-
Man City win as Inter stay perfect, Barca held in Champions League
-
French superstar DJ Snake wants new album to 'build bridges'
-
Barca rescue draw at Club Brugge in six-goal thriller
-
Foden hits top form as Man City thrash Dortmund
-
NBA officials brief Congress committee over gambling probe
-
Inter beat Kairat Almaty to maintain Champions League perfection
-
Newcastle sink Bilbao to extend Champions League winning run
-
Wall Street stocks rebound after positive jobs data
-
LPGA, European tour partner with Saudis for new Vegas event
-
Eyes turn to space to feed power-hungry data centers
-
Jazz lose Kessler for season with shoulder injury
-
League scoring leader Messi among MLS Best XI squad
-
MLS bans Suarez for Miami's winner-take-all playoff match
-
McIlroy appreciates PGA of America apology for Ryder Cup abuse
-
Garnacho equaliser saves Chelsea in Qarabag draw
-
Promotions lift McDonald's sales in tricky consumer market
-
Five things to know about New York's new mayor
-
Anisimova beats Swiatek to reach WTA Finals last four
-
US Supreme Court appears skeptical of Trump tariff legality
-
AC Milan post third straight annual profit on day of San Siro purchase
-
Angelina Jolie visits Ukrainian frontline city, media reports say
-
UN says forests should form key plank of COP30
-
Star designer Rousteing quits fashion group Balmain
-
Mexico's Sheinbaum steps up cartel fight after murder of anti-narco mayor
-
Attack on funeral in Sudan's Kordofan region kills 40: UN
-
Key PSG trio set for spell on sidelines
-
Democrats punch back in US elections - and see hope for 2026
-
BMW reports rising profitability, shares jump
-
US Supreme Court debates legality of Trump's tariffs
-
Bolivia Supreme Court orders release of jailed ex-president Jeanine Anez
-
Wall Street stocks rise after positive jobs data
-
'Hostage diplomacy': longstanding Iran tactic presenting dilemma for West
-
Rybakina stays perfect at WTA Finals with win over alternate Alexandrova
-
Le Garrec welcomes Dupont help in training for Springboks showdown
-
Brussels wants high-speed rail linking EU capitals by 2040
-
Swiss business chiefs met Trump on tariffs: Bern
-
At least 9 dead after cargo plane crashes near Louisville airport
-
France moves to suspend Shein website as first store opens in Paris
-
Spain's exiled king recounts history, scandals in wistful memoir
-
Wall Street stocks steady after positive jobs data
-
Trump blasts Democrats as government shutdown becomes longest ever
-
Indian pilgrims find 'warm welcome' in Pakistan despite tensions
-
Inter and AC Milan complete purchase of San Siro
-
Swedish authorities inspect worksite conditions at steel startup Stegra
-
Keys withdraws from WTA Finals with illness
-
Prince Harry says proud to be British despite new life in US
-
BMW boosts profitability, welcomes Nexperia signals
-
EU strikes last-ditch deal on climate targets as COP30 looms
-
Stocks retreat as tech bubble fears grow
-
Shein opens first permanent store amid heavy police presence
SpiNNcloud Advances AI-Driven Drug Discovery with Deployment of Brain-Inspired Supercomputer
The largest SpiNNaker2 supercomputer for molecule drug discovery yet, with 656,640 cores
DRESDEN, GERMANY / ACCESS Newswire / July 28, 2025 / Today SpiNNcloud secured a deal to deliver a brain-inspired supercomputer to Leipzig University, marking a significant milestone in the advancement of computing for small molecule research for personalized medicine. This is the largest SpiNNcloud System to be deployed specifically for drug discovery, encompassing around 650k cores.
Developed by deep-tech company SpiNNcloud, SpiNNcloud Server System can simulate up to a minimum of 10.5 billion neurons for AI, HPC, and other applications. The SpiNNcloud Server System is based on the current chip generation and was pioneered by Steve Furber, designer of the original ARM architecture,and uses a large number of low-power processors for efficiently computing AI and other workloads.
The multi-million Euro system to be deployed in Leipzig is intended for protein folding simulations to achieve personalized medicine. The approach leverages the extreme parallelism and scale of these systems to deploy millions of small models tasked with finding hits between molecules and patient profiles. The system will enable the discovery of new personalized drugs at faster convergence speeds and under a lower energy profile compared to traditional GPU-based systems.
"The SpiNNcloud Server System architecture makes screening billions of molecules in silico feasible with a brain-inspired supercomputer design," said Christian Mayr, SpiNNcloud co-founder. "Originally dedicated to biological neural network simulation, The SpiNNcloud Server System is tailored for massively parallel execution of small, heterogeneous compute workloads, with generally programmable 10 million ARM-based processors with many dedicated DNN accelerators. A prototype neural network allows the screening of 20 billion molecules in less than an hour, two orders of magnitude faster than on 1000 CPU cores."
"The extreme parallelism of SpiNNcloud supercomputers makes them ideally suited for protein folding applications like those used in small molecule drug discovery," said Jens Meiler, Alexander von Humboldt Professor and Director of the Institute for Drug Discovery at Leipzig University. "Protein folding can be viewed as an optimization problem where the protein aims to find its lowest energy state. SpiNNcloud supercomputers are good at solving optimization problems and can be used to find optimal protein structures."
The SpiNNcloud system employs a highly parallel architecture consisting of 48 SpiNNaker2 chips per server board, each containing 152 Arm-based cores with specialized accelerators. This design enables efficient, event-driven computation, allowing the system to perform complex simulations at a lower energy profile compared to traditional GPU-based systems. Such energy efficiency is crucial for applications where power consumption and cooling are limiting factors.
"Our brain-inspired computing architecture is uniquely suited for deploying efficient algorithms that require dynamic sparsity and extreme parallelism," said Hector Gonzalez, SpiNNcloud co-founder and CEO. "Our systems are 18 times more energy efficient than current GPUs and are being used by leading institutions across Europe and the US. The deployment in Leipzig demonstrates the flexibility of our systems, as well as the continued adoption of the technology for unrivaled performance and energy efficiency."
Looking ahead from a broader perspective, SpiNNcloud is enabling support for the next generation of Gen AI algorithms, paving a radically more efficient path to machine learning advancement through dynamic sparsity. Recent breakthroughs in machine learning are driving a transition from traditional dense modeling - centered on fixed feature selection within neural representations - to extreme dynamic sparsity, where a subset of neural pathways are selectively activated based on the input. This approach helps to shape entirely new architectures for AI foundation models, and addresses the current energy crisis driven by mainstream AI scaling trends.
"SpiNNcloud's approach reflects a broader shift in performance-intensive computing, where innovation demands that infrastructure and algorithms be co-designed from the ground up," said Peter Rutten, Research Vice-President, Performance Intensive Computing, Worldwide Infrastructure Research at IDC.
For more information about SpiNNcloud and the SpiNNcloud platform, please visit https://spinncloud.com.
About SpiNNcloud:
SpiNNcloud enables customers to realize complex AI-driven systems through brain-inspired supercomputing technology. Our SpiNNaker2 architecture supports dynamic sparsity in mainstream AI applications while delivering superior energy efficiency. As a winner of the prestigious EIC Accelerator program, SpiNNcloud continues to solidify itself as sole European champion for specialized AI Supercomputers.
Contact:
Forrest Carman
Owen Media
[email protected]
SOURCE: SpiNNcloud Systems GmbH
View the original press release on ACCESS Newswire
L.Miller--AMWN