NVIDIA® GPU Requirements

The following information covers the requirements when utilizing an NVIDIA GPU with your ViDi application. The GPU is utilized by ViDi during the development of your application, typically with the training of tools. In addition, a GPU can also be used with the In-Sight ViDi PC during runtime deployment, where it increase performance of runtime workspaces.

Note:
  • While technically a GPU is not required, it greatly improves the speed and performance while training ViDi tools. Therefore, Cognex highly recommends the use of a GPU.
  • A GPU does not affect the performance of the In-Sight D900 series vision system during runtime. With the vision system, the runtime workspace executes solely on the vision system itself.

NVIDIA Driver Support

  • NVIDIA GeForce® driver greater than or equal to 431.86 (Creator Ready)

  • NVIDIA Quadro® driver greater than or equal to 431.94 (Optimal Driver for Enterprise)

    Note: For more information about supported drivers, please visit the Cognex Support Site.

Supported NVIDIA GPUs

GPU Model Performance Level System Power Supply

NVIDIA GeForce®

GTX 1060

Low to Medium

≥ 500W

GTX 1070

Medium

≥ 600W

GTX 1080 Ti

High

≥ 600W

RTX™ 2070

Medium

≥ 550W

RTX 2080

Medium to High

≥ 650W

RTX 2080 Ti

High

≥ 650W
RTX 3080 High ≥ 650W

NVIDIA Quadro®

P2000

Low

≥ 500W

P4000

Medium to High

≥ 600W

GV100*

High

≥ 600W

RTX 4000

Medium

≥ 550W

RTX 5000

Medium to High

≥ 650W

RTX 6000

High

≥ 650W

RTX 8000

High

≥ 650W

Titan V*

High

≥ 600W

Titan RTX

High

≥ 650W

NVIDIA Tesla®

P5000

High

≥ 600W

V100*

High

≥ 600W
Note:

  • When selecting a GPU, Cognex only supports NVIDIA GPUs. Consider the following when choosing an NVIDIA GPU:

    At a minimum, an NVIDIA® CUDA® enabled GPU. When selecting an NVIDIA GPU, a unit with a higher core clock frequency, CUDA cores and Tensor cores will result in faster computational speeds. Due to this, Cognex strongly recommends the use of NVIDIA Quadro and Tesla GPUs for the following reasons:

    • These GPUs support the compute-optimized Tesla Compute Cluster (TCC) mode.
    • These GPUs are designed and tested for continuous duty-cycle operation.
    • These GPUs undergo rigorous testing and qualification by NVIDIA.
  • In-Sight ViDi 1.5.0 supports the use of any NVIDIA CUDA® enabled GPU that provides a compute capability of 3.0 and higher, and requires a driver version greater than or equal to 431.86.
  • CUDA compute capability 3.0 or higher is required to use the core ViDi functionality. The Low Precision parameter requires CUDA compute capability 6.1 or higher (for more information, visit the NVIDIA website).
  • A minimum of 4 GB of GPU memory is required for runtime operation, and a minimum of 8 GB of GPU memory is required for training.
  • The NVIDIA GeForce Titan V, Quadro GV100 and Tesla V100 include NVIDIA Tensor Cores. ViDi 4.1.3 will automatically utilize Tensor Cores if they are present, provided you have a Standard or Advanced security license. Please contact your Cognex Sales Representative for information about enabling the functionality on your Cognex Security Dongle.