2016). http:\/\/www.geforce.com\/hardware\/10series\/titan-x-pascal"},{"key":"e_1_3_2_1_4_1","volume-title":"Design Compiler","year":"2017","unstructured":"2017. Design Compiler , Synopsys Inc . ( 2017 ). 2017. Design Compiler, Synopsys Inc. (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"2017. Intel Instruction Set Architecture Extensions. (2017). https:\/\/software.intel.com\/en-us\/intel-isa-extensions  2017. Intel Instruction Set Architecture Extensions. (2017). https:\/\/software.intel.com\/en-us\/intel-isa-extensions"},{"key":"e_1_3_2_1_6_1","unstructured":"2017. Micron Automata Processor. (2017). https:\/\/www.micronautomata.com\/  2017. Micron Automata Processor. (2017). https:\/\/www.micronautomata.com\/"},{"key":"e_1_3_2_1_7_1","unstructured":"2017. NVIDIA cuDNN. (2017). https:\/\/developer.nvidia.com\/cudnn  2017. NVIDIA cuDNN. (2017). https:\/\/developer.nvidia.com\/cudnn"},{"key":"e_1_3_2_1_8_1","unstructured":"2017. NVIDIA System Management Interface. (2017). https:\/\/developer.nvidia.com\/nvidia-system-management-interface  2017. NVIDIA System Management Interface. (2017). https:\/\/developer.nvidia.com\/nvidia-system-management-interface"},{"key":"e_1_3_2_1_9_1","unstructured":"2017. Torch 7. (2017). http:\/\/torch.ch\/  2017. Torch 7. (2017). http:\/\/torch.ch\/"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2994149"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_2_1_13_1","first-page":"908","article-title":"Using storage cells to perform computation, (dec 2014)","volume":"8","author":"Akerib A.","year":"2014","unstructured":"A. Akerib , O. AGAM, E. Ehrman , and M. Meyassed . 2014 . Using storage cells to perform computation, (dec 2014) . US Patent 8 , 908 ,465. A. Akerib, O. AGAM, E. Ehrman, and M. Meyassed. 2014. Using storage cells to perform computation, (dec 2014). US Patent 8,908,465.","journal-title":"US Patent"},{"key":"e_1_3_2_1_14_1","first-page":"638","article-title":"In-memory computational device, (nov 2014)","volume":"14","author":"Akerib Avidan","year":"2014","unstructured":"Avidan Akerib and Eli Ehrman . 2014 . In-memory computational device, (nov 2014) . US Patent App. 14\/555 , 638 . Avidan Akerib and Eli Ehrman. 2014. In-memory computational device, (nov 2014). US Patent App. 14\/555,638.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_15_1","first-page":"419","article-title":"Non-volatile in-memory computing device, (may 2015)","volume":"14","author":"Akerib A.","year":"2015","unstructured":"A. Akerib and E. Ehrman . 2015 . Non-volatile in-memory computing device, (may 2015) . US Patent App. 14\/588 , 419 . A. Akerib and E. Ehrman. 2015. Non-volatile in-memory computing device, (may 2015). US Patent App. 14\/588,419.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750397"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2014.55"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446049"},{"key":"e_1_3_2_1_20_1","volume-title":"LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory. Computer Architecture Letters","author":"Boroumand Amirali","year":"2016","unstructured":"Amirali Boroumand , Saugata Ghose , Brandon Lucia , Kevin Hsieh , Krishna Malladi , Hongzhong Zheng , and Onur Mutlu . 2016. LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory. Computer Architecture Letters ( 2016 ), 1--1. Amirali Boroumand, Saugata Ghose, Brandon Lucia, Kevin Hsieh, Krishna Malladi, Hongzhong Zheng, and Onur Mutlu. 2016. LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory. Computer Architecture Letters (2016), 1--1."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.0010024"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_24_1","volume-title":"BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. arXiv: 1602.02830","author":"Courbariaux Matthieu","year":"2016","unstructured":"Matthieu Courbariaux and Yoshua Bengio . 2016. BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. arXiv: 1602.02830 ( 2016 ). Matthieu Courbariaux and Yoshua Bengio. 2016. BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. arXiv: 1602.02830 (2016)."