{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:57:52Z","timestamp":1780675072611,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T00:00:00Z","timestamp":1570838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100002790","name":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002790","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,12]]},"DOI":"10.1145\/3352460.3358295","type":"proceedings-article","created":{"date-parts":[[2019,10,11]],"date-time":"2019-10-11T11:16:45Z","timestamp":1570792605000},"page":"28-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["ShapeShifter"],"prefix":"10.1145","author":[{"given":"Alberto Delm\u00e1s","family":"Lascorz","sequence":"first","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayeh","family":"Sharify","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isak","family":"Edo","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan Malone","family":"Stuart","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omar Mohamed","family":"Awad","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Judd","sequence":"additional","affiliation":[{"name":"University of Toronto and NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mostafa","family":"Mahmoud","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milos","family":"Nikolic","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Siu","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zissis","family":"Poulos","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Moshovos","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,12]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"00930","article-title":"Mixed precision training of convolutional neural networks using integer operations","volume":"1802","author":"Das D.","year":"2018","unstructured":"D. Das, N. Mellempudi, D. Mudigere, D. D. Kalamkar, S. Avancha, K. Banerjee, S. Sridharan, K. Vaidyanathan, B. Kaul, E. Georganas, A. Heinecke, P. Dubey, J. Corbal, N. Shustrov, R. Dubtsov, E. Fomenko, and V. O. Pirogov, \"Mixed precision training of convolutional neural networks using integer operations,\" CoRR, vol. abs\/1802.00930, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_2_1","first-page":"01526","article-title":"End-to-end DNN training with block floating point arithmetic","volume":"1804","author":"Drumond M.","year":"2018","unstructured":"M. Drumond, T. Lin, M. Jaggi, and B. Falsafi, \"End-to-end DNN training with block floating point arithmetic,\" CoRR, vol. abs\/1804.01526, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_3_1","volume-title":"GPU Technology Conference.","author":"Migacz S.","unstructured":"S. Migacz, \"8-bit inference with tensorrt,\" 2017. GPU Technology Conference."},{"key":"e_1_3_2_1_4_1","unstructured":"P. Warden \"Low-precision matrix multiplication.\" https:\/\/petewarden.com 2016."},{"key":"e_1_3_2_1_5_1","first-page":"7024","article-title":"Low precision arithmetic for deep learning","volume":"1412","author":"Courbariaux M.","year":"2014","unstructured":"M. Courbariaux, Y. Bengio, and J. David, \"Low precision arithmetic for deep learning,\" CoRR, vol. abs\/1412.7024, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_6_1","first-page":"1737","volume-title":"ICML'15","author":"Gupta S.","year":"2015","unstructured":"S. Gupta, A. Agrawal, K. Gopalakrishnan, and P. Narayanan, \"Deep learning with limited numerical precision,\" in Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37, ICML'15, pp. 1737--1746, JMLR.org, 2015."},{"key":"e_1_3_2_1_7_1","first-page":"01134","article-title":"WRPN: wide reduced-precision networks","volume":"1709","author":"Mishra A. K.","year":"2017","unstructured":"A. K. Mishra, E. Nurvitadhi, J. J. Cook, and D. Marr, \"WRPN: wide reduced-precision networks,\" CoRR, vol. abs\/1709.01134, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_8_1","first-page":"7197","volume-title":"CVPR 2017","author":"Park E.","year":"2017","unstructured":"E. Park, J. Ahn, and S. Yoo, \"Weighted-entropy-based quantization for deep neural networks,\" in 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 7197--7205, 2017."},{"key":"e_1_3_2_1_9_1","first-page":"06160","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","volume":"1606","author":"Zhou S.","year":"2016","unstructured":"S. Zhou, Z. Ni, X. Zhou, H. Wen, Y. Wu, and Y. Zou, \"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients,\" CoRR, vol. abs\/1606.06160, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara I.","year":"2017","unstructured":"I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, \"Quantized neural networks: Training neural networks with low precision weights and activations,\" Journal of Machine Learning Research, vol. 18, pp. 187:1--187:30, 2017.