[BUG] atomics should always fully qualify when calling internal functions
Open
- Dominant language
- C++
- Stars
- 2.5k
- Forks
- 486
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 295
Description
> not related to this PR but important, missing qualifications
> ```suggestion
> ::__atomic_store(&::cuda::std::__atomic_force_align_host(__a)->__atom, &__val, ::cuda::std::__atomic_order_to_int(__order));
> ```
> applies to other occurences
_Originally posted by @fbusato in [#3440](https://github.com/NVIDIA/cccl/pull/3440/files#r2414866407)_
Contributor guide
Assessment
This issue has not been assessed yet.