Re: Passing gil::image and gil::kernel to CUDA

From: Mateusz Loskot (mateusz_at_[hidden])
Date: 2019-10-20 20:28:42

On Sun, 20 Oct 2019 at 13:00, Olzhas Zhumabek
<anonymous.from.applecity_at_[hidden]> wrote:
>
> I found out that to be able to call any GIL functions from device (e.g.
> GPU), they have to be marked __device__ (and __host__ too, to call from CPU
> side as well) recursively. So I guess I'll abandon the project. My plan for
> now is to write a thin wrapper around image, image_view and kernel.

I see no reason why such wrapper could not be added to GIL as an extension.

ML