Low‐Conductance and Multilevel CMOS‐Integrated Nanoscale Oxide Memristors
Source abstract
Abstract
Abstract Using memristors, such as oxide and phase change resistive switches, as tunable resistors to construct analog computing hardware accelerators is gaining keen attention. Such accelerators have demonstrated the potential to significantly outperform digital computers in highly relevant applications such as machine learning and image processing. However, improvements in device‐level performance of memristors, including reducing power consumption and high current–induced metal migration in interconnects, need continued developments. Nanoscaling and complementary metal‐oxide semiconductor (CMOS) integration are also of significant importance in commercialization of such accelerators. Here tantalum oxide memristors scaled down to 25 nm sizes and integrated on CMOS transistor circuits are presented. The memristor conductance is programmable with a 6 order‐of‐magnitude operating range, especially with 3‐bits below 10 µS for low current operation. The stability of such levels and the size scaling of the operating parameters are further studied. These results will aid device engineering of memristors and bolster development of neuromorphic hardware accelerators.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neuroscience and Neural Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Hewlett Packard Laboratories Hewlett Packard Enterprise Palo Alto CA 94304 USA
Funding
Intelligence Advanced Research Projects Activity
References (47)
Show source-provided references
1. 10.1038/nnano.2012.24010.1038/nnano.2012.240 ↗
2. Liu X. · 2015 · 1
3. 10.1021/nl203687n10.1021/nl203687n ↗
4. Shafiee A. · 2016 · 14
5. 10.1063/1.497118810.1063/1.4971188 ↗
6. 10.1109/JETCAS.2018.279637910.1109/JETCAS.2018.2796379 ↗
7. 10.1116/1.482702110.1116/1.4827021 ↗
8. 10.1021/nl904092h10.1021/nl904092h ↗
9. 10.1088/1361-6463/aade3f10.1088/1361-6463/aade3f ↗
10. 10.1080/23746149.2016.125958510.1080/23746149.2016.1259585 ↗
11. 10.1007/s10853-018-2134-610.1007/s10853-018-2134-6 ↗
12. 10.3390/make101000510.3390/make1010005 ↗
13. Kim Y. · 2012 · 328
14. 10.1038/nature1444110.1038/nature14441 ↗
15. 10.1109/TVLSI.2013.227771510.1109/TVLSI.2013.2277715 ↗
16. Hu M. · 2016 · 1
17. 10.1002/adma.20170591410.1002/adma.201705914 ↗
18. Chi P. · 2016 · 27
19. Tang S. · 2017 · 1
20. Yu S. · 2015 · 17.3.110.1109/IEDM.2015.7409718 ↗
21. Gu P. · 2015 · 106
22. Xu C. · 2013 · 1
23. 10.1016/j.neunet.2010.05.00110.1016/j.neunet.2010.05.001 ↗
24. 10.3389/fnins.2016.0048210.3389/fnins.2016.00482 ↗
25. 10.1038/s41928-017-0002-z10.1038/s41928-017-0002-z ↗
26. 10.1038/s41586-018-0180-510.1038/s41586-018-0180-5 ↗
27. Graves C. E. · 2018
28. Wu H. · 2018 · 11.5.1
29. Calderoni A. · 2014 · 1
30. Pi S. · arXiv prepr. arXiv · 2018
31. 10.1088/0957-4484/27/36/36520210.1088/0957-4484/27/36/365202 ↗
32. 10.1109/TED.2016.263092510.1109/TED.2016.2630925 ↗
33. Ito S. · 2018 · 1
34. 10.1063/1.499208910.1063/1.4992089 ↗
35. 10.1063/1.497875710.1063/1.4978757 ↗
36. 10.1109/LED.2017.265681810.1109/LED.2017.2656818 ↗
37. 10.1063/1.494579010.1063/1.4945790 ↗
38. 10.1109/TED.2017.277798610.1109/TED.2017.2777986 ↗
39. 10.1147/rd.462.021310.1147/rd.462.0213 ↗
40. 10.1038/nnano.2008.16010.1038/nnano.2008.160 ↗
41. 10.1002/adma.20090037510.1002/adma.200900375 ↗
42. 10.1088/0957-4484/22/25/25401510.1088/0957-4484/22/25/254015 ↗
43. 10.1021/acsnano.6b0627510.1021/acsnano.6b06275 ↗
44. 10.1002/adma.20150543510.1002/adma.201505435 ↗
45. Norris K. J. · SPIE Proceedings · 2015 · 9553 · 95530V10.1117/12.2192488 ↗
46. 10.1038/s41467-018-04452-w10.1038/s41467-018-04452-w ↗
47. 10.1017/S143192761500222610.1017/S1431927615002226 ↗