A company called SPiNNcloud is pioneering computational power for drug discovery with a brain-inspired supercomputer. The company sealed a multi-million Euro deal to deliver the supercomputer to Leipzig University in Germany. This partnership aims to significantly advance drug discovery, specifically small-molecule research. It reportedly provides the university with the largest SpiNNcloud System dedicated to drug discovery.
Supercomputer Drug Discovery
SpiNNcloud’s server system is reportedly capable of simulating a minimum of 10.5 billion neurons for various applications, including AI and High-Performance Computing (HPC). In addition, it utilizes numerous low-power processors.
Leipzig University’s primary goal is protein folding simulations, which researchers say are crucial for the advancement of personalized medicine. They say the approach leverages parallelism and scale to deploy millions of small models to identify interactions between molecules and patient profiles. Furthermore, researchers expect to accelerate the discovery of new personalized drugs.
Explore Tomorrow's World From Your Inbox
Get the latest science, technology, and sustainability content delivered to your inbox.
I understand that by providing my email address, I agree to receive emails from Tomorrow's World Today. I understand that I may opt out of receiving such communications at any time.
They say the system will also have a lower energy footprint than conventional 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’s 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.”
The system’s parallel architecture is reportedly “highly accurate.” Its accuracy enables “efficient, event-driven computation.” According to the researchers, its design enables complex simulations but uses less energy than traditional systems, which gives the supercomputer system an advantage where power consumption and cooling are constraints.
“Our systems are 18 times more energy efficient than current GPUs,” Hector Gonzalez, SpiNNcloud co-founder and CEO, claims.
Peter Rutten, Research Vice-President at IDC, added, “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.”
