{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:29:08Z","timestamp":1759332548767,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["JQ18013"],"award-info":[{"award-number":["JQ18013"]}]},{"name":"National Basic Research Program of China (973 Program)","award":["2015CB358800"],"award-info":[{"award-number":["2015CB358800"]}]},{"name":"National Science and Technology Major Project","award":["2018ZX01031102"],"award-info":[{"award-number":["2018ZX01031102"]}]},{"name":"National Key Research and Development Program of China","award":["2017YFA0700900,2017YFA0700902,2017YFA0700901,2017YFB1003101"],"award-info":[{"award-number":["2017YFA0700900,2017YFA0700902,2017YFA0700901,2017YFB1003101"]}]},{"name":"Key Research Projects in Frontier Science of Chinese Academy of Sciences","award":["QYZDB-SSW-JSC001"],"award-info":[{"award-number":["QYZDB-SSW-JSC001"]}]},{"name":"Transformation and Transfer of Scientific and Technological Achievements of Chinese Academy of Sciences","award":["KFJ-HGZX-013"],"award-info":[{"award-number":["KFJ-HGZX-013"]}]},{"name":"Strategic Priority Research Program of Chinese Academy of Science","award":["XDB32050200,XDC01020000"],"award-info":[{"award-number":["XDB32050200,XDC01020000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61432016,61532016,61672491,61602441,61602446,61732002,61702478,61732007,61732020"],"award-info":[{"award-number":["61432016,61532016,61672491,61602441,61602446,61732002,61702478,61732007,61732020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322226","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"788-801","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Cambricon-F"],"prefix":"10.1145","author":[{"given":"Yongwei","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Computing Technology and University of Chinese Academy of Sciences and Cambricon Tech. Ltd"}]},{"given":"Zidong","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and Cambricon Tech. Ltd"}]},{"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and Cambricon Tech. Ltd"}]},{"given":"Shaoli","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and Cambricon Tech. Ltd"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Software"}]},{"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and University of Chinese Academy of Sciences"}]},{"given":"Tianshi","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and Cambricon Tech. Ltd"}]},{"given":"Yunji","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology and University of Chinese Academy of Sciences"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"unstructured":"Google Inc. \"Cloud vision: Derive insight from your images with our powerful pretrained API models or easily train custom vision models with AutoML Vision.\" https:\/\/www.ibm.com\/thought-leadership\/summit-supercomputer\/.","key":"e_1_3_2_1_1_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"e_1_3_2_1_3_1","volume-title":"ImageNet Classification with Deep Convolutional Neural Networks,\" tech. rep","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, G. E. Hinton, I. Sutskever, and G. E. Hinton, \"ImageNet Classification with Deep Convolutional Neural Networks,\" tech. rep., 2012."},{"unstructured":"Google Inc. \"Cloud speech-to-text: Speech-to-text conversion powered by machine learning and available for short-form or long-form audio.\" https:\/\/cloud.google.com\/speech-to-text\/.","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","volume-title":"Wavenet: A generative model for raw audio,\" arXiv preprint arXiv:1609.03499","author":"van den Oord A.","year":"2016","unstructured":"A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, \"Wavenet: A generative model for raw audio,\" arXiv preprint arXiv:1609.03499, 2016."},{"unstructured":"Amazon \"Easily recognize famous individuals and celebrities using Amazon Rekognition.