Explore the use of `@inline` for kernel performance
Open
enhancement
- Dominant language
- Julia
- Stars
- 147
- Forks
- 30
- Avg merge
- 10h 28m
- Merged PRs (30d)
- 11
Description
Currently, it was reported that `@inline` give kernel code passed to the back end speed ups.
We would like to investigate this more for different workloads.
Contributor guide
Research direction
No files, tests, or specific entry points are named. Start by locating the kernel code passed to the back end and define representative workloads for comparison; done means documenting whether @inline consistently improves kernel performance across those workloads.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- performance
- Issue type
- Refactor
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100