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

[PoC]: Implement cuda::experimental::uninitialized_buffer #1831

Merged
merged 3 commits into from
Jul 31, 2024

Conversation

miscco
Copy link
Collaborator

@miscco miscco commented Jun 10, 2024

This uninitialized_buffer provides an allocation of N elements of type T utilitzing a cuda::mr::resource to allocate the storage.

The buffer takes care of alignment and deallocation of the storage. The user is required to ensure that the lifetime of the memory resource exceeds the lifetime of the buffer.

Design choices:

  1. uninitialized is in the name. Reading uninitialized memory is one of the more common security issues in C++ so we want it to be in the name.
  2. It is typed. There are some nontrivial calculations to be had. Does it account for the size of T what about alignment? We do not want to put that on the user, but uninitialized_buffer does it for you
  3. minimal interface. This is not a vector, we do not want to resize it. So the API is as minimal as possible containing only data(), size() and to_span() member functions.
  4. Interacts well with memory resources and their property system. Its the new thing and we want it.

What it is not:

There is unique_ptr<T[]> but that is a horrible design:

  • unique_ptr does initialize its element(s) which we explicitly do not want
  • unique_ptr in its current form has no way of passing in the allocator / memory resource used
  • unique_ptr does not offer the common size() and data() interface

Copy link
Contributor

🟨 CI finished in 2h 48m: Pass: 95%/361 | Total: 2d 04h | Avg: 8m 44s | Max: 40m 50s | Hits: 96%/481443
  • 🟨 libcudacxx: Pass: 87%/112 | Total: 22h 43m | Avg: 12m 10s | Max: 40m 50s | Hits: 93%/236537

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  86%/104 | Total: 21h 11m | Avg: 12m 13s | Max: 40m 50s | Hits:  93%/214125
      🟩 arm64              Pass: 100%/8   | Total:  1h 31m | Avg: 11m 29s | Max: 13m 47s | Hits:  91%/22412 
    🔍 cudacxx_name: nvcc 🔍
      🟩 clang-cuda         Pass: 100%/2   | Total: 36m 27s | Avg: 18m 13s | Max: 19m 11s | Hits:  37%/6121  
      🔍 nvcc               Pass:  87%/110 | Total: 22h 06m | Avg: 12m 03s | Max: 40m 50s | Hits:  95%/230416
    🟨 ctk
      🟨 11.1               Pass:  86%/15  | Total:  2h 26m | Avg:  9m 45s | Max: 40m 50s | Hits:  96%/34039 
      🟩 11.8               Pass: 100%/3   | Total: 53m 50s | Avg: 17m 56s | Max: 19m 59s | Hits:  69%/8086  
      🟨 12.4               Pass:  87%/94  | Total: 19h 22m | Avg: 12m 22s | Max: 25m 57s | Hits:  94%/194412
    🟨 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 36m 27s | Avg: 18m 13s | Max: 19m 11s | Hits:  37%/6121  
      🟨 nvcc11.1           Pass:  86%/15  | Total:  2h 26m | Avg:  9m 45s | Max: 40m 50s | Hits:  96%/34039 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 53m 50s | Avg: 17m 56s | Max: 19m 59s | Hits:  69%/8086  
      🟨 nvcc12.4           Pass:  86%/92  | Total: 18h 46m | Avg: 12m 14s | Max: 25m 57s | Hits:  96%/188291
    🟨 cxx_full
      🟨 clang9             Pass:  33%/6   | Total:  1h 15m | Avg: 12m 32s | Max: 16m 26s | Hits:  97%/4464  
      🟨 clang10            Pass:  33%/3   | Total: 52m 49s | Avg: 17m 36s | Max: 20m 17s | Hits:  70%/2239  
      🟩 clang11            Pass: 100%/4   | Total: 57m 51s | Avg: 14m 27s | Max: 15m 16s | Hits:  97%/11214 
      🟩 clang12            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 45s | Max: 19m 02s | Hits:  87%/11214 
      🟩 clang13            Pass: 100%/4   | Total: 38m 50s | Avg:  9m 42s | Max: 15m 30s | Hits:  98%/11214 
      🟩 clang14            Pass: 100%/4   | Total: 49m 40s | Avg: 12m 25s | Max: 15m 53s | Hits:  97%/11214 
      🟩 clang15            Pass: 100%/4   | Total: 43m 28s | Avg: 10m 52s | Max: 19m 10s | Hits:  93%/11206 
      🟨 clang16            Pass:  25%/4   | Total: 47m 20s | Avg: 11m 50s | Max: 14m 41s | Hits:  97%/2237  
      🟨 clang17            Pass:  92%/14  | Total:  2h 54m | Avg: 12m 28s | Max: 19m 11s | Hits:  83%/28533 
      🟩 gcc6               Pass: 100%/2   | Total: 43m 48s | Avg: 21m 54s | Max: 40m 50s | Hits:  86%/5056  
      🟩 gcc7               Pass: 100%/6   | Total:  1h 00m | Avg: 10m 05s | Max: 15m 29s | Hits:  97%/16190 
      🟩 gcc8               Pass: 100%/6   | Total: 59m 33s | Avg:  9m 55s | Max: 15m 39s | Hits:  97%/16198 
      🟩 gcc9               Pass: 100%/6   | Total: 38m 14s | Avg:  6m 22s | Max: 14m 08s | Hits:  98%/16202 
      🟩 gcc10              Pass: 100%/4   | Total: 36m 28s | Avg:  9m 07s | Max: 15m 10s | Hits:  98%/11214 
      🟩 gcc11              Pass: 100%/7   | Total:  1h 40m | Avg: 14m 24s | Max: 19m 59s | Hits:  85%/19292 
      🟩 gcc12              Pass: 100%/4   | Total: 47m 27s | Avg: 11m 51s | Max: 14m 48s | Hits:  97%/11206 
      🟩 gcc13              Pass: 100%/21  | Total:  4h 28m | Avg: 12m 46s | Max: 25m 57s | Hits:  96%/34001 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 27m 22s | Avg:  9m 07s | Max: 17m 02s | Hits:  98%/8121  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 19s | Avg: 16m 19s | Max: 16m 19s | Hits:  99%/2544  
      🟥 MSVC14.29          Pass:   0%/2   | Total: 24m 09s | Avg: 12m 04s | Max: 12m 08s
      🟨 MSVC14.39          Pass:  33%/3   | Total: 37m 04s | Avg: 12m 21s | Max: 12m 50s | Hits:  99%/2978  
    🟨 cxx_name
      🟨 clang              Pass:  78%/47  | Total: 10h 02m | Avg: 12m 49s | Max: 20m 17s | Hits:  90%/93535 
      🟩 gcc                Pass: 100%/56  | Total: 10h 55m | Avg: 11m 42s | Max: 40m 50s | Hits:  95%/129359
      🟩 Intel              Pass: 100%/3   | Total: 27m 22s | Avg:  9m 07s | Max: 17m 02s | Hits:  98%/8121  
      🟨 MSVC               Pass:  33%/6   | Total:  1h 17m | Avg: 12m 55s | Max: 16m 19s | Hits:  99%/5522  
    🟨 jobs
      🟨 Build              Pass:  86%/99  | Total: 18h 54m | Avg: 11m 27s | Max: 40m 50s | Hits:  93%/236517
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 08m | Avg: 17m 13s | Max: 18m 03s | Hits: 100%/20    
      🟨 Test               Pass:  87%/8   | Total:  2h 37m | Avg: 19m 38s | Max: 25m 57s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 05s | Avg:  2m 05s | Max:  2m 05s
    🟨 std
      🟩 11                 Pass: 100%/29  | Total:  6h 01m | Avg: 12m 27s | Max: 40m 50s | Hits:  94%/58200 
      🟨 14                 Pass:  81%/32  | Total:  6h 21m | Avg: 11m 54s | Max: 23m 16s | Hits:  96%/65397 
      🟨 17                 Pass:  77%/31  | Total:  6h 22m | Avg: 12m 20s | Max: 24m 12s | Hits:  91%/66717 
      🟨 20                 Pass:  94%/19  | Total:  3h 56m | Avg: 12m 26s | Max: 25m 57s | Hits:  92%/46223 
    🟨 gpu
      🟨 v100               Pass:  87%/112 | Total: 22h 43m | Avg: 12m 10s | Max: 40m 50s | Hits:  93%/236537
    🟨 os
      🟨 ubuntu18.04        Pass:  85%/14  | Total:  2h 09m | Avg:  9m 17s | Max: 40m 50s | Hits:  96%/31495 
      🟨 ubuntu20.04        Pass:  88%/35  | Total:  7h 26m | Avg: 12m 44s | Max: 20m 17s | Hits:  95%/84924 
      🟨 ubuntu22.04        Pass:  92%/57  | Total: 11h 49m | Avg: 12m 26s | Max: 25m 57s | Hits:  91%/114596
      🟨 windows2022        Pass:  33%/6   | Total:  1h 17m | Avg: 12m 55s | Max: 16m 19s | Hits:  99%/5522  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 53m 50s | Avg: 17m 56s | Max: 19m 59s | Hits:  69%/8086  
      🟩 90a                Pass: 100%/4   | Total: 14m 53s | Avg:  3m 43s | Max:  4m 07s | Hits:  99%/11569 
    
  • 🟨 cub: Pass: 96%/131 | Total: 18h 40m | Avg: 8m 33s | Max: 39m 38s | Hits: 99%/105640

