Computer hardware originally designed for 3-D games could hold the key to replicating the human brain

Computer hardware designed for 3D games could hold the key to replicating human brain
Dr James Knight and Prof Thomas Nowotny from the University of Sussex's School of Engineering and Informatics have beaten a top 50 supercomputer by running brain simulations using their own GeNN software and Graphics Processing Units (GPUs). Credit: University of Sussex/Stuart Robinson.

Researchers at the University of Sussex have created the fastest and most energy efficient simulation of part of a rat brain using off-the-shelf computer hardware.

Dr. James Knight and Prof Thomas Nowotny from the University of Sussex's School of Engineering and Informatics have beaten a top 50 supercomputer by running simulations using their own GeNN software and graphics processing units (GPUs).

By developing faster and more efficient simulators, the academics hope to increase the level of understanding into brain function and, in particular, identify how damage to particular structures in neurons can lead to deficits in . Faster, more advanced simulators could help improve understanding of neurological disorders by pinpointing the areas of the brain that cause epileptic seizures.

Improved simulators could also accelerate progress within the development of AI—the GeNN software is already being used at the University of Sussex to build autonomous robots including flying drones which can be controlled through simulated insect brains.

Prof Nowotny, Professor of Informatics at the University of Sussex, said: "Over the last three decades, computers have become drastically more powerful, largely due to our ability to fabricate computer chips with smaller and smaller components which, in turn, allows them to operate faster. This process has hit a wall and it has become much harder to build without employing radically different architectures. GPUs are one such architecture and our work shows that, in the near term, they are a competitive design for computing and have the potential to make advances far beyond where CPUs have brought us to so far."

A brain simulation using University of Sussex developed GeNN software and Graphics Processing Units (GPUs). The different colours indicate different types of neuron in the model and each flashing pixel represents a single neuron becoming active. Credit: University of Sussex

The research involved using the team's own GeNN software to implement and test two established computational neuroscience models; one of a cortical microcircuit consisting of eight populations of neurons and a balanced random network with spike-timing dependent plasticity—a process which has been shown to be fundamental to biological learning.

A single GPU was able to achieve processing speeds up to 10 percent faster than is currently possible using either a supercomputer or the SpiNNaker neuromorphic system, a custom-built machine developed as a part of the £1bn European Human Brain Project (HBP).

The University of Sussex team were also able to achieve energy savings of 10 times compared to either the SpiNNaker or supercomputer simulations.

Moving forward, the academics believe that the flexibility and power of GPUs means that they could play a key role in creating simulators capable of running models that begin to approach the complexity of the human brain.

Dr. Knight, Research Fellow in Computer Science at the University of Sussex, said: "Although we're a long way from having the understanding necessary to build models of the entire human brain, we're approaching the point where the latest exascale supercomputers have the raw computing power that would be required to simulate them. Many of these systems rely on GPUs so we're delighted with these latest results which show how well-suited GPUs are to brain simulations. Over the next year we are hoping to extend our work to a model 50 times larger of a monkey visual systems by using multiple, interconnected GPUs."

Chris Emerson, head of Higher-Education and Research Sales in UK and Ireland at NVIDIA, said: "We are very impressed by the use of the NVIDIA AI compute platform for brain simulations spear-headed at the University of Sussex and are glad we are able to support research at the leading edge of computational neuroscience as well as AI."


Explore further

'Human brain' supercomputer with 1 million processors switched on for first time

More information: James C. Knight et al. GPUs Outperform Current HPC and Neuromorphic Solutions in Terms of Speed and Energy When Simulating a Highly-Connected Cortical Model, Frontiers in Neuroscience (2018). DOI: 10.3389/fnins.2018.00941
Journal information: Frontiers in Neuroscience

Citation: Computer hardware originally designed for 3-D games could hold the key to replicating the human brain (2018, December 19) retrieved 17 July 2019 from https://medicalxpress.com/news/2018-12-hardware-d-games-key-replicating.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
2773 shares

Feedback to editors

User comments

Dec 19, 2018
GPUs aren't drastically different from CPUs, it's just that a CPU can have 12 computing cores, while a GPU can easily have 1200. The bottleneck for general purpose computation is still in memory access, where GPUs shine with massively parallel memory buses and clever interleaving of data (also, a lot of data is duplicated to speed up access) that allow them to handle a great number of simple calculations.

Neural simulations are exactly the kind of task that needs a very simple job done billions of times over. It's not computing the n-th digit of e, it's just adding 1+2 over and over.

Dec 19, 2018
This comment has been removed by a moderator.

Dec 20, 2018
"It's not computing the n-th digit of e, it's just adding 1+2 over and over." - Eikka

It is a little more complex than that. At a minimum a dot product is performed per node followed by a pass though some kind of non-linear function - typically one that looks like _/ or a sigmoid.

This non-linear operation is propagated over every virtual neuron in the network.

Dec 28, 2018
At a minimum a dot product is performed per node followed by a pass though some kind of non-linear function - typically one that looks like _/ or a sigmoid.


A dot product is essentially 1 x 2 instead of 1+2 so not much more difficult for dedicated hardware. (multiplication in binary isn't very difficult) and the point of research in neural simulation in recent times has been to reduce the non-linear functions into simple 8-bit lookup tables instead of computing difficult functions - to speed up the calculations.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more