Skip to content

fix: findings of the 0.4.0 end-to-end validation in OpenFAST and FAST.Farm - #83

Merged
SMI-Lab-Inha merged 4 commits into
devfrom
fix/e2e-findings
Nov 3, 2026
Merged

SMI-Lab-Inha merged 4 commits into
devfrom
fix/e2e-findings

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

Summary

Findings of the 0.4.0 end-to-end validation in OpenFAST and FAST.Farm (besides E2E-D2, fixed by #81).

  • A standalone TURBINES deck of EI = 0 and finite-EI lines runs. A power cable shared by two turbines beside their chain legs stopped with the internal message "no farm init was given (pass n_turbines + turbine_ref_pos)": the driver called the aggregate without the deck's TURBINES context. It now passes it; the Turbine<J> points are placed from the TURBINES rows, a finite-EI end on a Turbine<J> point starts turned by its turbine's PtfmInit, and each turbine's motionFile moves its points and turns its columns' frames. A Turbine<J> point in a run without a farm is refused by point.
  • A coupled deck takes bodies or rods, not both (documented; the lift is left for a later release). Such a deck stops at init on the coupled route while MoorDyn-F runs it, and the docs listed coupled bodies and rods without the limit. The message says what the coupled route takes and where such a deck runs; doc/openfast.rst, doc/coupling.rst, doc/capabilities.rst and doc/troubleshooting.rst state it, and the Python validator refuses the deck caller-driven.
  • FAST.Farm.exe of the CMake route gets a stack reserve on Windows GNU. With MinGW's 2 MiB default it stopped with 0xC00000FD while initialising a farm's turbines. New patch 0022 links openfast.exe and FAST.Farm.exe with a 256 MiB reserve on WIN32 with the GNU compilers; the release's Visual Studio projects keep their own.
  • Console messages that say what happens: the SeaState-kinematics line is printed only when a SeaState component is taken; the body/rod static start reports the largest turn and the move of every carried point (a pinned rod that only turned read "largest move 0.000E+00 m"); a deck refused for a current names the declaring input (CurrentMod 1 table or current OPTION); the torsion note reports the total twist Twist<L> beside Pretwist(B) - Pretwist(A); FAST.Farm names DT_Mooring, not a glue DT.

Checks

  • ctest 358 of 358 on two OpenBLAS kernels (Prescott and the default).
  • Checked Debug build (-fcheck=all) on the 38 touched tests.
  • Example A/B 53 of 53 identical.
  • Every example deck on the Prescott and Haswell kernels: same exit codes, no fallback, stall or relaxed-tolerance note.
  • Test needles updated and added (driver_cli_torsion_nmodes, mixed_route_torsion, openfast_aggregate, msg_pinned_rod_turn).
  • pre-commit, Sphinx -W.

…es runs

A standalone TURBINES deck that mixes EI = 0 lines and finite-EI cables (a power
cable shared by two turbines beside their chain legs) stopped with the internal
message "no farm init was given (pass n_turbines + turbine_ref_pos)": the driver
called the aggregate without the deck's TURBINES context.

The driver now passes deck_turbines to CD_AGG_Init_From_Deck. The aggregate's parse
then places the Turbine<J> points from the TURBINES rows as the single-route parse
does, a finite-EI end on a Turbine<J> point starts turned by its turbine's PtfmInit
rotation (turbine_end_dcm), and the per-turbine motionFile records move the points
and turn each moving column's frames with its own turbine (col_turb). A Turbine<J>
point in a run without a farm is refused by point, naming FAST.Farm and the
TURBINES section.

