`prefetch` on sycl with cuda backend on Windows

Open mmoadeli opened this issue 1 year ago • 1 comments

Windows doesn't support cudaMemPrefetchAsync() which is used in the call to prefetch. Would be a need to investigate alternatives for Windows.

https://github.com/intel/llvm/pull/13957 may be used to further information.

Jun 03 '24 12:06 mmoadeli

Is this not already dealt with by https://github.com/oneapi-src/unified-runtime/blob/f06bc02a24418990ecb9d41471b729f32aebd804/source/adapters/cuda/enqueue.cpp#L1644

Or maybe we need a similar fix in other parts of the code?

Jun 05 '24 12:06 JackAKirk