{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T14:05:48Z","timestamp":1768399548080,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"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":[[2016,6]]},"DOI":"10.1145\/2925426.2926294","type":"proceedings-article","created":{"date-parts":[[2016,6,10]],"date-time":"2016-06-10T13:04:07Z","timestamp":1465563847000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":49,"title":["Proteus"],"prefix":"10.1145","author":[{"given":"Patrick","family":"Judd","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jorge","family":"Albericio","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tayler","family":"Hetherington","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tor M.","family":"Aamodt","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Natalie Enright","family":"Jerger","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Moshovos","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"AMD GRAPHICS CORES NEXT (GCN). Whitepaper. \"https:\/\/www.amd.com\/Documents\/GCN_Architecture_whitepaper.pdf","author":"AMD.","year":"2012","unstructured":"AMD. AMD GRAPHICS CORES NEXT (GCN). Whitepaper. \"https:\/\/www.amd.com\/Documents\/GCN_Architecture_whitepaper.pdf \", 2012 . AMD. AMD GRAPHICS CORES NEXT (GCN). Whitepaper. \"https:\/\/www.amd.com\/Documents\/GCN_Architecture_whitepaper.pdf\", 2012."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178146"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581957"},{"key":"e_1_3_2_1_4_1","volume-title":"NVIDIA's Next-Gen Pascal GPU Architecture to Provide 10X Speedup for Deep Learning Apps. \"http:\/\/blogs.nvidia.com\/blog\/2015\/03\/17\/pascal\/","author":"Buck I.","year":"2015","unstructured":"I. Buck . NVIDIA's Next-Gen Pascal GPU Architecture to Provide 10X Speedup for Deep Learning Apps. \"http:\/\/blogs.nvidia.com\/blog\/2015\/03\/17\/pascal\/ \", 2015 . I. Buck. NVIDIA's Next-Gen Pascal GPU Architecture to Provide 10X Speedup for Deep Learning Apps. \"http:\/\/blogs.nvidia.com\/blog\/2015\/03\/17\/pascal\/\", 2015."},{"key":"e_1_3_2_1_5_1","volume-title":"A Block-sorting Lossless Data Compression Algorithm. Number no. 124. Digital","author":"Burrows M.","year":"1994","unstructured":"M. Burrows and D. Wheeler . A Block-sorting Lossless Data Compression Algorithm. Number no. 124. Digital , Systems Research Center , 1994 . M. Burrows and D. Wheeler. A Block-sorting Lossless Data Compression Algorithm. Number no. 124. Digital, Systems Research Center, 1994."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40763-5_51"},{"key":"e_1_3_2_1_9_1","volume-title":"Low precision arithmetic for deep learning. CoRR, abs\/1412.7024","author":"Courbariaux M.","year":"2014","unstructured":"M. Courbariaux , Y. Bengio , and J. David . Low precision arithmetic for deep learning. CoRR, abs\/1412.7024 , 2014 . M. Courbariaux, Y. Bengio, and J. David. Low precision arithmetic for deep learning. CoRR, abs\/1412.7024, 2014."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_11_1","volume-title":"Reduced-precision memory value approximation for deep learning","author":"Deng Z.","year":"2015","unstructured":"Z. Deng , C. Xu , Q. Cai , and P. Faraboschi . Reduced-precision memory value approximation for deep learning . 2015 . Z. Deng, C. Xu, Q. Cai, and P. Faraboschi. Reduced-precision memory value approximation for deep learning. 2015."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000108"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep learning with limited numerical precision. CoRR, abs\/1502.02551","author":"Gupta S.","year":"2015","unstructured":"S. Gupta , A. Agrawal , K. Gopalakrishnan , and P. Narayanan . Deep learning with limited numerical precision. CoRR, abs\/1502.02551 , 2015 . S. Gupta, A. Agrawal, K. Gopalakrishnan, and P. Narayanan. Deep learning with limited numerical precision. CoRR, abs\/1502.02551, 2015."