A High Throughput Generative Vector Autoregression Model for Stochastic Synapses

TL;DR

This paper introduces a high throughput generative vector autoregression model for simulating stochastic synapses in neuromorphic systems, accurately capturing device variability and correlations while enabling large-scale, fast simulations.

Contribution

It presents a novel, scalable generative model based on vector autoregression that reproduces device response, noise, and correlations for resistive memory synapses.

Findings

Model closely matches measured device data

Supports array sizes over one billion cells

Achieves over 100 million weight updates per second

Abstract

By imitating the synaptic connectivity and plasticity of the brain, emerging electronic nanodevices offer new opportunities as the building blocks of neuromorphic systems. One challenge for largescale simulations of computational architectures based on emerging devices is to accurately capture device response, hysteresis, noise, and the covariance structure in the temporal domain as well as between the different device parameters. We address this challenge with a high throughput generative model for synaptic arrays that is based on a recently available type of electrical measurement data for resistive memory cells. We map this real world data onto a vector autoregressive stochastic process to accurately reproduce the device parameters and their cross-correlation structure. While closely matching the measured data, our model is still very fast; we provide parallelized implementations for both CPUs and GPUs and demonstrate array sizes above one billion cells and throughputs exceeding one hundred million weight updates per second, above the pixel rate of a 30 frames/s 4K video stream.