Gate 9 (ctest mixed_route_turbines): a two-turbine deck (PtfmInit offsets and
yaws, heave and roll records) with a clamped cable restrained in torsion and two
chains, against its cable-only and legs-only decks. The chains agree bit for bit;
the cable agrees within the coupled Newton controls (4.2e-3 of the range) and,
marched through the library with the single-cable route's controls, to 0.44
printed units. With the coupled controls given to the single-cable route, a trial
wrote the mixed run's cable byte for byte. The gate fails on the old code (the
mixed deck does not run). The IEA 15 MW FAST.Farm twin (60 s) reproduces the
split decks to 3.2e-6 of the channel maxima and FAST.Farm to 2.3e-5.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
A coupled deck with both bodies (Rigid6 or Point3) and rods stops at init, in
OpenFAST CompMooring = 5, FAST.Farm and the C API: the aggregate step advances
either the body march or the rod march. MoorDyn-F runs such a deck, and the
OpenFAST and capability pages listed coupled bodies and coupled rods without the
limit; the message spoke of "one body/rod family per step".

The message now says what the coupled route takes (bodies or rods; a rod fixed to
a body counts as a rod, a zero-length rod is a point) and where such a deck runs
(MoorDyn CompMooring = 3, or the standalone multibody march for a deck without
CoupledPinned objects). doc/openfast.rst, doc/coupling.rst, doc/capabilities.rst
and doc/troubleshooting.rst state the limit, and the Python validator refuses the
deck with caller_driven=True. The lift itself is left for a later release.

Gates: test_deck_native_parity (the validator refuses a buoy with a body-fixed
rod for the coupled route, accepts it standalone, and accepts the buoy alone and
with a zero-length rod) and test_objects (the C API refusal names the limit and the
routes; it fails on the old message).

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…on Windows GNU

FAST.Farm.exe built through integration/openfast with the GNU compilers on Windows
has MinGW's 2 MiB stack reserve and stops with 0xC00000FD (stack overflow) while
it initialises the turbines of a farm, before any output. The release does not ship
FAST.Farm.exe, so FAST.Farm users always take this route.

The new patch 0022 (numbered after 0021 of the version-stamp branch) links
openfast.exe and FAST.Farm.exe with a 256 MiB reserve on WIN32 with the GNU
compilers (-Wl,--stack,268435456, the CableDyn driver's reserve); the Visual Studio
projects of the release keep their own. integration/openfast/README.md and NOTICE
name it, and tests/test_documentation.py checks the patch.

Checked on the two-turbine IEA 15 MW shared-mooring farm: the patched build has the
256 MiB reserve; the same FAST.Farm.exe with its header set back to 2 MiB stops
with 0xC00000FD after "Running ElastoDyn", and with the reserve it runs to normal
termination. The full series, 0022 included, applies to a clean OpenFAST
2895884d2 checkout, and 0021 applies on top of it.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
From the OpenFAST/FAST.Farm end-to-end validation of 0.4.0:
- OpenFAST printed "SeaState wave/current kinematics drive the mooring
  hydro" also for a WaterKin file with WaveKinMod 0 and CurrentMod 0,
  which correctly gives still water; it is printed only when a SeaState
  component is taken.
- The body/rod static start reported "largest move 0.000E+00 m" for a
  pinned rod that had turned (only translations were counted); it now
  reports the move of every point the objects carry and the largest
  turn of a body or rod.
- A mixed or FAST.Farm deck refused for a deck current said "Remove the
  current OPTION" also when the current came from the CurrentMod 1
  table of its WaterKin file; the refusal names the declaring input.
- The torsion note reported the pretwist as the imposed twist, leaving
  out the PtfmInit/TURBINES turn of the end frames; it reports the
  line's total twist Twist<L> beside Pretwist(B) - Pretwist(A).
- In FAST.Farm the time-step messages called DT_Mooring the glue DT.
Test needles updated and added (driver_cli_torsion_nmodes,
mixed_route_torsion, openfast_aggregate, msg_pinned_rod_turn).

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 Nov 3, 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 2026-11-03T08:34:26.274867Z 7ab9af0 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 #35606554 | 📁 Comparing 7ab9af0 against latest (fd1936d)

  🔍 Preview build  

33 files changed · ± 33 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Can't wait for the next one!

Reviewed commit: 7ab9af0ab5

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 7a7ef27 into dev Nov 3, 2026
21 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/e2e-findings branch November 3, 2026 09:53
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