SpMM message passing CUDA support for coalesced COO graphs#617
Merged
Conversation
…ions for COO graphs
- Leave public adjacency_matrix interface uniform, always returning a sparse adjacency_matrix - Implement custom _adjacency_matrix for propagate copy_xj for CUDA COO graphs, converting to dense when more efficient
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds support for efficient CUDA message passing on coalesced
:coographs by exploiting SpMM. Performance is comparable to the case of:sparsegraphs.The changes introduced by this PR include:
__adjacency_matrixfunction, used during message passing, that efficiently constructs aCuSparseMatrixCOOfor a:coograph. This is leveraged bypropagateto implement message passing via SpMM.CuSparseMatrixCOOis computed incorrectly. The fix involves changingcoalesceto sort the:coograph representation by target instead of source.GraphNeuralNetworksandGNNlibto cover coalesced:coographs.