The Polaris supercomputer, hosted at the laboratory’s Argonne Leadership Computing Facility (ALCF), will supercharge research and discovery with extreme scale for users’ algorithms and science. Accelerated by 2,240 Nvidia A100 Tensor Core GPUs, the system can achieve almost 1.4 exaflops of theoretical AI performance and approximately 44 petaflops of peak double-precision performance.
Polaris, to be built by Hewlett Packard Enterprise, will combine simulation and machine learning by tackling data-intensive and AI high-performance computing workloads, powered by 560 total nodes, each with four Nvidia A100 GPUs.
The system will accelerate transformative scientific exploration, such as advancing cancer treatments, exploring clean energy, and propelling particle collision research to discover new approaches to physics. Furthermore, it will transport the ALCF into the era of exascale AI by enabling researchers to update their scientific workloads for Aurora, Argonne’s forthcoming exascale system.
Polaris will also be available to researchers from academia, government agencies, and industry through the ALCF’s peer-reviewed allocation and application programs. These programs provide the scientific community with access to the nation’s fastest supercomputers to address grand challenges in science and engineering.