Access the full text.
Sign up today, get DeepDyve free for 14 days.
[ (2014)
DianNao: A small-footprint high-throughput accelerator for ubiquitous machine-learning19th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’14). ACM
S. Agarwal, S. Plimpton, D. Hughart, Alexander Hsia, Isaac Richter, Jonathan Cox, C. James, M. Marinella (2016)
Resistive memory device requirements for a neural algorithm accelerator2016 International Joint Conference on Neural Networks (IJCNN)
Yandong Luo, Panni Wang, Xiaochen Peng, Xiaoyu Sun, Shimeng Yu (2019)
Benchmark of Ferroelectric Transistor-Based Hybrid Precision Synapse for Neural Network AcceleratorIEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 5
S. Iyer, J. Barth, P. Parries, J. Norum, J. Rice, L. Logan, D. Hoyniak (2005)
Embedded DRAM: Technology platform for the Blue Gene/L chipIBM J. Res. Dev., 49
Fengbin Tu, Weiwei Wu, S. Yin, Leibo Liu, Shaojun Wei (2018)
RANA: Towards Efficient Neural Acceleration with Refresh-Optimized Embedded DRAM2018 ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)
Shuang Wu, Guoqi Li, F. Chen, Luping Shi (2018)
Training and Inference with Integers in Deep Neural NetworksArXiv, abs/1802.04680
Cheng-Xin Xue, Wei-Hao Chen, Je-Syu Liu, Jia-Fang Li, Wei-Yu Lin, Wei-En Lin, Jing-Hong Wang, Wei-Chen Wei, Ting-Wei Chang, Tung-Cheng Chang, Tsung-Yuan Huang, Hui-Yao Kao, Shih-Ying Wei, Yen-Cheng Chiu, Chun-Ying Lee, C. Lo, Y. King, Chorng-Jung Lin, Ren-Shuo Liu, C. Hsieh, K. Tang, Meng-Fan Chang (2019)
24.1 A 1Mb Multibit ReRAM Computing-In-Memory Macro with 14.6ns Parallel MAC Computing Time for CNN Based AI Edge Processors2019 IEEE International Solid- State Circuits Conference - (ISSCC)
Y. Kim, Sechung Oh, W. Lim, Ju-Sik Kim, Wang-Hyun Kim, Jun-Ho Jeong, Hyun-Sung Shin, Keunnam Kim, Kyung-Seop Kim, J. Park, Seongyong Park, Hye-young Kwon, K. Ah, JoonMyoung Lee, Soojeoung Park, S. Choi, H. Kang, C. Chung (2011)
Integration of 28nm MJT for 8∼16Gb level MRAM with full investigation of thermal stability2011 Symposium on VLSI Technology - Digest of Technical Papers
J.Y. Wu, Y.S. Chen, W. Khwa, S. Yu, T. Wang, J. Tseng, Y. Chih, Carlos Díaz (2018)
A 40nm Low-Power Logic Compatible Phase Change Memory Technology2018 IEEE International Electron Devices Meeting (IEDM)
Xiaochen Peng, Rui Liu, Shimeng Yu (2020)
Optimizing Weight Mapping and Data Flow for Convolutional Neural Networks on Processing-in-Memory ArchitecturesIEEE Transactions on Circuits and Systems I: Regular Papers, 67
Yun Long, Taesik Na, Prakshi Rastogi, Karthik Rao, A. Khan, S. Yalamanchili, S. Mukhopadhyay (2018)
A Ferroelectric FET based Power-efficient Architecture for Data-intensive Computing2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
Y. Song, J. Lee, H. Shin, K. Lee, K. Suh, J. Kang, S. Pyo, H. Jung, S. Hwang, G. Koh, Sechung Oh, Soojeoung Park, Jinhak Kim, Jae-Kyun Park, Ju-Sik Kim, K. Hwang, G. Jeong, K. Lee, E. Jung (2016)
Highly functional and reliable 8Mb STT-MRAM embedded in 28nm logic2016 IEEE International Electron Devices Meeting (IEDM)
(2019)
TIME: A training-inmemory architecture for RRAM-based deep neural networks
A. Kazemi, R. Rajaei, K. Ni, S. Datta, M. Niemier, X. Hu (2020)
A Hybrid FeMFET-CMOS Analog Synapse Circuit for Neural Network Training and Inference2020 IEEE International Symposium on Circuits and Systems (ISCAS)
