Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add CUB tests for segmented sort/radix sort with 64-bit num. items and segments #2254

Merged
merged 51 commits into from
Sep 26, 2024

Conversation

fbusato
Copy link
Contributor

@fbusato fbusato commented Aug 16, 2024

Provide 64-bit num. items and segments for DispatchSegmentedSort and DispatchSegmentedRadixSort, both for Keys and Pairs.
Address #2139 and #2140

The integration is blocked by #50

@fbusato fbusato requested review from a team as code owners August 16, 2024 22:12
@fbusato fbusato requested a review from gonidelis August 16, 2024 22:12
Copy link

copy-pr-bot bot commented Aug 16, 2024

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.

@fbusato
Copy link
Contributor Author

fbusato commented Aug 16, 2024

Additional comment. The tests for segmented sort/radix sort seem a bit messy and they can probably be simplified and partially merged, since they evaluate similar functions.

@elstehle
Copy link
Collaborator

/ok to test

Copy link
Contributor

🟨 CI finished in 4h 11m: Pass: 65%/250 | Total: 2d 14h | Avg: 15m 00s | Max: 47m 29s | Hits: 99%/11560
  • 🟨 cub: Pass: 59%/131 | Total: 1d 20h | Avg: 20m 13s | Max: 47m 29s

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  56%/123 | Total:  1d 17h | Avg: 20m 15s | Max: 47m 29s
      🟩 arm64              Pass: 100%/8   | Total:  2h 36m | Avg: 19m 30s | Max: 23m 07s
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 24m 37s | Avg: 12m 18s | Max: 12m 38s
      🔍 nvcc               Pass:  58%/129 | Total:  1d 19h | Avg: 20m 20s | Max: 47m 29s
    🟨 ctk
      🟨 11.1               Pass:  93%/15  | Total:  3h 49m | Avg: 15m 17s | Max: 20m 08s
      🟩 11.8               Pass: 100%/3   | Total:  1h 08m | Avg: 22m 52s | Max: 24m 27s
      🟨 12.5               Pass:  53%/113 | Total:  1d 15h | Avg: 20m 48s | Max: 47m 29s
    🟨 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 24m 37s | Avg: 12m 18s | Max: 12m 38s
      🟨 nvcc11.1           Pass:  93%/15  | Total:  3h 49m | Avg: 15m 17s | Max: 20m 08s
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 08m | Avg: 22m 52s | Max: 24m 27s
      🟨 nvcc12.5           Pass:  53%/111 | Total:  1d 14h | Avg: 20m 57s | Max: 47m 29s
    🟨 cxx
      🟨 Clang9             Pass:  50%/6   | Total:  1h 49m | Avg: 18m 18s | Max: 25m 18s
      🟩 Clang10            Pass: 100%/3   | Total:  1h 05m | Avg: 21m 41s | Max: 30m 06s
      🟨 Clang11            Pass:  75%/4   | Total:  1h 18m | Avg: 19m 38s | Max: 25m 26s
      🟨 Clang12            Pass:  25%/4   | Total:  1h 30m | Avg: 22m 40s | Max: 25m 15s
      🟥 Clang13            Pass:   0%/4   | Total:  1h 46m | Avg: 26m 36s | Max: 28m 27s
      🟥 Clang14            Pass:   0%/4   | Total:  1h 37m | Avg: 24m 23s | Max: 27m 10s
      🟥 Clang15            Pass:   0%/4   | Total:  1h 30m | Avg: 22m 31s | Max: 26m 20s
      🟥 Clang16            Pass:   0%/4   | Total:  1h 28m | Avg: 22m 06s | Max: 25m 50s
      🟨 Clang17            Pass:  53%/26  | Total:  8h 30m | Avg: 19m 37s | Max: 47m 29s
      🟩 GCC6               Pass: 100%/2   | Total: 29m 59s | Avg: 14m 59s | Max: 15m 08s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 38m | Avg: 16m 24s | Max: 19m 04s
      🟩 GCC8               Pass: 100%/6   | Total:  1h 35m | Avg: 15m 52s | Max: 17m 07s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 40m | Avg: 16m 43s | Max: 18m 48s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 15m | Avg: 18m 49s | Max: 19m 42s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 17m | Avg: 19m 37s | Max: 24m 27s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 14m | Avg: 18m 30s | Max: 19m 42s
      🟨 GCC13              Pass:  57%/28  | Total: 10h 05m | Avg: 21m 37s | Max: 40m 29s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 04m | Avg: 21m 21s | Max: 22m 54s
      🟥 MSVC14.16          Pass:   0%/1   | Total: 20m 08s | Avg: 20m 08s | Max: 20m 08s
      🟥 MSVC14.29          Pass:   0%/2   | Total: 41m 44s | Avg: 20m 52s | Max: 20m 54s
      🟥 MSVC14.39          Pass:   0%/3   | Total:  1h 09m | Avg: 23m 16s | Max: 23m 49s
    🟨 cxx_family
      🟨 Clang              Pass:  40%/59  | Total: 20h 36m | Avg: 20m 57s | Max: 47m 29s
      🟨 GCC                Pass:  80%/63  | Total: 20h 16m | Avg: 19m 18s | Max: 40m 29s
      🟩 Intel              Pass: 100%/3   | Total:  1h 04m | Avg: 21m 21s | Max: 22m 54s
      🟥 MSVC               Pass:   0%/6   | Total:  2h 11m | Avg: 21m 56s | Max: 23m 49s
    🟨 jobs
      🟨 Build              Pass:  70%/99  | Total:  1d 07h | Avg: 19m 08s | Max: 30m 06s
      🟥 DeviceLaunch       Pass:   0%/8   | Total:  3h 05m | Avg: 23m 12s | Max: 39m 28s
      🟥 GraphCapture       Pass:   0%/8   | Total:  2h 25m | Avg: 18m 08s | Max: 35m 39s
      🟥 HostLaunch         Pass:   0%/8   | Total:  2h 48m | Avg: 21m 02s | Max: 29m 31s
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 14m | Avg: 31m 47s | Max: 47m 29s
    🟨 gpu
      🟨 v100               Pass:  59%/131 | Total:  1d 20h | Avg: 20m 13s | Max: 47m 29s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 08m | Avg: 22m 52s | Max: 24m 27s
      🟩 90a                Pass: 100%/4   | Total: 39m 56s | Avg:  9m 59s | Max: 10m 30s
    🟨 std
      🟨 11                 Pass:  64%/34  | Total: 10h 51m | Avg: 19m 08s | Max: 28m 27s
      🟨 14                 Pass:  59%/37  | Total: 12h 19m | Avg: 19m 58s | Max: 35m 11s
      🟨 17                 Pass:  63%/36  | Total: 11h 53m | Avg: 19m 48s | Max: 40m 29s
      🟨 20                 Pass:  45%/24  | Total:  9h 04m | Avg: 22m 41s | Max: 47m 29s
    
  • 🟨 thrust: Pass: 72%/118 | Total: 17h 57m | Avg: 9m 07s | Max: 30m 34s | Hits: 99%/11560