},{"key":"e_1_3_2_1_15_1","volume-title":"EIE: efficient inference engine on compressed deep neural network. CoRR, abs\/1602.01528","author":"Han S.","year":"2016","unstructured":"S. Han , X. Liu , H. Mao , J. Pu , A. Pedram , M. A. Horowitz , and W. J. Dally . EIE: efficient inference engine on compressed deep neural network. CoRR, abs\/1602.01528 , 2016 . S. Han, X. Liu, H. Mao, J. Pu, A. Pedram, M. A. Horowitz, and W. J. Dally. EIE: efficient inference engine on compressed deep neural network. CoRR, abs\/1602.01528, 2016."},{"key":"e_1_3_2_1_16_1","volume-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs\/1510.00149","author":"Han S.","year":"2015","unstructured":"S. Han , H. Mao , and W. J. Dally . Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs\/1510.00149 , 2015 . S. Han, H. Mao, and W. J. Dally. Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding. CoRR, abs\/1510.00149, 2015."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155324"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.210171"},{"key":"e_1_3_2_1_19_1","volume-title":"Caffe model zoo. https:\/\/github.com\/BVLC\/caffe\/wiki\/Model-Zoo","author":"Jia Y.","year":"2015","unstructured":"Y. Jia . Caffe model zoo. https:\/\/github.com\/BVLC\/caffe\/wiki\/Model-Zoo , 2015 . Y. Jia. Caffe model zoo. https:\/\/github.com\/BVLC\/caffe\/wiki\/Model-Zoo, 2015."},{"key":"e_1_3_2_1_20_1","volume-title":"Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093","author":"Jia Y.","year":"2014","unstructured":"Y. Jia , E. Shelhamer , J. Donahue , S. Karayev , J. Long , R. Girshick , S. Guadarrama , and T. Darrell . Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 , 2014 . Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014."},{"key":"e_1_3_2_1_21_1","volume-title":"Nov.","author":"Judd P.","year":"2015","unstructured":"P. Judd , J. Albericio , T. Hetherington , T. Aamodt , N. Enright Jerger , R. Urtasun , and A. Moshovos . Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets. arXiv:1511.05236 {cs} , Nov. 2015 . arXiv: 1511.05236. P. Judd, J. Albericio, T. Hetherington, T. Aamodt, N. Enright Jerger, R. Urtasun, and A. Moshovos. Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets. arXiv:1511.05236 {cs}, Nov. 2015. arXiv: 1511.05236."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855060"},{"key":"e_1_3_2_1_23_1","unstructured":"A. Krizhevsky. cuda-convnet: High-performance C++\/CUDA implementation of convolutional neural networks. https:\/\/code.google.com\/p\/cuda-convnet\/.  A. Krizhevsky. cuda-convnet: High-performance C++\/CUDA implementation of convolutional neural networks. https:\/\/code.google.com\/p\/cuda-convnet\/."},{"key":"e_1_3_2_1_24_1","first-page":"1097","volume-title":"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 F. Pereira, C. Burges, L. Bottou, and K. Weinberger, editors , Advances in Neural Information Processing Systems 25 , pages 1097 -- 1105 . Curran Associates, Inc. , 2012 . A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In F. Pereira, C. Burges, L. Bottou, and K. Weinberger, editors, Advances in Neural Information Processing Systems 25, pages 1097--1105. Curran Associates, Inc., 2012."},{"key":"e_1_3_2_1_25_1","unstructured":"D. Larkin and A. Kinane. Towards hardware acceleration of neuroevolution for multimedia processing applications on mobile devices.  D. Larkin and A. Kinane. Towards hardware acceleration of neuroevolution for multimedia processing applications on mobile devices."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_27_1","volume-title":"Network in network. arXiv preprint arXiv:1312.4400","author":"Lin M.","year":"2013","unstructured":"M. Lin , Q. Chen , and S. Yan . Network in network. arXiv preprint arXiv:1312.4400 , 2013 . M. Lin, Q. Chen, and S. Yan. Network in network. arXiv preprint arXiv:1312.4400, 2013."