pyop3 #3318
Draft
pyop3 #3318
Conversation
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
Required to figure out how to do permuted maps (not too hard but ugly).
Had to add Dat.inner (in a much less stupid way).
* Ensemble fixes (slightly API breaking) * Remove refs to layout_vec in favour of template_vec
Needed for packing mixed things with transforms.
Still getting some failures for diagonal assembly.
I've observed that the cell-node list is different for degree>=3 which might be causing issues. Therefore I'm trying to apply the orientations to every pack operation.
Key is that the heuristics were local and so the materialisation steps would diverge. We now have compute-rank-0-then-bcast strategy that works and is hopefully not too expensive.
This is tricksy because it means that we apply bizarre permutations for simplex and quad meshes that we don't strictly need to, but it's consistent with the current approach.
Sheesh that was difficult! Things still appear to be very slow.
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Outdated suggestions cannot be applied.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.
Replace PyOP2 with pyop3.
Thesis link
Summary
Data structures for unstructured meshes are much more complicated than N-dimensional arrays. Firedrake therefore does an awful lot of very involved bookkeeping to make sure that things work.
The key contribution of pyop3 is a new abstraction for describing data layouts, called axis trees. Axis trees are able to describe mesh data layouts completely from a high-level specification. This has the dual set of benefits of: (a) being able to delete a lot of complex Firedrake code, and (b) we can now express a whole suite of algorithms that would otherwise be very difficult to write.
You can think of pyop3 as 'a JIT-compiled numpy for unstructured mesh data'.
pyop3
Core concepts
Expected benefits
API changes visible in Firedrake
Drop support for variable layer extruded meshes
Users should use a cell submesh instead to get the right behaviour.
Explanation
The functionality appeared not to be used by the community (e.g. thetisproject/thetis#405) and porting the functionality would have been a large amount of work.
.sub()expects a tuple instead of integer for tensor spaces.