MNSIM: Simulation platform for memristor-based neuromorphic computing system
作者： Lixue Xia , Boxun Li , Tianqi Tang , Peng Gu , Xiling Yin
DOI: 10.3850/9783981537079_0549
关键词:
摘要: Memristor-based neuromorphic computing system provides a promising solution to significantly boost the power efficiency of system. has wide range design choices, such as various memristor crossbar cell designs and different parallelism degrees peripheral circuits. However, memristor-based simulator, which is able model realize an early-stage space exploration, still missing. In this paper, we develop simulation platform (MNSIM). MNSIM proposes general hierarchical structure for neuromophic system, flexible interface users customize design. also detailed reference large-scale applications. embeds estimation models area, power, latency simulate performance To estimate accuracy, behavior-level between error rate parameters considering influence interconnect lines non-ideal device factors. The our accuracy SPICE result less than 1%. Experimental results show that achieves more 7000 times speed-up compared with obtains reasonable accuracy. can further trade-off energy, latency, area among optimization.
elsevier.com
sci-hub.st 参考文章(24)
K. Kurotsuchi, Y. Sasago, N. Takaura, S. Hanzawa, A. Shima, H. Kume, T. Morikawa, T. Mine, K. Torii, Y. Fujisaki, M. Kinoshita, H. Moriya, Cross-point phase change memory with 4F 2 cell size driven by low-contact-resistivity poly-Si diode symposium on vlsi technology. pp. 24- 25 ,(2006)
Ximeng Guan, Shimeng Yu, H.-S. Philip Wong, A SPICE Compact Model of Metal Oxide Resistive Switching Memory With Variations IEEE Electron Device Letters. ,vol. 33, pp. 1405- 1407 ,(2012) , 10.1109/LED.2012.2210856
Yue Bai, Huaqiang Wu, Ye Zhang, Minghao Wu, Jinyu Zhang, Ning Deng, He Qian, Zhiping Yu, Low power W:AlOx/WOx bilayer resistive switching structure based on conductive filament formation and rupture mechanism Applied Physics Letters. ,vol. 102, pp. 173503- ,(2013) , 10.1063/1.4803462
Yuan Xie, Future memory and interconnect technologies design, automation, and test in europe. pp. 964- 969 ,(2013) , 10.5555/2485288.2485520
Boxun Li, Lixue Xia, Peng Gu, Yu Wang, Huazhong Yang, Merging the interface: power, area and accuracy co-optimization for RRAM crossbar-based mixed-signal computing system design automation conference. pp. 13- ,(2015) , 10.1145/2744769.2744870
Hadi Esmaeilzadeh, Emily Blem, Renee St. Amant, Karthikeyan Sankaralingam, Doug Burger, Dark silicon and the end of multicore scaling Proceeding of the 38th annual international symposium on Computer architecture - ISCA '11. ,vol. 39, pp. 365- 376 ,(2011) , 10.1145/2000064.2000108
Xiangyu Dong, Cong Xu, Yuan Xie, N. P. Jouppi, NVSim: A Circuit-Level Performance, Energy, and Area Model for Emerging Nonvolatile Memory IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. ,vol. 31, pp. 994- 1007 ,(2012) , 10.1109/TCAD.2012.2185930
Sung Hyun Jo, Ting Chang, Idongesit Ebong, Bhavitavya B. Bhadviya, Pinaki Mazumder, Wei Lu, Nanoscale Memristor Device as Synapse in Neuromorphic Systems Nano Letters. ,vol. 10, pp. 1297- 1301 ,(2010) , 10.1021/NL904092H
Yu Wang, Tianqi Tang, Lixue Xia, Boxun Li, Peng Gu, Huazhong Yang, Hai Li, Yuan Xie, Energy Efficient RRAM Spiking Neural Network for Real Time Classification great lakes symposium on vlsi. pp. 189- 194 ,(2015) , 10.1145/2742060.2743756
C. Cagli, D. Ielmini, F. Nardi, A. L. Lacaita, Evidence for threshold switching in the set process of NiO-based RRAM and physical modeling for set, reset, retention and disturb prediction international electron devices meeting. pp. 1- 4 ,(2008) , 10.1109/IEDM.2008.4796678