},{"key":"e_1_3_2_1_25_1","volume-title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations. arXiv: 1511.00363","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux , Yoshua Bengio , and Jean-Pierre David . 2015. BinaryConnect: Training Deep Neural Networks with binary weights during propagations. arXiv: 1511.00363 ( 2015 ). Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training Deep Neural Networks with binary weights during propagations. arXiv: 1511.00363 (2015)."},{"key":"e_1_3_2_1_26_1","unstructured":"Bill Dally. 2015. The Path to Exascale. http:\/\/images.nvidia.com\/events\/sc15\/pdfs\/SC5102-path-exascale-computing.pdf. (2015).  Bill Dally. 2015. The Path to Exascale. http:\/\/images.nvidia.com\/events\/sc15\/pdfs\/SC5102-path-exascale-computing.pdf. (2015)."},{"key":"e_1_3_2_1_27_1","volume-title":"Parallel and Distributed Systems","author":"Dlugosch Paul","unstructured":"Paul Dlugosch , Dave Brown , Paul Glendenning , Michael Leventhal , and Harold Noyes . 2014. An efficient and scalable semiconductor architecture for parallel automata processing . In Parallel and Distributed Systems , IEEE Transactions on. IEEE , 99. Paul Dlugosch, Dave Brown, Paul Glendenning, Michael Leventhal, and Harold Noyes. 2014. An efficient and scalable semiconductor architecture for parallel automata processing. In Parallel and Distributed Systems, IEEE Transactions on. IEEE, 99."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_29_1","volume-title":"International Joint Conference on Neural Networks (IJCNN). IEEE, 1--10","author":"Esser Steve K.","unstructured":"Steve K. Esser , Alexander Andreopoulos , Rathinakumar Appuswamy , Pallab Datta , Davis Barch , Arnon Amir , John Arthur , Andrew Cassidy , Myron Flickner , Paul Merolla , Shyamal Chandra , Nicola Basilico , Stefano Carpin , Tom Zimmerman , Frank Zee , Rodrigo Alvarez-Icaza , Jeffrey A. Kusnitz , Theodore M. Wong , William P. Risk , Emmett McQuinn , Tapan K. Nayak , Raghavendra Singh , and Dharmendra S. Modha . 2013. Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores . In International Joint Conference on Neural Networks (IJCNN). IEEE, 1--10 . Steve K. Esser, Alexander Andreopoulos, Rathinakumar Appuswamy, Pallab Datta, Davis Barch, Arnon Amir, John Arthur, Andrew Cassidy, Myron Flickner, Paul Merolla, Shyamal Chandra, Nicola Basilico, Stefano Carpin, Tom Zimmerman, Frank Zee, Rodrigo Alvarez-Icaza, Jeffrey A. Kusnitz, Theodore M. Wong, William P. Risk, Emmett McQuinn, Tapan K. Nayak, Raghavendra Singh, and Dharmendra S. Modha. 2013. Cognitive computing systems: Algorithms and applications for networks of neurosynaptic cores. In International Joint Conference on Neural Networks (IJCNN). IEEE, 1--10."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"A 14 nm 1.1 Mb Embedded DRAM Macro With 1 ns Access","volume":"51","author":"Fredeman G.","year":"2016","unstructured":"G. Fredeman , D. W. Plass , A. Mathews , J. Viraraghavan , K. Reyer , T. J. Knips , T. Miller , E. L. Gerhard , D. Kannambadi , C. Paone , D. Lee , D. J. Rainey , M. Sperling , M. Whalen , S. Burns , R. R. Tummuru , H. Ho , A. Cestero , N. Arnold , B. A. Khan , T. Kirihata , and S. S. Iyer . 2016 . A 14 nm 1.1 Mb Embedded DRAM Macro With 1 ns Access . IEEE Journal of Solid-State Circuits 51 , 1 (jan 2016), 230--239. G. Fredeman, D. W. Plass, A. Mathews, J. Viraraghavan, K. Reyer, T. J. Knips, T. Miller, E. L. Gerhard, D. Kannambadi, C. Paone, D. Lee, D. J. Rainey, M. Sperling, M. Whalen, S. Burns, R. R. Tummuru, H. Ho, A. Cestero, N. Arnold, B. A. Khan, T. Kirihata, and S. S. Iyer. 2016. A 14 nm 1.1 Mb Embedded DRAM Macro With 1 ns Access. IEEE Journal of Solid-State Circuits 51, 1 (jan 2016), 230--239.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.22"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.51"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485939"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830788"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757412"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"e_1_3_2_1_40_1","volume-title":"Dally","author":"Han Song","year":"2015","unstructured":"Song Han , Huizi Mao , and William J . Dally . 2015 . Deep Compression : Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding . arXiv: 1510.00149 (2015). Song Han, Huizi Mao, and William J. Dally. 