\" https:\/\/console.aws.amazon.com\/rekognition\/home.","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-01270-0_1","article-title":"Gridface: Face rectification via learning local homography transformations","author":"Zhou E.","year":"2018","unstructured":"E. Zhou, Z. Cao, and J. Sun, \"Gridface: Face rectification via learning local homography transformations,\" Lecture Notes in Computer Science, p. 3--20, 2018.","journal-title":"Lecture Notes in Computer Science"},{"unstructured":"Google Inc. \"CLOUD VIDEO INTELLIGENCE: Search and discover your media content with Cloud Video Intelligence.\" https:\/\/cloud.google.com\/video-intelligence\/.","key":"e_1_3_2_1_8_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1145\/3123266.3130141"},{"key":"e_1_3_2_1_10_1","first-page":"01870","article-title":"Personalized advertisement recommendation: A ranking approach to address the ubiquitous click sparsity problem","volume":"1603","author":"Chaudhuri S.","year":"2016","unstructured":"S. Chaudhuri, G. Theocharous, and M. Ghavamzadeh, \"Personalized advertisement recommendation: A ranking approach to address the ubiquitous click sparsity problem,\" CoRR, vol. abs\/1603.01870, 2016.","journal-title":"CoRR"},{"key":"e_1_3_2_1_11_1","first-page":"178","volume-title":"Predicting player behavior in Tomb Raider: Underworld,\" in Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games","author":"Mahlmann T.","year":"2010","unstructured":"T. Mahlmann, A. Drachen, J. Togelius, A. Canossa, and G. N. Yannakakis, \"Predicting player behavior in Tomb Raider: Underworld,\" in Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games, pp. 178--185, Aug 2010."},{"key":"e_1_3_2_1_12_1","volume-title":"Mastering the game of Go without human knowledge,\" Nature","author":"Silver D.","year":"2017","unstructured":"D. Silver, J. Schrittwieser, K. Simonyan, I. Antonoglou, A. Huang, T. Hubert, L. Baker, M. Lai, A. Bolton, Y. Chen, F. Hui, L. Sifre, G. V. D. Driessche, T. Graepel, and D. Hassabis, \"Mastering the game of Go without human knowledge,\" Nature, vol. 550, 2017."},{"unstructured":"Cambricon \"Cambricon 1H provides strong AI computing in Huawei Kirin 980.\"","key":"e_1_3_2_1_13_1"},{"unstructured":"Apple Inc. \"Get Ready for Core ML 2.\" https:\/\/developer.apple.com\/machine-learning\/.","key":"e_1_3_2_1_14_1"},{"unstructured":"NVIDIA Corporation \"NVIDIA Tesla V100 GPU Architecture \" 2018. https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf.","key":"e_1_3_2_1_15_1"},{"unstructured":"NVIDIA Corporation \"NVIDIA DGX-2H \" 2018. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/es_em\/Solutions\/Data-Center\/dgx-2\/dgx-2h-datasheet-us-nvidia-841283-r6-web.pdf.","key":"e_1_3_2_1_16_1"},{"unstructured":"Google Inc. \"What makes TPUs fine-tuned for deep learning? \" 2018. https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/what-makes-tpus-fine-tuned-for-deep-learning.","key":"e_1_3_2_1_17_1"},{"unstructured":"IBM \"The most powerful computers on the planet.\" https:\/\/www.ibm.com\/thought-leadership\/summit-supercomputer\/.","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","first-page":"109","volume-title":"A runtime reconfigurable dataflow processor for vision,\" in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Farabet C.","year":"2011","unstructured":"C. Farabet, B. Martini, B. Corda, P. Akselrod, E. Culurciello, and Y. LeCun, \"NeuFlow: A runtime reconfigurable dataflow processor for vision,\" in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 109--116, Ieee, jun 2011."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1145\/2540708.2540710"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1145\/2541940.2541967"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/2694344.2694358"},{"key":"e_1_3_2_1_23_1","first-page":"367","volume-title":"Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks,\" in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA)","author":"Chen Y.-H.","year":"2016","unstructured":"Y.-H. Chen, J. Emer, and V. Sze, \"Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks,\" in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), pp. 367--379, 2016."