HPE, EPFL Launch Blue Brain 5 Supercomputer

By John Russell

July 10, 2018

HPE and the Ecole Polytechnique Federale de Lausannne (EPFL) Blue Brain Project yesterday introduced Blue Brain 5, a new supercomputer built by HPE, which displaces a long line of IBM Blue Gene systems that previously supported the 13-year-old Blue Brain Project whose ambitious goal is to “digitally reconstruct and simulate” the human brain. The Blue Brain project, which has occasionally stirred debate among European brain researchers, came into being in June 2005 when IBM and EPFL signed an agreement to launch the project and install a Blue Gene at EPFL – hence the name Blue Brain for the machine.

The most recent system, Blue Brain 4, was a Blue Gene/Q machine installed in 2014 at the Swiss National Computing Centre (CSCS). When IBM stopped development of Blue Gene around 2015, EPFL was forced to broaden its search for next generation supercomputing technology, said Felix Shürmann, EPFL, co-director EPFL Blue Brain Project during a press briefing yesterday. (Project timeline posted on the project website.)

Many vendors (presumably IBM among them) responded to its RFP and in the end, “[HPE] not only fulfilled the technical specs and scored well on the price, but I think what is important about HPE is that they are a technology company with their own research and forward-looking perspective to computing and the upcoming challenges, and this notion that this is a technology partner that allows us to navigate this space of available technologies and make the right choices, that was an important part in the selection process,” said Shürmann.

HPE SGI 8600 System

This is clearly a win for HPE although IBM may not be losing any sleep given its giant success on the most recent Top500 list with Summit (122PF, Rmax) on top and Sierra (71.6PF, Rmax) at number three (See HPCwire article, GPUs Power Five of World’s Top Seven Supercomputers).

Bragging rights aside, the new HPE machine, say both HPE and EPFL, was carefully designed to meet the massive data handling and simulation requirements of modern brain research. Repeating numbers you have likely already heard, there are on the order of 100 billion neurons and 100-to-1,000 trillion synapses in the human brain. Moreover there is a bewildering number of ways in which neurons and synapses interact helped along by a rather long list of other players (proteins, glial cells, etc.) all operating in a multi-scale system that spans the tiny (molecules) to the comparatively large (regions of the brain).

Henry Markram, EPFL Brain Project founder and co-director, said, “To gather all this data and to organize it and to make sense of how all this data fits together is really one of the biggest big data challenges that exists today.”

Schürmann added, “The Blue Brain Project’s scientific mission is critically dependent on our supercomputing capabilities. Modeling an individual neuron at Blue Brain today leads to around 20,000 ordinary differential equations – when modeling 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.”

The Blue Brain 5 core system is an HPE SGI 8600 system comprised of 372 compute nodes. HPE says it delivers 1.06 petaflops of peak performance and can be easily scaled up. The system has 94 terabytes of memory and runs Intel Xeon Gold 6140 and Intel Xeon Phi 7230 processors as well as Nvidia Tesla V100 graphic processors. Blue Brain 5 uses single and dual-rail Mellanox InfiniBand high-performance networks and has 4 petabytes of high-performance storage from DataDirect Networks (DDN), delivering more than 50 GB/s aggregated bandwidth, associated with an innovative 80 GB/s Infinite Memory Engine (IME) flash-based burst buffer. Blue Brain 5 was installed at CSCS this spring and is now running at full production.

The secret sauce – and HPE didn’t reveal much technical detail yesterday – is how HPE has apparently blended four systems into one. Its flexible architecture, says HPE, can host different sub systems that are specifically geared for tasks like visualization or deep learning, while being operated as one single system.

“Our first focus was on the workflow of the Blue Brain project,” said Eng Lim Goh, VP, CTO, HPC and AI, HPE. “We came up with a supercomputer that is made up of four subsystems, tightly bound together to work as one. The four subsystems include one that is strong for extracting data from storage, another subsystem was strong and designed to do well at extracting data fast from memory, the third one was for visualization, and a fourth one was a general purpose one spans across the other three. on top of that we bound the four subsystems tightly together with high bandwidth network, and in some areas doubling up on the bandwidth.”

“As you can see it was a detailed design process done by studying the workflow of the project and designing a supercomputer that matches the workflow. For example, when the workflow starts and it is trying to discover all the possible touch points from the neuron onward, the high IO bandwidth subsystem, the one that can extract data fast from storage, is first employed. After which, when simulation is actually done in detail, and at high resolution, we switch to the second subsystem where we can extract data very fast from memory. Finally when you visualize, the visualization subsystem is used. This gives you one example of how we looked at the workflow carefully and designed a system to match it,” explained Goh.

