kokkos / kokkos/kokkos.github.io
Direct Measurement Numerical Accuracy
Nobody has claimed this yet.
- Dominant language
- HTML
- Stars
- 3
- Forks
- 27
- Avg merge
- 2d 25m
- Merged PRs (30d)
- 11
Description
Shaman uses Error Free Transforms to explicitly evaluate order 1 rounding error of IEEE floating point. It works as a library and it just needs the user to replace their scalar types by Shaman's. We will soon adapt it to integrate well with Kokkos and be able to assess numerical accuracy of GPU kernels.
The long term goal is to ease the move to cheaper and faster datatypes introduced for AI computations.
Contributor guide
No contributing guide indexed for this repository
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
The issue names Shaman, Error Free Transforms, IEEE floating point, Kokkos, and GPU kernels, but no repository file, test, or entry point. Start by clarifying the intended website or integration change and its acceptance criteria; completion cannot be determined from the current description.
Written by the indexing model from the issue text.
Assessment
- Domain
- performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100