Setting performance tuning parameters for GPU kernels
Open
@shakedregev is already working on this.
Since Feb 26, 2026.
cuda
enhancement
hip
question
- Dominant language
- C++
- Stars
- 84
- Forks
- 13
- PR merge metrics
- No merged PRs in 30d
Description
Perhaps we should consider how to replace magic numbers used for performance parameters in GPU kernels with something that can be more easily adjusted, if needed. It would be good to allow expert user to tune code performance by setting these parameters.
Originally posted by @pelesh in https://github.com/ORNL/ReSolve/pull/83#discussion_r1408097301
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.
Assessment
This issue has not been assessed yet.