DifferentiableUniverseInitiative / DifferentiableUniverseInitiative/flowpm
Benchmarking full N-body simulation on GPU clusters
- Dominant language
- Jupyter Notebook
- Stars
- 93
- Forks
- 20
- PR merge metrics
- No merged PRs in 30d
Description
This issue is to track the work on benchmarking the new Horovod backend for GPU clusters and getting profiling information for FlowPM.
We want to do the following things:
- [x] : Run profiler on https://github.com/DifferentiableUniverseInitiative/flowpm/blob/mesh_update/scripts/mesh_nbody_benchmark.py and https://github.com/DifferentiableUniverseInitiative/flowpm/blob/mesh_update/scripts/pyramid_nbody.py
- [ ] : Compare the performance of both implementations as a function of the mesh size
- [x] : Identify the most costly parts of the computation
To learn how to do this profiling, keep an eye on https://github.com/DifferentiableUniverseInitiative/IDRIS-hackathon/issues/2
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.