[STF] Add python bindings by caugonnet · Pull Request #5315 · NVIDIA/cccl

caugonnet · 2025-07-18T21:28:42Z

Description

Introduce Python bindings for CUDASTF as a new cuda-stf package (module cuda.stf._experimental, Linux only). The bindings sit on top of the STF C API (c/experimental/stf, already merged to main) and expose contexts, logical data, tasks, execution/data places, CUDA graph utilities, and interop layers for Numba, PyTorch, Warp, and cuda.compute.

Scope note for reviewers: the C API itself is not in this diff (it landed separately); execution-grid reshape bindings are split out into #9899. Of the ~21k added lines, ~13k are tests and examples — the reviewable core is ~5.9k lines of bindings + support code.

What's in the PR (per-area breakdown)

Area	Lines	Files
Core Cython bindings	~4,550	`_stf_bindings_impl.pyx` (4,270), `_stf_bindings.py` loader, `__init__.py`, stream/version utils
Pure-Python support layer	~1,350	`device_array.py`, `task_graph.py`, `green_places.py`, `fill_utils.py`, `paths.py`, `interop/{numba,pytorch}.py`
Packaging	~730	`CMakeLists.txt`, `pyproject.toml`, `merge_cuda_wheels.py`, `README.md`
CI	~420	`ci/build_cuda_stf_python.sh`, `ci/build_cuda_stf_wheel.sh`, `ci/test_cuda_stf_python.sh`, `ci/matrix.yaml` hooks
Documentation	~750	`docs/python/stf.rst` (user guide), `docs/python/stf_api.rst` (API reference), setup docs
Unit tests	~4,250	`tests/stf/test_*.py` — one file per feature area
Interop tests	~3,700	`tests/stf/interop/` — Numba, PyTorch, Warp, cuda.compute, legacy-stream interop
Examples	~5,170	`tests/stf/examples/` — CG, BiCGStab, Cholesky/POTRI, Burgers, neural ODEs, FHE

Walkthrough of `_stf_bindings_impl.pyx`

The file is organized in layers, bottom-up (line anchors approximate):

FFI plumbing (top–L450): dlopen-based loading of libcccl.c.experimental.stf.so, ctypes structs for the data-place mapper callback (_MapperCallbackState, _make_mapper_callback), and AccessMode flags.
CUDA Array Interface helpers (L490–L690): CAI validation (dtype, C-contiguity), producer-stream synchronization, and stf_cai — the view type tasks hand back for deps.
Lifetime primitives (L691–L780): _AliveFlag (guards use-after-finalize) and _PrimaryContextPin (keeps primary contexts alive while STF holds resources on them).
logical_data and deps (L781–L1072): the central data abstraction plus read/write/rw dep constructors.
Places (L1086–L1820): CudaStream, green-context views/helpers, exec_place, exec_place_grid, data_place. Grid places own arrays of handles; note the linear-order guarantees.
Tasks (L1820–L2255): task (acquire/release protocol, per-dep CAI export on the task stream) and cuda_kernel (kernel-launch task flavor).
context (L2256–L2920): the main entry point — task creation, logical_data factories, finalize semantics, async_resources sharing.
Stackable/local STF (L2923–L3610): stackable_logical_data, stackable_task, LaunchableGraph + graph scopes — CUDA-graph capture of STF sections.
Control flow (L3612–end): cond expressions, while_loop/repeat scopes, and stackable_context tying it together.

Key design points worth focused review:

Ownership/lifetime: every cdef class wrapping a C handle uses explicit destroy-on-dealloc plus _AliveFlag; finalize order between Python GC and STF context shutdown is the trickiest part.
Stream semantics: data exchanged via CAI is synchronized against the producer stream (_sync_cai_producer_stream); task bodies run on the task's stream.
Error paths: C API failures raise Python exceptions rather than aborting; malformed CAI inputs are rejected before touching the C layer.

Checklist

New or existing tests cover these changes.
The documentation is up to date with these changes.

copy-pr-bot · 2025-07-18T21:28:46Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

caugonnet · 2025-07-18T21:39:18Z

/ok to test c9acb99

caugonnet · 2025-07-18T22:01:38Z

/ok to test 6971d8f

caugonnet · 2025-07-18T22:36:49Z

/ok to test 2f7299e

github-actions · 2025-07-19T00:18:55Z

🟨 CI finished in 1h 40m: Pass: 91%/205 | Total: 1d 11h | Avg: 10m 28s | Max: 43m 15s | Hits: 96%/340562

🟥 python: Pass: 0%/18 | Total: 18m 23s | Avg: 1m 01s | Max: 9m 23s

🟥 cpu
  🟥 amd64              Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 ctk
  🟥 12.9               Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 cxx
  🟥 GCC13              Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 cxx_family
  🟥 GCC                Pass:   0%/18  | Total: 18m 23s | Avg:  1m 01s | Max:  9m 23s
🟥 gpu
  🟥 h100               Pass:   0%/8  
  🟥 rtxa6000           Pass:   0%/10  | Total: 18m 23s | Avg:  1m 50s | Max:  9m 23s
🟥 jobs
  🟥 Build cuda.cccl    Pass:   0%/2   | Total: 18m 23s | Avg:  9m 11s | Max:  9m 23s
  🟥 Test cuda.cccl.cooperative Pass:   0%/4  
  🟥 Test cuda.cccl.examples Pass:   0%/4  
  🟥 Test cuda.cccl.headers Pass:   0%/4  
  🟥 Test cuda.cccl.parallel Pass:   0%/4  
🟥 py_version
  🟥 3.10               Pass:   0%/9   | Total:  9m 23s | Avg:  1m 02s | Max:  9m 23s
  🟥 3.13               Pass:   0%/9   | Total:  9m 00s | Avg:  1m 00s | Max:  9m 00s

🟩 cub: Pass: 100%/50 | Total: 12h 24m | Avg: 14m 53s | Max: 43m 15s | Hits: 99%/61706

🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total: 12h 10m | Avg: 15m 12s | Max: 43m 15s | Hits:  99%/59190 
  🟩 arm64              Pass: 100%/2   | Total: 14m 34s | Avg:  7m 17s | Max:  8m 24s | Hits:  99%/2516  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total:  1h 00m | Avg: 12m 00s | Max: 30m 17s | Hits:  99%/6186  
  🟩 12.9               Pass: 100%/45  | Total: 11h 24m | Avg: 15m 12s | Max: 43m 15s | Hits:  99%/55520 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 29s | Avg:  5m 14s | Max:  5m 18s | Hits:  99%/2165  
  🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 00m | Avg: 12m 00s | Max: 30m 17s | Hits:  99%/6186  
  🟩 nvcc12.9           Pass: 100%/43  | Total: 11h 14m | Avg: 15m 40s | Max: 43m 15s | Hits:  99%/53355 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 29s | Avg:  5m 14s | Max:  5m 18s | Hits:  99%/2165  
  🟩 nvcc               Pass: 100%/48  | Total: 12h 14m | Avg: 15m 17s | Max: 43m 15s | Hits:  99%/59541 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 26m 17s | Avg:  6m 34s | Max:  7m 00s | Hits:  99%/5034  
  🟩 Clang15            Pass: 100%/2   | Total: 13m 48s | Avg:  6m 54s | Max:  6m 55s | Hits:  99%/2513  
  🟩 Clang16            Pass: 100%/2   | Total: 13m 27s | Avg:  6m 43s | Max:  6m 45s | Hits:  99%/2513  
  🟩 Clang17            Pass: 100%/2   | Total: 14m 22s | Avg:  7m 11s | Max:  7m 17s | Hits:  99%/2513  
  🟩 Clang18            Pass: 100%/2   | Total: 13m 10s | Avg:  6m 35s | Max:  6m 36s | Hits:  99%/2513  
  🟩 Clang19            Pass: 100%/7   | Total:  1h 39m | Avg: 14m 13s | Max: 35m 00s | Hits:  99%/8449  
  🟩 GCC7               Pass: 100%/2   | Total: 16m 58s | Avg:  8m 29s | Max:  8m 32s | Hits:  99%/2516  
  🟩 GCC8               Pass: 100%/1   | Total:  8m 47s | Avg:  8m 47s | Max:  8m 47s | Hits:  99%/1258  
  🟩 GCC9               Pass: 100%/2   | Total: 18m 43s | Avg:  9m 21s | Max:  9m 43s | Hits:  99%/2516  
  🟩 GCC10              Pass: 100%/2   | Total: 18m 01s | Avg:  9m 00s | Max:  9m 05s | Hits:  99%/2517  
  🟩 GCC11              Pass: 100%/2   | Total: 17m 44s | Avg:  8m 52s | Max:  9m 14s | Hits:  99%/2513  
  🟩 GCC12              Pass: 100%/2   | Total: 19m 10s | Avg:  9m 35s | Max: 10m 03s | Hits:  99%/2513  
  🟩 GCC13              Pass: 100%/12  | Total:  4h 17m | Avg: 21m 28s | Max: 43m 15s | Hits:  99%/15105 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 02m | Avg: 31m 28s | Max: 32m 40s | Hits:  99%/2306  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  1h 57m | Avg: 29m 23s | Max: 32m 44s | Hits:  99%/4612  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 26m 34s | Avg: 13m 17s | Max: 13m 20s | Hits:  98%/2315  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  3h 00m | Avg:  9m 30s | Max: 35m 00s | Hits:  99%/23535 
  🟩 GCC                Pass: 100%/23  | Total:  5h 57m | Avg: 15m 31s | Max: 43m 15s | Hits:  99%/28938 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 00m | Avg: 30m 05s | Max: 32m 44s | Hits:  99%/6918  
  🟩 NVHPC              Pass: 100%/2   | Total: 26m 34s | Avg: 13m 17s | Max: 13m 20s | Hits:  98%/2315  
🟩 gpu
  🟩 h100               Pass: 100%/3   | Total: 59m 25s | Avg: 19m 48s | Max: 29m 32s | Hits:  99%/3777  
  🟩 rtx2080            Pass: 100%/39  | Total:  7h 25m | Avg: 11m 25s | Max: 32m 44s | Hits:  99%/47863 
  🟩 rtxa6000           Pass: 100%/8   | Total:  3h 59m | Avg: 29m 59s | Max: 43m 15s | Hits:  99%/10066 
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  7h 47m | Avg: 11m 08s | Max: 32m 44s | Hits:  99%/51638 
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 37m 41s | Avg: 37m 41s | Max: 37m 41s | Hits:  99%/1259  
  🟩 GraphCapture       Pass: 100%/1   | Total: 35m 39s | Avg: 35m 39s | Max: 35m 39s | Hits:  99%/1259  
  🟩 HostLaunch         Pass: 100%/3   | Total:  1h 42m | Avg: 34m 12s | Max: 38m 05s | Hits:  99%/3775  
  🟩 TestGPU            Pass: 100%/3   | Total:  1h 40m | Avg: 33m 39s | Max: 43m 15s | Hits:  99%/3775  
🟩 sm
  🟩 90                 Pass: 100%/3   | Total: 59m 25s | Avg: 19m 48s | Max: 29m 32s | Hits:  99%/3777  
  🟩 90;90a             Pass: 100%/2   | Total: 34m 58s | Avg: 17m 29s | Max: 26m 27s | Hits:  99%/2412  
  🟩 100;120            Pass: 100%/2   | Total: 35m 50s | Avg: 17m 55s | Max: 27m 10s | Hits:  99%/2412  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  4h 01m | Avg: 11m 30s | Max: 32m 44s | Hits:  99%/25810 
  🟩 20                 Pass: 100%/29  | Total:  8h 23m | Avg: 17m 20s | Max: 43m 15s | Hits:  99%/35896

🟩 thrust: Pass: 100%/50 | Total: 9h 24m | Avg: 11m 17s | Max: 36m 32s | Hits: 99%/95621

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 21m 03s | Avg: 10m 31s | Max: 13m 07s | Hits:  99%/3828  
🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total:  9h 12m | Avg: 11m 30s | Max: 36m 32s | Hits:  99%/91794 
  🟩 arm64              Pass: 100%/2   | Total: 12m 05s | Avg:  6m 02s | Max:  6m 59s | Hits:  99%/3827  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 52m 06s | Avg: 10m 25s | Max: 27m 17s | Hits:  99%/9560  
  🟩 12.9               Pass: 100%/45  | Total:  8h 32m | Avg: 11m 23s | Max: 36m 32s | Hits:  99%/86061 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 11m 13s | Avg:  5m 36s | Max:  5m 53s | Hits: 100%/3826  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 52m 06s | Avg: 10m 25s | Max: 27m 17s | Hits:  99%/9560  
  🟩 nvcc12.9           Pass: 100%/43  | Total:  8h 21m | Avg: 11m 39s | Max: 36m 32s | Hits:  99%/82235 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 11m 13s | Avg:  5m 36s | Max:  5m 53s | Hits: 100%/3826  
  🟩 nvcc               Pass: 100%/48  | Total:  9h 13m | Avg: 11m 31s | Max: 36m 32s | Hits:  99%/91795 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 23m 42s | Avg:  5m 55s | Max:  6m 24s | Hits: 100%/7652  
  🟩 Clang15            Pass: 100%/2   | Total: 11m 34s | Avg:  5m 47s | Max:  5m 48s | Hits: 100%/3826  
  🟩 Clang16            Pass: 100%/2   | Total: 12m 01s | Avg:  6m 00s | Max:  6m 06s | Hits: 100%/3826  
  🟩 Clang17            Pass: 100%/2   | Total: 11m 33s | Avg:  5m 46s | Max:  5m 50s | Hits: 100%/3826  
  🟩 Clang18            Pass: 100%/2   | Total: 11m 27s | Avg:  5m 43s | Max:  5m 44s | Hits: 100%/3826  
  🟩 Clang19            Pass: 100%/7   | Total: 47m 25s | Avg:  6m 46s | Max: 10m 58s | Hits: 100%/13391 
  🟩 GCC7               Pass: 100%/2   | Total: 13m 47s | Avg:  6m 53s | Max:  7m 21s | Hits:  99%/3828  
  🟩 GCC8               Pass: 100%/1   | Total:  7m 08s | Avg:  7m 08s | Max:  7m 08s | Hits:  99%/1914  
  🟩 GCC9               Pass: 100%/2   | Total: 15m 06s | Avg:  7m 33s | Max:  7m 58s | Hits:  99%/3828  
  🟩 GCC10              Pass: 100%/2   | Total: 14m 42s | Avg:  7m 21s | Max:  7m 24s | Hits:  99%/3828  
  🟩 GCC11              Pass: 100%/2   | Total: 15m 42s | Avg:  7m 51s | Max:  8m 00s | Hits:  99%/3828  
  🟩 GCC12              Pass: 100%/2   | Total: 16m 47s | Avg:  8m 23s | Max:  8m 29s | Hits:  99%/3828  
  🟩 GCC13              Pass: 100%/11  | Total:  1h 41m | Avg:  9m 14s | Max: 14m 40s | Hits:  99%/21054 
  🟩 MSVC14.29          Pass: 100%/2   | Total: 55m 13s | Avg: 27m 36s | Max: 27m 56s | Hits:  99%/3812  
  🟩 MSVC14.43          Pass: 100%/5   | Total:  2h 20m | Avg: 28m 05s | Max: 33m 15s | Hits:  99%/9530  
  🟩 NVHPC25.5          Pass: 100%/2   | Total:  1h 06m | Avg: 33m 17s | Max: 36m 32s | Hits:  99%/3824  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  1h 57m | Avg:  6m 11s | Max: 10m 58s | Hits: 100%/36347 
  🟩 GCC                Pass: 100%/22  | Total:  3h 04m | Avg:  8m 24s | Max: 14m 40s | Hits:  99%/42108 
  🟩 MSVC               Pass: 100%/7   | Total:  3h 15m | Avg: 27m 57s | Max: 33m 15s | Hits:  99%/13342 
  🟩 NVHPC              Pass: 100%/2   | Total:  1h 06m | Avg: 33m 17s | Max: 36m 32s | Hits:  99%/3824  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 20m 25s | Avg: 10m 12s | Max: 14m 40s | Hits:  99%/3828  
  🟩 rtx2080            Pass: 100%/38  | Total:  6h 45m | Avg: 10m 39s | Max: 36m 32s | Hits:  99%/72672 
  🟩 rtx4090            Pass: 100%/10  | Total:  2h 19m | Avg: 13m 54s | Max: 33m 15s | Hits:  99%/19121 
🟩 jobs
  🟩 Build              Pass: 100%/43  | Total:  7h 42m | Avg: 10m 44s | Max: 36m 32s | Hits:  99%/82233 
  🟩 TestCPU            Pass: 100%/3   | Total: 50m 42s | Avg: 16m 54s | Max: 33m 15s | Hits:  99%/5733  
  🟩 TestGPU            Pass: 100%/4   | Total: 52m 00s | Avg: 13m 00s | Max: 14m 40s | Hits:  99%/7655  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 20m 25s | Avg: 10m 12s | Max: 14m 40s | Hits:  99%/3828  
  🟩 90;90a             Pass: 100%/2   | Total: 31m 34s | Avg: 15m 47s | Max: 24m 24s | Hits:  99%/3820  
  🟩 100;120            Pass: 100%/2   | Total: 31m 29s | Avg: 15m 44s | Max: 24m 33s | Hits:  99%/3820  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  3h 56m | Avg: 11m 15s | Max: 36m 32s | Hits:  99%/40160 
  🟩 20                 Pass: 100%/27  | Total:  5h 07m | Avg: 11m 23s | Max: 33m 15s | Hits:  99%/51633

🟩 libcudacxx: Pass: 100%/48 | Total: 10h 07m | Avg: 12m 39s | Max: 34m 35s | Hits: 92%/166828

🟩 cpu
  🟩 amd64              Pass: 100%/46  | Total:  9h 58m | Avg: 13m 00s | Max: 34m 35s | Hits:  92%/159367
  🟩 arm64              Pass: 100%/2   | Total:  9m 08s | Avg:  4m 34s | Max:  4m 40s | Hits:  99%/7461  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 47m 32s | Avg:  9m 30s | Max: 30m 11s | Hits:  99%/18287 
  🟩 12.9               Pass: 100%/43  | Total:  9h 19m | Avg: 13m 01s | Max: 34m 35s | Hits:  91%/148541
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 53m 46s | Avg: 26m 53s | Max: 27m 32s | Hits:  29%/7425  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 47m 32s | Avg:  9m 30s | Max: 30m 11s | Hits:  99%/18287 
  🟩 nvcc12.9           Pass: 100%/41  | Total:  8h 26m | Avg: 12m 20s | Max: 34m 35s | Hits:  94%/141116
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 53m 46s | Avg: 26m 53s | Max: 27m 32s | Hits:  29%/7425  
  🟩 nvcc               Pass: 100%/46  | Total:  9h 13m | Avg: 12m 02s | Max: 34m 35s | Hits:  95%/159403
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 18m 45s | Avg:  4m 41s | Max:  5m 03s | Hits:  99%/14806 
  🟩 Clang15            Pass: 100%/2   | Total: 36m 25s | Avg: 18m 12s | Max: 31m 20s | Hits:  68%/7421  
  🟩 Clang16            Pass: 100%/2   | Total: 11m 12s | Avg:  5m 36s | Max:  6m 10s | Hits:  98%/7421  
  🟩 Clang17            Pass: 100%/2   | Total: 39m 30s | Avg: 19m 45s | Max: 34m 35s | Hits:  68%/7421  
  🟩 Clang18            Pass: 100%/2   | Total:  9m 50s | Avg:  4m 55s | Max:  4m 58s | Hits:  99%/7421  
  🟩 Clang19            Pass: 100%/6   | Total:  1h 30m | Avg: 15m 01s | Max: 27m 32s | Hits:  75%/22306 
  🟩 GCC7               Pass: 100%/2   | Total:  8m 54s | Avg:  4m 27s | Max:  4m 44s | Hits:  99%/7357  
  🟩 GCC8               Pass: 100%/1   | Total:  4m 33s | Avg:  4m 33s | Max:  4m 33s | Hits:  99%/3689  
  🟩 GCC9               Pass: 100%/2   | Total:  9m 47s | Avg:  4m 53s | Max:  5m 20s | Hits:  99%/7369  
  🟩 GCC10              Pass: 100%/2   | Total:  9m 43s | Avg:  4m 51s | Max:  4m 58s | Hits:  99%/7423  
  🟩 GCC11              Pass: 100%/2   | Total: 18m 13s | Avg:  9m 06s | Max: 13m 24s | Hits:  89%/7419  
  🟩 GCC12              Pass: 100%/2   | Total: 10m 06s | Avg:  5m 03s | Max:  5m 09s | Hits:  99%/7423  
  🟩 GCC13              Pass: 100%/11  | Total:  2h 16m | Avg: 12m 22s | Max: 24m 39s | Hits:  96%/30183 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 01m | Avg: 30m 59s | Max: 31m 47s | Hits:  99%/7093  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  2h 00m | Avg: 30m 05s | Max: 32m 19s | Hits:  99%/14669 
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 21m 55s | Avg: 10m 57s | Max: 11m 10s | Hits:  98%/7407  
🟩 cxx_family
  🟩 Clang              Pass: 100%/18  | Total:  3h 25m | Avg: 11m 26s | Max: 34m 35s | Hits:  84%/66796 
  🟩 GCC                Pass: 100%/22  | Total:  3h 17m | Avg:  8m 58s | Max: 24m 39s | Hits:  97%/70863 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 02m | Avg: 30m 23s | Max: 32m 19s | Hits:  99%/21762 
  🟩 NVHPC              Pass: 100%/2   | Total: 21m 55s | Avg: 10m 57s | Max: 11m 10s | Hits:  98%/7407  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 27m 15s | Avg: 13m 37s | Max: 22m 05s | Hits:  99%/7628  
  🟩 rtx2080            Pass: 100%/46  | Total:  9h 40m | Avg: 12m 36s | Max: 34m 35s | Hits:  92%/159200
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  8h 09m | Avg: 11m 39s | Max: 34m 35s | Hits:  92%/155511
  🟩 NVRTC              Pass: 100%/2   | Total: 48m 44s | Avg: 24m 22s | Max: 24m 39s | Hits:  90%/42    
  🟩 Test               Pass: 100%/3   | Total:  1h 07m | Avg: 22m 25s | Max: 23m 44s | Hits:  99%/11275 
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 58s | Avg:  1m 58s | Max:  1m 58s
🟩 sm
  🟩 75                 Pass: 100%/2   | Total: 48m 44s | Avg: 24m 22s | Max: 24m 39s | Hits:  90%/42    
  🟩 90                 Pass: 100%/2   | Total: 27m 15s | Avg: 13m 37s | Max: 22m 05s | Hits:  99%/7628  
  🟩 90;90a             Pass: 100%/2   | Total: 35m 18s | Avg: 17m 39s | Max: 30m 15s | Hits:  99%/7575  
  🟩 100;120            Pass: 100%/2   | Total: 34m 03s | Avg: 17m 01s | Max: 28m 28s | Hits:  99%/7575  
🟩 std
  🟩 17                 Pass: 100%/22  | Total:  4h 34m | Avg: 12m 27s | Max: 31m 47s | Hits:  91%/77045 
  🟩 20                 Pass: 100%/25  | Total:  5h 31m | Avg: 13m 15s | Max: 34m 35s | Hits:  93%/89783

🟩 cudax: Pass: 100%/28 | Total: 2h 37m | Avg: 5m 37s | Max: 12m 36s | Hits: 99%/15906

🟩 cpu
  🟩 amd64              Pass: 100%/24  | Total:  2h 24m | Avg:  6m 02s | Max: 12m 36s | Hits:  99%/13462 
  🟩 arm64              Pass: 100%/4   | Total: 12m 37s | Avg:  3m 09s | Max:  3m 27s | Hits:  99%/2444  
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 18m 20s | Avg:  6m 06s | Max: 11m 39s | Hits:  99%/1531  
  🟩 12.9               Pass: 100%/25  | Total:  2h 19m | Avg:  5m 33s | Max: 12m 36s | Hits:  99%/14375 
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 18m 20s | Avg:  6m 06s | Max: 11m 39s | Hits:  99%/1531  
  🟩 nvcc12.9           Pass: 100%/25  | Total:  2h 19m | Avg:  5m 33s | Max: 12m 36s | Hits:  99%/14375 
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/28  | Total:  2h 37m | Avg:  5m 37s | Max: 12m 36s | Hits:  99%/15906 
🟩 cxx
  🟩 Clang14            Pass: 100%/2   | Total:  6m 35s | Avg:  3m 17s | Max:  3m 31s | Hits: 100%/1224  
  🟩 Clang15            Pass: 100%/1   | Total:  3m 20s | Avg:  3m 20s | Max:  3m 20s | Hits: 100%/611   
  🟩 Clang16            Pass: 100%/1   | Total:  3m 20s | Avg:  3m 20s | Max:  3m 20s | Hits: 100%/611   
  🟩 Clang17            Pass: 100%/1   | Total:  3m 19s | Avg:  3m 19s | Max:  3m 19s | Hits: 100%/611   
  🟩 Clang18            Pass: 100%/1   | Total:  3m 22s | Avg:  3m 22s | Max:  3m 22s | Hits: 100%/611   
  🟩 Clang19            Pass: 100%/4   | Total: 17m 42s | Avg:  4m 25s | Max:  8m 44s | Hits: 100%/2444  
  🟩 GCC10              Pass: 100%/2   | Total:  7m 15s | Avg:  3m 37s | Max:  3m 38s | Hits:  99%/1224  
  🟩 GCC11              Pass: 100%/1   | Total:  3m 48s | Avg:  3m 48s | Max:  3m 48s | Hits:  99%/611   
  🟩 GCC12              Pass: 100%/1   | Total:  3m 55s | Avg:  3m 55s | Max:  3m 55s | Hits:  99%/611   
  🟩 GCC13              Pass: 100%/8   | Total: 44m 42s | Avg:  5m 35s | Max: 12m 36s | Hits:  99%/4888  
  🟩 MSVC14.39          Pass: 100%/1   | Total: 11m 39s | Avg: 11m 39s | Max: 11m 39s | Hits:  95%/309   
  🟩 MSVC14.43          Pass: 100%/3   | Total: 33m 15s | Avg: 11m 05s | Max: 11m 37s | Hits:  95%/933   
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 15m 16s | Avg:  7m 38s | Max:  7m 50s | Hits:  97%/1218  
🟩 cxx_family
  🟩 Clang              Pass: 100%/10  | Total: 37m 38s | Avg:  3m 45s | Max:  8m 44s | Hits: 100%/6112  
  🟩 GCC                Pass: 100%/12  | Total: 59m 40s | Avg:  4m 58s | Max: 12m 36s | Hits:  99%/7334  
  🟩 MSVC               Pass: 100%/4   | Total: 44m 54s | Avg: 11m 13s | Max: 11m 39s | Hits:  95%/1242  
  🟩 NVHPC              Pass: 100%/2   | Total: 15m 16s | Avg:  7m 38s | Max:  7m 50s | Hits:  97%/1218  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 13m 23s | Avg:  6m 41s | Max: 10m 08s | Hits:  99%/1222  
  🟩 rtx2080            Pass: 100%/26  | Total:  2h 24m | Avg:  5m 32s | Max: 12m 36s | Hits:  99%/14684 
🟩 jobs
  🟩 Build              Pass: 100%/25  | Total:  2h 06m | Avg:  5m 02s | Max: 11m 39s | Hits:  99%/14073 
  🟩 Test               Pass: 100%/3   | Total: 31m 28s | Avg: 10m 29s | Max: 12m 36s | Hits:  99%/1833  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 13m 23s | Avg:  6m 41s | Max: 10m 08s | Hits:  99%/1222  
  🟩 90;90a             Pass: 100%/2   | Total: 14m 56s | Avg:  7m 28s | Max: 11m 09s | Hits:  98%/922   
  🟩 100;120            Pass: 100%/2   | Total: 14m 12s | Avg:  7m 06s | Max: 10m 29s | Hits:  98%/922   
🟩 std
  🟩 17                 Pass: 100%/3   | Total: 14m 10s | Avg:  4m 43s | Max:  7m 50s | Hits:  99%/1831  
  🟩 20                 Pass: 100%/25  | Total:  2h 23m | Avg:  5m 43s | Max: 12m 36s | Hits:  99%/14075

🟩 packaging: Pass: 100%/4 | Total: 12m 18s | Avg: 3m 04s | Max: 3m 22s

🟩 cpu
  🟩 amd64              Pass: 100%/4   | Total: 12m 18s | Avg:  3m 04s | Max:  3m 22s
🟩 ctk
  🟩 12.0               Pass: 100%/2   | Total:  5m 42s | Avg:  2m 51s | Max:  2m 55s
  🟩 12.9               Pass: 100%/2   | Total:  6m 36s | Avg:  3m 18s | Max:  3m 22s
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/2   | Total:  5m 42s | Avg:  2m 51s | Max:  2m 55s
  🟩 nvcc12.9           Pass: 100%/2   | Total:  6m 36s | Avg:  3m 18s | Max:  3m 22s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 12m 18s | Avg:  3m 04s | Max:  3m 22s
🟩 cxx
  🟩 Clang14            Pass: 100%/1   | Total:  2m 47s | Avg:  2m 47s | Max:  2m 47s
  🟩 Clang19            Pass: 100%/1   | Total:  3m 14s | Avg:  3m 14s | Max:  3m 14s
  🟩 GCC12              Pass: 100%/1   | Total:  2m 55s | Avg:  2m 55s | Max:  2m 55s
  🟩 GCC13              Pass: 100%/1   | Total:  3m 22s | Avg:  3m 22s | Max:  3m 22s
🟩 cxx_family
  🟩 Clang              Pass: 100%/2   | Total:  6m 01s | Avg:  3m 00s | Max:  3m 14s
  🟩 GCC                Pass: 100%/2   | Total:  6m 17s | Avg:  3m 08s | Max:  3m 22s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 12m 18s | Avg:  3m 04s | Max:  3m 22s
🟩 jobs
  🟩 Test               Pass: 100%/4   | Total: 12m 18s | Avg:  3m 04s | Max:  3m 22s

🟩 stdpar: Pass: 100%/4 | Total: 17m 30s | Avg: 4m 22s | Max: 4m 48s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total:  9m 19s | Avg:  4m 39s | Max:  4m 48s
  🟩 arm64              Pass: 100%/2   | Total:  8m 11s | Avg:  4m 05s | Max:  4m 08s
🟩 ctk
  🟩 12.9               Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 cxx
  🟩 NVHPC25.5          Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 cxx_family
  🟩 NVHPC              Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 jobs
  🟩 Build              Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 48s
🟩 std
  🟩 17                 Pass: 100%/2   | Total:  8m 34s | Avg:  4m 17s | Max:  4m 31s
  🟩 20                 Pass: 100%/2   | Total:  8m 56s | Avg:  4m 28s | Max:  4m 48s

🟩 cccl_c_parallel: Pass: 100%/3 | Total: 26m 19s | Avg: 8m 46s | Max: 14m 09s | Hits: 98%/501

🟩 cpu
  🟩 amd64              Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 ctk
  🟩 12.9               Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 cxx
  🟩 GCC13              Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 cxx_family
  🟩 GCC                Pass: 100%/3   | Total: 26m 19s | Avg:  8m 46s | Max: 14m 09s | Hits:  98%/501   
🟩 gpu
  🟩 h100               Pass: 100%/1   | Total: 14m 09s | Avg: 14m 09s | Max: 14m 09s | Hits:  98%/167   
  🟩 rtx2080            Pass: 100%/2   | Total: 12m 10s | Avg:  6m 05s | Max:  9m 39s | Hits:  98%/334   
🟩 jobs
  🟩 Build              Pass: 100%/1   | Total:  2m 31s | Avg:  2m 31s | Max:  2m 31s | Hits:  97%/167   
  🟩 Test               Pass: 100%/2   | Total: 23m 48s | Avg: 11m 54s | Max: 14m 09s | Hits:  98%/334

👃 Inspect Changes

Modifications in project?

	Project
+/-	CCCL Infrastructure
	CCCL Packaging
	libcu++
	CUB
	Thrust
	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

Modifications in project or dependencies?

	Project
+/-	CCCL Infrastructure
+/-	CCCL Packaging
+/-	libcu++
+/-	CUB
+/-	Thrust
+/-	CUDA Experimental
+/-	stdpar
+/-	python
+/-	CCCL C Parallel Library
+/-	Catch2Helper

🏃‍ Runner counts (total jobs: 205)

#	Runner
128	`linux-amd64-cpu16`
23	`windows-amd64-cpu16`
14	`linux-amd64-gpu-h100-latest-1`
14	`linux-amd64-gpu-rtxa6000-latest-1`
12	`linux-arm64-cpu16`
11	`linux-amd64-gpu-rtx2080-latest-1`
3	`linux-amd64-gpu-rtx4090-latest-1`

caugonnet · 2025-07-19T07:42:49Z

/ok to test fa8c960

github-actions · 2025-07-19T08:55:08Z

🟨 CI finished in 1h 10m: Pass: 90%/205 | Total: 1d 13h | Avg: 10m 59s | Max: 39m 22s | Hits: 96%/340547

🟥 python: Pass: 0%/18 | Total: 19m 10s | Avg: 1m 03s | Max: 9m 56s

🟥 cpu
  🟥 amd64              Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 ctk
  🟥 12.9               Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 cxx
  🟥 GCC13              Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 cxx_family
  🟥 GCC                Pass:   0%/18  | Total: 19m 10s | Avg:  1m 03s | Max:  9m 56s
🟥 gpu
  🟥 h100               Pass:   0%/8  
  🟥 rtxa6000           Pass:   0%/10  | Total: 19m 10s | Avg:  1m 55s | Max:  9m 56s
🟥 jobs
  🟥 Build cuda.cccl    Pass:   0%/2   | Total: 19m 10s | Avg:  9m 35s | Max:  9m 56s
  🟥 Test cuda.cccl.cooperative Pass:   0%/4  
  🟥 Test cuda.cccl.examples Pass:   0%/4  
  🟥 Test cuda.cccl.headers Pass:   0%/4  
  🟥 Test cuda.cccl.parallel Pass:   0%/4  
🟥 py_version
  🟥 3.10               Pass:   0%/9   | Total:  9m 56s | Avg:  1m 06s | Max:  9m 56s
  🟥 3.13               Pass:   0%/9   | Total:  9m 14s | Avg:  1m 01s | Max:  9m 14s

🟨 libcudacxx: Pass: 97%/48 | Total: 9h 11m | Avg: 11m 28s | Max: 34m 17s | Hits: 94%/166807

🔍 cpu: amd64 🔍
  🔍 amd64              Pass:  97%/46  | Total:  9h 01m | Avg: 11m 46s | Max: 34m 17s | Hits:  94%/159346
  🟩 arm64              Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  4m 43s | Hits:  99%/7461  
🔍 ctk: 12.9 🔍
  🟩 12.0               Pass: 100%/5   | Total: 46m 43s | Avg:  9m 20s | Max: 29m 33s | Hits:  99%/18287 
  🔍 12.9               Pass:  97%/43  | Total:  8h 24m | Avg: 11m 43s | Max: 34m 17s | Hits:  94%/148520
🔍 cudacxx: nvcc12.9 🔍
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 52m 45s | Avg: 26m 22s | Max: 27m 01s | Hits:  29%/7425  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 46m 43s | Avg:  9m 20s | Max: 29m 33s | Hits:  99%/18287 
  🔍 nvcc12.9           Pass:  97%/41  | Total:  7h 31m | Avg: 11m 01s | Max: 34m 17s | Hits:  97%/141095
🔍 cudacxx_family: nvcc 🔍
  🟩 ClangCUDA          Pass: 100%/2   | Total: 52m 45s | Avg: 26m 22s | Max: 27m 01s | Hits:  29%/7425  
  🔍 nvcc               Pass:  97%/46  | Total:  8h 18m | Avg: 10m 50s | Max: 34m 17s | Hits:  97%/159382
🔍 cxx: GCC13 🔍
  🟩 Clang14            Pass: 100%/4   | Total: 19m 25s | Avg:  4m 51s | Max:  5m 18s | Hits:  99%/14806 
  🟩 Clang15            Pass: 100%/2   | Total: 10m 13s | Avg:  5m 06s | Max:  5m 08s | Hits:  99%/7421  
  🟩 Clang16            Pass: 100%/2   | Total: 10m 05s | Avg:  5m 02s | Max:  5m 08s | Hits:  99%/7421  
  🟩 Clang17            Pass: 100%/2   | Total:  9m 43s | Avg:  4m 51s | Max:  4m 52s | Hits:  99%/7421  
  🟩 Clang18            Pass: 100%/2   | Total:  9m 42s | Avg:  4m 51s | Max:  4m 57s | Hits:  99%/7421  
  🟩 Clang19            Pass: 100%/6   | Total:  1h 26m | Avg: 14m 27s | Max: 27m 01s | Hits:  75%/22306 
  🟩 GCC7               Pass: 100%/2   | Total:  8m 39s | Avg:  4m 19s | Max:  4m 41s | Hits:  99%/7357  
  🟩 GCC8               Pass: 100%/1   | Total:  4m 59s | Avg:  4m 59s | Max:  4m 59s | Hits:  99%/3689  
  🟩 GCC9               Pass: 100%/2   | Total:  9m 17s | Avg:  4m 38s | Max:  5m 02s | Hits:  99%/7369  
  🟩 GCC10              Pass: 100%/2   | Total: 39m 20s | Avg: 19m 40s | Max: 34m 17s | Hits:  68%/7423  
  🟩 GCC11              Pass: 100%/2   | Total:  9m 37s | Avg:  4m 48s | Max:  4m 49s | Hits:  99%/7419  
  🟩 GCC12              Pass: 100%/2   | Total: 10m 20s | Avg:  5m 10s | Max:  5m 16s | Hits:  99%/7423  
  🔍 GCC13              Pass:  90%/11  | Total:  1h 59m | Avg: 10m 50s | Max: 22m 56s | Hits:  99%/30162 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 00m | Avg: 30m 07s | Max: 30m 42s | Hits:  99%/7093  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  2h 02m | Avg: 30m 34s | Max: 31m 42s | Hits:  99%/14669 
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 21m 23s | Avg: 10m 41s | Max: 10m 55s | Hits:  98%/7407  
🔍 cxx_family: GCC 🔍
  🟩 Clang              Pass: 100%/18  | Total:  2h 25m | Avg:  8m 06s | Max: 27m 01s | Hits:  91%/66796 
  🔍 GCC                Pass:  95%/22  | Total:  3h 21m | Avg:  9m 09s | Max: 34m 17s | Hits:  96%/70842 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 02m | Avg: 30m 25s | Max: 31m 42s | Hits:  99%/21762 
  🟩 NVHPC              Pass: 100%/2   | Total: 21m 23s | Avg: 10m 41s | Max: 10m 55s | Hits:  98%/7407  
🔍 gpu: rtx2080 🔍
  🟩 h100               Pass: 100%/2   | Total: 27m 50s | Avg: 13m 55s | Max: 22m 56s | Hits:  99%/7628  
  🔍 rtx2080            Pass:  97%/46  | Total:  8h 43m | Avg: 11m 22s | Max: 34m 17s | Hits:  94%/159179
🔍 jobs: NVRTC 🔍
  🟩 Build              Pass: 100%/42  | Total:  7h 23m | Avg: 10m 33s | Max: 34m 17s | Hits:  94%/155511
  🔍 NVRTC              Pass:  50%/2   | Total: 42m 52s | Avg: 21m 26s | Max: 22m 09s | Hits:  90%/21    
  🟩 Test               Pass: 100%/3   | Total:  1h 03m | Avg: 21m 04s | Max: 22m 56s | Hits:  99%/11275 
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 52s | Avg:  1m 52s | Max:  1m 52s
🔍 sm: 75 🔍
  🔍 75                 Pass:  50%/2   | Total: 42m 52s | Avg: 21m 26s | Max: 22m 09s | Hits:  90%/21    
  🟩 90                 Pass: 100%/2   | Total: 27m 50s | Avg: 13m 55s | Max: 22m 56s | Hits:  99%/7628  
  🟩 90;90a             Pass: 100%/2   | Total: 33m 44s | Avg: 16m 52s | Max: 28m 17s | Hits:  99%/7575  
  🟩 100;120            Pass: 100%/2   | Total: 36m 03s | Avg: 18m 01s | Max: 31m 07s | Hits:  99%/7575  
🔍 std: 17 🔍
  🔍 17                 Pass:  95%/22  | Total:  3h 47m | Avg: 10m 21s | Max: 31m 11s | Hits:  96%/77024 
  🟩 20                 Pass: 100%/25  | Total:  5h 21m | Avg: 12m 51s | Max: 34m 17s | Hits:  93%/89783

