Skip to content
Discussion options

You must be logged in to vote

My plan for texture/surface objects is just to move what I implemented in CuPy to cuda.core (#467), and perhaps make cuda.core.launch() recognize these objects, similar to SMV that we discussed in the other issue.

However, if you already have working CuPy code today that allocates texture objects, you should already be able to pass tex_obj.ptr to cuda.core.launch() and reuse/launch the same C++ kernel that accepts a texture object. Let me know if it does not work for you!

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by leofang
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants