Skip to Main content Skip to Navigation
Conference papers

1S1R sub-threshold operation in Crossbar arrays for low power BNN inference computing

Abstract : We experimentally validated the sub-threshold reading strategy in OxRAM+OTS crossbar arrays for low precision inference in Binarized Neural Networks. In order to optimize the 1S1R sub-threshold current margin, an experimental and theoretical statistical study on HfO$_2$-based 1S1R stacks with various OTS technologies has been performed. Impact of device features (OxRAM RHRS, OTS non-linearity and OTS threshold current) on 1S1R sub-threshold reading is elucidated. Accuracy and power consumption of a Binarized Neural Network designed in 28nm CMOS have been estimated with Monte Carlo simulations. A gain of 3 orders of magnitude in power consumption is demonstrated in comparison with conventional threshold reading strategy, while preserving the same network accuracy.
Complete list of metadata

https://hal-cea.archives-ouvertes.fr/cea-03707392
Contributor : Joel MINGUET LOPEZ Connect in order to contact the contributor
Submitted on : Tuesday, June 28, 2022 - 3:32:39 PM
Last modification on : Saturday, September 24, 2022 - 2:58:04 PM

File

2022000040.pdf
Files produced by the author(s)

Identifiers

Citation

J. Minguet Lopez, F. Rummens, L. Reganaz, A. Heraud, T. Hirtzlin, et al.. 1S1R sub-threshold operation in Crossbar arrays for low power BNN inference computing. IMW 2022 - IEEE International Memory Workshop, May 2022, Dresden, Germany. pp.1-4, ⟨10.1109/IMW52921.2022.9779253⟩. ⟨cea-03707392⟩

Share

Metrics

Record views

37

Files downloads

9