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_11_1","first-page":"07706","article-title":"Low precision rnns: Quantizing rnns without losing accuracy","volume":"1710","author":"Kapur S.","year":"2017","unstructured":"S. Kapur, A. K. Mishra, and D. Marr, \"Low precision rnns: Quantizing rnns without losing accuracy,\" CoRR, vol. abs\/1710.07706, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_12_1","first-page":"01064","article-title":"Trained ternary quantization","volume":"1612","author":"Zhu C.","year":"2016","unstructured":"C. Zhu, S. Han, H. Mao, and W. J. Dally, \"Trained ternary quantization,\" CoRR, vol. abs\/1612.01064, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_13_1","first-page":"04711","article-title":"Ternary weight networks","volume":"1605","author":"Li F.","year":"2016","unstructured":"F. Li and B. Liu, \"Ternary weight networks,\" CoRR, vol. abs\/1605.04711, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_14_1","volume-title":"Nov.","author":"Courbariaux M.","year":"2015","unstructured":"M. Courbariaux, Y. Bengio, and J.-P. David, \"BinaryConnect: Training Deep Neural Networks with binary weights during propagations,\" ArXiv e-prints, Nov. 2015."},{"key":"e_1_3_2_1_15_1","first-page":"05279","article-title":"Xnor-net: Imagenet classification using binary convolutional neural networks","volume":"1603","author":"Rastegari M.","year":"2016","unstructured":"M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, \"Xnor-net: Imagenet classification using binary convolutional neural networks,\" CoRR, vol. abs\/1603.05279, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.01.010"},{"key":"e_1_3_2_1_17_1","first-page":"06071","article-title":"Bitwise neural networks","volume":"1601","author":"Kim M.","year":"2016","unstructured":"M. Kim and P. Smaragdis, \"Bitwise neural networks,\" CoRR, vol. abs\/1601.06071, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_18_1","first-page":"7510","volume-title":"Speech and Signal Processing (ICASSP)","author":"Kim J.","year":"2014","unstructured":"J. Kim, K. Hwang, and W. Sung, \"X1000 real-time phoneme recognition VLSI using feed-forward deep neural networks,\" in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7510--7514, May 2014."},{"key":"e_1_3_2_1_19_1","volume-title":"Envision: A 0.26-to-10tops\/w subword-parallel dynamic-voltage-accuracy-frequency-scalable convolutional neural network processor in 28nm fdsoi,\" in IEEE Solid-State Circuits Conference (ISSCC)","author":"Moons B.","year":"2017","unstructured":"B. Moons, R. Uytterhoeven, W. Dehaene, and M. Verhelst, \"Envision: A 0.26-to-10tops\/w subword-parallel dynamic-voltage-accuracy-frequency-scalable convolutional neural network processor in 28nm fdsoi,\" in IEEE Solid-State Circuits Conference (ISSCC), 2017."},{"key":"e_1_3_2_1_20_1","first-page":"01322","article-title":"Fixed point performance analysis of recurrent neural networks","volume":"1512","author":"Shin S.","year":"2015","unstructured":"S. Shin, K. Hwang, and W. Sung, \"Fixed point performance analysis of recurrent neural networks,\" CoRR, vol. abs\/1512.01322, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_21_1","volume-title":"Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets, arXiv:1511.05236v4 [cs.LG],\" arXiv.org","author":"Judd P.","year":"2015","unstructured":"P. Judd, J. Albericio, T. Hetherington, T. Aamodt, N. E. Jerger, R. Urtasun, and A. Moshovos, \"Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets, arXiv:1511.05236v4 [cs.LG],\" arXiv.org, 2015."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926294"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847265"},{"key":"e_1_3_2_1_24_1","first-page":"2849","volume-title":"ICML'16","author":"Lin D. D.","year":"2016","unstructured":"D. D. Lin, S. S. Talathi, and V. S. Annapureddy, \"Fixed point quantization of deep convolutional networks,\" in Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML'16, pp. 2849--2858, JMLR.org, 2016."},{"key":"e_1_3_2_1_25_1","first-page":"764","volume-title":"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,\" in ISCA","author":"Sharma H.","year":"2018","unstructured":"H. Sharma, J. Park, N. Suda, L. Lai, B. Chau, V. Chandra, and H. Esmaeilzadeh, \"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,\" in ISCA, pp. 764--775, IEEE Computer Society, 2018."