Home > Workload Solutions > High Performance Computing > White Papers > Dell Validated Design for Government HPC, Artificial Intelligence, and Data Analytics: AI Inferencing Option > System configuration
Performance benchmarking was conducted in the Dell HPC and AI Innovation Lab using the system configuration listed in Table 4.
Benchmark system configuration |
PowerEdge XE9680 |
Dual Intel Xeon Platinum 8480+ |
1TB GB RAM 32x 32 GB 4800 MT/s DIMMs @ 4400MT/s |
8x NVIDIA H100-SXM-80GB GPUs |
1.5TB NVMe |
The BIOS configurations used for the reference systems are described below:
BIOS Option | Settings |
Logical processor | Enabled |
System profile | Performance |
Sub NUMA Clustering | Disabled |
Component | Version |
Operating System | Red Hat Enterprise Linux 8.6 |
Kernel | 4.18.0-372.9.1.el8.x86_64 |
Omnia | 1.5 |
NVIDIA GPU Driver | 545.23.08 |
CUDA | 12.3.1 |
Kubernetes | 1.19 |
MLPerf | Inference 3.1 |