BC’s High Performance Computing (HPC) cluster, Andromeda, offers enterprise grade compute and data storage resource for your research needs. Initially installed in the Fall of 2020, it underwent an upgrade in January of 2022 and was further expanded in June or 2023. And is currently (2024) being expanded again.
Compute nodes
CPU Nodes
| Node Count | CPU Type | CPUs/node | Memory (RAM) |
| 92 | Intel Xeon Platinum 8260 @2.4Ghz | 48 | 192GB |
| 134 | Intel Xeon Platinum 8352Y @2.2Ghz | 64 | 256GB |
| 4 | Intel Xeon Platinum 8452Y @2.0Ghz | 72 | 512GB |
GPU Nodes
| Node Count | GPU Model | Memory(VRAM) | GPUs/node | CPU Type | CPUs/node | Memory (RAM) |
| 3 | Nvidia A100 | 320GB | 4 | Intel Xeon Platinum 8362 @2.8Ghz | 64 | 256GB |
| 4 | Nvidia A100 | 160GB | 4 | Intel Xeon Platinum 8358 @2.6Ghz | 64 | 256GB |
| 3 | Nvidia V100 | 64GB | 4 | Intel Xeon Platinum 8260 @2.4Ghz | 48 | 192GB |
| 2 | Nvidia A10 | 96GB | 4 | Intel Xeon Platinum 8362 @2.8Ghz | 64 | 512GB |
Node Totals
| Nodes | CPU(cores) | CPUs (RAM) | GPUs(cores) | GPUs (VRAM) |
| 230 (cpu) | 13,280 | 54,015GB (~55TB) | NP | NP |
| 12(gpu) | 720 | 3392GB | 48 | 1,984GB |
| 242 (total) | 14,000 | 57,470GB (~57TB) | 48 | 1,984GB |
Network
1Gbps Management/SSH between compute nodes
10Gbps Ethernet to Campus and Internet
200Gbps HDR Infiniband between compute nodes