[Feature Request] Flexible support for tcgen05 ld/st
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 7.4k
- Forks
- 745
- Avg merge
- 1d 5h
- Merged PRs (30d)
- 104
Description
Required prerequisites
- I have searched the Issue Tracker that this hasn't already been reported. (comment there if it has.)
Motivation
- Support lowering to tcgen05_ld 16dpxxxlanes, according to target fragment layout.
- Currently requires tcgen05_ld/st thread extents exactlly equal 128. However there may be multiple consumer warpgroups. Hence, we may only require the thread extent to be aligned with 128.
Solution
No response
Alternatives
No response
Additional context
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the tcgen05_ld/st lowering entry points and the target fragment layout handling. Confirm how 16dpxxxlanes is represented and how thread extents are validated; done means aligned extents support multiple consumer warpgroups without breaking existing lowering.
Written by the indexing model from the issue text.
Assessment
- Domain
- backend, compilers
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100