Developed in collaboration with Hewlett Packard Enterprise (HPE), Polaris is a leading-edge testbed system that will give scientists and application developers a platform to test and optimize codes for Aurora, Argonne's upcoming Intel-HPE exascale supercomputer.
The Polaris software environment is equipped with the HPE Cray programming environment, HPE Performance Cluster Manager (HPCM) system software, and the ability to test programming models, such as OpenMP and SYCL, that will be available on Aurora and the next-generation of DOE’s high performance computing systems. Polaris users will also benefit from NVIDIA’s HPC software development kit, a suite of compilers, libraries, and tools for GPU code development.
Polaris and Aurora will have many similarities at the system and user level.
Polaris System Specs
Peak Performance
44 Petaflop DP
NVIDIA GPU
A100
AMD EPYC Processor
Milan*
Platform
HPE Apollo Gen10+
Compute Node
1 AMD EPYC "Milan"* processor; 4 NVIDIA A100 GPUs; Unified Memory Architecture; 2 fabric endpoints; 2 NVMe SSDs
GPU Architecture
NVIDIA A100 GPU; HBM stack
CPU-GPU Interconnect
CPU-GPU: PCIe; GPU-GPU: NVLink
System Interconnect
HPE Slingshot 11*; Dragonfly topology with adaptive routing
Network Switch
25.6 Tb/s per switch, from 64–200 Gb/sports (25 GB/s per direction)
Node Performance
78 TF DP
System Size
560 nodes
* Processor will be upgraded to Milan and fabric to Slingshot 11