May 27, 2021 was the day when the world’s fastest AI supercomputer was launched. Tech giant Nvidia and National Energy Research Scientific Computing (NERSC) were behind the making of this supercomputer. This supercomputer is the fastest supercomputer ever. This supercomputer is named Perlmutter. This supercomputer is named after Saul Perlmutter.
Saul Perlmutter Mr. Joe Lawrence is also an astrophysicist at Berkeley National Laboratory. Talking about Perlmutter, this supercomputer is said to be the fastest in performing tasks related to Artificial Intelligence (AI).
Nvidia’s product marketing lead revealed Perlmutter’s details via an official blog post. Harris said Perlmutter is the “fastest system on the planet” for processing workloads, including 16-bit and 32-bit mixed-precision arithmetic, which are used in various artificial intelligence applications.
However, at the beginning, Perlmutter would be tasked to create the largest 3D map of our universe so far before moving on to other AI-based projects in the future. In addition, the researchers will add even more AI computing power to the system as part of the second phase of its development later this year.
“In one project, the supercomputer will help assemble the largest ever 3D map of the visible universe. It will process data from the Dark Energy Spectroscopic Instrument (DESI), a kind of cosmic camera that captures 5,000 galaxies in a single exposure. Can capture,” Dion Harris wrote in a blog post.
Now, coming to the computer’s interior, Perlmutter packs 6,144 Nvidia A100 Tensor Core GPUs.
So, more than six thousand Nvidia GPUs will power the system to process some of the most complex AI-based tasks. It is expected to give more than 7,000 NERSC researchers access to four exaflops of mixed-precision computing performance for AI-based scientific research.
“Traditional supercomputers can barely handle the math required to generate simulations of a few atoms in a few nanoseconds with programs like Quantum Espresso. But by combining their highly accurate simulations with machine learning, scientists can study more atoms for longer periods of time. Vahid Bhimji, acting head of NERSC’s data and analytics services team, said.