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  96%/123 | Total: 18h 04m | Avg:  8m 48s | Max: 39m 38s | Hits:  99%/98832 
      🟩 arm64              Pass: 100%/8   | Total: 36m 49s | Avg:  4m 36s | Max:  5m 03s | Hits:  99%/6808  
    🔍 ctk: 12.4 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 05m | Avg:  4m 21s | Max: 13m 43s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 13m 28s | Avg:  4m 29s | Max:  4m 35s | Hits:  99%/2553  
      🔍 12.4               Pass:  96%/113 | Total: 17h 22m | Avg:  9m 13s | Max: 39m 38s | Hits:  99%/91533 
    🔍 cudacxx_full: nvcc12.4 🔍
      🟩 clang-cuda17       Pass: 100%/2   | Total:  7m 24s | Avg:  3m 42s | Max:  3m 47s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 05m | Avg:  4m 21s | Max: 13m 43s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 28s | Avg:  4m 29s | Max:  4m 35s | Hits:  99%/2553  
      🔍 nvcc12.4           Pass:  96%/111 | Total: 17h 14m | Avg:  9m 19s | Max: 39m 38s | Hits:  99%/90125 
    🔍 cudacxx_name: nvcc 🔍
      🟩 clang-cuda         Pass: 100%/2   | Total:  7m 24s | Avg:  3m 42s | Max:  3m 47s | Hits: 100%/1408  
      🔍 nvcc               Pass:  96%/129 | Total: 18h 33m | Avg:  8m 37s | Max: 39m 38s | Hits:  99%/104232
    🔍 os: ubuntu22.04 🔍
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 51m 39s | Avg:  3m 41s | Max:  3m 51s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 41m | Avg:  4m 36s | Max:  5m 36s | Hits:  99%/29855 
      🔍 ubuntu22.04        Pass:  94%/76  | Total: 13h 57m | Avg: 11m 01s | Max: 39m 38s | Hits:  99%/60756 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 10m | Avg: 11m 45s | Max: 13m 43s | Hits:  98%/4170  
    🟨 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 26m 28s | Avg:  4m 24s | Max:  5m 08s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 15m 47s | Avg:  5m 15s | Max:  5m 36s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 17m 29s | Avg:  4m 22s | Max:  4m 26s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 17m 44s | Avg:  4m 26s | Max:  4m 47s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 17m 52s | Avg:  4m 28s | Max:  4m 31s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 17m 18s | Avg:  4m 19s | Max:  4m 27s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 18m 29s | Avg:  4m 37s | Max:  4m 52s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 18m 05s | Avg:  4m 31s | Max:  4m 42s | Hits: 100%/3404  
      🟨 clang17            Pass:  96%/26  | Total:  6h 40m | Avg: 15m 24s | Max: 39m 38s | Hits:  99%/20981 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 13s | Avg:  3m 36s | Max:  3m 42s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 24m 41s | Avg:  4m 06s | Max:  4m 45s | Hits:  99%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 24m 44s | Avg:  4m 07s | Max:  4m 38s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 26m 17s | Avg:  4m 22s | Max:  5m 19s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 17m 17s | Avg:  4m 19s | Max:  4m 29s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 31m 50s | Avg:  4m 32s | Max:  5m 26s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 19m 23s | Avg:  4m 50s | Max:  5m 14s | Hits:  99%/3404  
      🟨 gcc13              Pass:  89%/28  | Total:  5h 32m | Avg: 11m 53s | Max: 28m 19s | Hits:  99%/21275 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 16m 22s | Avg:  5m 27s | Max:  5m 38s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 43s | Avg: 13m 43s | Max: 13m 43s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 27s | Avg: 11m 13s | Max: 11m 29s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 34m 23s | Avg: 11m 27s | Max: 12m 04s | Hits:  98%/2085  
    🟨 cxx_name
      🟨 clang              Pass:  98%/59  | Total:  9h 09m | Avg:  9m 19s | Max: 39m 38s | Hits:  99%/48880 
      🟨 gcc                Pass:  95%/63  | Total:  8h 04m | Avg:  7m 41s | Max: 28m 19s | Hits:  99%/50259 
      🟩 Intel              Pass: 100%/3   | Total: 16m 22s | Avg:  5m 27s | Max:  5m 38s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 10m | Avg: 11m 45s | Max: 13m 43s | Hits:  98%/4170  
    🟨 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 04m | Avg:  4m 53s | Max: 13m 43s | Hits:  99%/81812 
      🟨 DeviceLaunch       Pass:  75%/8   | Total:  2h 20m | Avg: 17m 36s | Max: 25m 51s | Hits:  99%/5106  
      🟨 GraphCapture       Pass:  87%/8   | Total:  2h 01m | Avg: 15m 10s | Max: 22m 27s | Hits:  99%/5957  
      🟨 HostLaunch         Pass:  87%/8   | Total:  2h 11m | Avg: 16m 24s | Max: 20m 57s | Hits:  99%/5957  
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 03m | Avg: 30m 24s | Max: 39m 38s | Hits:  99%/6808  
    🟨 std
      🟩 11                 Pass: 100%/34  | Total:  4h 50m | Avg:  8m 31s | Max: 39m 38s | Hits:  99%/28503 
      🟨 14                 Pass:  94%/37  | Total:  5h 00m | Avg:  8m 06s | Max: 32m 57s | Hits:  99%/28886 
      🟩 17                 Pass: 100%/36  | Total:  5h 19m | Avg:  8m 52s | Max: 39m 05s | Hits:  99%/29822 
      🟨 20                 Pass:  91%/24  | Total:  3h 31m | Avg:  8m 48s | Max: 26m 54s | Hits:  99%/18429 
    🟨 gpu
      🟨 v100               Pass:  96%/131 | Total: 18h 40m | Avg:  8m 33s | Max: 39m 38s | Hits:  99%/105640
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 28s | Avg:  4m 29s | Max:  4m 35s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 16m 08s | Avg:  4m 02s | Max:  4m 07s | Hits:  99%/3404  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 09m | Avg: 5m 40s | Max: 21m 23s | Hits: 99%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 10h 38m | Avg:  5m 48s | Max: 21m 23s | Hits:  99%/129822
      🟩 arm64              Pass: 100%/8   | Total: 31m 14s | Avg:  3m 54s | Max:  4m 18s | Hits:  99%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 03m | Avg:  4m 12s | Max: 14m 52s | Hits:  99%/17705 
      🟩 11.8               Pass: 100%/3   | Total: 11m 14s | Avg:  3m 44s | Max:  3m 55s | Hits:  99%/3543  
      🟩 12.4               Pass: 100%/100 | Total:  9h 55m | Avg:  5m 57s | Max: 21m 23s | Hits:  99%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  8m 20s | Avg:  4m 10s | Max:  4m 25s | Hits: 100%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 03m | Avg:  4m 12s | Max: 14m 52s | Hits:  99%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 14s | Avg:  3m 44s | Max:  3m 55s | Hits:  99%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total:  9h 47m | Avg:  5m 59s | Max: 21m 23s | Hits:  99%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  8m 20s | Avg:  4m 10s | Max:  4m 25s | Hits: 100%/2360  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 01m | Avg:  5m 42s | Max: 21m 23s | Hits:  99%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 23m 36s | Avg:  3m 56s | Max:  4m 34s | Hits: 100%/7080  
      🟩 clang10            Pass: 100%/3   | Total: 13m 06s | Avg:  4m 22s | Max:  4m 32s | Hits: 100%/3540  
      🟩 clang11            Pass: 100%/4   | Total: 16m 46s | Avg:  4m 11s | Max:  4m 25s | Hits: 100%/4720  
      🟩 clang12            Pass: 100%/4   | Total: 16m 01s | Avg:  4m 00s | Max:  4m 11s | Hits: 100%/4720  
      🟩 clang13            Pass: 100%/4   | Total: 15m 54s | Avg:  3m 58s | Max:  4m 10s | Hits: 100%/4720  
      🟩 clang14            Pass: 100%/4   | Total: 14m 53s | Avg:  3m 43s | Max:  3m 53s | Hits: 100%/4720  
      🟩 clang15            Pass: 100%/4   | Total: 15m 40s | Avg:  3m 55s | Max:  4m 11s | Hits: 100%/4720  
      🟩 clang16            Pass: 100%/4   | Total: 15m 35s | Avg:  3m 53s | Max:  4m 14s | Hits: 100%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  2h 07m | Avg:  7m 03s | Max: 21m 23s | Hits: 100%/21240 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 07s | Avg:  3m 33s | Max:  3m 49s | Hits:  99%/2360  
      🟩 gcc7               Pass: 100%/6   | Total: 20m 58s | Avg:  3m 29s | Max:  3m 47s | Hits:  99%/7086  
      🟩 gcc8               Pass: 100%/6   | Total: 21m 53s | Avg:  3m 38s | Max:  4m 16s | Hits:  99%/7086  
      🟩 gcc9               Pass: 100%/6   | Total: 21m 20s | Avg:  3m 33s | Max:  3m 53s | Hits:  99%/7086  
      🟩 gcc10              Pass: 100%/4   | Total: 16m 29s | Avg:  4m 07s | Max:  4m 19s | Hits:  99%/4724  
      🟩 gcc11              Pass: 100%/7   | Total: 26m 40s | Avg:  3m 48s | Max:  4m 28s | Hits:  99%/8267  
      🟩 gcc12              Pass: 100%/4   | Total: 16m 07s | Avg:  4m 01s | Max:  4m 15s | Hits:  99%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  2h 10m | Avg:  6m 31s | Max: 15m 15s | Hits:  99%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 14m 41s | Avg:  4m 53s | Max:  5m 30s | Hits: 100%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 14m 52s | Avg: 14m 52s | Max: 14m 52s | Hits:  98%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 25m 35s | Avg: 12m 47s | Max: 13m 02s | Hits:  98%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 35m | Avg: 15m 52s | Max: 20m 16s | Hits:  98%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total:  4h 18m | Avg:  5m 04s | Max: 21m 23s | Hits: 100%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  4h 21m | Avg:  4m 44s | Max: 15m 15s | Hits:  99%/64953 
      🟩 Intel              Pass: 100%/3   | Total: 14m 41s | Avg:  4m 53s | Max:  5m 30s | Hits: 100%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 15m | Avg: 15m 04s | Max: 20m 16s | Hits:  98%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 09m | Avg:  5m 40s | Max: 21m 23s | Hits:  99%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  7h 21m | Avg:  4m 27s | Max: 14m 52s | Hits:  99%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 51m | Avg: 10m 09s | Max: 20m 16s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 56m | Avg: 14m 36s | Max: 21m 23s | Hits:  99%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 48m 19s | Avg:  3m 27s | Max:  4m 15s | Hits:  99%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 19m | Avg:  3m 59s | Max:  4m 34s | Hits:  99%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  5h 46m | Avg:  5m 46s | Max: 21m 23s | Hits:  99%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  2h 15m | Avg: 15m 04s | Max: 20m 16s | Hits:  98%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 14s | Avg:  3m 44s | Max:  3m 55s | Hits:  99%/3543  
      🟩 90a                Pass: 100%/4   | Total: 13m 56s | Avg:  3m 29s | Max:  3m 43s | Hits:  99%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 23m | Avg:  4m 47s | Max: 21m 23s | Hits:  99%/35418 
      🟩 14                 Pass: 100%/34  | Total:  3h 23m | Avg:  5m 59s | Max: 18m 16s | Hits:  99%/40122 
      🟩 17                 Pass: 100%/33  | Total:  3h 06m | Avg:  5m 39s | Max: 20m 16s | Hits:  99%/38946 
      🟩 20                 Pass: 100%/21  | Total:  2h 15m | Avg:  6m 28s | Max: 18m 21s | Hits:  99%/24780 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

@miscco miscco force-pushed the device_buffer branch 2 times, most recently from 4631d6b to 04f31bc Compare June 10, 2024 19:18
@harrism
Copy link
Contributor

harrism commented Jun 10, 2024

Is this not stream-ordered? Why?

In RAPIDS a buffer is always untyped, just raw byte storage. I understand not wanting to call it a vector, since it doesn't support the interface of a vector, and I like the explicit uninitialized, but a typed buffer feels strange.

Copy link
Contributor

🟨 CI finished in 5h 41m: Pass: 99%/361 | Total: 1d 22h | Avg: 7m 47s | Max: 42m 51s | Hits: 97%/519879
  • 🟨 cub: Pass: 97%/131 | Total: 18h 45m | Avg: 8m 35s | Max: 42m 51s | Hits: 99%/106491

