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

Do not rely on conversions between float and extended floating point types #2046

Merged
merged 1 commit into from
Jul 25, 2024

Conversation

miscco
Copy link
Collaborator

@miscco miscco commented Jul 24, 2024

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test

Fixes nvbug4739601

@miscco miscco requested review from a team as code owners July 24, 2024 06:39
…types

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
@miscco miscco force-pushed the avoid_extended_floatingpoint_conversions branch from 82f1c05 to a994cc5 Compare July 24, 2024 06:48
@miscco miscco added nvbug Has an associated internal NVIDIA NVBug. libcu++ For all items related to libcu++ bug: functional labels Jul 24, 2024
@miscco miscco requested a review from griwes July 24, 2024 13:26
Copy link
Contributor

🟨 CI finished in 8h 59m: Pass: 99%/417 | Total: 6d 08h | Avg: 22m 00s | Max: 1h 08m | Hits: 71%/522268
  • 🟨 cub: Pass: 97%/131 | Total: 3d 11h | Avg: 38m 21s | Max: 1h 08m | Hits: 67%/108523

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  97%/123 | Total:  3d 04h | Avg: 37m 10s | Max:  1h 08m | Hits:  68%/101587
      🟩 arm64              Pass: 100%/8   | Total:  7h 32m | Avg: 56m 32s | Max:  1h 00m | Hits:  45%/6936  
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 51m | Avg:  7m 27s | Max: 50m 56s | Hits:  97%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🔍 12.5               Pass:  97%/113 | Total:  3d 09h | Avg: 43m 21s | Max:  1h 08m | Hits:  62%/94130 
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 43m 31s | Avg: 21m 45s | Max: 21m 52s | Hits:  53%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 51m | Avg:  7m 27s | Max: 50m 56s | Hits:  97%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🔍 nvcc12.5           Pass:  97%/111 | Total:  3d 08h | Avg: 43m 44s | Max:  1h 08m | Hits:  63%/92694 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 43m 31s | Avg: 21m 45s | Max: 21m 52s | Hits:  53%/1436  
      🔍 nvcc               Pass:  97%/129 | Total:  3d 11h | Avg: 38m 36s | Max:  1h 08m | Hits:  67%/107087
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 50m | Avg: 28m 21s | Max: 56m 30s | Hits:  74%/4980  
      🟩 Clang10            Pass: 100%/3   | Total:  2h 46m | Avg: 55m 30s | Max: 57m 04s | Hits:  50%/2607  
      🟩 Clang11            Pass: 100%/4   | Total:  3h 28m | Avg: 52m 12s | Max: 55m 17s | Hits:  50%/3476  
      🟩 Clang12            Pass: 100%/4   | Total:  3h 37m | Avg: 54m 25s | Max: 58m 04s | Hits:  50%/3476  
      🟩 Clang13            Pass: 100%/4   | Total:  3h 29m | Avg: 52m 22s | Max: 54m 50s | Hits:  50%/3476  
      🟩 Clang14            Pass: 100%/4   | Total:  3h 36m | Avg: 54m 04s | Max:  1h 01m | Hits:  50%/3476  
      🟩 Clang15            Pass: 100%/4   | Total:  3h 34m | Avg: 53m 31s | Max: 56m 09s | Hits:  50%/3468  
      🟩 Clang16            Pass: 100%/4   | Total:  3h 33m | Avg: 53m 26s | Max: 56m 20s | Hits:  50%/3468  
      🟨 Clang17            Pass:  92%/26  | Total: 13h 04m | Avg: 30m 09s | Max: 58m 55s | Hits:  80%/20510 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 06s | Avg:  3m 33s | Max:  3m 50s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total:  2h 53m | Avg: 28m 52s | Max: 57m 28s | Hits:  73%/4983  
      🟩 GCC8               Pass: 100%/6   | Total:  3h 51m | Avg: 38m 30s | Max:  1h 03m | Hits:  67%/4983  
      🟩 GCC9               Pass: 100%/6   | Total:  2h 51m | Avg: 28m 38s | Max: 56m 14s | Hits:  73%/4983  
      🟩 GCC10              Pass: 100%/4   | Total:  3h 34m | Avg: 53m 36s | Max: 56m 17s | Hits:  50%/3476  
      🟩 GCC11              Pass: 100%/7   | Total:  3h 48m | Avg: 32m 38s | Max: 55m 49s | Hits:  71%/6069  
      🟩 GCC12              Pass: 100%/4   | Total:  3h 37m | Avg: 54m 24s | Max:  1h 00m | Hits:  49%/3468  
      🟨 GCC13              Pass:  96%/28  | Total: 14h 25m | Avg: 30m 55s | Max:  1h 00m | Hits:  74%/23409 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 58m | Avg: 59m 22s | Max:  1h 01m | Hits:  49%/2379  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 12m 41s | Avg: 12m 41s | Max: 12m 41s | Hits:  99%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 07m | Avg:  1h 03m | Max:  1h 04m | Hits:  52%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  3h 15m | Avg:  1h 05m | Max:  1h 08m | Hits:  52%/2127  
    🟨 cxx_family
      🟨 Clang              Pass:  96%/59  | Total:  1d 16h | Avg: 40m 41s | Max:  1h 01m | Hits:  65%/48937 
      🟨 GCC                Pass:  98%/63  | Total:  1d 11h | Avg: 33m 29s | Max:  1h 03m | Hits:  70%/52953 
      🟩 Intel              Pass: 100%/3   | Total:  2h 58m | Avg: 59m 22s | Max:  1h 01m | Hits:  49%/2379  
      🟩 MSVC               Pass: 100%/6   | Total:  5h 35m | Avg: 55m 57s | Max:  1h 08m | Hits:  60%/4254  
    🟨 jobs
      🟩 Build              Pass: 100%/99  | Total:  3d 01h | Avg: 44m 27s | Max:  1h 08m | Hits:  57%/83380 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 35m | Avg: 19m 28s | Max: 22m 40s | Hits:  99%/6936  
      🟨 GraphCapture       Pass:  75%/8   | Total:  1h 52m | Avg: 14m 07s | Max: 19m 38s | Hits:  99%/5202  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 33m | Avg: 19m 13s | Max: 22m 25s | Hits:  99%/6936  
      🟨 TestGPU            Pass:  87%/8   | Total:  3h 20m | Avg: 25m 00s | Max: 31m 24s | Hits:  99%/6069  
    🟨 std
      🟨 11                 Pass:  97%/34  | Total: 21h 14m | Avg: 37m 28s | Max:  1h 03m | Hits:  68%/28180 
      🟨 14                 Pass:  97%/37  | Total:  1d 00h | Avg: 39m 22s | Max:  1h 08m | Hits:  67%/30307 
      🟩 17                 Pass: 100%/36  | Total: 22h 27m | Avg: 37m 26s | Max:  1h 04m | Hits:  67%/30392 
      🟨 20                 Pass:  95%/24  | Total: 15h 45m | Avg: 39m 24s | Max:  1h 03m | Hits:  64%/19644 
    🟨 gpu
      🟨 v100               Pass:  97%/131 | Total:  3d 11h | Avg: 38m 21s | Max:  1h 08m | Hits:  67%/108523
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total:  1h 31m | Avg: 22m 48s | Max: 23m 44s | Hits:  40%/3468  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 1d 18h | Avg: 21m 35s | Max: 56m 07s | Hits: 71%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  1d 14h | Avg: 21m 06s | Max: 56m 07s | Hits:  73%/129492
      🟩 arm64              Pass: 100%/8   | Total:  3h 45m | Avg: 28m 08s | Max: 34m 06s | Hits:  40%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total: 59m 40s | Avg:  3m 58s | Max: 13m 56s | Hits:  99%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 12.5               Pass: 100%/100 | Total:  1d 17h | Avg: 24m 46s | Max: 56m 07s | Hits:  66%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 52m 36s | Avg: 26m 18s | Max: 27m 47s | Hits:  59%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total: 59m 40s | Avg:  3m 58s | Max: 13m 56s | Hits:  99%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total:  1d 16h | Avg: 24m 44s | Max: 56m 07s | Hits:  66%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 52m 36s | Avg: 26m 18s | Max: 27m 47s | Hits:  59%/2354  
      🟩 nvcc               Pass: 100%/116 | Total:  1d 17h | Avg: 21m 30s | Max: 56m 07s | Hits:  71%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 29m | Avg: 14m 53s | Max: 27m 37s | Hits:  80%/7062  
      🟩 Clang10            Pass: 100%/3   | Total:  1h 19m | Avg: 26m 22s | Max: 28m 47s | Hits:  60%/3531  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 45m | Avg: 26m 26s | Max: 28m 45s | Hits:  60%/4708  
      🟩 Clang12            Pass: 100%/4   | Total:  1h 42m | Avg: 25m 39s | Max: 28m 29s | Hits:  60%/4708  
      🟩 Clang13            Pass: 100%/4   | Total:  1h 44m | Avg: 26m 11s | Max: 28m 14s | Hits:  60%/4708  
      🟩 Clang14            Pass: 100%/4   | Total:  1h 44m | Avg: 26m 13s | Max: 28m 35s | Hits:  60%/4708  
      🟩 Clang15            Pass: 100%/4   | Total:  1h 45m | Avg: 26m 28s | Max: 29m 04s | Hits:  60%/4708  
      🟩 Clang16            Pass: 100%/4   | Total:  1h 42m | Avg: 25m 44s | Max: 28m 05s | Hits:  60%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  5h 31m | Avg: 18m 26s | Max: 28m 32s | Hits:  77%/21186 
      🟩 GCC6               Pass: 100%/2   | Total:  6m 23s | Avg:  3m 11s | Max:  3m 21s | Hits:  99%/2354  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 28s | Max: 29m 18s | Hits:  80%/7068  
      🟩 GCC8               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 21s | Max: 27m 38s | Hits:  80%/7068  
      🟩 GCC9               Pass: 100%/6   | Total:  1h 34m | Avg: 15m 40s | Max: 31m 05s | Hits:  80%/7068  
      🟩 GCC10              Pass: 100%/4   | Total:  1h 51m | Avg: 27m 49s | Max: 32m 18s | Hits:  60%/4712  
      🟩 GCC11              Pass: 100%/7   | Total:  2h 05m | Avg: 17m 57s | Max: 32m 04s | Hits:  77%/8246  
      🟩 GCC12              Pass: 100%/4   | Total:  1h 52m | Avg: 28m 09s | Max: 32m 02s | Hits:  60%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  6h 15m | Avg: 18m 45s | Max: 34m 06s | Hits:  67%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 41m | Avg: 33m 42s | Max: 37m 31s | Hits:  60%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 56s | Avg: 13m 56s | Max: 13m 56s | Hits:  98%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 41m | Avg: 50m 31s | Max: 51m 42s | Hits:  58%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 26m | Avg: 34m 20s | Max: 56m 07s | Hits:  78%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total: 18h 47m | Avg: 22m 06s | Max: 29m 04s | Hits:  68%/60027 
      🟩 GCC                Pass: 100%/55  | Total: 16h 38m | Avg: 18m 08s | Max: 34m 06s | Hits:  73%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  1h 41m | Avg: 33m 42s | Max: 37m 31s | Hits:  60%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  5h 21m | Avg: 35m 40s | Max: 56m 07s | Hits:  76%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  1d 18h | Avg: 21m 35s | Max: 56m 07s | Hits:  71%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  1d 15h | Avg: 23m 41s | Max: 56m 07s | Hits:  65%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 40m | Avg:  9m 10s | Max: 18m 03s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 41m | Avg: 12m 38s | Max: 14m 44s | Hits:  99%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 90a                Pass: 100%/4   | Total:  1h 01m | Avg: 15m 23s | Max: 17m 21s | Hits:  60%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  8h 31m | Avg: 17m 03s | Max: 27m 42s | Hits:  73%/35328 
      🟩 14                 Pass: 100%/34  | Total: 12h 11m | Avg: 21m 31s | Max: 49m 21s | Hits:  72%/40020 
      🟩 17                 Pass: 100%/33  | Total: 12h 50m | Avg: 23m 21s | Max: 51m 42s | Hits:  70%/38847 
      🟩 20                 Pass: 100%/21  | Total:  8h 53m | Avg: 25m 23s | Max: 56m 07s | Hits:  67%/24717 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 1d 00h | Avg: 12m 59s | Max: 1h 01m | Hits: 73%/273250

