Skip to content

1.5.0 Release Candidate - #205

Open
haykh wants to merge 159 commits into
masterfrom
1.5.0rc
Open

haykh wants to merge 159 commits into
masterfrom
1.5.0rc

Conversation

@haykh

@haykh haykh commented May 18, 2026 •

Copy link
Copy Markdown
Collaborator

New Features

Refactoring

  • metadomain and container functions for io/communications/checkpoints now factored out into specialized directories (mostly .cpp files).
  • [output.render] -> [render] + reading is done in dedicated parameters/ subfile.

QOL

haykh and others added 28 commits May 18, 2026 09:22
haykh and others added 28 commits September 21, 2026 15:53
Copied byte-identical from dev/qed (277eb74) so a future merge of
that branch resolves these as add/add with matching content.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
The restart reader opened the BP file on MPI_COMM_SELF, so every rank
independently parsed the full global metadata instead of a single
rank-0 read + broadcast. Phase 1 also had every rank loop over all
g_ndomains reading each subdomain's extent/ncells via per-element
Mode::Sync Gets. Both costs scale ~O(N_ranks^2) and made restart reads
dominate wall time at large rank counts (~3 h at 65536 ranks vs a
2-3 min write).

- Open the reader on MPI_COMM_WORLD so ADIOS2 reads/broadcasts metadata
  collectively and can aggregate reads.
- In Phase 1, each rank now reads only its own subdomain entry and
  MPI_Allgathers the ncells/xmin/xmax arrays; global_extent and the
  reconstruction check are computed from the gathered layout. Non-MPI
  path unchanged.

Verified ~50x faster on Frontier (read 209 s vs ~3 h) in the sibling
entity_bh tree.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Fix slow parallel checkpoint read (COMM_SELF + O(N^2) metadata loop)
@haykh
haykh marked this pull request as ready for review October 5, 2026 15:49

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants