1S1R Sub-Threshold Operation in Crossbar Arrays for Neural Networks Hardware Implementation

This paper presents an outlook of Crossbar memory array capabilities while operated in the sub-threshold regime. By means of experimental data obtained on a RRAM resistive device co-integrated in series with an OTS back-end selector, the pertinence of 1S1R sub-threshold read operation for both standard Binarized Neural Networks (BNNs) and Binarized Spiking Neural Networks (B'SNNs) inference implementation in hardware is elucidated.

[1]  A. Valentian,et al.  Improving the Robustness of Neural Networks to Noisy Multi-Level Non-Volatile Memory-based Synapses , 2023, 2023 International Joint Conference on Neural Networks (IJCNN).

[2]  L. Anghel,et al.  Are SNNs Really More Energy-Efficient Than ANNs? an In-Depth Hardware-Aware Study , 2023, IEEE Transactions on Emerging Topics in Computational Intelligence.

[3]  A. Pirovano,et al.  In-memory neural network accelerator based on phase change memory (PCM) with one-selector/one-resistor (1S1R) structure operated in the subthreshold regime , 2023, International Memory Workshop.

[4]  A. Valentian,et al.  Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey. , 2023, IEEE Transactions on Neural Networks and Learning Systems.

[5]  G. Molas,et al.  1S1R Optimization for High‐Frequency Inference on Binarized Spiking Neural Networks , 2022 .

[6]  G. Molas,et al.  1S1R sub-threshold operation in Crossbar arrays for low power BNN inference computing , 2022, 2022 IEEE International Memory Workshop (IMW).

[7]  G. Molas,et al.  OxRAM + OTS optimization for binarized neural network hardware implementation , 2021, Semiconductor Science and Technology.

[8]  G. Molas,et al.  Ge-Se-Sb-N-based OTS scaling perspectives for high-density 1 S1R crossbar arrays , 2021, International Memory Workshop.

[9]  V. Sze,et al.  Efficient Processing of Deep Neural Networks , 2020, Synthesis Lectures on Computer Architecture.

[10]  Chung-Cheng Chou,et al.  A 22nm 96KX144 RRAM Macro with a Self-Tracking Reference and a Low Ripple Charge Pump to Achieve a Configurable Read Window and a Wide Operating Voltage Range , 2020, 2020 IEEE Symposium on VLSI Circuits.

[11]  Stefano Fusi,et al.  Building brain-inspired computing , 2019, Nature Communications.

[12]  Meng-Fan Chang,et al.  CMOS-integrated memristive non-volatile computing-in-memory for AI edge processors , 2019, Nature Electronics.

[13]  Damien Querlioz,et al.  Digital Biologically Plausible Implementation of Binarized Neural Networks With Differential Hafnium Oxide Resistive Memory Arrays , 2019, Frontiers in Neuroscience.

[14]  Mingguo Zhao,et al.  Towards artificial general intelligence with hybrid Tianjic chip architecture , 2019, Nature.

[15]  A. Verdy,et al.  Tunable Performances in OTS Selectors Thanks to Ge3Se7-As2Te3 , 2019, 2019 IEEE 11th International Memory Workshop (IMW).

[16]  Stephen Richardson,et al.  Dark Memory and Accelerator-Rich System Optimization in the Dark Silicon Era , 2016, IEEE Design & Test.

[17]  N. Righos,et al.  A stackable cross point Phase Change Memory , 2009, 2009 IEEE International Electron Devices Meeting (IEDM).