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  97%/123 | Total: 18h 07m | Avg:  8m 50s | Max: 42m 51s | Hits:  99%/99683 
      🟩 arm64              Pass: 100%/8   | Total: 38m 24s | Avg:  4m 48s | Max:  5m 39s | Hits:  99%/6808  
    🔍 ctk: 12.4 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 08m | Avg:  4m 35s | Max: 14m 10s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🔍 12.4               Pass:  97%/113 | Total: 17h 22m | Avg:  9m 13s | Max: 42m 51s | Hits:  99%/92384 
    🔍 cudacxx_full: nvcc12.4 🔍
      🟩 clang-cuda17       Pass: 100%/2   | Total:  6m 57s | Avg:  3m 28s | Max:  3m 29s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 08m | Avg:  4m 35s | Max: 14m 10s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🔍 nvcc12.4           Pass:  97%/111 | Total: 17h 15m | Avg:  9m 19s | Max: 42m 51s | Hits:  99%/90976 
    🔍 cudacxx_name: nvcc 🔍
      🟩 clang-cuda         Pass: 100%/2   | Total:  6m 57s | Avg:  3m 28s | Max:  3m 29s | Hits: 100%/1408  
      🔍 nvcc               Pass:  97%/129 | Total: 18h 38m | Avg:  8m 40s | Max: 42m 51s | Hits:  99%/105083
    🔍 os: ubuntu22.04 🔍
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 54m 41s | Avg:  3m 54s | Max:  4m 40s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 42m | Avg:  4m 39s | Max:  6m 02s | Hits:  99%/29855 
      🔍 ubuntu22.04        Pass:  96%/76  | Total: 13h 56m | Avg: 11m 00s | Max: 42m 51s | Hits:  99%/61607 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 12m | Avg: 12m 00s | Max: 14m 10s | Hits:  98%/4170  
    🟨 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 27m 05s | Avg:  4m 30s | Max:  5m 18s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 45s | Avg:  5m 35s | Max:  5m 47s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 17m 47s | Avg:  4m 26s | Max:  4m 36s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 17m 45s | Avg:  4m 26s | Max:  4m 35s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 17m 59s | Avg:  4m 29s | Max:  4m 36s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 17m 32s | Avg:  4m 23s | Max:  4m 29s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 17m 56s | Avg:  4m 29s | Max:  4m 32s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 17m 44s | Avg:  4m 26s | Max:  4m 35s | Hits: 100%/3404  
      🟨 clang17            Pass:  96%/26  | Total:  5h 30m | Avg: 12m 42s | Max: 27m 04s | Hits: 100%/20981 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 41s | Avg:  3m 50s | Max:  3m 55s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 24m 46s | Avg:  4m 07s | Max:  4m 52s | Hits:  99%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 00s | Avg:  4m 10s | Max:  4m 22s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 25m 39s | Avg:  4m 16s | Max:  5m 15s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 19m 37s | Avg:  4m 54s | Max:  6m 02s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 31m 46s | Avg:  4m 32s | Max:  5m 09s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 19m 02s | Avg:  4m 45s | Max:  5m 09s | Hits:  99%/3404  
      🟨 gcc13              Pass:  92%/28  | Total:  6h 44m | Avg: 14m 25s | Max: 42m 51s | Hits:  99%/22126 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 14s | Avg:  5m 04s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 14m 10s | Avg: 14m 10s | Max: 14m 10s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 56s | Avg: 11m 28s | Max: 11m 35s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 34m 54s | Avg: 11m 38s | Max: 11m 55s | Hits:  98%/2085  
    🟨 cxx_name
      🟨 clang              Pass:  98%/59  | Total:  8h 01m | Avg:  8m 09s | Max: 27m 04s | Hits: 100%/48880 
      🟨 gcc                Pass:  96%/63  | Total:  9h 17m | Avg:  8m 51s | Max: 42m 51s | Hits:  99%/51110 
      🟩 Intel              Pass: 100%/3   | Total: 15m 14s | Avg:  5m 04s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 12m | Avg: 12m 00s | Max: 14m 10s | Hits:  98%/4170  
    🟨 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 10m | Avg:  4m 57s | Max: 14m 10s | Hits:  99%/81812 
      🟨 DeviceLaunch       Pass:  87%/8   | Total:  2h 43m | Avg: 20m 24s | Max: 30m 06s | Hits:  99%/5957  
      🟨 GraphCapture       Pass:  87%/8   | Total:  1h 50m | Avg: 13m 50s | Max: 20m 41s | Hits:  99%/5957  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 38m | Avg: 19m 46s | Max: 29m 05s | Hits:  99%/6808  
      🟨 TestGPU            Pass:  87%/8   | Total:  3h 22m | Avg: 25m 22s | Max: 42m 51s | Hits:  99%/5957  
    🟨 std
      🟨 11                 Pass:  97%/34  | Total:  4h 07m | Avg:  7m 16s | Max: 27m 04s | Hits:  99%/27652 
      🟩 14                 Pass: 100%/37  | Total:  5h 38m | Avg:  9m 08s | Max: 42m 51s | Hits:  99%/30588 
      🟨 17                 Pass:  97%/36  | Total:  5h 12m | Avg:  8m 41s | Max: 37m 06s | Hits:  99%/28971 
      🟨 20                 Pass:  95%/24  | Total:  3h 47m | Avg:  9m 29s | Max: 26m 25s | Hits:  99%/19280 
    🟨 gpu
      🟨 v100               Pass:  97%/131 | Total: 18h 45m | Avg:  8m 35s | Max: 42m 51s | Hits:  99%/106491
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 17s | Avg:  3m 49s | Max:  4m 12s | Hits:  99%/3404  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 53m | Avg: 6m 02s | Max: 29m 49s | Hits: 98%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 11h 20m | Avg:  6m 10s | Max: 29m 49s | Hits:  98%/129822
      🟩 arm64              Pass: 100%/8   | Total: 33m 04s | Avg:  4m 08s | Max:  5m 09s | Hits:  99%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 29m | Avg:  5m 56s | Max: 28m 43s | Hits:  94%/17705 
      🟩 11.8               Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 12.4               Pass: 100%/100 | Total: 10h 12m | Avg:  6m 07s | Max: 29m 49s | Hits:  99%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  8m 38s | Avg:  4m 19s | Max:  4m 36s | Hits: 100%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 29m | Avg:  5m 56s | Max: 28m 43s | Hits:  94%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total: 10h 03m | Avg:  6m 09s | Max: 29m 49s | Hits:  99%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  8m 38s | Avg:  4m 19s | Max:  4m 36s | Hits: 100%/2360  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 44m | Avg:  6m 04s | Max: 29m 49s | Hits:  98%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 24m 55s | Avg:  4m 09s | Max:  5m 08s | Hits: 100%/7080  
      🟩 clang10            Pass: 100%/3   | Total: 13m 22s | Avg:  4m 27s | Max:  4m 34s | Hits: 100%/3540  
      🟩 clang11            Pass: 100%/4   | Total: 15m 20s | Avg:  3m 50s | Max:  4m 02s | Hits: 100%/4720  
      🟩 clang12            Pass: 100%/4   | Total: 15m 39s | Avg:  3m 54s | Max:  4m 32s | Hits: 100%/4720  
      🟩 clang13            Pass: 100%/4   | Total: 15m 04s | Avg:  3m 46s | Max:  4m 02s | Hits: 100%/4720  
      🟩 clang14            Pass: 100%/4   | Total: 15m 54s | Avg:  3m 58s | Max:  4m 09s | Hits: 100%/4720  
      🟩 clang15            Pass: 100%/4   | Total: 15m 52s | Avg:  3m 58s | Max:  4m 22s | Hits: 100%/4720  
      🟩 clang16            Pass: 100%/4   | Total: 15m 21s | Avg:  3m 50s | Max:  4m 18s | Hits: 100%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  1h 56m | Avg:  6m 28s | Max: 14m 30s | Hits: 100%/21240 
      🟩 gcc6               Pass: 100%/2   | Total:  6m 40s | Avg:  3m 20s | Max:  3m 47s | Hits:  99%/2360  
      🟩 gcc7               Pass: 100%/6   | Total: 46m 13s | Avg:  7m 42s | Max: 28m 43s | Hits:  86%/7086  
      🟩 gcc8               Pass: 100%/6   | Total: 20m 53s | Avg:  3m 28s | Max:  3m 50s | Hits:  99%/7086  
      🟩 gcc9               Pass: 100%/6   | Total: 21m 42s | Avg:  3m 37s | Max:  3m 55s | Hits:  99%/7086  
      🟩 gcc10              Pass: 100%/4   | Total: 15m 37s | Avg:  3m 54s | Max:  4m 25s | Hits:  99%/4724  
      🟩 gcc11              Pass: 100%/7   | Total: 26m 56s | Avg:  3m 50s | Max:  4m 15s | Hits:  99%/8267  
      🟩 gcc12              Pass: 100%/4   | Total: 41m 47s | Avg: 10m 26s | Max: 29m 49s | Hits:  90%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  2h 14m | Avg:  6m 42s | Max: 22m 13s | Hits:  99%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 13m 46s | Avg:  4m 35s | Max:  4m 42s | Hits: 100%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 20s | Avg: 16m 20s | Max: 16m 20s | Hits:  98%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 12s | Avg: 12m 06s | Max: 12m 19s | Hits:  98%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 36m | Avg: 16m 08s | Max: 20m 07s | Hits:  98%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total:  4h 07m | Avg:  4m 51s | Max: 14m 30s | Hits: 100%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  5h 14m | Avg:  5m 42s | Max: 29m 49s | Hits:  97%/64953 
      🟩 Intel              Pass: 100%/3   | Total: 13m 46s | Avg:  4m 35s | Max:  4m 42s | Hits: 100%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 17m | Avg: 15m 15s | Max: 20m 07s | Hits:  98%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 53m | Avg:  6m 02s | Max: 29m 49s | Hits:  98%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 10m | Avg:  4m 57s | Max: 29m 49s | Hits:  98%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 47m | Avg:  9m 44s | Max: 20m 07s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 55m | Avg: 14m 25s | Max: 22m 13s | Hits:  99%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  1h 12m | Avg:  5m 12s | Max: 28m 43s | Hits:  94%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 18m | Avg:  3m 57s | Max:  5m 08s | Hits:  99%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  6h 04m | Avg:  6m 04s | Max: 29m 49s | Hits:  99%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  2h 17m | Avg: 15m 15s | Max: 20m 07s | Hits:  98%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 90a                Pass: 100%/4   | Total: 13m 11s | Avg:  3m 17s | Max:  3m 22s | Hits:  99%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 11m | Avg:  4m 23s | Max: 14m 24s | Hits:  99%/35418 
      🟩 14                 Pass: 100%/34  | Total:  3h 45m | Avg:  6m 37s | Max: 28m 43s | Hits:  97%/40122 
      🟩 17                 Pass: 100%/33  | Total:  3h 10m | Avg:  5m 46s | Max: 20m 07s | Hits:  99%/38946 
      🟩 20                 Pass: 100%/21  | Total:  2h 46m | Avg:  7m 54s | Max: 29m 49s | Hits:  98%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 16h 16m | Avg: 8m 42s | Max: 23m 19s | Hits: 95%/274122

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 15h 14m | Avg:  8m 47s | Max: 23m 19s | Hits:  94%/251704
      🟩 arm64              Pass: 100%/8   | Total:  1h 02m | Avg:  7m 45s | Max: 14m 50s | Hits:  98%/22418 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 21m | Avg:  5m 26s | Max: 17m 55s | Hits:  97%/39896 
      🟩 11.8               Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 12.4               Pass: 100%/94  | Total: 14h 23m | Avg:  9m 11s | Max: 23m 19s | Hits:  94%/226138
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 35m 07s | Avg: 17m 33s | Max: 17m 50s | Hits:  37%/6123  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 21m | Avg:  5m 26s | Max: 17m 55s | Hits:  97%/39896 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 13h 48m | Avg:  9m 00s | Max: 23m 19s | Hits:  96%/220015
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 35m 07s | Avg: 17m 33s | Max: 17m 50s | Hits:  37%/6123  
      🟩 nvcc               Pass: 100%/110 | Total: 15h 41m | Avg:  8m 33s | Max: 23m 19s | Hits:  96%/267999
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 58m 23s | Avg:  9m 43s | Max: 14m 33s | Hits:  94%/16208 
      🟩 clang10            Pass: 100%/3   | Total: 14m 55s | Avg:  4m 58s | Max:  5m 17s | Hits:  99%/8133  
      🟩 clang11            Pass: 100%/4   | Total: 43m 57s | Avg: 10m 59s | Max: 14m 53s | Hits:  91%/11217 
      🟩 clang12            Pass: 100%/4   | Total: 16m 28s | Avg:  4m 07s | Max:  4m 42s | Hits:  99%/11217 
      🟩 clang13            Pass: 100%/4   | Total: 17m 09s | Avg:  4m 17s | Max:  5m 09s | Hits:  99%/11217 
      🟩 clang14            Pass: 100%/4   | Total: 31m 09s | Avg:  7m 47s | Max: 17m 35s | Hits:  85%/11217 
      🟩 clang15            Pass: 100%/4   | Total: 32m 14s | Avg:  8m 03s | Max: 20m 05s | Hits:  83%/11209 
      🟩 clang16            Pass: 100%/4   | Total: 32m 46s | Avg:  8m 11s | Max: 14m 31s | Hits:  91%/11209 
      🟩 clang17            Pass: 100%/14  | Total:  2h 39m | Avg: 11m 21s | Max: 23m 10s | Hits:  85%/28541 
      🟩 gcc6               Pass: 100%/2   | Total:  5m 17s | Avg:  2m 38s | Max:  3m 06s | Hits:  99%/5057  
      🟩 gcc7               Pass: 100%/6   | Total: 37m 37s | Avg:  6m 16s | Max: 13m 30s | Hits:  99%/16194 
      🟩 gcc8               Pass: 100%/6   | Total: 18m 12s | Avg:  3m 02s | Max:  3m 24s | Hits:  99%/16202 
      🟩 gcc9               Pass: 100%/6   | Total: 29m 56s | Avg:  4m 59s | Max: 14m 20s | Hits:  99%/16206 
      🟩 gcc10              Pass: 100%/4   | Total: 14m 37s | Avg:  3m 39s | Max:  3m 58s | Hits:  99%/11217 
      🟩 gcc11              Pass: 100%/7   | Total:  1h 07m | Avg:  9m 35s | Max: 14m 52s | Hits:  98%/19297 
      🟩 gcc12              Pass: 100%/4   | Total: 27m 28s | Avg:  6m 52s | Max: 14m 08s | Hits:  98%/11209 
      🟩 gcc13              Pass: 100%/21  | Total:  3h 57m | Avg: 11m 17s | Max: 23m 19s | Hits:  98%/34010 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 52m 38s | Avg: 17m 32s | Max: 20m 36s | Hits:  86%/8123  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 55s | Avg: 17m 55s | Max: 17m 55s | Hits:  99%/2544  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 31s | Avg: 12m 15s | Max: 12m 45s | Hits:  99%/5458  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 37m 43s | Avg: 12m 34s | Max: 12m 47s | Hits:  99%/8437  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  6h 46m | Avg:  8m 38s | Max: 23m 10s | Hits:  91%/120168
      🟩 gcc                Pass: 100%/56  | Total:  7h 17m | Avg:  7m 48s | Max: 23m 19s | Hits:  98%/129392
      🟩 Intel              Pass: 100%/3   | Total: 52m 38s | Avg: 17m 32s | Max: 20m 36s | Hits:  86%/8123  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 20m | Avg: 13m 21s | Max: 17m 55s | Hits:  99%/16439 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 16h 16m | Avg:  8m 42s | Max: 23m 19s | Hits:  95%/274122
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 12h 32m | Avg:  7m 35s | Max: 20m 36s | Hits:  95%/274102
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 19m | Avg: 19m 53s | Max: 22m 04s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  2h 22m | Avg: 17m 47s | Max: 23m 19s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 09s | Avg:  2m 09s | Max:  2m 09s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  1h 03m | Avg:  4m 33s | Max: 11m 29s | Hits:  97%/37352 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  3h 43m | Avg:  6m 23s | Max: 17m 35s | Hits:  96%/96733 
      🟩 ubuntu22.04        Pass: 100%/57  | Total: 10h 08m | Avg: 10m 40s | Max: 23m 19s | Hits:  92%/123598
      🟩 windows2022        Pass: 100%/6   | Total:  1h 20m | Avg: 13m 21s | Max: 17m 55s | Hits:  99%/16439 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 90a                Pass: 100%/4   | Total: 15m 29s | Avg:  3m 52s | Max:  4m 41s | Hits:  99%/11572 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  3h 45m | Avg:  7m 47s | Max: 20m 36s | Hits:  97%/58200 
      🟩 14                 Pass: 100%/32  | Total:  4h 47m | Avg:  8m 59s | Max: 22m 04s | Hits:  95%/82132 
      🟩 17                 Pass: 100%/31  | Total:  4h 34m | Avg:  8m 52s | Max: 20m 05s | Hits:  93%/84470 
      🟩 20                 Pass: 100%/19  | Total:  3h 05m | Avg:  9m 45s | Max: 23m 19s | Hits:  93%/49320 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

@bernhardmgruber
Copy link
Contributor

In RAPIDS a buffer is always untyped, just raw byte storage. I understand not wanting to call it a vector, since it doesn't support the interface of a vector, and I like the explicit uninitialized, but a typed buffer feels strange.

We discussed this briefly yesterday in our code review hour and I advocated for having a container interface instead of a to_span member function. I saw great use of uninitialized_buffer for algorithms which allocate data overwritten by a kernel later.

