| Sustained/peek performance |
6.9 petaflops/10.1 petaflops |
| Number of compute nodes/CPUs/cores |
960 nodes, 1920 CPUs AMD Epyc 7H12, 122.000 cores |
| Number of GPU nodes/GPUs |
60 GPU nodes, 240 GPUs NVidia A100 with 40 GB HBMI2, 120 CPUs AMD Epyc 7H12, 7680 CPU cores |
| CPU Partition |
768 nodes with 256 GB, 192 nodes with 1 TB of RAM DDR4-3200, local 1.92 TB M.2 SSD |
| GPU Partition |
60 nodes with 512 GB of RAM DDR4-3200, local 1.92 TB M.2 SSD |
| Storage |
High-Performance Storage Tier (HPST): 10 DDN Exascaler ES400NVX (NVMe disks), usable capacity 1 PB, Large-Capacity Storage Tier (LCST): 61 storage nodes, 23 PB Raw, 18 PB Usable |
| Login and virtualization nodes |
4 CPU login nodes, 4 GPU login nodes, 30 virtualization nodes |
| External interface |
NorduGrid ARC |
| Rescource manager and scheduling |
Slurm |
| Virtualization software |
Red Hat Virtualization |
| Operating System |
Red Hat Enterprise Linux 8 |
| Software and RunTimeEnvironment |
Modules / Singularity |