Is it possible to run CUDA on AMD GPUs?

Nope, you can’t use CUDA for that. CUDA is limited to NVIDIA hardware. OpenCL would be the best alternative.

Khronos itself has a list of resources. As does the StreamComputing.eu website. For your AMD specific resources, you might want to have a look at AMD’s APP SDK page.

Note that at this time there are several initiatives to translate/cross-compile CUDA to different languages and APIs. One such an example is HIP. Note however that this still does not mean that CUDA runs on AMD GPUs.

Related Posts:

  1. NVIDIA NVML Driver/library version mismatch
  2. When to call cudaDeviceSynchronize?
  3. How do I select which GPU to run a job on?
  4. How to get the CUDA version?
  5. How to get the CUDA version?
  6. Error Message : Cannot find or open the PDB file
  7. Cudamemcpy function usage
  8. CUDA driver version is insufficient for CUDA runtime version
  9. Error compiling CUDA from Command Prompt
  10. How to verify CuDNN installation?
  11. Does __syncthreads() synchronize all threads in the grid?
  12. ImportError: libcublas.so.9.0: cannot open shared object file
  13. How to tell if tensorflow is using gpu acceleration from inside python shell?
  14. Import error when trying to import tensorflow with gpu
  15. Tensorflow not running on GPU
  16. Relation between CommonJS, AMD and RequireJS?
  17. Does Numpy automatically detect and use GPU?
  18. Error: OOM when allocating tensor with shape
  19. Android Studio – How Can I Make an AVD With ARM Instead of HAXM?
  20. Use of cudamalloc(). Why the double pointer?
  21. X Error of failed request: BadValue (integer parameter out of range for operation)

Leave a Comment