Improve decomposition and geometry reading #817
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rupertnash
force-pushed
the
debug-decomp
branch
3 times, most recently
from
841e74a to
efbe76c
Compare
rupertnash
force-pushed
the
debug-decomp
branch
2 times, most recently
from
e2d5459 to
cd76198
Compare
I could not understand how the OptimisedDecomposition class worked while trying to track down a bug. This lead to a complete re-write of how the distributed graph optimised by ParMETIS was constructed and how the "moves" (i.e. which vertices need to go to which process) were calculated. This has been rewritten in a much simpler and slightly faster way, using the net::SparseExchange class. The GeometryReader is also much simpler and leans more on the octree to avoid unnecessary work. The IO pattern is much simpler also now: the GMY block data is now collectively streamed onto node "leader" processes and then individual MPI processes copy out the parts they care about.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
I failed to find the cause of @CharlesQiZhou's bug beyond "something in the domain decomposition".
This massive simplification is now passing tests and appears to be a bit faster although I've not done detailed scaling comparisons.
Charles - can you please check if it's working for you?