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 22h 50m | Avg: 13m 10s | Max:  1h 01m | Hits:  73%/250904
      🟩 arm64              Pass: 100%/8   | Total:  1h 23m | Avg: 10m 29s | Max: 19m 45s | Hits:  71%/22346 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 19m | Avg:  9m 16s | Max: 41m 00s | Hits:  81%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 12.5               Pass: 100%/94  | Total: 21h 31m | Avg: 13m 44s | Max:  1h 01m | Hits:  71%/225406
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 35m 46s | Avg: 17m 53s | Max: 19m 09s | Hits:  37%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 19m | Avg:  9m 16s | Max: 41m 00s | Hits:  81%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 nvcc12.5           Pass: 100%/92  | Total: 20h 56m | Avg: 13m 39s | Max:  1h 01m | Hits:  72%/219307
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 35m 46s | Avg: 17m 53s | Max: 19m 09s | Hits:  37%/6099  
      🟩 nvcc               Pass: 100%/110 | Total: 23h 38m | Avg: 12m 53s | Max:  1h 01m | Hits:  73%/267151
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 05m | Avg: 10m 59s | Max: 20m 21s | Hits:  73%/16160 
      🟩 Clang10            Pass: 100%/3   | Total: 48m 03s | Avg: 16m 01s | Max: 23m 03s | Hits:  57%/8109  
      🟩 Clang11            Pass: 100%/4   | Total: 45m 21s | Avg: 11m 20s | Max: 19m 34s | Hits:  67%/11181 
      🟩 Clang12            Pass: 100%/4   | Total: 48m 42s | Avg: 12m 10s | Max: 19m 35s | Hits:  74%/11181 
      🟩 Clang13            Pass: 100%/4   | Total:  1h 00m | Avg: 15m 10s | Max: 19m 55s | Hits:  52%/11181 
      🟩 Clang14            Pass: 100%/4   | Total: 46m 24s | Avg: 11m 36s | Max: 19m 11s | Hits:  74%/11181 
      🟩 Clang15            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 20m 15s | Hits:  58%/11173 
      🟩 Clang16            Pass: 100%/4   | Total: 33m 05s | Avg:  8m 16s | Max: 19m 13s | Hits:  81%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  2h 20m | Avg: 10m 02s | Max: 19m 09s | Hits:  83%/28445 
      🟩 GCC6               Pass: 100%/2   | Total: 15m 05s | Avg:  7m 32s | Max: 12m 52s | Hits:  69%/5045  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 29m | Avg: 14m 51s | Max: 41m 00s | Hits:  75%/16146 
      🟩 GCC8               Pass: 100%/6   | Total: 57m 00s | Avg:  9m 30s | Max: 17m 56s | Hits:  67%/16154 
      🟩 GCC9               Pass: 100%/6   | Total:  1h 05m | Avg: 10m 50s | Max: 20m 00s | Hits:  72%/16158 
      🟩 GCC10              Pass: 100%/4   | Total: 46m 17s | Avg: 11m 34s | Max: 18m 53s | Hits:  72%/11181 
      🟩 GCC11              Pass: 100%/7   | Total:  1h 23m | Avg: 11m 55s | Max: 19m 42s | Hits:  68%/19237 
      🟩 GCC12              Pass: 100%/4   | Total: 31m 39s | Avg:  7m 54s | Max: 18m 53s | Hits:  80%/11173 
      🟩 GCC13              Pass: 100%/21  | Total:  6h 43m | Avg: 19m 11s | Max:  1h 01m | Hits:  67%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 20s | Avg:  5m 46s | Max:  6m 06s | Hits:  95%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 40s | Avg: 16m 40s | Max: 16m 40s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 37s | Avg: 11m 48s | Max: 12m 10s | Hits:  95%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 53m 24s | Avg: 17m 48s | Max: 26m 22s | Hits:  79%/8401  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/47  | Total:  9h 12m | Avg: 11m 45s | Max: 23m 03s | Hits:  71%/119784
      🟩 GCC                Pass: 100%/56  | Total: 13h 10m | Avg: 14m 07s | Max:  1h 01m | Hits:  71%/128996
      🟩 Intel              Pass: 100%/3   | Total: 17m 20s | Avg:  5m 46s | Max:  6m 06s | Hits:  95%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 33m | Avg: 15m 36s | Max: 26m 22s | Hits:  87%/16371 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total:  1d 00h | Avg: 12m 59s | Max:  1h 01m | Hits:  73%/273250
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 18h 54m | Avg: 11m 27s | Max: 41m 00s | Hits:  73%/273230
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 14m | Avg: 18m 32s | Max: 19m 53s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  4h 03m | Avg: 30m 26s | Max:  1h 01m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 50s | Avg:  1m 50s | Max:  1m 50s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 90a                Pass: 100%/4   | Total: 15m 40s | Avg:  3m 55s | Max:  4m 18s | Hits:  95%/11536 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  5h 53m | Avg: 12m 11s | Max: 41m 00s | Hits:  80%/58200 
      🟩 14                 Pass: 100%/32  | Total:  6h 33m | Avg: 12m 18s | Max: 26m 22s | Hits:  69%/81788 
      🟩 17                 Pass: 100%/31  | Total:  7h 05m | Avg: 13m 43s | Max: 59m 48s | Hits:  70%/84134 
      🟩 20                 Pass: 100%/19  | Total:  4h 39m | Avg: 14m 43s | Max:  1h 01m | Hits:  74%/49128 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 19m | Avg: 2m 32s | Max: 6m 48s | Hits: 96%/1583

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 11m | Avg:  2m 34s | Max:  6m 48s | Hits:  96%/1467  
      🟩 arm64              Pass: 100%/4   | Total:  8m 24s | Avg:  2m 06s | Max:  2m 22s | Hits:  96%/116   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total: 56m 59s | Avg:  2m 28s | Max:  6m 33s | Hits:  95%/661   
      🟩 12.5               Pass: 100%/32  | Total:  1h 22m | Avg:  2m 35s | Max:  6m 48s | Hits:  96%/922   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total: 56m 59s | Avg:  2m 28s | Max:  6m 33s | Hits:  95%/661   
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 22m | Avg:  2m 35s | Max:  6m 48s | Hits:  96%/922   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 19m | Avg:  2m 32s | Max:  6m 48s | Hits:  96%/1583  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 04s | Avg:  2m 02s | Max:  2m 16s | Hits: 100%/58    
      🟩 Clang10            Pass: 100%/2   | Total:  4m 17s | Avg:  2m 08s | Max:  2m 12s | Hits: 100%/58    
      🟩 Clang11            Pass: 100%/4   | Total:  7m 47s | Avg:  1m 56s | Max:  2m 15s | Hits: 100%/116   
      🟩 Clang12            Pass: 100%/4   | Total:  8m 40s | Avg:  2m 10s | Max:  2m 16s | Hits: 100%/116   
      🟩 Clang13            Pass: 100%/4   | Total:  8m 19s | Avg:  2m 04s | Max:  2m 15s | Hits: 100%/116   
      🟩 Clang14            Pass: 100%/6   | Total: 16m 38s | Avg:  2m 46s | Max:  4m 00s | Hits: 100%/174   
      🟩 Clang15            Pass: 100%/2   | Total:  4m 59s | Avg:  2m 29s | Max:  2m 43s | Hits: 100%/58    
      🟩 Clang16            Pass: 100%/6   | Total: 16m 59s | Avg:  2m 49s | Max:  4m 06s | Hits: 100%/174   
      🟩 GCC9               Pass: 100%/2   | Total:  3m 52s | Avg:  1m 56s | Max:  1m 57s | Hits:  93%/58    
      🟩 GCC10              Pass: 100%/4   | Total:  7m 48s | Avg:  1m 57s | Max:  2m 08s | Hits:  93%/116   
      🟩 GCC11              Pass: 100%/4   | Total:  8m 25s | Avg:  2m 06s | Max:  2m 21s | Hits:  93%/116   
      🟩 GCC12              Pass: 100%/12  | Total: 31m 57s | Avg:  2m 39s | Max:  4m 09s | Hits:  93%/348   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 35s | Avg:  2m 35s | Max:  2m 35s | Hits: 100%/29    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  6m 33s | Avg:  6m 33s | Max:  6m 33s | Hits:  65%/23    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 48s | Avg:  6m 48s | Max:  6m 48s | Hits:  65%/23    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 11m | Avg:  2m 23s | Max:  4m 06s | Hits: 100%/870   
      🟩 GCC                Pass: 100%/22  | Total: 52m 02s | Avg:  2m 21s | Max:  4m 09s | Hits:  93%/638   
      🟩 Intel              Pass: 100%/1   | Total:  2m 35s | Avg:  2m 35s | Max:  2m 35s | Hits: 100%/29    
      🟩 MSVC               Pass: 100%/2   | Total: 13m 21s | Avg:  6m 40s | Max:  6m 48s | Hits:  65%/46    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 19m | Avg:  2m 32s | Max:  6m 48s | Hits:  96%/1583  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  1h 49m | Avg:  2m 19s | Max:  6m 48s | Hits:  96%/1351  
      🟩 Test               Pass: 100%/8   | Total: 30m 10s | Avg:  3m 46s | Max:  4m 09s | Hits:  96%/232   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  1m 52s | Avg:  1m 52s | Max:  1m 52s | Hits:  93%/29    
      🟩 90a                Pass: 100%/1   | Total:  1m 59s | Avg:  1m 59s | Max:  1m 59s | Hits:  93%/29    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 12m | Avg:  2m 20s | Max:  3m 58s | Hits:  97%/899   
      🟩 20                 Pass: 100%/24  | Total:  1h 07m | Avg:  2m 47s | Max:  6m 48s | Hits:  95%/684   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    

👃 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: 417)

# Runner
305 linux-amd64-cpu16
61 linux-amd64-gpu-v100-latest-1
28 linux-arm64-cpu16
23 windows-amd64-cpu16

Copy link
Contributor

🟩 CI finished in 1d 06h: Pass: 100%/417 | Total: 6d 10h | Avg: 22m 10s | Max: 1h 08m | Hits: 71%/524869
  • 🟩 cub: Pass: 100%/131 | Total: 3d 12h | Avg: 38m 52s | Max: 1h 08m | Hits: 68%/111124