🟩 cub: Pass: 100%/50 | Total: 12h 26m | Avg: 14m 55s | Max: 39m 22s | Hits: 99%/61706

🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total: 12h 12m | Avg: 15m 15s | Max: 39m 22s | Hits:  99%/59190 
  🟩 arm64              Pass: 100%/2   | Total: 14m 35s | Avg:  7m 17s | Max:  8m 33s | Hits:  99%/2516  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total:  1h 00m | Avg: 12m 11s | Max: 32m 09s | Hits:  99%/6186  
  🟩 12.9               Pass: 100%/45  | Total: 11h 25m | Avg: 15m 14s | Max: 39m 22s | Hits:  99%/55520 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 35s | Avg:  5m 17s | Max:  5m 18s | Hits:  99%/2165  
  🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 00m | Avg: 12m 11s | Max: 32m 09s | Hits:  99%/6186  
  🟩 nvcc12.9           Pass: 100%/43  | Total: 11h 15m | Avg: 15m 41s | Max: 39m 22s | Hits:  99%/53355 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 35s | Avg:  5m 17s | Max:  5m 18s | Hits:  99%/2165  
  🟩 nvcc               Pass: 100%/48  | Total: 12h 16m | Avg: 15m 20s | Max: 39m 22s | Hits:  99%/59541 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 26m 31s | Avg:  6m 37s | Max:  6m 59s | Hits:  99%/5034  
  🟩 Clang15            Pass: 100%/2   | Total: 14m 01s | Avg:  7m 00s | Max:  7m 01s | Hits:  99%/2513  
  🟩 Clang16            Pass: 100%/2   | Total: 13m 34s | Avg:  6m 47s | Max:  6m 55s | Hits:  99%/2513  
  🟩 Clang17            Pass: 100%/2   | Total: 14m 17s | Avg:  7m 08s | Max:  7m 21s | Hits:  99%/2513  
  🟩 Clang18            Pass: 100%/2   | Total: 13m 23s | Avg:  6m 41s | Max:  6m 45s | Hits:  99%/2513  
  🟩 Clang19            Pass: 100%/7   | Total:  1h 34m | Avg: 13m 31s | Max: 32m 06s | Hits:  99%/8449  
  🟩 GCC7               Pass: 100%/2   | Total: 16m 28s | Avg:  8m 14s | Max:  8m 27s | Hits:  99%/2516  
  🟩 GCC8               Pass: 100%/1   | Total:  8m 30s | Avg:  8m 30s | Max:  8m 30s | Hits:  99%/1258  
  🟩 GCC9               Pass: 100%/2   | Total: 17m 11s | Avg:  8m 35s | Max:  8m 56s | Hits:  99%/2516  
  🟩 GCC10              Pass: 100%/2   | Total: 17m 44s | Avg:  8m 52s | Max:  9m 02s | Hits:  99%/2517  
  🟩 GCC11              Pass: 100%/2   | Total: 17m 37s | Avg:  8m 48s | Max:  8m 56s | Hits:  99%/2513  
  🟩 GCC12              Pass: 100%/2   | Total: 19m 42s | Avg:  9m 51s | Max:  9m 55s | Hits:  99%/2513  
  🟩 GCC13              Pass: 100%/12  | Total:  4h 25m | Avg: 22m 08s | Max: 39m 22s | Hits:  99%/15105 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 01m | Avg: 30m 51s | Max: 32m 09s | Hits:  99%/2306  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  1h 59m | Avg: 29m 51s | Max: 33m 28s | Hits:  99%/4612  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 26m 08s | Avg: 13m 04s | Max: 13m 19s | Hits:  98%/2315  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  2h 56m | Avg:  9m 17s | Max: 32m 06s | Hits:  99%/23535 
  🟩 GCC                Pass: 100%/23  | Total:  6h 02m | Avg: 15m 46s | Max: 39m 22s | Hits:  99%/28938 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 01m | Avg: 30m 11s | Max: 33m 28s | Hits:  99%/6918  
  🟩 NVHPC              Pass: 100%/2   | Total: 26m 08s | Avg: 13m 04s | Max: 13m 19s | Hits:  98%/2315  
🟩 gpu
  🟩 h100               Pass: 100%/3   | Total:  1h 16m | Avg: 25m 37s | Max: 36m 05s | Hits:  99%/3777  
  🟩 rtx2080            Pass: 100%/39  | Total:  7h 23m | Avg: 11m 22s | Max: 33m 28s | Hits:  99%/47863 
  🟩 rtxa6000           Pass: 100%/8   | Total:  3h 46m | Avg: 28m 16s | Max: 39m 22s | Hits:  99%/10066 
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  7h 46m | Avg: 11m 06s | Max: 33m 28s | Hits:  99%/51638 
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 38m 47s | Avg: 38m 47s | Max: 38m 47s | Hits:  99%/1259  
  🟩 GraphCapture       Pass: 100%/1   | Total: 30m 49s | Avg: 30m 49s | Max: 30m 49s | Hits:  99%/1259  
  🟩 HostLaunch         Pass: 100%/3   | Total:  1h 47m | Avg: 35m 49s | Max: 39m 22s | Hits:  99%/3775  
  🟩 TestGPU            Pass: 100%/3   | Total:  1h 43m | Avg: 34m 20s | Max: 36m 34s | Hits:  99%/3775  
🟩 sm
  🟩 90                 Pass: 100%/3   | Total:  1h 16m | Avg: 25m 37s | Max: 36m 05s | Hits:  99%/3777  
  🟩 90;90a             Pass: 100%/2   | Total: 34m 31s | Avg: 17m 15s | Max: 26m 45s | Hits:  99%/2412  
  🟩 100;120            Pass: 100%/2   | Total: 35m 18s | Avg: 17m 39s | Max: 27m 07s | Hits:  99%/2412  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  4h 01m | Avg: 11m 29s | Max: 33m 28s | Hits:  99%/25810 
  🟩 20                 Pass: 100%/29  | Total:  8h 25m | Avg: 17m 25s | Max: 39m 22s | Hits:  99%/35896

🟩 thrust: Pass: 100%/50 | Total: 9h 20m | Avg: 11m 12s | Max: 37m 02s | Hits: 99%/95621

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 21m 12s | Avg: 10m 36s | Max: 13m 15s | Hits:  99%/3828  
🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total:  9h 08m | Avg: 11m 25s | Max: 37m 02s | Hits:  99%/91794 
  🟩 arm64              Pass: 100%/2   | Total: 12m 06s | Avg:  6m 03s | Max:  6m 56s | Hits:  99%/3827  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 52m 47s | Avg: 10m 33s | Max: 28m 13s | Hits:  99%/9560  
  🟩 12.9               Pass: 100%/45  | Total:  8h 27m | Avg: 11m 17s | Max: 37m 02s | Hits:  99%/86061 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 11m 25s | Avg:  5m 42s | Max:  5m 51s | Hits: 100%/3826  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 52m 47s | Avg: 10m 33s | Max: 28m 13s | Hits:  99%/9560  
  🟩 nvcc12.9           Pass: 100%/43  | Total:  8h 16m | Avg: 11m 32s | Max: 37m 02s | Hits:  99%/82235 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 11m 25s | Avg:  5m 42s | Max:  5m 51s | Hits: 100%/3826  
  🟩 nvcc               Pass: 100%/48  | Total:  9h 09m | Avg: 11m 26s | Max: 37m 02s | Hits:  99%/91795 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 22m 29s | Avg:  5m 37s | Max:  6m 08s | Hits: 100%/7652  
  🟩 Clang15            Pass: 100%/2   | Total: 11m 45s | Avg:  5m 52s | Max:  5m 54s | Hits: 100%/3826  
  🟩 Clang16            Pass: 100%/2   | Total: 12m 13s | Avg:  6m 06s | Max:  6m 23s | Hits: 100%/3826  
  🟩 Clang17            Pass: 100%/2   | Total: 11m 42s | Avg:  5m 51s | Max:  5m 58s | Hits: 100%/3826  
  🟩 Clang18            Pass: 100%/2   | Total: 11m 40s | Avg:  5m 50s | Max:  6m 02s | Hits: 100%/3826  
  🟩 Clang19            Pass: 100%/7   | Total: 47m 00s | Avg:  6m 42s | Max: 10m 02s | Hits: 100%/13391 
  🟩 GCC7               Pass: 100%/2   | Total: 14m 15s | Avg:  7m 07s | Max:  7m 12s | Hits:  99%/3828  
  🟩 GCC8               Pass: 100%/1   | Total:  7m 01s | Avg:  7m 01s | Max:  7m 01s | Hits:  99%/1914  
  🟩 GCC9               Pass: 100%/2   | Total: 14m 16s | Avg:  7m 08s | Max:  7m 17s | Hits:  99%/3828  
  🟩 GCC10              Pass: 100%/2   | Total: 15m 34s | Avg:  7m 47s | Max:  8m 17s | Hits:  99%/3828  
  🟩 GCC11              Pass: 100%/2   | Total: 16m 45s | Avg:  8m 22s | Max:  9m 11s | Hits:  99%/3828  
  🟩 GCC12              Pass: 100%/2   | Total: 15m 55s | Avg:  7m 57s | Max:  8m 04s | Hits:  99%/3828  
  🟩 GCC13              Pass: 100%/11  | Total:  1h 41m | Avg:  9m 12s | Max: 15m 07s | Hits:  99%/21054 
  🟩 MSVC14.29          Pass: 100%/2   | Total: 55m 50s | Avg: 27m 55s | Max: 28m 13s | Hits:  99%/3812  
  🟩 MSVC14.43          Pass: 100%/5   | Total:  2h 27m | Avg: 29m 31s | Max: 37m 02s | Hits:  99%/9530  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 55m 24s | Avg: 27m 42s | Max: 28m 21s | Hits:  99%/3824  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  1h 56m | Avg:  6m 08s | Max: 10m 02s | Hits: 100%/36347 
  🟩 GCC                Pass: 100%/22  | Total:  3h 05m | Avg:  8m 24s | Max: 15m 07s | Hits:  99%/42108 
  🟩 MSVC               Pass: 100%/7   | Total:  3h 23m | Avg: 29m 04s | Max: 37m 02s | Hits:  99%/13342 
  🟩 NVHPC              Pass: 100%/2   | Total: 55m 24s | Avg: 27m 42s | Max: 28m 21s | Hits:  99%/3824  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 20m 53s | Avg: 10m 26s | Max: 15m 07s | Hits:  99%/3828  
  🟩 rtx2080            Pass: 100%/38  | Total:  6h 37m | Avg: 10m 28s | Max: 32m 11s | Hits:  99%/72672 
  🟩 rtx4090            Pass: 100%/10  | Total:  2h 22m | Avg: 14m 12s | Max: 37m 02s | Hits:  99%/19121 
🟩 jobs
  🟩 Build              Pass: 100%/43  | Total:  7h 34m | Avg: 10m 34s | Max: 32m 11s | Hits:  99%/82233 
  🟩 TestCPU            Pass: 100%/3   | Total: 54m 40s | Avg: 18m 13s | Max: 37m 02s | Hits:  99%/5733  
  🟩 TestGPU            Pass: 100%/4   | Total: 51m 33s | Avg: 12m 53s | Max: 15m 07s | Hits:  99%/7655  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 20m 53s | Avg: 10m 26s | Max: 15m 07s | Hits:  99%/3828  
  🟩 90;90a             Pass: 100%/2   | Total: 31m 24s | Avg: 15m 42s | Max: 24m 29s | Hits:  99%/3820  
  🟩 100;120            Pass: 100%/2   | Total: 32m 04s | Avg: 16m 02s | Max: 25m 02s | Hits:  99%/3820  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  3h 52m | Avg: 11m 03s | Max: 32m 11s | Hits:  99%/40160 
  🟩 20                 Pass: 100%/27  | Total:  5h 07m | Avg: 11m 22s | Max: 37m 02s | Hits:  99%/51633

🟩 cudax: Pass: 100%/28 | Total: 5h 17m | Avg: 11m 20s | Max: 21m 47s | Hits: 85%/15906

🟩 cpu
  🟩 amd64              Pass: 100%/24  | Total:  4h 37m | Avg: 11m 34s | Max: 21m 47s | Hits:  85%/13462 
  🟩 arm64              Pass: 100%/4   | Total: 39m 49s | Avg:  9m 57s | Max: 11m 11s | Hits:  82%/2444  
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 31m 04s | Avg: 10m 21s | Max: 11m 21s | Hits:  85%/1531  
  🟩 12.9               Pass: 100%/25  | Total:  4h 46m | Avg: 11m 27s | Max: 21m 47s | Hits:  85%/14375 
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 31m 04s | Avg: 10m 21s | Max: 11m 21s | Hits:  85%/1531  
  🟩 nvcc12.9           Pass: 100%/25  | Total:  4h 46m | Avg: 11m 27s | Max: 21m 47s | Hits:  85%/14375 
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/28  | Total:  5h 17m | Avg: 11m 20s | Max: 21m 47s | Hits:  85%/15906 
🟩 cxx
  🟩 Clang14            Pass: 100%/2   | Total: 18m 49s | Avg:  9m 24s | Max:  9m 33s | Hits:  82%/1224  
  🟩 Clang15            Pass: 100%/1   | Total: 10m 25s | Avg: 10m 25s | Max: 10m 25s | Hits:  82%/611   
  🟩 Clang16            Pass: 100%/1   | Total: 10m 59s | Avg: 10m 59s | Max: 10m 59s | Hits:  82%/611   
  🟩 Clang17            Pass: 100%/1   | Total: 10m 43s | Avg: 10m 43s | Max: 10m 43s | Hits:  82%/611   
  🟩 Clang18            Pass: 100%/1   | Total: 10m 42s | Avg: 10m 42s | Max: 10m 42s | Hits:  82%/611   
  🟩 Clang19            Pass: 100%/4   | Total: 38m 06s | Avg:  9m 31s | Max: 10m 34s | Hits:  87%/2444  
  🟩 GCC10              Pass: 100%/2   | Total: 22m 24s | Avg: 11m 12s | Max: 11m 57s | Hits:  82%/1224  
  🟩 GCC11              Pass: 100%/1   | Total: 11m 04s | Avg: 11m 04s | Max: 11m 04s | Hits:  82%/611   
  🟩 GCC12              Pass: 100%/1   | Total: 12m 00s | Avg: 12m 00s | Max: 12m 00s | Hits:  82%/611   
  🟩 GCC13              Pass: 100%/8   | Total:  1h 23m | Avg: 10m 29s | Max: 12m 26s | Hits:  86%/4888  
  🟩 MSVC14.39          Pass: 100%/1   | Total: 11m 21s | Avg: 11m 21s | Max: 11m 21s | Hits:  95%/309   
  🟩 MSVC14.43          Pass: 100%/3   | Total: 35m 23s | Avg: 11m 47s | Max: 12m 29s | Hits:  96%/933   
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 41m 43s | Avg: 20m 51s | Max: 21m 47s | Hits:  80%/1218  
🟩 cxx_family
  🟩 Clang              Pass: 100%/10  | Total:  1h 39m | Avg:  9m 58s | Max: 10m 59s | Hits:  84%/6112  
  🟩 GCC                Pass: 100%/12  | Total:  2h 09m | Avg: 10m 47s | Max: 12m 26s | Hits:  85%/7334  
  🟩 MSVC               Pass: 100%/4   | Total: 46m 44s | Avg: 11m 41s | Max: 12m 29s | Hits:  95%/1242  
  🟩 NVHPC              Pass: 100%/2   | Total: 41m 43s | Avg: 20m 51s | Max: 21m 47s | Hits:  80%/1218  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 18m 17s | Avg:  9m 08s | Max:  9m 11s | Hits:  91%/1222  
  🟩 rtx2080            Pass: 100%/26  | Total:  4h 59m | Avg: 11m 30s | Max: 21m 47s | Hits:  85%/14684 
🟩 jobs
  🟩 Build              Pass: 100%/25  | Total:  4h 48m | Avg: 11m 32s | Max: 21m 47s | Hits:  83%/14073 
  🟩 Test               Pass: 100%/3   | Total: 29m 14s | Avg:  9m 44s | Max: 10m 59s | Hits:  99%/1833  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 18m 17s | Avg:  9m 08s | Max:  9m 11s | Hits:  91%/1222  
  🟩 90;90a             Pass: 100%/2   | Total: 21m 27s | Avg: 10m 43s | Max: 10m 47s | Hits:  87%/922   
  🟩 100;120            Pass: 100%/2   | Total: 22m 21s | Avg: 11m 10s | Max: 12m 07s | Hits:  86%/922   
🟩 std
  🟩 17                 Pass: 100%/3   | Total: 39m 02s | Avg: 13m 00s | Max: 19m 56s | Hits:  81%/1831  
  🟩 20                 Pass: 100%/25  | Total:  4h 38m | Avg: 11m 08s | Max: 21m 47s | Hits:  85%/14075

