Is it possible to do asynchronous transfers (and kernel callls, 1.1) to device data that’s bound to a texture. Or do I have to do the memcopy synchronously if I intend to bind to a texture?
I’ve tried:
Async memcopy to device
Bind to texture
Make Kernel call (one for each stream)
Async memcopy to host
I don’t get any errors, but I also don’t get the correct result :D
If I just do async copy things work well and if I just to texture binding things work well also. I’m just wondering if I can combine both ideas.