Skip to content

fix: accept seabed recompute inputs equal to rounding - #31

Merged
SMI-Lab-Inha merged 1 commit into
devfrom
fix/seabed-recompute-ulps
Oct 20, 2026
Merged

SMI-Lab-Inha merged 1 commit into
devfrom
fix/seabed-recompute-ulps

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

The clean-machine check of the 0.2.0 release assets found that the Intel-built release driver stops examples/buoy_clamped_cable.dat:

CableDyn_DeckDriver: finite-EI Hermite seabed recompute wiring failed: CD_HermiteCable_Dyn_Set_Control_Seabed: the inputs do not reproduce the installed nodal contact damping
  • What the check does. For every finite-EI cable with seabed contact, the deck driver stores the seabed recompute inputs: kBot, the contact diameters and cBot/kBot. Active line control (feat(control): active tension of finite-EI cables; committed lengths under the force blend #26) uses them to rebuild the nodal contact coefficients after a length change. CD_HermiteCable_Dyn_Set_Control_Seabed checked that these inputs reproduce the installed coefficients bit for bit.
  • Why it failed. The deck computes the damping as kn*(cBot/kBot), and the check computes the same product. The optimised Intel release build (IFX 2025.3.2, /Qipo) rounds the two differently. The gfortran builds of CI round them the same way, so no test showed it.
  • Fix. The check accepts coefficients within 8 units in the last place. Inputs that do not belong to the installed coefficients are still rejected, for example the existing twice-the-stiffness case. The docstring says why the comparison is not bit for bit.

This blocks the 0.2.0 release: the published executable would refuse every deck whose values round this way.

Tests

  • New assertions in test_hermite_cable_control:
    • a damping ratio one rounding step (NEAREST) off is accepted;
    • a ratio 1e-9 off is rejected as not reproducing the contact damping;
    • the exact inputs are then set again.
  • Release flags, local build (Intel Fortran 2025.3.2, /Qipo, static runtime, reference LAPACK 3.12.1):
    • the driver built from dev stops on buoy_clamped_cable.dat with the message above;
    • the fixed driver runs it and every other shipped example (51 decks, 0 failures).
  • Full suite (Windows, gfortran, Release, slow tier included): 293/293. Python: 2036 passed. pre-commit run --all-files and the Sphinx build with -W pass.

Checklist

  • pre-commit run --all-files passes
  • ctest --test-dir build --output-on-failure passes
  • python -m pytest tests python/tests passes (if Python or validation records changed)
  • VALIDATION.md updated if a validation result changed (none changed)
  • CHANGELOG.md updated (no user-visible change against 0.2.0's notes: this fixes a defect found before its release)
  • Documentation in doc/ updated for changed inputs, options, or outputs (docstring only)
  • Conventional Commit title (feat:, fix:, docs:, ...)
  • Commits are signed off (git commit -s) under the
    Developer Certificate of Origin

The deck driver stores the seabed recompute inputs of every finite-EI
cable with seabed contact (kBot, the contact diameters and cBot/kBot),
so that active line control can rebuild the nodal contact coefficients
after a length change, and CD_HermiteCable_Dyn_Set_Control_Seabed
checked that the inputs reproduce the installed coefficients bit for
bit. The deck computes the damping as kn*(cBot/kBot) and the check
computes the same product, but the optimised Intel build of the release
evaluates the two with different rounding: the release driver stopped
examples/buoy_clamped_cable.dat with "the inputs do not reproduce the
installed nodal contact damping". The gfortran builds of the test suite
round both the same way and did not show it.

The check now accepts coefficients within 8 units in the last place,
which still rejects inputs that do not belong to the installed
coefficients. Built with the release flags (Intel Fortran 2025.3.2,
/Qipo, reference LAPACK), the driver of dev stops on that deck and the
fixed driver runs it and every other shipped example (51 decks).

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
@SMI-Lab-Inha

Copy link
Copy Markdown
Owner Author

@codex review

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Oct 20, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-10-20T11:44:10.062344Z 18e6ecf Manual request
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@read-the-docs-community

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35268264 | 📁 Comparing 18e6ecf against latest (f27c5e3)

  🔍 Preview build  

33 files changed · ± 33 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Chef's kiss.

Reviewed commit: 18e6ecf30d

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@SMI-Lab-Inha
SMI-Lab-Inha merged commit 3c066f4 into dev Oct 20, 2026
15 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/seabed-recompute-ulps branch October 20, 2026 12:47
@SMI-Lab-Inha SMI-Lab-Inha mentioned this pull request Oct 20, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant