Samuel Dayo
ABSTRACT
Charge-trap transistors (CTTs) are compute-in-memory devices that are used to model synaptic arrays in neuromorphic systems. CTTs enable non von Neumann architectures, thus, eliminating the energy spent on compute-memory communication. Synaptic weights can be stored in CTTs by shifting the threshold voltage of the devices in an analog manner. CTTs are, however, susceptible to unintentional de-trapping of charge over time due to threshold voltage instability, leading to loss of the stored synaptic weights. The proposed weight refresh system performs statistical refresh of the CTT array to replenish the charge of individual CTT devices (restore synaptic weights) based on characterization of threshold voltage instability in high-k dielectrics.
- S. Friedmann et al., "Demonstrating Hybrid Learning in a Flexible Neuromorphic Hardware System," IEEE Transactions on Biomedical Circuits and Systems, Vol. 11, No. 1, pp. 128--142, Feb. 2017.Google Scholar
Cross Ref
- E. Painkras et al., "SpiNNaker: A 1-W 18-Core System-on-Chip for Massively- Parallel Neural Network Simulation," IEEE Journal of Solid-State Circuits, Vol. 48, No. 8, pp. 1943--1953, May 2013.Google ScholarCross Ref
- F. Akopyan et al., "TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. 34, No. 10, pp. 1537--1557, Aug. 2015.Google ScholarDigital Library
- M. Davies et al., "Loihi: A Neuromorphic Manycore Processor with On-Chip Learning," IEEE Micro, Vol. 38, No. 1, pp. 82--99, Jan./Feb. 2018.Google ScholarCross Ref
- M. Karimi, A. S. Monir, R. Mohammadrezaee, and B. Vaisband, "CTT-Based Scalable Neuromorphic Architecture," IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Vol. 13, No. 1, pp. 96--107, March 2023.Google ScholarCross Ref
- C. Frenkel, M. Lefebvre, J.-D. Legat, and D. Bol, "A 0.086-mm2 12.7-pJ/SOP 64k- Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28-nm CMOS," IEEE Transactions on Biomedical Circuits and Systems, Vol. 13, No. 1, pp. 145--158, Nov. 2019.Google Scholar
- F. Khan et al., "The Impact of Self-Heating on Charge Trapping in High- k - Metal-Gate nFETs," IEEE Electron Device Letters, Vol. 37, No. 1, pp. 88--91, Dec. 2016.Google ScholarCross Ref
- G. Bersuker et al., "Mechanism of Electron Trapping and Characteristics of Traps in HfO2 Gate Stacks," IEEE Transactions on Device and Materials Reliability, Vol. 7, No. 1, pp. 138--145, Mar. 2007.Google ScholarCross Ref
- S. Zafar, A. Kumar, E. Gusev, and E. Cartier, "Threshold Voltage Instabilities in High-"? Gate Dielectric Stacks," IEEE Transactions on Device and Materials Reliability, Vol. 5, No. 1, pp. 45--64, Mar. 2005.Google ScholarCross Ref
- G. Ribes et al., "Characterization of Vt Instability in Hafnium Based Dielectrics by Pulse Gate Voltage Aechniques," Proceedings of the IEEE European Solid-State Circuits Conference, pp. 89--92, Sep. 2004Google Scholar
Index Terms
- Statistical Weight Refresh System for CTT-Based Synaptic Arrays
Recommendations
Dynamic Reliability Management in Neuromorphic Computing
Neuromorphic computing systems execute machine learning tasks designed with spiking neural networks. These systems are embracing non-volatile memory to implement high-density and low-energy synaptic storage. Elevated voltages and currents needed to ...
Design-Technology Co-Optimization for NVM-Based Neuromorphic Processing Elements
An emerging use case of machine learning (ML) is to train a model on a high-performance system and deploy the trained model on energy-constrained embedded systems. Neuromorphic hardware platforms, which operate on principles of the biological brain, can ...
Mitigating Effects of Non-ideal Synaptic Device Characteristics for On-chip Learning
ICCAD '15: Proceedings of the IEEE/ACM International Conference on Computer-Aided DesignThe cross-point array architecture with resistive synaptic devices has been proposed for on-chip implementation of weighted sum and weight update in the training process of learning algorithms. However, the non-ideal properties of the synaptic devices ...
Comments