Repository navigation
test: long-run VIV checks; one OpenMP thread per batch job; load-power and bending-damping speed-ups - #173
Merged
Conversation
…thread per batch job viv_long_run runs the synchronisation model for 400 cycles. Prescribed motion: every node of a finite-EI cable moved across a 0.3 m/s flow as a rigid body, so the shedding phase obeys Adler's equation, d psi/dt = a - b sin(psi), solved in closed form. Outside the band (5.5 rad/s) the largest node error grows linearly in time (T/(T/2) 2.00 and 2.02 at 50 and 100 steps per cycle) and is second order (3.98 from 50 to 100 steps): 0.033 rad after 400 cycles at 100 steps per cycle. Inside the band the lag holds within 2.9e-5 rad of psi*, the averaging-ripple floor, at every step size, and the mean rate is the motion's within 1.8e-10. Lock-in, finite-EI and EI = 0 (taut 20 m line, rho_inf = 1, no added mass, 100 and 200 steps per cycle): the load powers close E(t) - E(0) to 8.3e-5 / 7.9e-5 of the VIV work, second order (4.2 / 4.0; 1.1e-3 to 2.3e-7 over 25 to 1600 steps per cycle), and the mismatch grows no faster than the work. The halves of the last three quarters agree in RMS A/D within 4.3e-4, mean VIV power within 1.1e-3 and lock-in frequency within 4.5e-4, below the change from 100 to 200 steps per cycle. The coupled lock-in frequency converges at first order or slower (0.74, 0.41, 0.27 % per halving from 25 steps per cycle), while the phase update itself is second order. Every tolerance and its measured value is in the test header. 26 s Release, 160 s Debug; label slow, TIMEOUT 1200. At 50 steps per cycle with rho_inf = 1 the finite-EI step does not converge on this line. run_study with jobs > 1 now runs every case with OMP_NUM_THREADS=1 unless the environment sets it, and study.json records omp_num_threads. Measured on the 24-core workstation (gfortran Release): 96 finite-EI VIV cases scale 13.3x at 24 jobs and 15.1x at 48; OpenMP inside one VIV run changes nothing (1.79 s against 1.76 s), but on the 1024-element lazy-wave example 24 jobs take 16.7 s with one thread each, 17.9 s with four and 19.1 s with the OpenMP default. The Python manual gives the table and the recommended settings. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
…its Jacobian tensors Profiling the finite-EI step with VIV on (gfortran Release, one thread): - The load power channels evaluated CD_HermiteCable_Dyn_Load_Power (VIV lift, drag and structural damping over every element) once per channel: with VIVPow, DragPow and DampPow 19 % of a VIV run. A row now evaluates a line's node powers once for all its power channels: the Hermite row writer passes a per-row cache to eval_cable_channel, and the EI = 0 / system planned writer resolves the channels to CH_LOAD_POWER with a per-line, per-row stamp like its state and tension caches. Any failure still goes through the channel-at-a-time path, so its message is unchanged. viv_taut_cable_inline.dat 2.39 s to 2.14 s, the same line with 200 elements at 100 steps per cycle 18.1 s to 16.1 s. - CD_HermiteCable_Bending_Damping computed the second derivatives of the curvature (T, dP, dK, about 300 terms per Gauss point) in every residual evaluation, where only Kq uses them: 32 % of the Delta Flume case 9 run (64 elements, 80 000 steps, EI|-zeta|f). They are now evaluated only with Kq; the force takes the same operations. 73.2 s to 58.6 s. Bit-identical: the 134 example and test-data decks, the two Delta Flume decks (cases 5 and 9) and the load power decks of the EI = 0 line, the system and the cable match the reference build byte for byte. load_power_deck P6 checks that a power channel read alone equals the same channel among its line's other power channels and changes from row to row, on all three routes. Remaining hot spots of the Delta Flume run: the bending damping's force path (Jacobian of the curvature, MATMULs), the Morison drag kernels with their finiteness scans, the line position file the deck writes every step (about 8 %), and the banded solves. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
On the mid-point phase update of #171 the energy closure of the locked-in line is 2.0e-4 (finite EI) and 1.8e-4 (EI = 0) of the VIV work at 100 steps per cycle, still second order (3.98 and 3.67 per halving) and stationary (T against T/2 1.00): the lift takes the phase predicted from the previous step's mid-point rate, half a step behind, so the bound moves from 1.5e-4 to 3e-4. The phase error under prescribed motion halves to 0.0167 rad after 400 cycles (order 4.01), and the lock-in frequency now changes by 1.6e-4 and 1.9e-4 from 100 to 200 steps per cycle; the header no longer says it converges at first order, nor that the finite-EI line fails at 50 steps per cycle (#169). Every measured value in the header, the L2-VIV-long row and the changelog is from this run. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
Owner
Author
|
@codex review |
Codex Review Summary: ✅ CompletedThis 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. Chef's kiss. 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 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
Three changes:
viv_long_run). Under prescribed motion, the phase error grows linearly in time and falls fourfold per halving of the step. On a locked-in line the load powers close the energy balance at second order, and the run's two halves agree, so nothing drifts.jobs > 1, which removes oversubscription.1. Long-run VIV check (
tests/test_viv_long_run.f90)(P) Prescribed motion. Every node of a finite-EI cable moves across a 0.3 m/s flow as a rigid body, so the shedding phase obeys Adler's equation$\dot\psi = a - b\sin\psi$ , solved in closed form.
(C) Lock-in. A taut 20 m line, finite-EI and$\rho_\infty = 1$ and no added mass, so the load powers are the whole energy change. Run at 100 and 200 steps per cycle.
EI = 0, withWhy C1's bound is 3e-4. On the second-order phase update of #171, the lift takes the phase predicted from the previous step's mid-point rate, half a step behind the step's own. That is a second-order lag. The mismatch was 8.3e-5 before #171 and is 2.0e-4 now, still second order and stationary.
Every tolerance and its measured value is in the test header. The test takes 57 s in Release; label
slow, TIMEOUT 1200.2. One OpenMP thread per batch job
With
jobs > 1,run_study(andcabledyn-study) runs every case withOMP_NUM_THREADS=1unless the environment sets it, andstudy.jsonrecordsomp_num_threads.Measured on a 24-core workstation (gfortran Release):
The Python manual gives the table and the recommended settings.
3. Speed-ups (outputs bit-identical)
VIVPow,DragPowandDampPoweach evaluated a line's node powers, 19 % of a VIV run. A row now evaluates them once for all of its power channels, on the Hermite,EI = 0and system routes. Any failure still goes through the channel-at-a-time path, so its message is unchanged.viv_taut_cable_inline.dat: 2.39 → 2.14 s.load_power_deckP6 checks that a power channel read alone equals the same channel among its line's other power channels, on all three routes.Checks
All on the branch rebased on dev f4c9958 (#171). The rebase onto 05a4f14 (#172) changes no Fortran source or test.
response_comparison.csvexactly.pre-commit.