Raw CSC factor path streaming into helper shared memory#1
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a raw CSC overload to
sparse_factor—sparse_factor(solver, nrow, ncol, nz, col_ptr, row_idx, val, status)— that streams the matrix arrays straight into the UMFPACK helper's shared mapping instead of routing through acsc_tcopy. Callers that already hold CSC arrays (NEO-2'ssparse_solve_fortsparseadapter) drop one matrix-sized allocation per factorization.Motivation: itpplasma/NEO-2#101's run-golden-record job dies on the runner during the multispecies QL case; local PSS profiling of that case shows the IPC backend peaking ~2 GB above the in-process UMFPACK path, with the adapter's
csc_tcopy the largest avoidable share.Verification
Test fails on main
test_fortsparse_umfpack_ipcextensions (raw-factor roundtrip real/complex, refactor-after-free) do not exist on main; with the test but no raw overload the build fails to resolve the newsparse_factorspecifics.Test passes after fix
fo lintclean (0 warnings).