rustytorch

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…

CI #779:Commit 05ed96f383 pushed by osobh

main

2026-09-18 17:08:30 +00:00

24h53m21s

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

CI #776:Commit c13b07b68d pushed by osobh

main

2026-09-18 17:08:30 +00:00

24h56m1s

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=…

CI #773:Commit 0794e1b6db pushed by osobh

main

2026-09-18 17:08:30 +00:00

24h56m33s

rtx-cfd/rtx-fsi PERF-2 P3-iii K-stream mode: each lane thread's device operator lives on its own CUDA stream (no rendezvous; set_plane_streams, RTX_FSI2O_PLANE_MODE=streams default | batch); stream-mode unit test digit-identical to the solo apply

CI #770:Commit 7e135893a2 pushed by osobh

main

2026-09-18 17:08:30 +00:00

29h27m43s

rtx-cfd/rtx-fsi PERF-2 P3-iii: the MarchPlane — lane-table V-cycle kernels (ml_*), the batched apply over K lanes' own operators, the plane rendezvous inside the CG's preconditioner (lane thread-local, CG guard), set_plane_lane/plane_counters; the fsi…

CI #767:Commit 95ffde9591 pushed by osobh

main

2026-09-17 23:08:30 +00:00

25h4m36s

rtx-cfd legacy GPU tests: the two point-source Poisson tests expect the sign of ∇²φ = f

CI #764:Commit 49ccebc863 pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h32m20s

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

CI #761:Commit eba2f61ddf pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h33m58s

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

CI #758:Commit 52fd40f8f2 pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h35m57s

rtx-cfd legacy GPU: per-block buffer mutability; the D3Q19 getters extract before borrowing

CI #755:Commit 1f77ec637a pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h37m43s

rtx-cfd legacy GPU: buffers re-borrowed after nested device calls; writing and delegating methods take &mut self

CI #752:Commit 8999548aca pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h38m25s

rtx-cfd legacy GPU: the kernel-writing methods take &mut self; read-only ones keep a shared borrow

CI #749:Commit fd5972c949 pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h39m24s

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…

CI #746:Commit 0de750bad1 pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h39m45s

rtx-cfd CUDA kernels: no host includes at all in the NVRTC sources; the float limits defined inline

CI #743:Commit f3f6ac21fb pushed by osobh

main

2026-09-17 17:08:31 +00:00

28h43m31s

rtx-cfd CUDA kernels: no host headers in the NVRTC sources (cuda_runtime.h was never found: every legacy GPU test failed at manager creation)

CI #740:Commit 64faa095a2 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h45m24s

rtx-cfd legacy GPU modules: the launches that already sat in unsafe blocks are not wrapped twice

CI #737:Commit f429bdd415 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h47m32s

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

CI #734:Commit 7f4d437199 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h48m33s

rtx-cfd legacy GPU tests: one base struct per literal

CI #731:Commit 3dadf1ab5c pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h48m59s

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

CI #728:Commit 147e0c0422 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h49m13s

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

CI #725:Commit 534801e16a pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h49m27s

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…

CI #722:Commit 1381b5b633 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h49m54s

rtx-cfd k-ε GPU: memcpy_dtoh argument order

CI #719:Commit af19860c04 pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h51m31s

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

CI #716:Commit 5e402918bb pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h51m48s

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

CI #713:Commit de435eb91c pushed by osobh

main

2026-09-17 17:08:30 +00:00

28h53m2s

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

CI #710:Commit 3fd4fb7b8c pushed by osobh

main

2026-09-17 11:08:30 +00:00

28h44m10s

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…

CI #707:Commit fc556f8a88 pushed by osobh

main

2026-09-17 11:08:30 +00:00

28h51m31s

PERF-2 P3 bench: the coarsest level uses the CPU's red-black symmetric ordering (a nearly singular coarsest system settles on a smoother-dependent constant, which the prolongation doubled up every level: the 19 % disagreement)

CI #704:Commit 3b7f8fb362 pushed by osobh

main

2026-09-17 11:08:30 +00:00

28h58m14s

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

CI #701:Commit 06a60b5fed pushed by osobh

main

2026-09-17 11:08:30 +00:00

28h59m56s

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

CI #698:Commit cb1647c0ef pushed by osobh

main

2026-09-17 11:08:30 +00:00

29h2m48s

rtx-cfd: the cuda feature builds again — the duplicate CudaKernelManager::stream removed, the legacy k-epsilon GPU model (broken since the initial commit) kept out of the build

CI #695:Commit 956e9d38e2 pushed by osobh

main

2026-09-17 11:08:30 +00:00

29h4m52s

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), LevelExpo…

CI #692:Commit 0dc95a8de5 pushed by osobh

main

2026-09-17 11:08:30 +00:00

29h5m23s