implement C++23 `byteswap` #3093

davebayer · 2024-12-09T14:34:49Z

This PR introduces C++23 std::byteswap to CCCL and makes it available back in C++11.

The implementation uses compiler intrinsics __builtin_bswap if available.

copy-pr-bot · 2024-12-09T14:34:54Z

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.

libcudacxx/include/cuda/std/__bit/byteswap.h

libcudacxx/include/cuda/std/__cccl/builtin.h

fbusato · 2024-12-09T18:07:18Z

there are some optimization opportunities, @davebayer would do you like to explore them? in this case, I can add some suggestions

davebayer · 2024-12-09T18:26:53Z

there are some optimization opportunities, @davebayer would do you like to explore them? in this case, I can add some suggestions

I wanted to do that in a separate PR, but sure, why not!

fbusato · 2024-12-09T18:36:21Z

perfect. I added a set of optimization for CUDA a while ago, and it also includes byteswap #2239

libcudacxx/include/cuda/std/__bit/byteswap.h

davebayer · 2024-12-10T07:41:19Z

perfect. I added a set of optimization for CUDA a while ago, and it also includes byteswap #2239

Thank you for the hint. I've implemented the optimized versions of 32-bit and 64-bit byte swap. The PTX output is now more or less identical to the clang-cuda builtin functions.

In case you are interested, here is the link to godbolt: https://godbolt.org/z/91eceT8so

libcudacxx/include/cuda/std/__bit/byteswap.h

miscco · 2024-12-10T10:05:31Z

/ok to test

…ation to save a register

miscco · 2024-12-10T12:35:51Z

/ok to test

github-actions · 2024-12-10T14:45:01Z

🟨 CI finished in 2h 07m: Pass: 93%/168 | Total: 3d 04h | Avg: 27m 27s | Max: 1h 15m | Hits: 61%/12600

🟨 libcudacxx: Pass: 77%/48 | Total: 9h 16m | Avg: 11m 35s | Max: 33m 50s

🔍 cudacxx_family: nvcc 🔍
  🟩 ClangCUDA          Pass: 100%/4   | Total:  1h 02m | Avg: 15m 37s | Max: 20m 37s
  🔍 nvcc               Pass:  75%/44  | Total:  8h 14m | Avg: 11m 13s | Max: 33m 50s
🔍 jobs: Build 🔍
  🔍 Build              Pass:  73%/41  | Total:  7h 07m | Avg: 10m 25s | Max: 33m 50s
  🟩 NVRTC              Pass: 100%/4   | Total:  1h 18m | Avg: 19m 42s | Max: 24m 21s
  🟩 Test               Pass: 100%/2   | Total: 48m 49s | Avg: 24m 24s | Max: 25m 43s
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s
🟨 cudacxx
  🟩 ClangCUDA18        Pass: 100%/4   | Total:  1h 02m | Avg: 15m 37s | Max: 20m 37s
  🟨 nvcc11.1           Pass:  42%/7   | Total:  1h 29m | Avg: 12m 45s | Max: 19m 09s
  🟥 nvcc12.5           Pass:   0%/2   | Total:  1h 04m | Avg: 32m 24s | Max: 33m 50s
  🟨 nvcc12.6           Pass:  85%/35  | Total:  5h 40m | Avg:  9m 42s | Max: 25m 43s
🟨 cxx
  🟨 Clang9             Pass:  75%/4   | Total: 44m 49s | Avg: 11m 12s | Max: 18m 56s
  🟩 Clang10            Pass: 100%/1   | Total:  7m 06s | Avg:  7m 06s | Max:  7m 06s
  🟩 Clang11            Pass: 100%/1   | Total:  6m 23s | Avg:  6m 23s | Max:  6m 23s
  🟩 Clang12            Pass: 100%/1   | Total:  6m 52s | Avg:  6m 52s | Max:  6m 52s
  🟩 Clang13            Pass: 100%/1   | Total:  6m 13s | Avg:  6m 13s | Max:  6m 13s
  🟩 Clang14            Pass: 100%/1   | Total:  6m 15s | Avg:  6m 15s | Max:  6m 15s
  🟩 Clang15            Pass: 100%/1   | Total:  6m 45s | Avg:  6m 45s | Max:  6m 45s
  🟩 Clang16            Pass: 100%/1   | Total:  7m 17s | Avg:  7m 17s | Max:  7m 17s
  🟩 Clang17            Pass: 100%/1   | Total:  6m 59s | Avg:  6m 59s | Max:  6m 59s
  🟨 Clang18            Pass:  87%/8   | Total:  1h 40m | Avg: 12m 34s | Max: 23m 06s
  🟨 GCC6               Pass:  50%/2   | Total: 23m 41s | Avg: 11m 50s | Max: 19m 09s
  🟩 GCC7               Pass: 100%/2   | Total: 15m 03s | Avg:  7m 31s | Max: 10m 26s
  🟩 GCC8               Pass: 100%/1   | Total:  5m 28s | Avg:  5m 28s | Max:  5m 28s
  🟨 GCC9               Pass:  66%/3   | Total: 30m 25s | Avg: 10m 08s | Max: 17m 48s
  🟩 GCC10              Pass: 100%/1   | Total:  6m 52s | Avg:  6m 52s | Max:  6m 52s
  🟩 GCC11              Pass: 100%/1   | Total:  6m 09s | Avg:  6m 09s | Max:  6m 09s
  🟩 GCC12              Pass: 100%/1   | Total:  6m 11s | Avg:  6m 11s | Max:  6m 11s
  🟩 GCC13              Pass: 100%/10  | Total:  2h 09m | Avg: 12m 57s | Max: 25m 43s
  🟥 Intel2023.2.0      Pass:   0%/1   | Total: 21m 58s | Avg: 21m 58s | Max: 21m 58s
  🟥 MSVC14.16          Pass:   0%/1   | Total: 16m 16s | Avg: 16m 16s | Max: 16m 16s
  🟥 MSVC14.29          Pass:   0%/1   | Total:  9m 10s | Avg:  9m 10s | Max:  9m 10s
  🟥 MSVC14.39          Pass:   0%/2   | Total: 21m 52s | Avg: 10m 56s | Max: 11m 12s
  🟥 NVHPC24.7          Pass:   0%/2   | Total:  1h 04m | Avg: 32m 24s | Max: 33m 50s
🟨 std
  🟩 11                 Pass: 100%/6   | Total:  1h 34m | Avg: 15m 49s | Max: 19m 09s
  🟨 14                 Pass:  60%/5   | Total: 50m 44s | Avg: 10m 08s | Max: 18m 03s
  🟨 17                 Pass:  53%/13  | Total:  2h 34m | Avg: 11m 52s | Max: 30m 58s
  🟨 20                 Pass:  86%/23  | Total:  4h 14m | Avg: 11m 04s | Max: 33m 50s
🟨 gpu
  🟨 v100               Pass:  77%/48  | Total:  9h 16m | Avg: 11m 35s | Max: 33m 50s
🟨 cpu
  🟨 amd64              Pass:  78%/46  | Total:  9h 08m | Avg: 11m 55s | Max: 33m 50s
  🟨 arm64              Pass:  50%/2   | Total:  7m 46s | Avg:  3m 53s | Max:  5m 29s
🟨 ctk
  🟨 11.1               Pass:  42%/7   | Total:  1h 29m | Avg: 12m 45s | Max: 19m 09s
  🟥 12.5               Pass:   0%/2   | Total:  1h 04m | Avg: 32m 24s | Max: 33m 50s
  🟨 12.6               Pass:  87%/39  | Total:  6h 42m | Avg: 10m 19s | Max: 25m 43s
🟨 cxx_family
  🟨 Clang              Pass:  90%/20  | Total:  3h 19m | Avg:  9m 57s | Max: 23m 06s
  🟨 GCC                Pass:  90%/21  | Total:  3h 43m | Avg: 10m 38s | Max: 25m 43s
  🟥 Intel              Pass:   0%/1   | Total: 21m 58s | Avg: 21m 58s | Max: 21m 58s
  🟥 MSVC               Pass:   0%/4   | Total: 47m 18s | Avg: 11m 49s | Max: 16m 16s
  🟥 NVHPC              Pass:   0%/2   | Total:  1h 04m | Avg: 32m 24s | Max: 33m 50s
🟩 sm
  🟩 90                 Pass: 100%/1   | Total: 11m 52s | Avg: 11m 52s | Max: 11m 52s
  🟩 90a                Pass: 100%/2   | Total: 17m 52s | Avg:  8m 56s | Max: 12m 53s