We also discussed the untyped interface, but concluded it to be too dangerous and less practical. You would have to reinterpret the storage before you could do anything useful. And if you would need a buffer of bytes, you can just instantiate the buffer with char or int8_t or std::byte, etc.

However, I later concluded that maybe what a really want (and what's also safer), is a policy to thrust::device_vector which prevents value initialization and only performs default initialization. That is, we skip the zero-init for trivial types, but where a user-defined constructur is present, it is called. I think that's the right trade-off for me. Whether cuda::uninitialized_buffer is the right vehicle for this featur is less clear now for me.

@miscco
Copy link
Collaborator Author

miscco commented Jun 11, 2024

Is this not stream-ordered? Why?

In RAPIDS a buffer is always untyped, just raw byte storage. I understand not wanting to call it a vector, since it doesn't support the interface of a vector, and I like the explicit uninitialized, but a typed buffer feels strange.

The reason this is not stream ordered is that I want to add a uninitialized_async_buffer that takes a async_resource_ref as an argument.

async_resource_ref is really picky about providing a stream ordered interface and so far our other resources aka cuda_memory_resource, cuda_managed_memory_resource and cuda_pinned_memory_resource do not provide that interface.

That said, there will be no real difference between these buffers, so I did not want to write both just to change both when there are comments

@miscco
Copy link
Collaborator Author

miscco commented Jun 11, 2024

However, I later concluded that maybe what a really want (and what's also safer), is a policy to thrust::device_vector which prevents value initialization and only performs default initialization. That is, we skip the zero-init for trivial types, but where a user-defined constructur is present, it is called. I think that's the right trade-off for me. Whether cuda::uninitialized_buffer is the right vehicle for this featur is less clear now for me.

I believe that these are orthogonal issues. A simple uninitialized_buffer can be much more efficient when you do not need to resize your allocations.

As we discussed device_vector is a totally different beast regarding compile times and complexity, whereas this is a really simple class

@gonzalobg gonzalobg removed their request for review June 11, 2024 08:35
Copy link
Contributor

🟩 CI finished in 15h 15m: Pass: 100%/361 | Total: 2d 00h | Avg: 8m 03s | Max: 1h 02m | Hits: 97%/522432
  • 🟩 cub: Pass: 100%/131 | Total: 20h 21m | Avg: 9m 19s | Max: 1h 02m | Hits: 99%/109044

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total: 19h 42m | Avg:  9m 36s | Max:  1h 02m | Hits:  99%/102236
      🟩 arm64              Pass: 100%/8   | Total: 38m 24s | Avg:  4m 48s | Max:  5m 39s | Hits:  99%/6808  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 08m | Avg:  4m 35s | Max: 14m 10s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🟩 12.4               Pass: 100%/113 | Total: 18h 58m | Avg: 10m 04s | Max:  1h 02m | Hits:  99%/94937 
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  6m 57s | Avg:  3m 28s | Max:  3m 29s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 08m | Avg:  4m 35s | Max: 14m 10s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🟩 nvcc12.4           Pass: 100%/111 | Total: 18h 51m | Avg: 10m 11s | Max:  1h 02m | Hits:  99%/93529 
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  6m 57s | Avg:  3m 28s | Max:  3m 29s | Hits: 100%/1408  
      🟩 nvcc               Pass: 100%/129 | Total: 20h 14m | Avg:  9m 24s | Max:  1h 02m | Hits:  99%/107636
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 27m 05s | Avg:  4m 30s | Max:  5m 18s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 45s | Avg:  5m 35s | Max:  5m 47s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 17m 47s | Avg:  4m 26s | Max:  4m 36s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 17m 45s | Avg:  4m 26s | Max:  4m 35s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 17m 59s | Avg:  4m 29s | Max:  4m 36s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 17m 32s | Avg:  4m 23s | Max:  4m 29s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 17m 56s | Avg:  4m 29s | Max:  4m 32s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 17m 44s | Avg:  4m 26s | Max:  4m 35s | Hits: 100%/3404  
      🟩 clang17            Pass: 100%/26  | Total:  5h 57m | Avg: 13m 45s | Max: 27m 24s | Hits: 100%/21832 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 41s | Avg:  3m 50s | Max:  3m 55s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 24m 46s | Avg:  4m 07s | Max:  4m 52s | Hits:  99%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 00s | Avg:  4m 10s | Max:  4m 22s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 25m 39s | Avg:  4m 16s | Max:  5m 15s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 19m 37s | Avg:  4m 54s | Max:  6m 02s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 31m 46s | Avg:  4m 32s | Max:  5m 09s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 19m 02s | Avg:  4m 45s | Max:  5m 09s | Hits:  99%/3404  
      🟩 gcc13              Pass: 100%/28  | Total:  7h 51m | Avg: 16m 51s | Max:  1h 02m | Hits:  99%/23828 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 14s | Avg:  5m 04s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 14m 10s | Avg: 14m 10s | Max: 14m 10s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 56s | Avg: 11m 28s | Max: 11m 35s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 34m 54s | Avg: 11m 38s | Max: 11m 55s | Hits:  98%/2085  
    🟩 cxx_name
      🟩 clang              Pass: 100%/59  | Total:  8h 28m | Avg:  8m 37s | Max: 27m 24s | Hits: 100%/49731 
      🟩 gcc                Pass: 100%/63  | Total: 10h 25m | Avg:  9m 55s | Max:  1h 02m | Hits:  99%/52812 
      🟩 Intel              Pass: 100%/3   | Total: 15m 14s | Avg:  5m 04s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 12m | Avg: 12m 00s | Max: 14m 10s | Hits:  98%/4170  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total: 20h 21m | Avg:  9m 19s | Max:  1h 02m | Hits:  99%/109044
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 10m | Avg:  4m 57s | Max: 14m 10s | Hits:  99%/81812 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  3h 10m | Avg: 23m 49s | Max: 30m 06s | Hits:  99%/6808  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 01m | Avg: 15m 11s | Max: 20m 41s | Hits:  99%/6808  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 38m | Avg: 19m 46s | Max: 29m 05s | Hits:  99%/6808  
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 20m | Avg: 32m 30s | Max:  1h 02m | Hits:  99%/6808  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 54m 41s | Avg:  3m 54s | Max:  4m 40s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 42m | Avg:  4m 39s | Max:  6m 02s | Hits:  99%/29855 
      🟩 ubuntu22.04        Pass: 100%/76  | Total: 15h 31m | Avg: 12m 15s | Max:  1h 02m | Hits:  99%/64160 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 12m | Avg: 12m 00s | Max: 14m 10s | Hits:  98%/4170  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 06s | Avg:  4m 42s | Max:  5m 09s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 17s | Avg:  3m 49s | Max:  4m 12s | Hits:  99%/3404  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total:  5h 04m | Avg:  8m 57s | Max:  1h 02m | Hits:  99%/28503 
      🟩 14                 Pass: 100%/37  | Total:  5h 38m | Avg:  9m 08s | Max: 42m 51s | Hits:  99%/30588 
      🟩 17                 Pass: 100%/36  | Total:  5h 23m | Avg:  8m 59s | Max: 37m 06s | Hits:  99%/29822 
      🟩 20                 Pass: 100%/24  | Total:  4h 15m | Avg: 10m 37s | Max: 27m 24s | Hits:  99%/20131 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 53m | Avg: 6m 02s | Max: 29m 49s | Hits: 98%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 11h 20m | Avg:  6m 10s | Max: 29m 49s | Hits:  98%/129822
      🟩 arm64              Pass: 100%/8   | Total: 33m 04s | Avg:  4m 08s | Max:  5m 09s | Hits:  99%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 29m | Avg:  5m 56s | Max: 28m 43s | Hits:  94%/17705 
      🟩 11.8               Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 12.4               Pass: 100%/100 | Total: 10h 12m | Avg:  6m 07s | Max: 29m 49s | Hits:  99%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  8m 38s | Avg:  4m 19s | Max:  4m 36s | Hits: 100%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 29m | Avg:  5m 56s | Max: 28m 43s | Hits:  94%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total: 10h 03m | Avg:  6m 09s | Max: 29m 49s | Hits:  99%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  8m 38s | Avg:  4m 19s | Max:  4m 36s | Hits: 100%/2360  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 44m | Avg:  6m 04s | Max: 29m 49s | Hits:  98%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 24m 55s | Avg:  4m 09s | Max:  5m 08s | Hits: 100%/7080  
      🟩 clang10            Pass: 100%/3   | Total: 13m 22s | Avg:  4m 27s | Max:  4m 34s | Hits: 100%/3540  
      🟩 clang11            Pass: 100%/4   | Total: 15m 20s | Avg:  3m 50s | Max:  4m 02s | Hits: 100%/4720  
      🟩 clang12            Pass: 100%/4   | Total: 15m 39s | Avg:  3m 54s | Max:  4m 32s | Hits: 100%/4720  
      🟩 clang13            Pass: 100%/4   | Total: 15m 04s | Avg:  3m 46s | Max:  4m 02s | Hits: 100%/4720  
      🟩 clang14            Pass: 100%/4   | Total: 15m 54s | Avg:  3m 58s | Max:  4m 09s | Hits: 100%/4720  
      🟩 clang15            Pass: 100%/4   | Total: 15m 52s | Avg:  3m 58s | Max:  4m 22s | Hits: 100%/4720  
      🟩 clang16            Pass: 100%/4   | Total: 15m 21s | Avg:  3m 50s | Max:  4m 18s | Hits: 100%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  1h 56m | Avg:  6m 28s | Max: 14m 30s | Hits: 100%/21240 
      🟩 gcc6               Pass: 100%/2   | Total:  6m 40s | Avg:  3m 20s | Max:  3m 47s | Hits:  99%/2360  
      🟩 gcc7               Pass: 100%/6   | Total: 46m 13s | Avg:  7m 42s | Max: 28m 43s | Hits:  86%/7086  
      🟩 gcc8               Pass: 100%/6   | Total: 20m 53s | Avg:  3m 28s | Max:  3m 50s | Hits:  99%/7086  
      🟩 gcc9               Pass: 100%/6   | Total: 21m 42s | Avg:  3m 37s | Max:  3m 55s | Hits:  99%/7086  
      🟩 gcc10              Pass: 100%/4   | Total: 15m 37s | Avg:  3m 54s | Max:  4m 25s | Hits:  99%/4724  
      🟩 gcc11              Pass: 100%/7   | Total: 26m 56s | Avg:  3m 50s | Max:  4m 15s | Hits:  99%/8267  
      🟩 gcc12              Pass: 100%/4   | Total: 41m 47s | Avg: 10m 26s | Max: 29m 49s | Hits:  90%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  2h 14m | Avg:  6m 42s | Max: 22m 13s | Hits:  99%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 13m 46s | Avg:  4m 35s | Max:  4m 42s | Hits: 100%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 20s | Avg: 16m 20s | Max: 16m 20s | Hits:  98%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 12s | Avg: 12m 06s | Max: 12m 19s | Hits:  98%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 36m | Avg: 16m 08s | Max: 20m 07s | Hits:  98%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total:  4h 07m | Avg:  4m 51s | Max: 14m 30s | Hits: 100%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  5h 14m | Avg:  5m 42s | Max: 29m 49s | Hits:  97%/64953 
      🟩 Intel              Pass: 100%/3   | Total: 13m 46s | Avg:  4m 35s | Max:  4m 42s | Hits: 100%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 17m | Avg: 15m 15s | Max: 20m 07s | Hits:  98%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 53m | Avg:  6m 02s | Max: 29m 49s | Hits:  98%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 10m | Avg:  4m 57s | Max: 29m 49s | Hits:  98%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 47m | Avg:  9m 44s | Max: 20m 07s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 55m | Avg: 14m 25s | Max: 22m 13s | Hits:  99%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  1h 12m | Avg:  5m 12s | Max: 28m 43s | Hits:  94%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 18m | Avg:  3m 57s | Max:  5m 08s | Hits:  99%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  6h 04m | Avg:  6m 04s | Max: 29m 49s | Hits:  99%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  2h 17m | Avg: 15m 15s | Max: 20m 07s | Hits:  98%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 17s | Avg:  3m 45s | Max:  4m 12s | Hits:  99%/3543  
      🟩 90a                Pass: 100%/4   | Total: 13m 11s | Avg:  3m 17s | Max:  3m 22s | Hits:  99%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 11m | Avg:  4m 23s | Max: 14m 24s | Hits:  99%/35418 
      🟩 14                 Pass: 100%/34  | Total:  3h 45m | Avg:  6m 37s | Max: 28m 43s | Hits:  97%/40122 
      🟩 17                 Pass: 100%/33  | Total:  3h 10m | Avg:  5m 46s | Max: 20m 07s | Hits:  99%/38946 
      🟩 20                 Pass: 100%/21  | Total:  2h 46m | Avg:  7m 54s | Max: 29m 49s | Hits:  98%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 16h 16m | Avg: 8m 42s | Max: 23m 19s | Hits: 95%/274122

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 15h 14m | Avg:  8m 47s | Max: 23m 19s | Hits:  94%/251704
      🟩 arm64              Pass: 100%/8   | Total:  1h 02m | Avg:  7m 45s | Max: 14m 50s | Hits:  98%/22418 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 21m | Avg:  5m 26s | Max: 17m 55s | Hits:  97%/39896 
      🟩 11.8               Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 12.4               Pass: 100%/94  | Total: 14h 23m | Avg:  9m 11s | Max: 23m 19s | Hits:  94%/226138
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 35m 07s | Avg: 17m 33s | Max: 17m 50s | Hits:  37%/6123  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 21m | Avg:  5m 26s | Max: 17m 55s | Hits:  97%/39896 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 13h 48m | Avg:  9m 00s | Max: 23m 19s | Hits:  96%/220015
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 35m 07s | Avg: 17m 33s | Max: 17m 50s | Hits:  37%/6123  
      🟩 nvcc               Pass: 100%/110 | Total: 15h 41m | Avg:  8m 33s | Max: 23m 19s | Hits:  96%/267999
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 58m 23s | Avg:  9m 43s | Max: 14m 33s | Hits:  94%/16208 
      🟩 clang10            Pass: 100%/3   | Total: 14m 55s | Avg:  4m 58s | Max:  5m 17s | Hits:  99%/8133  
      🟩 clang11            Pass: 100%/4   | Total: 43m 57s | Avg: 10m 59s | Max: 14m 53s | Hits:  91%/11217 
      🟩 clang12            Pass: 100%/4   | Total: 16m 28s | Avg:  4m 07s | Max:  4m 42s | Hits:  99%/11217 
      🟩 clang13            Pass: 100%/4   | Total: 17m 09s | Avg:  4m 17s | Max:  5m 09s | Hits:  99%/11217 
      🟩 clang14            Pass: 100%/4   | Total: 31m 09s | Avg:  7m 47s | Max: 17m 35s | Hits:  85%/11217 
      🟩 clang15            Pass: 100%/4   | Total: 32m 14s | Avg:  8m 03s | Max: 20m 05s | Hits:  83%/11209 
      🟩 clang16            Pass: 100%/4   | Total: 32m 46s | Avg:  8m 11s | Max: 14m 31s | Hits:  91%/11209 
      🟩 clang17            Pass: 100%/14  | Total:  2h 39m | Avg: 11m 21s | Max: 23m 10s | Hits:  85%/28541 
      🟩 gcc6               Pass: 100%/2   | Total:  5m 17s | Avg:  2m 38s | Max:  3m 06s | Hits:  99%/5057  
      🟩 gcc7               Pass: 100%/6   | Total: 37m 37s | Avg:  6m 16s | Max: 13m 30s | Hits:  99%/16194 
      🟩 gcc8               Pass: 100%/6   | Total: 18m 12s | Avg:  3m 02s | Max:  3m 24s | Hits:  99%/16202 
      🟩 gcc9               Pass: 100%/6   | Total: 29m 56s | Avg:  4m 59s | Max: 14m 20s | Hits:  99%/16206 
      🟩 gcc10              Pass: 100%/4   | Total: 14m 37s | Avg:  3m 39s | Max:  3m 58s | Hits:  99%/11217 
      🟩 gcc11              Pass: 100%/7   | Total:  1h 07m | Avg:  9m 35s | Max: 14m 52s | Hits:  98%/19297 
      🟩 gcc12              Pass: 100%/4   | Total: 27m 28s | Avg:  6m 52s | Max: 14m 08s | Hits:  98%/11209 
      🟩 gcc13              Pass: 100%/21  | Total:  3h 57m | Avg: 11m 17s | Max: 23m 19s | Hits:  98%/34010 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 52m 38s | Avg: 17m 32s | Max: 20m 36s | Hits:  86%/8123  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 55s | Avg: 17m 55s | Max: 17m 55s | Hits:  99%/2544  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 31s | Avg: 12m 15s | Max: 12m 45s | Hits:  99%/5458  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 37m 43s | Avg: 12m 34s | Max: 12m 47s | Hits:  99%/8437  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  6h 46m | Avg:  8m 38s | Max: 23m 10s | Hits:  91%/120168
      🟩 gcc                Pass: 100%/56  | Total:  7h 17m | Avg:  7m 48s | Max: 23m 19s | Hits:  98%/129392
      🟩 Intel              Pass: 100%/3   | Total: 52m 38s | Avg: 17m 32s | Max: 20m 36s | Hits:  86%/8123  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 20m | Avg: 13m 21s | Max: 17m 55s | Hits:  99%/16439 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 16h 16m | Avg:  8m 42s | Max: 23m 19s | Hits:  95%/274122
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 12h 32m | Avg:  7m 35s | Max: 20m 36s | Hits:  95%/274102
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 19m | Avg: 19m 53s | Max: 22m 04s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  2h 22m | Avg: 17m 47s | Max: 23m 19s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 09s | Avg:  2m 09s | Max:  2m 09s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  1h 03m | Avg:  4m 33s | Max: 11m 29s | Hits:  97%/37352 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  3h 43m | Avg:  6m 23s | Max: 17m 35s | Hits:  96%/96733 
      🟩 ubuntu22.04        Pass: 100%/57  | Total: 10h 08m | Avg: 10m 40s | Max: 23m 19s | Hits:  92%/123598
      🟩 windows2022        Pass: 100%/6   | Total:  1h 20m | Avg: 13m 21s | Max: 17m 55s | Hits:  99%/16439 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 31m 15s | Avg: 10m 25s | Max: 14m 01s | Hits:  97%/8088  
      🟩 90a                Pass: 100%/4   | Total: 15m 29s | Avg:  3m 52s | Max:  4m 41s | Hits:  99%/11572 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  3h 45m | Avg:  7m 47s | Max: 20m 36s | Hits:  97%/58200 
      🟩 14                 Pass: 100%/32  | Total:  4h 47m | Avg:  8m 59s | Max: 22m 04s | Hits:  95%/82132 
      🟩 17                 Pass: 100%/31  | Total:  4h 34m | Avg:  8m 52s | Max: 20m 05s | Hits:  93%/84470 
      🟩 20                 Pass: 100%/19  | Total:  3h 05m | Avg:  9m 45s | Max: 23m 19s | Hits:  93%/49320 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

Copy link
Contributor

🟨 CI finished in 8h 04m: Pass: 99%/361 | Total: 4d 01h | Avg: 16m 08s | Max: 1h 02m | Hits: 81%/519938
  • 🟨 cub: Pass: 98%/131 | Total: 22h 31m | Avg: 10m 19s | Max: 44m 58s | Hits: 99%/107342

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  98%/123 | Total: 21h 51m | Avg: 10m 39s | Max: 44m 58s | Hits:  99%/100534
      🟩 arm64              Pass: 100%/8   | Total: 40m 35s | Avg:  5m 04s | Max:  5m 57s | Hits:  99%/6808  
    🔍 ctk: 12.4 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 13m 38s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🔍 12.4               Pass:  98%/113 | Total: 21h 07m | Avg: 11m 12s | Max: 44m 58s | Hits:  99%/93235 
    🔍 cudacxx_full: nvcc12.4 🔍
      🟩 clang-cuda17       Pass: 100%/2   | Total:  8m 23s | Avg:  4m 11s | Max:  4m 30s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 13m 38s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🔍 nvcc12.4           Pass:  98%/111 | Total: 20h 58m | Avg: 11m 20s | Max: 44m 58s | Hits:  99%/91827 
    🔍 cudacxx_name: nvcc 🔍
      🟩 clang-cuda         Pass: 100%/2   | Total:  8m 23s | Avg:  4m 11s | Max:  4m 30s | Hits: 100%/1408  
      🔍 nvcc               Pass:  98%/129 | Total: 22h 23m | Avg: 10m 24s | Max: 44m 58s | Hits:  99%/105934
    🔍 jobs: DeviceLaunch 🔍
      🟩 Build              Pass: 100%/99  | Total:  8h 48m | Avg:  5m 20s | Max: 34m 01s | Hits:  99%/81812 
      🔍 DeviceLaunch       Pass:  75%/8   | Total:  2h 36m | Avg: 19m 30s | Max: 32m 53s | Hits:  99%/5106  
      🟩 GraphCapture       Pass: 100%/8   | Total:  3h 09m | Avg: 23m 39s | Max: 44m 58s | Hits:  95%/6808  
      🟩 HostLaunch         Pass: 100%/8   | Total:  3h 31m | Avg: 26m 28s | Max: 33m 07s | Hits:  99%/6808  
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 25m | Avg: 33m 14s | Max: 43m 22s | Hits:  99%/6808  
    🔍 os: ubuntu22.04 🔍
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 57m 01s | Avg:  4m 04s | Max:  4m 43s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  3h 15m | Avg:  5m 34s | Max: 34m 01s | Hits:  98%/29855 
      🔍 ubuntu22.04        Pass:  97%/76  | Total: 17h 08m | Avg: 13m 31s | Max: 44m 58s | Hits:  99%/62458 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 38s | Hits:  98%/4170  
    🟨 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 27m 10s | Avg:  4m 31s | Max:  5m 08s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 32s | Avg:  5m 30s | Max:  6m 07s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 18m 28s | Avg:  4m 37s | Max:  5m 17s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 18m 42s | Avg:  4m 40s | Max:  5m 40s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 18m 28s | Avg:  4m 37s | Max:  5m 02s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 20m 58s | Avg:  5m 14s | Max:  7m 21s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 18m 49s | Avg:  4m 42s | Max:  5m 25s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 18m 20s | Avg:  4m 35s | Max:  4m 59s | Hits: 100%/3404  
      🟨 clang17            Pass:  96%/26  | Total:  7h 11m | Avg: 16m 36s | Max: 37m 35s | Hits: 100%/20981 
      🟩 gcc6               Pass: 100%/2   | Total:  9m 20s | Avg:  4m 40s | Max:  4m 43s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 53m 37s | Avg:  8m 56s | Max: 34m 01s | Hits:  93%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 24s | Avg:  4m 14s | Max:  4m 31s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 25m 40s | Avg:  4m 16s | Max:  4m 36s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 17m 47s | Avg:  4m 26s | Max:  4m 51s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 31m 35s | Avg:  4m 30s | Max:  4m 54s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 18m 40s | Avg:  4m 40s | Max:  4m 59s | Hits:  99%/3404  
      🟨 gcc13              Pass:  96%/28  | Total:  8h 13m | Avg: 17m 37s | Max: 44m 58s | Hits:  98%/22977 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 23s | Avg:  5m 07s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 38s | Avg: 13m 38s | Max: 13m 38s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 38s | Avg: 11m 19s | Max: 11m 28s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 35m 13s | Avg: 11m 44s | Max: 12m 09s | Hits:  98%/2085  
    🟨 cxx_name
      🟨 clang              Pass:  98%/59  | Total:  9h 49m | Avg:  9m 59s | Max: 37m 35s | Hits: 100%/48880 
      🟨 gcc                Pass:  98%/63  | Total: 11h 15m | Avg: 10m 43s | Max: 44m 58s | Hits:  98%/51961 
      🟩 Intel              Pass: 100%/3   | Total: 15m 23s | Avg:  5m 07s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 38s | Hits:  98%/4170  
    🟨 std
      🟨 11                 Pass:  97%/34  | Total:  5h 58m | Avg: 10m 32s | Max: 44m 58s | Hits:  98%/27652 
      🟩 14                 Pass: 100%/37  | Total:  6h 40m | Avg: 10m 48s | Max: 34m 01s | Hits:  98%/30588 
      🟩 17                 Pass: 100%/36  | Total:  5h 27m | Avg:  9m 05s | Max: 37m 19s | Hits:  99%/29822 
      🟨 20                 Pass:  95%/24  | Total:  4h 26m | Avg: 11m 05s | Max: 37m 35s | Hits:  99%/19280 
    🟨 gpu
      🟨 v100               Pass:  98%/131 | Total: 22h 31m | Avg: 10m 19s | Max: 44m 58s | Hits:  99%/107342
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 32s | Avg:  3m 53s | Max:  4m 14s | Hits:  99%/3404  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 2d 07h | Avg: 28m 01s | Max: 1h 02m | Hits: 56%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  2d 03h | Avg: 27m 58s | Max:  1h 02m | Hits:  57%/129822
      🟩 arm64              Pass: 100%/8   | Total:  3h 50m | Avg: 28m 51s | Max: 32m 07s | Hits:  48%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  7h 03m | Avg: 28m 15s | Max: 58m 27s | Hits:  48%/17705 
      🟩 11.8               Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 12.4               Pass: 100%/100 | Total:  1d 22h | Avg: 27m 40s | Max:  1h 02m | Hits:  58%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 56m 42s | Avg: 28m 21s | Max: 28m 37s | Hits:  48%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  7h 03m | Avg: 28m 15s | Max: 58m 27s | Hits:  48%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total:  1d 21h | Avg: 27m 39s | Max:  1h 02m | Hits:  58%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 56m 42s | Avg: 28m 21s | Max: 28m 37s | Hits:  48%/2360  
      🟩 nvcc               Pass: 100%/116 | Total:  2d 06h | Avg: 28m 01s | Max:  1h 02m | Hits:  57%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total:  2h 40m | Avg: 26m 45s | Max: 29m 17s | Hits:  48%/7080  
      🟩 clang10            Pass: 100%/3   | Total:  1h 27m | Avg: 29m 13s | Max: 32m 27s | Hits:  48%/3540  
      🟩 clang11            Pass: 100%/4   | Total:  2h 01m | Avg: 30m 21s | Max: 33m 22s | Hits:  48%/4720  
      🟩 clang12            Pass: 100%/4   | Total:  1h 56m | Avg: 29m 03s | Max: 31m 57s | Hits:  48%/4720  
      🟩 clang13            Pass: 100%/4   | Total:  1h 56m | Avg: 29m 04s | Max: 31m 07s | Hits:  48%/4720  
      🟩 clang14            Pass: 100%/4   | Total:  1h 59m | Avg: 29m 45s | Max: 31m 16s | Hits:  48%/4720  
      🟩 clang15            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 21s | Max: 31m 25s | Hits:  48%/4720  
      🟩 clang16            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 26s | Max: 31m 57s | Hits:  48%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  6h 20m | Avg: 21m 08s | Max: 31m 24s | Hits:  71%/21240 
      🟩 gcc6               Pass: 100%/2   | Total: 53m 19s | Avg: 26m 39s | Max: 29m 19s | Hits:  48%/2360  
      🟩 gcc7               Pass: 100%/6   | Total:  2h 43m | Avg: 27m 17s | Max: 31m 11s | Hits:  48%/7086  
      🟩 gcc8               Pass: 100%/6   | Total:  2h 46m | Avg: 27m 49s | Max: 31m 31s | Hits:  48%/7086  
      🟩 gcc9               Pass: 100%/6   | Total:  2h 48m | Avg: 28m 02s | Max: 30m 27s | Hits:  48%/7086  
      🟩 gcc10              Pass: 100%/4   | Total:  2h 04m | Avg: 31m 10s | Max: 34m 47s | Hits:  48%/4724  
      🟩 gcc11              Pass: 100%/7   | Total:  3h 58m | Avg: 34m 02s | Max: 42m 21s | Hits:  52%/8267  
      🟩 gcc12              Pass: 100%/4   | Total:  2h 07m | Avg: 31m 55s | Max: 33m 57s | Hits:  48%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  6h 46m | Avg: 20m 18s | Max: 32m 12s | Hits:  70%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 59m | Avg: 39m 40s | Max: 43m 13s | Hits:  48%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 58m 27s | Avg: 58m 27s | Max: 58m 27s | Hits:  46%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 56m | Avg: 58m 24s | Max:  1h 02m | Hits:  46%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 46m | Avg: 37m 48s | Max: 59m 04s | Hits:  72%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total: 22h 16m | Avg: 26m 12s | Max: 33m 22s | Hits:  56%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  1d 00h | Avg: 26m 20s | Max: 42m 21s | Hits:  56%/64953 
      🟩 Intel              Pass: 100%/3   | Total:  1h 59m | Avg: 39m 40s | Max: 43m 13s | Hits:  48%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 42m | Avg: 44m 40s | Max:  1h 02m | Hits:  64%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  2d 07h | Avg: 28m 01s | Max:  1h 02m | Hits:  56%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  2d 02h | Avg: 30m 47s | Max:  1h 02m | Hits:  49%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 45m | Avg:  9m 33s | Max: 20m 07s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 32m 12s | Hits:  90%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  6h 05m | Avg: 26m 06s | Max: 29m 59s | Hits:  48%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total: 17h 12m | Avg: 29m 30s | Max: 34m 47s | Hits:  48%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  1d 01h | Avg: 25m 07s | Max: 43m 13s | Hits:  62%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  6h 42m | Avg: 44m 40s | Max:  1h 02m | Hits:  64%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 90a                Pass: 100%/4   | Total:  1h 13m | Avg: 18m 28s | Max: 19m 52s | Hits:  48%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total: 12h 02m | Avg: 24m 05s | Max: 36m 36s | Hits:  55%/35418 
      🟩 14                 Pass: 100%/34  | Total: 17h 04m | Avg: 30m 07s | Max: 58m 27s | Hits:  56%/40122 
      🟩 17                 Pass: 100%/33  | Total: 16h 21m | Avg: 29m 44s | Max:  1h 02m | Hits:  56%/38946 
      🟩 20                 Pass: 100%/21  | Total:  9h 38m | Avg: 27m 33s | Max: 59m 04s | Hits:  61%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 19h 29m | Avg: 10m 26s | Max: 40m 20s | Hits: 86%/273330

