Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
c89059f
feat: add torsion to the Hermite finite-EI cable (#2)
SMI-Lab-Inha Oct 1, 2026
0050063
fix: keep large arrays off the stack on Windows GNU builds (#3)
SMI-Lab-Inha Oct 2, 2026
95cc0af
Report every abnormal end of the standalone driver (#5)
SMI-Lab-Inha Oct 9, 2026
c1817de
Set the version to 0.1.1 and check that every file names it
SMI-Lab-Inha Oct 9, 2026
9a8f31e
Record the Python typing, test-suite and EPUB changes of 0.1.1
SMI-Lab-Inha Oct 9, 2026
6f24498
Name the line, end and value in END CONNECTIONS errors
SMI-Lab-Inha Oct 9, 2026
6da919e
Stop a static twist above 1000 turns by name
SMI-Lab-Inha Oct 9, 2026
a44d80d
Invalidate the step snapshot when the torsion changes
SMI-Lab-Inha Oct 9, 2026
9491277
Refuse end connections set under an installed torsion
SMI-Lab-Inha Oct 9, 2026
eceb997
Label torsion channels and name the END CONNECTIONS row in its errors
SMI-Lab-Inha Oct 9, 2026
bfbc084
Re-run the experimental comparisons with 0.1.1
SMI-Lab-Inha Oct 9, 2026
5e977d5
Refuse a static twist above 1000 turns in the Python deck check too
SMI-Lab-Inha Oct 9, 2026
5af554e
Record the builds and checks of 0.1.1
SMI-Lab-Inha Oct 9, 2026
c09a492
State the known modal-test issue and mark deliberate past-release fix…
SMI-Lab-Inha Oct 9, 2026
5eef9ab
State the driver's exit contract exactly and report Fortran runtime e…
SMI-Lab-Inha Oct 9, 2026
84c5e5d
Describe the release driver's exit after an interrupt as it is
SMI-Lab-Inha Oct 9, 2026
f27c5e3
Record the final 0.1.1 builds and checks
SMI-Lab-Inha Oct 9, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions ARCHITECTURE.md
Original file line number Diff line number Diff line change
Expand Up @@ -394,6 +394,8 @@ src/
cabledyn_blas.c BLAS thread policy; run-time OpenBLAS loading (Windows GNU)
cabledyn_mutex.c C-ABI registry and initialisation locks
cabledyn_crt_locale.c MinGW-w64 guard for libgfortran's locale restore
CableDyn_FatalReport.f90 abnormal-end report of the driver (time reached)
cabledyn_fatal.c interrupt, fault and stack-overflow handlers of the driver

EI = 0 cable path:
CableDyn_Mesh.f90 connectivity, property, and DOF-partition validation
Expand Down
78 changes: 78 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,88 @@ All notable changes to CableDyn are recorded in this file. The format follows

## [Unreleased]

## [0.1.1] - 2026-10-09

### Added

- Torsion of finite-EI lines in the standalone driver (condensed, quasi-static, uniform torque):
`END CONNECTIONS` columns `TorsStiffness NxX NxY NxZ [Pretwist]`, a `motionFile` roll column,
the torque returned to Rigid6 bodies, channels `Torq<L>N<J>`, `Twist<L>N<J>` and `Twist<L>`,
range-graph columns, `DeckModel` and channel support in Python, and the example
`torsion_lazy_wave_hangoff_twist.dat`. Validated in VALIDATION.md (Torsion). Routes outside
its scope, coupled OpenFAST (NLR) runs included, stop with a named error; results without
torsion are unchanged.

### Changed

- Python: NumPy arrays in the public functions carry explicit element types, and the package
type-checks under `mypy --strict` on Python 3.10 and on current NumPy. Tests that need the
native shared library are skipped with a reason when it has not been built.
- The test suite runs in parallel (`ctest -j`) and holds on hosted CI runners: the catenary
reference solve converges from a robust start on every platform, and the driver-path tests
check the case-insensitive spelling of an output root only on Windows.

