Building and reconstructing brains in painstaking detail digitally could become a reality.
Hewlett Packard Enterprise (HPE) has been selected by the Swiss Federal Institute for Technology in Lausanne to build a supercomputer for “The Blue Brain Project”.
The Blue Brain Project’s goal is to build digital reconstructions and simulations of the rodent and human brain. The advanced supercomputer built by HPE is based on the HPE SGI 8600 System. The system is equipped with 94 terabytes of memory – a memory equivalent of 23,000 laptops.
It will provide the compute foundations for the Blue Brain Project to pursue its scientific roadmap goal for 2020 to model entire regions of the mouse brain, in particular the thalamus and neocortex.
Co-Director of the Blue Brain Project, Felix Schürmann highlighted that the project’s mission was “critically dependent on supercomputing capabilities”.
Schürmann said: “Modelling an individual neuron at Blue Brain today leads to around 20,000 ordinary differential equations – when modelling entire brain regions, this quickly raises to 100 billion equations that have to be solved concurrently. HPE helps us to navigate the challenging technology landscape in supercomputing.”
Blue Brain releases systematically open-access data, models, and open-source tools to help the community understand the brain at different levels of organisation.
It also added on their website that the project allows reconstructing and building the brain digitally at “unprecedented levels of biological detail”.
How Will Blue Brain 5 Be Used?
Blue Brain 5 will be used primarily for simulation neuroscience, most particularly in simulation-based research, analysis and visualisation.
The supercomputer is designed to host different sub systems that are specifically geared towards visualisation or deep learning, whilst operating as one system.
Four different configurations are integrated in Blue Brain 5, each optimised for a different workload profile.
The profiles provide strengths in areas such as memory bandwidth, network bandwidth, processing power, graphical processing, and input/output.
HPE’s supercomputer provides tailored and scalable compute performance, enabling the Blue Brain Project to pursue its scientific roadmap goal from 2020 of modelling entire regions of the mouse brain.
CEO of HPE, Antonio Neri added: “Through our relationship with the Blue Brain Project, HPE is bringing advanced supercomputing and bespoke applications to empower new research that can have transformative benefits for the neuroscientific community and society at large.”
The supercomputer runs Intel Xeon Gold 6140 and Intel Xeon Phi 7230 processors as well as NVIDIA Tesla V100 graphic processors.
The system uses single and dual-rail Mellanox InfiniBand high-performance networks and has 4 petabytes of high-performance storage from DataDirect Networks, delivering more than 50GB/s aggregated bandwidth, associated with an 80 GB/s Infinite Memory Engine (IME) flash-based burst buffer.
HPE said the system also features an energy efficient liquid cooling solution that does not exhaust heated air into the data center. The new system has been installed at the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland.