diff --git a/doc/options.rst b/doc/options.rst index ca74bbde..e9223ba2 100644 --- a/doc/options.rst +++ b/doc/options.rst @@ -355,10 +355,14 @@ rejected as unknown. The dynamic Newton controls are set with ``dynamic_solver`` - ``False`` - ``True`` enables guarded within-step tangent reuse on every dynamic solver the deck builds. It does not relax convergence tolerances and should be qualified against full Newton. - Measured against full Newton: 8-12 % faster on free-hanging finite-EI cables (lazy wave, - buoyed cable), about 1.5 times slower on finite-EI lines on the seabed (contact fails the - reuse contraction test and rebuilds the tangent), 3 % slower to 5 % faster on ``EI = 0`` - systems; + Measured against full Newton on the example decks (one thread): 4 to 20 % faster on + finite-EI cables, free-hanging or with a touchdown (lazy waves in waves, current and vessel + motion, a buoyed cable, rods on a spar); 12 % slower on an ``EI = 0`` cable laid on a + frictional seabed in a current, whose stick-slip friction makes a reused tangent take more + iterations; within a few per cent elsewhere on ``EI = 0`` systems. A finite-EI cable in + the monolithic step of the multibody march keeps full Newton, as it is stepped again from + the same start at every coupling iteration (reuse there made ``mixed_body_rods_points.dat`` + 7.0 s against 5.8 s); results move at the solver tolerance (Bergdahl mean cycle maxima within 0.16 %) - both - ``False modified_newton`` diff --git a/src/CableDyn_DeckDriver.f90 b/src/CableDyn_DeckDriver.f90 index bb3317d5..f620ab90 100644 --- a/src/CableDyn_DeckDriver.f90 +++ b/src/CableDyn_DeckDriver.f90 @@ -22586,6 +22586,15 @@ SUBROUTINE write_multibody_dynamic_out(deck_path, out_root, channels, types, bod mb%cab_imp(c) = mb%cab_imp(c) .OR. attachment_moves(mb%cab_kind_b(c), mb%cab_obj_b(c)) IF (mb%cab_imp(c)) mb%cables(c)%tol = MIN(mb%cables(c)%tol, CLAMPED_CABLE_TOL) END IF + ! A cable in the monolithic step is restored and stepped again from the same start at every + ! coupling iteration; within-step tangent reuse (OPTIONS modified_newton) made each of those + ! steps dearer than a full Newton one (mixed_body_rods_points.dat: 7.0 s against 5.8 s), so + ! such a cable keeps full Newton; the other solvers of the deck keep the option. The + ! staggered march (bodyScheme staggered) steps each cable once per step and keeps it. + IF (mb%implicit .AND. mb%cab_imp(c) .AND. opts%dynamic_modified_newton) THEN + CALL CD_HFMF_Set_ModifiedNewton(mb%cables(c), .FALSE., ErrStat, ErrMsg) + IF (ErrStat /= CD_HFMF_OK) GOTO 900 + END IF END DO ALLOCATE (mb%cable_points(2, SIZE(cab_lines))) DO c = 1, SIZE(cab_lines)