},{"key":"e_1_3_2_1_28_1","unstructured":"N. Muralimanohar and R. Balasubramonian. CACTI 6.0: A tool to understand large caches.  N. Muralimanohar and R. Balasubramonian. CACTI 6.0: A tool to understand large caches."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370870"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2755753.2757168"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.1994.324283"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/L-CA.2011.4"},{"key":"e_1_3_2_1_33_1","volume-title":"Sept.","author":"Russakovsky O.","year":"2014","unstructured":"O. Russakovsky , J. Deng , H. Su , J. Krause , S. Satheesh , S. Ma , Z. Huang , A. Karpathy , A. Khosla , M. Bernstein , A. C. Berg , and L. Fei-Fei . ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575 {cs} , Sept. 2014 . arXiv: 1409.0575. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575 {cs}, Sept. 2014. arXiv: 1409.0575."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_35_1","volume-title":"Interspeech 2014","author":"Seide F.","year":"2014","unstructured":"F. Seide , H. Fu , J. Droppo , G. Li , and D. Yu . 1-bit stochastic gradient descent and application to data-parallel distributed training of speech dnns . In Interspeech 2014 , September 2014 . F. Seide, H. Fu, J. Droppo, G. Li, and D. Yu. 1-bit stochastic gradient descent and application to data-parallel distributed training of speech dnns. In Interspeech 2014, September 2014."},{"key":"e_1_3_2_1_36_1","volume-title":"A new concept for parallel neurocomputer architectures","author":"Strey A.","year":"1996","unstructured":"A. Strey and N. Avellana . A new concept for parallel neurocomputer architectures , 1996 . A. Strey and N. Avellana. A new concept for parallel neurocomputer architectures, 1996."},{"key":"e_1_3_2_1_37_1","unstructured":"Synopsys. Design Compiler. http:\/\/www.synopsys.com\/Tools\/Implementation\/RTLSynthesis\/DesignCompiler\/Pages\/default.aspx.  Synopsys. Design Compiler. http:\/\/www.synopsys.com\/Tools\/Implementation\/RTLSynthesis\/DesignCompiler\/Pages\/default.aspx."},{"key":"e_1_3_2_1_38_1","volume-title":"Going deeper with convolutions. CoRR, abs\/1409.4842","author":"Szegedy C.","year":"2014","unstructured":"C. Szegedy , W. Liu , Y. Jia , P. Sermanet , S. Reed , D. Anguelov , D. Erhan , V. Vanhoucke , and A. Rabinovich . Going deeper with convolutions. CoRR, abs\/1409.4842 , 2014 . C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. CoRR, abs\/1409.4842, 2014."},{"key":"e_1_3_2_1_39_1","volume-title":"Training algorithms for limited precision feedforward neural networks. Technical report","author":"Xie Y.","year":"1991","unstructured":"Y. Xie and M. A. Jabri . Training algorithms for limited precision feedforward neural networks. Technical report , 1991 . Y. Xie and M. A. Jabri. Training algorithms for limited precision feedforward neural networks. Technical report, 1991."}],"event":{"name":"ICS '16: 2016 International Conference on Supercomputing","location":"Istanbul Turkey","acronym":"ICS '16","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 2016 International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926294","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2925426.2926294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:04:26Z","timestamp":1750273466000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2925426.2926294"}},"subtitle":["Exploiting Numerical Precision Variability in Deep Neural Networks"],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":39,"alternative-id":["10.1145\/2925426.2926294","10.1145\/2925426"],"URL":"https:\/\/doi.org\/10.1145\/2925426.2926294","relation":{},"subject":[],"published":{"date-parts":[[2016,6]]},"assertion":[{"value":"2016-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}