Nvidia, in collaboration with the National Energy Research Scientific Computing Center (NERSC), started Perlmutter, labelled as the world’s fastest supercomputer for AI workloads. The supercomputer, named after renowned astrophysicist Saul Perlmutter is packed with 6,144 Nvidia A100 Tensor Core GPUs and will be tasked with making the largest ever 3D map of the visible universe, among other projects. Nvidia, during a press briefing last week said that the Perlmutter is the fastest system on the planet at processing workloads with the 16-bit and 32-bit mixed-precision math used in artificial intelligence (AI) applications. The company also said that later this year, it will add even more AI supercomputing power to the Perlmutter, which is kept at the NERSC at the Lawrence Berkeley National Laboratory in California, San Francisco.
Nvidia’s HPC/AI product marketing lead Dion Harris, in a blog post, said, “in one project, the supercomputer will help assemble the largest 3D map of the visible universe to date. It will process data from the Dark Energy Spectroscopic Instrument (DESI), a kind of cosmic camera that can capture as many as 5,000 galaxies in a single exposure.” He said that the researchers need the speed of Perlmutter’ GPUs to capture dozens of exposures from one night to know where to point DESI the next night. “Preparing a year’s worth of the data for publication would take weeks or months on prior systems, but Perlmutter should help them accomplish the task in as little as a few days,” Harris said in the blog post.
NERSC’s acting lead for data and analytics service group, Wahid Bhimji said that starting an AI-optimised supercomputer “represents a very real milestone.”AI for science is a growth area at the U.S. Department of Energy, where proof of concepts are moving into production use cases in areas like particle physics, materials science, and bioenergy,” Bhimji said.
The Perlmutter will give NERSC’s researchers access to four exaflops of mixed-precision computing performance for AI-assisted scientific projects. Researchers are also looking to make use of the supercomputer for work in fields like climate science, where Perlmutter will assist in probing subatomic interactions to discover green energy sources.
NERSC data architect Rollin Thomas said that in preparatory work with researchers to get code ready for Perlmutter supercomputer workloads, NERSC was seeing up to 20x faster GPU processing performance than in previously available systems.