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  70%/110 | Total: 17h 27m | Avg:  9m 31s | Max: 30m 34s | Hits:  99%/11560 
      🟩 arm64              Pass: 100%/8   | Total: 30m 18s | Avg:  3m 47s | Max:  4m 03s
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 03m | Avg:  4m 15s | Max: 16m 55s | Hits:  99%/1445  
      🟩 11.8               Pass: 100%/3   | Total: 12m 08s | Avg:  4m 02s | Max:  4m 25s
      🔍 12.5               Pass:  68%/100 | Total: 16h 41m | Avg: 10m 00s | Max: 30m 34s | Hits:  99%/10115 
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  8m 32s | Avg:  4m 16s | Max:  4m 23s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 03m | Avg:  4m 15s | Max: 16m 55s | Hits:  99%/1445  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 12m 08s | Avg:  4m 02s | Max:  4m 25s
      🔍 nvcc12.5           Pass:  67%/98  | Total: 16h 32m | Avg: 10m 07s | Max: 30m 34s | Hits:  99%/10115 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  8m 32s | Avg:  4m 16s | Max:  4m 23s
      🔍 nvcc               Pass:  72%/116 | Total: 17h 48m | Avg:  9m 12s | Max: 30m 34s | Hits:  99%/11560 
    🔍 sm: 90a 🔍
      🟩 60;70;80;90        Pass: 100%/3   | Total: 12m 08s | Avg:  4m 02s | Max:  4m 25s
      🔍 90a                Pass:  50%/4   | Total: 35m 18s | Avg:  8m 49s | Max: 14m 16s
    🟨 cxx
      🟨 Clang9             Pass:  83%/6   | Total: 33m 24s | Avg:  5m 34s | Max: 13m 45s
      🟥 Clang10            Pass:   0%/3   | Total: 40m 08s | Avg: 13m 22s | Max: 13m 25s
      🟨 Clang11            Pass:  75%/4   | Total: 38m 42s | Avg:  9m 40s | Max: 18m 04s
      🟥 Clang12            Pass:   0%/4   | Total: 50m 08s | Avg: 12m 32s | Max: 12m 42s
      🟥 Clang13            Pass:   0%/4   | Total:  1h 02m | Avg: 15m 35s | Max: 17m 08s
      🟨 Clang14            Pass:  25%/4   | Total: 46m 53s | Avg: 11m 43s | Max: 16m 25s
      🟥 Clang15            Pass:   0%/4   | Total:  1h 00m | Avg: 15m 07s | Max: 15m 30s
      🟩 Clang16            Pass: 100%/4   | Total: 15m 52s | Avg:  3m 58s | Max:  4m 11s
      🟩 Clang17            Pass: 100%/18  | Total:  2h 17m | Avg:  7m 37s | Max: 25m 20s
      🟩 GCC6               Pass: 100%/2   | Total:  6m 25s | Avg:  3m 12s | Max:  3m 15s
      🟨 GCC7               Pass:  66%/6   | Total: 46m 12s | Avg:  7m 42s | Max: 19m 05s
      🟨 GCC8               Pass:  66%/6   | Total: 41m 02s | Avg:  6m 50s | Max: 13m 34s
      🟨 GCC9               Pass:  66%/6   | Total: 40m 31s | Avg:  6m 45s | Max: 13m 33s
      🟩 GCC10              Pass: 100%/4   | Total: 16m 32s | Avg:  4m 08s | Max:  4m 55s
      🟨 GCC11              Pass:  71%/7   | Total: 50m 52s | Avg:  7m 16s | Max: 15m 41s
      🟨 GCC12              Pass:  75%/4   | Total: 28m 41s | Avg:  7m 10s | Max: 15m 11s
      🟨 GCC13              Pass:  90%/20  | Total:  3h 09m | Avg:  9m 28s | Max: 26m 50s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 29s | Avg:  5m 09s | Max:  5m 23s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 55s | Avg: 16m 55s | Max: 16m 55s | Hits:  99%/1445  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 26m 24s | Avg: 13m 12s | Max: 13m 33s | Hits:  99%/2890  
      🟨 MSVC14.39          Pass:  83%/6   | Total:  1h 53m | Avg: 18m 58s | Max: 30m 34s | Hits:  99%/7225  
    🟨 cxx_family
      🟨 Clang              Pass:  60%/51  | Total:  8h 05m | Avg:  9m 30s | Max: 25m 20s
      🟨 GCC                Pass:  80%/55  | Total:  6h 59m | Avg:  7m 37s | Max: 26m 50s
      🟩 Intel              Pass: 100%/3   | Total: 15m 29s | Avg:  5m 09s | Max:  5m 23s
      🟨 MSVC               Pass:  88%/9   | Total:  2h 37m | Avg: 17m 27s | Max: 30m 34s | Hits:  99%/11560 
    🟨 jobs
      🟨 Build              Pass:  68%/99  | Total: 13h 08m | Avg:  7m 57s | Max: 19m 05s | Hits:  99%/8670  
      🟨 TestCPU            Pass:  90%/11  | Total:  2h 03m | Avg: 11m 11s | Max: 30m 34s | Hits:  99%/2890  
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 45m | Avg: 20m 44s | Max: 26m 50s
    🟨 gpu
      🟨 v100               Pass:  72%/118 | Total: 17h 57m | Avg:  9m 07s | Max: 30m 34s | Hits:  99%/11560 
    🟨 std
      🟨 11                 Pass:  73%/30  | Total:  3h 50m | Avg:  7m 41s | Max: 26m 50s
      🟨 14                 Pass:  76%/34  | Total:  4h 57m | Avg:  8m 45s | Max: 24m 09s | Hits:  99%/5780  
      🟨 17                 Pass:  72%/33  | Total:  5h 22m | Avg:  9m 46s | Max: 25m 20s | Hits:  99%/4335  
      🟨 20                 Pass:  66%/21  | Total:  3h 45m | Avg: 10m 45s | Max: 30m 34s | Hits:  99%/1445  
    
  • 🟥 pycuda: Pass: 0%/1 | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s

    🟥 cpu
      🟥 amd64              Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 ctk
      🟥 12.5               Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 cudacxx
      🟥 nvcc12.5           Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 cudacxx_family
      🟥 nvcc               Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 cxx
      🟥 GCC13              Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 cxx_family
      🟥 GCC                Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 gpu
      🟥 v100               Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    🟥 jobs
      🟥 Test               Pass:   0%/1   | Total: 25m 50s | Avg: 25m 50s | Max: 25m 50s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda

🏃‍ Runner counts (total jobs: 250)

# Runner
178 linux-amd64-cpu16
41 linux-amd64-gpu-v100-latest-1
16 linux-arm64-cpu16
15 windows-amd64-cpu16

@fbusato
Copy link
Contributor Author

fbusato commented Aug 27, 2024

Added a macro guard to protect segmented sort tests that are not supported yet.
The idea is to merge the PR in the main branch and enable these tests later when the CUB library supports them.

Copy link
Collaborator

@elstehle elstehle left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks a lot for helping to add tests here. Overall the tests are written very nicely. I would just need to extend coverage a bit, particularly across offset types, for it to meet my current use case for verifying the correctness when using different offset types during benchmarking, i.e., int32_t, uint32_t, int64_t, uint64_t.

@fbusato
Copy link
Contributor Author

fbusato commented Aug 30, 2024

@elstehle, thanks for the careful review!
the only thing missing is the huge segment case

@fbusato
Copy link
Contributor Author

fbusato commented Aug 30, 2024

/ok to test

@elstehle elstehle self-requested a review September 3, 2024 12:18
@fbusato
Copy link
Contributor Author

fbusato commented Sep 3, 2024

/ok to test

Copy link
Contributor

github-actions bot commented Sep 3, 2024

🟩 CI finished in 4h 51m: Pass: 100%/251 | Total: 1d 17h | Avg: 9m 58s | Max: 1h 24m | Hits: 99%/24375
  • 🟩 cub: Pass: 100%/132 | Total: 1d 04h | Avg: 13m 05s | Max: 1h 24m | Hits: 98%/4296

    🟩 cpu
      🟩 amd64              Pass: 100%/124 | Total:  1d 03h | Avg: 13m 16s | Max:  1h 24m | Hits:  98%/4296  
      🟩 arm64              Pass: 100%/8   | Total:  1h 22m | Avg: 10m 20s | Max: 17m 41s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 21m | Avg:  9m 24s | Max: 19m 52s | Hits:  98%/716   
      🟩 11.8               Pass: 100%/3   | Total: 37m 13s | Avg: 12m 24s | Max: 21m 11s
      🟩 12.5               Pass: 100%/114 | Total:  1d 01h | Avg: 13m 35s | Max:  1h 24m | Hits:  98%/3580  
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 11m 10s | Avg:  5m 35s | Max:  5m 56s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 21m | Avg:  9m 24s | Max: 19m 52s | Hits:  98%/716   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 37m 13s | Avg: 12m 24s | Max: 21m 11s
      🟩 nvcc12.5           Pass: 100%/112 | Total:  1d 01h | Avg: 13m 44s | Max:  1h 24m | Hits:  98%/3580  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 11m 10s | Avg:  5m 35s | Max:  5m 56s
      🟩 nvcc               Pass: 100%/130 | Total:  1d 04h | Avg: 13m 12s | Max:  1h 24m | Hits:  98%/4296  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 54m 58s | Avg:  9m 09s | Max: 15m 59s
      🟩 Clang10            Pass: 100%/3   | Total: 29m 53s | Avg:  9m 57s | Max: 14m 37s
      🟩 Clang11            Pass: 100%/4   | Total: 34m 52s | Avg:  8m 43s | Max: 14m 12s
      🟩 Clang12            Pass: 100%/4   | Total: 34m 11s | Avg:  8m 32s | Max: 14m 44s
      🟩 Clang13            Pass: 100%/4   | Total: 35m 21s | Avg:  8m 50s | Max: 15m 48s
      🟩 Clang14            Pass: 100%/4   | Total: 36m 24s | Avg:  9m 06s | Max: 16m 08s
      🟩 Clang15            Pass: 100%/4   | Total: 34m 49s | Avg:  8m 42s | Max: 14m 58s
      🟩 Clang16            Pass: 100%/4   | Total: 36m 41s | Avg:  9m 10s | Max: 15m 34s
      🟩 Clang17            Pass: 100%/26  | Total:  6h 46m | Avg: 15m 38s | Max: 37m 23s
      🟩 GCC6               Pass: 100%/2   | Total: 19m 26s | Avg:  9m 43s | Max: 12m 44s
      🟩 GCC7               Pass: 100%/6   | Total: 52m 00s | Avg:  8m 40s | Max: 14m 11s
      🟩 GCC8               Pass: 100%/6   | Total: 52m 51s | Avg:  8m 48s | Max: 15m 06s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 00m | Avg: 10m 03s | Max: 17m 37s
      🟩 GCC10              Pass: 100%/4   | Total: 36m 33s | Avg:  9m 08s | Max: 16m 50s
      🟩 GCC11              Pass: 100%/7   | Total:  1h 14m | Avg: 10m 40s | Max: 21m 11s
      🟩 GCC12              Pass: 100%/4   | Total: 36m 03s | Avg:  9m 00s | Max: 14m 57s
      🟩 GCC13              Pass: 100%/29  | Total:  9h 09m | Avg: 18m 56s | Max:  1h 24m
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 38m 04s | Avg: 12m 41s | Max: 19m 33s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 19m 52s | Avg: 19m 52s | Max: 19m 52s | Hits:  98%/716   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 33m 28s | Avg: 16m 44s | Max: 18m 11s | Hits:  98%/1432  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 51m 52s | Avg: 17m 17s | Max: 17m 56s | Hits:  98%/2148  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/59  | Total: 11h 43m | Avg: 11m 55s | Max: 37m 23s
      🟩 GCC                Pass: 100%/64  | Total: 14h 41m | Avg: 13m 46s | Max:  1h 24m
      🟩 Intel              Pass: 100%/3   | Total: 38m 04s | Avg: 12m 41s | Max: 19m 33s
      🟩 MSVC               Pass: 100%/6   | Total:  1h 45m | Avg: 17m 32s | Max: 19m 52s | Hits:  98%/4296  
    🟩 gpu
      🟩 v100               Pass: 100%/132 | Total:  1d 04h | Avg: 13m 05s | Max:  1h 24m | Hits:  98%/4296  
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 16h 03m | Avg:  9m 43s | Max: 21m 11s | Hits:  98%/4296  
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  3h 45m | Avg: 28m 11s | Max:  1h 24m
      🟩 GraphCapture       Pass: 100%/8   | Total:  1h 57m | Avg: 14m 40s | Max: 15m 37s
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 48m | Avg: 21m 04s | Max: 28m 58s
      🟩 SmallGMem          Pass: 100%/1   | Total: 29m 44s | Avg: 29m 44s | Max: 29m 44s
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 43m | Avg: 27m 56s | Max: 38m 31s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 37m 13s | Avg: 12m 24s | Max: 21m 11s
      🟩 90a                Pass: 100%/4   | Total: 23m 42s | Avg:  5m 55s | Max: 10m 08s
    🟩 std
      🟩 11                 Pass: 100%/34  | Total:  9h 35m | Avg: 16m 55s | Max: 37m 23s
      🟩 14                 Pass: 100%/37  | Total:  7h 45m | Avg: 12m 34s | Max:  1h 24m | Hits:  98%/2148  
      🟩 17                 Pass: 100%/37  | Total:  7h 01m | Avg: 11m 22s | Max: 38m 31s | Hits:  98%/1432  
      🟩 20                 Pass: 100%/24  | Total:  4h 26m | Avg: 11m 06s | Max: 23m 11s | Hits:  98%/716   
    