2015. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. arXiv: 1510.00149 (2015)."},{"key":"e_1_3_2_1_41_1","volume-title":"Deep Residual Learning for Image Recognition. arXiv: 1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2015. Deep Residual Learning for Image Recognition. arXiv: 1512.03385 ( 2015 ). Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arXiv: 1512.03385 (2015)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967958"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2006.876103"},{"key":"e_1_3_2_1_44_1","volume-title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. arXiv: 1609.07061","author":"Hubara Itay","year":"2016","unstructured":"Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , and Yoshua Bengio . 2016. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. arXiv: 1609.07061 ( 2016 ). Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations. arXiv: 1609.07061 (2016)."},{"key":"e_1_3_2_1_45_1","volume-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv: 1502.03167","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015 . Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv: 1502.03167 (2015). Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv: 1502.03167 (2015)."},{"key":"e_1_3_2_1_46_1","volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1243--1248","author":"Lee J.","unstructured":"J. Lee and J. H. Ahn and K. Choi . 2016. Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic. In Design , Automation Test in Europe Conference Exhibition (DATE). 1243--1248 . J. Lee and J. H. Ahn and K. Choi. 2016. Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic. In Design, Automation Test in Europe Conference Exhibition (DATE). 1243--1248."},{"key":"e_1_3_2_1_47_1","unstructured":"Jan Van Lunteren. 2016. Programmable Near-Memory Acceleration on ConTutto. In OpenPower Summit.  Jan Van Lunteren. 2016. Programmable Near-Memory Acceleration on ConTutto. In OpenPower Summit."},{"key":"e_1_3_2_1_48_1","volume-title":"Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1--13","author":"Ji Y.","unstructured":"Y. Ji , Y. Zhang , S. Li , P. Chi , C. Jiang , P. Qu , Y. Xie , and W. Chen . 2016. NEUTRAMS: Neural network transformation and co-design under neuromorphic hardware constraints . In Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1--13 . Y. Ji, Y. Zhang, S. Li, P. Chi, C. Jiang, P. Qu, Y. Xie, and W. Chen. 2016. NEUTRAMS: Neural network transformation and co-design under neuromorphic hardware constraints. In Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1--13."},{"key":"e_1_3_2_1_49_1","volume-title":"CMOS digital integrated circuits","author":"Kang Sung-Mo","unstructured":"Sung-Mo Kang and Yusuf Leblebici . 2003. CMOS digital integrated circuits . Tata McGraw-Hill Education . Sung-Mo Kang and Yusuf Leblebici. 2003. CMOS digital integrated circuits. Tata McGraw-Hill Education."},{"key":"e_1_3_2_1_50_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). EDA Consortium, IEEE, 33--38","author":"Chen Ke","year":"2012","unstructured":"Ke Chen , Sheng Li , Naveen Muralimanohar , Jung Ho Ahn , Jay B Brockman , and Norman P Jouppi . 2012 . CACTI-3DD: Architecture-level modeling for 3D die-stacked DRAM main memory. In Design , Automation & Test in Europe Conference & Exhibition (DATE). EDA Consortium, IEEE, 33--38 . Ke Chen, Sheng Li, Naveen Muralimanohar, Jung Ho Ahn, Jay B Brockman, and Norman P Jouppi. 2012. CACTI-3DD: Architecture-level modeling for 3D die-stacked DRAM main memory. In Design, Automation & Test in Europe Conference & Exhibition (DATE). EDA Consortium, IEEE, 33--38."},{"key":"e_1_3_2_1_51_1","volume-title":"DRAM Circuit Design: Fundamental and High-Speed Topics","author":"Keeth Brent","unstructured":"Brent Keeth , R. Jacob Baker , Brian Johnson , and Feng Lin . 2007. DRAM Circuit Design: Fundamental and High-Speed Topics ( 2 nd ed.). Wiley-IEEE Press . Brent Keeth, R. Jacob Baker, Brian Johnson, and Feng Lin. 2007. DRAM Circuit Design: Fundamental and High-Speed Topics (2nd ed.). Wiley-IEEE Press.","edition":"2"},{"key":"e_1_3_2_1_52_1","volume-title":"Evaluation. In International Conference on Computer Design (ICCD).","author":"Kevin Hsieh Saugata Ghose","year":"2016","unstructured":"Saugata Ghose Kevin Hsieh , Samira Khan , Nandita Vijaykumar , Kevin K. Chang , Amirali Boroumand and Onur Mutlu . 