Cerebras Systems, a pioneer in wafer-scale processing, in collaboration with researchers from Sandia, Lawrence Livermore, and Los Alamos National Laboratories, has set another world record and important breakthrough in molecular dynamics (MD) simulations. For the first time in the history of the field, researchers achieved more than 1 million simulation steps per second. A single Cerebras Wafer Scale Engine achieved over 1.1 million steps per second, which is 748x faster than what is possible on the world’s leading supercomputer ‘Frontier.’
In addition, Cerebras outperformed Anton 3 – the world’s leading purpose-built supercomputer for molecular dynamics. Anton 3 uses 512 specialized processors and 400 kilowatts of power. In contrast, the Cerebras system uses a single accelerator, 7% of the power, and outperforms Anton 3 by 20%.
“This new world record means that scientists can now complete two years’ worth of GPU-based simulation work every single day. This will greatly accelerate the rate of innovation derived from molecular simulations,” said Michael James, Chief Architect of Advanced Technologies and co-founder of Cerebras Systems. “This critical breakthrough will provide insights into material structure and function. When we extend our work to biomolecules, it will unlock new capabilities in protein folding, medicine, and drug development.”
Supercomputing performance can be achieved via weak scaling or strong scaling. Weak scaling increases the size of a simulation, while strong scaling increases its speed. Existing supercomputer designs use many GPUs to increase simulation scale at the same speed. Cerebras, in contrast, achieves strong scaling – it accelerates simulation speed by hundreds of times over today’s leading supercomputers. Faster speed allows scientists to simulate materials longer, effectively seeing into its future.
Without strong scaling, existing supercomputers have been limited to simulating materials at the atomic scale for a few microseconds. This breakthrough by Cerebras and scientists at US national laboratories gives researchers a new scientific instrument to investigate vital materials at the millisecond timescale, a view 1,000x further than what is possible today.
“The partnership between the NNSA laboratories and Cerebras Systems is part of the Advanced Memory Technology (AMT) program, which aims to accelerate exascale supercomputers by 40x as early as 2025. With Cerebras’ currently deployed wafer-scale computers, the teams achieved this materials science breakthrough and a speedup that exceeded the goal of the AMT program by more than 4X,” said James H. Laros III, Distinguished Member of Technical Staff and AMT program lead. “This experience bodes well for future impacts on our program and potential scientific advances.”
Long timescale simulations allow scientists to explore previously inaccessible phenomena across a wide range of domains:
- Materials scientists can now study the long-term behavior of complex materials, such as the evolution of grain boundaries in metals, leading to the development of stronger, more resilient materials.Pharmaceutical researchers can simulate protein folding and drug-target interactions over physiologically relevant timescales, accelerating the discovery of life-saving therapies.Renewable energy experts can optimize catalytic reactions and design more efficient energy storage systems by simulating atomic-scale processes over extended durations.
Sandia recently announced the deployment of a cutting-edge Cerebras CS-3 testbed for future AI workloads.
This work has been nominated as a finalist for the ACM Gordon Bell Prize. For more information on this molecular dynamics simulation work, please see the paper on ArXiv.
This article first appeared on sister site HPCwire.
