rustytorch

embedded3 S2-3b: the flag driver's span knob (full width = the 2D geometry extruded)

Performance Benchmarks #862:Commit fc8d69af29 pushed by osobh

main

2026-09-18 02:14:05 +00:00

2m44s

embedded3 S2-2a/S2-3: moving bodies on the device (phased tables, host rebuild per step, impose kernel; gate test), the per-span cut wall route, the flag-wake driver and its geometry pre-flight

Performance Benchmarks #847:Commit aa096465a6 pushed by osobh

main

2026-09-17 23:55:40 +00:00

2m36s

embedded3 loads: the control-volume route between no-slip z walls carries the walls' shear (control_volume_force_with_walls); the DFG driver uses it

Performance Benchmarks #841:Commit 32546b1222 pushed by osobh

main

2026-09-17 22:29:41 +00:00

2m18s

embedded3 item 12: the DFG 3D-2Z device driver (loads by both routes, Δp, settle criterion, CSV) and the VTK instant export

Performance Benchmarks #835:Commit 338d66f85e pushed by osobh

main

2026-09-17 22:26:47 +00:00

2m7s

embedded3 item 10: the apertured cut-cell wall (AM-wall) — cutwall.rs classification, apertured projection with the compatible wall flux, cut predictor (V_u = αhA, averaged mass fluxes, implicit wall shear, inertia floor), cut load route; sphere MMS …

Performance Benchmarks #823:Commit 0e4c97ed24 pushed by osobh

main

2026-09-17 20:36:52 +00:00

2m40s

rtx-cfd embedded3 item 9: wall.rs (binary ghost mask: three face families, trilinear stencil with periodic-z wrap, z-weighted least-squares ghost fit, flux compatibility correction; slip walls allowed as touched sides) + loads.rs (surface-stress route …

Performance Benchmarks #820:Commit d337afa8f9 pushed by osobh

main

2026-09-17 20:17:34 +00:00

2m51s

rtx-cfd embedded3 item 7: e3_step.cu + step::device::{DeviceStep, StepTimers} on the shared runtime (FMA off); gate 7 HELD: device = host ≤ 7e-12 under tight tolerances on MMS/Beltrami/Poiseuille, equal CG counts on every step, periodic planes within …

Performance Benchmarks #814:Commit 54911b4db3 pushed by osobh

main

2026-09-17 19:59:56 +00:00

3m5s

rtx-cfd embedded3 items 4–6: field.rs + step/{mod, predictor, projection} (364/700/419 lines) — the host PISO step re-laid from the verified three_d code; gates HELD: MMS + Poiseuille marches value-identical to the 2D embedded solver at nz=1 over 200…

Performance Benchmarks #811:Commit 8821e18520 pushed by osobh

main

2026-09-17 19:59:36 +00:00

4m14s

rtx-cfd embedded3 item 2: e3_mg.cu + poisson::{export, device} (one shared CUDA runtime and module loader for embedded3); gate 2 HELD: device V-cycle = host f32 to 4e-7 relative on 96×40×{1,8} and 378×62×62, 4.97 ms per V-cycle at 1.45 M cells incl. tr…

Performance Benchmarks #805:Commit 5e2b565971 pushed by osobh

main

2026-09-17 19:55:22 +00:00

2m59s

rtx-cfd 3D Stage 1 item 6: three_d::geometry::{Body3, CutGeometry3} — nodal signed distance, face apertures and cell volumes exact for the linear interpolant on a fixed Kuhn six-tet split (consistent across faces), the wall polygon by closure, face-ce…

Performance Benchmarks #799:Commit 13d30c3ce6 pushed by osobh

main

2026-09-17 16:53:15 +00:00

4m7s

rtx-cfd three_d piso_device: pass the pointer table by reference (clippy)

Performance Benchmarks #793:Commit bd43b34850 pushed by osobh

main

2026-09-17 16:48:42 +00:00

4m14s

rtx-cfd 3D Stage 1 item 2: mg3_vcycle.cu (seven-point red-black half-sweep, residual, coarsest; top/bot neighbour arrays carry the periodic wrap), LevelExport3/export_hierarchy3/vcycle_f32_reference3, DeviceVcycle3 (the K=1 sequence); gate 2 HELD: devi…

Performance Benchmarks #778:Commit 05ed96f383 pushed by osobh

main

2026-09-17 16:18:56 +00:00

3m48s

rtx-cfd three_d: ignore reasons on the probes (clippy)

Performance Benchmarks #775:Commit c13b07b68d pushed by osobh

main

2026-09-17 16:18:35 +00:00

6m10s

rtx-cfd 3D Stage 1 item 1: three_d::{Grid3, poisson} — the 2D Poisson stack transcribed to a seven-point operator (sanitised coefficients, 2×2×2 Galerkin aggregation, (i+j+k)%2 colouring, periodic z, run_pcg line for line, PcgCache3); gate 1 HELD: nz=…

Performance Benchmarks #772:Commit 0794e1b6db pushed by osobh

main

2026-09-17 16:18:22 +00:00

6m25s

rtx-cfd CUDA Poisson kernels: solve ∇²φ = f as documented (the updates subtracted the source with the wrong sign); the Jacobi test's stop is absolute on a source of size 2π²

Performance Benchmarks #760:Commit eba2f61ddf pushed by osobh

main

2026-09-16 12:36:15 +00:00

1m42s

rtx-cfd legacy GPU tests: the Jacobi Poisson test stops at 1e-4 (the accuracy check is the pin); rustfmt

Performance Benchmarks #757:Commit 52fd40f8f2 pushed by osobh

main

2026-09-16 12:34:40 +00:00

2m6s

rtx-cfd legacy GPU: kernel outputs were device-buffer CLONES (every write lost) — the buffers are borrowed mutably now; the Poisson kernels keep boundary Dirichlet values; tests: the advection pulse marched 50 steps, the Jacobi budget 20k, the reducti…

Performance Benchmarks #745:Commit 0de750bad1 pushed by osobh

main

2026-09-16 12:31:36 +00:00

2m50s

rtx-cfd: rustfmt over the repaired GPU modules and tests

Performance Benchmarks #733:Commit 7f4d437199 pushed by osobh

main

2026-09-16 12:22:24 +00:00

2m31s

rtx-cfd legacy GPU tests: struct-update commas and the Poisson in-out buffer

Performance Benchmarks #727:Commit 147e0c0422 pushed by osobh

main

2026-09-16 12:23:06 +00:00

3m50s

rtx-cfd legacy GPU tests: the kernels' output buffers are &mut

Performance Benchmarks #724:Commit 534801e16a pushed by osobh

main

2026-09-16 12:22:45 +00:00

3m42s

rtx-cfd legacy GPU tests: the current CudaKernelManager API (Arc-held manager, allocate-on-copy, copy_from_device returning the host vector), MatrixOpsKernel::tridiagonal_matvec added over the existing kernel, PoissonKernel::solve_jacobi_2d kept as the…

Performance Benchmarks #721:Commit 1381b5b633 pushed by osobh

main

2026-09-16 12:21:59 +00:00

3m23s

rtx-cfd legacy GPU modules: cudarc 0.18 API — unsafe launches, the stream accessor, memcpy_htod argument order; the renamed k-ε constants and ::standard(); get_module clones; CfdConfig test literals take ..Default

Performance Benchmarks #715:Commit 5e402918bb pushed by osobh

main

2026-09-16 12:18:42 +00:00

2m0s

rtx-cfd: the legacy GPU modules back in the cuda build (repair in progress)

Performance Benchmarks #712:Commit de435eb91c pushed by osobh

main

2026-09-16 12:18:25 +00:00

2m59s

rtx-fsi: the interface noise probe reads RTX_FSI2_MG_DEVICE (the device V-cycle's regime gate)

Performance Benchmarks #709:Commit 3fd4fb7b8c pushed by osobh

main

2026-09-16 06:27:31 +00:00

3m11s

PERF-2 P3-ii: the device V-cycle as the CG's preconditioner — poisson/device.rs (one CUDA runtime per process, persistent per-operator buffers, the mg_vcycle.cu kernels at K = 1; upload r, run the V-cycle, download z; the f64 CG unchanged), MultigridP…

Performance Benchmarks #706:Commit fc556f8a88 pushed by osobh

main

2026-09-16 06:20:17 +00:00

3m18s

PERF-2 P3 bench: per-level comparison of the device V-cycle's work vectors against the CPU's (vcycle_f32_work) to locate the disagreement

Performance Benchmarks #700:Commit 06a60b5fed pushed by osobh

main

2026-09-16 06:08:55 +00:00

22s

rtx-cfd: the legacy GPU solver modules (piso_gpu, simple_gpu, d2q9_gpu, d3q19_gpu, smagorinsky_gpu) kept out of the cuda build — broken since the initial commit; the PERF-2 benchmark uses cudarc directly

Performance Benchmarks #697:Commit cb1647c0ef pushed by osobh

main

2026-09-16 06:08:46 +00:00

3m4s

rtx-cfd: get_features compiles under --features cuda (the vector must be mutable)

Performance Benchmarks #688:Commit 53078c2aa7 pushed by osobh

main

2026-09-16 06:03:59 +00:00

3m21s

rtx-fsi harness: the embedded harness's EmbeddedParameters carries the smoother field (the previous commit did not compile the rtx-fsi tests)

Performance Benchmarks #670:Commit 43d5abde8d pushed by osobh

main

2026-09-16 04:53:35 +00:00

4m1s

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 t…

Performance Benchmarks #667:Commit cb5771fa71 pushed by osobh

main

2026-09-16 04:53:14 +00:00

4m14s