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 18h 17m | Avg: 10m 33s | Max: 40m 20s | Hits:  86%/250976
      🟩 arm64              Pass: 100%/8   | Total:  1h 12m | Avg:  9m 01s | Max: 12m 40s | Hits:  83%/22354 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 39m | Avg: 10m 36s | Max: 40m 20s | Hits:  86%/39776 
      🟩 11.8               Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 12.4               Pass: 100%/94  | Total: 16h 09m | Avg: 10m 18s | Max: 38m 31s | Hits:  87%/225490
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 37m 59s | Avg: 18m 59s | Max: 20m 02s | Hits:  37%/6107  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 39m | Avg: 10m 36s | Max: 40m 20s | Hits:  86%/39776 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 15h 31m | Avg: 10m 07s | Max: 38m 31s | Hits:  88%/219383
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 37m 59s | Avg: 18m 59s | Max: 20m 02s | Hits:  37%/6107  
      🟩 nvcc               Pass: 100%/110 | Total: 18h 51m | Avg: 10m 17s | Max: 40m 20s | Hits:  87%/267223
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 36m 41s | Avg:  6m 06s | Max: 13m 04s | Hits:  88%/16160 
      🟩 clang10            Pass: 100%/3   | Total: 23m 07s | Avg:  7m 42s | Max: 13m 26s | Hits:  88%/8109  
      🟩 clang11            Pass: 100%/4   | Total: 15m 56s | Avg:  3m 59s | Max:  4m 15s | Hits:  99%/11185 
      🟩 clang12            Pass: 100%/4   | Total: 23m 42s | Avg:  5m 55s | Max: 12m 08s | Hits:  91%/11185 
      🟩 clang13            Pass: 100%/4   | Total: 16m 05s | Avg:  4m 01s | Max:  4m 23s | Hits:  98%/11185 
      🟩 clang14            Pass: 100%/4   | Total: 29m 29s | Avg:  7m 22s | Max: 10m 56s | Hits:  87%/11185 
      🟩 clang15            Pass: 100%/4   | Total: 33m 16s | Avg:  8m 19s | Max: 13m 03s | Hits:  87%/11177 
      🟩 clang16            Pass: 100%/4   | Total: 24m 37s | Avg:  6m 09s | Max: 12m 52s | Hits:  91%/11177 
      🟩 clang17            Pass: 100%/14  | Total:  3h 07m | Avg: 13m 22s | Max: 22m 42s | Hits:  75%/28461 
      🟩 gcc6               Pass: 100%/2   | Total: 43m 08s | Avg: 21m 34s | Max: 40m 20s | Hits:  89%/5041  
      🟩 gcc7               Pass: 100%/6   | Total:  1h 33m | Avg: 15m 32s | Max: 37m 34s | Hits:  77%/16146 
      🟩 gcc8               Pass: 100%/6   | Total: 24m 10s | Avg:  4m 01s | Max:  8m 52s | Hits:  94%/16154 
      🟩 gcc9               Pass: 100%/6   | Total: 53m 17s | Avg:  8m 52s | Max: 12m 12s | Hits:  77%/16158 
      🟩 gcc10              Pass: 100%/4   | Total: 43m 53s | Avg: 10m 58s | Max: 16m 36s | Hits:  76%/11185 
      🟩 gcc11              Pass: 100%/7   | Total:  1h 24m | Avg: 12m 04s | Max: 19m 50s | Hits:  80%/19241 
      🟩 gcc12              Pass: 100%/4   | Total: 48m 28s | Avg: 12m 07s | Max: 17m 07s | Hits:  79%/11177 
      🟩 gcc13              Pass: 100%/21  | Total:  4h 27m | Avg: 12m 42s | Max: 38m 31s | Hits:  92%/33914 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 23m 37s | Avg:  7m 52s | Max: 12m 33s | Hits:  93%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 00s | Avg: 17m 00s | Max: 17m 00s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 41m 29s | Avg: 20m 44s | Max: 21m 49s | Hits:  71%/5442  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 39m 25s | Avg: 13m 08s | Max: 14m 19s | Hits:  98%/8413  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  6h 30m | Avg:  8m 17s | Max: 22m 42s | Hits:  87%/119824
      🟩 gcc                Pass: 100%/56  | Total: 10h 57m | Avg: 11m 44s | Max: 40m 20s | Hits:  84%/129016
      🟩 Intel              Pass: 100%/3   | Total: 23m 37s | Avg:  7m 52s | Max: 12m 33s | Hits:  93%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 37m | Avg: 16m 19s | Max: 21m 49s | Hits:  89%/16391 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 19h 29m | Avg: 10m 26s | Max: 40m 20s | Hits:  86%/273330
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 14h 52m | Avg:  9m 01s | Max: 40m 20s | Hits:  86%/273310
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 29m | Avg: 22m 26s | Max: 28m 16s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  3h 04m | Avg: 23m 06s | Max: 38m 31s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 02s | Avg:  2m 02s | Max:  2m 02s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  2h 22m | Avg: 10m 08s | Max: 40m 20s | Hits:  85%/37240 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  4h 20m | Avg:  7m 26s | Max: 17m 34s | Hits:  88%/96453 
      🟩 ubuntu22.04        Pass: 100%/57  | Total: 11h 08m | Avg: 11m 43s | Max: 38m 31s | Hits:  85%/123246
      🟩 windows2022        Pass: 100%/6   | Total:  1h 37m | Avg: 16m 19s | Max: 21m 49s | Hits:  89%/16391 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 90a                Pass: 100%/4   | Total: 14m 47s | Avg:  3m 41s | Max:  4m 23s | Hits:  99%/11540 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  5h 09m | Avg: 10m 40s | Max: 40m 20s | Hits:  90%/57992 
      🟩 14                 Pass: 100%/32  | Total:  4h 54m | Avg:  9m 11s | Max: 33m 44s | Hits:  88%/81900 
      🟩 17                 Pass: 100%/31  | Total:  5h 49m | Avg: 11m 17s | Max: 23m 22s | Hits:  80%/84246 
      🟩 20                 Pass: 100%/19  | Total:  3h 33m | Avg: 11m 14s | Max: 38m 31s | Hits:  87%/49192 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

@jrhemstad
Copy link
Collaborator

That said, there will be no real difference between these buffers, so I did not want to write both just to change both when there are comments

There is a big and important difference between a stream-ordered and non-stream-ordered buffer: the memory owned by a stream-ordered buffer object may still be valid after the object is destroyed.

Consider:

{
   uninitialized_async_buffer buff(...., stream);
   kernel<<<..., stream>>>(buff.data());
} // buff object is destroyed at the end of this scope, but the kernel may still be using the memory pointed to by `buff.data()`

Stream-ordering and RAII object lifetime don't mix together very cleanly, and I've never been able to come up with a sane way to reconcile them other than just pretend the problem doesn't exist :).

@harrism
Copy link
Contributor

harrism commented Jun 12, 2024

Jake your example is safe*, but not realistic, since it doesn't have any output that persists so could be replaced with a no-op.

*It's safe assuming uninitialized_async_buffer::~uninitialized_async_buffer calls deallocate_async with the same stream passed to the ctor.

The way to make your example unsafe is to run the kernel on a different stream from the device_buffer construction. I had a similar but more complex example in my GTC 2023 presentation:
image

This example uses two streams, and the way to make it safe is to synchronize stream_b before closing the scope (or insert an event dependency).

@miscco
Copy link
Collaborator Author

miscco commented Jun 12, 2024

Jake your example is safe*, but not realistic, since it doesn't have any output that persists so could be replaced with a no-op.

*It's safe assuming uninitialized_async_buffer::~uninitialized_async_buffer calls deallocate_async with the same stream passed to the ctor.

The way to make your example unsafe is to run the kernel on a different stream from the device_buffer construction. I had a similar but more complex example in my GTC 2023 presentation: image

This example uses two streams, and the way to make it safe is to synchronize stream_b before closing the scope (or insert an event dependency).