D. Reis, S. Datta, M. Niemier, X. Hu, K. Ni, W. Chakraborty, Xunzhao Yin, M. Trentzsch, S. Dünkel, T. Melde, Johannes Müller, S. Beyer (2019)
Design and Analysis of an Ultra-Dense, Low-Leakage, and Fast FeFET-Based Random Access Memory ArrayIEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 5
Xiaoyu Sun, Panni Wang, K. Ni, S. Datta, Shimeng Yu (2018)
Exploiting Hybrid Precision for Training and Inference: A 2T-1FeFET Based Analog Synaptic Weight Cell2018 IEEE International Electron Devices Meeting (IEDM)
O. Golonzka, J. Alzate, U. Arslan, M. Bohr, P. Bai, S. BrockmanJustin, Buford Benjamin, C. Connor, N. Das, B. Doyle, T. Ghani, F. Hamzaoglu, P. Heil, P. Hentges, R. Jahan, D. Kencke, Blake Lin, M. Lu, M. Mainuddin, M. Meterelliyoz, P. Nguyen, D. Nikonov, P. O'brienKevin, J. Donnell, K. Oguz, G. OuelletteDaniel, Joodong Park, J. Pellegren, C. Puls, Pedro Quintero, T. Rahman, A. Romang, M. Sekhar, A. Selarka, M. Seth, A. Smith, A. Smith, Liqiong Wei, C. Wiegand, Z. Zhang, K. Fischer (2018)
MRAM as Embedded Non-Volatile Memory Solution for 22FFL FinFET Technology2018 IEEE International Electron Devices Meeting (IEDM)
M. Trentzsch, S. Flachowsky, Ralf Richter, Jan Paul, Berthold Reimer, Dirk Utess, S. Jansen, H. Mulaosmanovic, S. Müller, S. Slesazeck, J. Ocker, M. Noack, J. Müller, P. Polakowski, J. Schreiter, Sven Beyer, T. Mikolajick, B. Rice (2016)
A 28nm HKMG super low power embedded NVM technology based on ferroelectric FETs2016 IEEE International Electron Devices Meeting (IEDM)
[ (2011)
Integration of 28nm MJT for 8∼16Gb level MRAM with full investigation of thermal stability2011 Symposium on VLSI Technology (VLSI’11). IEEE, 2011
M. Jerry, Pai-Yu Chen, Jianchi Zhang, Pankaj Sharma, K. Ni, Shimeng Yu, S. Datta (2017)
Ferroelectric FET analog synapse for acceleration of deep neural network training2017 IEEE International Electron Devices Meeting (IEDM)
Tianshi Chen, Zidong Du, Ninghui Sun, Jia Wang, Chengyong Wu, Yunji Chen, O. Temam (2014)
DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learningProceedings of the 19th international conference on Architectural support for programming languages and operating systems
Abhishek Sharma, B. Doyle, H. Yoo, I. Tung, J. Kavalieros, M. Metz, M. Reshotko, P. Majhi, Tobias Brown-Heft, Yu-Jin Chen, V. Le (2020)
High Speed Memory Operation in Channel-Last, Back-gated Ferroelectric Transistors2020 IEEE International Electron Devices Meeting (IEDM)
Linghao Song, Xuehai Qian, Hai Li, Yiran Chen (2017)
PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)
Xue Cheng-Xin (2019)
388
Panni Wang, Zheng Wang, Xiaoyu Sun, Jae Hur, S. Datta, A. Khan, Shimeng Yu (2020)
Investigating Ferroelectric Minor Loop Dynamics and History Effect—Part I: Device CharacterizationIEEE Transactions on Electron Devices, 67
By Deng, Guoqi Li, Song Han, Luping Shi, Yuan Xie (2020)
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive SurveyProceedings of the IEEE, 108
Yandong Luo, Shimeng Yu (2020)
Accelerating Deep Neural Network In-Situ Training With Non-Volatile and Volatile Memory Based Hybrid Precision SynapsesIEEE Transactions on Computers, 69
Hongwu Jiang, Xiaochen Peng, Shanshi Huang, Shimeng Yu (2020)
