An Inference and Learning Engine for Spiking Neural Networks in Computational RAM (CRAM)

TL;DR

This paper introduces a novel in-memory SNN accelerator using Spintronic CRAM, significantly reducing energy consumption and addressing scalability issues of traditional architectures.

Contribution

It presents a new in-memory SNN accelerator based on Spintronic CRAM, demonstrating substantial energy efficiency improvements over ASIC solutions.

Findings

Energy consumption reduced by up to 164.1× compared to ASICs.

Scalability limitations of traditional SNN accelerators are effectively addressed.

In-memory computation with Spintronic CRAM enhances efficiency for neural network processing.

Abstract

Spiking Neural Networks (SNN) represent a biologically inspired computation model capable of emulating neural computation in human brain and brain-like structures. The main promise is very low energy consumption. Unfortunately, classic Von Neumann architecture based SNN accelerators often fail to address demanding computation and data transfer requirements efficiently at scale. In this work, we propose a promising alternative, an in-memory SNN accelerator based on Spintronic Computational RAM (CRAM) to overcome scalability limitations, which can reduce the energy consumption by up to 164.1$\times$ when compared to a representative ASIC solution.