2016 . Accelerating Pointer Chasing in 3D-Stacked Memory: Challenges, Mechanisms , Evaluation. In International Conference on Computer Design (ICCD). Saugata Ghose Kevin Hsieh, Samira Khan, Nandita Vijaykumar, Kevin K. Chang, Amirali Boroumand and Onur Mutlu. 2016. Accelerating Pointer Chasing in 3D-Stacked Memory: Challenges, Mechanisms, Evaluation. In International Conference on Computer Design (ICCD)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/2337159.2337202"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9260(99)00006-1"},{"key":"e_1_3_2_1_56_1","volume-title":"Advances in Neural Information Processing Systems, F Pereira, C J C Burges, L Bottou, and K Q Weinberger (Eds.). Curran Associates","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012. ImageNet Classification with Deep Convolutional Neural Networks . In Advances in Neural Information Processing Systems, F Pereira, C J C Burges, L Bottou, and K Q Weinberger (Eds.). Curran Associates , Inc ., 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems, F Pereira, C J C Burges, L Bottou, and K Q Weinberger (Eds.). Curran Associates, Inc., 1097--1105."},{"key":"e_1_3_2_1_57_1","volume-title":"Deep learning. Nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun , Yoshua Bengio , and Geoffrey Hinton . 2015. Deep learning. Nature 521, 7553 ( 2015 ), 436--444. Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757501"},{"key":"e_1_3_2_1_59_1","volume-title":"Ternary Weight Networks. arXiv: 1605.04711","author":"Li Fengfu","year":"2016","unstructured":"Fengfu Li and Bin Liu . 2016. Ternary Weight Networks. arXiv: 1605.04711 ( 2016 ). Fengfu Li and Bin Liu. 2016. Ternary Weight Networks. arXiv: 1605.04711 (2016)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.42"},{"key":"e_1_3_2_1_62_1","volume-title":"Custom Integrated Circuits Conference (CICC). IEEE, 1--4.","author":"Merolla Paul","unstructured":"Paul Merolla , John Arthur , Filipp Akopyan , Nabil Imam , Rajit Manohar , and Dharmendra S. Modha . 2011. A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm . In Custom Integrated Circuits Conference (CICC). IEEE, 1--4. Paul Merolla, John Arthur, Filipp Akopyan, Nabil Imam, Rajit Manohar, and Dharmendra S. Modha. 2011. A digital neurosynaptic core using embedded crossbar memory with 45pJ per spike in 45nm. In Custom Integrated Circuits Conference (CICC). IEEE, 1--4."},{"key":"e_1_3_2_1_63_1","volume-title":"A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 6197","author":"Merolla Paul A","year":"2014","unstructured":"Paul A Merolla , John V Arthur , Rodrigo Alvarez-Icaza , Andrew S Cassidy , Jun Sawada , Filipp Akopyan , Bryan L Jackson , Nabil Imam , Chen Guo , Yutaka Nakamura , Bernard Brezzo , Ivan Vo , Steven K Esser , Rathinakumar Appuswamy , Brian Taba , Arnon Amir , Myron D Flickner , William P Risk , Rajit Manohar , and Dharmendra S Modha . 2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 6197 ( 2014 ), 668--673. Paul A Merolla, John V Arthur, Rodrigo Alvarez-Icaza, Andrew S Cassidy, Jun Sawada, Filipp Akopyan, Bryan L Jackson, Nabil Imam, Chen Guo, Yutaka Nakamura, Bernard Brezzo, Ivan Vo, Steven K Esser, Rathinakumar Appuswamy, Brian Taba, Arnon Amir, Myron D Flickner, William P Risk, Rajit Manohar, and Dharmendra S Modha. 2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345, 6197 (2014), 668--673."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522314"},{"key":"e_1_3_2_1_65_1","unstructured":"Norman P Muralimanohar Naveen and Balasubramonian Rajeev and Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP Lab. (2009) 22--31.  Norman P Muralimanohar Naveen and Balasubramonian Rajeev and Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP Lab. (2009) 22--31."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485929"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2015.2409732"},{"key":"e_1_3_2_1_68_1","unstructured":"David Harris Neil Weste. 2006. CMOS VLSI Design: A Circuits And Systems Perspective 3\/E. Pearson.  David Harris Neil Weste. 2006. CMOS VLSI Design: A Circuits And Systems Perspective 3\/E. Pearson."},{"key":"e_1_3_2_1_69_1","volume-title":"Recurrent Neural Networks With Limited Numerical Precision. arXiv: 1608.06902","author":"Ott Joachim","year":"2016","unstructured":"Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , and Yoshua Bengio . 2016. Recurrent Neural Networks With Limited Numerical Precision. arXiv: 1608.06902 ( 2016 ). Joachim Ott, Zhouhan Lin, Ying Zhang, Shih-Chii Liu, and Yoshua Bengio. 2016. Recurrent Neural Networks With Limited Numerical Precision. arXiv: 1608.06902 (2016)."},{"key":"e_1_3_2_1_70_1","volume-title":"2015 IEEE International Electron Devices Meeting (IEDM). 26","author":"Park J. M.","unstructured":"J. M. Park , Y. S. Hwang , S. W. Kim , S. Y. Han , J. S. Park , J. Kim , J. W. Seo , B. S. Kim , S. H. Shin , C. H. Cho , S. W. Nam , H. S. Hong , K. P. Lee , G. Y. Jin , and E. S. Jung . 2015. 20nm DRAM: A new beginning of another revolution . In 2015 IEEE International Electron Devices Meeting (IEDM). 26 .5.1--26.5.4. J. M. Park, Y. S. Hwang, S. W. Kim, S. Y. Han, J. S. Park, J. Kim, J. W. Seo, B. S. Kim, S. H. Shin, C. H. Cho, S. W. Nam, H. S. Hong, K. P. Lee, G. Y. Jin, and E. S. Jung. 2015. 20nm DRAM: A new beginning of another revolution. In 2015 IEEE International Electron Devices Meeting (IEDM). 26.5.1--26.5.4."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.592312"},{"key":"e_1_3_2_1_72_1","unstructured":"David A Patterson and John L Hennessy. 2013. Computer organization and design: the hardware\/software interface. Newnes.   David A Patterson and John L Hennessy. 2013. Computer organization and design: the hardware\/software interface. Newnes."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477494"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2014.54"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_2_1_77_1","volume-title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. arXiv: 1603.05279","author":"Rastegari Mohammad","year":"2016","unstructured":"Mohammad Rastegari , Vicente Ordonez , Joseph Redmon , and Ali Farhadi . 2016. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. arXiv: 1603.05279 ( 2016 ). Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. arXiv: 1603.05279 (2016)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_79_1","volume-title":"Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Systems. arXiv: 1605.06483","author":"Seshadri Vivek","year":"2016","unstructured":"Vivek Seshadri . 2016. Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Systems. arXiv: 1605.06483 ( 2016 ). Vivek Seshadri. 2016. Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Systems. arXiv: 1605.06483 (2016)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_2_1_82_1","volume-title":"Mowry","author":"Seshadri Vivek","year":"2016","unstructured":"Vivek Seshadri , Donghyuk Lee , Thomas Mullins , Hasan Hassan , Amirali Boroumand , Jeremie Kim , Michael A. Kozuch , Onur Mutlu , Phillip B. Gibbons , and Todd C . Mowry . 2016 . Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM. arXiv: 1611.09988 (2016). Vivek Seshadri, Donghyuk Lee, Thomas Mullins, Hasan Hassan, Amirali Boroumand, Jeremie Kim, Michael A. Kozuch, Onur Mutlu, Phillip B. Gibbons, and Todd C. Mowry. 2016. Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM. arXiv: 1611.09988 (2016)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195659"},{"key":"e_1_3_2_1_84_1","first-page":"108","article-title":"INTEL 1103-MOS memory taht defied cores","volume":"46","author":"Sideris George","year":"1973","unstructured":"George Sideris . 1973 . INTEL 1103-MOS memory taht defied cores . ELECTRONICS 46 , 9 (1973), 108 -- 113 . George Sideris. 1973. INTEL 1103-MOS memory taht defied cores. ELECTRONICS 46, 9 (1973), 108--113.","journal-title":"ELECTRONICS"},{"key":"e_1_3_2_1_85_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv: 1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv: 1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv: 1409.1556 (2014)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485955"},{"key":"e_1_3_2_1_87_1","volume-title":"Going Deeper with Convolutions. arXiv: 1409.4842","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy , Wei Liu , Yangqing Jia , Pierre Sermanet , Scott E. Reed , Dragomir Anguelov , Dumitru Erhan , Vincent Vanhoucke , and Andrew Rabinovich . 