A supercomputer is a computer that performs at or near the highest operational rate for computers. Traditionally, supercomputers have been used for scientific and engineering applications that must handle massive databases, do a great amount of computation or both.
Supercomputers were originally used in applications related to national security, including nuclear weapons design and cryptography. Today they are also routinely employed by the aerospace, petroleum, and automotive industries.
The supercomputer will be able to help with modelling and simulating complex scientific research, across biological, physical and chemical sciences. It can be used to develop AI models that are 4.5X faster and 8X larger, allowing to train more data that can increase predictability and speed time-to-discovery, according to HPE.
Exascale computing refers to computing systems capable of calculating at least 10¹⁸ floating point operations per second. The terminology generally refers to the performance of supercomputer systems, with the Fugaku being the first supercomputer in history to hit this milestone
The first exascale computer has officially arrived.
The world’s fastest supercomputer performed more than a quintillion calculations per second, entering the realm of exascale computing. That’s according to a ranking of the world’s speediest supercomputers called the TOP500, announced on May 30. The computer, known as Frontier, is the first exascale computer to be included on the biannual list.
Exascale computing is expected to allow for new advances in a variety of scientific fields that depend on vastly complex calculations. The exascale milestone “represents an unprecedented capability for researchers around the world to use the computer to ask their specific scientific questions,” says Frontier’s project director Justin Whitt of Oak Ridge National Laboratory in Tennessee.
Oak Ridge’s Frontier clocked in at about 1.1 exaflops, or 1.1 quintillion operations per second. Frontier beat out the previous record-holder, a supercomputer called Fugaku at the RIKEN Center for Computational Science in Kobe, Japan, which achieved more than 0.4 exaflops.
While tentative reports have suggested that some Chinese supercomputers are already achieving exascale performance, they have not been reported on the TOP500 ranking so far.
After about three years of development, Frontier will be ready for scientists to begin using it at the end of 2022. With its new exascale capability, researchers aim to simulate how stars explode, calculate the properties of subatomic particles, investigate new energy sources such as nuclear fusion and harness artificial intelligence to improve the diagnosis and prevention of disease, among many other research topics.
“Frontier is a first-of-its-kind system that was envisioned by technologists, scientists and researchers to unleash a new level of capability to deliver open science, AI (artificial intelligence) and other breakthroughs, that will benefit humanity,” Justin Hotard, EVP and GM, HPC & AI, at HPE, said in a statement.
Frontier has 8,730,112 total cores and is built on the latest HPE Cray EX235a architecture and powered with AMD EPYC 64C 2GHz processors. Fugaku, now the second-most powerful supercomputer, has 7,630,848 cores.
Frontier is also ranked number one as the world’s most energy-efficient supercomputer, on the Green500 list, which measures supercomputing energy use and efficiency, with 52.23 gigaflops performance per watt, making it 32% more energy-efficient compared to the previous number one system, according to HPE.
The most powerful supercomputer in the world is expected to reach even higher levels of speed with a theoretical peak performance of 2 exaflops.
You must be logged in to post a comment.