GPU Requirements

Both integrated and dedicated GPUs can work well with Zivid.

An OpenCL driver (1.2 or later) for the GPU is necessary to use Zivid.

For Windows, it is usually installed together with the graphics driver: Nvidia, AMD, Intel.
For Linux, you usually need to install the OpenCL driver.

Follow the instructions on how to check whether you have the OpenCL.

Integrated CPU

CPU with integrated GPU

The is the most cost-efficient and preferred solution for Zivid. The benefit of an integrated GPU is that the data transfer from GPU to CPU is fast. A high-end integrated GPU with 3GB of memory available is required for optimal performance.

Recommendations:

AMD Ryzen 5 2400G or better
- NOTE: Radeon no longer supports SPIR on some GPUs, please verify your GPU drivers support SPIR to be compatible with Zivid Software.
- NOTE: Zivid no longer supports AMD on Ubuntu 16.04 (AMD dropped support for Ubuntu 16.04 as of Radeon Software 18.50 for Linux).
Intel i7 with HD630 or better

Dedicated GPU

This solution may be best if the GPU is planned to be used for more than Zivid computations. A medium to high-end AMD or Nvidia GPU with 3GB of memory is required for optimal performance.

Requirements:

Nvidia GPUs must have compute capability higher than a minimum required value of 3.3.
- If this requirement is not fulfilled, the SDK will throw an exception The compute capability X.Y of the Nvidia compute device is lower than the minimum required compute capability 3.3 (or The minimum required SM version is 3.3. Device has version X.Y).
- An overview of Nividia GPUs and their corresponding compute capability can be found in https://developer.nvidia.com/cuda-gpus.