},{"key":"e_1_3_2_1_24_1","first-page":"246","volume-title":"Envision: A 0.26-to-10TOPS\/W subword-parallel dynamic-voltage-accuracy-frequency-scalable Convolutional Neural Network processor in 28nm FDSOI,\" IEEE International Solid-State Circuits Conference","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,\" IEEE International Solid-State Circuits Conference, vol. 60, pp. 246--247, 2017."},{"key":"e_1_3_2_1_25_1","first-page":"488","article-title":"Conv-RAM: An energy-efficient SRAM with embedded convolution computation for low-power CNN-based machine learning applications","volume":"61","author":"Biswas A.","year":"2018","unstructured":"A. Biswas and A. P. Chandrakasan, \"Conv-RAM: An energy-efficient SRAM with embedded convolution computation for low-power CNN-based machine learning applications,\" in IEEE International Solid-State Circuits Conference, vol. 61, pp. 488--490, 2018.","journal-title":"IEEE International Solid-State Circuits Conference"},{"unstructured":"NVIDIA Corporation \"Parallel Thread Execution ISA Version 6.2 \" 2018. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/index.html.","key":"e_1_3_2_1_26_1"},{"key":"e_1_3_2_1_27_1","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume":"16","author":"Abadi M.","year":"2016","unstructured":"M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al., \"Tensorflow: a system for large-scale machine learning.,\" in OSDI, vol. 16, pp. 265--283, 2016.","journal-title":"OSDI"},{"unstructured":"Huawei \"Huawei Launches HiAI 2.0 Commits to Creating the Ultimate AI App Experience.\" https:\/\/www.huawei.com\/en\/press-events\/news\/2018\/11\/huawei-hiai-2-ultimate-ai-app-experience.","key":"e_1_3_2_1_28_1"},{"unstructured":"W. Sierpi\u0144ski \"Sur une courbe cantorienne qui contient une image biunivoque et continue de toute courbe donn\u00e9e \" 1916.","key":"e_1_3_2_1_29_1"},{"key":"e_1_3_2_1_30_1","first-page":"225","article-title":"The construction of brownian motion on the sierpinski carpet","volume":"25","author":"Barlow M. T.","year":"1989","unstructured":"M. T. Barlow and R. F. Bass, \"The construction of brownian motion on the sierpinski carpet,\" Ann. Inst. H. Poincar\u00e9, vol. 25, no. 1989, pp. 225--257, 1989.","journal-title":"Ann. Inst. H. Poincar\u00e9"},{"key":"e_1_3_2_1_31_1","volume-title":"Towards Pervasive and User Staisfactory CNN across GPU Microarchitecture,\" in Proceedings of The 23rd IEEE Symposium on High Performance Computer Architecture (HPCA)","author":"Wzr W.","year":"2017","unstructured":"W. Wzr, V. Surfhvv, L. V. Ghsor, H. G. Rq, K. Hqg, D. Rq, P. D. Q. Fkdoohqjlqj, P. Ohduqlqj, H. J. L. W. Wdnhv, W. Zhhnv, W. R. Wudlq, R. Q. Irxu, and K. Hqg, \"Towards Pervasive and User Staisfactory CNN across GPU Microarchitecture,\" in Proceedings of The 23rd IEEE Symposium on High Performance Computer Architecture (HPCA), 2017."},{"key":"e_1_3_2_1_32_1","volume-title":"Towards Memory Friendly Long-Short Term Memory Networks (LSTMs) on Mobile GPUs,\" in Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Zhang X.","year":"2018","unstructured":"X. Zhang, C. Xie, J. Wang, W. Zhang, and X. Fu, \"Towards Memory Friendly Long-Short Term Memory Networks (LSTMs) on Mobile GPUs,\" in Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture, vol. 1537085, 2018."},{"doi-asserted-by":"publisher","unstructured":"P. Hill A. Jain M. Hill B. Zamirai C.-H. Hsu M. A. Laurenzano and S. Mahlke \"DeftNN: Addressing Bottlenecks for DNN Execution on GPUs via Synapse Vector Elimination and Near-compute Data Fission \" in Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture pp. 786--799 2017. 10.1145\/3123939.3123970","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3123939.3123970"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1145\/3123939.3123979"},{"key":"e_1_3_2_1_35_1","first-page":"535","volume-title":"Maximizing CNN Accelerator Efficiency Through Resource Partitioning,\" in Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA'17)","author":"Shen Y.","year":"2017","unstructured":"Y. Shen, M. Ferdman, and P. Milder, \"Maximizing CNN Accelerator Efficiency Through Resource Partitioning,\" in Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA'17), pp. 535--547, 2017."