🟩 packaging: Pass: 100%/4 | Total: 14m 55s | Avg: 3m 43s | Max: 4m 02s

🟩 cpu
  🟩 amd64              Pass: 100%/4   | Total: 14m 55s | Avg:  3m 43s | Max:  4m 02s
🟩 ctk
  🟩 12.0               Pass: 100%/2   | Total:  7m 27s | Avg:  3m 43s | Max:  3m 51s
  🟩 12.9               Pass: 100%/2   | Total:  7m 28s | Avg:  3m 44s | Max:  4m 02s
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/2   | Total:  7m 27s | Avg:  3m 43s | Max:  3m 51s
  🟩 nvcc12.9           Pass: 100%/2   | Total:  7m 28s | Avg:  3m 44s | Max:  4m 02s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 14m 55s | Avg:  3m 43s | Max:  4m 02s
🟩 cxx
  🟩 Clang14            Pass: 100%/1   | Total:  3m 51s | Avg:  3m 51s | Max:  3m 51s
  🟩 Clang19            Pass: 100%/1   | Total:  4m 02s | Avg:  4m 02s | Max:  4m 02s
  🟩 GCC12              Pass: 100%/1   | Total:  3m 36s | Avg:  3m 36s | Max:  3m 36s
  🟩 GCC13              Pass: 100%/1   | Total:  3m 26s | Avg:  3m 26s | Max:  3m 26s
🟩 cxx_family
  🟩 Clang              Pass: 100%/2   | Total:  7m 53s | Avg:  3m 56s | Max:  4m 02s
  🟩 GCC                Pass: 100%/2   | Total:  7m 02s | Avg:  3m 31s | Max:  3m 36s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 14m 55s | Avg:  3m 43s | Max:  4m 02s
🟩 jobs
  🟩 Test               Pass: 100%/4   | Total: 14m 55s | Avg:  3m 43s | Max:  4m 02s

🟩 stdpar: Pass: 100%/4 | Total: 16m 14s | Avg: 4m 03s | Max: 4m 24s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total:  8m 40s | Avg:  4m 20s | Max:  4m 24s
  🟩 arm64              Pass: 100%/2   | Total:  7m 34s | Avg:  3m 47s | Max:  3m 53s
🟩 ctk
  🟩 12.9               Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 cxx
  🟩 NVHPC25.5          Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 cxx_family
  🟩 NVHPC              Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 jobs
  🟩 Build              Pass: 100%/4   | Total: 16m 14s | Avg:  4m 03s | Max:  4m 24s
🟩 std
  🟩 17                 Pass: 100%/2   | Total:  7m 57s | Avg:  3m 58s | Max:  4m 16s
  🟩 20                 Pass: 100%/2   | Total:  8m 17s | Avg:  4m 08s | Max:  4m 24s

🟩 cccl_c_parallel: Pass: 100%/3 | Total: 28m 11s | Avg: 9m 23s | Max: 15m 03s | Hits: 98%/507

🟩 cpu
  🟩 amd64              Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 ctk
  🟩 12.9               Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 cxx
  🟩 GCC13              Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 cxx_family
  🟩 GCC                Pass: 100%/3   | Total: 28m 11s | Avg:  9m 23s | Max: 15m 03s | Hits:  98%/507   
🟩 gpu
  🟩 h100               Pass: 100%/1   | Total: 15m 03s | Avg: 15m 03s | Max: 15m 03s | Hits:  98%/169   
  🟩 rtx2080            Pass: 100%/2   | Total: 13m 08s | Avg:  6m 34s | Max: 10m 25s | Hits:  97%/338   
🟩 jobs
  🟩 Build              Pass: 100%/1   | Total:  2m 43s | Avg:  2m 43s | Max:  2m 43s | Hits:  96%/169   
  🟩 Test               Pass: 100%/2   | Total: 25m 28s | Avg: 12m 44s | Max: 15m 03s | Hits:  98%/338

👃 Inspect Changes

Modifications in project?

	Project
+/-	CCCL Infrastructure
	CCCL Packaging
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

Modifications in project or dependencies?

	Project
+/-	CCCL Infrastructure
+/-	CCCL Packaging
+/-	libcu++
+/-	CUB
+/-	Thrust
+/-	CUDA Experimental
+/-	stdpar
+/-	python
+/-	CCCL C Parallel Library
+/-	Catch2Helper

🏃‍ Runner counts (total jobs: 205)

#	Runner
128	`linux-amd64-cpu16`
23	`windows-amd64-cpu16`
14	`linux-amd64-gpu-h100-latest-1`
14	`linux-amd64-gpu-rtxa6000-latest-1`
12	`linux-arm64-cpu16`
11	`linux-amd64-gpu-rtx2080-latest-1`
3	`linux-amd64-gpu-rtx4090-latest-1`

caugonnet · 2025-07-20T08:05:16Z

Rebased on #5319 (low level cuda_kernel API) and #5215 (CUfunction support in cuda_kernel)

caugonnet · 2025-07-20T08:05:36Z

/ok to test f3b57da

github-actions · 2025-07-20T09:13:36Z

🟨 CI finished in 1h 05m: Pass: 89%/205 | Total: 1d 13h | Avg: 10m 53s | Max: 40m 23s | Hits: 95%/340359

🟥 python: Pass: 0%/18 | Total: 18m 25s | Avg: 1m 01s | Max: 9m 21s

🟥 cpu
  🟥 amd64              Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 ctk
  🟥 12.9               Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 cxx
  🟥 GCC13              Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 cxx_family
  🟥 GCC                Pass:   0%/18  | Total: 18m 25s | Avg:  1m 01s | Max:  9m 21s
🟥 gpu
  🟥 h100               Pass:   0%/8  
  🟥 rtxa6000           Pass:   0%/10  | Total: 18m 25s | Avg:  1m 50s | Max:  9m 21s
🟥 jobs
  🟥 Build cuda.cccl    Pass:   0%/2   | Total: 18m 25s | Avg:  9m 12s | Max:  9m 21s
  🟥 Test cuda.cccl.cooperative Pass:   0%/4  
  🟥 Test cuda.cccl.examples Pass:   0%/4  
  🟥 Test cuda.cccl.headers Pass:   0%/4  
  🟥 Test cuda.cccl.parallel Pass:   0%/4  
🟥 py_version
  🟥 3.10               Pass:   0%/9   | Total:  9m 04s | Avg:  1m 00s | Max:  9m 04s
  🟥 3.13               Pass:   0%/9   | Total:  9m 21s | Avg:  1m 02s | Max:  9m 21s

🟥 cccl_c_parallel: Pass: 0%/3 | Total: 2m 07s | Avg: 0m 42s | Max: 2m 07s

🟥 cpu
  🟥 amd64              Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 ctk
  🟥 12.9               Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 cxx
  🟥 GCC13              Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 cxx_family
  🟥 GCC                Pass:   0%/3   | Total:  2m 07s | Avg:  0m 42s | Max:  2m 07s
🟥 gpu
  🟥 h100               Pass:   0%/1  
  🟥 rtx2080            Pass:   0%/2   | Total:  2m 07s | Avg:  1m 03s | Max:  2m 07s
🟥 jobs
  🟥 Build              Pass:   0%/1   | Total:  2m 07s | Avg:  2m 07s | Max:  2m 07s
  🟥 Test               Pass:   0%/2

🟩 cub: Pass: 100%/50 | Total: 12h 16m | Avg: 14m 43s | Max: 40m 23s | Hits: 99%/61956

🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total: 12h 01m | Avg: 15m 02s | Max: 40m 23s | Hits:  99%/59430 
  🟩 arm64              Pass: 100%/2   | Total: 14m 32s | Avg:  7m 16s | Max:  8m 27s | Hits:  99%/2526  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 58m 55s | Avg: 11m 47s | Max: 30m 19s | Hits:  99%/6211  
  🟩 12.9               Pass: 100%/45  | Total: 11h 17m | Avg: 15m 03s | Max: 40m 23s | Hits:  99%/55745 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 46s | Avg:  5m 23s | Max:  5m 24s | Hits:  99%/2175  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 58m 55s | Avg: 11m 47s | Max: 30m 19s | Hits:  99%/6211  
  🟩 nvcc12.9           Pass: 100%/43  | Total: 11h 06m | Avg: 15m 30s | Max: 40m 23s | Hits:  99%/53570 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 46s | Avg:  5m 23s | Max:  5m 24s | Hits:  99%/2175  
  🟩 nvcc               Pass: 100%/48  | Total: 12h 05m | Avg: 15m 07s | Max: 40m 23s | Hits:  99%/59781 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 26m 14s | Avg:  6m 33s | Max:  6m 59s | Hits:  99%/5054  
  🟩 Clang15            Pass: 100%/2   | Total: 14m 11s | Avg:  7m 05s | Max:  7m 21s | Hits:  99%/2523  
  🟩 Clang16            Pass: 100%/2   | Total: 13m 53s | Avg:  6m 56s | Max:  7m 01s | Hits:  99%/2523  
  🟩 Clang17            Pass: 100%/2   | Total: 13m 42s | Avg:  6m 51s | Max:  6m 55s | Hits:  99%/2523  
  🟩 Clang18            Pass: 100%/2   | Total: 13m 17s | Avg:  6m 38s | Max:  6m 41s | Hits:  99%/2523  
  🟩 Clang19            Pass: 100%/7   | Total:  1h 34m | Avg: 13m 33s | Max: 32m 28s | Hits:  99%/8484  
  🟩 GCC7               Pass: 100%/2   | Total: 16m 18s | Avg:  8m 09s | Max:  8m 26s | Hits:  99%/2526  
  🟩 GCC8               Pass: 100%/1   | Total:  8m 22s | Avg:  8m 22s | Max:  8m 22s | Hits:  99%/1263  
  🟩 GCC9               Pass: 100%/2   | Total: 17m 05s | Avg:  8m 32s | Max:  8m 44s | Hits:  99%/2526  
  🟩 GCC10              Pass: 100%/2   | Total: 18m 28s | Avg:  9m 14s | Max:  9m 27s | Hits:  99%/2527  
  🟩 GCC11              Pass: 100%/2   | Total: 18m 04s | Avg:  9m 02s | Max:  9m 15s | Hits:  99%/2523  
  🟩 GCC12              Pass: 100%/2   | Total: 18m 03s | Avg:  9m 01s | Max:  9m 15s | Hits:  99%/2523  
  🟩 GCC13              Pass: 100%/12  | Total:  4h 21m | Avg: 21m 47s | Max: 40m 23s | Hits:  99%/15165 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 00m | Avg: 30m 26s | Max: 30m 33s | Hits:  99%/2316  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  1h 56m | Avg: 29m 06s | Max: 31m 48s | Hits:  99%/4632  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 25m 18s | Avg: 12m 39s | Max: 12m 49s | Hits:  98%/2325  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  2h 56m | Avg:  9m 16s | Max: 32m 28s | Hits:  99%/23630 
  🟩 GCC                Pass: 100%/23  | Total:  5h 57m | Avg: 15m 33s | Max: 40m 23s | Hits:  99%/29053 
  🟩 MSVC               Pass: 100%/6   | Total:  2h 57m | Avg: 29m 32s | Max: 31m 48s | Hits:  99%/6948  
  🟩 NVHPC              Pass: 100%/2   | Total: 25m 18s | Avg: 12m 39s | Max: 12m 49s | Hits:  98%/2325  
🟩 gpu
  🟩 h100               Pass: 100%/3   | Total:  1h 11m | Avg: 23m 46s | Max: 34m 12s | Hits:  99%/3792  
  🟩 rtx2080            Pass: 100%/39  | Total:  7h 17m | Avg: 11m 12s | Max: 31m 48s | Hits:  99%/48058 
  🟩 rtxa6000           Pass: 100%/8   | Total:  3h 47m | Avg: 28m 28s | Max: 40m 23s | Hits:  99%/10106 
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  7h 40m | Avg: 10m 57s | Max: 31m 48s | Hits:  99%/51848 
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 38m 59s | Avg: 38m 59s | Max: 38m 59s | Hits:  99%/1264  
  🟩 GraphCapture       Pass: 100%/1   | Total: 31m 11s | Avg: 31m 11s | Max: 31m 11s | Hits:  99%/1264  
  🟩 HostLaunch         Pass: 100%/3   | Total:  1h 43m | Avg: 34m 25s | Max: 40m 23s | Hits:  99%/3790  
  🟩 TestGPU            Pass: 100%/3   | Total:  1h 43m | Avg: 34m 20s | Max: 36m 38s | Hits:  99%/3790  
🟩 sm
  🟩 90                 Pass: 100%/3   | Total:  1h 11m | Avg: 23m 46s | Max: 34m 12s | Hits:  99%/3792  
  🟩 90;90a             Pass: 100%/2   | Total: 34m 23s | Avg: 17m 11s | Max: 26m 41s | Hits:  99%/2422  
  🟩 100;120            Pass: 100%/2   | Total: 34m 33s | Avg: 17m 16s | Max: 26m 14s | Hits:  99%/2422  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  3h 56m | Avg: 11m 14s | Max: 31m 48s | Hits:  99%/25915 
  🟩 20                 Pass: 100%/29  | Total:  8h 20m | Avg: 17m 15s | Max: 40m 23s | Hits:  99%/36041

🟩 thrust: Pass: 100%/50 | Total: 9h 24m | Avg: 11m 17s | Max: 35m 03s | Hits: 99%/95621

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 21m 15s | Avg: 10m 37s | Max: 13m 16s | Hits:  99%/3828  
🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total:  9h 12m | Avg: 11m 30s | Max: 35m 03s | Hits:  99%/91794 
  🟩 arm64              Pass: 100%/2   | Total: 12m 03s | Avg:  6m 01s | Max:  6m 53s | Hits:  99%/3827  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 51m 30s | Avg: 10m 18s | Max: 27m 23s | Hits:  99%/9560  
  🟩 12.9               Pass: 100%/45  | Total:  8h 32m | Avg: 11m 23s | Max: 35m 03s | Hits:  99%/86061 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 46s | Avg:  5m 23s | Max:  5m 32s | Hits: 100%/3826  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 51m 30s | Avg: 10m 18s | Max: 27m 23s | Hits:  99%/9560  
  🟩 nvcc12.9           Pass: 100%/43  | Total:  8h 22m | Avg: 11m 40s | Max: 35m 03s | Hits:  99%/82235 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 46s | Avg:  5m 23s | Max:  5m 32s | Hits: 100%/3826  
  🟩 nvcc               Pass: 100%/48  | Total:  9h 13m | Avg: 11m 31s | Max: 35m 03s | Hits:  99%/91795 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 23m 06s | Avg:  5m 46s | Max:  6m 39s | Hits: 100%/7652  
  🟩 Clang15            Pass: 100%/2   | Total: 11m 52s | Avg:  5m 56s | Max:  6m 09s | Hits: 100%/3826  
  🟩 Clang16            Pass: 100%/2   | Total: 12m 33s | Avg:  6m 16s | Max:  6m 24s | Hits: 100%/3826  
  🟩 Clang17            Pass: 100%/2   | Total: 11m 38s | Avg:  5m 49s | Max:  5m 51s | Hits: 100%/3826  
  🟩 Clang18            Pass: 100%/2   | Total: 11m 56s | Avg:  5m 58s | Max:  6m 05s | Hits: 100%/3826  
  🟩 Clang19            Pass: 100%/7   | Total: 45m 34s | Avg:  6m 30s | Max: 10m 03s | Hits: 100%/13391 
  🟩 GCC7               Pass: 100%/2   | Total: 13m 59s | Avg:  6m 59s | Max:  7m 27s | Hits:  99%/3828  
  🟩 GCC8               Pass: 100%/1   | Total:  7m 09s | Avg:  7m 09s | Max:  7m 09s | Hits:  99%/1914  
  🟩 GCC9               Pass: 100%/2   | Total: 14m 30s | Avg:  7m 15s | Max:  7m 28s | Hits:  99%/3828  
  🟩 GCC10              Pass: 100%/2   | Total: 14m 24s | Avg:  7m 12s | Max:  7m 19s | Hits:  99%/3828  
  🟩 GCC11              Pass: 100%/2   | Total: 15m 13s | Avg:  7m 36s | Max:  7m 50s | Hits:  99%/3828  
  🟩 GCC12              Pass: 100%/2   | Total: 15m 43s | Avg:  7m 51s | Max:  8m 05s | Hits:  99%/3828  
  🟩 GCC13              Pass: 100%/11  | Total:  1h 38m | Avg:  8m 55s | Max: 13m 27s | Hits:  99%/21054 
  🟩 MSVC14.29          Pass: 100%/2   | Total: 54m 40s | Avg: 27m 20s | Max: 27m 23s | Hits:  99%/3812  
  🟩 MSVC14.43          Pass: 100%/5   | Total:  2h 25m | Avg: 29m 11s | Max: 32m 45s | Hits:  99%/9530  
  🟩 NVHPC25.5          Pass: 100%/2   | Total:  1h 07m | Avg: 33m 57s | Max: 35m 03s | Hits:  99%/3824  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  1h 56m | Avg:  6m 08s | Max: 10m 03s | Hits: 100%/36347 
  🟩 GCC                Pass: 100%/22  | Total:  2h 59m | Avg:  8m 08s | Max: 13m 27s | Hits:  99%/42108 
  🟩 MSVC               Pass: 100%/7   | Total:  3h 20m | Avg: 28m 39s | Max: 32m 45s | Hits:  99%/13342 
  🟩 NVHPC              Pass: 100%/2   | Total:  1h 07m | Avg: 33m 57s | Max: 35m 03s | Hits:  99%/3824  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 18m 20s | Avg:  9m 10s | Max: 12m 20s | Hits:  99%/3828  
  🟩 rtx2080            Pass: 100%/38  | Total:  6h 48m | Avg: 10m 44s | Max: 35m 03s | Hits:  99%/72672 
  🟩 rtx4090            Pass: 100%/10  | Total:  2h 17m | Avg: 13m 46s | Max: 32m 45s | Hits:  99%/19121 
🟩 jobs
  🟩 Build              Pass: 100%/43  | Total:  7h 45m | Avg: 10m 49s | Max: 35m 03s | Hits:  99%/82233 
  🟩 TestCPU            Pass: 100%/3   | Total: 49m 59s | Avg: 16m 39s | Max: 32m 45s | Hits:  99%/5733  
  🟩 TestGPU            Pass: 100%/4   | Total: 49m 06s | Avg: 12m 16s | Max: 13m 27s | Hits:  99%/7655  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 18m 20s | Avg:  9m 10s | Max: 12m 20s | Hits:  99%/3828  
  🟩 90;90a             Pass: 100%/2   | Total: 31m 39s | Avg: 15m 49s | Max: 25m 02s | Hits:  99%/3820  
  🟩 100;120            Pass: 100%/2   | Total: 34m 02s | Avg: 17m 01s | Max: 27m 28s | Hits:  99%/3820  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  3h 54m | Avg: 11m 10s | Max: 35m 03s | Hits:  99%/40160 
  🟩 20                 Pass: 100%/27  | Total:  5h 08m | Avg: 11m 25s | Max: 32m 52s | Hits:  99%/51633

🟩 libcudacxx: Pass: 100%/48 | Total: 9h 19m | Avg: 11m 39s | Max: 34m 31s | Hits: 93%/166828

🟩 cpu
  🟩 amd64              Pass: 100%/46  | Total:  9h 02m | Avg: 11m 47s | Max: 34m 31s | Hits:  93%/159367
  🟩 arm64              Pass: 100%/2   | Total: 17m 18s | Avg:  8m 39s | Max: 12m 44s | Hits:  88%/7461  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 45m 26s | Avg:  9m 05s | Max: 28m 38s | Hits:  99%/18287 
  🟩 12.9               Pass: 100%/43  | Total:  8h 33m | Avg: 11m 57s | Max: 34m 31s | Hits:  92%/148541
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 57m 59s | Avg: 28m 59s | Max: 30m 44s | Hits:  29%/7425  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 45m 26s | Avg:  9m 05s | Max: 28m 38s | Hits:  99%/18287 
  🟩 nvcc12.9           Pass: 100%/41  | Total:  7h 35m | Avg: 11m 07s | Max: 34m 31s | Hits:  96%/141116
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 57m 59s | Avg: 28m 59s | Max: 30m 44s | Hits:  29%/7425  
  🟩 nvcc               Pass: 100%/46  | Total:  8h 21m | Avg: 10m 54s | Max: 34m 31s | Hits:  96%/159403
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 41m 54s | Avg: 10m 28s | Max: 28m 09s | Hits:  84%/14806 
  🟩 Clang15            Pass: 100%/2   | Total: 10m 08s | Avg:  5m 04s | Max:  5m 12s | Hits:  99%/7421  
  🟩 Clang16            Pass: 100%/2   | Total:  9m 58s | Avg:  4m 59s | Max:  5m 03s | Hits:  99%/7421  
  🟩 Clang17            Pass: 100%/2   | Total:  9m 43s | Avg:  4m 51s | Max:  4m 54s | Hits:  99%/7421  
  🟩 Clang18            Pass: 100%/2   | Total: 10m 15s | Avg:  5m 07s | Max:  5m 15s | Hits:  99%/7421  
  🟩 Clang19            Pass: 100%/6   | Total:  1h 33m | Avg: 15m 38s | Max: 30m 44s | Hits:  75%/22306 
  🟩 GCC7               Pass: 100%/2   | Total: 16m 12s | Avg:  8m 06s | Max: 12m 10s | Hits:  89%/7357  
  🟩 GCC8               Pass: 100%/1   | Total:  5m 04s | Avg:  5m 04s | Max:  5m 04s | Hits:  99%/3689  
  🟩 GCC9               Pass: 100%/2   | Total:  9m 31s | Avg:  4m 45s | Max:  5m 13s | Hits:  99%/7369  
  🟩 GCC10              Pass: 100%/2   | Total:  9m 49s | Avg:  4m 54s | Max:  5m 01s | Hits:  99%/7423  
  🟩 GCC11              Pass: 100%/2   | Total:  9m 36s | Avg:  4m 48s | Max:  4m 51s | Hits:  99%/7419  
  🟩 GCC12              Pass: 100%/2   | Total: 10m 33s | Avg:  5m 16s | Max:  5m 31s | Hits:  99%/7423  
  🟩 GCC13              Pass: 100%/11  | Total:  2h 02m | Avg: 11m 10s | Max: 23m 15s | Hits:  96%/30183 
  🟩 MSVC14.29          Pass: 100%/2   | Total: 58m 25s | Avg: 29m 12s | Max: 29m 47s | Hits:  88%/7093  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  2h 00m | Avg: 30m 00s | Max: 34m 31s | Hits:  99%/14669 
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 21m 28s | Avg: 10m 44s | Max: 10m 54s | Hits:  98%/7407  
🟩 cxx_family
  🟩 Clang              Pass: 100%/18  | Total:  2h 55m | Avg:  9m 46s | Max: 30m 44s | Hits:  88%/66796 
  🟩 GCC                Pass: 100%/22  | Total:  3h 03m | Avg:  8m 20s | Max: 23m 15s | Hits:  97%/70863 
  🟩 MSVC               Pass: 100%/6   | Total:  2h 58m | Avg: 29m 44s | Max: 34m 31s | Hits:  95%/21762 
  🟩 NVHPC              Pass: 100%/2   | Total: 21m 28s | Avg: 10m 44s | Max: 10m 54s | Hits:  98%/7407  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 22m 30s | Avg: 11m 15s | Max: 17m 49s | Hits:  99%/7628  
  🟩 rtx2080            Pass: 100%/46  | Total:  8h 56m | Avg: 11m 40s | Max: 34m 31s | Hits:  93%/159200
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  7h 34m | Avg: 10m 48s | Max: 34m 31s | Hits:  93%/155511
  🟩 NVRTC              Pass: 100%/2   | Total: 41m 11s | Avg: 20m 35s | Max: 21m 27s | Hits:  90%/42    
  🟩 Test               Pass: 100%/3   | Total:  1h 02m | Avg: 20m 45s | Max: 23m 15s | Hits:  99%/11275 
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s
🟩 sm
  🟩 75                 Pass: 100%/2   | Total: 41m 11s | Avg: 20m 35s | Max: 21m 27s | Hits:  90%/42    
  🟩 90                 Pass: 100%/2   | Total: 22m 30s | Avg: 11m 15s | Max: 17m 49s | Hits:  99%/7628  
  🟩 90;90a             Pass: 100%/2   | Total: 33m 08s | Avg: 16m 34s | Max: 27m 46s | Hits:  99%/7575  
  🟩 100;120            Pass: 100%/2   | Total: 32m 51s | Avg: 16m 25s | Max: 27m 32s | Hits:  99%/7575  
🟩 std
  🟩 17                 Pass: 100%/22  | Total:  4h 16m | Avg: 11m 38s | Max: 30m 11s | Hits:  91%/77045 
  🟩 20                 Pass: 100%/25  | Total:  5h 01m | Avg: 12m 03s | Max: 34m 31s | Hits:  95%/89783

🟩 cudax: Pass: 100%/28 | Total: 5h 20m | Avg: 11m 26s | Max: 21m 35s | Hits: 84%/15954

🟩 cpu
  🟩 amd64              Pass: 100%/24  | Total:  4h 39m | Avg: 11m 39s | Max: 21m 35s | Hits:  85%/13502 
  🟩 arm64              Pass: 100%/4   | Total: 40m 25s | Avg: 10m 06s | Max: 10m 55s | Hits:  82%/2452  
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 30m 31s | Avg: 10m 10s | Max: 11m 00s | Hits:  85%/1535  
  🟩 12.9               Pass: 100%/25  | Total:  4h 49m | Avg: 11m 35s | Max: 21m 35s | Hits:  84%/14419 
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 30m 31s | Avg: 10m 10s | Max: 11m 00s | Hits:  85%/1535  
  🟩 nvcc12.9           Pass: 100%/25  | Total:  4h 49m | Avg: 11m 35s | Max: 21m 35s | Hits:  84%/14419 
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/28  | Total:  5h 20m | Avg: 11m 26s | Max: 21m 35s | Hits:  84%/15954 
🟩 cxx
  🟩 Clang14            Pass: 100%/2   | Total: 20m 15s | Avg: 10m 07s | Max: 10m 45s | Hits:  82%/1228  
  🟩 Clang15            Pass: 100%/1   | Total: 10m 30s | Avg: 10m 30s | Max: 10m 30s | Hits:  82%/613   
  🟩 Clang16            Pass: 100%/1   | Total: 10m 53s | Avg: 10m 53s | Max: 10m 53s | Hits:  82%/613   
  🟩 Clang17            Pass: 100%/1   | Total: 11m 21s | Avg: 11m 21s | Max: 11m 21s | Hits:  82%/613   
  🟩 Clang18            Pass: 100%/1   | Total: 10m 33s | Avg: 10m 33s | Max: 10m 33s | Hits:  82%/613   
  🟩 Clang19            Pass: 100%/4   | Total: 38m 29s | Avg:  9m 37s | Max: 10m 36s | Hits:  86%/2452  
  🟩 GCC10              Pass: 100%/2   | Total: 20m 55s | Avg: 10m 27s | Max: 10m 54s | Hits:  82%/1228  
  🟩 GCC11              Pass: 100%/1   | Total: 11m 14s | Avg: 11m 14s | Max: 11m 14s | Hits:  82%/613   
  🟩 GCC12              Pass: 100%/1   | Total: 12m 30s | Avg: 12m 30s | Max: 12m 30s | Hits:  82%/613   
  🟩 GCC13              Pass: 100%/8   | Total:  1h 27m | Avg: 10m 55s | Max: 15m 43s | Hits:  85%/4904  
  🟩 MSVC14.39          Pass: 100%/1   | Total: 11m 00s | Avg: 11m 00s | Max: 11m 00s | Hits:  95%/309   
  🟩 MSVC14.43          Pass: 100%/3   | Total: 33m 54s | Avg: 11m 18s | Max: 12m 14s | Hits:  95%/933   
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 41m 22s | Avg: 20m 41s | Max: 21m 35s | Hits:  79%/1222  
🟩 cxx_family
  🟩 Clang              Pass: 100%/10  | Total:  1h 42m | Avg: 10m 12s | Max: 11m 21s | Hits:  84%/6132  
  🟩 GCC                Pass: 100%/12  | Total:  2h 12m | Avg: 11m 00s | Max: 15m 43s | Hits:  84%/7358  
  🟩 MSVC               Pass: 100%/4   | Total: 44m 54s | Avg: 11m 13s | Max: 12m 14s | Hits:  95%/1242  
  🟩 NVHPC              Pass: 100%/2   | Total: 41m 22s | Avg: 20m 41s | Max: 21m 35s | Hits:  79%/1222  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 15m 58s | Avg:  7m 59s | Max:  8m 40s | Hits:  90%/1226  
  🟩 rtx2080            Pass: 100%/26  | Total:  5h 04m | Avg: 11m 42s | Max: 21m 35s | Hits:  84%/14728 
🟩 jobs
  🟩 Build              Pass: 100%/25  | Total:  4h 48m | Avg: 11m 32s | Max: 21m 35s | Hits:  83%/14115 
  🟩 Test               Pass: 100%/3   | Total: 31m 41s | Avg: 10m 33s | Max: 15m 43s | Hits:  96%/1839  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 15m 58s | Avg:  7m 59s | Max:  8m 40s | Hits:  90%/1226  
  🟩 90;90a             Pass: 100%/2   | Total: 21m 13s | Avg: 10m 36s | Max: 11m 04s | Hits:  86%/924   
  🟩 100;120            Pass: 100%/2   | Total: 22m 02s | Avg: 11m 01s | Max: 11m 26s | Hits:  86%/924   
🟩 std
  🟩 17                 Pass: 100%/3   | Total: 39m 21s | Avg: 13m 07s | Max: 19m 47s | Hits:  81%/1837  
  🟩 20                 Pass: 100%/25  | Total:  4h 41m | Avg: 11m 14s | Max: 21m 35s | Hits:  85%/14117

🟩 packaging: Pass: 100%/4 | Total: 16m 23s | Avg: 4m 05s | Max: 4m 44s

🟩 cpu
  🟩 amd64              Pass: 100%/4   | Total: 16m 23s | Avg:  4m 05s | Max:  4m 44s
🟩 ctk
  🟩 12.0               Pass: 100%/2   | Total:  7m 50s | Avg:  3m 55s | Max:  4m 02s
  🟩 12.9               Pass: 100%/2   | Total:  8m 33s | Avg:  4m 16s | Max:  4m 44s
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/2   | Total:  7m 50s | Avg:  3m 55s | Max:  4m 02s
  🟩 nvcc12.9           Pass: 100%/2   | Total:  8m 33s | Avg:  4m 16s | Max:  4m 44s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 16m 23s | Avg:  4m 05s | Max:  4m 44s
🟩 cxx
  🟩 Clang14            Pass: 100%/1   | Total:  3m 48s | Avg:  3m 48s | Max:  3m 48s
  🟩 Clang19            Pass: 100%/1   | Total:  3m 49s | Avg:  3m 49s | Max:  3m 49s
  🟩 GCC12              Pass: 100%/1   | Total:  4m 02s | Avg:  4m 02s | Max:  4m 02s
  🟩 GCC13              Pass: 100%/1   | Total:  4m 44s | Avg:  4m 44s | Max:  4m 44s
🟩 cxx_family
  🟩 Clang              Pass: 100%/2   | Total:  7m 37s | Avg:  3m 48s | Max:  3m 49s
  🟩 GCC                Pass: 100%/2   | Total:  8m 46s | Avg:  4m 23s | Max:  4m 44s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 16m 23s | Avg:  4m 05s | Max:  4m 44s
🟩 jobs
  🟩 Test               Pass: 100%/4   | Total: 16m 23s | Avg:  4m 05s | Max:  4m 44s

🟩 stdpar: Pass: 100%/4 | Total: 15m 06s | Avg: 3m 46s | Max: 4m 01s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total:  7m 19s | Avg:  3m 39s | Max:  3m 43s
  🟩 arm64              Pass: 100%/2   | Total:  7m 47s | Avg:  3m 53s | Max:  4m 01s
🟩 ctk
  🟩 12.9               Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 cxx
  🟩 NVHPC25.5          Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 cxx_family
  🟩 NVHPC              Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 jobs
  🟩 Build              Pass: 100%/4   | Total: 15m 06s | Avg:  3m 46s | Max:  4m 01s
🟩 std
  🟩 17                 Pass: 100%/2   | Total:  7m 44s | Avg:  3m 52s | Max:  4m 01s
  🟩 20                 Pass: 100%/2   | Total:  7m 22s | Avg:  3m 41s | Max:  3m 46s

👃 Inspect Changes

Modifications in project?

	Project
+/-	CCCL Infrastructure
	CCCL Packaging
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

Modifications in project or dependencies?

	Project
+/-	CCCL Infrastructure
+/-	CCCL Packaging
+/-	libcu++
+/-	CUB
+/-	Thrust
+/-	CUDA Experimental
+/-	stdpar
+/-	python
+/-	CCCL C Parallel Library
+/-	Catch2Helper

🏃‍ Runner counts (total jobs: 205)

#	Runner
128	`linux-amd64-cpu16`
23	`windows-amd64-cpu16`
14	`linux-amd64-gpu-h100-latest-1`
14	`linux-amd64-gpu-rtxa6000-latest-1`
12	`linux-arm64-cpu16`
11	`linux-amd64-gpu-rtx2080-latest-1`
3	`linux-amd64-gpu-rtx4090-latest-1`

caugonnet · 2025-07-21T16:43:24Z

/ok to test 4fb7000

github-actions · 2025-07-21T18:27:52Z

🟨 CI finished in 1h 41m: Pass: 89%/205 | Total: 1d 12h | Avg: 10m 49s | Max: 45m 35s | Hits: 97%/340383

🟥 python: Pass: 0%/18 | Total: 18m 52s | Avg: 1m 02s | Max: 9m 56s

🟥 cpu
  🟥 amd64              Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 ctk
  🟥 12.9               Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 cxx
  🟥 GCC13              Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 cxx_family
  🟥 GCC                Pass:   0%/18  | Total: 18m 52s | Avg:  1m 02s | Max:  9m 56s
🟥 gpu
  🟥 h100               Pass:   0%/8  
  🟥 rtxa6000           Pass:   0%/10  | Total: 18m 52s | Avg:  1m 53s | Max:  9m 56s
🟥 jobs
  🟥 Build cuda.cccl    Pass:   0%/2   | Total: 18m 52s | Avg:  9m 26s | Max:  9m 56s
  🟥 Test cuda.cccl.cooperative Pass:   0%/4  
  🟥 Test cuda.cccl.examples Pass:   0%/4  
  🟥 Test cuda.cccl.headers Pass:   0%/4  
  🟥 Test cuda.cccl.parallel Pass:   0%/4  
🟥 py_version
  🟥 3.10               Pass:   0%/9   | Total:  9m 56s | Avg:  1m 06s | Max:  9m 56s
  🟥 3.13               Pass:   0%/9   | Total:  8m 56s | Avg:  0m 59s | Max:  8m 56s

🟥 cccl_c_parallel: Pass: 0%/3 | Total: 2m 53s | Avg: 0m 57s | Max: 2m 53s

🟥 cpu
  🟥 amd64              Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 ctk
  🟥 12.9               Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 cudacxx
  🟥 nvcc12.9           Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 cudacxx_family
  🟥 nvcc               Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 cxx
  🟥 GCC13              Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 cxx_family
  🟥 GCC                Pass:   0%/3   | Total:  2m 53s | Avg:  0m 57s | Max:  2m 53s
🟥 gpu
  🟥 h100               Pass:   0%/1  
  🟥 rtx2080            Pass:   0%/2   | Total:  2m 53s | Avg:  1m 26s | Max:  2m 53s
🟥 jobs
  🟥 Build              Pass:   0%/1   | Total:  2m 53s | Avg:  2m 53s | Max:  2m 53s
  🟥 Test               Pass:   0%/2

🟩 cub: Pass: 100%/50 | Total: 12h 45m | Avg: 15m 18s | Max: 45m 35s | Hits: 99%/61956

🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total: 12h 30m | Avg: 15m 38s | Max: 45m 35s | Hits:  99%/59430 
  🟩 arm64              Pass: 100%/2   | Total: 14m 33s | Avg:  7m 16s | Max:  8m 28s | Hits:  99%/2526  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total:  1h 00m | Avg: 12m 02s | Max: 30m 19s | Hits:  99%/6211  
  🟩 12.9               Pass: 100%/45  | Total: 11h 45m | Avg: 15m 40s | Max: 45m 35s | Hits:  99%/55745 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 43s | Avg:  5m 21s | Max:  5m 29s | Hits:  99%/2175  
  🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 00m | Avg: 12m 02s | Max: 30m 19s | Hits:  99%/6211  
  🟩 nvcc12.9           Pass: 100%/43  | Total: 11h 34m | Avg: 16m 09s | Max: 45m 35s | Hits:  99%/53570 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 43s | Avg:  5m 21s | Max:  5m 29s | Hits:  99%/2175  
  🟩 nvcc               Pass: 100%/48  | Total: 12h 34m | Avg: 15m 43s | Max: 45m 35s | Hits:  99%/59781 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 26m 29s | Avg:  6m 37s | Max:  6m 51s | Hits:  99%/5054  
  🟩 Clang15            Pass: 100%/2   | Total: 13m 32s | Avg:  6m 46s | Max:  6m 46s | Hits:  99%/2523  
  🟩 Clang16            Pass: 100%/2   | Total: 13m 53s | Avg:  6m 56s | Max:  7m 05s | Hits:  99%/2523  
  🟩 Clang17            Pass: 100%/2   | Total: 14m 00s | Avg:  7m 00s | Max:  7m 04s | Hits:  99%/2523  
  🟩 Clang18            Pass: 100%/2   | Total: 13m 57s | Avg:  6m 58s | Max:  7m 05s | Hits:  99%/2523  
  🟩 Clang19            Pass: 100%/7   | Total:  1h 40m | Avg: 14m 19s | Max: 36m 11s | Hits:  99%/8484  
  🟩 GCC7               Pass: 100%/2   | Total: 16m 47s | Avg:  8m 23s | Max:  8m 49s | Hits:  99%/2526  
  🟩 GCC8               Pass: 100%/1   | Total:  9m 05s | Avg:  9m 05s | Max:  9m 05s | Hits:  99%/1263  
  🟩 GCC9               Pass: 100%/2   | Total: 18m 41s | Avg:  9m 20s | Max:  9m 38s | Hits:  99%/2526  
  🟩 GCC10              Pass: 100%/2   | Total: 18m 06s | Avg:  9m 03s | Max:  9m 35s | Hits:  99%/2527  
  🟩 GCC11              Pass: 100%/2   | Total: 18m 09s | Avg:  9m 04s | Max:  9m 10s | Hits:  99%/2523  
  🟩 GCC12              Pass: 100%/2   | Total: 18m 44s | Avg:  9m 22s | Max:  9m 34s | Hits:  99%/2523  
  🟩 GCC13              Pass: 100%/12  | Total:  4h 34m | Avg: 22m 51s | Max: 45m 35s | Hits:  99%/15165 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 02m | Avg: 31m 14s | Max: 32m 10s | Hits:  99%/2316  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  2h 00m | Avg: 30m 01s | Max: 35m 23s | Hits:  99%/4632  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 27m 00s | Avg: 13m 30s | Max: 13m 41s | Hits:  98%/2325  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  3h 02m | Avg:  9m 35s | Max: 36m 11s | Hits:  99%/23630 
  🟩 GCC                Pass: 100%/23  | Total:  6h 13m | Avg: 16m 15s | Max: 45m 35s | Hits:  99%/29053 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 02m | Avg: 30m 25s | Max: 35m 23s | Hits:  99%/6948  
  🟩 NVHPC              Pass: 100%/2   | Total: 27m 00s | Avg: 13m 30s | Max: 13m 41s | Hits:  98%/2325  
🟩 gpu
  🟩 h100               Pass: 100%/3   | Total:  1h 08m | Avg: 22m 45s | Max: 35m 40s | Hits:  99%/3792  
  🟩 rtx2080            Pass: 100%/39  | Total:  7h 28m | Avg: 11m 30s | Max: 35m 23s | Hits:  99%/48058 
  🟩 rtxa6000           Pass: 100%/8   | Total:  4h 08m | Avg: 31m 04s | Max: 45m 35s | Hits:  99%/10106 
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  7h 51m | Avg: 11m 13s | Max: 35m 23s | Hits:  99%/51848 
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 43m 12s | Avg: 43m 12s | Max: 43m 12s | Hits:  99%/1264  
  🟩 GraphCapture       Pass: 100%/1   | Total: 30m 00s | Avg: 30m 00s | Max: 30m 00s | Hits:  99%/1264  
  🟩 HostLaunch         Pass: 100%/3   | Total:  1h 57m | Avg: 39m 08s | Max: 45m 35s | Hits:  99%/3790  
  🟩 TestGPU            Pass: 100%/3   | Total:  1h 43m | Avg: 34m 30s | Max: 43m 28s | Hits:  99%/3790  
🟩 sm
  🟩 90                 Pass: 100%/3   | Total:  1h 08m | Avg: 22m 45s | Max: 35m 40s | Hits:  99%/3792  
  🟩 90;90a             Pass: 100%/2   | Total: 34m 40s | Avg: 17m 20s | Max: 26m 47s | Hits:  99%/2422  
  🟩 100;120            Pass: 100%/2   | Total: 35m 31s | Avg: 17m 45s | Max: 27m 13s | Hits:  99%/2422  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  4h 02m | Avg: 11m 32s | Max: 32m 10s | Hits:  99%/25915 
  🟩 20                 Pass: 100%/29  | Total:  8h 42m | Avg: 18m 01s | Max: 45m 35s | Hits:  99%/36041

🟩 thrust: Pass: 100%/50 | Total: 9h 17m | Avg: 11m 08s | Max: 34m 07s | Hits: 99%/95621

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 21m 13s | Avg: 10m 36s | Max: 13m 14s | Hits:  99%/3828  
🟩 cpu
  🟩 amd64              Pass: 100%/48  | Total:  9h 05m | Avg: 11m 21s | Max: 34m 07s | Hits:  99%/91794 
  🟩 arm64              Pass: 100%/2   | Total: 12m 10s | Avg:  6m 05s | Max:  7m 02s | Hits:  99%/3827  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 54m 31s | Avg: 10m 54s | Max: 30m 27s | Hits:  99%/9560  
  🟩 12.9               Pass: 100%/45  | Total:  8h 22m | Avg: 11m 10s | Max: 34m 07s | Hits:  99%/86061 
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 10m 53s | Avg:  5m 26s | Max:  5m 32s | Hits: 100%/3826  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 54m 31s | Avg: 10m 54s | Max: 30m 27s | Hits:  99%/9560  
  🟩 nvcc12.9           Pass: 100%/43  | Total:  8h 11m | Avg: 11m 26s | Max: 34m 07s | Hits:  99%/82235 
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 53s | Avg:  5m 26s | Max:  5m 32s | Hits: 100%/3826  
  🟩 nvcc               Pass: 100%/48  | Total:  9h 06m | Avg: 11m 22s | Max: 34m 07s | Hits:  99%/91795 
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 23m 13s | Avg:  5m 48s | Max:  6m 19s | Hits: 100%/7652  
  🟩 Clang15            Pass: 100%/2   | Total: 12m 07s | Avg:  6m 03s | Max:  6m 25s | Hits: 100%/3826  
  🟩 Clang16            Pass: 100%/2   | Total: 12m 00s | Avg:  6m 00s | Max:  6m 09s | Hits: 100%/3826  
  🟩 Clang17            Pass: 100%/2   | Total: 12m 17s | Avg:  6m 08s | Max:  6m 27s | Hits: 100%/3826  
  🟩 Clang18            Pass: 100%/2   | Total: 11m 44s | Avg:  5m 52s | Max:  6m 00s | Hits: 100%/3826  
  🟩 Clang19            Pass: 100%/7   | Total: 45m 38s | Avg:  6m 31s | Max: 10m 02s | Hits: 100%/13391 
  🟩 GCC7               Pass: 100%/2   | Total: 13m 33s | Avg:  6m 46s | Max:  7m 09s | Hits:  99%/3828  
  🟩 GCC8               Pass: 100%/1   | Total:  7m 11s | Avg:  7m 11s | Max:  7m 11s | Hits:  99%/1914  
  🟩 GCC9               Pass: 100%/2   | Total: 14m 54s | Avg:  7m 27s | Max:  8m 07s | Hits:  99%/3828  
  🟩 GCC10              Pass: 100%/2   | Total: 14m 19s | Avg:  7m 09s | Max:  7m 15s | Hits:  99%/3828  
  🟩 GCC11              Pass: 100%/2   | Total: 15m 17s | Avg:  7m 38s | Max:  7m 53s | Hits:  99%/3828  
  🟩 GCC12              Pass: 100%/2   | Total: 16m 49s | Avg:  8m 24s | Max:  8m 33s | Hits:  99%/3828  
  🟩 GCC13              Pass: 100%/11  | Total:  1h 39m | Avg:  9m 04s | Max: 13m 16s | Hits:  99%/21054 
  🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 00m | Avg: 30m 08s | Max: 30m 27s | Hits:  99%/3812  
  🟩 MSVC14.43          Pass: 100%/5   | Total:  2h 23m | Avg: 28m 42s | Max: 34m 07s | Hits:  99%/9530  
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 54m 35s | Avg: 27m 17s | Max: 27m 57s | Hits:  99%/3824  
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  1h 56m | Avg:  6m 09s | Max: 10m 02s | Hits: 100%/36347 
  🟩 GCC                Pass: 100%/22  | Total:  3h 01m | Avg:  8m 16s | Max: 13m 16s | Hits:  99%/42108 
  🟩 MSVC               Pass: 100%/7   | Total:  3h 23m | Avg: 29m 06s | Max: 34m 07s | Hits:  99%/13342 
  🟩 NVHPC              Pass: 100%/2   | Total: 54m 35s | Avg: 27m 17s | Max: 27m 57s | Hits:  99%/3824  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 18m 02s | Avg:  9m 01s | Max: 12m 17s | Hits:  99%/3828  
  🟩 rtx2080            Pass: 100%/38  | Total:  6h 39m | Avg: 10m 30s | Max: 30m 57s | Hits:  99%/72672 
  🟩 rtx4090            Pass: 100%/10  | Total:  2h 19m | Avg: 13m 59s | Max: 34m 07s | Hits:  99%/19121 
🟩 jobs
  🟩 Build              Pass: 100%/43  | Total:  7h 36m | Avg: 10m 37s | Max: 30m 57s | Hits:  99%/82233 
  🟩 TestCPU            Pass: 100%/3   | Total: 51m 45s | Avg: 17m 15s | Max: 34m 07s | Hits:  99%/5733  
  🟩 TestGPU            Pass: 100%/4   | Total: 48m 49s | Avg: 12m 12s | Max: 13m 16s | Hits:  99%/7655  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 18m 02s | Avg:  9m 01s | Max: 12m 17s | Hits:  99%/3828  
  🟩 90;90a             Pass: 100%/2   | Total: 31m 15s | Avg: 15m 37s | Max: 24m 36s | Hits:  99%/3820  
  🟩 100;120            Pass: 100%/2   | Total: 31m 57s | Avg: 15m 58s | Max: 24m 38s | Hits:  99%/3820  
🟩 std
  🟩 17                 Pass: 100%/21  | Total:  3h 52m | Avg: 11m 04s | Max: 30m 57s | Hits:  99%/40160 
  🟩 20                 Pass: 100%/27  | Total:  5h 03m | Avg: 11m 14s | Max: 34m 07s | Hits:  99%/51633

🟩 libcudacxx: Pass: 100%/48 | Total: 8h 44m | Avg: 10m 55s | Max: 34m 02s | Hits: 96%/166828

🟩 cpu
  🟩 amd64              Pass: 100%/46  | Total:  8h 35m | Avg: 11m 12s | Max: 34m 02s | Hits:  96%/159367
  🟩 arm64              Pass: 100%/2   | Total:  9m 08s | Avg:  4m 34s | Max:  4m 38s | Hits:  99%/7461  
🟩 ctk
  🟩 12.0               Pass: 100%/5   | Total: 46m 39s | Avg:  9m 19s | Max: 29m 00s | Hits:  99%/18287 
  🟩 12.9               Pass: 100%/43  | Total:  7h 57m | Avg: 11m 06s | Max: 34m 02s | Hits:  95%/148541
🟩 cudacxx
  🟩 ClangCUDA19        Pass: 100%/2   | Total: 52m 08s | Avg: 26m 04s | Max: 26m 48s | Hits:  29%/7425  
  🟩 nvcc12.0           Pass: 100%/5   | Total: 46m 39s | Avg:  9m 19s | Max: 29m 00s | Hits:  99%/18287 
  🟩 nvcc12.9           Pass: 100%/41  | Total:  7h 05m | Avg: 10m 23s | Max: 34m 02s | Hits:  99%/141116
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 52m 08s | Avg: 26m 04s | Max: 26m 48s | Hits:  29%/7425  
  🟩 nvcc               Pass: 100%/46  | Total:  7h 52m | Avg: 10m 16s | Max: 34m 02s | Hits:  99%/159403
🟩 cxx
  🟩 Clang14            Pass: 100%/4   | Total: 19m 02s | Avg:  4m 45s | Max:  5m 13s | Hits:  99%/14806 
  🟩 Clang15            Pass: 100%/2   | Total: 10m 13s | Avg:  5m 06s | Max:  5m 18s | Hits:  99%/7421  
  🟩 Clang16            Pass: 100%/2   | Total: 10m 46s | Avg:  5m 23s | Max:  5m 25s | Hits:  99%/7421  
  🟩 Clang17            Pass: 100%/2   | Total: 10m 03s | Avg:  5m 01s | Max:  5m 04s | Hits:  99%/7421  
  🟩 Clang18            Pass: 100%/2   | Total: 10m 07s | Avg:  5m 03s | Max:  5m 13s | Hits:  99%/7421  
  🟩 Clang19            Pass: 100%/6   | Total:  1h 26m | Avg: 14m 23s | Max: 26m 48s | Hits:  75%/22306 
  🟩 GCC7               Pass: 100%/2   | Total:  9m 12s | Avg:  4m 36s | Max:  4m 57s | Hits:  99%/7357  
  🟩 GCC8               Pass: 100%/1   | Total:  4m 49s | Avg:  4m 49s | Max:  4m 49s | Hits:  99%/3689  
  🟩 GCC9               Pass: 100%/2   | Total:  9m 32s | Avg:  4m 46s | Max:  4m 54s | Hits:  99%/7369  
  🟩 GCC10              Pass: 100%/2   | Total: 10m 03s | Avg:  5m 01s | Max:  5m 17s | Hits:  99%/7423  
  🟩 GCC11              Pass: 100%/2   | Total: 10m 26s | Avg:  5m 13s | Max:  5m 19s | Hits:  99%/7419  
  🟩 GCC12              Pass: 100%/2   | Total: 10m 06s | Avg:  5m 03s | Max:  5m 08s | Hits:  99%/7423  
  🟩 GCC13              Pass: 100%/11  | Total:  2h 00m | Avg: 10m 57s | Max: 24m 28s | Hits:  99%/30183 
  🟩 MSVC14.29          Pass: 100%/2   | Total: 58m 19s | Avg: 29m 09s | Max: 29m 19s | Hits:  99%/7093  
  🟩 MSVC14.43          Pass: 100%/4   | Total:  2h 02m | Avg: 30m 40s | Max: 34m 02s | Hits:  99%/14669 
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 22m 20s | Avg: 11m 10s | Max: 11m 33s | Hits:  98%/7407  
🟩 cxx_family
  🟩 Clang              Pass: 100%/18  | Total:  2h 26m | Avg:  8m 08s | Max: 26m 48s | Hits:  91%/66796 
  🟩 GCC                Pass: 100%/22  | Total:  2h 54m | Avg:  7m 56s | Max: 24m 28s | Hits:  99%/70863 
  🟩 MSVC               Pass: 100%/6   | Total:  3h 01m | Avg: 30m 10s | Max: 34m 02s | Hits:  99%/21762 
  🟩 NVHPC              Pass: 100%/2   | Total: 22m 20s | Avg: 11m 10s | Max: 11m 33s | Hits:  98%/7407  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 23m 04s | Avg: 11m 32s | Max: 17m 47s | Hits:  99%/7628  
  🟩 rtx2080            Pass: 100%/46  | Total:  8h 21m | Avg: 10m 54s | Max: 34m 02s | Hits:  96%/159200
🟩 jobs
  🟩 Build              Pass: 100%/42  | Total:  6h 54m | Avg:  9m 52s | Max: 34m 02s | Hits:  95%/155511
  🟩 NVRTC              Pass: 100%/2   | Total: 46m 20s | Avg: 23m 10s | Max: 24m 28s | Hits:  90%/42    
  🟩 Test               Pass: 100%/3   | Total:  1h 01m | Avg: 20m 32s | Max: 24m 09s | Hits:  99%/11275 
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s
🟩 sm
  🟩 75                 Pass: 100%/2   | Total: 46m 20s | Avg: 23m 10s | Max: 24m 28s | Hits:  90%/42    
  🟩 90                 Pass: 100%/2   | Total: 23m 04s | Avg: 11m 32s | Max: 17m 47s | Hits:  99%/7628  
  🟩 90;90a             Pass: 100%/2   | Total: 35m 39s | Avg: 17m 49s | Max: 30m 18s | Hits:  99%/7575  
  🟩 100;120            Pass: 100%/2   | Total: 33m 01s | Avg: 16m 30s | Max: 28m 00s | Hits:  99%/7575  
🟩 std
  🟩 17                 Pass: 100%/22  | Total:  3h 52m | Avg: 10m 33s | Max: 34m 02s | Hits:  96%/77045 
  🟩 20                 Pass: 100%/25  | Total:  4h 50m | Avg: 11m 37s | Max: 30m 23s | Hits:  96%/89783

🟩 cudax: Pass: 100%/28 | Total: 5h 17m | Avg: 11m 20s | Max: 22m 04s | Hits: 85%/15978

🟩 cpu
  🟩 amd64              Pass: 100%/24  | Total:  4h 35m | Avg: 11m 29s | Max: 22m 04s | Hits:  85%/13522 
  🟩 arm64              Pass: 100%/4   | Total: 41m 36s | Avg: 10m 24s | Max: 11m 16s | Hits:  82%/2456  
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 30m 33s | Avg: 10m 11s | Max: 11m 23s | Hits:  85%/1537  
  🟩 12.9               Pass: 100%/25  | Total:  4h 46m | Avg: 11m 28s | Max: 22m 04s | Hits:  85%/14441 
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 30m 33s | Avg: 10m 11s | Max: 11m 23s | Hits:  85%/1537  
  🟩 nvcc12.9           Pass: 100%/25  | Total:  4h 46m | Avg: 11m 28s | Max: 22m 04s | Hits:  85%/14441 
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/28  | Total:  5h 17m | Avg: 11m 20s | Max: 22m 04s | Hits:  85%/15978 
🟩 cxx
  🟩 Clang14            Pass: 100%/2   | Total: 19m 44s | Avg:  9m 52s | Max: 10m 14s | Hits:  82%/1230  
  🟩 Clang15            Pass: 100%/1   | Total: 11m 01s | Avg: 11m 01s | Max: 11m 01s | Hits:  82%/614   
  🟩 Clang16            Pass: 100%/1   | Total: 11m 34s | Avg: 11m 34s | Max: 11m 34s | Hits:  82%/614   
  🟩 Clang17            Pass: 100%/1   | Total: 11m 05s | Avg: 11m 05s | Max: 11m 05s | Hits:  82%/614   
  🟩 Clang18            Pass: 100%/1   | Total: 11m 08s | Avg: 11m 08s | Max: 11m 08s | Hits:  82%/614   
  🟩 Clang19            Pass: 100%/4   | Total: 37m 54s | Avg:  9m 28s | Max: 10m 43s | Hits:  86%/2456  
  🟩 GCC10              Pass: 100%/2   | Total: 21m 00s | Avg: 10m 30s | Max: 11m 20s | Hits:  82%/1230  
  🟩 GCC11              Pass: 100%/1   | Total: 11m 42s | Avg: 11m 42s | Max: 11m 42s | Hits:  82%/614   
  🟩 GCC12              Pass: 100%/1   | Total: 12m 13s | Avg: 12m 13s | Max: 12m 13s | Hits:  82%/614   
  🟩 GCC13              Pass: 100%/8   | Total:  1h 21m | Avg: 10m 13s | Max: 12m 07s | Hits:  86%/4912  
  🟩 MSVC14.39          Pass: 100%/1   | Total: 11m 23s | Avg: 11m 23s | Max: 11m 23s | Hits:  95%/309   
  🟩 MSVC14.43          Pass: 100%/3   | Total: 33m 59s | Avg: 11m 19s | Max: 11m 49s | Hits:  96%/933   
  🟩 NVHPC25.5          Pass: 100%/2   | Total: 42m 49s | Avg: 21m 24s | Max: 22m 04s | Hits:  79%/1224  
🟩 cxx_family
  🟩 Clang              Pass: 100%/10  | Total:  1h 42m | Avg: 10m 14s | Max: 11m 34s | Hits:  84%/6142  
  🟩 GCC                Pass: 100%/12  | Total:  2h 06m | Avg: 10m 33s | Max: 12m 13s | Hits:  85%/7370  
  🟩 MSVC               Pass: 100%/4   | Total: 45m 22s | Avg: 11m 20s | Max: 11m 49s | Hits:  96%/1242  
  🟩 NVHPC              Pass: 100%/2   | Total: 42m 49s | Avg: 21m 24s | Max: 22m 04s | Hits:  79%/1224  
🟩 gpu
  🟩 h100               Pass: 100%/2   | Total: 15m 58s | Avg:  7m 59s | Max:  8m 30s | Hits:  90%/1228  
  🟩 rtx2080            Pass: 100%/26  | Total:  5h 01m | Avg: 11m 35s | Max: 22m 04s | Hits:  84%/14750 
🟩 jobs
  🟩 Build              Pass: 100%/25  | Total:  4h 51m | Avg: 11m 39s | Max: 22m 04s | Hits:  83%/14136 
  🟩 Test               Pass: 100%/3   | Total: 25m 49s | Avg:  8m 36s | Max: 10m 15s | Hits:  99%/1842  
🟩 sm
  🟩 90                 Pass: 100%/2   | Total: 15m 58s | Avg:  7m 59s | Max:  8m 30s | Hits:  90%/1228  
  🟩 90;90a             Pass: 100%/2   | Total: 21m 31s | Avg: 10m 45s | Max: 10m 59s | Hits:  86%/925   
  🟩 100;120            Pass: 100%/2   | Total: 21m 37s | Avg: 10m 48s | Max: 11m 11s | Hits:  86%/925   
🟩 std
  🟩 17                 Pass: 100%/3   | Total: 42m 40s | Avg: 14m 13s | Max: 22m 04s | Hits:  81%/1840  
  🟩 20                 Pass: 100%/25  | Total:  4h 34m | Avg: 10m 59s | Max: 20m 45s | Hits:  85%/14138

