Skip to content

Check error codes from CUDA functions

Kenneth Moreland requested to merge kmorel/vtk-m:check-cuda-errors into master

Most functions in the CUDA runtime API return an error code that must be checked to determine whether the operation completed successfully. Most operations in VTK-m just called the function and assumed it completed correctly, which could lead to further errors. This change wraps most CUDA calls in a VTKM_CUDA_CALL macro that checks the error code and throws an exception if the call fails.

Merge request reports