That is the current design, I intended to store the stream_ref in the uninitialized_async_buffer and the call both stream.wait() and finally deallocate_async on it

Copy link
Contributor

🟩 CI finished in 8h 04m: Pass: 100%/361 | Total: 4d 01h | Avg: 16m 08s | Max: 1h 02m | Hits: 81%/521640
  • 🟩 cub: Pass: 100%/131 | Total: 22h 31m | Avg: 10m 19s | Max: 44m 58s | Hits: 99%/109044

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total: 21h 51m | Avg: 10m 39s | Max: 44m 58s | Hits:  99%/102236
      🟩 arm64              Pass: 100%/8   | Total: 40m 35s | Avg:  5m 04s | Max:  5m 57s | Hits:  99%/6808  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 13m 38s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🟩 12.4               Pass: 100%/113 | Total: 21h 07m | Avg: 11m 12s | Max: 44m 58s | Hits:  99%/94937 
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  8m 23s | Avg:  4m 11s | Max:  4m 30s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 13m 38s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🟩 nvcc12.4           Pass: 100%/111 | Total: 20h 58m | Avg: 11m 20s | Max: 44m 58s | Hits:  99%/93529 
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  8m 23s | Avg:  4m 11s | Max:  4m 30s | Hits: 100%/1408  
      🟩 nvcc               Pass: 100%/129 | Total: 22h 23m | Avg: 10m 24s | Max: 44m 58s | Hits:  99%/107636
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 27m 10s | Avg:  4m 31s | Max:  5m 08s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 32s | Avg:  5m 30s | Max:  6m 07s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 18m 28s | Avg:  4m 37s | Max:  5m 17s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 18m 42s | Avg:  4m 40s | Max:  5m 40s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 18m 28s | Avg:  4m 37s | Max:  5m 02s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 20m 58s | Avg:  5m 14s | Max:  7m 21s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 18m 49s | Avg:  4m 42s | Max:  5m 25s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 18m 20s | Avg:  4m 35s | Max:  4m 59s | Hits: 100%/3404  
      🟩 clang17            Pass: 100%/26  | Total:  7h 11m | Avg: 16m 36s | Max: 37m 35s | Hits: 100%/21832 
      🟩 gcc6               Pass: 100%/2   | Total:  9m 20s | Avg:  4m 40s | Max:  4m 43s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 53m 37s | Avg:  8m 56s | Max: 34m 01s | Hits:  93%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 24s | Avg:  4m 14s | Max:  4m 31s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 25m 40s | Avg:  4m 16s | Max:  4m 36s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 17m 47s | Avg:  4m 26s | Max:  4m 51s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 31m 35s | Avg:  4m 30s | Max:  4m 54s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 18m 40s | Avg:  4m 40s | Max:  4m 59s | Hits:  99%/3404  
      🟩 gcc13              Pass: 100%/28  | Total:  8h 13m | Avg: 17m 37s | Max: 44m 58s | Hits:  98%/23828 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 23s | Avg:  5m 07s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 38s | Avg: 13m 38s | Max: 13m 38s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 38s | Avg: 11m 19s | Max: 11m 28s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 35m 13s | Avg: 11m 44s | Max: 12m 09s | Hits:  98%/2085  
    🟩 cxx_name
      🟩 clang              Pass: 100%/59  | Total:  9h 49m | Avg:  9m 59s | Max: 37m 35s | Hits: 100%/49731 
      🟩 gcc                Pass: 100%/63  | Total: 11h 15m | Avg: 10m 43s | Max: 44m 58s | Hits:  98%/52812 
      🟩 Intel              Pass: 100%/3   | Total: 15m 23s | Avg:  5m 07s | Max:  5m 13s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 38s | Hits:  98%/4170  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total: 22h 31m | Avg: 10m 19s | Max: 44m 58s | Hits:  99%/109044
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 48m | Avg:  5m 20s | Max: 34m 01s | Hits:  99%/81812 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 36m | Avg: 19m 30s | Max: 32m 53s | Hits:  99%/6808  
      🟩 GraphCapture       Pass: 100%/8   | Total:  3h 09m | Avg: 23m 39s | Max: 44m 58s | Hits:  95%/6808  
      🟩 HostLaunch         Pass: 100%/8   | Total:  3h 31m | Avg: 26m 28s | Max: 33m 07s | Hits:  99%/6808  
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 25m | Avg: 33m 14s | Max: 43m 22s | Hits:  99%/6808  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 57m 01s | Avg:  4m 04s | Max:  4m 43s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  3h 15m | Avg:  5m 34s | Max: 34m 01s | Hits:  98%/29855 
      🟩 ubuntu22.04        Pass: 100%/76  | Total: 17h 08m | Avg: 13m 31s | Max: 44m 58s | Hits:  99%/64160 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 38s | Hits:  98%/4170  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 54s | Avg:  4m 38s | Max:  4m 54s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 32s | Avg:  3m 53s | Max:  4m 14s | Hits:  99%/3404  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total:  5h 58m | Avg: 10m 32s | Max: 44m 58s | Hits:  98%/28503 
      🟩 14                 Pass: 100%/37  | Total:  6h 40m | Avg: 10m 48s | Max: 34m 01s | Hits:  98%/30588 
      🟩 17                 Pass: 100%/36  | Total:  5h 27m | Avg:  9m 05s | Max: 37m 19s | Hits:  99%/29822 
      🟩 20                 Pass: 100%/24  | Total:  4h 26m | Avg: 11m 05s | Max: 37m 35s | Hits:  99%/20131 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 2d 07h | Avg: 28m 01s | Max: 1h 02m | Hits: 56%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  2d 03h | Avg: 27m 58s | Max:  1h 02m | Hits:  57%/129822
      🟩 arm64              Pass: 100%/8   | Total:  3h 50m | Avg: 28m 51s | Max: 32m 07s | Hits:  48%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  7h 03m | Avg: 28m 15s | Max: 58m 27s | Hits:  48%/17705 
      🟩 11.8               Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 12.4               Pass: 100%/100 | Total:  1d 22h | Avg: 27m 40s | Max:  1h 02m | Hits:  58%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 56m 42s | Avg: 28m 21s | Max: 28m 37s | Hits:  48%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  7h 03m | Avg: 28m 15s | Max: 58m 27s | Hits:  48%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total:  1d 21h | Avg: 27m 39s | Max:  1h 02m | Hits:  58%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 56m 42s | Avg: 28m 21s | Max: 28m 37s | Hits:  48%/2360  
      🟩 nvcc               Pass: 100%/116 | Total:  2d 06h | Avg: 28m 01s | Max:  1h 02m | Hits:  57%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total:  2h 40m | Avg: 26m 45s | Max: 29m 17s | Hits:  48%/7080  
      🟩 clang10            Pass: 100%/3   | Total:  1h 27m | Avg: 29m 13s | Max: 32m 27s | Hits:  48%/3540  
      🟩 clang11            Pass: 100%/4   | Total:  2h 01m | Avg: 30m 21s | Max: 33m 22s | Hits:  48%/4720  
      🟩 clang12            Pass: 100%/4   | Total:  1h 56m | Avg: 29m 03s | Max: 31m 57s | Hits:  48%/4720  
      🟩 clang13            Pass: 100%/4   | Total:  1h 56m | Avg: 29m 04s | Max: 31m 07s | Hits:  48%/4720  
      🟩 clang14            Pass: 100%/4   | Total:  1h 59m | Avg: 29m 45s | Max: 31m 16s | Hits:  48%/4720  
      🟩 clang15            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 21s | Max: 31m 25s | Hits:  48%/4720  
      🟩 clang16            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 26s | Max: 31m 57s | Hits:  48%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  6h 20m | Avg: 21m 08s | Max: 31m 24s | Hits:  71%/21240 
      🟩 gcc6               Pass: 100%/2   | Total: 53m 19s | Avg: 26m 39s | Max: 29m 19s | Hits:  48%/2360  
      🟩 gcc7               Pass: 100%/6   | Total:  2h 43m | Avg: 27m 17s | Max: 31m 11s | Hits:  48%/7086  
      🟩 gcc8               Pass: 100%/6   | Total:  2h 46m | Avg: 27m 49s | Max: 31m 31s | Hits:  48%/7086  
      🟩 gcc9               Pass: 100%/6   | Total:  2h 48m | Avg: 28m 02s | Max: 30m 27s | Hits:  48%/7086  
      🟩 gcc10              Pass: 100%/4   | Total:  2h 04m | Avg: 31m 10s | Max: 34m 47s | Hits:  48%/4724  
      🟩 gcc11              Pass: 100%/7   | Total:  3h 58m | Avg: 34m 02s | Max: 42m 21s | Hits:  52%/8267  
      🟩 gcc12              Pass: 100%/4   | Total:  2h 07m | Avg: 31m 55s | Max: 33m 57s | Hits:  48%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  6h 46m | Avg: 20m 18s | Max: 32m 12s | Hits:  70%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 59m | Avg: 39m 40s | Max: 43m 13s | Hits:  48%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 58m 27s | Avg: 58m 27s | Max: 58m 27s | Hits:  46%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 56m | Avg: 58m 24s | Max:  1h 02m | Hits:  46%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 46m | Avg: 37m 48s | Max: 59m 04s | Hits:  72%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total: 22h 16m | Avg: 26m 12s | Max: 33m 22s | Hits:  56%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  1d 00h | Avg: 26m 20s | Max: 42m 21s | Hits:  56%/64953 
      🟩 Intel              Pass: 100%/3   | Total:  1h 59m | Avg: 39m 40s | Max: 43m 13s | Hits:  48%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 42m | Avg: 44m 40s | Max:  1h 02m | Hits:  64%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  2d 07h | Avg: 28m 01s | Max:  1h 02m | Hits:  56%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  2d 02h | Avg: 30m 47s | Max:  1h 02m | Hits:  49%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 45m | Avg:  9m 33s | Max: 20m 07s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 32m 12s | Hits:  90%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  6h 05m | Avg: 26m 06s | Max: 29m 59s | Hits:  48%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total: 17h 12m | Avg: 29m 30s | Max: 34m 47s | Hits:  48%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  1d 01h | Avg: 25m 07s | Max: 43m 13s | Hits:  62%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  6h 42m | Avg: 44m 40s | Max:  1h 02m | Hits:  64%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 55m | Avg: 38m 33s | Max: 42m 21s | Hits:  53%/3543  
      🟩 90a                Pass: 100%/4   | Total:  1h 13m | Avg: 18m 28s | Max: 19m 52s | Hits:  48%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total: 12h 02m | Avg: 24m 05s | Max: 36m 36s | Hits:  55%/35418 
      🟩 14                 Pass: 100%/34  | Total: 17h 04m | Avg: 30m 07s | Max: 58m 27s | Hits:  56%/40122 
      🟩 17                 Pass: 100%/33  | Total: 16h 21m | Avg: 29m 44s | Max:  1h 02m | Hits:  56%/38946 
      🟩 20                 Pass: 100%/21  | Total:  9h 38m | Avg: 27m 33s | Max: 59m 04s | Hits:  61%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 19h 29m | Avg: 10m 26s | Max: 40m 20s | Hits: 86%/273330

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 18h 17m | Avg: 10m 33s | Max: 40m 20s | Hits:  86%/250976
      🟩 arm64              Pass: 100%/8   | Total:  1h 12m | Avg:  9m 01s | Max: 12m 40s | Hits:  83%/22354 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 39m | Avg: 10m 36s | Max: 40m 20s | Hits:  86%/39776 
      🟩 11.8               Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 12.4               Pass: 100%/94  | Total: 16h 09m | Avg: 10m 18s | Max: 38m 31s | Hits:  87%/225490
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 37m 59s | Avg: 18m 59s | Max: 20m 02s | Hits:  37%/6107  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 39m | Avg: 10m 36s | Max: 40m 20s | Hits:  86%/39776 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 15h 31m | Avg: 10m 07s | Max: 38m 31s | Hits:  88%/219383
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 37m 59s | Avg: 18m 59s | Max: 20m 02s | Hits:  37%/6107  
      🟩 nvcc               Pass: 100%/110 | Total: 18h 51m | Avg: 10m 17s | Max: 40m 20s | Hits:  87%/267223
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 36m 41s | Avg:  6m 06s | Max: 13m 04s | Hits:  88%/16160 
      🟩 clang10            Pass: 100%/3   | Total: 23m 07s | Avg:  7m 42s | Max: 13m 26s | Hits:  88%/8109  
      🟩 clang11            Pass: 100%/4   | Total: 15m 56s | Avg:  3m 59s | Max:  4m 15s | Hits:  99%/11185 
      🟩 clang12            Pass: 100%/4   | Total: 23m 42s | Avg:  5m 55s | Max: 12m 08s | Hits:  91%/11185 
      🟩 clang13            Pass: 100%/4   | Total: 16m 05s | Avg:  4m 01s | Max:  4m 23s | Hits:  98%/11185 
      🟩 clang14            Pass: 100%/4   | Total: 29m 29s | Avg:  7m 22s | Max: 10m 56s | Hits:  87%/11185 
      🟩 clang15            Pass: 100%/4   | Total: 33m 16s | Avg:  8m 19s | Max: 13m 03s | Hits:  87%/11177 
      🟩 clang16            Pass: 100%/4   | Total: 24m 37s | Avg:  6m 09s | Max: 12m 52s | Hits:  91%/11177 
      🟩 clang17            Pass: 100%/14  | Total:  3h 07m | Avg: 13m 22s | Max: 22m 42s | Hits:  75%/28461 
      🟩 gcc6               Pass: 100%/2   | Total: 43m 08s | Avg: 21m 34s | Max: 40m 20s | Hits:  89%/5041  
      🟩 gcc7               Pass: 100%/6   | Total:  1h 33m | Avg: 15m 32s | Max: 37m 34s | Hits:  77%/16146 
      🟩 gcc8               Pass: 100%/6   | Total: 24m 10s | Avg:  4m 01s | Max:  8m 52s | Hits:  94%/16154 
      🟩 gcc9               Pass: 100%/6   | Total: 53m 17s | Avg:  8m 52s | Max: 12m 12s | Hits:  77%/16158 
      🟩 gcc10              Pass: 100%/4   | Total: 43m 53s | Avg: 10m 58s | Max: 16m 36s | Hits:  76%/11185 
      🟩 gcc11              Pass: 100%/7   | Total:  1h 24m | Avg: 12m 04s | Max: 19m 50s | Hits:  80%/19241 
      🟩 gcc12              Pass: 100%/4   | Total: 48m 28s | Avg: 12m 07s | Max: 17m 07s | Hits:  79%/11177 
      🟩 gcc13              Pass: 100%/21  | Total:  4h 27m | Avg: 12m 42s | Max: 38m 31s | Hits:  92%/33914 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 23m 37s | Avg:  7m 52s | Max: 12m 33s | Hits:  93%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 00s | Avg: 17m 00s | Max: 17m 00s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 41m 29s | Avg: 20m 44s | Max: 21m 49s | Hits:  71%/5442  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 39m 25s | Avg: 13m 08s | Max: 14m 19s | Hits:  98%/8413  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  6h 30m | Avg:  8m 17s | Max: 22m 42s | Hits:  87%/119824
      🟩 gcc                Pass: 100%/56  | Total: 10h 57m | Avg: 11m 44s | Max: 40m 20s | Hits:  84%/129016
      🟩 Intel              Pass: 100%/3   | Total: 23m 37s | Avg:  7m 52s | Max: 12m 33s | Hits:  93%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 37m | Avg: 16m 19s | Max: 21m 49s | Hits:  89%/16391 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 19h 29m | Avg: 10m 26s | Max: 40m 20s | Hits:  86%/273330
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 14h 52m | Avg:  9m 01s | Max: 40m 20s | Hits:  86%/273310
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 29m | Avg: 22m 26s | Max: 28m 16s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  3h 04m | Avg: 23m 06s | Max: 38m 31s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 02s | Avg:  2m 02s | Max:  2m 02s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total:  2h 22m | Avg: 10m 08s | Max: 40m 20s | Hits:  85%/37240 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  4h 20m | Avg:  7m 26s | Max: 17m 34s | Hits:  88%/96453 
      🟩 ubuntu22.04        Pass: 100%/57  | Total: 11h 08m | Avg: 11m 43s | Max: 38m 31s | Hits:  85%/123246
      🟩 windows2022        Pass: 100%/6   | Total:  1h 37m | Avg: 16m 19s | Max: 21m 49s | Hits:  89%/16391 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 40m 39s | Avg: 13m 33s | Max: 19m 50s | Hits:  72%/8064  
      🟩 90a                Pass: 100%/4   | Total: 14m 47s | Avg:  3m 41s | Max:  4m 23s | Hits:  99%/11540 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  5h 09m | Avg: 10m 40s | Max: 40m 20s | Hits:  90%/57992 
      🟩 14                 Pass: 100%/32  | Total:  4h 54m | Avg:  9m 11s | Max: 33m 44s | Hits:  88%/81900 
      🟩 17                 Pass: 100%/31  | Total:  5h 49m | Avg: 11m 17s | Max: 23m 22s | Hits:  80%/84246 
      🟩 20                 Pass: 100%/19  | Total:  3h 33m | Avg: 11m 14s | Max: 38m 31s | Hits:  87%/49192 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

