Hewlett Packard Enterprise and the Department of Energy’s Argonne National Laboratory have launched a testbed supercomputer designed to help developers and scientists optimize artificial intelligence, scientific and engineering projects planned for Aurora, the forthcoming exascale supercomputer.
The Argonne Leadership Computing Facility will host and manage the Polaris testbed supercomputer, which will be installed by HPE starting in August, ANL said Wednesday.
HPE will use 280 HPE Apollo Gen10 Plus systems to build Polaris, which ANL said will “deliver approximately 44 petaflops of peak double precision performance and nearly 1.4 exaflops of theoretical AI performance.”
Polaris will be available for use by early 2022. The high performance computing community can begin using the supercomputer by the spring of 2022.
“Beyond getting us ready for Aurora, Polaris will further provide a platform to experiment with the integration of supercomputers and large-scale experiment facilities, like the Advanced Photon Source, making HPC available to more scientific communities,” said Michael Papka, director of ALCF.
“Polaris will also provide a broader opportunity to help prototype and test the integration of HPC with real-time experiments and sensor networks,” added Papka.
Argonne also collaborates with HPE and Intel on the Aurora exascale supercomputer.