[FEA]: Improve performance of atomic_ref
Open
- Dominant language
- C++
- Stars
- 2.5k
- Forks
- 486
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 295
Description
This will generate release/acquire/acq_rel/seq_cst fences within the inner loop, but it'd suffice to issue the right fences before/after the loop.
_Originally posted by @gonzalobg in https://github.com/NVIDIA/cccl/pull/2255#discussion_r1779740262_
Contributor guide
Assessment
This issue has not been assessed yet.