},{"key":"e_1_3_2_1_26_1","unstructured":"Z. Song Z. Liu and D. Wang \"Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design \" in Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) the 30th innovative Applications of Artificial Intelligence (IAAI-18) and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18) New Orleans Louisiana USA February 2-7 2018 pp. 816--823 2018."},{"key":"e_1_3_2_1_27_1","first-page":"4","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks,\" in Advances in Neural Information Processing Systems 30","volume":"2017","author":"K\u00f6ster U.","year":"2017","unstructured":"U. K\u00f6ster, T. Webb, X. Wang, M. Nassar, A. K. Bansal, W. Constable, O. Elibol, S. Hall, L. Hornof, A. Khosrowshahi, C. Kloss, R. J. Pai, and N. Rao, \"Flexpoint: An adaptive numerical format for efficient training of deep neural networks,\" in Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pp. 1740--1750, 2017.","journal-title":"Annual Conference on Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi M.","year":"2015","unstructured":"M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Man\u00e9, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Vi\u00e9gas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, \"TensorFlow: Large-scale machine learning on heterogeneous systems,\" 2015. Software available from tensorflow.org."},{"key":"e_1_3_2_1_29_1","volume-title":"MICRO-49","author":"Judd P.","year":"2016","unstructured":"P. Judd, J. Albericio, T. Hetherington, T. Aamodt, and A. Moshovos, \"Stripes: Bit-serial Deep Neural Network Computing,\" in Proceedings of the 49th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO-49, 2016."},{"key":"e_1_3_2_1_30_1","first-page":"07853","article-title":"Loom: Exploiting weight and activation precisions to accelerate convolutional neural networks","volume":"1706","author":"Sharify S.","year":"2017","unstructured":"S. Sharify, A. D. Lascorz, P. Judd, and A. Moshovos, \"Loom: Exploiting weight and activation precisions to accelerate convolutional neural networks,\" CoRR, vol. abs\/1706.07853, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_31_1","first-page":"383","volume-title":"ISCA 2018","author":"Eckert C.","year":"2018","unstructured":"C. Eckert, X. Wang, J. Wang, A. Subramaniyan, R. R. Iyer, D. Sylvester, D. T. Blaauw, and R. Das, \"Neural cache: Bit-serial in-cache acceleration of deep neural networks,\" in 45th ACM\/IEEE Annual International Symposium on Computer Architecture, ISCA 2018, Los Angeles, CA, USA, June 1-6, 2018, pp. 383--396, 2018."},{"key":"e_1_3_2_1_32_1","first-page":"688","volume-title":"Energy-efficient neural network accelerator based on outlier-aware low-precision computation,\" in ISCA","author":"Park E.","year":"2018","unstructured":"E. Park, D. Kim, and S. Yoo, \"Energy-efficient neural network accelerator based on outlier-aware low-precision computation,\" in ISCA, pp. 688--698, IEEE Computer Society, 2018."},{"key":"e_1_3_2_1_33_1","volume-title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning,\" in 5th International Conference on Learning Representations (ICLR)","author":"Park J.","year":"2017","unstructured":"J. Park, S. Li, W. Wen, P. T. P. Tang, H. Li, Y. Chen, and P. Dubey, \"Faster CNNs with Direct Sparse Convolutions and Guided Pruning,\" in 5th International Conference on Learning Representations (ICLR), 2017."},{"key":"e_1_3_2_1_34_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."},{"key":"e_1_3_2_1_35_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."},{"key":"e_1_3_2_1_36_1","first-page":"03385","article-title":"Deep residual learning for image recognition","volume":"1512","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" CoRR, vol. abs\/1512.03385, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_37_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Tien-Ju","year":"2017","unstructured":"Yang, Tien-Ju and Chen, Yu-Hsin and Sze, Vivienne, \"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning,\" in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017."