Reconfigurable processing in memory architecture based on spin orbit torque

作者: Liang Chang , Zhaohao Wang , Youguang Zhang , Weisheng Zhao

DOI: 10.1109/NANOARCH.2017.8053713

关键词:

摘要: Data intensive workloads increase significantly bandwidth and power pressures to the memory system. One possible solution is processing-in-memory (PIM) which moves several logic components into main accelerate computation. Recently, concept of processing-in-nonvolatile-memory (PINVM) was proposed against technology issue in DRAM require different metal layer. In addition, PINVM has potential mitigates thermal influence 3D-technology based PIM. Spin-orbit-torque (SOT) Magnetoresistive Random Access Memory (MRAM) one promising NVMs with high energy-efficiency, fast switching, separate read/write paths etc. this paper, we propose a reconfigurable processing-in-SOT MRAM (PISOTM) architecture integrate non-volatile memory. We extend existing interface modify controller obtained various arithmetic function. Several dataintensive are selected evaluate performance our PISOTM architecture. The simulation results show that can achieve high-speedup improvement.

参考文章(9)
Penny Li, Jinuk Luke Shin, Georgios Konstadinidis, Francis Schumacher, Venkat Krishnaswamy, Hoyeol Cho, Sudesna Dash, Robert Masleid, Chaoyang Zheng, Yuanjung David Lin, Paul Loewenstein, Heechoul Park, Vijay Srinivasan, Dawei Huang, Changku Hwang, Wenjay Hsu, Curtis McAllister, 4.2 A 20nm 32-Core 64MB L3 cache SPARC M7 processor international solid-state circuits conference. pp. 1- 3 ,(2015) , 10.1109/ISSCC.2015.7062931
L. Liu, C.-F. Pai, Y. Li, H. W. Tseng, D. C. Ralph, R. A. Buhrman, Spin-torque switching with the giant spin hall effect of tantalum Science. ,vol. 336, pp. 555- 558 ,(2012) , 10.1126/SCIENCE.1218197
Stephen W. Keckler, William J. Dally, Brucek Khailany, Michael Garland, David Glasco, GPUs and the Future of Parallel Computing IEEE Micro. ,vol. 31, pp. 7- 17 ,(2011) , 10.1109/MM.2011.89
Kejie Huang, Rong Zhao, Wei He, Yong Lian, High-Density and High-Reliability Nonvolatile Field-Programmable Gate Array With Stacked 1D2R RRAM Array IEEE Transactions on Very Large Scale Integration Systems. ,vol. 24, pp. 139- 150 ,(2016) , 10.1109/TVLSI.2015.2389260
Junwhan Ahn, Sungjoo Yoo, Onur Mutlu, Kiyoung Choi, PIM-enabled instructions: a low-overhead, locality-aware processing-in-memory architecture international symposium on computer architecture. ,vol. 43, pp. 336- 348 ,(2015) , 10.1145/2749469.2750385
Rafael Ubal, Byunghyun Jang, Perhaad Mistry, Dana Schaa, David Kaeli, Multi2Sim: a simulation framework for CPU-GPU computing international conference on parallel architectures and compilation techniques. pp. 335- 344 ,(2012) , 10.1145/2370816.2370865
Zhaohao Wang, Weisheng Zhao, Erya Deng, Jacques-Olivier Klein, Claude Chappert, Perpendicular-anisotropy magnetic tunnel junction switched by spin-Hall-assisted spin-transfer torque Journal of Physics D. ,vol. 48, pp. 065001- ,(2015) , 10.1088/0022-3727/48/6/065001
Ping Chi, Shuangchen Li, Cong Xu, Tao Zhang, Jishen Zhao, Yongpan Liu, Yu Wang, Yuan Xie, PRIME: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory international symposium on computer architecture. ,vol. 44, pp. 27- 39 ,(2016) , 10.1145/3007787.3001140
Weisheng Zhao, Wang Kang, Liang Chang, Yuqian Gao, Zhaohao Wang, Youguang Zhang, Evaluation of spin-Hall-assisted STT-MRAM for cache replacement international symposium on nanoscale architectures. pp. 73- 78 ,(2016) , 10.1145/2950067.2950107