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)
  • 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

Please log in to see file attachments. If you are not registered, you may register for no charge.

The use of machine learning (ML) to develop models is now commonplace in trading and investment. Whether the business imperative is reducing time to market for new algorithms, improving model quality, or reducing costs, financial firms have to offload major aspects of model development to machines in order to continue competing in the markets.