8 Commits

Include renames

Author	SHA1	Message	Date
Omar SobhandClaude Fable 5.1	0dc95a8de5	PERF-2 P3: the batched device V-cycle microbenchmark — mg_vcycle.cu (masked variable-coefficient five-point red-black half-sweeps, residual, CSR restriction in a fixed order, prolongation, coarsest sweeps; [K][n] layout, blockIdx.y = march), LevelExport/export_hierarchy and vcycle_f32_reference on the CPU side, and the ignored cuda-feature test that checks the K = 1 device V-cycle against the CPU f32 reference and times K = 1 / 8 / 16 per march ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01YJPeT6WA2e7YvAnS875AHL	2026-09-16 01:03:02 -05:00
Omar Sobh	822041fb3f	PERF-2 P2: the parallel maps run only on levels with ≥ 8,192 active cells and in tasks of ≥ 2,048 cells (a fork-join over a small level costs more than the map); values unchanged	2026-09-16 00:10:42 -05:00
Omar SobhandClaude Fable 5.1	7f144e0005	PERF-2 P2: the red-black colour maps, the residual and the V-cycle's per-level maps on rayon threads (MultigridParameters::threads; RTX_THREADS in the harness; rtx_cfd::configure_threads) — each colour's values computed from the unchanged other colour into a scratch and written back, the L1 sum in the serial order: bit-identical to the serial red-black (pin: 4 right-hand sides at 4 threads); the coarsest level stays serial; no effect on the lexicographic regime ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01YJPeT6WA2e7YvAnS875AHL	2026-09-15 23:59:29 -05:00
Omar SobhandClaude Fable 5.1	cb5771fa71	PERF-2: red-black symmetric Gauss–Seidel smoother behind a knob (MgSmoother::RedBlack; default lexicographic = the recorded regime, bit-identical) — red/black cell lists per level, the symmetric pair red,black,black,red, the operator cache keyed on the smoother; EmbeddedParameters::poisson_smoother, harness knobs RTX_FSI2O_MG_RB (overset) and RTX_FSI2_MG_RB (embedded, the noise probe); pin: solves the masked problem to the same stop, agrees with lexicographic to 2e-12, cached = uncached bit for bit ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01YJPeT6WA2e7YvAnS875AHL	2026-09-15 23:48:55 -05:00
Omar SobhandClaude Fable 5.1	79c18def32	PERF-2 P1.1: the multigrid-PCG's prepared operator (hierarchy, f64 fine level, active cells, components) cached on the embedded solver and reused while the operator is bit-identical (an exact key over the coefficient bit patterns, the mask and the hierarchy parameters); solve_multigrid_pcg_cached gives the uncached solve's answer bit for bit (pin poisson_cache_exact.rs: five right-hand sides on one operator, a one-coefficient miss, both precisions); the CG driver split into Prepared::build + run_pcg ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01YJPeT6WA2e7YvAnS875AHL	2026-09-15 23:30:53 -05:00
Omar SobhandClaude Fable 5.1	172a26dee4	PERF-2 P0: intra-step profiler — StepTimers on the overset solver (RTX_PROFILE; overlap build / predictors / patch BiCGSTAB / background Poisson with its setup-vs-iterate split / round exchange / apply / end exchange), PoissonSolution carries setup_ns and iterate_ns, the harness times advance / restore / snapshot / load sampling / force / FEA predictor and prints the wall split of the coupled phase; no clock is read when profiling is off; the reclassified/step progress denominator fixed (was ×4) ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01YJPeT6WA2e7YvAnS875AHL	2026-09-15 22:25:52 -05:00
Omar SobhandClaude Fable 5.1	c63d79c300	rtx-cfd/rtx-fsi: overset A-P0 GATED + M1 precision probe — curvilinear collocated PISO: relative-reduction pressure stop (the absolute stop floored |du/dt| at 2e-4 on 64²), line-implicit-n sign fix, adjustPhi; gates: Cartesian reduction 1.37–1.40x the staggered error at orders 0.83/0.90; skewed stretched periodic annulus Stokes orders 2.30/2.06 (explicit and line-implicit), upwind 1.08/0.80; Poiseuille exact to 1e-9 on Cartesian and affine-sheared periodic channels (both diffusion variants), varying-skew channel order 2.02 (v 1.9), cell mass 1e-14; divergence ≤ 1e-11 relative every step; snapshot/restore bit-identical. M1: poisson.rs multigrid hierarchy generic over MgScalar (f32/f64), f64 CG keeps its own fine level; MgPrecision on MultigridParameters/EmbeddedParameters/PisoParameters, set_poisson_precision, harness RTX_FSI2_POISSON_F32 (march + noise probe, printed marker); f64 arm bit-identical in vivo (FSI2 default line-for-line with 08-31), f32 arm holds the noise floor and stall pins and the FSI2 band; poisson_equivalence f32 arm ... Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01X2GmJXeQ2njUecEKiJZ1G2	2026-09-04 12:40:43 -07:00
Omar SobhandClaude Fable 5	327da7ff47	rtx-cfd: multigrid-PCG projection — 30x faster, same answers — and the CFD1 refinement study ... Falsifier 4 of the Turek–Hron geometry decision fired (the SOR projection cost 0.09 s/step at 250x41 and an hour per run at 5 mm); this answers it. solvers::incompressible::poisson: PoissonProblem (cell-centred five-point SPD operator as per-cell face coefficients + Dirichlet diagonal extra + active mask) and solve_multigrid_pcg — conjugate gradient preconditioned by one V-cycle of geometric multigrid: aggregation by 2 per direction (odd sizes absorbed, coarse cell active iff any child is), the Galerkin coarse operator for piecewise-constant prolongation / summation restriction, symmetric Gauss–Seidel smoothing, coarse correction scaled by 2 (Braess's under-correction of unsmoothed aggregation; scalar, so the preconditioner stays symmetric and positive on range(A)), L1 TRUE-residual stop with a stagnation guard. Singular systems are handled per connected component of the active cells (mean projection and level per pure-Neumann component; the anchor's component to p[anchor] = 0). PoissonSolverKind::{Sor, Multigrid} on PisoParameters / EmbeddedParameters; Sor is the default and its code is byte-for-byte untouched; an unconverged multigrid solve falls back to the SOR sweeps for that projection. Verified (poisson/tests.rs, tests/poisson_equivalence.rs): - PCG iterations to cut the residual 1e-8 on the closed Neumann box at 32^2..256^2: 4, 4, 4, 4; ragged masked domains 8/8/8; - manufactured recoveries to ~1e-14; Galerkin identity A_c v = R A P v to 7e-15 on every level (masked, outlet column, non-uniform conductances); V-cycle symmetric to 1e-14; NaN-poisoned inactive cells untouched; - two Neumann components with opposite imbalances, and a Dirichlet component beside an imbalanced Neumann one (review scenarios): converge, each component right up to its own constant; - speed vs plain SOR at the same stop: 22.7x (128^2), 41x (256^2); - same answers as SOR: PISO MMS 4.6e-8 relative, Taylor–Green divergence 1.4e-9 every step, embedded-circle MMS 7e-8, no-body bit-identity with MG on both solvers, channel+outlet+circle 1.4e-10; CFD1 loads identical to four digits at 0.003 s/step vs 0.094 (30x). CFD1 refinement study (tests/turek_hron_cfd.rs, three grids, 257 s): h = 10 / 6.6 / 5 mm -> control-volume drag 15.6156 / 15.2829 / 15.0988 vs 14.2929 (+9.25 / +6.93 / +5.64%), apparent order 0.71, Richardson extrapolate 14.04; surface route and lift not monotone (flag 2/3/4 cells thick) — the test asserts the measured band at the finest grid. Built with a 4-agent workflow (core, integration, refinement study, adversarial review); the review found no defects and four risks, three fixed here (per-component projection, one symmetric smoother-sweep parameter, acting on `converged` with an SOR fallback) and one recorded (isotropic aggregation loses grid-independence on anisotropic cells). rtx-cfd 301 -> 318 green. Co-Authored-By: Claude Fable 5 <[email protected]>	2026-08-20 10:20:25 -07:00