{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:09Z","timestamp":1750220289604,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["109-2221-E-006-215-MY3"],"award-info":[{"award-number":["109-2221-E-006-215-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3477314.3507090","type":"proceedings-article","created":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T00:37:36Z","timestamp":1651883856000},"page":"116-123","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["RAM"],"prefix":"10.1145","author":[{"given":"Chien-Chung","family":"Ho","sequence":"first","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}]},{"given":"Wei-Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Macronix International Co., Ltd., Hsinchu, Taiwan"}]},{"given":"Szu-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"National Chung Cheng University, Chiayi, Taiwan"}]},{"given":"Yung-Chun","family":"Li","sequence":"additional","affiliation":[{"name":"Macronix International Co., Ltd., Hsinchu, Taiwan"}]},{"given":"Kun-Chi","family":"Chiang","sequence":"additional","affiliation":[{"name":"Macronix International Co., Ltd., Hsinchu, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2022,5,6]]},"reference":[{"volume-title":"TensorFlow: A System for Large-scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi M.","key":"e_1_3_2_1_1_1","unstructured":"M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng. 2016. TensorFlow: A System for Large-scale Machine Learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). 265--283. https:\/\/www.usenix.org\/system\/files\/conference\/osdi16\/osdi16-abadi.pdf"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2018.2825145"},{"key":"e_1_3_2_1_3_1","volume-title":"Butterfly Transform: An Efficient FFT Based Neural Architecture Design. CoRR abs\/1906.02256","author":"Alizadeh K.","year":"2019","unstructured":"K. Alizadeh, A. Farhadi, and M. Rastegari. 2019. Butterfly Transform: An Efficient FFT Based Neural Architecture Design. CoRR abs\/1906.02256 (2019)."},{"volume-title":"PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA). 27--39","author":"Chi P.","key":"e_1_3_2_1_4_1","unstructured":"P. Chi, S. Li, C. Xu, T. Zhang, J. Zhao, Y. Liu, Y. Wang, and Y. Xie. 2016. PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA). 27--39."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2017.2746342"},{"volume-title":"Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '17)","author":"Han S.","key":"e_1_3_2_1_6_1","unstructured":"S. Han, J. Kang, H. Mao, Y. Hu, X. Li, Y. Li, D. Xie, H. Luo, S. Yao, Y. Wang, H. Yang, and W. J. Dally. 2017. ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA. In Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA '17). 75--84."},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. arXiv preprint arXiv:1510.00149","author":"Han S.","year":"2015","unstructured":"S. Han, H. Mao, and W. J. Dally. 2015. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1107\/S0021889888014487"},{"key":"e_1_3_2_1_9_1","unstructured":"F. N. Iandola M. W. Moskewicz K. Ashraf S. Han W. J. Dally and K. Keutzer. 2016. SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and <1MB Model Size. CoRR abs\/1602.07360 (2016)."},{"key":"e_1_3_2_1_10_1","unstructured":"W. Jiang E. Sha X. Zhang L. Yang Q. Zhuge Y. Shi and J. Hu. 2019. Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference. CoRR abs\/1907.08985 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012250"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2015.7059057"},{"key":"e_1_3_2_1_13_1","unstructured":"Y. Kim E. Park S. Yoo T. Choi L. Yang and D. Shin. 2015. Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications. arXiv preprint arXiv:1511.06530 (2015)."},{"key":"e_1_3_2_1_14_1","unstructured":"A. Krizhevsky V. Nair and G. Hinton. 2009. CIFAR-10 (Canadian Institute for Advanced Research). (2009). http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555758"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555758"},{"volume-title":"Proceedings of the Conference on Design, Automation & Test in Europe (DATE '14)","author":"Li B.","key":"e_1_3_2_1_18_1","unstructured":"B. Li, S. Shan, Y. Hu, and X. Li. 2014. Partial-SET: Write Speedup of PCM Main Memory. In Proceedings of the Conference on Design, Automation & Test in Europe (DATE '14). 53:1--53:4."},{"volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1045--1050","author":"Lin S.","key":"e_1_3_2_1_19_1","unstructured":"S. Lin, N. Liu, M. Nazemi, H. Li, C. Ding, Y. Wang, and M. Pedram. 2018. FFT-based deep learning deployment in embedded systems. In 2018 Design, Automation Test in Europe Conference Exhibition (DATE). 1045--1050."},{"volume-title":"2019 IEEE International Electron Devices Meeting (IEDM). 38","author":"Lue H.","key":"e_1_3_2_1_20_1","unstructured":"H. Lue, P. Hsu, M. Wei, T. Yeh, P. Du, W. Chen, K. Wang, and C. Lu. 2019. Optimal Design Methods to Transform 3D NAND Flash into a High-Density, High-Bandwidth and Low-Power Nonvolatile Computing in Memory (nvCIM) Accelerator for Deep-Learning Neural Networks (DNN). In 2019 IEEE International Electron Devices Meeting (IEDM). 38.1.1--38.1.4."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858360"},{"volume-title":"Proceedings of the 27th international conference on machine learning (ICML-10)","author":"Nair V.","key":"e_1_3_2_1_22_1","unstructured":"V. Nair and G. E. Hinton. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In Proceedings of the 27th international conference on machine learning (ICML-10). 807--814."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366231.2337203"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/ab37b6"},{"key":"e_1_3_2_1_26_1","unstructured":"K. Simonyan and A. Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2014)."},{"volume-title":"Going Deeper with Convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1--9.","author":"Szegedy C.","key":"e_1_3_2_1_27_1","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going Deeper with Convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1--9."},{"key":"e_1_3_2_1_28_1","volume-title":"Fast Convolutional Nets With fbfft: A GPU Performance Evaluation. arXiv preprint arXiv:1412.7580","author":"Vasilache N.","year":"2014","unstructured":"N. Vasilache, J. Johnson, M. Mathieu, S. Chintala, S. Piantino, and Y. LeCun. 2014. Fast Convolutional Nets With fbfft: A GPU Performance Evaluation. arXiv preprint arXiv:1412.7580 (2014)."},{"volume-title":"Parallel Multi Channel Convolution Using General Matrix Multiplication. In 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP). 19--24","author":"Vasudevan A.","key":"e_1_3_2_1_29_1","unstructured":"A. Vasudevan, A. Anderson, and D. Gregg. 2017. Parallel Multi Channel Convolution Using General Matrix Multiplication. In 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP). 19--24."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3358191"},{"key":"e_1_3_2_1_31_1","unstructured":"W. Wen C. Wu Y. Wang Y. Chen and H. Li. 2016. Learning Structured Sparsity in Deep Neural Networks. In Advances in Neural Information Processing Systems 29. 2074--2082."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858459"}],"event":{"name":"SAC '22: The 37th ACM\/SIGAPP Symposium on Applied Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"location":"Virtual Event","acronym":"SAC '22"},"container-title":["Proceedings of the 37th ACM\/SIGAPP Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507090","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477314.3507090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:28Z","timestamp":1750188688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477314.3507090"}},"subtitle":["exploiting restrained and approximate management for enabling neural network training on NVM-based systems"],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":32,"alternative-id":["10.1145\/3477314.3507090","10.1145\/3477314"],"URL":"https:\/\/doi.org\/10.1145\/3477314.3507090","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-05-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}