STAC-ML™ Pack for CUDA and cuDNN with 1 x NVIDIA A100 80GB PCIe GPU in a Supermicro SYS-620U-TNR Server, latency-optimized for the STAC-ML Tacana Suite

Type: Audited

Specs: STAC-ML™ Markets (Inference) Benchmarks (Tacana suite)

Stack under test:

• STAC-ML™ Pack for CUDA and cuDNN (Rev A)
• NVIDIA CUDA Toolkit 11.7
• NVIDIA CUDA Deep Neural Network library (cuDNN) 8.4.1.50
• gcc 9.4.0
• Ubuntu 20.04.5 LTS
• Supermicro Ultra SuperServer® SYS-620U-TNR
• 1 x NVIDIA A100 80GB PCIe Tensor Core GPU
• 2 x Intel® Xeon® Gold 6354 CPU @ 3.00GHz
• 16 x 32 GiB DDR4 @ 3200 MHz - 512GiB total memory