CIMAT: A Compute-In-Memory Architecture for On-chip Training Based on Transpose SRAM ArraysIEEE Transactions on Computers, 69
Xiaochen Peng, Shanshi Huang, Yandong Luo, Xiaoyu Sun, Shimeng Yu (2019)
DNN+NeuroSim: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators with Versatile Device Technologies2019 IEEE International Electron Devices Meeting (IEDM)
Shihui Yin, Jae-sun Seo, Yulhwa Kim, Xu Han, H. Barnaby, Shimeng Yu, Yandong Luo, Wangxin He, Xiaoyu Sun, Jae-Joon Kim (2019)
Monolithically Integrated RRAM- and CMOS-Based In-Memory Computing Optimizations for Efficient Deep LearningIEEE Micro, 39
S. Dunkel, M. Trentzsch, R. Richter, P. Moll, C. Fuchs, O. Gehring, M. Majer, S. Wittek, B. Muller, T. Melde, H. Mulaosmanovic, S. Slesazeck, S. Müller, J. Ocker, M. Noack, D. Lohr, P. Polakowski, J. Müller, T. Mikolajick, J. Hontschel, B. Rice, J. Pellerin, S. Beyer (2017)
A FeFET based super-low-power ultra-fast embedded NVM technology for 22nm FDSOI and beyond2017 IEEE International Electron Devices Meeting (IEDM)
Panni Wang, Z. Wang, Wonbo Shim, Jae Hur, S. Datta, A. Khan, Shimeng Yu (2020)
Drain–Erase Scheme in Ferroelectric Field-Effect Transistor—Part I: Device CharacterizationIEEE Transactions on Electron Devices, 67
O. Golonzka, U. Arslan, P. Bai, M. Bohr, O. Baykan, Yao-Feng Chang, A. Chaudhari, Albert Chen, N. Das, C. English, Pulkit Jain, H. Kothari, Blake Lin, James Clarke, Christopher Connor, Tahir Ghani, F. Hamzaoglu, P. Hentges, Christopher Jezewski, I. Karpov, Roza Kotlyar, M. Metz, J. O'Donnell, G. OuelletteDaniel, Joodong Park, A. Pirkle, Pedro Quintero, D. Seghete, M. Sekhar, A. Gupta, M. Seth, Strutt Nathan, C. Wiegand, Y. Jae, Kevin Fischer (2019)
Non-Volatile RRAM Embedded into 22FFL FinFET Technology2019 Symposium on VLSI Technology
S. Ambrogio, P. Narayanan, H. Tsai, R. Shelby, I. Boybat, C. Nolfo, Severin Sidler, M. Giordano, Martina Bodini, Nathan Farinha, Benjamin Killeen, Christina Cheng, Yassine Jaoudi, G. Burr (2018)
Equivalent-accuracy accelerated neural-network training using analogue memoryNature, 558
In this article, we propose a hardware accelerator design using ferroelectric transistor (FeFET)-based hybrid precision synapse (HPS) for deep neural network (DNN) on-chip training. The drain erase scheme for FeFET programming is incorporated for both FeFET HPS design and FeFET buffer design. By using drain erase, high-density FeFET buffers can be integrated onchip to store the intermediate input-output activations and gradients, which reduces the energy consuming off-chip DRAM access. Architectural evaluation results show that the energy efficiency could be improved by 1.2× ∼ 2.1×, 3.9× ∼ 6.0× compared to the other HPS-based designs and emerging non-volatile memory baselines, respectively. The chip area is reduced by 19% ∼ 36% compared with designs using SRAM on-chip buffer even though the capacity of FeFET buffer is increased. Besides, by utilizing drain erase scheme for FeFET programming, the chip area is reduced by 11% ∼ 28.5% compared with the designs using body erase scheme.
ACM Journal on Emerging Technologies in Computing Systems (JETC) – Association for Computing Machinery
Published: Jan 12, 2022
Keywords: Deep neural network
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.