Chipmaker AMD along with the US Department of Energy, Oak Ridge National (ORNL) Laboratory and Cray Inc have announced what they claim to be the fastest exascale-class supercomputer. This beast of a device is scheduled to be delivered to ORNL in 2021.
Exascale computing refers to computing systems capable of at least one exaFLOPS, or a quintillion calculations per second. The supercomputer called the Frontier system, provides in excess of 1.5 exaflops of raw computing power. As per AMD, the Frontier system is designed to use AMD EPYC CPU, and AMD Radeon Instinct GPU processors. These are optimised for future generation High-Performance Computing (HPC) and Artificial Intelligence.
The Frontier system also has a custom high-bandwidth and low-latency coherent Infinity Fabric which connects our AMD Radeon Instinct GPUs to one AMD EPYC CPU per node.
“AMD is proud to partner with Cray and ORNL to deliver what is expected to be the world’s most powerful supercomputer,” said Forrest Norrod, senior vice president and general manager, AMD Datacenter and Embedded Systems Group.
ORNL researchers will be using the Frontier system to “simulate, model and advance understanding of the interactions underlying the science of weather, sub-atomic structures, genomics, physics, and other important scientific fields.”
“Frontier represents the state-of-the-art in high-performance computing. Designing and standing up a machine of its scope requires working closely with industry, partnerships which not only enable breakthrough science but also ensure American scientific and economic competitiveness on the global stage,” said Jeff Nichols, associate laboratory director for Computing and Computational Sciences, ORNL.