Broadly, HPE characterizes the subsystems as:

  • Subsystem 1: Intel KNL, 16GB of HBM, 96GB DRAM
  • Subsystem 2: Dual Intel Xeon, 768 GB memory + 4 Nvidia V100 GPUs
  • Subsystem 3: Dual Intel Xeon, 384 GB memory
  • Subsystem 4: Dual Intel Xeon, 384 GB memory + 2 NVME

Brain research is expensive and over the years there has been vigorous discussion over how best to spend scarce research dollars. The EPFL Blue Brain project, led by Markram, sometimes drew criticism for its approach. In recent years, the Swiss-funded Blue Brain project has become part of the broader European-wide Human Brain Project (HBP) whose compass is broader. The HBP is exploring everything from new neuromorphic processor technology, to bioinformatics tools development, and specific disease research.

Said Markram, “What is very different and unique about the Blue Brain Project is that we are very much focused on the biology. Our goal is to be able to capture [brain biology] with as high fidelity as possible – as much as the computing allows us and as the biological data informs us – to be able to build models that are as accurate and as the actual biological specimen. So in a way it is a digital reconstruction.”

Henry Markram, EPFL Blue Brain Project

The insights can later be applied to other cognitive and biomedical research. One of the Blue Brain Project’s discoveries, said Markram, is how ‘micro circuits’ in the brain are structured and behave.

“We deliberately chose the micro circuit. It’s the minimal systems of neurons. Neurons need other neurons. There’s a minimum number of them [to form a micro circuit]. In the mammalian cortex that turned out to be 30,000, which is a number we discovered through the simulation; it was not a number that was known in experiments or through theory. That’s the minimum ecosystem. We wanted to identify that first because that provides the sort of unit of operation in the mammalian neocortex,” said Markram.

“This gave us a new insight into what the brain is trying to process but what we don’t know today is how that changes when you go from a micro circuit to a brain region such as the touch region or the vision region or the hearing region. These are larger regions [and] can be composed of several hundreds of these micro circuits. It’s a question of how all these micro circuits interact that we are now going to be able to explore with the kind of computing that we have obtained with HPE. That will allow us to begin understanding how entire sensory modalities are forming in response to when the sensory input comes in, which neurons are active, which synapses are active, and how these micro circuits are interacting to sculpture an electrical landscape which is effectively coding information for what is happening in the outside world.”

HPE has long been active in life sciences research including NIH’s Living Heart Project and the work with the Center for Neurodegenerative Diseases and the University of Bonn targeting, among other things Alzheimer’s Disease.

During yesterday’s press briefing, a question about needing exascale compute power came up. It will indeed be helpful agreed EPFL and HPE. HPE, of course, has been an active participant in the Path Forward program in the U.S. although it isn’t currently the prime contractor on any U.S.-funded pre-exascale machines. Markram was quick to note that simulating a full human brain was probably not realistic any time soon.

“It depends on the resolution of the simulation,” he said. “If you take it to the extreme level, as I’ve said, you have a billion organic proteins in a single neuron and you got 100 billion of them and their interactions are happening at sort of microsecond scale. If you had to do the calculation, if you wanted to simulate every molecule in the human brain you would probably need a computer that’s about 1030 flops so that’s way beyond the yotta scale (1024 ). This is not what we are talking about when we say we are going to simulate the brain.

“What we are doing is building – with the constraints of what the computing can allow us – technologies [that] we call multiscale simulation. That means that a lot of the big parts of the brain would be simulated at low resolution. That neurons may not be as elaborate, they may be even point neurons. Not all the molecules in all of the neurons would be simulated. But when you identify an area of interest, you would be able to zoom in effectively and as you zoom in you’d be able to see the region, the activity there at much higher resolution. We are building models that allow you to go down to not just the neurons but the supporting cell which are of course ether glial cells and even down to the blood vessels to see how neurons are being supported by the blood supply.”

Big Science takes time and, increasingly, lots of computational power.

