THOR – A Neuromorphic Processor with 7.29G TSOP^2/mm^2Js Energy-Throughput Efficiency

12/03/2022
by   Mayank Senapati, et al.
0

Neuromorphic computing using biologically inspired Spiking Neural Networks (SNNs) is a promising solution to meet Energy-Throughput (ET) efficiency needed for edge computing devices. Neuromorphic hardware architectures that emulate SNNs in analog/mixed-signal domains have been proposed to achieve order-of-magnitude higher energy efficiency than all-digital architectures, however at the expense of limited scalability, susceptibility to noise, complex verification, and poor flexibility. On the other hand, state-of-the-art digital neuromorphic architectures focus either on achieving high energy efficiency (Joules/synaptic operation (SOP)) or throughput efficiency (SOPs/second/area), resulting in poor ET efficiency. In this work, we present THOR, an all-digital neuromorphic processor with a novel memory hierarchy and neuron update architecture that addresses both energy consumption and throughput bottlenecks. We implemented THOR in 28nm FDSOI CMOS technology and our post-layout results demonstrate an ET efficiency of 7.29G TSOP^2/mm^2Js at 0.9V, 400 MHz, which represents a 3X improvement over state-of-the-art digital neuromorphic processors.

READ FULL TEXT

page 1

page 5

research
03/27/2023

Open the box of digital neuromorphic processor: Towards effective algorithm-hardware co-design

Sparse and event-driven spiking neural network (SNN) algorithms are the ...
research
12/19/2022

PEZY-SC3: A MIMD Many-core Processor for Energy-efficient Computing

PEZY-SC3 is a highly energy- and area-efficient processor for supercompu...
research
04/29/2021

Hessian Aware Quantization of Spiking Neural Networks

To achieve the low latency, high throughput, and energy efficiency benef...
research
03/05/2020

Memory Organization for Energy-Efficient Learning and Inference in Digital Neuromorphic Accelerators

The energy efficiency of neuromorphic hardware is greatly affected by th...
research
06/13/2018

Exploiting Inherent Error-Resiliency of Neuromorphic Computing to achieve Extreme Energy-Efficiency through Mixed-Signal Neurons

Neuromorphic computing, inspired by the brain, promises extreme efficien...
research
08/07/2019

3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories

The first contribution of this paper is the development of extremely den...
research
12/27/2019

Structural plasticity on an accelerated analog neuromorphic hardware system

In computational neuroscience, as well as in machine learning, neuromorp...

Please sign up or login with your details

Forgot password? Click here to reset