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total:  3d 05h | Avg: 37m 43s | Max:  1h 08m | Hits:  69%/104188
      🟩 arm64              Pass: 100%/8   | Total:  7h 32m | Avg: 56m 32s | Max:  1h 00m | Hits:  45%/6936  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 51m | Avg:  7m 27s | Max: 50m 56s | Hits:  97%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🟩 12.5               Pass: 100%/113 | Total:  3d 10h | Avg: 43m 57s | Max:  1h 08m | Hits:  63%/96731 
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 43m 31s | Avg: 21m 45s | Max: 21m 52s | Hits:  53%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 51m | Avg:  7m 27s | Max: 50m 56s | Hits:  97%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🟩 nvcc12.5           Pass: 100%/111 | Total:  3d 10h | Avg: 44m 21s | Max:  1h 08m | Hits:  64%/95295 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 43m 31s | Avg: 21m 45s | Max: 21m 52s | Hits:  53%/1436  
      🟩 nvcc               Pass: 100%/129 | Total:  3d 12h | Avg: 39m 08s | Max:  1h 08m | Hits:  68%/109688
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 50m | Avg: 28m 21s | Max: 56m 30s | Hits:  74%/4980  
      🟩 Clang10            Pass: 100%/3   | Total:  2h 46m | Avg: 55m 30s | Max: 57m 04s | Hits:  50%/2607  
      🟩 Clang11            Pass: 100%/4   | Total:  3h 28m | Avg: 52m 12s | Max: 55m 17s | Hits:  50%/3476  
      🟩 Clang12            Pass: 100%/4   | Total:  3h 37m | Avg: 54m 25s | Max: 58m 04s | Hits:  50%/3476  
      🟩 Clang13            Pass: 100%/4   | Total:  3h 29m | Avg: 52m 22s | Max: 54m 50s | Hits:  50%/3476  
      🟩 Clang14            Pass: 100%/4   | Total:  3h 36m | Avg: 54m 04s | Max:  1h 01m | Hits:  50%/3476  
      🟩 Clang15            Pass: 100%/4   | Total:  3h 34m | Avg: 53m 31s | Max: 56m 09s | Hits:  50%/3468  
      🟩 Clang16            Pass: 100%/4   | Total:  3h 33m | Avg: 53m 26s | Max: 56m 20s | Hits:  50%/3468  
      🟩 Clang17            Pass: 100%/26  | Total: 14h 00m | Avg: 32m 19s | Max: 58m 55s | Hits:  81%/22244 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 06s | Avg:  3m 33s | Max:  3m 50s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total:  2h 53m | Avg: 28m 52s | Max: 57m 28s | Hits:  73%/4983  
      🟩 GCC8               Pass: 100%/6   | Total:  3h 51m | Avg: 38m 30s | Max:  1h 03m | Hits:  67%/4983  
      🟩 GCC9               Pass: 100%/6   | Total:  2h 51m | Avg: 28m 38s | Max: 56m 14s | Hits:  73%/4983  
      🟩 GCC10              Pass: 100%/4   | Total:  3h 34m | Avg: 53m 36s | Max: 56m 17s | Hits:  50%/3476  
      🟩 GCC11              Pass: 100%/7   | Total:  3h 48m | Avg: 32m 38s | Max: 55m 49s | Hits:  71%/6069  
      🟩 GCC12              Pass: 100%/4   | Total:  3h 37m | Avg: 54m 24s | Max:  1h 00m | Hits:  49%/3468  
      🟩 GCC13              Pass: 100%/28  | Total: 14h 38m | Avg: 31m 21s | Max:  1h 00m | Hits:  75%/24276 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 58m | Avg: 59m 22s | Max:  1h 01m | Hits:  49%/2379  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 12m 41s | Avg: 12m 41s | Max: 12m 41s | Hits:  99%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 07m | Avg:  1h 03m | Max:  1h 04m | Hits:  52%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  3h 15m | Avg:  1h 05m | Max:  1h 08m | Hits:  52%/2127  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/59  | Total:  1d 16h | Avg: 41m 39s | Max:  1h 01m | Hits:  66%/50671 
      🟩 GCC                Pass: 100%/63  | Total:  1d 11h | Avg: 33m 40s | Max:  1h 03m | Hits:  71%/53820 
      🟩 Intel              Pass: 100%/3   | Total:  2h 58m | Avg: 59m 22s | Max:  1h 01m | Hits:  49%/2379  
      🟩 MSVC               Pass: 100%/6   | Total:  5h 35m | Avg: 55m 57s | Max:  1h 08m | Hits:  60%/4254  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total:  3d 12h | Avg: 38m 52s | Max:  1h 08m | Hits:  68%/111124
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  3d 01h | Avg: 44m 27s | Max:  1h 08m | Hits:  57%/83380 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 35m | Avg: 19m 28s | Max: 22m 40s | Hits:  99%/6936  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 41m | Avg: 20m 09s | Max: 40m 13s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 33m | Avg: 19m 13s | Max: 22m 25s | Hits:  99%/6936  
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 40m | Avg: 27m 34s | Max: 31m 24s | Hits:  99%/6936  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 41s | Avg:  4m 33s | Max:  4m 48s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total:  1h 31m | Avg: 22m 48s | Max: 23m 44s | Hits:  40%/3468  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total: 21h 50m | Avg: 38m 32s | Max:  1h 03m | Hits:  69%/29047 
      🟩 14                 Pass: 100%/37  | Total:  1d 00h | Avg: 39m 55s | Max:  1h 08m | Hits:  68%/31174 
      🟩 17                 Pass: 100%/36  | Total: 22h 27m | Avg: 37m 26s | Max:  1h 04m | Hits:  67%/30392 
      🟩 20                 Pass: 100%/24  | Total: 15h 58m | Avg: 39m 55s | Max:  1h 03m | Hits:  66%/20511 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 1d 18h | Avg: 21m 35s | Max: 56m 07s | Hits: 71%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  1d 14h | Avg: 21m 06s | Max: 56m 07s | Hits:  73%/129492
      🟩 arm64              Pass: 100%/8   | Total:  3h 45m | Avg: 28m 08s | Max: 34m 06s | Hits:  40%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total: 59m 40s | Avg:  3m 58s | Max: 13m 56s | Hits:  99%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 12.5               Pass: 100%/100 | Total:  1d 17h | Avg: 24m 46s | Max: 56m 07s | Hits:  66%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 52m 36s | Avg: 26m 18s | Max: 27m 47s | Hits:  59%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total: 59m 40s | Avg:  3m 58s | Max: 13m 56s | Hits:  99%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total:  1d 16h | Avg: 24m 44s | Max: 56m 07s | Hits:  66%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 52m 36s | Avg: 26m 18s | Max: 27m 47s | Hits:  59%/2354  
      🟩 nvcc               Pass: 100%/116 | Total:  1d 17h | Avg: 21m 30s | Max: 56m 07s | Hits:  71%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 29m | Avg: 14m 53s | Max: 27m 37s | Hits:  80%/7062  
      🟩 Clang10            Pass: 100%/3   | Total:  1h 19m | Avg: 26m 22s | Max: 28m 47s | Hits:  60%/3531  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 45m | Avg: 26m 26s | Max: 28m 45s | Hits:  60%/4708  
      🟩 Clang12            Pass: 100%/4   | Total:  1h 42m | Avg: 25m 39s | Max: 28m 29s | Hits:  60%/4708  
      🟩 Clang13            Pass: 100%/4   | Total:  1h 44m | Avg: 26m 11s | Max: 28m 14s | Hits:  60%/4708  
      🟩 Clang14            Pass: 100%/4   | Total:  1h 44m | Avg: 26m 13s | Max: 28m 35s | Hits:  60%/4708  
      🟩 Clang15            Pass: 100%/4   | Total:  1h 45m | Avg: 26m 28s | Max: 29m 04s | Hits:  60%/4708  
      🟩 Clang16            Pass: 100%/4   | Total:  1h 42m | Avg: 25m 44s | Max: 28m 05s | Hits:  60%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  5h 31m | Avg: 18m 26s | Max: 28m 32s | Hits:  77%/21186 
      🟩 GCC6               Pass: 100%/2   | Total:  6m 23s | Avg:  3m 11s | Max:  3m 21s | Hits:  99%/2354  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 28s | Max: 29m 18s | Hits:  80%/7068  
      🟩 GCC8               Pass: 100%/6   | Total:  1h 26m | Avg: 14m 21s | Max: 27m 38s | Hits:  80%/7068  
      🟩 GCC9               Pass: 100%/6   | Total:  1h 34m | Avg: 15m 40s | Max: 31m 05s | Hits:  80%/7068  
      🟩 GCC10              Pass: 100%/4   | Total:  1h 51m | Avg: 27m 49s | Max: 32m 18s | Hits:  60%/4712  
      🟩 GCC11              Pass: 100%/7   | Total:  2h 05m | Avg: 17m 57s | Max: 32m 04s | Hits:  77%/8246  
      🟩 GCC12              Pass: 100%/4   | Total:  1h 52m | Avg: 28m 09s | Max: 32m 02s | Hits:  60%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  6h 15m | Avg: 18m 45s | Max: 34m 06s | Hits:  67%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 41m | Avg: 33m 42s | Max: 37m 31s | Hits:  60%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 56s | Avg: 13m 56s | Max: 13m 56s | Hits:  98%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 41m | Avg: 50m 31s | Max: 51m 42s | Hits:  58%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 26m | Avg: 34m 20s | Max: 56m 07s | Hits:  78%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total: 18h 47m | Avg: 22m 06s | Max: 29m 04s | Hits:  68%/60027 
      🟩 GCC                Pass: 100%/55  | Total: 16h 38m | Avg: 18m 08s | Max: 34m 06s | Hits:  73%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  1h 41m | Avg: 33m 42s | Max: 37m 31s | Hits:  60%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  5h 21m | Avg: 35m 40s | Max: 56m 07s | Hits:  76%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  1d 18h | Avg: 21m 35s | Max: 56m 07s | Hits:  71%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  1d 15h | Avg: 23m 41s | Max: 56m 07s | Hits:  65%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 40m | Avg:  9m 10s | Max: 18m 03s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 41m | Avg: 12m 38s | Max: 14m 44s | Hits:  99%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 10m 56s | Avg:  3m 38s | Max:  3m 48s | Hits:  99%/3534  
      🟩 90a                Pass: 100%/4   | Total:  1h 01m | Avg: 15m 23s | Max: 17m 21s | Hits:  60%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  8h 31m | Avg: 17m 03s | Max: 27m 42s | Hits:  73%/35328 
      🟩 14                 Pass: 100%/34  | Total: 12h 11m | Avg: 21m 31s | Max: 49m 21s | Hits:  72%/40020 
      🟩 17                 Pass: 100%/33  | Total: 12h 50m | Avg: 23m 21s | Max: 51m 42s | Hits:  70%/38847 
      🟩 20                 Pass: 100%/21  | Total:  8h 53m | Avg: 25m 23s | Max: 56m 07s | Hits:  67%/24717 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 1d 00h | Avg: 12m 59s | Max: 1h 01m | Hits: 73%/273250

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 22h 50m | Avg: 13m 10s | Max:  1h 01m | Hits:  73%/250904
      🟩 arm64              Pass: 100%/8   | Total:  1h 23m | Avg: 10m 29s | Max: 19m 45s | Hits:  71%/22346 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 19m | Avg:  9m 16s | Max: 41m 00s | Hits:  81%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 12.5               Pass: 100%/94  | Total: 21h 31m | Avg: 13m 44s | Max:  1h 01m | Hits:  71%/225406
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 35m 46s | Avg: 17m 53s | Max: 19m 09s | Hits:  37%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 19m | Avg:  9m 16s | Max: 41m 00s | Hits:  81%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 nvcc12.5           Pass: 100%/92  | Total: 20h 56m | Avg: 13m 39s | Max:  1h 01m | Hits:  72%/219307
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 35m 46s | Avg: 17m 53s | Max: 19m 09s | Hits:  37%/6099  
      🟩 nvcc               Pass: 100%/110 | Total: 23h 38m | Avg: 12m 53s | Max:  1h 01m | Hits:  73%/267151
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 05m | Avg: 10m 59s | Max: 20m 21s | Hits:  73%/16160 
      🟩 Clang10            Pass: 100%/3   | Total: 48m 03s | Avg: 16m 01s | Max: 23m 03s | Hits:  57%/8109  
      🟩 Clang11            Pass: 100%/4   | Total: 45m 21s | Avg: 11m 20s | Max: 19m 34s | Hits:  67%/11181 
      🟩 Clang12            Pass: 100%/4   | Total: 48m 42s | Avg: 12m 10s | Max: 19m 35s | Hits:  74%/11181 
      🟩 Clang13            Pass: 100%/4   | Total:  1h 00m | Avg: 15m 10s | Max: 19m 55s | Hits:  52%/11181 
      🟩 Clang14            Pass: 100%/4   | Total: 46m 24s | Avg: 11m 36s | Max: 19m 11s | Hits:  74%/11181 
      🟩 Clang15            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 20m 15s | Hits:  58%/11173 
      🟩 Clang16            Pass: 100%/4   | Total: 33m 05s | Avg:  8m 16s | Max: 19m 13s | Hits:  81%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  2h 20m | Avg: 10m 02s | Max: 19m 09s | Hits:  83%/28445 
      🟩 GCC6               Pass: 100%/2   | Total: 15m 05s | Avg:  7m 32s | Max: 12m 52s | Hits:  69%/5045  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 29m | Avg: 14m 51s | Max: 41m 00s | Hits:  75%/16146 
      🟩 GCC8               Pass: 100%/6   | Total: 57m 00s | Avg:  9m 30s | Max: 17m 56s | Hits:  67%/16154 
      🟩 GCC9               Pass: 100%/6   | Total:  1h 05m | Avg: 10m 50s | Max: 20m 00s | Hits:  72%/16158 
      🟩 GCC10              Pass: 100%/4   | Total: 46m 17s | Avg: 11m 34s | Max: 18m 53s | Hits:  72%/11181 
      🟩 GCC11              Pass: 100%/7   | Total:  1h 23m | Avg: 11m 55s | Max: 19m 42s | Hits:  68%/19237 
      🟩 GCC12              Pass: 100%/4   | Total: 31m 39s | Avg:  7m 54s | Max: 18m 53s | Hits:  80%/11173 
      🟩 GCC13              Pass: 100%/21  | Total:  6h 43m | Avg: 19m 11s | Max:  1h 01m | Hits:  67%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 20s | Avg:  5m 46s | Max:  6m 06s | Hits:  95%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 40s | Avg: 16m 40s | Max: 16m 40s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 37s | Avg: 11m 48s | Max: 12m 10s | Hits:  95%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 53m 24s | Avg: 17m 48s | Max: 26m 22s | Hits:  79%/8401  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/47  | Total:  9h 12m | Avg: 11m 45s | Max: 23m 03s | Hits:  71%/119784
      🟩 GCC                Pass: 100%/56  | Total: 13h 10m | Avg: 14m 07s | Max:  1h 01m | Hits:  71%/128996
      🟩 Intel              Pass: 100%/3   | Total: 17m 20s | Avg:  5m 46s | Max:  6m 06s | Hits:  95%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 33m | Avg: 15m 36s | Max: 26m 22s | Hits:  87%/16371 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total:  1d 00h | Avg: 12m 59s | Max:  1h 01m | Hits:  73%/273250
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 18h 54m | Avg: 11m 27s | Max: 41m 00s | Hits:  73%/273230
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 14m | Avg: 18m 32s | Max: 19m 53s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  4h 03m | Avg: 30m 26s | Max:  1h 01m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 50s | Avg:  1m 50s | Max:  1m 50s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 23m 21s | Avg:  7m 47s | Max: 16m 40s | Hits:  79%/8064  
      🟩 90a                Pass: 100%/4   | Total: 15m 40s | Avg:  3m 55s | Max:  4m 18s | Hits:  95%/11536 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  5h 53m | Avg: 12m 11s | Max: 41m 00s | Hits:  80%/58200 
      🟩 14                 Pass: 100%/32  | Total:  6h 33m | Avg: 12m 18s | Max: 26m 22s | Hits:  69%/81788 
      🟩 17                 Pass: 100%/31  | Total:  7h 05m | Avg: 13m 43s | Max: 59m 48s | Hits:  70%/84134 
      🟩 20                 Pass: 100%/19  | Total:  4h 39m | Avg: 14m 43s | Max:  1h 01m | Hits:  74%/49128 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 19m | Avg: 2m 32s | Max: 6m 48s | Hits: 96%/1583

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 11m | Avg:  2m 34s | Max:  6m 48s | Hits:  96%/1467  
      🟩 arm64              Pass: 100%/4   | Total:  8m 24s | Avg:  2m 06s | Max:  2m 22s | Hits:  96%/116   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total: 56m 59s | Avg:  2m 28s | Max:  6m 33s | Hits:  95%/661   
      🟩 12.5               Pass: 100%/32  | Total:  1h 22m | Avg:  2m 35s | Max:  6m 48s | Hits:  96%/922   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total: 56m 59s | Avg:  2m 28s | Max:  6m 33s | Hits:  95%/661   
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 22m | Avg:  2m 35s | Max:  6m 48s | Hits:  96%/922   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 19m | Avg:  2m 32s | Max:  6m 48s | Hits:  96%/1583  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 04s | Avg:  2m 02s | Max:  2m 16s | Hits: 100%/58    
      🟩 Clang10            Pass: 100%/2   | Total:  4m 17s | Avg:  2m 08s | Max:  2m 12s | Hits: 100%/58    
      🟩 Clang11            Pass: 100%/4   | Total:  7m 47s | Avg:  1m 56s | Max:  2m 15s | Hits: 100%/116   
      🟩 Clang12            Pass: 100%/4   | Total:  8m 40s | Avg:  2m 10s | Max:  2m 16s | Hits: 100%/116   
      🟩 Clang13            Pass: 100%/4   | Total:  8m 19s | Avg:  2m 04s | Max:  2m 15s | Hits: 100%/116   
      🟩 Clang14            Pass: 100%/6   | Total: 16m 38s | Avg:  2m 46s | Max:  4m 00s | Hits: 100%/174   
      🟩 Clang15            Pass: 100%/2   | Total:  4m 59s | Avg:  2m 29s | Max:  2m 43s | Hits: 100%/58    
      🟩 Clang16            Pass: 100%/6   | Total: 16m 59s | Avg:  2m 49s | Max:  4m 06s | Hits: 100%/174   
      🟩 GCC9               Pass: 100%/2   | Total:  3m 52s | Avg:  1m 56s | Max:  1m 57s | Hits:  93%/58    
      🟩 GCC10              Pass: 100%/4   | Total:  7m 48s | Avg:  1m 57s | Max:  2m 08s | Hits:  93%/116   
      🟩 GCC11              Pass: 100%/4   | Total:  8m 25s | Avg:  2m 06s | Max:  2m 21s | Hits:  93%/116   
      🟩 GCC12              Pass: 100%/12  | Total: 31m 57s | Avg:  2m 39s | Max:  4m 09s | Hits:  93%/348   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 35s | Avg:  2m 35s | Max:  2m 35s | Hits: 100%/29    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  6m 33s | Avg:  6m 33s | Max:  6m 33s | Hits:  65%/23    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 48s | Avg:  6m 48s | Max:  6m 48s | Hits:  65%/23    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 11m | Avg:  2m 23s | Max:  4m 06s | Hits: 100%/870   
      🟩 GCC                Pass: 100%/22  | Total: 52m 02s | Avg:  2m 21s | Max:  4m 09s | Hits:  93%/638   
      🟩 Intel              Pass: 100%/1   | Total:  2m 35s | Avg:  2m 35s | Max:  2m 35s | Hits: 100%/29    
      🟩 MSVC               Pass: 100%/2   | Total: 13m 21s | Avg:  6m 40s | Max:  6m 48s | Hits:  65%/46    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 19m | Avg:  2m 32s | Max:  6m 48s | Hits:  96%/1583  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  1h 49m | Avg:  2m 19s | Max:  6m 48s | Hits:  96%/1351  
      🟩 Test               Pass: 100%/8   | Total: 30m 10s | Avg:  3m 46s | Max:  4m 09s | Hits:  96%/232   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  1m 52s | Avg:  1m 52s | Max:  1m 52s | Hits:  93%/29    
      🟩 90a                Pass: 100%/1   | Total:  1m 59s | Avg:  1m 59s | Max:  1m 59s | Hits:  93%/29    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 12m | Avg:  2m 20s | Max:  3m 58s | Hits:  97%/899   
      🟩 20                 Pass: 100%/24  | Total:  1h 07m | Avg:  2m 47s | Max:  6m 48s | Hits:  95%/684   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 10m 54s | Avg: 10m 54s | Max: 10m 54s
    

