Modular Simulation Framework for Process Variation Analysis of MRAM-based Deep Belief Networks
This work addresses process variation analysis for MRAM-based deep belief networks, which is incremental as it provides a simulation tool for optimizing device and network parameters in a specific domain.
The researchers tackled the problem of process variation affecting MRAM-based p-bit neuromorphic devices in Restricted Boltzmann Machines (RBMs) by developing a modular simulation framework, revealing energy vs. accuracy tradeoffs in evaluations using the MNIST dataset.
Magnetic Random-Access Memory (MRAM) based p-bit neuromorphic computing devices are garnering increasing interest as a means to compactly and efficiently realize machine learning operations in Restricted Boltzmann Machines (RBMs). When embedded within an RBM resistive crossbar array, the p-bit based neuron realizes a tunable sigmoidal activation function. Since the stochasticity of activation is dependent on the energy barrier of the MRAM device, it is essential to assess the impact of process variation on the voltage-dependent behavior of the sigmoid function. Other influential performance factors arise from varying energy barriers on power consumption requiring a simulation environment to facilitate the multi-objective optimization of device and network parameters. Herein, transportable Python scripts are developed to analyze the output variation under changes in device dimensions on the accuracy of machine learning applications. Evaluation with RBM circuits using the MNIST dataset reveal impacts and limits for processing variation of device fabrication in terms of the resulting energy vs. accuracy tradeoffs, and the resulting simulation framework is available via a Creative Commons license.