  • 🟩 thrust: Pass: 100%/118 | Total: 12h 44m | Avg: 6m 28s | Max: 26m 13s | Hits: 99%/20079

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 12h 08m | Avg:  6m 37s | Max: 26m 13s | Hits:  99%/20079 
      🟩 arm64              Pass: 100%/8   | Total: 35m 32s | Avg:  4m 26s | Max:  5m 15s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 09m | Avg:  4m 37s | Max: 15m 17s | Hits:  99%/2231  
      🟩 11.8               Pass: 100%/3   | Total: 14m 09s | Avg:  4m 43s | Max:  5m 01s
      🟩 12.5               Pass: 100%/100 | Total: 11h 20m | Avg:  6m 48s | Max: 26m 13s | Hits:  99%/17848 
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  9m 52s | Avg:  4m 56s | Max:  5m 08s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 09m | Avg:  4m 37s | Max: 15m 17s | Hits:  99%/2231  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 09s | Avg:  4m 43s | Max:  5m 01s
      🟩 nvcc12.5           Pass: 100%/98  | Total: 11h 11m | Avg:  6m 50s | Max: 26m 13s | Hits:  99%/17848 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 52s | Avg:  4m 56s | Max:  5m 08s
      🟩 nvcc               Pass: 100%/116 | Total: 12h 34m | Avg:  6m 30s | Max: 26m 13s | Hits:  99%/20079 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 28m 50s | Avg:  4m 48s | Max:  5m 34s
      🟩 Clang10            Pass: 100%/3   | Total: 16m 48s | Avg:  5m 36s | Max:  5m 46s
      🟩 Clang11            Pass: 100%/4   | Total: 17m 52s | Avg:  4m 28s | Max:  4m 56s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 02s | Avg:  4m 30s | Max:  5m 02s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 12s | Avg:  4m 33s | Max:  4m 46s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 36s | Avg:  4m 39s | Max:  5m 00s
      🟩 Clang15            Pass: 100%/4   | Total: 19m 10s | Avg:  4m 47s | Max:  5m 16s
      🟩 Clang16            Pass: 100%/4   | Total: 18m 54s | Avg:  4m 43s | Max:  5m 07s
      🟩 Clang17            Pass: 100%/18  | Total:  2h 10m | Avg:  7m 15s | Max: 14m 53s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 41s | Avg:  3m 50s | Max:  4m 24s
      🟩 GCC7               Pass: 100%/6   | Total: 22m 41s | Avg:  3m 46s | Max:  4m 23s
      🟩 GCC8               Pass: 100%/6   | Total: 25m 43s | Avg:  4m 17s | Max:  5m 05s
      🟩 GCC9               Pass: 100%/6   | Total: 25m 32s | Avg:  4m 15s | Max:  4m 55s
      🟩 GCC10              Pass: 100%/4   | Total: 18m 50s | Avg:  4m 42s | Max:  5m 05s
      🟩 GCC11              Pass: 100%/7   | Total: 33m 52s | Avg:  4m 50s | Max:  5m 18s
      🟩 GCC12              Pass: 100%/4   | Total: 19m 54s | Avg:  4m 58s | Max:  5m 37s
      🟩 GCC13              Pass: 100%/20  | Total:  2h 16m | Avg:  6m 49s | Max: 14m 42s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 07s | Avg:  5m 42s | Max:  6m 19s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 15m 17s | Avg: 15m 17s | Max: 15m 17s | Hits:  99%/2231  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 30m 41s | Avg: 15m 20s | Max: 15m 30s | Hits:  99%/4462  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  2h 03m | Avg: 20m 34s | Max: 26m 13s | Hits:  99%/13386 
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total:  4h 47m | Avg:  5m 37s | Max: 14m 53s
      🟩 GCC                Pass: 100%/55  | Total:  4h 50m | Avg:  5m 17s | Max: 14m 42s
      🟩 Intel              Pass: 100%/3   | Total: 17m 07s | Avg:  5m 42s | Max:  6m 19s
      🟩 MSVC               Pass: 100%/9   | Total:  2h 49m | Avg: 18m 49s | Max: 26m 13s | Hits:  99%/20079 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 12h 44m | Avg:  6m 28s | Max: 26m 13s | Hits:  99%/20079 
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 46m | Avg:  5m 18s | Max: 17m 29s | Hits:  99%/13386 
      🟩 TestCPU            Pass: 100%/11  | Total:  2h 11m | Avg: 11m 59s | Max: 26m 13s | Hits:  99%/6693  
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 46m | Avg: 13m 19s | Max: 14m 53s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 09s | Avg:  4m 43s | Max:  5m 01s
      🟩 90a                Pass: 100%/4   | Total: 16m 58s | Avg:  4m 14s | Max:  4m 44s
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 29m | Avg:  4m 58s | Max: 13m 31s
      🟩 14                 Pass: 100%/34  | Total:  3h 50m | Avg:  6m 47s | Max: 23m 17s | Hits:  99%/8924  
      🟩 17                 Pass: 100%/33  | Total:  3h 47m | Avg:  6m 53s | Max: 26m 13s | Hits:  99%/6693  
      🟩 20                 Pass: 100%/21  | Total:  2h 36m | Avg:  7m 27s | Max: 24m 08s | Hits:  99%/4462  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 12m 58s | Avg: 12m 58s | Max: 12m 58s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda

🏃‍ Runner counts (total jobs: 251)

# Runner
178 linux-amd64-cpu16
42 linux-amd64-gpu-v100-latest-1
16 linux-arm64-cpu16
15 windows-amd64-cpu16

@fbusato
Copy link
Contributor Author

fbusato commented Sep 21, 2024

/ok to test

@fbusato
Copy link
Contributor Author

fbusato commented Sep 21, 2024

the idea of cudaMallocHost is a good solution. I slightly simplified the code and propagated to the other files

Copy link
Contributor

🟨 CI finished in 50m 38s: Pass: 99%/208 | Total: 1d 15h | Avg: 11m 15s | Max: 34m 49s | Hits: 98%/14058
  • 🟨 cub: Pass: 99%/104 | Total: 1d 04h | Avg: 16m 30s | Max: 34m 49s | Hits: 93%/2908

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  98%/96  | Total:  1d 02h | Avg: 16m 27s | Max: 34m 49s | Hits:  93%/2908  
      🟩 arm64              Pass: 100%/8   | Total:  2h 16m | Avg: 17m 07s | Max: 18m 50s
    🔍 ctk: 12.6 🔍
      🟩 11.1               Pass: 100%/15  | Total:  3h 51m | Avg: 15m 26s | Max: 34m 49s | Hits:  93%/727   
      🟩 11.8               Pass: 100%/3   | Total:  1h 05m | Avg: 21m 55s | Max: 22m 46s
      🔍 12.6               Pass:  98%/86  | Total: 23h 40m | Avg: 16m 30s | Max: 31m 20s | Hits:  93%/2181  
    🔍 cudacxx: nvcc12.6 🔍
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 21m 14s | Avg: 10m 37s | Max: 11m 21s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  3h 51m | Avg: 15m 26s | Max: 34m 49s | Hits:  93%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 05m | Avg: 21m 55s | Max: 22m 46s
      🔍 nvcc12.6           Pass:  98%/84  | Total: 23h 18m | Avg: 16m 39s | Max: 31m 20s | Hits:  93%/2181  
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 21m 14s | Avg: 10m 37s | Max: 11m 21s
      🔍 nvcc               Pass:  99%/102 | Total:  1d 04h | Avg: 16m 37s | Max: 34m 49s | Hits:  93%/2908  
    🔍 cxx: GCC13 🔍
      🟩 Clang9             Pass: 100%/6   | Total:  1h 30m | Avg: 15m 01s | Max: 17m 56s
      🟩 Clang10            Pass: 100%/3   | Total: 50m 19s | Avg: 16m 46s | Max: 17m 19s
      🟩 Clang11            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 18m 13s
      🟩 Clang12            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 50s | Max: 17m 37s
      🟩 Clang13            Pass: 100%/4   | Total:  1h 01m | Avg: 15m 20s | Max: 16m 15s
      🟩 Clang14            Pass: 100%/4   | Total:  1h 04m | Avg: 16m 02s | Max: 17m 53s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 01m | Avg: 15m 16s | Max: 15m 51s
      🟩 Clang16            Pass: 100%/4   | Total:  1h 02m | Avg: 15m 38s | Max: 17m 11s
      🟩 Clang17            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 45s | Max: 16m 35s
      🟩 Clang18            Pass: 100%/9   | Total:  2h 26m | Avg: 16m 17s | Max: 25m 59s
      🟩 GCC6               Pass: 100%/2   | Total: 29m 01s | Avg: 14m 30s | Max: 15m 12s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 30m | Avg: 15m 02s | Max: 16m 18s
      🟩 GCC8               Pass: 100%/6   | Total:  1h 32m | Avg: 15m 26s | Max: 16m 54s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 29m | Avg: 14m 55s | Max: 16m 37s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 07m | Avg: 16m 51s | Max: 18m 20s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 08m | Avg: 18m 21s | Max: 22m 46s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 05m | Avg: 16m 27s | Max: 17m 26s
      🔍 GCC13              Pass:  93%/16  | Total:  3h 55m | Avg: 14m 43s | Max: 27m 21s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 08m | Avg: 22m 53s | Max: 24m 54s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 34m 49s | Avg: 34m 49s | Max: 34m 49s | Hits:  93%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 59m 24s | Avg: 29m 42s | Max: 31m 20s | Hits:  93%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 29m 24s | Avg: 29m 24s | Max: 29m 24s | Hits:  93%/727   
    🔍 cxx_family: GCC 🔍
      🟩 Clang              Pass: 100%/46  | Total: 12h 06m | Avg: 15m 47s | Max: 25m 59s
      🔍 GCC                Pass:  98%/51  | Total: 13h 18m | Avg: 15m 39s | Max: 27m 21s
      🟩 Intel              Pass: 100%/3   | Total:  1h 08m | Avg: 22m 53s | Max: 24m 54s
      🟩 MSVC               Pass: 100%/4   | Total:  2h 03m | Avg: 30m 54s | Max: 34m 49s | Hits:  93%/2908  
    🚨 jobs: DeviceLaunch 🚨
      🟩 Build              Pass: 100%/96  | Total:  1d 02h | Avg: 16m 25s | Max: 34m 49s | Hits:  93%/2908  
      🔥 DeviceLaunch       Pass:   0%/1  
      🟩 GraphCapture       Pass: 100%/1   | Total: 15m 00s | Avg: 15m 00s | Max: 15m 00s
      🟩 HostLaunch         Pass: 100%/3   | Total: 53m 05s | Avg: 17m 41s | Max: 18m 51s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 13m | Avg: 24m 24s | Max: 27m 21s
    🔍 std: 20 🔍
      🟩 11                 Pass: 100%/28  | Total:  7h 44m | Avg: 16m 35s | Max: 23m 47s
      🟩 14                 Pass: 100%/27  | Total:  7h 57m | Avg: 17m 41s | Max: 34m 49s | Hits:  93%/1454  
      🟩 17                 Pass: 100%/26  | Total:  6h 44m | Avg: 15m 34s | Max: 28m 04s | Hits:  93%/727   
      🔍 20                 Pass:  95%/23  | Total:  6h 10m | Avg: 16m 06s | Max: 29m 24s | Hits:  93%/727   
    🟨 gpu
      🟨 v100               Pass:  99%/104 | Total:  1d 04h | Avg: 16m 30s | Max: 34m 49s | Hits:  93%/2908  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 05m | Avg: 21m 55s | Max: 22m 46s
      🟩 90a                Pass: 100%/4   | Total: 36m 11s | Avg:  9m 02s | Max:  9m 29s
    
  • 🟩 thrust: Pass: 100%/103 | Total: 10h 06m | Avg: 5m 53s | Max: 24m 51s | Hits: 99%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total:  9h 28m | Avg:  5m 59s | Max: 24m 51s | Hits:  99%/11150 
      🟩 arm64              Pass: 100%/8   | Total: 37m 13s | Avg:  4m 39s | Max:  5m 21s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 15m | Avg:  5m 00s | Max: 19m 27s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 13m 50s | Avg:  4m 36s | Max:  5m 12s
      🟩 12.6               Pass: 100%/85  | Total:  8h 37m | Avg:  6m 05s | Max: 24m 51s | Hits:  99%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  8m 50s | Avg:  4m 25s | Max:  4m 29s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 15m | Avg:  5m 00s | Max: 19m 27s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 50s | Avg:  4m 36s | Max:  5m 12s
      🟩 nvcc12.6           Pass: 100%/83  | Total:  8h 28m | Avg:  6m 07s | Max: 24m 51s | Hits:  99%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  8m 50s | Avg:  4m 25s | Max:  4m 29s
      🟩 nvcc               Pass: 100%/101 | Total:  9h 57m | Avg:  5m 54s | Max: 24m 51s | Hits:  99%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 30m 29s | Avg:  5m 04s | Max:  6m 02s
      🟩 Clang10            Pass: 100%/3   | Total: 17m 12s | Avg:  5m 44s | Max:  5m 51s
      🟩 Clang11            Pass: 100%/4   | Total: 18m 57s | Avg:  4m 44s | Max:  5m 03s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 09s | Avg:  4m 32s | Max:  4m 46s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 39s | Avg:  4m 39s | Max:  5m 07s
      🟩 Clang14            Pass: 100%/4   | Total: 19m 17s | Avg:  4m 49s | Max:  5m 05s
      🟩 Clang15            Pass: 100%/4   | Total: 20m 39s | Avg:  5m 09s | Max:  5m 37s
      🟩 Clang16            Pass: 100%/4   | Total: 20m 36s | Avg:  5m 09s | Max:  5m 35s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 33s | Avg:  4m 53s | Max:  4m 56s
      🟩 Clang18            Pass: 100%/9   | Total: 51m 56s | Avg:  5m 46s | Max: 13m 13s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 24s | Avg:  3m 42s | Max:  3m 42s
      🟩 GCC7               Pass: 100%/6   | Total: 24m 44s | Avg:  4m 07s | Max:  4m 54s
      🟩 GCC8               Pass: 100%/6   | Total: 25m 37s | Avg:  4m 16s | Max:  4m 53s
      🟩 GCC9               Pass: 100%/6   | Total: 26m 12s | Avg:  4m 22s | Max:  4m 57s
      🟩 GCC10              Pass: 100%/4   | Total: 20m 05s | Avg:  5m 01s | Max:  5m 16s
      🟩 GCC11              Pass: 100%/7   | Total: 33m 17s | Avg:  4m 45s | Max:  5m 12s
      🟩 GCC12              Pass: 100%/4   | Total: 20m 23s | Avg:  5m 05s | Max:  5m 23s
      🟩 GCC13              Pass: 100%/14  | Total:  1h 37m | Avg:  6m 59s | Max: 23m 36s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 56s | Avg:  5m 58s | Max:  6m 19s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 19m 27s | Avg: 19m 27s | Max: 19m 27s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 34m 15s | Avg: 17m 07s | Max: 17m 23s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total: 43m 27s | Avg: 21m 43s | Max: 24m 51s | Hits:  99%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  3h 55m | Avg:  5m 07s | Max: 13m 13s
      🟩 GCC                Pass: 100%/49  | Total:  4h 15m | Avg:  5m 12s | Max: 23m 36s
      🟩 Intel              Pass: 100%/3   | Total: 17m 56s | Avg:  5m 58s | Max:  6m 19s
      🟩 MSVC               Pass: 100%/5   | Total:  1h 37m | Avg: 19m 25s | Max: 24m 51s | Hits:  99%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total: 10h 06m | Avg:  5m 53s | Max: 24m 51s | Hits:  99%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  8h 28m | Avg:  5m 18s | Max: 19m 27s | Hits:  99%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total: 47m 03s | Avg: 11m 45s | Max: 24m 51s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 50m 05s | Avg: 16m 41s | Max: 23m 36s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 50s | Avg:  4m 36s | Max:  5m 12s
      🟩 90a                Pass: 100%/4   | Total: 16m 03s | Avg:  4m 00s | Max:  4m 21s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 16m | Avg:  4m 51s | Max: 13m 16s
      🟩 14                 Pass: 100%/27  | Total:  2h 33m | Avg:  5m 41s | Max: 19m 27s | Hits:  99%/4460  
      🟩 17                 Pass: 100%/26  | Total:  2h 22m | Avg:  5m 28s | Max: 17m 23s | Hits:  99%/2230  
      🟩 20                 Pass: 100%/22  | Total:  2h 53m | Avg:  7m 54s | Max: 24m 51s | Hits:  99%/4460  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 208)

# Runner
171 linux-amd64-cpu16
16 linux-arm64-cpu16
12 linux-amd64-gpu-v100-latest-1
9 windows-amd64-cpu16

Copy link
Collaborator

@elstehle elstehle left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

One last change request, otherwise looks good to be merged.

I left the comments only on cub/test/catch2_test_device_segmented_radix_sort_keys.cu, but they equally apply to the other test files.

cub/test/catch2_test_device_segmented_radix_sort_keys.cu Outdated Show resolved Hide resolved
cub/test/catch2_test_device_segmented_radix_sort_keys.cu Outdated Show resolved Hide resolved
cub/test/catch2_test_device_segmented_radix_sort_keys.cu Outdated Show resolved Hide resolved
@fbusato
Copy link
Contributor Author

fbusato commented Sep 25, 2024

/ok to test

Copy link
Contributor

🟩 CI finished in 1h 08m: Pass: 100%/208 | Total: 1d 15h | Avg: 11m 26s | Max: 34m 06s | Hits: 98%/14058
  • 🟩 cub: Pass: 100%/104 | Total: 1d 05h | Avg: 16m 59s | Max: 34m 06s | Hits: 93%/2908

    🟩 cpu
      🟩 amd64              Pass: 100%/96  | Total:  1d 03h | Avg: 16m 55s | Max: 34m 06s | Hits:  93%/2908  
      🟩 arm64              Pass: 100%/8   | Total:  2h 22m | Avg: 17m 46s | Max: 19m 21s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  3h 48m | Avg: 15m 12s | Max: 34m 06s | Hits:  93%/727   
      🟩 11.8               Pass: 100%/3   | Total:  1h 03m | Avg: 21m 01s | Max: 22m 11s
      🟩 12.6               Pass: 100%/86  | Total:  1d 00h | Avg: 17m 09s | Max: 32m 55s | Hits:  93%/2181  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 13m 10s | Avg:  6m 35s | Max:  6m 37s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  3h 48m | Avg: 15m 12s | Max: 34m 06s | Hits:  93%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 03m | Avg: 21m 01s | Max: 22m 11s
      🟩 nvcc12.6           Pass: 100%/84  | Total:  1d 00h | Avg: 17m 25s | Max: 32m 55s | Hits:  93%/2181  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 13m 10s | Avg:  6m 35s | Max:  6m 37s
      🟩 nvcc               Pass: 100%/102 | Total:  1d 05h | Avg: 17m 11s | Max: 34m 06s | Hits:  93%/2908  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 34m | Avg: 15m 40s | Max: 19m 06s
      🟩 Clang10            Pass: 100%/3   | Total: 49m 34s | Avg: 16m 31s | Max: 17m 13s
      🟩 Clang11            Pass: 100%/4   | Total:  1h 07m | Avg: 16m 55s | Max: 19m 26s
      🟩 Clang12            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 48s | Max: 16m 43s
      🟩 Clang13            Pass: 100%/4   | Total:  1h 08m | Avg: 17m 09s | Max: 19m 39s
      🟩 Clang14            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 49s | Max: 16m 29s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 02m | Avg: 15m 40s | Max: 16m 30s
      🟩 Clang16            Pass: 100%/4   | Total:  1h 07m | Avg: 16m 51s | Max: 19m 02s
      🟩 Clang17            Pass: 100%/4   | Total:  1h 02m | Avg: 15m 34s | Max: 16m 16s
      🟩 Clang18            Pass: 100%/9   | Total:  2h 26m | Avg: 16m 13s | Max: 27m 31s
      🟩 GCC6               Pass: 100%/2   | Total: 30m 23s | Avg: 15m 11s | Max: 16m 24s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 28m | Avg: 14m 40s | Max: 16m 36s
      🟩 GCC8               Pass: 100%/6   | Total:  1h 31m | Avg: 15m 17s | Max: 17m 39s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 33m | Avg: 15m 32s | Max: 18m 27s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 09m | Avg: 17m 20s | Max: 19m 13s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 07m | Avg: 18m 13s | Max: 22m 11s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 13m | Avg: 18m 19s | Max: 20m 01s
      🟩 GCC13              Pass: 100%/16  | Total:  4h 16m | Avg: 16m 00s | Max: 22m 44s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 03m | Avg: 21m 07s | Max: 22m 23s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 34m 06s | Avg: 34m 06s | Max: 34m 06s | Hits:  93%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 02m | Avg: 31m 12s | Max: 31m 44s | Hits:  93%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 32m 55s | Avg: 32m 55s | Max: 32m 55s | Hits:  93%/727   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total: 12h 24m | Avg: 16m 11s | Max: 27m 31s
      🟩 GCC                Pass: 100%/51  | Total: 13h 49m | Avg: 16m 16s | Max: 22m 44s
      🟩 Intel              Pass: 100%/3   | Total:  1h 03m | Avg: 21m 07s | Max: 22m 23s
      🟩 MSVC               Pass: 100%/4   | Total:  2h 09m | Avg: 32m 21s | Max: 34m 06s | Hits:  93%/2908  
    🟩 gpu
      🟩 v100               Pass: 100%/104 | Total:  1d 05h | Avg: 16m 59s | Max: 34m 06s | Hits:  93%/2908  
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  1d 02h | Avg: 16m 43s | Max: 34m 06s | Hits:  93%/2908  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 16m 01s | Avg: 16m 01s | Max: 16m 01s
      🟩 GraphCapture       Pass: 100%/1   | Total: 18m 05s | Avg: 18m 05s | Max: 18m 05s
      🟩 HostLaunch         Pass: 100%/3   | Total: 56m 23s | Avg: 18m 47s | Max: 22m 28s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 11m | Avg: 23m 57s | Max: 27m 31s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 03m | Avg: 21m 01s | Max: 22m 11s
      🟩 90a                Pass: 100%/4   | Total: 36m 40s | Avg:  9m 10s | Max:  9m 21s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  7h 53m | Avg: 16m 55s | Max: 22m 11s
      🟩 14                 Pass: 100%/27  | Total:  8h 08m | Avg: 18m 06s | Max: 34m 06s | Hits:  93%/1454  
      🟩 17                 Pass: 100%/26  | Total:  6h 47m | Avg: 15m 40s | Max: 31m 44s | Hits:  93%/727   
      🟩 20                 Pass: 100%/23  | Total:  6h 37m | Avg: 17m 17s | Max: 32m 55s | Hits:  93%/727   
    
