Add HIP backend to runahead scheduling #143
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added HIP support for new scikit-build-core driven compilation to support AMD machines.
Runahead scheduling bugs still exist here, but ..are shared between CUDA and HIP. They will be fixed in a followup PR.
Everything should be working for non-runahead and via CuPy.
Be aware that CuPy does not support sparse CUSOLVER routines with ROCm and our initialization skips this preinit step.
On Cray systems you may need to add cce libraries to your LIBRARY_PATH manually. I haven't been able to resolve this automatically on Tioga.
On TIOGA you may need to filter HIP_VISIBLE_DEVICES to 0,2,4,6.