Repository navigation
perf(ei0): coupled loads from the end rows; no OpenMP region on one thread (bit-identical) - #117
Conversation
…rows The coupled loads of an EI=0 line are the end rows of the residual M a + f_int - f_ext + M_add a - load. CD_Calc_Model_CoupledLoads formed the whole residual: the full structural mass product, the added-mass force and every load contributor of every element, to read the rows of the coupled DOFs. Every result stays bit-identical. - A line whose coupled DOFs all belong to its first or last node (a line between points), with finite accelerations, now forms the remaining terms on the two end rows only (coupled_loads_at_ends). It uses the elements that touch an end node and the end nodes' own terms (model_contributor_force end_nodes_only, as CD_Get_Model_EndForces does). Each row takes its terms in the element order of the whole-line assembly, so the loads are bit-identical. The whole-line internal force is kept, with its geometry and finiteness checks. A line with an interior coupled DOF, or a non-finite acceleration, takes the whole-line path as before, so it fails as before. - CD_Step_System and CD_Calc_System_CoupledLoads run their per-line loops without entering an OpenMP region when the team has one thread. The inactive region still set up a team on every call. The loop bodies are unchanged. - extract_element_state and extract_element_positions copy the two nodes' contiguous triples instead of gathering them through a vector subscript. All 54 examples give byte-identical output files on one thread (progress timing aside), and so do the line-break, mixed-body and two-train decks on the default thread count. The Rigid6 line-break decks als_volturnus_line_break_time and _tension run 7-8 % faster. Signed-off-by: Jae Hoon Seo <jaehoon.seo@inha.ac.kr>
|
@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. |
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 them coming! 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". |
|
Codex Review: Didn't find any major issues. More of your lovely PRs please. 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 EI = 0 line route and the point system. Results are bit-identical on all 54 examples.
Changes
CD_Calc_Model_CoupledLoadsassembled the full residual of every line at every step, then read only the coupled rows.coupled_loads_at_endsforms just the two end rows. It uses the elements touching an end node, through the existingmodel_contributor_force(end_nodes_only=.TRUE.)contract.CD_Step_SystemandCD_Calc_System_CoupledLoadsrun their per-line loops serially when the team has one thread. The formerIF(.FALSE.)region still set up a team, with heap calls, on every call.extract_element_stateandextract_element_positionscopy contiguous triples instead of using a vector subscript.Evidence
als_volturnus_line_break_timeals_volturnus_line_break_tensionTests
-fcheck=all: all 130 EI = 0, system, coupled, OpenFAST, C API and hydro tests pass.