1S1R sub-threshold operation in Crossbar arrays for low power BNN inference computing - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (1) , (2) , (3) , (3) , (1) , (1)
1
2
3

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.
Fichier principal
Vignette du fichier
2022000040.pdf (809.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-03707392 , version 1 (28-06-2022)

Identifiers

Cite

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⟩
44 View
15 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More