🟩 thrust: Pass: 100%/46 | Total: 1d 01h | Avg: 33m 07s | Max: 1h 15m | Hits: 70%/9260

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 49m 34s | Avg: 24m 47s | Max: 32m 47s
🟩 cpu
  🟩 amd64              Pass: 100%/44  | Total:  1d 00h | Avg: 33m 09s | Max:  1h 15m | Hits:  70%/9260  
  🟩 arm64              Pass: 100%/2   | Total:  1h 04m | Avg: 32m 29s | Max: 35m 35s
🟩 ctk
  🟩 11.1               Pass: 100%/7   | Total:  3h 33m | Avg: 30m 29s | Max: 54m 13s | Hits:  62%/1852  
  🟩 12.5               Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 53m 53s
  🟩 12.6               Pass: 100%/37  | Total: 20h 04m | Avg: 32m 32s | Max:  1h 15m | Hits:  71%/7408  
🟩 cudacxx
  🟩 ClangCUDA18        Pass: 100%/2   | Total:  1h 00m | Avg: 30m 07s | Max: 32m 01s
  🟩 nvcc11.1           Pass: 100%/7   | Total:  3h 33m | Avg: 30m 29s | Max: 54m 13s | Hits:  62%/1852  
  🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 53m 53s
  🟩 nvcc12.6           Pass: 100%/35  | Total: 19h 03m | Avg: 32m 41s | Max:  1h 15m | Hits:  71%/7408  
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total:  1h 00m | Avg: 30m 07s | Max: 32m 01s
  🟩 nvcc               Pass: 100%/44  | Total:  1d 00h | Avg: 33m 15s | Max:  1h 15m | Hits:  70%/9260  
🟩 cxx
  🟩 Clang9             Pass: 100%/4   | Total:  1h 57m | Avg: 29m 22s | Max: 34m 26s
  🟩 Clang10            Pass: 100%/1   | Total: 35m 01s | Avg: 35m 01s | Max: 35m 01s
  🟩 Clang11            Pass: 100%/1   | Total: 32m 51s | Avg: 32m 51s | Max: 32m 51s
  🟩 Clang12            Pass: 100%/1   | Total: 34m 59s | Avg: 34m 59s | Max: 34m 59s
  🟩 Clang13            Pass: 100%/1   | Total: 33m 08s | Avg: 33m 08s | Max: 33m 08s
  🟩 Clang14            Pass: 100%/1   | Total: 30m 32s | Avg: 30m 32s | Max: 30m 32s
  🟩 Clang15            Pass: 100%/1   | Total: 32m 18s | Avg: 32m 18s | Max: 32m 18s
  🟩 Clang16            Pass: 100%/1   | Total: 33m 59s | Avg: 33m 59s | Max: 33m 59s
  🟩 Clang17            Pass: 100%/1   | Total: 35m 37s | Avg: 35m 37s | Max: 35m 37s
  🟩 Clang18            Pass: 100%/7   | Total:  3h 03m | Avg: 26m 16s | Max: 36m 05s
  🟩 GCC6               Pass: 100%/2   | Total: 50m 13s | Avg: 25m 06s | Max: 26m 51s
  🟩 GCC7               Pass: 100%/2   | Total: 55m 41s | Avg: 27m 50s | Max: 30m 35s
  🟩 GCC8               Pass: 100%/1   | Total: 32m 50s | Avg: 32m 50s | Max: 32m 50s
  🟩 GCC9               Pass: 100%/3   | Total:  1h 28m | Avg: 29m 39s | Max: 34m 08s
  🟩 GCC10              Pass: 100%/1   | Total: 34m 05s | Avg: 34m 05s | Max: 34m 05s
  🟩 GCC11              Pass: 100%/1   | Total: 34m 05s | Avg: 34m 05s | Max: 34m 05s
  🟩 GCC12              Pass: 100%/1   | Total: 41m 28s | Avg: 41m 28s | Max: 41m 28s
  🟩 GCC13              Pass: 100%/8   | Total:  3h 21m | Avg: 25m 14s | Max: 42m 48s
  🟩 Intel2023.2.0      Pass: 100%/1   | Total: 40m 03s | Avg: 40m 03s | Max: 40m 03s
  🟩 MSVC14.16          Pass: 100%/1   | Total: 54m 13s | Avg: 54m 13s | Max: 54m 13s | Hits:  62%/1852  
  🟩 MSVC14.29          Pass: 100%/1   | Total: 54m 42s | Avg: 54m 42s | Max: 54m 42s | Hits:  62%/1852  
  🟩 MSVC14.39          Pass: 100%/3   | Total:  2h 39m | Avg: 53m 09s | Max:  1h 15m | Hits:  75%/5556  
  🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 53m 53s
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  9h 29m | Avg: 29m 59s | Max: 36m 05s
  🟩 GCC                Pass: 100%/19  | Total:  8h 59m | Avg: 28m 23s | Max: 42m 48s
  🟩 Intel              Pass: 100%/1   | Total: 40m 03s | Avg: 40m 03s | Max: 40m 03s
  🟩 MSVC               Pass: 100%/5   | Total:  4h 28m | Avg: 53m 40s | Max:  1h 15m | Hits:  70%/9260  
  🟩 NVHPC              Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 53m 53s
🟩 gpu
  🟩 v100               Pass: 100%/46  | Total:  1d 01h | Avg: 33m 07s | Max:  1h 15m | Hits:  70%/9260  
🟩 jobs
  🟩 Build              Pass: 100%/40  | Total:  1d 00h | Avg: 36m 01s | Max:  1h 15m | Hits:  62%/7408  
  🟩 TestCPU            Pass: 100%/3   | Total: 37m 34s | Avg: 12m 31s | Max: 21m 59s | Hits:  99%/1852  
  🟩 TestGPU            Pass: 100%/3   | Total: 45m 09s | Avg: 15m 03s | Max: 17m 40s
🟩 sm
  🟩 90a                Pass: 100%/1   | Total: 21m 47s | Avg: 21m 47s | Max: 21m 47s
🟩 std
  🟩 11                 Pass: 100%/5   | Total:  2h 05m | Avg: 25m 06s | Max: 28m 56s
  🟩 14                 Pass: 100%/4   | Total:  2h 26m | Avg: 36m 31s | Max: 54m 13s | Hits:  62%/1852  
  🟩 17                 Pass: 100%/12  | Total:  8h 01m | Avg: 40m 08s | Max:  1h 15m | Hits:  62%/3704  
  🟩 20                 Pass: 100%/23  | Total: 12h 01m | Avg: 31m 21s | Max:  1h 02m | Hits:  81%/3704

🟩 cub: Pass: 100%/45 | Total: 1d 15h | Avg: 52m 10s | Max: 1h 05m | Hits: 30%/3028

🟩 cpu
  🟩 amd64              Pass: 100%/43  | Total:  1d 13h | Avg: 51m 56s | Max:  1h 05m | Hits:  30%/3028  
  🟩 arm64              Pass: 100%/2   | Total:  1h 54m | Avg: 57m 16s | Max: 59m 21s
🟩 ctk
  🟩 11.1               Pass: 100%/7   | Total:  5h 55m | Avg: 50m 44s | Max:  1h 03m | Hits:  30%/757   
  🟩 12.5               Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 05m
  🟩 12.6               Pass: 100%/36  | Total:  1d 07h | Avg: 51m 43s | Max:  1h 05m | Hits:  30%/2271  
🟩 cudacxx
  🟩 ClangCUDA18        Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 01m
  🟩 nvcc11.1           Pass: 100%/7   | Total:  5h 55m | Avg: 50m 44s | Max:  1h 03m | Hits:  30%/757   
  🟩 nvcc12.5           Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 05m
  🟩 nvcc12.6           Pass: 100%/34  | Total:  1d 05h | Avg: 51m 11s | Max:  1h 05m | Hits:  30%/2271  
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 01m
  🟩 nvcc               Pass: 100%/43  | Total:  1d 13h | Avg: 51m 46s | Max:  1h 05m | Hits:  30%/3028  
🟩 cxx
  🟩 Clang9             Pass: 100%/4   | Total:  3h 19m | Avg: 49m 49s | Max: 55m 32s
  🟩 Clang10            Pass: 100%/1   | Total:  1h 00m | Avg:  1h 00m | Max:  1h 00m
  🟩 Clang11            Pass: 100%/1   | Total: 59m 29s | Avg: 59m 29s | Max: 59m 29s
  🟩 Clang12            Pass: 100%/1   | Total: 58m 06s | Avg: 58m 06s | Max: 58m 06s
  🟩 Clang13            Pass: 100%/1   | Total: 58m 29s | Avg: 58m 29s | Max: 58m 29s
  🟩 Clang14            Pass: 100%/1   | Total: 59m 02s | Avg: 59m 02s | Max: 59m 02s
  🟩 Clang15            Pass: 100%/1   | Total: 59m 48s | Avg: 59m 48s | Max: 59m 48s
  🟩 Clang16            Pass: 100%/1   | Total: 59m 06s | Avg: 59m 06s | Max: 59m 06s
  🟩 Clang17            Pass: 100%/1   | Total: 59m 52s | Avg: 59m 52s | Max: 59m 52s
  🟩 Clang18            Pass: 100%/7   | Total:  5h 23m | Avg: 46m 14s | Max:  1h 01m
  🟩 GCC6               Pass: 100%/2   | Total:  1h 47m | Avg: 53m 30s | Max:  1h 02m
  🟩 GCC7               Pass: 100%/2   | Total:  1h 47m | Avg: 53m 40s | Max: 55m 29s
  🟩 GCC8               Pass: 100%/1   | Total: 54m 46s | Avg: 54m 46s | Max: 54m 46s
  🟩 GCC9               Pass: 100%/3   | Total:  2h 28m | Avg: 49m 25s | Max: 54m 34s
  🟩 GCC10              Pass: 100%/1   | Total: 58m 00s | Avg: 58m 00s | Max: 58m 00s
  🟩 GCC11              Pass: 100%/1   | Total: 56m 53s | Avg: 56m 53s | Max: 56m 53s
  🟩 GCC12              Pass: 100%/1   | Total: 55m 55s | Avg: 55m 55s | Max: 55m 55s
  🟩 GCC13              Pass: 100%/8   | Total:  5h 20m | Avg: 40m 06s | Max:  1h 03m
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  1h 01m | Avg:  1h 01m | Max:  1h 01m
  🟩 MSVC14.16          Pass: 100%/1   | Total:  1h 03m | Avg:  1h 03m | Max:  1h 03m | Hits:  30%/757   
  🟩 MSVC14.29          Pass: 100%/1   | Total:  1h 00m | Avg:  1h 00m | Max:  1h 00m | Hits:  30%/757   
  🟩 MSVC14.39          Pass: 100%/2   | Total:  2h 05m | Avg:  1h 02m | Max:  1h 05m | Hits:  30%/1514  
  🟩 NVHPC24.7          Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 05m
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total: 16h 37m | Avg: 52m 29s | Max:  1h 01m
  🟩 GCC                Pass: 100%/19  | Total: 15h 09m | Avg: 47m 50s | Max:  1h 03m
  🟩 Intel              Pass: 100%/1   | Total:  1h 01m | Avg:  1h 01m | Max:  1h 01m
  🟩 MSVC               Pass: 100%/4   | Total:  4h 09m | Avg:  1h 02m | Max:  1h 05m | Hits:  30%/3028  
  🟩 NVHPC              Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 05m
🟩 gpu
  🟩 v100               Pass: 100%/45  | Total:  1d 15h | Avg: 52m 10s | Max:  1h 05m | Hits:  30%/3028  
🟩 jobs
  🟩 Build              Pass: 100%/39  | Total:  1d 12h | Avg: 56m 14s | Max:  1h 05m | Hits:  30%/3028  
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 17m 49s | Avg: 17m 49s | Max: 17m 49s
  🟩 GraphCapture       Pass: 100%/1   | Total: 17m 31s | Avg: 17m 31s | Max: 17m 31s
  🟩 HostLaunch         Pass: 100%/2   | Total: 36m 44s | Avg: 18m 22s | Max: 20m 43s
  🟩 TestGPU            Pass: 100%/2   | Total:  1h 22m | Avg: 41m 13s | Max:  1h 02m
🟩 sm
  🟩 90a                Pass: 100%/1   | Total: 24m 35s | Avg: 24m 35s | Max: 24m 35s
🟩 std
  🟩 11                 Pass: 100%/5   | Total:  4h 00m | Avg: 48m 11s | Max: 53m 09s
  🟩 14                 Pass: 100%/4   | Total:  3h 57m | Avg: 59m 16s | Max:  1h 03m | Hits:  30%/757   
  🟩 17                 Pass: 100%/12  | Total: 11h 23m | Avg: 56m 56s | Max:  1h 05m | Hits:  30%/1514  
  🟩 20                 Pass: 100%/24  | Total: 19h 46m | Avg: 49m 25s | Max:  1h 05m | Hits:  29%/757

🟩 cudax: Pass: 100%/26 | Total: 2h 30m | Avg: 5m 46s | Max: 23m 03s | Hits: 90%/312

🟩 cpu
  🟩 amd64              Pass: 100%/22  | Total:  2h 16m | Avg:  6m 11s | Max: 23m 03s | Hits:  90%/312   
  🟩 arm64              Pass: 100%/4   | Total: 13m 53s | Avg:  3m 28s | Max:  3m 30s
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 15m 38s | Avg:  5m 12s | Max:  8m 41s | Hits:  90%/156   
  🟩 12.5               Pass: 100%/2   | Total: 12m 08s | Avg:  6m 04s | Max:  6m 16s
  🟩 12.6               Pass: 100%/21  | Total:  2h 02m | Avg:  5m 49s | Max: 23m 03s | Hits:  90%/156   
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 15m 38s | Avg:  5m 12s | Max:  8m 41s | Hits:  90%/156   
  🟩 nvcc12.5           Pass: 100%/2   | Total: 12m 08s | Avg:  6m 04s | Max:  6m 16s
  🟩 nvcc12.6           Pass: 100%/21  | Total:  2h 02m | Avg:  5m 49s | Max: 23m 03s | Hits:  90%/156   
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/26  | Total:  2h 30m | Avg:  5m 46s | Max: 23m 03s | Hits:  90%/312   
🟩 cxx
  🟩 Clang9             Pass: 100%/1   | Total:  3m 32s | Avg:  3m 32s | Max:  3m 32s
  🟩 Clang10            Pass: 100%/1   | Total:  4m 38s | Avg:  4m 38s | Max:  4m 38s
  🟩 Clang11            Pass: 100%/1   | Total:  3m 56s | Avg:  3m 56s | Max:  3m 56s
  🟩 Clang12            Pass: 100%/1   | Total:  3m 35s | Avg:  3m 35s | Max:  3m 35s
  🟩 Clang13            Pass: 100%/1   | Total:  3m 43s | Avg:  3m 43s | Max:  3m 43s
  🟩 Clang14            Pass: 100%/1   | Total:  3m 39s | Avg:  3m 39s | Max:  3m 39s
  🟩 Clang15            Pass: 100%/1   | Total:  3m 57s | Avg:  3m 57s | Max:  3m 57s
  🟩 Clang16            Pass: 100%/1   | Total:  4m 03s | Avg:  4m 03s | Max:  4m 03s
  🟩 Clang17            Pass: 100%/1   | Total:  4m 06s | Avg:  4m 06s | Max:  4m 06s
  🟩 Clang18            Pass: 100%/4   | Total: 33m 42s | Avg:  8m 25s | Max: 22m 39s
  🟩 GCC9               Pass: 100%/1   | Total:  3m 25s | Avg:  3m 25s | Max:  3m 25s
  🟩 GCC10              Pass: 100%/1   | Total:  3m 47s | Avg:  3m 47s | Max:  3m 47s
  🟩 GCC11              Pass: 100%/1   | Total:  3m 58s | Avg:  3m 58s | Max:  3m 58s
  🟩 GCC12              Pass: 100%/2   | Total: 26m 42s | Avg: 13m 21s | Max: 23m 03s
  🟩 GCC13              Pass: 100%/4   | Total: 13m 16s | Avg:  3m 19s | Max:  3m 30s
  🟩 MSVC14.36          Pass: 100%/1   | Total:  8m 41s | Avg:  8m 41s | Max:  8m 41s | Hits:  90%/156   
  🟩 MSVC14.39          Pass: 100%/1   | Total:  9m 16s | Avg:  9m 16s | Max:  9m 16s | Hits:  90%/156   
  🟩 NVHPC24.7          Pass: 100%/2   | Total: 12m 08s | Avg:  6m 04s | Max:  6m 16s
🟩 cxx_family
  🟩 Clang              Pass: 100%/13  | Total:  1h 08m | Avg:  5m 17s | Max: 22m 39s
  🟩 GCC                Pass: 100%/9   | Total: 51m 08s | Avg:  5m 40s | Max: 23m 03s
  🟩 MSVC               Pass: 100%/2   | Total: 17m 57s | Avg:  8m 58s | Max:  9m 16s | Hits:  90%/312   
  🟩 NVHPC              Pass: 100%/2   | Total: 12m 08s | Avg:  6m 04s | Max:  6m 16s
🟩 gpu
  🟩 v100               Pass: 100%/26  | Total:  2h 30m | Avg:  5m 46s | Max: 23m 03s | Hits:  90%/312   
🟩 jobs
  🟩 Build              Pass: 100%/24  | Total:  1h 44m | Avg:  4m 20s | Max:  9m 16s | Hits:  90%/312   
  🟩 Test               Pass: 100%/2   | Total: 45m 42s | Avg: 22m 51s | Max: 23m 03s
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  2m 57s | Avg:  2m 57s | Max:  2m 57s
  🟩 90a                Pass: 100%/1   | Total:  3m 25s | Avg:  3m 25s | Max:  3m 25s
🟩 std
  🟩 17                 Pass: 100%/6   | Total: 23m 04s | Avg:  3m 50s | Max:  6m 16s
  🟩 20                 Pass: 100%/20  | Total:  2h 07m | Avg:  6m 21s | Max: 23m 03s | Hits:  90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 9m 11s | Avg: 4m 35s | Max: 7m 02s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 ctk
  🟩 12.6               Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 cudacxx
  🟩 nvcc12.6           Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 cxx
  🟩 GCC13              Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 cxx_family
  🟩 GCC                Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 gpu
  🟩 v100               Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  7m 02s
🟩 jobs
  🟩 Build              Pass: 100%/1   | Total:  2m 09s | Avg:  2m 09s | Max:  2m 09s
  🟩 Test               Pass: 100%/1   | Total:  7m 02s | Avg:  7m 02s | Max:  7m 02s

🟩 python: Pass: 100%/1 | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 ctk
  🟩 12.6               Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 cudacxx
  🟩 nvcc12.6           Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 168)

#	Runner
124	`linux-amd64-cpu16`
19	`linux-amd64-gpu-v100-latest-1`
15	`windows-amd64-cpu16`
10	`linux-arm64-cpu16`

…ts warning

miscco · 2024-12-11T08:19:49Z

/ok to test

github-actions · 2024-12-11T09:59:58Z

🟨 CI finished in 1h 38m: Pass: 98%/168 | Total: 1d 21h | Avg: 16m 05s | Max: 1h 11m | Hits: 48%/22354

🟨 libcudacxx: Pass: 93%/48 | Total: 10h 12m | Avg: 12m 45s | Max: 37m 50s | Hits: 31%/9754

🔍 cpu: amd64 🔍
  🔍 amd64              Pass:  93%/46  | Total: 10h 01m | Avg: 13m 04s | Max: 37m 50s | Hits:  31%/9754  
  🟩 arm64              Pass: 100%/2   | Total: 11m 03s | Avg:  5m 31s | Max:  5m 35s
🔍 ctk: 11.1 🔍
  🔍 11.1               Pass:  57%/7   | Total:  1h 37m | Avg: 13m 56s | Max: 27m 50s | Hits:  34%/2215  
  🟩 12.5               Pass: 100%/2   | Total: 23m 00s | Avg: 11m 30s | Max: 11m 44s
  🟩 12.6               Pass: 100%/39  | Total:  8h 12m | Avg: 12m 36s | Max: 37m 50s | Hits:  30%/7539  
🔍 cudacxx: nvcc11.1 🔍
  🟩 ClangCUDA18        Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 21m 31s
  🔍 nvcc11.1           Pass:  57%/7   | Total:  1h 37m | Avg: 13m 56s | Max: 27m 50s | Hits:  34%/2215  
  🟩 nvcc12.5           Pass: 100%/2   | Total: 23m 00s | Avg: 11m 30s | Max: 11m 44s
  🟩 nvcc12.6           Pass: 100%/35  | Total:  7h 08m | Avg: 12m 14s | Max: 37m 50s | Hits:  30%/7539  
🔍 cudacxx_family: nvcc 🔍
  🟩 ClangCUDA          Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 21m 31s
  🔍 nvcc               Pass:  93%/44  | Total:  9h 08m | Avg: 12m 28s | Max: 37m 50s | Hits:  31%/9754  
🔍 jobs: Build 🔍
  🔍 Build              Pass:  92%/41  | Total:  7h 49m | Avg: 11m 27s | Max: 37m 50s | Hits:  31%/9754  
  🟩 NVRTC              Pass: 100%/4   | Total:  1h 35m | Avg: 23m 45s | Max: 28m 50s
  🟩 Test               Pass: 100%/2   | Total: 45m 45s | Avg: 22m 52s | Max: 24m 22s
  🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 59s | Avg:  1m 59s | Max:  1m 59s
🟨 cxx
  🟨 Clang9             Pass:  75%/4   | Total: 44m 05s | Avg: 11m 01s | Max: 17m 37s
  🟩 Clang10            Pass: 100%/1   | Total:  7m 01s | Avg:  7m 01s | Max:  7m 01s
  🟩 Clang11            Pass: 100%/1   | Total:  6m 53s | Avg:  6m 53s | Max:  6m 53s
  🟩 Clang12            Pass: 100%/1   | Total:  7m 04s | Avg:  7m 04s | Max:  7m 04s
  🟩 Clang13            Pass: 100%/1   | Total:  6m 55s | Avg:  6m 55s | Max:  6m 55s
  🟩 Clang14            Pass: 100%/1   | Total:  7m 01s | Avg:  7m 01s | Max:  7m 01s
  🟩 Clang15            Pass: 100%/1   | Total:  6m 25s | Avg:  6m 25s | Max:  6m 25s
  🟩 Clang16            Pass: 100%/1   | Total:  6m 40s | Avg:  6m 40s | Max:  6m 40s
  🟩 Clang17            Pass: 100%/1   | Total:  7m 03s | Avg:  7m 03s | Max:  7m 03s
  🟩 Clang18            Pass: 100%/8   | Total:  1h 47m | Avg: 13m 29s | Max: 24m 22s
  🟨 GCC6               Pass:  50%/2   | Total: 20m 35s | Avg: 10m 17s | Max: 17m 44s
  🟩 GCC7               Pass: 100%/2   | Total:  8m 38s | Avg:  4m 19s | Max:  5m 19s
  🟩 GCC8               Pass: 100%/1   | Total:  5m 29s | Avg:  5m 29s | Max:  5m 29s
  🟨 GCC9               Pass:  66%/3   | Total: 30m 55s | Avg: 10m 18s | Max: 17m 21s
  🟩 GCC10              Pass: 100%/1   | Total:  6m 49s | Avg:  6m 49s | Max:  6m 49s
  🟩 GCC11              Pass: 100%/1   | Total:  6m 10s | Avg:  6m 10s | Max:  6m 10s
  🟩 GCC12              Pass: 100%/1   | Total:  6m 48s | Avg:  6m 48s | Max:  6m 48s
  🟩 GCC13              Pass: 100%/10  | Total:  2h 20m | Avg: 14m 03s | Max: 28m 50s
  🟩 Intel2023.2.0      Pass: 100%/1   | Total: 24m 27s | Avg: 24m 27s | Max: 24m 27s
  🟩 MSVC14.16          Pass: 100%/1   | Total: 27m 50s | Avg: 27m 50s | Max: 27m 50s | Hits:  34%/2215  
  🟩 MSVC14.29          Pass: 100%/1   | Total: 33m 36s | Avg: 33m 36s | Max: 33m 36s | Hits:  30%/2464  
  🟩 MSVC14.39          Pass: 100%/2   | Total:  1h 10m | Avg: 35m 16s | Max: 37m 50s | Hits:  30%/5075  
  🟩 NVHPC24.7          Pass: 100%/2   | Total: 23m 00s | Avg: 11m 30s | Max: 11m 44s
🟨 cxx_family
  🟨 Clang              Pass:  95%/20  | Total:  3h 27m | Avg: 10m 21s | Max: 24m 22s
  🟨 GCC                Pass:  90%/21  | Total:  3h 46m | Avg: 10m 45s | Max: 28m 50s
  🟩 Intel              Pass: 100%/1   | Total: 24m 27s | Avg: 24m 27s | Max: 24m 27s
  🟩 MSVC               Pass: 100%/4   | Total:  2h 11m | Avg: 32m 59s | Max: 37m 50s | Hits:  31%/9754  
  🟩 NVHPC              Pass: 100%/2   | Total: 23m 00s | Avg: 11m 30s | Max: 11m 44s
🟨 std
  🟩 11                 Pass: 100%/6   | Total:  1h 31m | Avg: 15m 19s | Max: 23m 37s
  🟨 14                 Pass:  80%/5   | Total:  1h 02m | Avg: 12m 34s | Max: 27m 50s | Hits:  34%/2215  
  🟨 17                 Pass:  84%/13  | Total:  3h 10m | Avg: 14m 37s | Max: 33m 36s | Hits:  30%/4928  
  🟩 20                 Pass: 100%/23  | Total:  4h 25m | Avg: 11m 33s | Max: 37m 50s | Hits:  29%/2611  
🟨 gpu
  🟨 v100               Pass:  93%/48  | Total: 10h 12m | Avg: 12m 45s | Max: 37m 50s | Hits:  31%/9754  
🟩 sm
  🟩 90                 Pass: 100%/1   | Total: 12m 31s | Avg: 12m 31s | Max: 12m 31s
  🟩 90a                Pass: 100%/2   | Total: 15m 45s | Avg:  7m 52s | Max: 11m 38s

🟩 thrust: Pass: 100%/46 | Total: 13h 41m | Avg: 17m 50s | Max: 1h 11m | Hits: 70%/9260

🟩 cmake_options
  🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 17m 37s | Avg:  8m 48s | Max: 12m 02s
🟩 cpu
  🟩 amd64              Pass: 100%/44  | Total: 13h 31m | Avg: 18m 26s | Max:  1h 11m | Hits:  70%/9260  
  🟩 arm64              Pass: 100%/2   | Total:  9m 49s | Avg:  4m 54s | Max:  5m 14s
🟩 ctk
  🟩 11.1               Pass: 100%/7   | Total:  2h 03m | Avg: 17m 37s | Max: 57m 26s | Hits:  62%/1852  
  🟩 12.5               Pass: 100%/2   | Total:  1h 54m | Avg: 57m 00s | Max: 59m 57s
  🟩 12.6               Pass: 100%/37  | Total:  9h 43m | Avg: 15m 46s | Max:  1h 11m | Hits:  71%/7408  
🟩 cudacxx
  🟩 ClangCUDA18        Pass: 100%/2   | Total: 10m 01s | Avg:  5m 00s | Max:  5m 11s
  🟩 nvcc11.1           Pass: 100%/7   | Total:  2h 03m | Avg: 17m 37s | Max: 57m 26s | Hits:  62%/1852  
  🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 54m | Avg: 57m 00s | Max: 59m 57s
  🟩 nvcc12.6           Pass: 100%/35  | Total:  9h 33m | Avg: 16m 23s | Max:  1h 11m | Hits:  71%/7408  
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 01s | Avg:  5m 00s | Max:  5m 11s
  🟩 nvcc               Pass: 100%/44  | Total: 13h 31m | Avg: 18m 25s | Max:  1h 11m | Hits:  70%/9260  
🟩 cxx
  🟩 Clang9             Pass: 100%/4   | Total:  1h 49m | Avg: 27m 20s | Max: 35m 12s
  🟩 Clang10            Pass: 100%/1   | Total: 34m 45s | Avg: 34m 45s | Max: 34m 45s
  🟩 Clang11            Pass: 100%/1   | Total: 31m 33s | Avg: 31m 33s | Max: 31m 33s
  🟩 Clang12            Pass: 100%/1   | Total: 33m 14s | Avg: 33m 14s | Max: 33m 14s
  🟩 Clang13            Pass: 100%/1   | Total: 31m 21s | Avg: 31m 21s | Max: 31m 21s
  🟩 Clang14            Pass: 100%/1   | Total:  5m 34s | Avg:  5m 34s | Max:  5m 34s
  🟩 Clang15            Pass: 100%/1   | Total:  5m 49s | Avg:  5m 49s | Max:  5m 49s
  🟩 Clang16            Pass: 100%/1   | Total:  5m 17s | Avg:  5m 17s | Max:  5m 17s
  🟩 Clang17            Pass: 100%/1   | Total:  5m 43s | Avg:  5m 43s | Max:  5m 43s
  🟩 Clang18            Pass: 100%/7   | Total: 45m 10s | Avg:  6m 27s | Max: 11m 58s
  🟩 GCC6               Pass: 100%/2   | Total:  8m 10s | Avg:  4m 05s | Max:  4m 07s
  🟩 GCC7               Pass: 100%/2   | Total:  9m 55s | Avg:  4m 57s | Max:  5m 20s
  🟩 GCC8               Pass: 100%/1   | Total:  5m 28s | Avg:  5m 28s | Max:  5m 28s
  🟩 GCC9               Pass: 100%/3   | Total: 14m 24s | Avg:  4m 48s | Max:  5m 41s
  🟩 GCC10              Pass: 100%/1   | Total:  5m 15s | Avg:  5m 15s | Max:  5m 15s
  🟩 GCC11              Pass: 100%/1   | Total:  5m 37s | Avg:  5m 37s | Max:  5m 37s
  🟩 GCC12              Pass: 100%/1   | Total:  5m 56s | Avg:  5m 56s | Max:  5m 56s
  🟩 GCC13              Pass: 100%/8   | Total:  1h 02m | Avg:  7m 48s | Max: 15m 33s
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  6m 40s | Avg:  6m 40s | Max:  6m 40s
  🟩 MSVC14.16          Pass: 100%/1   | Total: 57m 26s | Avg: 57m 26s | Max: 57m 26s | Hits:  62%/1852  
  🟩 MSVC14.29          Pass: 100%/1   | Total:  1h 01m | Avg:  1h 01m | Max:  1h 01m | Hits:  62%/1852  
  🟩 MSVC14.39          Pass: 100%/3   | Total:  2h 36m | Avg: 52m 11s | Max:  1h 11m | Hits:  75%/5556  
  🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 54m | Avg: 57m 00s | Max: 59m 57s
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  5h 07m | Avg: 16m 12s | Max: 35m 12s
  🟩 GCC                Pass: 100%/19  | Total:  1h 57m | Avg:  6m 10s | Max: 15m 33s
  🟩 Intel              Pass: 100%/1   | Total:  6m 40s | Avg:  6m 40s | Max:  6m 40s
  🟩 MSVC               Pass: 100%/5   | Total:  4h 35m | Avg: 55m 03s | Max:  1h 11m | Hits:  70%/9260  
  🟩 NVHPC              Pass: 100%/2   | Total:  1h 54m | Avg: 57m 00s | Max: 59m 57s
🟩 gpu
  🟩 v100               Pass: 100%/46  | Total: 13h 41m | Avg: 17m 50s | Max:  1h 11m | Hits:  70%/9260  
🟩 jobs
  🟩 Build              Pass: 100%/40  | Total: 12h 23m | Avg: 18m 35s | Max:  1h 11m | Hits:  62%/7408  
  🟩 TestCPU            Pass: 100%/3   | Total: 38m 01s | Avg: 12m 40s | Max: 22m 34s | Hits:  99%/1852  
  🟩 TestGPU            Pass: 100%/3   | Total: 39m 33s | Avg: 13m 11s | Max: 15m 33s
🟩 sm
  🟩 90a                Pass: 100%/1   | Total:  4m 32s | Avg:  4m 32s | Max:  4m 32s
🟩 std
  🟩 11                 Pass: 100%/5   | Total: 58m 35s | Avg: 11m 43s | Max: 25m 08s
  🟩 14                 Pass: 100%/4   | Total:  1h 42m | Avg: 25m 31s | Max: 57m 26s | Hits:  62%/1852  
  🟩 17                 Pass: 100%/12  | Total:  4h 39m | Avg: 23m 19s | Max:  1h 02m | Hits:  62%/3704  
  🟩 20                 Pass: 100%/23  | Total:  6h 02m | Avg: 15m 46s | Max:  1h 11m | Hits:  81%/3704

🟩 cub: Pass: 100%/45 | Total: 18h 15m | Avg: 24m 20s | Max: 1h 06m | Hits: 30%/3028

🟩 cpu
  🟩 amd64              Pass: 100%/43  | Total: 18h 06m | Avg: 25m 15s | Max:  1h 06m | Hits:  30%/3028  
  🟩 arm64              Pass: 100%/2   | Total:  9m 28s | Avg:  4m 44s | Max:  4m 53s
🟩 ctk
  🟩 11.1               Pass: 100%/7   | Total:  3h 08m | Avg: 26m 56s | Max:  1h 02m | Hits:  30%/757   
  🟩 12.5               Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m
  🟩 12.6               Pass: 100%/36  | Total: 12h 58m | Avg: 21m 37s | Max:  1h 06m | Hits:  30%/2271  
🟩 cudacxx
  🟩 ClangCUDA18        Pass: 100%/2   | Total:  8m 48s | Avg:  4m 24s | Max:  4m 32s
  🟩 nvcc11.1           Pass: 100%/7   | Total:  3h 08m | Avg: 26m 56s | Max:  1h 02m | Hits:  30%/757   
  🟩 nvcc12.5           Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m
  🟩 nvcc12.6           Pass: 100%/34  | Total: 12h 49m | Avg: 22m 37s | Max:  1h 06m | Hits:  30%/2271  
🟩 cudacxx_family
  🟩 ClangCUDA          Pass: 100%/2   | Total:  8m 48s | Avg:  4m 24s | Max:  4m 32s
  🟩 nvcc               Pass: 100%/43  | Total: 18h 06m | Avg: 25m 16s | Max:  1h 06m | Hits:  30%/3028  
🟩 cxx
  🟩 Clang9             Pass: 100%/4   | Total:  3h 37m | Avg: 54m 17s | Max: 58m 26s
  🟩 Clang10            Pass: 100%/1   | Total: 54m 58s | Avg: 54m 58s | Max: 54m 58s
  🟩 Clang11            Pass: 100%/1   | Total: 55m 31s | Avg: 55m 31s | Max: 55m 31s
  🟩 Clang12            Pass: 100%/1   | Total: 52m 09s | Avg: 52m 09s | Max: 52m 09s
  🟩 Clang13            Pass: 100%/1   | Total: 57m 47s | Avg: 57m 47s | Max: 57m 47s
  🟩 Clang14            Pass: 100%/1   | Total:  5m 29s | Avg:  5m 29s | Max:  5m 29s
  🟩 Clang15            Pass: 100%/1   | Total:  5m 27s | Avg:  5m 27s | Max:  5m 27s
  🟩 Clang16            Pass: 100%/1   | Total:  5m 16s | Avg:  5m 16s | Max:  5m 16s
  🟩 Clang17            Pass: 100%/1   | Total:  5m 30s | Avg:  5m 30s | Max:  5m 30s
  🟩 Clang18            Pass: 100%/7   | Total:  1h 12m | Avg: 10m 18s | Max: 29m 07s
  🟩 GCC6               Pass: 100%/2   | Total:  8m 27s | Avg:  4m 13s | Max:  4m 26s
  🟩 GCC7               Pass: 100%/2   | Total: 10m 33s | Avg:  5m 16s | Max:  5m 25s
  🟩 GCC8               Pass: 100%/1   | Total:  5m 19s | Avg:  5m 19s | Max:  5m 19s
  🟩 GCC9               Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 26s
  🟩 GCC10              Pass: 100%/1   | Total:  5m 40s | Avg:  5m 40s | Max:  5m 40s
  🟩 GCC11              Pass: 100%/1   | Total:  5m 30s | Avg:  5m 30s | Max:  5m 30s
  🟩 GCC12              Pass: 100%/1   | Total:  5m 48s | Avg:  5m 48s | Max:  5m 48s
  🟩 GCC13              Pass: 100%/8   | Total:  1h 56m | Avg: 14m 34s | Max: 28m 28s
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  6m 27s | Avg:  6m 27s | Max:  6m 27s
  🟩 MSVC14.16          Pass: 100%/1   | Total:  1h 02m | Avg:  1h 02m | Max:  1h 02m | Hits:  30%/757   
  🟩 MSVC14.29          Pass: 100%/1   | Total:  1h 03m | Avg:  1h 03m | Max:  1h 03m | Hits:  30%/757   
  🟩 MSVC14.39          Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 06m | Hits:  30%/1514  
  🟩 NVHPC24.7          Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m
🟩 cxx_family
  🟩 Clang              Pass: 100%/19  | Total:  8h 51m | Avg: 27m 58s | Max: 58m 26s
  🟩 GCC                Pass: 100%/19  | Total:  2h 51m | Avg:  9m 03s | Max: 28m 28s
  🟩 Intel              Pass: 100%/1   | Total:  6m 27s | Avg:  6m 27s | Max:  6m 27s
  🟩 MSVC               Pass: 100%/4   | Total:  4h 16m | Avg:  1h 04m | Max:  1h 06m | Hits:  30%/3028  
  🟩 NVHPC              Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m
🟩 gpu
  🟩 v100               Pass: 100%/45  | Total: 18h 15m | Avg: 24m 20s | Max:  1h 06m | Hits:  30%/3028  
🟩 jobs
  🟩 Build              Pass: 100%/39  | Total: 15h 52m | Avg: 24m 25s | Max:  1h 06m | Hits:  30%/3028  
  🟩 DeviceLaunch       Pass: 100%/1   | Total: 28m 15s | Avg: 28m 15s | Max: 28m 15s
  🟩 GraphCapture       Pass: 100%/1   | Total: 16m 31s | Avg: 16m 31s | Max: 16m 31s
  🟩 HostLaunch         Pass: 100%/2   | Total: 47m 13s | Avg: 23m 36s | Max: 28m 28s
  🟩 TestGPU            Pass: 100%/2   | Total: 50m 51s | Avg: 25m 25s | Max: 29m 07s
🟩 sm
  🟩 90a                Pass: 100%/1   | Total:  4m 12s | Avg:  4m 12s | Max:  4m 12s
🟩 std
  🟩 11                 Pass: 100%/5   | Total:  2h 03m | Avg: 24m 46s | Max: 58m 26s
  🟩 14                 Pass: 100%/4   | Total:  2h 09m | Avg: 32m 15s | Max:  1h 02m | Hits:  30%/757   
  🟩 17                 Pass: 100%/12  | Total:  5h 34m | Avg: 27m 50s | Max:  1h 04m | Hits:  30%/1514  
  🟩 20                 Pass: 100%/24  | Total:  8h 28m | Avg: 21m 11s | Max:  1h 06m | Hits:  29%/757

