The U.S. Department of Energy’s Argonne National Laboratory has selected Hewlett Packard Enterprise to build a new testbed supercomputer to prepare critical workloads for future exascale systems that will deliver up to four times faster performance than Argonne’s current supercomputers.
The new system, which Argonne has named Polaris, will deliver approximately 44 petaflops of peak double precision performance and nearly 1.4 exaflops of theoretical AI performance, which is based on mixed-precision compute capabilities.
Polaris uses 280 HPE Apollo Gen10 Plus systems, which are HPC and AI architectures built for the exascale era and customized to include the following:
- 560 2nd and 3rd Gen AMD EPYC processors
- 2240 NVIDIA A100 Tensor Core GPUs, making it ALCF’s largest GPU-based system to date.
- HPE Slingshot, a high performance Ethernet fabric designed for HPC and AI solutions. HPE Slingshot will also be featured in Argonne’s Aurora exascale system.
- HPE Performance Cluster Manager, a system management software solution.
“As we approach the exascale era, which will power a new age of insight and innovation, high performance computing (HPC) will play a critical role in harnessing data to take on the world’s most pressing challenges. Increasingly, the computational power and scale required to process artificial intelligence and machine learning data sets can only be delivered through HPC systems, and HPE uniquely provides a powerful, software-driven platform capable of tackling complex scientific data and simulations,” said Justin Hotard, senior vice president and general manager, HPC and Mission Critical Solutions at HPE.
