Skip to content

Conversation

@roystgnr
Copy link
Member

@roystgnr roystgnr commented Oct 9, 2018

This should be just as fast for restarts and O(Nsplits/Nprocs) times
faster for mesh splitting. Thanks to @friedmud for the idea.

I'm about to head home so I haven't yet made 100% sure this optimizes things. Or works correctly. Or compiles. Hopefully @friedmud can check up on the first question and Civet will scream at me if I've flubbed the latter two.

This should be just as fast for restarts and O(Nsplits/Nprocs) times
faster for mesh splitting.  Thanks to @friedmud for the idea.
@roystgnr
Copy link
Member Author

roystgnr commented Oct 9, 2018

Ping #1859 where the idea was floated.

@friedmud
Copy link
Member

friedmud commented Oct 9, 2018

Testing this momentarily

@friedmud
Copy link
Member

friedmud commented Oct 9, 2018

Also: put in a PR for the new node_to_elem map based ghosting functor: #1887

@roystgnr
Copy link
Member Author

#1859 (comment) is awesome - merging.

@roystgnr roystgnr merged commit 483e8f7 into libMesh:master Oct 10, 2018
@roystgnr roystgnr deleted the cache_sorted_bcs branch October 10, 2018 02:42
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants