eBrainII: A 3 kW Realtime Custom 3D DRAM integrated ASIC implementation of a Biologically Plausible Model of a Human Scale Cortex

TL;DR

This paper presents eBrainII, a custom 3D DRAM ASIC that enables real-time, biologically plausible cortical models at human scale with significantly reduced power consumption, making field deployment feasible.

Contribution

It introduces a novel ASIC implementation of a biologically plausible cortical model, achieving real-time performance at human scale with low power consumption.

Findings

eBrainII consumes only 3 kW for human scale cortex model.

The ASIC implementation enables real-time processing of biologically plausible models.

Power efficiency makes field deployment of complex brain models feasible.

Abstract

The Artificial Neural Networks (ANNs) like CNN/DNN and LSTM are not biologically plausible and in spite of their initial success, they cannot attain the cognitive capabilities enabled by the dynamic hierarchical associative memory systems of biological brains. The biologically plausible spiking brain models, for e.g. cortex, basal ganglia and amygdala have a greater potential to achieve biological brain like cognitive capabilities. Bayesian Confidence Propagation Neural Network (BCPNN) is a biologically plausible spiking model of cortex. A human scale model of BCPNN in real time requires 162 TFlops/s, 50 TBs of synaptic weight storage to be accessed with a bandwidth of 200 TBs. The spiking bandwidth is relatively modest at 250 GBs/s. A hand optimized implementation of rodent scale BCPNN has been implemented on Tesla K80 GPUs require 3 kW, we extrapolate from that a human scale network will require 3 MW. These power numbers rule out such implementations for field deployment as advanced cognition engines in embedded systems. The key innovation that this paper reports is that it is feasible and affordable to implement real time BCPNN as a custom tiled ASIC in 28 nm technology with custom 3D DRAM - eBrain II - that consumes 3 kWs for human scale and 12 W for rodent scale cortex model. Such implementations eminently fulfill the demands for field deployment.