🟩 cudax: Pass: 100%/26 | Total: 2h 14m | Avg: 5m 10s | Max: 21m 02s | Hits: 90%/312

🟩 cpu
  🟩 amd64              Pass: 100%/22  | Total:  2h 04m | Avg:  5m 38s | Max: 21m 02s | Hits:  90%/312   
  🟩 arm64              Pass: 100%/4   | Total: 10m 28s | Avg:  2m 37s | Max:  2m 44s
🟩 ctk
  🟩 12.0               Pass: 100%/3   | Total: 15m 12s | Avg:  5m 04s | Max:  9m 06s | Hits:  90%/156   
  🟩 12.5               Pass: 100%/2   | Total: 11m 37s | Avg:  5m 48s | Max:  5m 51s
  🟩 12.6               Pass: 100%/21  | Total:  1h 47m | Avg:  5m 07s | Max: 21m 02s | Hits:  90%/156   
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/3   | Total: 15m 12s | Avg:  5m 04s | Max:  9m 06s | Hits:  90%/156   
  🟩 nvcc12.5           Pass: 100%/2   | Total: 11m 37s | Avg:  5m 48s | Max:  5m 51s
  🟩 nvcc12.6           Pass: 100%/21  | Total:  1h 47m | Avg:  5m 07s | Max: 21m 02s | Hits:  90%/156   
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/26  | Total:  2h 14m | Avg:  5m 10s | Max: 21m 02s | Hits:  90%/312   
🟩 cxx
  🟩 Clang9             Pass: 100%/1   | Total:  3m 24s | Avg:  3m 24s | Max:  3m 24s
  🟩 Clang10            Pass: 100%/1   | Total:  4m 09s | Avg:  4m 09s | Max:  4m 09s
  🟩 Clang11            Pass: 100%/1   | Total:  3m 53s | Avg:  3m 53s | Max:  3m 53s
  🟩 Clang12            Pass: 100%/1   | Total:  3m 35s | Avg:  3m 35s | Max:  3m 35s
  🟩 Clang13            Pass: 100%/1   | Total:  3m 38s | Avg:  3m 38s | Max:  3m 38s
  🟩 Clang14            Pass: 100%/1   | Total:  3m 01s | Avg:  3m 01s | Max:  3m 01s
  🟩 Clang15            Pass: 100%/1   | Total:  3m 23s | Avg:  3m 23s | Max:  3m 23s
  🟩 Clang16            Pass: 100%/1   | Total:  3m 07s | Avg:  3m 07s | Max:  3m 07s
  🟩 Clang17            Pass: 100%/1   | Total:  3m 14s | Avg:  3m 14s | Max:  3m 14s
  🟩 Clang18            Pass: 100%/4   | Total: 28m 07s | Avg:  7m 01s | Max: 19m 40s
  🟩 GCC9               Pass: 100%/1   | Total:  2m 42s | Avg:  2m 42s | Max:  2m 42s
  🟩 GCC10              Pass: 100%/1   | Total:  3m 42s | Avg:  3m 42s | Max:  3m 42s
  🟩 GCC11              Pass: 100%/1   | Total:  2m 56s | Avg:  2m 56s | Max:  2m 56s
  🟩 GCC12              Pass: 100%/2   | Total: 24m 14s | Avg: 12m 07s | Max: 21m 02s
  🟩 GCC13              Pass: 100%/4   | Total: 10m 39s | Avg:  2m 39s | Max:  2m 49s
  🟩 MSVC14.36          Pass: 100%/1   | Total:  9m 06s | Avg:  9m 06s | Max:  9m 06s | Hits:  90%/156   
  🟩 MSVC14.39          Pass: 100%/1   | Total: 10m 06s | Avg: 10m 06s | Max: 10m 06s | Hits:  90%/156   
  🟩 NVHPC24.7          Pass: 100%/2   | Total: 11m 37s | Avg:  5m 48s | Max:  5m 51s
🟩 cxx_family
  🟩 Clang              Pass: 100%/13  | Total: 59m 31s | Avg:  4m 34s | Max: 19m 40s
  🟩 GCC                Pass: 100%/9   | Total: 44m 13s | Avg:  4m 54s | Max: 21m 02s
  🟩 MSVC               Pass: 100%/2   | Total: 19m 12s | Avg:  9m 36s | Max: 10m 06s | Hits:  90%/312   
  🟩 NVHPC              Pass: 100%/2   | Total: 11m 37s | Avg:  5m 48s | Max:  5m 51s
🟩 gpu
  🟩 v100               Pass: 100%/26  | Total:  2h 14m | Avg:  5m 10s | Max: 21m 02s | Hits:  90%/312   
🟩 jobs
  🟩 Build              Pass: 100%/24  | Total:  1h 33m | Avg:  3m 54s | Max: 10m 06s | Hits:  90%/312   
  🟩 Test               Pass: 100%/2   | Total: 40m 42s | Avg: 20m 21s | Max: 21m 02s
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  2m 49s | Avg:  2m 49s | Max:  2m 49s
  🟩 90a                Pass: 100%/1   | Total:  2m 46s | Avg:  2m 46s | Max:  2m 46s
🟩 std
  🟩 17                 Pass: 100%/6   | Total: 20m 02s | Avg:  3m 20s | Max:  5m 51s
  🟩 20                 Pass: 100%/20  | Total:  1h 54m | Avg:  5m 43s | Max: 21m 02s | Hits:  90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 04s | Avg: 5m 02s | Max: 8m 06s

🟩 cpu
  🟩 amd64              Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 ctk
  🟩 12.6               Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 cudacxx
  🟩 nvcc12.6           Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 cxx
  🟩 GCC13              Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 cxx_family
  🟩 GCC                Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 gpu
  🟩 v100               Pass: 100%/2   | Total: 10m 04s | Avg:  5m 02s | Max:  8m 06s
🟩 jobs
  🟩 Build              Pass: 100%/1   | Total:  1m 58s | Avg:  1m 58s | Max:  1m 58s
  🟩 Test               Pass: 100%/1   | Total:  8m 06s | Avg:  8m 06s | Max:  8m 06s

🟩 python: Pass: 100%/1 | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 ctk
  🟩 12.6               Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 cudacxx
  🟩 nvcc12.6           Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 168)

#	Runner
124	`linux-amd64-cpu16`
19	`linux-amd64-gpu-v100-latest-1`
15	`windows-amd64-cpu16`
10	`linux-arm64-cpu16`

davebayer added 2 commits December 9, 2024 15:32

implement byteswap

999e8ca

update docs

1ee219d

davebayer requested review from a team as code owners December 9, 2024 14:34

davebayer requested review from miscco and alliepiper December 9, 2024 14:34

miscco requested changes Dec 9, 2024

View reviewed changes

libcudacxx/include/cuda/std/__bit/byteswap.h Outdated Show resolved Hide resolved

libcudacxx/include/cuda/std/__bit/byteswap.h Outdated Show resolved Hide resolved

libcudacxx/include/cuda/std/__cccl/builtin.h Outdated Show resolved Hide resolved

davebayer added 3 commits December 9, 2024 18:02

fix builtins, remove __unsigned_type from __byteswap_impl

6ef1a8e

fix template definitions

ab88583

remove builtin support for nvcc

5cdfc0f

miscco reviewed Dec 9, 2024

View reviewed changes

libcudacxx/include/cuda/std/__bit/byteswap.h Outdated Show resolved Hide resolved

optimized implementation

ef17865

davebayer added 2 commits December 10, 2024 09:22

fix bswap builtins

9c318ac

move device implementations to private section

05e34dc

davebayer requested a review from miscco December 10, 2024 08:26

miscco requested changes Dec 10, 2024

View reviewed changes

libcudacxx/include/cuda/std/__bit/byteswap.h Outdated Show resolved Hide resolved

miscco reviewed Dec 10, 2024

View reviewed changes

libcudacxx/include/cuda/std/__bit/byteswap.h Outdated Show resolved Hide resolved

use __int128_t-like type for 128-bit ints, fix bswap for msvc

ed09f81

miscco approved these changes Dec 10, 2024

View reviewed changes

davebayer added 2 commits December 10, 2024 11:51

use only _CCCL_DEVICE for device implementation, use inplace permut…

5968432

…ation to save a register

use out of place for 32-bit, inplace for 64-bit device impls

7b85332

miscco approved these changes Dec 10, 2024

View reviewed changes

allow device implementation only if CUDA compiler is allowed, fix tes…

2c5fd5b

…ts warning

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

implement C++23 `byteswap` #3093

implement C++23 `byteswap` #3093

davebayer commented Dec 9, 2024 •

edited

Loading

copy-pr-bot bot commented Dec 9, 2024

fbusato commented Dec 9, 2024

davebayer commented Dec 9, 2024

fbusato commented Dec 9, 2024

davebayer commented Dec 10, 2024 •

edited

Loading

miscco commented Dec 10, 2024

miscco commented Dec 10, 2024

github-actions bot commented Dec 10, 2024

🟨 libcudacxx: Pass: 77%/48 | Total: 9h 16m | Avg: 11m 35s | Max: 33m 50s

🟩 thrust: Pass: 100%/46 | Total: 1d 01h | Avg: 33m 07s | Max: 1h 15m | Hits: 70%/9260

🟩 cub: Pass: 100%/45 | Total: 1d 15h | Avg: 52m 10s | Max: 1h 05m | Hits: 30%/3028

🟩 cudax: Pass: 100%/26 | Total: 2h 30m | Avg: 5m 46s | Max: 23m 03s | Hits: 90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 9m 11s | Avg: 4m 35s | Max: 7m 02s

🟩 python: Pass: 100%/1 | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 168)

miscco commented Dec 11, 2024

github-actions bot commented Dec 11, 2024

🟨 libcudacxx: Pass: 93%/48 | Total: 10h 12m | Avg: 12m 45s | Max: 37m 50s | Hits: 31%/9754

🟩 thrust: Pass: 100%/46 | Total: 13h 41m | Avg: 17m 50s | Max: 1h 11m | Hits: 70%/9260

🟩 cub: Pass: 100%/45 | Total: 18h 15m | Avg: 24m 20s | Max: 1h 06m | Hits: 30%/3028

🟩 cudax: Pass: 100%/26 | Total: 2h 14m | Avg: 5m 10s | Max: 21m 02s | Hits: 90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 04s | Avg: 5m 02s | Max: 8m 06s

🟩 python: Pass: 100%/1 | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 168)

implement C++23 byteswap #3093

Are you sure you want to change the base?

implement C++23 byteswap #3093

Conversation

davebayer commented Dec 9, 2024 • edited Loading

copy-pr-bot bot commented Dec 9, 2024

fbusato commented Dec 9, 2024

davebayer commented Dec 9, 2024

fbusato commented Dec 9, 2024

davebayer commented Dec 10, 2024 • edited Loading

miscco commented Dec 10, 2024

miscco commented Dec 10, 2024

github-actions bot commented Dec 10, 2024

🟨 libcudacxx: Pass: 77%/48 | Total: 9h 16m | Avg: 11m 35s | Max: 33m 50s

🟩 thrust: Pass: 100%/46 | Total: 1d 01h | Avg: 33m 07s | Max: 1h 15m | Hits: 70%/9260

🟩 cub: Pass: 100%/45 | Total: 1d 15h | Avg: 52m 10s | Max: 1h 05m | Hits: 30%/3028

🟩 cudax: Pass: 100%/26 | Total: 2h 30m | Avg: 5m 46s | Max: 23m 03s | Hits: 90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 9m 11s | Avg: 4m 35s | Max: 7m 02s

🟩 python: Pass: 100%/1 | Total: 26m 19s | Avg: 26m 19s | Max: 26m 19s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 168)

miscco commented Dec 11, 2024

github-actions bot commented Dec 11, 2024

🟨 libcudacxx: Pass: 93%/48 | Total: 10h 12m | Avg: 12m 45s | Max: 37m 50s | Hits: 31%/9754

🟩 thrust: Pass: 100%/46 | Total: 13h 41m | Avg: 17m 50s | Max: 1h 11m | Hits: 70%/9260

🟩 cub: Pass: 100%/45 | Total: 18h 15m | Avg: 24m 20s | Max: 1h 06m | Hits: 30%/3028

🟩 cudax: Pass: 100%/26 | Total: 2h 14m | Avg: 5m 10s | Max: 21m 02s | Hits: 90%/312

🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 04s | Avg: 5m 02s | Max: 8m 06s

🟩 python: Pass: 100%/1 | Total: 29m 32s | Avg: 29m 32s | Max: 29m 32s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 168)

implement C++23 `byteswap` #3093

implement C++23 `byteswap` #3093

davebayer commented Dec 9, 2024 •

edited

Loading

davebayer commented Dec 10, 2024 •

edited

Loading