[Feature]: Analyze and implement a fast path for local accesses
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 202
- Forks
- 47
- Avg merge
- 6d 11h
- Merged PRs (30d)
- 4
Description
Suggestion Description
Users may use iris.load or other APIs for local accesses, however, at the moment translation will still take place. Ideally, we have a past path for local accesses by using an if statement. It is unclear if that if statement will add an overhead for the main (remote) memory access path so some measurement is required before adding this change.
Operating System
No response
GPU
No response
ROCm Component
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 tracing iris.load and the other local-access APIs through the translation path. Benchmark local and remote memory accesses before and after any proposed fast path; done means local accesses avoid unnecessary translation without adding unacceptable overhead to remote accesses.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- distributed-systems, performance
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100