👃 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: 417)

# Runner
305 linux-amd64-cpu16
61 linux-amd64-gpu-v100-latest-1
28 linux-arm64-cpu16
23 windows-amd64-cpu16

Copy link
Contributor

@bernhardmgruber bernhardmgruber left a comment

Choose a reason for hiding this comment

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

LGTM, except for:

@@ -37,47 +37,47 @@ _LIBCUDACXX_BEGIN_NAMESPACE_STD
// trigonometric functions
inline _LIBCUDACXX_INLINE_VISIBILITY __nv_bfloat16 sin(__nv_bfloat16 __v)
{
NV_IF_ELSE_TARGET(NV_IS_DEVICE, (return ::hsin(__v);), (return __nv_bfloat16(::sin(float(__v)));))
NV_IF_ELSE_TARGET(NV_IS_DEVICE, (return ::hsin(__v);), (return __float2bfloat16(::sin(__bfloat162float(__v)));))
Copy link
Contributor

Choose a reason for hiding this comment

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

Important: The host path does not seem right. The code calls the C library's ::sin here, which promotes the argumet to a double. We should either call ::sinf or std::sin here.

Applies to several math functions below.

Copy link
Contributor

Choose a reason for hiding this comment

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

Created issue: #2078

Copy link
Collaborator

@griwes griwes left a comment

Choose a reason for hiding this comment

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

LGTM. @bernhardmgruber is right about the host paths I think, but this was preexisting condition of how I wrote that code in the first place, so while we should fix that, it shouldn't block this.

@miscco miscco merged commit 1797742 into NVIDIA:main Jul 25, 2024
432 of 434 checks passed
@miscco miscco deleted the avoid_extended_floatingpoint_conversions branch July 25, 2024 21:28
pciolkosz pushed a commit to pciolkosz/cccl that referenced this pull request Aug 4, 2024
…types (NVIDIA#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
pciolkosz pushed a commit to pciolkosz/cccl that referenced this pull request Aug 4, 2024
…types (NVIDIA#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
wmaxey pushed a commit that referenced this pull request Aug 12, 2024
…types (#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
wmaxey pushed a commit that referenced this pull request Aug 13, 2024
…types (#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
wmaxey pushed a commit that referenced this pull request Aug 13, 2024
…types (#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test
wmaxey added a commit that referenced this pull request Aug 14, 2024
* Do not rely on conversions between float and extended floating point types (#2046)

The issue we have is that our tests rely extensively on those conversions which makes it incredibly painfull to test

* Fix including `<complex>` when bad CUDA bfloat/half macros are used. (#2226)

* Add <complex> test for bad macros being defined

* Fix <complex> failing upon inclusion when bad macros are defined

* Rather use explicit specializations and some evil hackery to get the complex interop to work

* Fix typos

* Inline everything

* Move workarounds together

* Use conversion functions instead of explicit specializations

* Drop unneeded conversions

---------

Co-authored-by: Michael Schellenberger Costa <[email protected]>

---------

Co-authored-by: Michael Schellenberger Costa <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug: functional libcu++ For all items related to libcu++ nvbug Has an associated internal NVIDIA NVBug.
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

3 participants