FE optimization - #3546
Merged
Merged
Conversation
This makes shape evaluations *much* faster for rational shape functions
This doesn't do anything directly but it might help compiler optimization and it could definitely improve optimization in the future.
This helps speed up RATIONAL_BERNSTEIN maps a lot
This should let us use it for mapping functions (which can be expensive to do one by one with RATIONAL_BERNSTEIN), not just basis functions.
To avoid the slow code paths in RATIONAL_BERNSTEIN we need to avoid calling them *anywhere*.
This shaves a couple percent off of LIBMESH_BENCHMARK runs for me
Member
Author
|
Refs #2935, where I've been stashing benchmark results. |
|
Job Coverage on 4749734 wanted to post the following: Coverage
Warnings
This comment will be updated on new commits. |
||||||||||||||||||||||||||
jwpeterson
approved these changes
May 15, 2023
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
More all_shape* specializations (and more usage of them) enables us to take advantage of tensor products in LAGRANGE HEX evaluations and of the special structure of
RATIONAL_BERNSTEIN. Overall I've only shaved a couple percent off ofLIBMESH_BENCHMARK, but it doesn't hit those cases super hard. IGA is much less slow now.