Skip to content

docs(validation): re-measure the L5 performance records and commit their scripts - #118

Merged
SMI-Lab-Inha merged 5 commits into
devfrom
perf/performance-records
Nov 8, 2026
Merged

SMI-Lab-Inha merged 5 commits into
devfrom
perf/performance-records

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

The L5 performance records in VALIDATION.md and validation/performance/ dated from about 0.1.0 and were measured on another host. Their timing models and scripts were never committed. This PR re-measures them and commits the scripts that produce them.

Protocol

  • Host: AMD Ryzen Threadripper PRO 7965WX, Windows 11, 2026-11-08.
  • Threads: one for every code. OMP_NUM_THREADS and OPENBLAS_NUM_THREADS are 1, and OrcaFlex runs with threadCount = 1.
  • Statistic: median of 3 runs after one warm-up. The range and the host load are recorded for each row.
  • CableDyn builds: the v0.4.1 release driver (IFX, the shipped binary) and a GNU Release build of dev.

Results

L5-DPC: 60 s on the pinned-touchdown lazy-wave spans

Depth CableDyn IFX CableDyn GNU OrcaFlex 11.6d MoorDyn-F, 4× refined
80 m 1.44 s 2.06 s 2.69 s 326.6 s
200 m 2.56 s 3.40 s 5.31 s 191.9 s
800 m 5.29 s 7.59 s 27.81 s 320.7 s

The models match OrcaFlex's hang-off tension statistics to 0.12 % for CableDyn and 0.29 % for MoorDyn-F.

L5-V: VolturnUS-S chain, one hour

CableDyn IFX CableDyn GNU OrcaFlex
4.44 s 6.18 s 19.72 s

The old record said 18–32 s for CableDyn against 14.5 s for OrcaFlex. The response matches L3-7.

L5-wc: 80 s on the WD0050 chain

CableDyn IFX CableDyn GNU MoorDyn-C v2.7.2 (RK2, 1 ms)
0.200 s 0.277 s 0.482 s

The original external solver appears to have been MoorDyn-C v2.6.1, with deck settings that were never recorded. These rows use v2.7.2 with a documented deck, and the docs say so.

Scripts

  • validation/scripts/performance_records.py: run builds, checks and times each case; --step-check re-checks the MoorDyn-F step; write produces the record files.
  • validation/scripts/performance_models.py: writes the CableDyn, MoorDyn-C and MoorDyn-F models.
  • orcaflex_longduration_mooring.py: now exposes build_model().

Records

  • Records: performance_summary.csv, the new wallclock_summary.csv, performance_metrics.json (versions, builds, hashes, host, responses, step checks), README.md and PERFORMANCE_AUDIT.md.
  • VALIDATION.md, L5: the summary rows and the Wall-clock section are rewritten.
  • Hermite solver bullet: each figure it states is re-measured on the test it names. Figures without a committed case are removed: the snap 0.03/0.26 s, "2.21 ms per step" and "banded equals dense".
  • Coupled IEA-15 throughput: these figures have no committed model, so they are now labelled as measured in September 2026 on the earlier host.

Tests

test_validation_records.py now checks the new row structure, the JSON consistency and the MoorDyn-F step checks. release/check_release_metadata.py treats validation/performance/ as dated history.

No solver code changes.

…ted timing scripts

The L5 performance records were measured around 0.1.0 on another host, and
their models and driver scripts were not in the repository.

validation/scripts/performance_records.py (with performance_models.py) now
builds, checks and times every L5 case on one host, one thread, as the
median of three runs after one warm-up:

- L5-DPC: the matched 80/200/800 m pinned-touchdown lazy-wave spans of the
  L3-6 protocol. CableDyn driver decks with 240/480/960 Hermite elements,
  the OrcaFlex models of orcaflex_lazywave_dynamic_reference.py, and the
  MoorDyn-F decks of moordyn_lazywave_dynamic_reference.py refined fourfold,
  with an optional half-step check of the MoorDyn-F step.
- L5-V: the one-hour VolturnUS-S chain, as a CableDyn deck with the
  l3_longduration_mooring drive and the OrcaFlex model of
  orcaflex_longduration_mooring.py (now exposing build_model()).
- L5-wc: the WD0050 chain under the L2-2 A1 heave, CableDyn against
  MoorDyn-C v2.7.2 through moordyn_c_driver.cpp.

Each timed model must reproduce its reference response before it is
recorded. The records keep the code versions, builds and hashes, the host
and date, the ranges, the host load, the CableDyn phase split and solver
counts, and the driver notes. CableDyn is timed with the release driver
(IFX) and with a GNU build of dev.

VALIDATION.md: the L5-V, L5-wc and L5-DPC rows and the wall-clock section
carry the new figures; the Hermite solver bullet is re-measured on the
committed tests it names (figures without a committed case are removed);
the coupled-throughput figures are labelled with their date and host. The
performance records are dated history for the release-version check.

Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
The [Unreleased] entries of the open changes are added together in one
change, so that they do not conflict with each other.

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 8, 2026 •

Copy link
Copy Markdown
Codex Review Summary: ✅ Completed

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

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-08T19:03:45.194521Z f2366ef 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.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7e3a069c18

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".

The documentation build resolves VALIDATION.md links as cross-references;
a relative path to a script is not one.

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

Copy link
Copy Markdown
Owner Author

@codex review

@read-the-docs-community

read-the-docs-community Bot commented Nov 8, 2026 •

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35737938 | 📁 Comparing f2366ef against latest (e8f88f5)

  🔍 Preview build  

1 file changed
± validation.html

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. 🎉

Reviewed commit: c4f48266d1

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".

The write step now checks the CableDyn vs MoorDyn-C mean and maximum fairlead
tension differences against WC_TOLERANCE (15 %) and refuses to write any record
file when either is outside it, or when the traces share no output time. The
committed records are unchanged (1.35 % and 1.71 %).

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 left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: f48977fb7d

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".

performance_records.py turned --moordyn-f-driver (default moordyn_driver),
CD_MDF_DRIVER, --cabledyn-driver and --gxx into paths under the working
directory, so a driver installed on PATH was never found. A name without a
directory separator that is not a file there is now resolved with
shutil.which, and a missing one is refused by name.

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

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. What shall we delve into next?

Reviewed commit: f2366ef05e

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 ae59f10 into dev Nov 8, 2026
16 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the perf/performance-records branch November 9, 2026 08:56
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