The New Frontier Initiative’s Hydro system was a compute cluster focused on supporting research and development related to national security and preparedness as well as research in other domains.
System Description
The system was composed of 70 nodes, together making available 944 Intel Sandy Bridge cores, 256 AMD Interlagos cores, and 560 AMD Rome & Milan cores with over 27TB aggregate system memory, as well as 18 NVIDIA 80GB A100 GPUs.
All nodes were connected to 4 PB of Lustre-based parallel storage across two filesystems.
FDR Infiniband connected the storage, while 40Gbe and 100Gbe connect the nodes to the internet. Both IB and Ethernet networks were usable by MPI communications.
Software Environment
The software environment included:
- RHEL 8 OS
- SLURM job scheduler
- Singularity container support
- NVIDIA CUDA 11.7 GPU toolset