Blue Brain Project video:

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

D-Wave Delivers 5000-qubit System; Targets Quantum Advantage

September 29, 2020

D-Wave today launched its newest and largest quantum annealing computer, a 5000-qubit goliath named Advantage that features 15-way qubit interconnectivity. It also introduced the D-Wave Launch program intended to jump st Read more…

By John Russell

What’s New in Computing vs. COVID-19: AMD, Remdesivir, Fab Spending & More

September 29, 2020

Supercomputing, big data and artificial intelligence are crucial tools in the fight against the coronavirus pandemic. Around the world, researchers, corporations and governments are urgently devoting their computing reso Read more…

By Oliver Peckham

Global QC Market Projected to Grow to More Than $800 million by 2024

September 28, 2020

The Quantum Economic Development Consortium (QED-C) and Hyperion Research are projecting that the global quantum computing (QC) market - worth an estimated $320 million in 2020 - will grow at an anticipated 27% CAGR betw Read more…

By Staff Reports

DoE’s ASCAC Backs AI for Science Program that Emulates the Exascale Initiative

September 28, 2020

Roughly a year after beginning formal efforts to explore an AI for Science initiative the Department of Energy’s Advanced Scientific Computing Advisory Committee last week accepted a subcommittee report calling for a t Read more…

By John Russell

Supercomputer Research Aims to Supercharge COVID-19 Antiviral Remdesivir

September 25, 2020

Remdesivir is one of a handful of therapeutic antiviral drugs that have been proven to improve outcomes for COVID-19 patients, and as such, is a crucial weapon in the fight against the pandemic – especially in the abse Read more…

By Oliver Peckham

AWS Solution Channel

The Water Institute of the Gulf runs compute-heavy storm surge and wave simulations on AWS

The Water Institute of the Gulf (Water Institute) runs its storm surge and wave analysis models on Amazon Web Services (AWS)—a task that sometimes requires large bursts of compute power. Read more…

Intel® HPC + AI Pavilion

Berlin Institute of Health: Putting HPC to Work for the World

Researchers from the Center for Digital Health at the Berlin Institute of Health (BIH) are using science to understand the pathophysiology of COVID-19, which can help to inform the development of targeted treatments. Read more…

NOAA Announces Major Upgrade to Ensemble Forecast Model, Extends Range to 35 Days

September 23, 2020

A bit over a year ago, the United States’ Global Forecast System (GFS) received a major upgrade: a new dynamical core – its first in 40 years – called the finite-volume cubed-sphere, or FV3. Now, the National Oceanic and Atmospheric Administration (NOAA) is bringing the FV3 dynamical core to... Read more…

By Oliver Peckham

D-Wave Delivers 5000-qubit System; Targets Quantum Advantage

September 29, 2020

D-Wave today launched its newest and largest quantum annealing computer, a 5000-qubit goliath named Advantage that features 15-way qubit interconnectivity. It a Read more…

By John Russell

DoE’s ASCAC Backs AI for Science Program that Emulates the Exascale Initiative

September 28, 2020

Roughly a year after beginning formal efforts to explore an AI for Science initiative the Department of Energy’s Advanced Scientific Computing Advisory Commit Read more…

By John Russell

NOAA Announces Major Upgrade to Ensemble Forecast Model, Extends Range to 35 Days

September 23, 2020

A bit over a year ago, the United States’ Global Forecast System (GFS) received a major upgrade: a new dynamical core – its first in 40 years – called the finite-volume cubed-sphere, or FV3. Now, the National Oceanic and Atmospheric Administration (NOAA) is bringing the FV3 dynamical core to... Read more…

By Oliver Peckham

Arm Targets HPC with New Neoverse Platforms

September 22, 2020

UK-based semiconductor design company Arm today teased details of its Neoverse roadmap, introducing V1 (codenamed Zeus) and N2 (codenamed Perseus), Arm’s second generation N-series platform. The chip IP vendor said the new platforms will deliver 50 percent and 40 percent more... Read more…

By Tiffany Trader

Oracle Cloud Deepens HPC Embrace with Launch of A100 Instances, Plans for Arm, More 

September 22, 2020

Oracle Cloud Infrastructure (OCI) continued its steady ramp-up of HPC capabilities today with a flurry of announcements. Topping the list is general availabilit Read more…

By John Russell

European Commission Declares €8 Billion Investment in Supercomputing

September 18, 2020

Just under two years ago, the European Commission formalized the EuroHPC Joint Undertaking (JU): a concerted HPC effort (comprising 32 participating states at c Read more…

By Oliver Peckham

Google Hires Longtime Intel Exec Bill Magro to Lead HPC Strategy

September 18, 2020

In a sign of the times, another prominent HPCer has made a move to a hyperscaler. Longtime Intel executive Bill Magro joined Google as chief technologist for hi Read more…

By Tiffany Trader

Future of Fintech on Display at HPC + AI Wall Street

September 17, 2020

Those who tuned in for Tuesday's HPC + AI Wall Street event got a peak at the future of fintech and lively discussion of topics like blockchain, AI for risk man Read more…

