Alpaka: Build correct workDiv for HIP devices. #580
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Outdated suggestions cannot be applied.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.
This is a tiny change that was missed as part of the Alpaka HIP work.
Without it, we'd be making
workDiv
s for the CPU and attempting to run them on the GPU...which isn't ideal and obviously broke lots of things (in testing the HIP code would run part of the seeding before crashing, due to incorrectly formed spacepoint binning).With this change, we now have HIP-backed Alpaka results working!
This is on a machine with a few AMD Instinct MI210, and 2 AMD EPYC 7F72 CPUs.
This is just from the
seeding_example
at the moment, but will look at integrating with my other PR (#558) to get some more realistic numbers soon.There is still an instability, where if compiled for debugging there is a crash...which I'm hoping is the same sort of crash that I'm hitting every so often in the Alpaka-CUDA version, so will be debugging separately.