  • 🟩 thrust: Pass: 100%/103 | Total: 9h 55m | Avg: 5m 46s | Max: 23m 00s | Hits: 99%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total:  9h 18m | Avg:  5m 52s | Max: 23m 00s | Hits:  99%/11150 
      🟩 arm64              Pass: 100%/8   | Total: 36m 54s | Avg:  4m 36s | Max:  5m 29s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 14m | Avg:  4m 56s | Max: 19m 42s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 13m 51s | Avg:  4m 37s | Max:  4m 51s
      🟩 12.6               Pass: 100%/85  | Total:  8h 27m | Avg:  5m 58s | Max: 23m 00s | Hits:  99%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 26s | Avg:  4m 43s | Max:  4m 55s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 14m | Avg:  4m 56s | Max: 19m 42s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 51s | Avg:  4m 37s | Max:  4m 51s
      🟩 nvcc12.6           Pass: 100%/83  | Total:  8h 17m | Avg:  5m 59s | Max: 23m 00s | Hits:  99%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 26s | Avg:  4m 43s | Max:  4m 55s
      🟩 nvcc               Pass: 100%/101 | Total:  9h 45m | Avg:  5m 48s | Max: 23m 00s | Hits:  99%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 29m 50s | Avg:  4m 58s | Max:  6m 18s
      🟩 Clang10            Pass: 100%/3   | Total: 16m 51s | Avg:  5m 37s | Max:  5m 55s
      🟩 Clang11            Pass: 100%/4   | Total: 19m 02s | Avg:  4m 45s | Max:  5m 00s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 57s | Avg:  4m 44s | Max:  4m 59s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 57s | Avg:  4m 44s | Max:  4m 53s
      🟩 Clang14            Pass: 100%/4   | Total: 20m 39s | Avg:  5m 09s | Max:  5m 35s
      🟩 Clang15            Pass: 100%/4   | Total: 19m 58s | Avg:  4m 59s | Max:  5m 33s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 56s | Avg:  4m 59s | Max:  5m 17s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 41s | Avg:  4m 55s | Max:  5m 01s
      🟩 Clang18            Pass: 100%/9   | Total: 49m 30s | Avg:  5m 30s | Max: 10m 59s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 10s | Avg:  3m 35s | Max:  3m 46s
      🟩 GCC7               Pass: 100%/6   | Total: 24m 11s | Avg:  4m 01s | Max:  5m 01s
      🟩 GCC8               Pass: 100%/6   | Total: 25m 05s | Avg:  4m 10s | Max:  4m 36s
      🟩 GCC9               Pass: 100%/6   | Total: 26m 16s | Avg:  4m 22s | Max:  4m 55s
      🟩 GCC10              Pass: 100%/4   | Total: 18m 41s | Avg:  4m 40s | Max:  4m 50s
      🟩 GCC11              Pass: 100%/7   | Total: 32m 44s | Avg:  4m 40s | Max:  4m 56s
      🟩 GCC12              Pass: 100%/4   | Total: 21m 37s | Avg:  5m 24s | Max:  6m 05s
      🟩 GCC13              Pass: 100%/14  | Total:  1h 30m | Avg:  6m 25s | Max: 14m 30s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 19m 38s | Avg:  6m 32s | Max:  7m 06s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 19m 42s | Avg: 19m 42s | Max: 19m 42s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 36m 21s | Avg: 18m 10s | Max: 19m 41s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total: 40m 29s | Avg: 20m 14s | Max: 23m 00s | Hits:  99%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  3h 53m | Avg:  5m 04s | Max: 10m 59s
      🟩 GCC                Pass: 100%/49  | Total:  4h 05m | Avg:  5m 00s | Max: 14m 30s
      🟩 Intel              Pass: 100%/3   | Total: 19m 38s | Avg:  6m 32s | Max:  7m 06s
      🟩 MSVC               Pass: 100%/5   | Total:  1h 36m | Avg: 19m 18s | Max: 23m 00s | Hits:  99%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total:  9h 55m | Avg:  5m 46s | Max: 23m 00s | Hits:  99%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  8h 30m | Avg:  5m 19s | Max: 19m 42s | Hits:  99%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total: 45m 27s | Avg: 11m 21s | Max: 23m 00s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 39m 13s | Avg: 13m 04s | Max: 14m 30s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 51s | Avg:  4m 37s | Max:  4m 51s
      🟩 90a                Pass: 100%/4   | Total: 16m 19s | Avg:  4m 04s | Max:  4m 16s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 18m | Avg:  4m 56s | Max: 14m 30s
      🟩 14                 Pass: 100%/27  | Total:  2h 37m | Avg:  5m 50s | Max: 19m 42s | Hits:  99%/4460  
      🟩 17                 Pass: 100%/26  | Total:  2h 20m | Avg:  5m 23s | Max: 16m 40s | Hits:  99%/2230  
      🟩 20                 Pass: 100%/22  | Total:  2h 39m | Avg:  7m 14s | Max: 23m 00s | Hits:  99%/4460  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 208)

# Runner
171 linux-amd64-cpu16
16 linux-arm64-cpu16
12 linux-amd64-gpu-v100-latest-1
9 windows-amd64-cpu16

@fbusato fbusato enabled auto-merge (squash) September 25, 2024 17:14
@fbusato
Copy link
Contributor Author

fbusato commented Sep 25, 2024

/ok to test

@fbusato fbusato self-assigned this Sep 26, 2024
@elstehle
Copy link
Collaborator

/ok to test

@elstehle elstehle self-requested a review September 26, 2024 16:56
Copy link
Contributor

🟩 CI finished in 1h 47m: Pass: 100%/208 | Total: 1d 14h | Avg: 11m 05s | Max: 39m 46s | Hits: 98%/14058
  • 🟩 cub: Pass: 100%/104 | Total: 1d 03h | Avg: 15m 48s | Max: 34m 35s | Hits: 93%/2908

    🟩 cpu
      🟩 amd64              Pass: 100%/96  | Total:  1d 01h | Avg: 15m 45s | Max: 34m 35s | Hits:  93%/2908  
      🟩 arm64              Pass: 100%/8   | Total:  2h 11m | Avg: 16m 26s | Max: 19m 36s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  3h 48m | Avg: 15m 14s | Max: 34m 35s | Hits:  93%/727   
      🟩 11.8               Pass: 100%/3   | Total: 58m 30s | Avg: 19m 30s | Max: 20m 03s
      🟩 12.6               Pass: 100%/86  | Total: 22h 36m | Avg: 15m 46s | Max: 26m 42s | Hits:  93%/2181  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 20m 28s | Avg: 10m 14s | Max: 10m 15s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  3h 48m | Avg: 15m 14s | Max: 34m 35s | Hits:  93%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 58m 30s | Avg: 19m 30s | Max: 20m 03s
      🟩 nvcc12.6           Pass: 100%/84  | Total: 22h 15m | Avg: 15m 54s | Max: 26m 42s | Hits:  93%/2181  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 20m 28s | Avg: 10m 14s | Max: 10m 15s
      🟩 nvcc               Pass: 100%/102 | Total:  1d 03h | Avg: 15m 54s | Max: 34m 35s | Hits:  93%/2908  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 27m | Avg: 14m 38s | Max: 17m 00s
      🟩 Clang10            Pass: 100%/3   | Total: 47m 51s | Avg: 15m 57s | Max: 16m 38s
      🟩 Clang11            Pass: 100%/4   | Total:  1h 00m | Avg: 15m 02s | Max: 17m 35s
      🟩 Clang12            Pass: 100%/4   | Total: 58m 20s | Avg: 14m 35s | Max: 15m 29s
      🟩 Clang13            Pass: 100%/4   | Total: 57m 08s | Avg: 14m 17s | Max: 14m 55s
      🟩 Clang14            Pass: 100%/4   | Total: 57m 28s | Avg: 14m 22s | Max: 14m 58s
      🟩 Clang15            Pass: 100%/4   | Total: 59m 11s | Avg: 14m 47s | Max: 16m 52s
      🟩 Clang16            Pass: 100%/4   | Total: 58m 24s | Avg: 14m 36s | Max: 15m 51s
      🟩 Clang17            Pass: 100%/4   | Total: 57m 48s | Avg: 14m 27s | Max: 15m 26s
      🟩 Clang18            Pass: 100%/9   | Total:  2h 24m | Avg: 16m 06s | Max: 26m 42s
      🟩 GCC6               Pass: 100%/2   | Total: 30m 41s | Avg: 15m 20s | Max: 16m 26s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 28m | Avg: 14m 40s | Max: 17m 05s
      🟩 GCC8               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 28s | Max: 16m 08s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 20s | Max: 15m 17s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 00m | Avg: 15m 04s | Max: 16m 29s
      🟩 GCC11              Pass: 100%/7   | Total:  1h 58m | Avg: 16m 54s | Max: 20m 03s
      🟩 GCC12              Pass: 100%/4   | Total: 59m 09s | Avg: 14m 47s | Max: 15m 23s
      🟩 GCC13              Pass: 100%/16  | Total:  4h 18m | Avg: 16m 09s | Max: 26m 42s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 54m 55s | Avg: 18m 18s | Max: 20m 26s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 34m 35s | Avg: 34m 35s | Max: 34m 35s | Hits:  93%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 51m 47s | Avg: 25m 53s | Max: 26m 33s | Hits:  93%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 25m 13s | Avg: 25m 13s | Max: 25m 13s | Hits:  93%/727   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total: 11h 29m | Avg: 14m 58s | Max: 26m 42s
      🟩 GCC                Pass: 100%/51  | Total: 13h 07m | Avg: 15m 27s | Max: 26m 42s
      🟩 Intel              Pass: 100%/3   | Total: 54m 55s | Avg: 18m 18s | Max: 20m 26s
      🟩 MSVC               Pass: 100%/4   | Total:  1h 51m | Avg: 27m 53s | Max: 34m 35s | Hits:  93%/2908  
    🟩 gpu
      🟩 v100               Pass: 100%/104 | Total:  1d 03h | Avg: 15m 48s | Max: 34m 35s | Hits:  93%/2908  
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  1d 00h | Avg: 15m 19s | Max: 34m 35s | Hits:  93%/2908  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 20m 46s | Avg: 20m 46s | Max: 20m 46s
      🟩 GraphCapture       Pass: 100%/1   | Total: 18m 55s | Avg: 18m 55s | Max: 18m 55s
      🟩 HostLaunch         Pass: 100%/3   | Total: 55m 29s | Avg: 18m 29s | Max: 20m 43s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 17m | Avg: 25m 59s | Max: 26m 42s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 58m 30s | Avg: 19m 30s | Max: 20m 03s
      🟩 90a                Pass: 100%/4   | Total: 33m 15s | Avg:  8m 18s | Max:  8m 51s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  7h 18m | Avg: 15m 39s | Max: 24m 33s
      🟩 14                 Pass: 100%/27  | Total:  7h 33m | Avg: 16m 46s | Max: 34m 35s | Hits:  93%/1454  
      🟩 17                 Pass: 100%/26  | Total:  6h 12m | Avg: 14m 19s | Max: 26m 33s | Hits:  93%/727   
      🟩 20                 Pass: 100%/23  | Total:  6h 19m | Avg: 16m 30s | Max: 26m 42s | Hits:  93%/727   
    
  • 🟩 thrust: Pass: 100%/103 | Total: 10h 49m | Avg: 6m 18s | Max: 39m 46s | Hits: 99%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total: 10h 14m | Avg:  6m 28s | Max: 39m 46s | Hits:  99%/11150 
      🟩 arm64              Pass: 100%/8   | Total: 35m 10s | Avg:  4m 23s | Max:  4m 45s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 40m | Avg:  6m 40s | Max: 28m 04s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 13m 53s | Avg:  4m 37s | Max:  4m 53s
      🟩 12.6               Pass: 100%/85  | Total:  8h 55m | Avg:  6m 18s | Max: 39m 46s | Hits:  99%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 06s | Avg:  4m 33s | Max:  4m 34s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 40m | Avg:  6m 40s | Max: 28m 04s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 53s | Avg:  4m 37s | Max:  4m 53s
      🟩 nvcc12.6           Pass: 100%/83  | Total:  8h 46m | Avg:  6m 20s | Max: 39m 46s | Hits:  99%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 06s | Avg:  4m 33s | Max:  4m 34s
      🟩 nvcc               Pass: 100%/101 | Total: 10h 40m | Avg:  6m 20s | Max: 39m 46s | Hits:  99%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 29m 30s | Avg:  4m 55s | Max:  5m 54s
      🟩 Clang10            Pass: 100%/3   | Total: 17m 46s | Avg:  5m 55s | Max:  6m 23s
      🟩 Clang11            Pass: 100%/4   | Total: 18m 42s | Avg:  4m 40s | Max:  5m 12s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 45s | Avg:  4m 41s | Max:  4m 53s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 41s | Avg:  4m 40s | Max:  4m 51s
      🟩 Clang14            Pass: 100%/4   | Total: 19m 00s | Avg:  4m 45s | Max:  5m 02s
      🟩 Clang15            Pass: 100%/4   | Total: 18m 59s | Avg:  4m 44s | Max:  4m 57s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 34s | Avg:  4m 53s | Max:  5m 38s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 22s | Avg:  4m 50s | Max:  5m 17s
      🟩 Clang18            Pass: 100%/9   | Total: 54m 29s | Avg:  6m 03s | Max: 15m 39s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 13s | Avg:  3m 36s | Max:  3m 45s
      🟩 GCC7               Pass: 100%/6   | Total: 49m 16s | Avg:  8m 12s | Max: 28m 04s
      🟩 GCC8               Pass: 100%/6   | Total: 25m 38s | Avg:  4m 16s | Max:  4m 35s
      🟩 GCC9               Pass: 100%/6   | Total: 26m 36s | Avg:  4m 26s | Max:  5m 06s
      🟩 GCC10              Pass: 100%/4   | Total: 19m 06s | Avg:  4m 46s | Max:  5m 15s
      🟩 GCC11              Pass: 100%/7   | Total: 33m 31s | Avg:  4m 47s | Max:  5m 14s
      🟩 GCC12              Pass: 100%/4   | Total: 19m 43s | Avg:  4m 55s | Max:  5m 08s
      🟩 GCC13              Pass: 100%/14  | Total:  1h 59m | Avg:  8m 32s | Max: 39m 46s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 49s | Avg:  5m 56s | Max:  6m 16s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 19m 25s | Avg: 19m 25s | Max: 19m 25s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 35m 19s | Avg: 17m 39s | Max: 18m 36s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total: 41m 31s | Avg: 20m 45s | Max: 23m 01s | Hits:  99%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  3h 54m | Avg:  5m 06s | Max: 15m 39s
      🟩 GCC                Pass: 100%/49  | Total:  5h 00m | Avg:  6m 08s | Max: 39m 46s
      🟩 Intel              Pass: 100%/3   | Total: 17m 49s | Avg:  5m 56s | Max:  6m 16s
      🟩 MSVC               Pass: 100%/5   | Total:  1h 36m | Avg: 19m 15s | Max: 23m 01s | Hits:  99%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total: 10h 49m | Avg:  6m 18s | Max: 39m 46s | Hits:  99%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  8h 48m | Avg:  5m 30s | Max: 28m 04s | Hits:  99%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total:  1h 17m | Avg: 19m 20s | Max: 39m 46s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 43m 33s | Avg: 14m 31s | Max: 15m 39s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 53s | Avg:  4m 37s | Max:  4m 53s
      🟩 90a                Pass: 100%/4   | Total: 16m 22s | Avg:  4m 05s | Max:  4m 24s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 11m | Avg:  4m 42s | Max: 12m 24s
      🟩 14                 Pass: 100%/27  | Total:  3h 00m | Avg:  6m 40s | Max: 28m 04s | Hits:  99%/4460  
      🟩 17                 Pass: 100%/26  | Total:  2h 19m | Avg:  5m 21s | Max: 16m 43s | Hits:  99%/2230  
      🟩 20                 Pass: 100%/22  | Total:  3h 18m | Avg:  9m 00s | Max: 39m 46s | Hits:  99%/4460  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 14m 27s | Avg: 14m 27s | Max: 14m 27s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 208)

# Runner
171 linux-amd64-cpu16
16 linux-arm64-cpu16
12 linux-amd64-gpu-v100-latest-1
9 windows-amd64-cpu16

@fbusato
Copy link
Contributor Author

fbusato commented Sep 26, 2024

/ok to test

Copy link
Contributor

🟩 CI finished in 1h 01m: Pass: 100%/208 | Total: 1d 01h | Avg: 7m 24s | Max: 49m 15s | Hits: 99%/14058
  • 🟩 cub: Pass: 100%/104 | Total: 13h 26m | Avg: 7m 45s | Max: 49m 15s | Hits: 99%/2908