},{"key":"e_1_3_2_1_36_1","volume-title":"An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware,\" in Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture, no. 2","author":"Chen T.","year":"2018","unstructured":"T. Chen, S. Srinath, C. Batten, and G. E. Suh, \"An Architectural Framework for Accelerating Dynamic Parallel Algorithms on Reconfigurable Hardware,\" in Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture, no. 2, 2018."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1109\/MICRO.2014.58"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_38_1","DOI":"10.1145\/2996864"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_39_1","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_40_1","first-page":"1","volume-title":"In-Datacenter Performance Analysis of a Tensor Processing Unit,\" in Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA'17)","author":"Jouppi N. P.","year":"2017","unstructured":"N. P. Jouppi, C. Young, N. Patil, D. Patterson, G. Agrawal, R. Bajwa, S. Bates, S. Bhatia, N. Boden, A. Borchers, R. Boyle, P.-L. Cantin, C. Chao, C. Clark, J. Coriell, M. Daley, M. Dau, J. Dean, B. Gelb, T. V. Ghaemmaghami, R. Gottipati, W. Gulland, R. Hagmann, C. R. Ho, D. Hogberg, J. Hu, R. Hundt, D. Hurt, J. Ibarz, A. Jaffey, A. Jaworski, A. Kaplan, H. Khaitan, A. Koch, N. Kumar, S. Lacy, J. Laudon, J. Law, D. Le, C. Leary, Z. Liu, K. Lucke, A. Lundin, G. Mackean, A. Maggiore, M. Mahony, K. Miller, R. Nagarajan, R. Narayanaswami, R. Ni, K. Nix, T. Norrie, M. Omernick, N. Penukonda, A. Phelps, J. Ross, M. Ross, A. Salek, E. Samadiani, C. Severn, G. Sizikov, M. Snelham, J. Souter, D. Steinberg, A. Swing, M. Tan, G. Thorson, B. Tian, H. Toma, E. Tuttle, V. Vasudevan, R. Walter, W. Wang, E. Wilcox, and D. H. Yoon, \"In-Datacenter Performance Analysis of a Tensor Processing Unit,\" in Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA'17), pp. 1--17, 2017."},{"key":"e_1_3_2_1_41_1","volume-title":"ImageNet: A Large-Scale Hierarchical Image Database,\" in CVPR09","author":"Deng J.","year":"2009","unstructured":"J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, \"ImageNet: A Large-Scale Hierarchical Image Database,\" in CVPR09, 2009."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1145\/3007787.3001179"},{"key":"e_1_3_2_1_43_1","volume-title":"Neural Information Processing Systems Conference (NIPS)","author":"Vanhoucke V.","year":"2011","unstructured":"V. Vanhoucke, A. Senior, and M. Z. Mao, \"Improving the speed of neural networks on CPUs,\" in Deep Learning and Unsupervised Feature Learning Workshop, Neural Information Processing Systems Conference (NIPS), 2011."},{"key":"e_1_3_2_1_44_1","first-page":"2773","volume-title":"Neural Network Stream Processing Core (NnSP) for Embedded Systems,\" in 2006 IEEE International Symposium on Circuits and Systems (ISCS)","author":"Esmaeilzadeh H.","year":"2006","unstructured":"H. Esmaeilzadeh, P. Saeedi, B. Araabi, C. Lucas, and S. Fakhraie, \"Neural Network Stream Processing Core (NnSP) for Embedded Systems,\" in 2006 IEEE International Symposium on Circuits and Systems (ISCS), pp. 2773--2776, Ieee, 2006."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1006\/jpdc.1993.1087"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/1498765.1498785"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_47_1","DOI":"10.5555\/646247.685036"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.5555\/2755753.2757168"},{"key":"e_1_3_2_1_49_1","first-page":"1556","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"1409","author":"Simonyan K.","year":"2014","unstructured":"K. Simonyan and A. Zisserman, \"Very deep convolutional networks for large-scale image recognition,\" CoRR, vol. abs\/1409.1556, 2014.","journal-title":"CoRR"},{"key":"e_1_3_2_1_50_1","volume-title":"June","author":"He K.","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Deep residual learning for image recognition,\" in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016."