🟩 packaging: Pass: 100%/4 | Total: 14m 24s | Avg: 3m 36s | Max: 3m 47s

🟩 cpu
  🟩 amd64              Pass: 100%/4   | Total: 14m 24s | Avg:  3m 36s | Max:  3m 47s
🟩 ctk
  🟩 12.0               Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 47s
  🟩 12.9               Pass: 100%/2   | Total:  7m 03s | Avg:  3m 31s | Max:  3m 45s
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 47s
  🟩 nvcc12.9           Pass: 100%/2   | Total:  7m 03s | Avg:  3m 31s | Max:  3m 45s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 14m 24s | Avg:  3m 36s | Max:  3m 47s
🟩 cxx
  🟩 Clang14            Pass: 100%/1   | Total:  3m 34s | Avg:  3m 34s | Max:  3m 34s
  🟩 Clang19            Pass: 100%/1   | Total:  3m 45s | Avg:  3m 45s | Max:  3m 45s
  🟩 GCC12              Pass: 100%/1   | Total:  3m 47s | Avg:  3m 47s | Max:  3m 47s
  🟩 GCC13              Pass: 100%/1   | Total:  3m 18s | Avg:  3m 18s | Max:  3m 18s
🟩 cxx_family
  🟩 Clang              Pass: 100%/2   | Total:  7m 19s | Avg:  3m 39s | Max:  3m 45s
  🟩 GCC                Pass: 100%/2   | Total:  7m 05s | Avg:  3m 32s | Max:  3m 47s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 14m 24s | Avg:  3m 36s | Max:  3m 47s
🟩 jobs
  🟩 Test               Pass: 100%/4   | Total: 14m 24s | Avg:  3m 36s | Max:  3m 47s

🟩 stdpar: Pass: 100%/4 | Total: 17m 21s | Avg: 4m 20s | Max: 4m 38s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total:  9m 01s | Avg:  4m 30s | Max:  4m 38s
  🟩 arm64              Pass: 100%/2   | Total:  8m 20s | Avg:  4m 10s | Max:  4m 19s
🟩 ctk
  🟩 12.9               Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 cudacxx
  🟩 nvcc12.9           Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 cxx
  🟩 NVHPC25.5          Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 cxx_family
  🟩 NVHPC              Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 gpu
  🟩 rtx2080            Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 jobs
  🟩 Build              Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 38s
🟩 std
  🟩 17                 Pass: 100%/2   | Total:  8m 39s | Avg:  4m 19s | Max:  4m 38s
  🟩 20                 Pass: 100%/2   | Total:  8m 42s | Avg:  4m 21s | Max:  4m 23s

👃 Inspect Changes

Modifications in project?

	Project
+/-	CCCL Infrastructure
	CCCL Packaging
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental
	stdpar
	python
	CCCL C Parallel Library
	Catch2Helper

Modifications in project or dependencies?

	Project
+/-	CCCL Infrastructure
+/-	CCCL Packaging
+/-	libcu++
+/-	CUB
+/-	Thrust
+/-	CUDA Experimental
+/-	stdpar
+/-	python
+/-	CCCL C Parallel Library
+/-	Catch2Helper

🏃‍ Runner counts (total jobs: 205)

#	Runner
128	`linux-amd64-cpu16`
23	`windows-amd64-cpu16`
14	`linux-amd64-gpu-h100-latest-1`
14	`linux-amd64-gpu-rtxa6000-latest-1`
12	`linux-arm64-cpu16`
11	`linux-amd64-gpu-rtx2080-latest-1`
3	`linux-amd64-gpu-rtx4090-latest-1`

caugonnet · 2025-07-23T22:51:27Z

/ok to test 9acc75b

caugonnet · 2026-07-19T06:47:02Z

+#  define STF_WHILE_COND_MAX_TERMS 8
+
+//! \brief Combiner for multi-term while conditions.
+typedef enum stf_cond_combiner


This could be extracted as as standalone PR (C combined conditions)

Extracted in #10006

Mirror the fixes the regular logical_data path already had, which the stackable factory never received: - Require C-contiguous buffer-protocol exporters (PyBUF_C_CONTIGUOUS): the registered byte range is interpreted with the stored C-order shape, so a Fortran-ordered exporter was silently read in the wrong element order. - Keep the Py_buffer export alive until __dealloc__ instead of releasing it immediately: STF holds view.buf and may touch it asynchronously, and a resizable exporter (e.g. bytearray) could reallocate after release, leaving STF with a stale pointer. The held export also makes resize attempts fail loudly with BufferError. - Capture the source's readonly flag (CAI and buffer protocol), expose it as .readonly, and reject write()/rw() deps and write-capable push() modes on read-only sources. A read-only source is additionally auto-marked STF-level read-only: the stackable auto-import otherwise promotes even read accesses in nested scopes to an RW freeze, which triggers a pop/finalize write-back into memory the exporter declared immutable. set_read_only() now also raises the Python-side flag so misuse fails with a clear ValueError instead of a release-mode compiled-out C++ assertion. Add regression tests for all of the above across both context types, including the previously untested readonly-rejection path of the regular context. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Mirror pytorch_task: a failing t.end() in __enter__'s error path or in __exit__ while a body exception is propagating must not mask the original failure; only surface cleanup errors when the body succeeded. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

check_result defaulted to False, so the example harness (which calls main() with default arguments) only exercised control flow without ever validating the math. Check by default and replace the CLI --check flag with --no-check for benchmarking runs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

logical_data() previously rejected any CUDA Array Interface object that advertised a producer stream. Honor the CAI v3 contract instead: the consumer must order against the producer stream before touching the data, so synchronize the advertised stream once at registration (matching what Numba does on import). None means no synchronization, 1/2 map directly to the runtime's legacy/per-thread default stream handles, other values are raw cudaStream_t handles; 0 is rejected as the spec disallows it. An asynchronous producer-to-STF prerequisite (event wait instead of a host synchronization) can replace this later without an API change. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Point at the complete tested program in tests/stf/test_cuda_kernel.py so readers know where the undefined names (ctx, lX, kernel, ...) come from. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Same treatment as the cuda_kernel snippet: point at the complete tested program in tests/stf/interop/test_cuda_compute.py. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

- test_from_context: importorskip("cupy") before device/green-context setup so a missing cupy skips without allocating a green context. - test_numba: drop dead return after pytest.skip(). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

github-actions · 2026-07-19T08:06:28Z

😬 CI Workflow Results

🟥 Finished in 2h 37m: Pass: 91%/528 | Total: 18d 13h | Max: 2h 36m | Hits: 36%/1869685

See results here.

caugonnet · 2026-07-19T08:12:22Z

@coderabbitai full review

coderabbitai · 2026-07-19T08:12:27Z

✅ Action performed

Full review finished.

coderabbitai

Actionable comments posted: 4

🧹 Nitpick comments (4)

python/cuda_stf/tests/test_examples.py (1)

121-129: 🩺 Stability & Availability | 🔵 Trivial | 💤 Low value

suggestion: add a timeout= to subprocess.run so a hanging example fails the test instead of stalling CI indefinitely.

python/cuda_stf/tests/stf/examples/cg.py (1)

5-32: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

suggestion: docstring lists host_launch under "Demonstrates" (Line 12), but this example never calls host_launch. Drop that bullet to keep the teaching doc accurate.

python/cuda_stf/tests/stf/examples/potri.py (1)

1033-1102: 🚀 Performance & Scalability | 🔵 Trivial | ⚡ Quick win

suggestion: the timed region (start_time at Line 1034 → end_time at Line 1093) wraps the check_result matrix fills (host Python loops, Lines 1063-1075), the compute_norm host tasks, and finalize. So elapsed_ms/GFLOPS is inflated by verification/setup work when check_result=True. Mirror cholesky.py: bracket only the POTRI submission with a deviceSynchronize, and prefer time.perf_counter() over time.time().

python/cuda_stf/cuda/stf/_experimental/_stf_bindings_impl.pyx (1)

3279-3298: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

suggestion: terms[8] and the n > 8 bound are hardcoded while STF_WHILE_COND_MAX_TERMS is declared as an extern C constant (and _combine_cond at Line 3739 repeats the literal 8). If the C side ever changes the max, these silently diverge. Consider centralizing on the C constant.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: abc605ed-4698-4aff-ba70-c12f40e878eb

📥 Commits

Reviewing files that changed from the base of the PR and between db2f947 and cbceed3.

📒 Files selected for processing (83)

.github/CODEOWNERS
AGENTS.md
c/experimental/stf/include/cccl/c/experimental/stf/stf.h
c/experimental/stf/src/stf.cu
c/experimental/stf/test/test_stackable.cu
ci/build_cuda_stf_combined_python.sh
ci/build_cuda_stf_python.sh
ci/build_cuda_stf_wheel.sh
ci/matrix.yaml
ci/project_files_and_dependencies.yaml
ci/test/inspect_changes/c2h_dependency.output
ci/test_cuda_stf_python.sh
ci/util/workflow/get_wheel_artifact_name.sh
docs/conf.py
docs/python/api_reference.rst
docs/python/index.rst
docs/python/setup.rst
docs/python/stf.rst
docs/python/stf_api.rst
python/cuda_stf/.gitignore
python/cuda_stf/CMakeLists.txt
python/cuda_stf/LICENSE
python/cuda_stf/README.md
python/cuda_stf/cuda/stf/_experimental/__init__.py
python/cuda_stf/cuda/stf/_experimental/_cuda_version_utils.py
python/cuda_stf/cuda/stf/_experimental/_stf_bindings.py
python/cuda_stf/cuda/stf/_experimental/_stf_bindings_impl.pyx
python/cuda_stf/cuda/stf/_experimental/_stream_utils.py
python/cuda_stf/cuda/stf/_experimental/device_array.py
python/cuda_stf/cuda/stf/_experimental/fill_utils.py
python/cuda_stf/cuda/stf/_experimental/green_places.py
python/cuda_stf/cuda/stf/_experimental/interop/__init__.py
python/cuda_stf/cuda/stf/_experimental/interop/numba.py
python/cuda_stf/cuda/stf/_experimental/interop/pytorch.py
python/cuda_stf/cuda/stf/_experimental/paths.py
python/cuda_stf/cuda/stf/_experimental/task_graph.py
python/cuda_stf/merge_cuda_wheels.py
python/cuda_stf/pyproject.toml
python/cuda_stf/tests/stf/examples/__init__.py
python/cuda_stf/tests/stf/examples/bicgstab.py
python/cuda_stf/tests/stf/examples/burger.py
python/cuda_stf/tests/stf/examples/burger_reference.py
python/cuda_stf/tests/stf/examples/cg.py
python/cuda_stf/tests/stf/examples/cholesky.py
python/cuda_stf/tests/stf/examples/fhe.py
python/cuda_stf/tests/stf/examples/fhe_decorator.py
python/cuda_stf/tests/stf/examples/neural_ode_dopri5.py
python/cuda_stf/tests/stf/examples/neural_ode_rk4.py
python/cuda_stf/tests/stf/examples/potri.py
python/cuda_stf/tests/stf/examples/stackable_branch_while_warp.py
python/cuda_stf/tests/stf/interop/__init__.py
python/cuda_stf/tests/stf/interop/test_cuda_compute.py
python/cuda_stf/tests/stf/interop/test_decorator.py
python/cuda_stf/tests/stf/interop/test_fdtd.py
python/cuda_stf/tests/stf/interop/test_jacobi_numba.py
python/cuda_stf/tests/stf/interop/test_jacobi_pytorch.py
python/cuda_stf/tests/stf/interop/test_jacobi_warp.py
python/cuda_stf/tests/stf/interop/test_legacy_to_stf.py
python/cuda_stf/tests/stf/interop/test_local_stf_capture.py
python/cuda_stf/tests/stf/interop/test_numba.py
python/cuda_stf/tests/stf/interop/test_pytorch.py
python/cuda_stf/tests/stf/interop/test_pytorch_task_context.py
python/cuda_stf/tests/stf/interop/test_scoped_capture.py
python/cuda_stf/tests/stf/interop/test_stencil_decorator.py
python/cuda_stf/tests/stf/interop/test_warp_pytorch_dag.py
python/cuda_stf/tests/stf/test_cai.py
python/cuda_stf/tests/stf/test_composite_places.py
python/cuda_stf/tests/stf/test_context.py
python/cuda_stf/tests/stf/test_cuda_kernel.py
python/cuda_stf/tests/stf/test_fill_utils.py
python/cuda_stf/tests/stf/test_from_context.py
python/cuda_stf/tests/stf/test_graph_scope.py
python/cuda_stf/tests/stf/test_host_launch.py
python/cuda_stf/tests/stf/test_launchable_graph.py
python/cuda_stf/tests/stf/test_lifecycle.py
python/cuda_stf/tests/stf/test_nested_scopes.py
python/cuda_stf/tests/stf/test_packaging.py
python/cuda_stf/tests/stf/test_place_support.py
python/cuda_stf/tests/stf/test_stream_utils.py
python/cuda_stf/tests/stf/test_task_graph.py
python/cuda_stf/tests/stf/test_token.py
python/cuda_stf/tests/stf/test_while_cond.py
python/cuda_stf/tests/test_examples.py

- cg.py: drop the host_launch docstring bullet, the example never calls it - potri.py: bracket only the POTRI submission with device synchronizes and time.perf_counter(), matching cholesky.py, so verification and finalize no longer inflate the reported GFLOPS - _stf_bindings_impl.pyx: use the STF_WHILE_COND_MAX_TERMS C constant instead of hardcoded 8s for while-condition term limits Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

If _get_stream_pointer raised on a malformed stream argument after the _PrimaryContextPin was acquired, context.__cinit__ aborted with _ctx still NULL, and since _PrimaryContextPin.__dealloc__ is a deliberate no-op the primary-context retains leaked until process exit. Resolve the stream pointer first so argument validation cannot strand the pin. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

caugonnet · 2026-07-20T14:22:12Z

@coderabbitai full review

coderabbitai · 2026-07-20T14:22:37Z

✅ Action performed

Full review finished.

coderabbitai

Actionable comments posted: 3

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

ci/util/workflow/get_wheel_artifact_name.sh (1)
49-49: 🎯 Functional Correctness | 🟠 Major | ⚡ Quick win

important: Missing echo on line 49 causes an unhelpful "command not found" error instead of printing the job definition. With set -e active, the script exits before reaching exit 1 on line 50.
-    "Job definition: $job_def" >&2
+    echo "Job definition: $job_def" >&2

🧹 Nitpick comments (1)

python/cuda_stf/tests/test_examples.py (1)

92-95: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

suggestion: hasattr(module, "__main__") / getattr(module, "__main__") is effectively dead — modules don't expose a __main__ attribute, so only the main path ever fires. Drop the __main__ branch or replace it with the intended entry-point check.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 752e048a-cc2f-46da-9a8a-18ee3e5a3029

📥 Commits

Reviewing files that changed from the base of the PR and between 9ce4e4d and a4032b0.