    🟩 cpu
      🟩 amd64              Pass: 100%/96  | Total: 12h 37m | Avg:  7m 53s | Max: 49m 15s | Hits:  99%/2908  
      🟩 arm64              Pass: 100%/8   | Total: 48m 28s | Avg:  6m 03s | Max:  8m 26s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 15m 10s | Hits:  99%/727   
      🟩 11.8               Pass: 100%/3   | Total: 15m 05s | Avg:  5m 01s | Max:  5m 19s
      🟩 12.6               Pass: 100%/86  | Total: 12h 02m | Avg:  8m 23s | Max: 49m 15s | Hits:  99%/2181  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  8m 35s | Avg:  4m 17s | Max:  4m 18s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 15m 10s | Hits:  99%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 15m 05s | Avg:  5m 01s | Max:  5m 19s
      🟩 nvcc12.6           Pass: 100%/84  | Total: 11h 53m | Avg:  8m 29s | Max: 49m 15s | Hits:  99%/2181  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  8m 35s | Avg:  4m 17s | Max:  4m 18s
      🟩 nvcc               Pass: 100%/102 | Total: 13h 17m | Avg:  7m 49s | Max: 49m 15s | Hits:  99%/2908  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 27m 13s | Avg:  4m 32s | Max:  5m 17s
      🟩 Clang10            Pass: 100%/3   | Total: 16m 14s | Avg:  5m 24s | Max:  5m 48s
      🟩 Clang11            Pass: 100%/4   | Total: 18m 03s | Avg:  4m 30s | Max:  4m 37s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 37s | Avg:  4m 39s | Max:  5m 04s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 19s | Avg:  4m 34s | Max:  4m 51s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 37s | Avg:  4m 39s | Max:  4m 54s
      🟩 Clang15            Pass: 100%/4   | Total: 33m 46s | Avg:  8m 26s | Max:  8m 53s
      🟩 Clang16            Pass: 100%/4   | Total: 32m 48s | Avg:  8m 12s | Max:  8m 49s
      🟩 Clang17            Pass: 100%/4   | Total: 33m 47s | Avg:  8m 26s | Max:  9m 01s
      🟩 Clang18            Pass: 100%/9   | Total:  1h 30m | Avg: 10m 02s | Max: 23m 43s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 19s | Avg:  3m 39s | Max:  3m 56s
      🟩 GCC7               Pass: 100%/6   | Total: 24m 18s | Avg:  4m 03s | Max:  4m 35s
      🟩 GCC8               Pass: 100%/6   | Total: 24m 14s | Avg:  4m 02s | Max:  4m 38s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 09m | Avg: 11m 38s | Max: 48m 40s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 02m | Avg: 15m 36s | Max: 49m 15s
      🟩 GCC11              Pass: 100%/7   | Total: 44m 50s | Avg:  6m 24s | Max:  8m 05s
      🟩 GCC12              Pass: 100%/4   | Total: 32m 10s | Avg:  8m 02s | Max:  8m 33s
      🟩 GCC13              Pass: 100%/16  | Total:  2h 33m | Avg:  9m 36s | Max: 23m 35s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 24m 45s | Avg:  8m 15s | Max:  8m 39s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 15m 10s | Avg: 15m 10s | Max: 15m 10s | Hits:  99%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 25m 44s | Avg: 12m 52s | Max: 13m 25s | Hits:  99%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 13m 58s | Avg: 13m 58s | Max: 13m 58s | Hits:  99%/727   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  5h 07m | Avg:  6m 41s | Max: 23m 43s
      🟩 GCC                Pass: 100%/51  | Total:  6h 58m | Avg:  8m 12s | Max: 49m 15s
      🟩 Intel              Pass: 100%/3   | Total: 24m 45s | Avg:  8m 15s | Max:  8m 39s
      🟩 MSVC               Pass: 100%/4   | Total: 54m 52s | Avg: 13m 43s | Max: 15m 10s | Hits:  99%/2908  
    🟩 gpu
      🟩 v100               Pass: 100%/104 | Total: 13h 26m | Avg:  7m 45s | Max: 49m 15s | Hits:  99%/2908  
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total: 10h 51m | Avg:  6m 47s | Max: 49m 15s | Hits:  99%/2908  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 17m 56s | Avg: 17m 56s | Max: 17m 56s
      🟩 GraphCapture       Pass: 100%/1   | Total: 14m 38s | Avg: 14m 38s | Max: 14m 38s
      🟩 HostLaunch         Pass: 100%/3   | Total: 52m 30s | Avg: 17m 30s | Max: 18m 41s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 09m | Avg: 23m 11s | Max: 23m 43s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 15m 05s | Avg:  5m 01s | Max:  5m 19s
      🟩 90a                Pass: 100%/4   | Total: 15m 02s | Avg:  3m 45s | Max:  3m 57s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  3h 39m | Avg:  7m 49s | Max: 48m 40s
      🟩 14                 Pass: 100%/27  | Total:  2h 43m | Avg:  6m 02s | Max: 15m 10s | Hits:  99%/1454  
      🟩 17                 Pass: 100%/26  | Total:  3h 18m | Avg:  7m 36s | Max: 49m 15s | Hits:  99%/727   
      🟩 20                 Pass: 100%/23  | Total:  3h 45m | Avg:  9m 49s | Max: 23m 43s | Hits:  99%/727   
    
  • 🟩 thrust: Pass: 100%/103 | Total: 11h 58m | Avg: 6m 58s | Max: 40m 56s | Hits: 99%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total: 11h 10m | Avg:  7m 03s | Max: 40m 56s | Hits:  99%/11150 
      🟩 arm64              Pass: 100%/8   | Total: 48m 28s | Avg:  6m 03s | Max:  7m 43s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 15m | Avg:  5m 02s | Max: 19m 00s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 17m 38s | Avg:  5m 52s | Max:  6m 43s
      🟩 12.6               Pass: 100%/85  | Total: 10h 25m | Avg:  7m 21s | Max: 40m 56s | Hits:  99%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 13m 28s | Avg:  6m 44s | Max:  7m 06s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 15m | Avg:  5m 02s | Max: 19m 00s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 17m 38s | Avg:  5m 52s | Max:  6m 43s
      🟩 nvcc12.6           Pass: 100%/83  | Total: 10h 12m | Avg:  7m 22s | Max: 40m 56s | Hits:  99%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 13m 28s | Avg:  6m 44s | Max:  7m 06s
      🟩 nvcc               Pass: 100%/101 | Total: 11h 45m | Avg:  6m 58s | Max: 40m 56s | Hits:  99%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 28m 52s | Avg:  4m 48s | Max:  5m 48s
      🟩 Clang10            Pass: 100%/3   | Total: 17m 41s | Avg:  5m 53s | Max:  6m 43s
      🟩 Clang11            Pass: 100%/4   | Total: 18m 30s | Avg:  4m 37s | Max:  4m 52s
      🟩 Clang12            Pass: 100%/4   | Total: 19m 13s | Avg:  4m 48s | Max:  5m 13s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 45s | Avg:  4m 41s | Max:  4m 55s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 31s | Avg:  4m 37s | Max:  4m 53s
      🟩 Clang15            Pass: 100%/4   | Total: 32m 57s | Avg:  8m 14s | Max:  8m 42s
      🟩 Clang16            Pass: 100%/4   | Total: 33m 58s | Avg:  8m 29s | Max:  9m 13s
      🟩 Clang17            Pass: 100%/4   | Total: 35m 06s | Avg:  8m 46s | Max:  8m 53s
      🟩 Clang18            Pass: 100%/9   | Total:  1h 10m | Avg:  7m 50s | Max: 11m 54s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 37s | Avg:  3m 48s | Max:  4m 11s
      🟩 GCC7               Pass: 100%/6   | Total: 25m 13s | Avg:  4m 12s | Max:  5m 04s
      🟩 GCC8               Pass: 100%/6   | Total: 26m 04s | Avg:  4m 20s | Max:  4m 44s
      🟩 GCC9               Pass: 100%/6   | Total: 26m 02s | Avg:  4m 20s | Max:  4m 52s
      🟩 GCC10              Pass: 100%/4   | Total: 18m 28s | Avg:  4m 37s | Max:  4m 48s
      🟩 GCC11              Pass: 100%/7   | Total:  1h 20m | Avg: 11m 28s | Max: 40m 56s
      🟩 GCC12              Pass: 100%/4   | Total: 32m 11s | Avg:  8m 02s | Max:  9m 00s
      🟩 GCC13              Pass: 100%/14  | Total:  1h 25m | Avg:  6m 08s | Max: 13m 09s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 28m 19s | Avg:  9m 26s | Max:  9m 49s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 19m 00s | Avg: 19m 00s | Max: 19m 00s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 33m 34s | Avg: 16m 47s | Max: 17m 02s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total: 41m 55s | Avg: 20m 57s | Max: 22m 16s | Hits:  99%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  4h 54m | Avg:  6m 23s | Max: 11m 54s
      🟩 GCC                Pass: 100%/49  | Total:  5h 01m | Avg:  6m 09s | Max: 40m 56s
      🟩 Intel              Pass: 100%/3   | Total: 28m 19s | Avg:  9m 26s | Max:  9m 49s
      🟩 MSVC               Pass: 100%/5   | Total:  1h 34m | Avg: 18m 53s | Max: 22m 16s | Hits:  99%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total: 11h 58m | Avg:  6m 58s | Max: 40m 56s | Hits:  99%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total: 10h 35m | Avg:  6m 37s | Max: 40m 56s | Hits:  99%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total: 45m 06s | Avg: 11m 16s | Max: 22m 16s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 37m 56s | Avg: 12m 38s | Max: 13m 09s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 17m 38s | Avg:  5m 52s | Max:  6m 43s
      🟩 90a                Pass: 100%/4   | Total: 15m 39s | Avg:  3m 54s | Max:  4m 06s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 35m | Avg:  5m 33s | Max: 13m 09s
      🟩 14                 Pass: 100%/27  | Total:  2h 57m | Avg:  6m 34s | Max: 19m 00s | Hits:  99%/4460  
      🟩 17                 Pass: 100%/26  | Total:  2h 48m | Avg:  6m 28s | Max: 17m 02s | Hits:  99%/2230  
      🟩 20                 Pass: 100%/22  | Total:  3h 37m | Avg:  9m 52s | Max: 40m 56s | Hits:  99%/4460  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 15m 39s | Avg: 15m 39s | Max: 15m 39s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 208)

# Runner
171 linux-amd64-cpu16
16 linux-arm64-cpu16
12 linux-amd64-gpu-v100-latest-1
9 windows-amd64-cpu16

@fbusato fbusato merged commit 5d45850 into NVIDIA:main Sep 26, 2024
221 checks passed
@fbusato fbusato deleted the cub/test/64bit_segmented_sort branch October 3, 2024 22:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

3 participants