How to copy from cuda allocated memory to directx10 texture memory

Hi

I’m trying to use some data processed by a CUDA kernel as a texture in a DirectX shader. I can get a texture pointer by mapping it, and then do a memcopy, but I’m unsure whether this is the best way to do it.

The flow is basically this:

Data in -> Process in CUDA -> Transfer to DirectX Texture -> Render to a surface using a shader -> Flip buffers

Is there any “best practice” way of doing this? I have not been able to find anything in the documentation.

Thank You

Henrik

Hi

I’m trying to use some data processed by a CUDA kernel as a texture in a DirectX shader. I can get a texture pointer by mapping it, and then do a memcopy, but I’m unsure whether this is the best way to do it.

The flow is basically this:

Data in -> Process in CUDA -> Transfer to DirectX Texture -> Render to a surface using a shader -> Flip buffers

Is there any “best practice” way of doing this? I have not been able to find anything in the documentation.

Thank You

Henrik