### Fixed

- The standalone driver no longer ends without a word when its process is interrupted or hits a
fatal fault. Ctrl+C, Ctrl+Break, closing the console window, `SIGINT`, `SIGTERM` and `SIGHUP`
are reported as `CableDyn_driver: stopped by <cause>`, and an access violation, a stack
overflow or another fatal fault as `CableDyn_driver: fatal error: <cause>`. Both reports give
the simulated time of the last committed step, and the exit status is unchanged. On Windows a
fault report also names the module and offset of the fault and, for an access violation, the
address read or written. Previously a stack overflow in a Windows GNU build ended the process
with no message. Every thread that enters an OpenMP parallel region keeps room to report its
own stack overflow, and on Linux and macOS a hardware fault reaches the handler that was there
before (the Fortran runtime's backtrace, or the default action and its core dump) with its
original address and context, and a previous handler runs under its own flags and signal mask;
a fault signal sent by another process (`kill`) is passed on as sent. A signal the driver was
started with ignored (for example under `nohup`) stays ignored.
- Every non-zero exit the driver makes itself now ends stderr with the closing line
`CableDyn_driver: ended with exit code <n>`. A process ended from outside (`taskkill /F`, *End
task*, `kill -9`) runs none of its own code and cannot report anything; the missing closing
line now identifies it, since `taskkill /F` leaves exit code 1, the same code as a refused
input. The driver states this at start, after the banner, in an `Exit status:` line.
`CableDynDriver.run`, `cabledyn-run` and `cabledyn-study` report such a run as ended early,
with the time its output reached, instead of relaying the start-up log as the error; with a
driver that does not write the `Exit status:` line (0.1.0 and earlier), a failure is reported
with the driver's own text as before. The documentation explains how to recognise each kind of
early end and warns that `taskkill /IM CableDyn_driver.exe /F` ends every CableDyn run on the
computer. A run the Fortran runtime ends with its own error (for example when memory runs out)
is reported as ended with a Fortran runtime error, quoting the runtime's line.
- The static solve of a taut, neutrally buoyant finite-EI line (mass per length equal to
the displaced mass) no longer depends on the sign of the round-off weight: a line whose
total weight is below 1e-12 of its axial stiffness is seeded as a straight, uniformly
stretched line. Previously the catenary seed could fail to close on some platforms.
- Windows builds with gfortran: the `modal` test could stop with a stack overflow on some
CPUs, because it kept 1.7 MB of dense matrices on the stack. Large test arrays and the
initialisation workspaces of the coupled aggregate and the C API are now allocated on the
heap, every executable of such a build reserves a 64 MiB stack, and the new `stack` tests
run the library on a 1 MiB thread stack. Results are unchanged.
- The static Windows `openfast.exe` compiles the CableDyn adapter with `/heap-arrays:1024`,
like the CableDyn core, so its run-time-sized arrays no longer use the
`openfast.exe` stack.
- Builds with gfortran 16 are free of `-Wuninitialized` warnings; the reported values (the
bounds of unallocated components) were never read.
- The EPUB edition of the manual no longer contains the `.nojekyll` marker file.
- Python: `DeckFile` messages for an `END CONNECTIONS` row name the line, the end and the
offending value, and the unit of a main-output channel written with leading zeros in its ids
(`Ten01N04`, `Torq03N4`) is recognised, as the driver accepts such names.
- Torsion: an imposed static twist `Pretwist(B) − Pretwist(A)` above 1000 turns (for example
a value given in the wrong units) now stops with a message naming the line and the value.
Before, the static twist ramp could run for millions of stages.
- Torsion: installing a torsion description on a dynamic cable now invalidates its step
snapshot, as a new end connection does, so a later restore cannot rewind to a state taken
under the previous loads; a rejected description leaves the cable and its snapshot as they
were, and ending a cable module also clears its torsion frame. End connections set after
the torsion, and a torsion director that is not the rigid connection direction, are refused
by name.
- `END CONNECTIONS` row errors now name the line, the end and the offending value.

### Known issues

- An intermittent access violation in the modal analysis tests has been seen on some hosted
CI runners with GNU builds that use OpenBLAS 0.3.34. The cause is under investigation. The
released Windows driver uses reference LAPACK and is not affected.

## [0.1.0] - 2026-10-01

Expand Down Expand Up @@ -364,4 +440,6 @@ Corrections made during the pre-release review.
values of the shipped example decks and states which tension (end element or
`FairTen` end force) each comparison uses.

[Unreleased]: https://github.com/SMI-Lab-Inha/CableDyn/compare/v0.1.1...HEAD
[0.1.1]: https://github.com/SMI-Lab-Inha/CableDyn/releases/tag/v0.1.1
[0.1.0]: https://github.com/SMI-Lab-Inha/CableDyn/releases/tag/v0.1.0
4 changes: 2 additions & 2 deletions CITATION.cff
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,8 @@ authors:
repository-code: "https://github.com/SMI-Lab-Inha/CableDyn"
url: "https://github.com/SMI-Lab-Inha/CableDyn"
license: Apache-2.0
version: 0.1.0
date-released: 2026-10-01
version: 0.1.1
date-released: 2026-10-09
keywords:
- mooring dynamics
- cable dynamics
Expand Down
Loading
Loading