Unify accumulator type handling across CUB/Thrust
Open
- Dominant language
- C++
- Stars
- 2.5k
- Forks
- 486
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 295
Description
I vaguely remember that not every reduce or scan algorithm uses `::cuda::std::__accumulator_t` to determine the accumulator type to use. We should consolidate this behavior.
Contributor guide
Assessment
This issue has not been assessed yet.