},{"unstructured":"NVIDIA Corporation \"CUDA Toolkit Documentation v9.0.176 \" 2018. https:\/\/docs.nvidia.com\/cuda\/archive\/9.0\/.","key":"e_1_3_2_1_51_1"},{"unstructured":"NVIDIA Corporation \"NVIDIA Deep Learning SDK \" 2018. https:\/\/docs.nvidia.com\/deeplearning\/sdk\/index.html.","key":"e_1_3_2_1_52_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_53_1","DOI":"10.1145\/2370816.2370864"},{"unstructured":"NVIDIA Corporation \"NVIDIA Tesla P100 \" 2017. https:\/\/images.nvidia.com\/content\/pdf\/tesla\/whitepaper\/pascal-architecture-whitepaper.pdf.","key":"e_1_3_2_1_54_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_55_1","DOI":"10.1109\/ISCA.2018.00015"},{"key":"e_1_3_2_1_56_1","first-page":"340","volume-title":"RANA: Towards efficient neural acceleration with refresh-optimized embedded DRAM,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Tu F.","year":"2018","unstructured":"F. Tu, W. Wu, S. Yin, L. Liu, and S. Wei, \"RANA: Towards efficient neural acceleration with refresh-optimized embedded DRAM,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 340--352, June 2018."},{"key":"e_1_3_2_1_57_1","first-page":"383","volume-title":"Neural cache: Bit-serial in-cache acceleration of deep neural networks,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Eckert C.","year":"2018","unstructured":"C. Eckert, X. Wang, J. Wang, A. Subramaniyan, R. Iyer, D. Sylvester, D. Blaaauw, and R. Das, \"Neural cache: Bit-serial in-cache acceleration of deep neural networks,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 383--396, June 2018."},{"key":"e_1_3_2_1_58_1","first-page":"674","volume-title":"UCNN: Exploiting computational reuse in deep neural networks via weight repetition,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Hegde K.","year":"2018","unstructured":"K. Hegde, J. Yu, R. Agrawal, M. Yan, M. Pellauer, and C. Fletcher, \"UCNN: Exploiting computational reuse in deep neural networks via weight repetition,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 674--687, June 2018."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_59_1","DOI":"10.1109\/ISCA.2018.00061"},{"key":"e_1_3_2_1_60_1","first-page":"688","volume-title":"Energy-efficient neural network accelerator based on outlier-aware low-precision computation,\" in 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (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 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), pp. 688--698, June 2018."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_61_1","DOI":"10.1109\/ISCA.2018.00069"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_62_1","DOI":"10.1145\/3079856.3080231"},{"key":"e_1_3_2_1_63_1","first-page":"42","volume-title":"Composite-ISA Cores: Enabling Multi-ISA Heterogeneity Using a Single ISA,\" in 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Venkat A.","year":"2019","unstructured":"A. Venkat, H. Basavaraj, and D. M. Tullsen, \"Composite-ISA Cores: Enabling Multi-ISA Heterogeneity Using a Single ISA,\" in 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 42--55, Feb 2019."}],"event":{"sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"],"acronym":"ISCA '19","name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona"},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322226","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:38Z","timestamp":1750202018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322226"}},"subtitle":["machine learning computers with fractal von neumann architecture"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":63,"alternative-id":["10.1145\/3307650.3322226","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322226","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}