Repository navigation
perf(profile): split the line and cable steps into their kernels - #34
Merged
Merged
Conversation
The run-time profile (CABLEDYN_PROFILE=1) counted the steps and Newton iterations of EI = 0 lines but did not say where their time went, and it reported the factorisation and back-substitution of finite-EI cables as one "linear solve". Deciding whether a reused, scheduled factorisation is worth building needs both. The step of an EI = 0 line now times its residual-only evaluations, its residual and tangent evaluations, its LU factorisations and its back-substitutions (CableDyn_Profile kernel counters, updated atomically because lines step concurrently; their times are summed over the lines). The finite-EI cable profile times its factorisations apart from its back-substitutions, which now also include the force-blend correction that ends each step. The standalone driver and the OpenFAST module report both; the OpenFAST module arms and disarms the line counters with its own profiler. Unprofiled, every new entry point returns after one test: three decks run in the same time as with 0.2.0 (ratios 0.96-1.00) and write byte-identical outputs, and the driver tests check that every output file is identical with and without the profile. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Owner
Author
|
@codex review |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
Codex Review: Didn't find any major issues. What shall we delve into next? Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
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". |
This was referenced Oct 21, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The run-time profile (
CABLEDYN_PROFILE=1) now shows where the time inside the line and cable steps goes. It is the first step of the plan for a reused, scheduled factorisation, whose payoff depends on how much of the step the tangent and its factorisation take.EI = 0lines. Four kernels ofCD_Cable_Gen_Alpha_Stepare timed and counted: residual-only evaluations, residual and tangent evaluations, LU factorisations and back-substitutions.eval_dynamicbecame a thin timing wrapper around the unchangedeval_dynamic_core.CableDyn_Profilekernel counters are updated atomically, because lines step concurrently; their times are summed over the lines.EI = 0 line step kernelsline and the split cable line.CableDyn EI = 0 profileandcountslines, and the split Hermite line. It arms and disarms the line counters with its own profiler.Measurement
IEA-15 VolturnUS-S, DLC-1.6 environment (turbulent wind 10.6 m/s, JONSWAP sea), 600 s at
dtM = DT = 0.025 s,OMP_NUM_THREADS=1, gfortran build of this branch.step_s)wave_s)CalcOutput(69k calls, loads 3.3 / 19.9 s)EI = 0lines: residual / tangent / factor / back-substitutionEI = 0line work and 49 % of the cable step. Both are above the 30 % threshold set for building the scheduled factorisation.CalcOutput(about 3 calls per step) and the SeaState sampling are as large as the step itself. They are the next things to profile.Tests
test_profile, new kernel case:driver_profile_ei0,driver_profile_finite_ei: they require the new lines. As before, every output file must be byte-identical with and without the profile.dynamic_chain_current,lozon_gomex80_power_cable_motionandbuoy_clamped_cablerun in the same time (ratios 0.96–1.00, minimum of five alternating runs) and write byte-identical.outfiles.pre-commit run --all-filesand the Sphinx build with-Wpass. OpenFAST builds; the solver sources build without warnings.Checklist
pre-commit run --all-filespassesctest --test-dir build --output-on-failurepassespython -m pytest tests python/testspasses (if Python or validation records changed)[Unreleased](heading added if missing) for user-visible changesdoc/updated for changed inputs, options, or outputsfeat:,fix:,docs:, ...)git commit -s) under theDeveloper Certificate of Origin