},{"key":"e_1_3_2_1_38_1","first-page":"07360","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size","volume":"1602","author":"Iandola F. N.","year":"2016","unstructured":"F. N. Iandola, M. W. Moskewicz, K. Ashraf, S. Han, W. J. Dally, and K. Keutzer, \"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size,\" CoRR, vol. abs\/1602.07360, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_39_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.","journal-title":"CoRR"},{"key":"e_1_3_2_1_40_1","article-title":"Semantic object classes in video: A high-definition ground truth database","author":"Brostow G. J.","unstructured":"G. J. Brostow, J. Fauqueur, and R. Cipolla, \"Semantic object classes in video: A high-definition ground truth database,\" Pattern Recognition Letters, vol. xx, no. x, pp. xx--xx, 2008.","journal-title":"Pattern Recognition Letters"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"e_1_3_2_1_43_1","first-page":"08242","article-title":"YOLO9000: better, faster, stronger","volume":"1612","author":"Redmon J.","year":"2016","unstructured":"J. Redmon and A. Farhadi, \"YOLO9000: better, faster, stronger,\" CoRR, vol. abs\/1612.08242, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"e_1_3_2_1_45_1","first-page":"860","volume-title":"Fields of experts: a framework for learning image priors,\" in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","author":"Roth S.","year":"2005","unstructured":"S. Roth and M. J. Black, \"Fields of experts: a framework for learning image priors,\" in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), vol. 2, pp. 860--867 vol. 2, June 2005."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.135"},{"key":"e_1_3_2_1_47_1","first-page":"711","volume-title":"P. Chenin, A. Cohen, C. Gout, T. Lyche, M.-L","author":"Zeyde R.","year":"2012","unstructured":"R. Zeyde, M. Elad, and M. Protter, \"On single image scale-up using sparse-representations,\" in Curves and Surfaces (J.-D. Boissonnat, P. Chenin, A. Cohen, C. Gout, T. Lyche, M.-L. Mazure, and L. Schumaker, eds.), (Berlin, Heidelberg), pp. 711--730, Springer Berlin Heidelberg, 2012."},{"key":"e_1_3_2_1_48_1","first-page":"3929","volume-title":"Learning deep cnn denoiser prior for image restoration,\" in IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhang K.","year":"2017","unstructured":"K. Zhang, W. Zuo, S. Gu, and L. Zhang, \"Learning deep cnn denoiser prior for image restoration,\" in IEEE Conference on Computer Vision and Pattern Recognition, pp. 3929--3938, 2017."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2017.2671360"},{"key":"e_1_3_2_1_50_1","first-page":"3104","volume-title":"Sequence to sequence learning with neural networks,\" in Proceedings of the 27th International Conference on Neural Information Processing Systems -","author":"Sutskever I.","year":"2014","unstructured":"I. Sutskever, O. Vinyals, and Q. V. Le, \"Sequence to sequence learning with neural networks,\" in Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS'14, (Cambridge, MA, USA), pp. 3104--3112, MIT Press, 2014."},{"key":"e_1_3_2_1_51_1","first-page":"0312","article-title":"Microsoft COCO: common objects in context","volume":"1405","author":"Lin T.","year":"2014","unstructured":"T. Lin, M. Maire, S. J. Belongie, L. D. Bourdev, R. B. Girshick, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C. L. Zitnick, \"Microsoft COCO: common objects in context,\" CoRR, vol. abs\/1405.0312, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_52_1","volume-title":"Long-term recurrent convolutional networks for visual recognition and description,\" in CVPR","author":"Donahue J.","year":"2015","unstructured":"J. Donahue, L. A. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, and T. Darrell, \"Long-term recurrent convolutional networks for visual recognition and description,\" in CVPR, 2015."},{"key":"e_1_3_2_1_53_1","first-page":"139","volume-title":"CSLDAMT '10, (Stroudsburg, PA, USA)","author":"Rashtchian C.","year":"2010","unstructured":"C. Rashtchian, P. Young, M. Hodosh, and J. Hockenmaier, \"Collecting image annotations using amazon's mechanical turk,\" in Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk, CSLDAMT '10, (Stroudsburg, PA, USA), pp. 139--147, Association for Computational Linguistics, 2010."},{"key":"e_1_3_2_1_54_1","volume-title":"ACM","author":"Wang C.","year":"2016","unstructured":"C. Wang, H. Yang, C. Bartz, and C. Meinel, \"Image captioning with deep bidirectional lstms,\" in Proceedings of the 2016 ACM on Multimedia Conference, pp. 988--997, ACM, 2016."