By Alex Woodie, Tiffany Trader and Todd R. Weiss

Supercomputer-Powered Research Uncovers Signs of ‘Bradykinin Storm’ That May Explain COVID-19 Symptoms

July 28, 2020

Doctors and medical researchers have struggled to pinpoint – let alone explain – the deluge of symptoms induced by COVID-19 infections in patients, and what Read more…

By Oliver Peckham

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

Intel’s 7nm Slip Raises Questions About Ponte Vecchio GPU, Aurora Supercomputer

July 30, 2020

During its second-quarter earnings call, Intel announced a one-year delay of its 7nm process technology, which it says it will create an approximate six-month shift for its CPU product timing relative to prior expectations. The primary issue is a defect mode in the 7nm process that resulted in yield degradation... Read more…

By Tiffany Trader

Google Hires Longtime Intel Exec Bill Magro to Lead HPC Strategy

September 18, 2020

In a sign of the times, another prominent HPCer has made a move to a hyperscaler. Longtime Intel executive Bill Magro joined Google as chief technologist for hi Read more…

By Tiffany Trader

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

Neocortex Will Be First-of-Its-Kind 800,000-Core AI Supercomputer

June 9, 2020

Pittsburgh Supercomputing Center (PSC - a joint research organization of Carnegie Mellon University and the University of Pittsburgh) has won a $5 million award Read more…

By Tiffany Trader

European Commission Declares €8 Billion Investment in Supercomputing

September 18, 2020

Just under two years ago, the European Commission formalized the EuroHPC Joint Undertaking (JU): a concerted HPC effort (comprising 32 participating states at c Read more…

By Oliver Peckham

Leading Solution Providers

Contributors

Oracle Cloud Infrastructure Powers Fugaku’s Storage, Scores IO500 Win

August 28, 2020

In June, RIKEN shook the supercomputing world with its Arm-based, Fujitsu-built juggernaut: Fugaku. The system, which weighs in at 415.5 Linpack petaflops, topp Read more…

By Oliver Peckham

Google Cloud Debuts 16-GPU Ampere A100 Instances

July 7, 2020

On the heels of the Nvidia’s Ampere A100 GPU launch in May, Google Cloud is announcing alpha availability of the A100 “Accelerator Optimized” VM A2 instance family on Google Compute Engine. The instances are powered by the HGX A100 16-GPU platform, which combines two HGX A100 8-GPU baseboards using... Read more…

By Tiffany Trader

DOD Orders Two AI-Focused Supercomputers from Liqid

August 24, 2020

The U.S. Department of Defense is making a big investment in data analytics and AI computing with the procurement of two HPC systems that will provide the High Read more…

By Tiffany Trader

Supercomputer Modeling Tests How COVID-19 Spreads in Grocery Stores

April 8, 2020

In the COVID-19 era, many people are treating simple activities like getting gas or groceries with caution as they try to heed social distancing mandates and protect their own health. Still, significant uncertainty surrounds the relative risk of different activities, and conflicting information is prevalent. A team of Finnish researchers set out to address some of these uncertainties by... Read more…

By Oliver Peckham

Microsoft Azure Adds A100 GPU Instances for ‘Supercomputer-Class AI’ in the Cloud

August 19, 2020

Microsoft Azure continues to infuse its cloud platform with HPC- and AI-directed technologies. Today the cloud services purveyor announced a new virtual machine Read more…

By Tiffany Trader

Japan’s Fugaku Tops Global Supercomputing Rankings

June 22, 2020

A new Top500 champ was unveiled today. Supercomputer Fugaku, the pride of Japan and the namesake of Mount Fuji, vaulted to the top of the 55th edition of the To Read more…

By Tiffany Trader

Joliot-Curie Supercomputer Used to Build First Full, High-Fidelity Aircraft Engine Simulation

July 14, 2020

When industrial designers plan the design of a new element of a vehicle’s propulsion or exterior, they typically use fluid dynamics to optimize airflow and in Read more…

By Oliver Peckham

Intel Speeds NAMD by 1.8x: Saves Xeon Processor Users Millions of Compute Hours

August 12, 2020

Potentially saving datacenters millions of CPU node hours, Intel and the University of Illinois at Urbana–Champaign (UIUC) have collaborated to develop AVX-512 optimizations for the NAMD scalable molecular dynamics code. These optimizations will be incorporated into release 2.15 with patches available for earlier versions. Read more…

By Rob Farber

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This