Use more threading in mesh algorithms
Open
roadmap
- Dominant language
- C++
- Stars
- 1.2k
- Forks
- 261
- Avg merge
- 1d 19h
- Merged PRs (30d)
- 71
Description
Add more threading to mesh topology computations
* dual graph construction
* sub-entity computation
Generally speed up mesh creation on multi-core machines, especially relevant to GPU, where often running one GPU per MPI rank, with many CPU cores.
Contributor guide
Assessment
This issue has not been assessed yet.