journal article·2022-05Open access

High On/Off Ratio Spintronic Multi‐Level Memory Unit for Deep Neural Network

Kun Zhang, Xiaotao Jia, Kaihua Cao, Jinkai Wang, Yue Zhang, Kelian Lin, Lei Chen, Xueqiang Feng, Zhenyi Zheng, Zhizhong Zhang, Youguang Zhang, Weisheng Zhao

Advanced Science· Volume 9· Issue 13

Abstract

Abstract Spintronic devices are considered as one of the most promising technologies for non‐volatile memory and computing. However, two crucial drawbacks, that is, lack of intrinsic multi‐level operation and low on/off ratio, greatly hinder their further application for advanced computing concepts, such as deep neural network (DNN) accelerator. In this paper, a spintronic multi‐level memory unit with high on/off ratio is proposed by integrating several series‐connected magnetic tunnel junctions (MTJs) with perpendicular magnetic anisotropy (PMA) and a Schottky diode in parallel. Due to the rectification effect on the PMA MTJ, an on/off ratio over 100, two orders of magnitude higher than intrinsic values, is obtained under proper proportion of alternating current and direct current. Multiple resistance states are stably achieved and can be reconfigured by spin transfer torque effect. A computing‐in‐memory architecture based DNN accelerator for image classification with the experimental parameters of this proposal to evidence its application potential is also evaluated. This work can satisfy the rigorous requirements of DNN for memory unit and promote the development of high‐accuracy and robust artificial intelligence applications.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural Networks and Reservoir Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Fert Beijing Research Institute MIIT Key Laboratory of Spintronics School of Integrated Circuit Science and Engineering Beihang University Beijing 100191 P. R. China

Beihang‐Goertek Joint Microelectronics Institute Qingdao Research Institute Beihang University Qingdao 266101 P. R. China

Beihang Hangzhou Innovation Institute Yuhang Xixi Octagon City, Yuhang District Hangzhou 310023 P. R. China

Nanoelectronics Science and Technology Center Hefei Innovation Research Institute Beihang University Hefei 230013 P. R. China

Funding

National Natural Science Foundation of China

References (41)

Show source-provided references
1. 10.1145/306538610.1145/3065386 ↗
2. 10.1109/MSP.2012.220559710.1109/MSP.2012.2205597 ↗
3. C.Chen A.Seff A.Kornhauser J.Xiao 2015 IEEE Int. Conf. Computer Vision (ICCV) IEEE Santiago Chile 2015 p. 2722.
4. 10.1109/ACCESS.2019.289688010.1109/ACCESS.2019.2896880 ↗
5. 10.1109/JAS.2019.191182510.1109/JAS.2019.1911825 ↗
6. 10.1002/adfm.20200980310.1002/adfm.202009803 ↗
7. 10.1038/s41467-020-16108-910.1038/s41467-020-16108-9 ↗
8. 10.1021/nl201040y10.1021/nl201040y ↗
9. 10.1002/aelm.20180079510.1002/aelm.201800795 ↗
10. 10.1002/aelm.20200076010.1002/aelm.202000760 ↗
11. 10.1021/acs.nanolett.9b0018010.1021/acs.nanolett.9b00180 ↗
12. 10.1038/nmat202310.1038/nmat2023 ↗
13. Q.Wang X.Wang S. H.Lee F.‐H.Meng W. D.Lu 2019 IEEE Int. Electron Devices Meeting IEEE San Francisco CA 2019 p. 14.4.1.10.1109/IEDM19573.2019.8993641 ↗
14. 10.1038/s41586-020-1942-410.1038/s41586-020-1942-4 ↗
15. 10.1038/s41928-019-0360-910.1038/s41928-019-0360-9 ↗
16. 10.1038/nature2301110.1038/nature23011 ↗
17. A. D.Patil H.Hua S.Gonugondla M.Kang N. R.Shanbhag IEEE Int. Symp. Circuits and System (ISCAS) IEEE Piscataway2019.
18. M.‐H.Wu M.‐C.Hong C.‐C.Chang P.Sahu J.‐H.Wei H.‐Y.Lee S.‐S.Sheu T.‐H.Hou2019 Symp. VLSI Technology IEEE Kyoto Japan 2019 p. T34.
19. 10.1109/JPROC.2018.279084010.1109/JPROC.2018.2790840 ↗
20. 10.1109/TVLSI.2017.277695410.1109/TVLSI.2017.2776954 ↗
21. 10.1109/LED.2017.273095910.1109/LED.2017.2730959 ↗
22. B.Chen F.Cai J.Zhou W.Ma P.Sheridan W. D.Lu 2015 IEEE. Int. Electron Devices Meeting (IEDM) IEEE Piscataway2015 p.17.5.1.10.1109/IEDM.2015.7409720 ↗
23. 10.1038/nature0693210.1038/nature06932 ↗
24. 10.1038/nnano.2015.2910.1038/nnano.2015.29 ↗
25. 10.1038/nnano.2015.2410.1038/nnano.2015.24 ↗
26. S. H.Kang C.Park 2017 IEEE. Int. Electron Devices Meeting (IEDM) IEEE San Francisco CA 2017 p. 38.2.1.10.1109/IEDM.2017.8268514 ↗
27. 10.1109/TED.2019.290693210.1109/TED.2019.2906932 ↗
28. 10.1038/s41467-018-03140-z10.1038/s41467-018-03140-z ↗
29. 10.3390/jlpea804003810.3390/jlpea8040038 ↗
30. 10.1109/TBCAS.2016.253379810.1109/TBCAS.2016.2533798 ↗
31. 10.1002/aisy.20200014310.1002/aisy.202000143 ↗
32. T.Ishigaki T.Kawahara R.Takemura K.Ono K.Ito H.Matsuoka H.Ohno 2010 Symp. VLSI Technology IEEE Honolulu HI 2010 p. 47.10.1109/VLSIT.2010.5556126 ↗
33. Y.Zhang L.Zhang W.Wen G.Sun Y.Chen 2012 IEEE/ACM Int. Conf. Computer‐Aided Design (ICCAD) IEEE San Jose CA 2012 p. 526.10.1145/2429384.2429498 ↗
34. 10.1109/JPROC.2016.252171210.1109/JPROC.2016.2521712 ↗
35. 10.1038/srep3151010.1038/srep31510 ↗
36. 10.1002/advs.20200464510.1002/advs.202004645 ↗
37. 10.1063/1.304961710.1063/1.3049617 ↗
38. 10.1038/s41928-020-0385-010.1038/s41928-020-0385-0 ↗
39. Xia L. · IEEE Trans. CAD · 2017 · 37 · 1009
40. A.Krizhevsk Master Thesis University of Toronto2009.
41. 10.3389/fnins.2019.0059310.3389/fnins.2019.00593 ↗