2014. Going Deeper with Convolutions. arXiv: 1409.4842 ( 2014 ). Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott E. Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2014. Going Deeper with Convolutions. arXiv: 1409.4842 (2014)."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/2742854.2742874"},{"key":"e_1_3_2_1_89_1","unstructured":"G. Venkatesh E. Nurvitadhi and D. Marr. 2016. Accelerating Deep Convolutional Networks using low-precision and sparsity. arXiv: 1610.00324 (2016).  G. Venkatesh E. Nurvitadhi and D. Marr. 2016. Accelerating Deep Convolutional Networks using low-precision and sparsity. arXiv: 1610.00324 (2016)."},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.73"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.42"},{"key":"e_1_3_2_1_92_1","volume-title":"Deep Image: Scaling up Image Recognition. arXiv: 1501.02876","author":"Wu Ren","year":"2015","unstructured":"Ren Wu , Shengen Yan , Yi Shan , Qingqing Dang , and Gang Sun . 2015 . Deep Image: Scaling up Image Recognition. arXiv: 1501.02876 (2015). Ren Wu, Shengen Yan, Yi Shan, Qingqing Dang, and Gang Sun. 2015. Deep Image: Scaling up Image Recognition. arXiv: 1501.02876 (2015)."},{"key":"e_1_3_2_1_93_1","volume-title":"Data Movement Aware Computation Partitioning. In International Symposium on Microarchitecture (MICRO).","author":"Mustafa Karakoy Xulong Tang Mahmut Kandemir","year":"2018","unstructured":"Mahmut Kandemir Mustafa Karakoy Xulong Tang , Orhan Kislal . 2018 . Data Movement Aware Computation Partitioning. In International Symposium on Microarchitecture (MICRO). Mahmut Kandemir Mustafa Karakoy Xulong Tang, Orhan Kislal. 2018. Data Movement Aware Computation Partitioning. In International Symposium on Microarchitecture (MICRO)."},{"key":"e_1_3_2_1_94_1","volume-title":"Thermal Feasibility of Die-Stacked Processing in Memory. In WoNDP: 2nd Workshop on Near-Data Processing, International Symposium on Microarchitecture. IEEE.","author":"Nuwan Jayasena Yasuko Eckert","year":"2014","unstructured":"Yasuko Eckert Nuwan Jayasena and Gabriel Loh . 2014 . Thermal Feasibility of Die-Stacked Processing in Memory. In WoNDP: 2nd Workshop on Near-Data Processing, International Symposium on Microarchitecture. IEEE. Yasuko Eckert Nuwan Jayasena and Gabriel Loh. 2014. Thermal Feasibility of Die-Stacked Processing in Memory. In WoNDP: 2nd Workshop on Near-Data Processing, International Symposium on Microarchitecture. IEEE."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.5555\/2665671.2665724"},{"key":"e_1_3_2_1_97_1","volume-title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. arXiv: 1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou , Zekun Ni , Xinyu Zhou , He Wen , Yuxin Wu , and Yuheng Zou . 2016. DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. arXiv: 1606.06160 ( 2016 ). Shuchang Zhou, Zekun Ni, Xinyu Zhou, He Wen, Yuxin Wu, and Yuheng Zou. 2016. DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients. arXiv: 1606.06160 (2016)."}],"event":{"name":"MICRO-50: The 50th Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Cambridge Massachusetts","acronym":"MICRO-50","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123939.3123977","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123939.3123977","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123939.3123977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:30:31Z","timestamp":1750217431000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123939.3123977"}},"subtitle":["a DRAM-based Reconfigurable In-Situ Accelerator"],"short-title":[],"issued":{"date-parts":[[2017,10,14]]},"references-count":96,"alternative-id":["10.1145\/3123939.3123977","10.1145\/3123939"],"URL":"https:\/\/doi.org\/10.1145\/3123939.3123977","relation":{},"subject":[],"published":{"date-parts":[[2017,10,14]]},"assertion":[{"value":"2017-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}