},{"key":"e_1_3_2_1_55_1","first-page":"07289","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","volume":"1511","author":"Clevert D.","year":"2015","unstructured":"D. Clevert, T. Unterthiner, and S. Hochreiter, \"Fast and accurate deep network learning by exponential linear units (elus),\" CoRR, vol. abs\/1511.07289, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_56_1","first-page":"1026","volume-title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,\" in 2015 IEEE International Conference on Computer Vision (ICCV)","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,\" in 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026--1034, Dec 2015."},{"key":"e_1_3_2_1_57_1","first-page":"570","volume-title":"HPCA 2019","author":"Young V.","year":"2019","unstructured":"V. Young, S. Kariyappa, and M. K. Qureshi, \"Enabling transparent memorycompression for commodity memory systems,\" in 25th IEEE International Symposium on High Performance Computer Architecture, HPCA 2019, Washington, DC, USA, February 16-20, 2019, pp. 570--581, 2019."},{"key":"e_1_3_2_1_58_1","volume-title":"Memory requirements for convolutional neural network hardware accelerators,\" in IEEE International Symposium on Workload Characterization","author":"Siu K.","year":"2018","unstructured":"K. Siu, D. M. Stuart, M. Mahmoud, and A. Moshovos, \"Memory requirements for convolutional neural network hardware accelerators,\" in IEEE International Symposium on Workload Characterization, 2018."},{"key":"e_1_3_2_1_59_1","first-page":"1106","volume-title":"Proceedings of a meeting held","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: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States., pp. 1106--1114, 2012."},{"key":"e_1_3_2_1_60_1","first-page":"3531","article-title":"Return of the devil in the details: Delving deep into convolutional nets","volume":"1405","author":"Chatfield K.","year":"2014","unstructured":"K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman, \"Return of the devil in the details: Delving deep into convolutional nets,\" CoRR, vol. abs\/1405.3531, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_61_1","first-page":"03385","article-title":"Deep residual learning for image recognition","volume":"1512","author":"He K.","year":"2015","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" CoRR, vol. abs\/1512.03385, 2015.","journal-title":"CoRR"},{"key":"e_1_3_2_1_62_1","first-page":"04381","article-title":"Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation","volume":"1801","author":"Sandler M.","year":"2018","unstructured":"M. Sandler, A. G. Howard, M. Zhu, A. Zhmoginov, and L. Chen, \"Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation,\" CoRR, vol. abs\/1801.04381, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_63_1","unstructured":"Synopsys \"Design Compiler.\" http:\/\/www.synopsys.com\/Tools\/Implementation\/RTLSynthesis\/DesignCompiler\/Pages."},{"key":"e_1_3_2_1_64_1","unstructured":"N. Muralimanohar and R. Balasubramonian \"Cacti 6.0: A tool to understand large caches.\""},{"key":"e_1_3_2_1_65_1","first-page":"04070","article-title":"DNN dataflow choice is overrated","volume":"1809","author":"Yang X.","year":"2018","unstructured":"X. Yang, M. Gao, J. Pu, A. Nayak, Q. Liu, S. Bell, J. Setter, K. Cao, H. Ha, C. Kozyrakis, and M. Horowitz, \"DNN dataflow choice is overrated,\" CoRR, vol. abs\/1809.04070, 2018.","journal-title":"CoRR"},{"key":"e_1_3_2_1_66_1","volume-title":"Oct.","author":"Han S.","year":"2015","unstructured":"S. Han, H. Mao, and W. J. Dally, \"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding,\" arXiv:1510.00149 [cs], Oct. 2015. arXiv: 1510.00149."},{"key":"e_1_3_2_1_67_1","volume-title":"Fused-layer cnn accelerators,\" in 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Alwani M.","year":"2016","unstructured":"M. Alwani, H. Chen, M. Ferdman, and P. Milder, \"Fused-layer cnn accelerators,\" in 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), 2016."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_69_1","volume-title":"CMOS VLSI Design: A Circuits and Systems Perspective","author":"Weste N.","year":"2010","unstructured":"N. Weste and D. Harris, CMOS VLSI Design: A Circuits and Systems Perspective. USA: Addison-Wesley Publishing Company, 4th ed., 2010.","edition":"4"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196072"},{"key":"e_1_3_2_1_71_1","first-page":"688","volume-title":"Energy-efficient neural network accelerator based on outlier-aware low-precision computation,\" in ISCA","author":"Park E.","year":"2018","unstructured":"E. Park, D. Kim, and S. Yoo, \"Energy-efficient neural network accelerator based on outlier-aware low-precision computation,\" in ISCA, pp. 688--698, IEEE Computer Society, 2018."