NVIDIA / NVIDIA/cccl

Support `cp.async.bulk.ignore_oob` in `cub::detail::BlockLoadToShared`

Open
#7,168 2 comments 0 reactions 1 assignee Assigned to @pauleonix View on GitHub
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.