Support `cp.async.bulk.ignore_oob` in `cub::detail::BlockLoadToShared`
Open
- Dominant language
- C++
- Stars
- 2.5k
- Forks
- 486
- Avg merge
- 2d 6h
- Merged PRs (30d)
- 295
Description
PTX ISA 9.2 probably brings a new `.ignore_oob` variant that improves the usability of bulk copying, since head and tail peeling are no longer required for copy size multiples and alignments smaller than 16 bytes. We should generate this new instruction in `cub::detail::BlockLoadToShared` when available.
Contributor guide
Assessment
This issue has not been assessed yet.