Repository navigation
perf(hermite): remove overhead from the finite-EI dynamic step (bit-identical) - #115
Conversation
|
@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. Breezy! 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". |
The cubic-Hermite dynamic step spent a measurable share of its time on work that does not change any result. Every change below keeps the floating-point operations of each output value and their order, so all results are bit-identical. - Band operators: the fill-in rows above the stored band are zero in every operator and only the LU factor writes them. The tangent and added-mass zeroing, the step-mass sum, the effective-tangent combination and the added-mass finiteness check now sweep the stored rows only, and the step mass Mgb + Mamb is formed in one sweep instead of a copy and an add. The sweeps take CONTIGUOUS dummies. - scatter12_band adds each element-matrix column into its contiguous run of the band column (the element DOFs are consecutive). - The rigid-end transport tangent forms its left vector on the band rows of the three end-tangent columns instead of two full band products. - The rigid end-connection moment takes the end tangent's rows from the elements at the node (node_reaction, now also for the tangent rows), not from a full residual and added-mass assembly; lines with torsion keep the full assembly. - Element kernels: the axial damping, drag and Froude-Krylov Jacobians form their 3 x 3 Gauss-point factor once instead of per entry; the bending-element tangent skips the node blocks below the diagonal when only the upper triangle is formed; the tangent worker no longer clears the wave and held-field blocks that their single contributor sets whole. - The drag element validates rho, diameter and the drag coefficients once before its quadrature loop; CD_Morison_Drag_Per_Length_Jac gains an optional scalars_validated argument that skips the same checks at each Gauss point. Vector inputs and results are still checked there. - CD_All_Finite on 2-D and 3-D arrays tests each column inline instead of calling the 1-D test per column. All 54 examples give byte-identical output files (progress timing aside). The finite-EI decks lazy_wave_vessel_rao, lazy_wave_bend_stiffener, lazy_wave_vessel_motion and buoy_clamped_cable run 2-15 % faster. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
bf60f40 to
c6a1b2e
Compare
|
@codex review |
|
Codex Review: Didn't find any major issues. Nice work! 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". |
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>
|
@codex review |
|
Codex Review: Didn't find any major issues. Keep it up! 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 PR removes overhead from the finite-EI (cubic-Hermite) dynamic step. Every output keeps the floating-point operations of its values and their order, so all example outputs are bit-identical to dev's.
Changes
band_combine) cover only the stored rows.band_suminstead ofband_copyplusband_add.scatter12_band: adds each element column into its contiguous run of the band column.CD_HermiteCable_Dyn_EndConnection_Momentat a rigid end: it reads the end-tangent rows fromnode_reaction(a new optionaltangent_rows). Before, every call did a full residual, added-mass assembly and matvec. Lines with torsion keep the full assembly.hermite_element_integratedskips the node blocks below the diagonal.evaluate_tangent_element: it no longer clears blocks that their single contributor sets in full.CD_Morison_Drag_Per_Length_Jactakes an optionalscalars_validated. The drag element, which has already checked the same scalars before its Gauss loop, passes it. Vector inputs and results are still checked at every Gauss point, so every fail-closed message is unchanged.CD_All_Finiteon 2-D and 3-D arrays: checks columns inline.Evidence
.out,.static.out,.elements.out,.range.out,.modes.out, stdout, stderr, exit codes). Of 268 files, 214 are byte-identical and 54 match once paths and progress timings are masked. None differ.buoy_clamped_cablelazy_wave_vessel_motionlazy_wave_bend_stiffenerlazy_wave_vessel_raoThe EI = 0 decks are untouched.
Tests
-fcheck=all): all 108 Hermite-related tests pass.