Skip to content

perf(statics): stop the axial refinement when it leaves the compression where it was - #131

Merged
SMI-Lab-Inha merged 2 commits into
devfrom
fix/axial-refinement-stall
Nov 8, 2026
Merged

SMI-Lab-Inha merged 2 commits into
devfrom
fix/axial-refinement-stall

Conversation

@SMI-Lab-Inha

Copy link
Copy Markdown
Owner

A compression that belongs to the equilibrium itself (rather than to the mesh) does not fall as elements are split. Its violation stayed flat from pass to pass (57.65124, 57.65104, 57.65109, …), yet changes of about 1e-6 still counted as progress. The axial refinement therefore kept doubling the mesh to its 32768-element budget on each of three static routes before it failed.

It now stops once two successive passes leave the violation within 0.1 % of the previous one, and the message says the compression is the equilibrium's, not the mesh's.

Case Before After
Doubled power-cable deck 75.7 s 6.0 s (same −514.88 N compression)
cable_statics_matrix 101.6 s 99.6 s (all 521 output files byte-identical)

Every example (TMax cut to 4 steps) gives identical output files.

Test. A driver test that requires the early stop; it failed before, taking 79 s. CTest passes on both BLAS kernels; pytest passes.

@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 2026-11-08T17:49:50.529643Z c06ea98 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

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

Copy link
Copy Markdown

Documentation build overview

📚 CableDyn | 🛠️ Build #35737038 | 📁 Comparing c06ea98 against latest (e8f88f5)

  🔍 Preview build  

10 files changed · ± 10 modified

± Modified

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Chef's kiss.

Reviewed commit: d087ad3e47

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".

…on where it was

With tensile_safety True the AutoMesh static solve splits the elements around
an element-mean axial compression until the compression falls below its
tolerance, the minimum axial strain stops improving for four passes, or the
mesh reaches its element budget. A compression of the equilibrium itself (a
line too long for its span, held by its bending stiffness) does not move under
refinement, but tiny round-off changes of its value counted as improvement, so
the loop doubled the mesh to the budget (32768 elements) on each of the static
routes it tried: a power cable deck with its sections given twice failed after
76 s.

The loop now also stops when two successive passes leave the violation within
0.1 % of the previous pass's, naming the compression as the equilibrium's. A
compression that is a mesh effect falls as its elements are split, by far more
than 0.1 % a pass, so a resolvable state still refines as before.

Measured: the doubled power cable fails in 6.0 s (75.7 s before) with the same
compressive resultant (-514.88 N); cable_statics_matrix writes all 521 output
files byte for byte as before (99.6 s, 101.6 s before); every shipped example
(TMax cut to four steps) writes identical output files.

Tests: the parity tests run the doubled power cable through the driver and
require the new stop (fails before: the budget stop after 79 s).

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

@SMI-Lab-Inha
SMI-Lab-Inha force-pushed the fix/axial-refinement-stall branch from d087ad3 to c06ea98 Compare November 8, 2026 17:48
@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. You're on a roll.

Reviewed commit: c06ea98a05

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 026b9d9 into dev Nov 8, 2026
16 checks passed
@SMI-Lab-Inha
SMI-Lab-Inha deleted the fix/axial-refinement-stall branch November 9, 2026 08:55
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