},{"key":"e_1_3_2_1_72_1","first-page":"243","volume-title":"ISCA 2016","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,\" in 43rd ACM\/IEEE Annual International Symposium on Computer Architecture, ISCA 2016, Seoul, South Korea, June 18-22, 2016, pp. 243--254, 2016."},{"key":"e_1_3_2_1_73_1","volume-title":"MICRO","author":"Zhou X.","year":"2018","unstructured":"X. Zhou, Z. Du, Q. Guo, C. Liu, C. Wang, X. Zhou, L. Li, T. Chen, and Y. Chen, \"Cambricon-s: Addressing irregularity in sparse neural networks through a cooperative software\/hardware approach,\" in Proceedings of the 51th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO, 2018."},{"key":"e_1_3_2_1_74_1","first-page":"05877","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","volume":"1712","author":"Jacob B.","year":"2017","unstructured":"B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, A. G. Howard, H. Adam, and D. Kalenichenko, \"Quantization and training of neural networks for efficient integer-arithmetic-only inference,\" CoRR, vol. abs\/1712.05877, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_75_1","first-page":"608","volume-title":"Munich, Germany","author":"Park E.","year":"2018","unstructured":"E. Park, S. Yoo, and P. Vajda, \"Value-aware quantization for training and inference of neural networks,\" in Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IV, pp. 608--624, 2018."},{"key":"e_1_3_2_1_76_1","first-page":"3123","volume-title":"Training deep neural networks with binary weights during propagations,\" in Advances in Neural Information Processing Systems","author":"Courbariaux M.","year":"2015","unstructured":"M. Courbariaux, Y. Bengio, and J.-P. David, \"Binaryconnect: Training deep neural networks with binary weights during propagations,\" in Advances in Neural Information Processing Systems, pp. 3123--3131, 2015."},{"key":"e_1_3_2_1_77_1","first-page":"78","volume-title":"HPCA 2018","author":"Rhu M.","year":"2018","unstructured":"M. Rhu, M. O'Connor, N. Chatterjee, J. Pool, Y. Kwon, and S. W. Keckler, \"Compressing DMA engine: Leveraging activation sparsity for training deep neural networks,\" in IEEE International Symposium on High Performance Computer Architecture, HPCA 2018, Vienna, Austria, February 24-28, 2018, pp. 78--91, 2018."},{"key":"e_1_3_2_1_78_1","first-page":"09068","article-title":"Tartan: Accelerating fully-connected and convolutional layers in deep learning networks by exploiting numerical precision variability","volume":"1707","author":"Delmas A.","year":"2017","unstructured":"A. Delmas, S. Sharify, P. Judd, and A. Moshovos, \"Tartan: Accelerating fully-connected and convolutional layers in deep learning networks by exploiting numerical precision variability,\" CoRR, vol. abs\/1707.09068, 2017.","journal-title":"CoRR"},{"key":"e_1_3_2_1_79_1","first-page":"134","volume-title":"MICRO-51, (Piscataway, NJ, USA)","author":"Mahmoud M.","year":"2018","unstructured":"M. Mahmoud, K. Siu, and A. Moshovos, \"Diffy: A d\u00c9j\u00c0 vu-free differential deep neural network accelerator,\" in Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO-51, (Piscataway, NJ, USA), pp. 134--147, IEEE Press, 2018."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1049\/el.2013.4212"},{"key":"e_1_3_2_1_81_1","first-page":"06732","article-title":"Dpred: Making typical activation values matter in deep learning computing","volume":"1804","author":"Delmas A.","year":"2018","unstructured":"A. Delmas, S. Sharify, P. Judd, M. Nikolic, and A. Moshovos, \"Dpred: Making typical activation values matter in deep learning computing,\" CoRR, vol. abs\/1804.06732, 2018.","journal-title":"CoRR"}],"event":{"name":"MICRO '52: The 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","location":"Columbus OH USA","acronym":"MICRO '52","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing","IEEE CS"]},"container-title":["Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358295","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3352460.3358295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T22:28:29Z","timestamp":1753828109000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3352460.3358295"}},"subtitle":["Enabling Fine-Grain Data Width Adaptation in Deep Learning"],"short-title":[],"issued":{"date-parts":[[2019,10,12]]},"references-count":81,"alternative-id":["10.1145\/3352460.3358295","10.1145\/3352460"],"URL":"https:\/\/doi.org\/10.1145\/3352460.3358295","relation":{},"subject":[],"published":{"date-parts":[[2019,10,12]]},"assertion":[{"value":"2019-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}