📒 Files selected for processing (80)

.github/CODEOWNERS
AGENTS.md
ci/build_cuda_stf_combined_python.sh
ci/build_cuda_stf_python.sh
ci/build_cuda_stf_wheel.sh
ci/matrix.yaml
ci/project_files_and_dependencies.yaml
ci/test/inspect_changes/c2h_dependency.output
ci/test_cuda_stf_python.sh
ci/util/workflow/get_wheel_artifact_name.sh
docs/conf.py
docs/python/api_reference.rst
docs/python/index.rst
docs/python/setup.rst
docs/python/stf.rst
docs/python/stf_api.rst
python/cuda_stf/.gitignore
python/cuda_stf/CMakeLists.txt
python/cuda_stf/LICENSE
python/cuda_stf/README.md
python/cuda_stf/cuda/stf/_experimental/__init__.py
python/cuda_stf/cuda/stf/_experimental/_cuda_version_utils.py
python/cuda_stf/cuda/stf/_experimental/_stf_bindings.py
python/cuda_stf/cuda/stf/_experimental/_stf_bindings_impl.pyx
python/cuda_stf/cuda/stf/_experimental/_stream_utils.py
python/cuda_stf/cuda/stf/_experimental/device_array.py
python/cuda_stf/cuda/stf/_experimental/fill_utils.py
python/cuda_stf/cuda/stf/_experimental/green_places.py
python/cuda_stf/cuda/stf/_experimental/interop/__init__.py
python/cuda_stf/cuda/stf/_experimental/interop/numba.py
python/cuda_stf/cuda/stf/_experimental/interop/pytorch.py
python/cuda_stf/cuda/stf/_experimental/paths.py
python/cuda_stf/cuda/stf/_experimental/task_graph.py
python/cuda_stf/merge_cuda_wheels.py
python/cuda_stf/pyproject.toml
python/cuda_stf/tests/stf/examples/__init__.py
python/cuda_stf/tests/stf/examples/bicgstab.py
python/cuda_stf/tests/stf/examples/burger.py
python/cuda_stf/tests/stf/examples/burger_reference.py
python/cuda_stf/tests/stf/examples/cg.py
python/cuda_stf/tests/stf/examples/cholesky.py
python/cuda_stf/tests/stf/examples/fhe.py
python/cuda_stf/tests/stf/examples/fhe_decorator.py
python/cuda_stf/tests/stf/examples/neural_ode_dopri5.py
python/cuda_stf/tests/stf/examples/neural_ode_rk4.py
python/cuda_stf/tests/stf/examples/potri.py
python/cuda_stf/tests/stf/examples/stackable_branch_while_warp.py
python/cuda_stf/tests/stf/interop/__init__.py
python/cuda_stf/tests/stf/interop/test_cuda_compute.py
python/cuda_stf/tests/stf/interop/test_decorator.py
python/cuda_stf/tests/stf/interop/test_fdtd.py
python/cuda_stf/tests/stf/interop/test_jacobi_numba.py
python/cuda_stf/tests/stf/interop/test_jacobi_pytorch.py
python/cuda_stf/tests/stf/interop/test_jacobi_warp.py
python/cuda_stf/tests/stf/interop/test_legacy_to_stf.py
python/cuda_stf/tests/stf/interop/test_local_stf_capture.py
python/cuda_stf/tests/stf/interop/test_numba.py
python/cuda_stf/tests/stf/interop/test_pytorch.py
python/cuda_stf/tests/stf/interop/test_pytorch_task_context.py
python/cuda_stf/tests/stf/interop/test_scoped_capture.py
python/cuda_stf/tests/stf/interop/test_stencil_decorator.py
python/cuda_stf/tests/stf/interop/test_warp_pytorch_dag.py
python/cuda_stf/tests/stf/test_cai.py
python/cuda_stf/tests/stf/test_composite_places.py
python/cuda_stf/tests/stf/test_context.py
python/cuda_stf/tests/stf/test_cuda_kernel.py
python/cuda_stf/tests/stf/test_fill_utils.py
python/cuda_stf/tests/stf/test_from_context.py
python/cuda_stf/tests/stf/test_graph_scope.py
python/cuda_stf/tests/stf/test_host_launch.py
python/cuda_stf/tests/stf/test_launchable_graph.py
python/cuda_stf/tests/stf/test_lifecycle.py
python/cuda_stf/tests/stf/test_nested_scopes.py
python/cuda_stf/tests/stf/test_packaging.py
python/cuda_stf/tests/stf/test_place_support.py
python/cuda_stf/tests/stf/test_stream_utils.py
python/cuda_stf/tests/stf/test_task_graph.py
python/cuda_stf/tests/stf/test_token.py
python/cuda_stf/tests/stf/test_while_cond.py
python/cuda_stf/tests/test_examples.py

coderabbitai · 2026-07-20T14:47:01Z

+mkdir -p wheelhouse
+
+# Clear stale STF wheels from a previous run so the per-CTK wheel selection
+# below is unambiguous. Leave any co-located wheels (e.g. a cuda_cccl wheel
+# staged by a combined producer job) untouched.
+rm -f wheelhouse/cuda_stf-*.whl


🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win

important: remove stale wheelhouse_merged/ and wheelhouse_final/ before building. An interrupted prior run leaves repaired or merged wheels there; Lines 164-169 then glob and move them with the current result, potentially publishing stale artifacts. Keep the intentional dist/ lifecycle unchanged. As per path instructions, CI changes must handle cache and artifact state safely.

Sources: Path instructions, Learnings

coderabbitai · 2026-07-20T14:47:01Z

+dependencies = [
+  "numpy",
+  "cuda-pathfinder>=1.2.3",
+  "cuda-core",
+  "typing_extensions",


📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash set -euo pipefail # Map repository layout and find the relevant docs/files first. git ls-files | sed -n '1,200p' printf '\n--- CONTRIBUTING / CI docs ---\n' fd -a 'CONTRIBUTING.md|CI|ci|workflow' . printf '\n--- cuda_stf package files ---\n' fd -a 'pyproject.toml|green_places|cuda-core' python/cuda_stf .

Repository: NVIDIA/cccl

Length of output: 20939

🏁 Script executed:

#!/bin/bash set -euo pipefail # Read the relevant documentation and package metadata in targeted slices. for f in CONTRIBUTING.md .github/workflows/ci.yml python/cuda_stf/pyproject.toml; do if [ -f "$f" ]; then echo "===== $f =====" wc -l "$f" fi done echo "===== CONTRIBUTING.md (head) =====" sed -n '1,220p' CONTRIBUTING.md echo "===== CI workflow files =====" fd -a '.github/workflows' . -t f | while read -r wf; do echo "--- $wf ---" sed -n '1,220p' "$wf" done echo "===== python/cuda_stf/pyproject.toml =====" sed -n '1,220p' python/cuda_stf/pyproject.toml

Repository: NVIDIA/cccl

Length of output: 13079

🏁 Script executed:

#!/bin/bash set -euo pipefail # Search for green_places() definitions, docs, and any cuda-core version constraints. rg -n "green_places\(|cuda-core|cuda_core|>= 1\.0|>=1\.0|1\.0" python/cuda_stf .github -g '!**/.git/**'

Repository: NVIDIA/cccl

Length of output: 22677

🏁 Script executed:

#!/bin/bash set -euo pipefail echo '=== file inventory ===' git ls-files | rg '^(CONTRIBUTING\.md|\.github/workflows/|python/cuda_stf/)' echo echo '=== CONTRIBUTING.md ===' if [ -f CONTRIBUTING.md ]; then sed -n '1,220p' CONTRIBUTING.md fi echo echo '=== CI workflow files ===' fd -a '.github/workflows' . -t f | while read -r wf; do echo "--- $wf ---" sed -n '1,220p' "$wf" done echo echo '=== python/cuda_stf/pyproject.toml ===' sed -n '1,220p' python/cuda_stf/pyproject.toml echo echo '=== search for green_places and cuda-core references ===' rg -n "green_places\(|cuda-core|cuda_core|>= ?1\.0|>=1\.0" python/cuda_stf .github

Repository: NVIDIA/cccl

Length of output: 17463

🌐 Web query:

cuda-stf green_places cuda-core >= 1.0 documentation

💡 Result:

In the context of the CUDA Core Compute Libraries (CCCL), CUDASTF is a C++ library that implements a Sequential Task Flow (STF) model for CUDA [1][2]. The "green_places" you are inquiring about refers to the use of "green contexts" within the cuda::experimental::stf namespace, which provides SM-level partitioning of GPU resources [3]. Key documentation points include: 1. Green Contexts: Introduced in CUDA 12.4+, green contexts allow for partitioning GPU resources at the Streaming Multiprocessor (SM) level [3]. 2. Execution Places: In CUDASTF, an execution place defines where a task should run. exec_place_green_ctx is a specific execution place that designates tasks to run on a green context [4]. 3. Helper Classes: The green_context_helper class is provided to simplify the creation of green context views that can be utilized as execution places [5]. The green_ctx_view holds the underlying green context and its associated stream pool [6]. 4. Access: These features are part of the cuda::experimental::places namespace [3]. While they are integrated with CUDASTF, the places API can also be used as a standalone component [3]. Documentation for these features is available under the CUDA Core Compute Libraries (CCCL) documentation, specifically within the CUDA Experimental (CUDAX) section [3][1]. Regarding your mention of "cuda-core >= 1.0," note that CUDASTF is part of the experimental library (CUDAX) in the CCCL project and is distributed via the CCCL GitHub repository, rather than as part of the standard CUDA Toolkit [1].

Citations:

1: https://nvidia.github.io/cccl/unstable/cudax/stf.html

2: https://doi.org/10.1109/sc41406.2024.00049

3: https://nvidia.github.io/cccl/unstable/cudax/places.html

4: https://gevtushenko.github.io/cccl/cudax/api/classcuda_1_1experimental_1_1stf_1_1exec__place__green__ctx.html

5: https://gevtushenko.github.io/cccl/cudax/api/classcuda_1_1experimental_1_1stf_1_1green__context__helper.html

6: https://gevtushenko.github.io/cccl/cudax/api/classcuda_1_1experimental_1_1stf_1_1green__ctx__view.html

🏁 Script executed:

#!/bin/bash set -euo pipefail echo '=== python/cuda_stf/pyproject.toml dependency section ===' sed -n '24,48p' python/cuda_stf/pyproject.toml echo echo '=== python/cuda_stf/cuda/stf/_experimental/green_places.py ===' sed -n '1,220p' python/cuda_stf/cuda/stf/_experimental/green_places.py echo echo '=== python/cuda_stf/cuda/stf/_experimental/__init__.py ===' sed -n '1,220p' python/cuda_stf/cuda/stf/_experimental/__init__.py echo echo '=== python/cuda_stf/README.md mentions ===' rg -n "green_places|cuda-core|green context|green-context" python/cuda_stf/README.md python/cuda_stf/tests/stf/test_from_context.py python/cuda_stf/tests/stf/test_packaging.py

Repository: NVIDIA/cccl

Length of output: 11061

🏁 Script executed:

#!/bin/bash set -euo pipefail python3 - <<'PY' from pathlib import Path p = Path("python/cuda_stf/pyproject.toml") text = p.read_text() for needle in ['"cuda-core"', 'green_places', 'cuda-core >= 1.0', 'cuda-core>=1.0']: print(needle, text.find(needle)) PY

Repository: NVIDIA/cccl

Length of output: 220

important: pin cuda-core>=1.0 in python/cuda_stf/pyproject.toml; green_places() is public and requires the green-context API, so the current unconstrained dependency can leave an older installed release in place until the feature fails at runtime.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

caugonnet · 2026-07-20T19:30:33Z

 # make an exception for the cudax test cmake file
 cudax/test/CMakeLists.txt @nvidia/cccl-cudax-codeowners
-# make an exception for STF test cmake files, following the PR #5406 cudax test precedent
+# make an exception for STF test cmake files


Part of #9782

The Cython extension calls cudaStreamSynchronize directly (nogil CAI producer-stream sync) but links only the CUDA driver, so it relies on libcudart already being present in the process. Preload it through cuda.pathfinder alongside nvrtc and nvJitLink so a bare import works. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

cudaStreamSynchronize in _sync_cai_producer_stream was the extension's single CUDA runtime call, yet the module links only the CUDA driver, so imports relied on another package having already loaded cudart into the process. Call cuda.bindings.runtime instead (registration is not a hot path) and drop the RTLD_GLOBAL cudart preload workaround: the compiled bindings' symbol table is now honestly driver-only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

caugonnet self-assigned this Jul 18, 2025

caugonnet requested review from a team as code owners July 18, 2025 21:28

caugonnet requested a review from bernhardmgruber July 18, 2025 21:28

caugonnet added the stf Sequential Task Flow programming model label Jul 18, 2025

github-project-automation Bot added this to CCCL Jul 18, 2025

github-project-automation Bot moved this to Todo in CCCL Jul 18, 2025

cccl-authenticator-app Bot moved this from Todo to In Review in CCCL Jul 18, 2025

caugonnet force-pushed the stf_c_api branch from 8b910b1 to f388814 Compare July 18, 2025 21:34

caugonnet commented Jul 19, 2025

View reviewed changes

Comment thread cudax/include/cuda/experimental/__stf/internal/context.cuh

caugonnet force-pushed the stf_c_api branch from cc8c594 to f3b57da Compare July 20, 2025 08:03

caugonnet requested a review from a team as a code owner July 20, 2025 08:03

caugonnet requested a review from gonidelis July 20, 2025 08:03

caugonnet force-pushed the stf_c_api branch from 2ba0be7 to f06f72e Compare July 20, 2025 10:53

caugonnet requested a review from a team as a code owner July 23, 2025 16:14

caugonnet requested a review from kkraus14 July 23, 2025 16:14

caugonnet commented Jul 19, 2026

View reviewed changes

caugonnet and others added 4 commits July 19, 2026 08:47

caugonnet mentioned this pull request Jul 19, 2026

[STF] Support compound while-loop conditions in the C API #10006

Merged

2 tasks

caugonnet and others added 3 commits July 19, 2026 09:43

[STF] Note that the cuda_kernel doc snippet is an excerpt

61e7d3f

Point at the complete tested program in tests/stf/test_cuda_kernel.py so readers know where the undefined names (ctx, lX, kernel, ...) come from. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

[STF] Note that the numba_task doc snippet is an excerpt

93918dc

Same treatment as the cuda_kernel snippet: point at the complete tested program in tests/stf/interop/test_cuda_compute.py. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

[STF] Apply review nitpicks in Python tests

cbceed3

- test_from_context: importorskip("cupy") before device/green-context setup so a missing cupy skips without allocating a green context. - test_numba: drop dead return after pytest.skip(). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

coderabbitai Bot reviewed Jul 19, 2026

View reviewed changes

Comment thread ci/build_cuda_stf_python.sh

Comment thread docs/python/stf.rst

Comment thread python/cuda_stf/cuda/stf/_experimental/_cuda_version_utils.py

Comment thread python/cuda_stf/cuda/stf/_experimental/_stf_bindings_impl.pyx Outdated

caugonnet and others added 6 commits July 19, 2026 15:46

[STF] Point pytorch_task and jit doc snippets at their complete tests

9ef5687

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

[STF] Point the while_loop doc snippet at the complete cg.py solver

64db026

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Merge branch 'main' into stf_c_api

3e8b3fa

Merge branch 'main' into stf_c_api

a4032b0

coderabbitai Bot reviewed Jul 20, 2026

View reviewed changes

[STF] Fix stale docstring in graph_scope while_loop test

8dc1432

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

caugonnet commented Jul 20, 2026

View reviewed changes

caugonnet mentioned this pull request Jul 21, 2026

[STF] Expose geometry-aware allocation and native partition functions in the C API #10038

Merged

3 tasks

caugonnet force-pushed the stf_c_api branch from 411c010 to 4e3d6f4 Compare July 21, 2026 12:43

caugonnet and others added 3 commits July 21, 2026 17:10

[STF] Drop PR-history references from binding comments

de7befe

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Merge branch 'main' into stf_c_api

c0b8626

Uh oh!

Conversation

caugonnet commented Jul 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

What's in the PR (per-area breakdown)

Suggested reading order

Walkthrough of _stf_bindings_impl.pyx

Checklist

Uh oh!

copy-pr-bot Bot commented Jul 18, 2025

Uh oh!

caugonnet commented Jul 18, 2025

Uh oh!

caugonnet commented Jul 18, 2025

Uh oh!

caugonnet commented Jul 18, 2025

Uh oh!

github-actions Bot commented Jul 19, 2025

🟥 python: Pass: 0%/18 | Total: 18m 23s | Avg: 1m 01s | Max: 9m 23s

🟩 cub: Pass: 100%/50 | Total: 12h 24m | Avg: 14m 53s | Max: 43m 15s | Hits: 99%/61706

🟩 thrust: Pass: 100%/50 | Total: 9h 24m | Avg: 11m 17s | Max: 36m 32s | Hits: 99%/95621

🟩 libcudacxx: Pass: 100%/48 | Total: 10h 07m | Avg: 12m 39s | Max: 34m 35s | Hits: 92%/166828

🟩 cudax: Pass: 100%/28 | Total: 2h 37m | Avg: 5m 37s | Max: 12m 36s | Hits: 99%/15906

🟩 packaging: Pass: 100%/4 | Total: 12m 18s | Avg: 3m 04s | Max: 3m 22s

🟩 stdpar: Pass: 100%/4 | Total: 17m 30s | Avg: 4m 22s | Max: 4m 48s

🟩 cccl_c_parallel: Pass: 100%/3 | Total: 26m 19s | Avg: 8m 46s | Max: 14m 09s | Hits: 98%/501

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 205)

Uh oh!

caugonnet commented Jul 19, 2025

Uh oh!

Uh oh!

github-actions Bot commented Jul 19, 2025

🟥 python: Pass: 0%/18 | Total: 19m 10s | Avg: 1m 03s | Max: 9m 56s

🟨 libcudacxx: Pass: 97%/48 | Total: 9h 11m | Avg: 11m 28s | Max: 34m 17s | Hits: 94%/166807

🟩 cub: Pass: 100%/50 | Total: 12h 26m | Avg: 14m 55s | Max: 39m 22s | Hits: 99%/61706

🟩 thrust: Pass: 100%/50 | Total: 9h 20m | Avg: 11m 12s | Max: 37m 02s | Hits: 99%/95621

🟩 cudax: Pass: 100%/28 | Total: 5h 17m | Avg: 11m 20s | Max: 21m 47s | Hits: 85%/15906

🟩 packaging: Pass: 100%/4 | Total: 14m 55s | Avg: 3m 43s | Max: 4m 02s

🟩 stdpar: Pass: 100%/4 | Total: 16m 14s | Avg: 4m 03s | Max: 4m 24s

🟩 cccl_c_parallel: Pass: 100%/3 | Total: 28m 11s | Avg: 9m 23s | Max: 15m 03s | Hits: 98%/507

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 205)

Uh oh!

caugonnet commented Jul 20, 2025

Uh oh!

caugonnet commented Jul 20, 2025

Uh oh!

github-actions Bot commented Jul 20, 2025

🟥 python: Pass: 0%/18 | Total: 18m 25s | Avg: 1m 01s | Max: 9m 21s

🟥 cccl_c_parallel: Pass: 0%/3 | Total: 2m 07s | Avg: 0m 42s | Max: 2m 07s

🟩 cub: Pass: 100%/50 | Total: 12h 16m | Avg: 14m 43s | Max: 40m 23s | Hits: 99%/61956

🟩 thrust: Pass: 100%/50 | Total: 9h 24m | Avg: 11m 17s | Max: 35m 03s | Hits: 99%/95621

🟩 libcudacxx: Pass: 100%/48 | Total: 9h 19m | Avg: 11m 39s | Max: 34m 31s | Hits: 93%/166828

🟩 cudax: Pass: 100%/28 | Total: 5h 20m | Avg: 11m 26s | Max: 21m 35s | Hits: 84%/15954

🟩 packaging: Pass: 100%/4 | Total: 16m 23s | Avg: 4m 05s | Max: 4m 44s

🟩 stdpar: Pass: 100%/4 | Total: 15m 06s | Avg: 3m 46s | Max: 4m 01s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 205)

Uh oh!

caugonnet commented Jul 21, 2025

Uh oh!

github-actions Bot commented Jul 21, 2025

🟥 python: Pass: 0%/18 | Total: 18m 52s | Avg: 1m 02s | Max: 9m 56s

🟥 cccl_c_parallel: Pass: 0%/3 | Total: 2m 53s | Avg: 0m 57s | Max: 2m 53s

🟩 cub: Pass: 100%/50 | Total: 12h 45m | Avg: 15m 18s | Max: 45m 35s | Hits: 99%/61956

🟩 thrust: Pass: 100%/50 | Total: 9h 17m | Avg: 11m 08s | Max: 34m 07s | Hits: 99%/95621

🟩 libcudacxx: Pass: 100%/48 | Total: 8h 44m | Avg: 10m 55s | Max: 34m 02s | Hits: 96%/166828

🟩 cudax: Pass: 100%/28 | Total: 5h 17m | Avg: 11m 20s | Max: 22m 04s | Hits: 85%/15978

🟩 packaging: Pass: 100%/4 | Total: 14m 24s | Avg: 3m 36s | Max: 3m 47s

🟩 stdpar: Pass: 100%/4 | Total: 17m 21s | Avg: 4m 20s | Max: 4m 38s

👃 Inspect Changes

Modifications in project?

caugonnet commented Jul 18, 2025 •

edited

Loading

Walkthrough of `_stf_bindings_impl.pyx`

coderabbitai Bot commented Jul 19, 2026 •

edited

Loading

coderabbitai Bot commented Jul 20, 2026 •

edited

Loading