Copy link
Contributor

🟨 CI finished in 9h 39m: Pass: 99%/361 | Total: 1d 19h | Avg: 7m 15s | Max: 46m 29s | Hits: 97%/520789
  • 🟨 cub: Pass: 99%/131 | Total: 18h 30m | Avg: 8m 28s | Max: 41m 23s | Hits: 99%/108193

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  99%/123 | Total: 17h 50m | Avg:  8m 42s | Max: 41m 23s | Hits:  99%/101385
      🟩 arm64              Pass: 100%/8   | Total: 40m 34s | Avg:  5m 04s | Max:  5m 31s | Hits:  99%/6808  
    🔍 ctk: 12.4 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 13m 44s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🔍 12.4               Pass:  99%/113 | Total: 17h 07m | Avg:  9m 05s | Max: 41m 23s | Hits:  99%/94086 
    🔍 cudacxx_full: nvcc12.4 🔍
      🟩 clang-cuda17       Pass: 100%/2   | Total:  7m 20s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 13m 44s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🔍 nvcc12.4           Pass:  99%/111 | Total: 17h 00m | Avg:  9m 11s | Max: 41m 23s | Hits:  99%/92678 
    🔍 cudacxx_name: nvcc 🔍
      🟩 clang-cuda         Pass: 100%/2   | Total:  7m 20s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1408  
      🔍 nvcc               Pass:  99%/129 | Total: 18h 23m | Avg:  8m 33s | Max: 41m 23s | Hits:  99%/106785
    🔍 cxx_full: gcc13 🔍
      🟩 clang9             Pass: 100%/6   | Total: 27m 28s | Avg:  4m 34s | Max:  5m 14s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 08s | Avg:  5m 22s | Max:  5m 34s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 18m 49s | Avg:  4m 42s | Max:  4m 49s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 18m 24s | Avg:  4m 36s | Max:  5m 05s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 26s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 17m 59s | Avg:  4m 29s | Max:  4m 35s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 19m 15s | Avg:  4m 48s | Max:  5m 24s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 20m 04s | Avg:  5m 01s | Max:  6m 24s | Hits: 100%/3404  
      🟩 clang17            Pass: 100%/26  | Total:  5h 36m | Avg: 12m 57s | Max: 25m 30s | Hits: 100%/21832 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 48s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 24m 35s | Avg:  4m 05s | Max:  4m 50s | Hits:  99%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 13s | Avg:  4m 12s | Max:  4m 56s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 26m 11s | Avg:  4m 21s | Max:  4m 43s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 18m 21s | Avg:  4m 35s | Max:  5m 08s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 33m 34s | Avg:  4m 47s | Max:  5m 19s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 19m 19s | Avg:  4m 49s | Max:  5m 03s | Hits:  99%/3404  
      🔍 gcc13              Pass:  96%/28  | Total:  6h 17m | Avg: 13m 28s | Max: 41m 23s | Hits:  99%/22977 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 12s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 44s | Avg: 13m 44s | Max: 13m 44s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 55s | Avg: 11m 27s | Max: 11m 49s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 34m 45s | Avg: 11m 35s | Max: 11m 58s | Hits:  98%/2085  
    🔍 cxx_name: gcc 🔍
      🟩 clang              Pass: 100%/59  | Total:  8h 12m | Avg:  8m 20s | Max: 25m 30s | Hits: 100%/49731 
      🔍 gcc                Pass:  98%/63  | Total:  8h 51m | Avg:  8m 26s | Max: 41m 23s | Hits:  99%/51961 
      🟩 Intel              Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 12s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 44s | Hits:  98%/4170  
    🔍 jobs: HostLaunch 🔍
      🟩 Build              Pass: 100%/99  | Total:  8h 19m | Avg:  5m 02s | Max: 13m 44s | Hits:  99%/81812 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 23m | Avg: 17m 54s | Max: 21m 16s | Hits:  99%/6808  
      🟩 GraphCapture       Pass: 100%/8   | Total:  1h 58m | Avg: 14m 50s | Max: 22m 17s | Hits:  99%/6808  
      🔍 HostLaunch         Pass:  87%/8   | Total:  2h 01m | Avg: 15m 08s | Max: 20m 53s | Hits:  99%/5957  
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 48m | Avg: 28m 34s | Max: 41m 23s | Hits:  99%/6808  
    🔍 os: ubuntu22.04 🔍
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 55m 20s | Avg:  3m 57s | Max:  4m 39s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 42m | Avg:  4m 38s | Max:  5m 34s | Hits:  99%/29855 
      🔍 ubuntu22.04        Pass:  98%/76  | Total: 13h 41m | Avg: 10m 48s | Max: 41m 23s | Hits:  99%/63309 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 44s | Hits:  98%/4170  
    🔍 std: 14 🔍
      🟩 11                 Pass: 100%/34  | Total:  4h 13m | Avg:  7m 27s | Max: 24m 33s | Hits:  99%/28503 
      🔍 14                 Pass:  97%/37  | Total:  5h 05m | Avg:  8m 14s | Max: 41m 23s | Hits:  99%/29737 
      🟩 17                 Pass: 100%/36  | Total:  5h 03m | Avg:  8m 25s | Max: 28m 00s | Hits:  99%/29822 
      🟩 20                 Pass: 100%/24  | Total:  4h 09m | Avg: 10m 22s | Max: 40m 07s | Hits:  99%/20131 
    🟨 gpu
      🟨 v100               Pass:  99%/131 | Total: 18h 30m | Avg:  8m 28s | Max: 41m 23s | Hits:  99%/108193
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 13s | Avg:  3m 48s | Max:  3m 57s | Hits:  99%/3404  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 23m | Avg: 5m 47s | Max: 28m 33s | Hits: 99%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 10h 44m | Avg:  5m 51s | Max: 28m 33s | Hits:  99%/129822
      🟩 arm64              Pass: 100%/8   | Total: 39m 01s | Avg:  4m 52s | Max:  5m 42s | Hits:  99%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 02m | Avg:  4m 11s | Max: 14m 34s | Hits:  99%/17705 
      🟩 11.8               Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 12.4               Pass: 100%/100 | Total: 10h 09m | Avg:  6m 05s | Max: 28m 33s | Hits:  99%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  7m 36s | Avg:  3m 48s | Max:  3m 59s | Hits: 100%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 02m | Avg:  4m 11s | Max: 14m 34s | Hits:  99%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total: 10h 01m | Avg:  6m 08s | Max: 28m 33s | Hits:  99%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  7m 36s | Avg:  3m 48s | Max:  3m 59s | Hits: 100%/2360  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 16m | Avg:  5m 49s | Max: 28m 33s | Hits:  99%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 26m 44s | Avg:  4m 27s | Max:  6m 52s | Hits: 100%/7080  
      🟩 clang10            Pass: 100%/3   | Total: 13m 31s | Avg:  4m 30s | Max:  4m 51s | Hits: 100%/3540  
      🟩 clang11            Pass: 100%/4   | Total: 15m 10s | Avg:  3m 47s | Max:  3m 56s | Hits: 100%/4720  
      🟩 clang12            Pass: 100%/4   | Total: 14m 53s | Avg:  3m 43s | Max:  3m 54s | Hits: 100%/4720  
      🟩 clang13            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  3m 58s | Hits: 100%/4720  
      🟩 clang14            Pass: 100%/4   | Total: 15m 35s | Avg:  3m 53s | Max:  4m 07s | Hits: 100%/4720  
      🟩 clang15            Pass: 100%/4   | Total: 15m 36s | Avg:  3m 54s | Max:  4m 07s | Hits: 100%/4720  
      🟩 clang16            Pass: 100%/4   | Total: 16m 29s | Avg:  4m 07s | Max:  4m 14s | Hits: 100%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  1h 53m | Avg:  6m 18s | Max: 11m 52s | Hits: 100%/21240 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 41s | Hits:  99%/2360  
      🟩 gcc7               Pass: 100%/6   | Total: 26m 31s | Avg:  4m 25s | Max:  7m 51s | Hits:  92%/7086  
      🟩 gcc8               Pass: 100%/6   | Total: 21m 39s | Avg:  3m 36s | Max:  3m 47s | Hits:  99%/7086  
      🟩 gcc9               Pass: 100%/6   | Total: 21m 47s | Avg:  3m 37s | Max:  4m 02s | Hits:  99%/7086  
      🟩 gcc10              Pass: 100%/4   | Total: 15m 04s | Avg:  3m 46s | Max:  3m 53s | Hits:  99%/4724  
      🟩 gcc11              Pass: 100%/7   | Total: 27m 00s | Avg:  3m 51s | Max:  4m 06s | Hits:  99%/8267  
      🟩 gcc12              Pass: 100%/4   | Total: 16m 32s | Avg:  4m 08s | Max:  4m 22s | Hits:  99%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  2h 34m | Avg:  7m 44s | Max: 28m 33s | Hits:  99%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 14m 21s | Avg:  4m 47s | Max:  4m 53s | Hits: 100%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 14m 34s | Avg: 14m 34s | Max: 14m 34s | Hits:  98%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 41s | Avg: 11m 50s | Max: 12m 03s | Hits:  98%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 33m | Avg: 15m 34s | Max: 19m 09s | Hits:  98%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total:  4h 06m | Avg:  4m 50s | Max: 11m 52s | Hits: 100%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  4h 50m | Avg:  5m 17s | Max: 28m 33s | Hits:  98%/64953 
      🟩 Intel              Pass: 100%/3   | Total: 14m 21s | Avg:  4m 47s | Max:  4m 53s | Hits: 100%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 11m | Avg: 14m 37s | Max: 19m 09s | Hits:  98%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 23m | Avg:  5m 47s | Max: 28m 33s | Hits:  99%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  7h 45m | Avg:  4m 41s | Max: 17m 12s | Hits:  99%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 46m | Avg:  9m 38s | Max: 19m 09s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 52m | Avg: 14m 04s | Max: 28m 33s | Hits:  99%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 48m 23s | Avg:  3m 27s | Max:  3m 51s | Hits:  99%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 25m | Avg:  4m 09s | Max:  7m 51s | Hits:  98%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  5h 58m | Avg:  5m 58s | Max: 28m 33s | Hits:  99%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  2h 11m | Avg: 14m 37s | Max: 19m 09s | Hits:  98%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 90a                Pass: 100%/4   | Total: 13m 42s | Avg:  3m 25s | Max:  3m 37s | Hits:  99%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 20m | Avg:  4m 41s | Max: 12m 22s | Hits:  98%/35418 
      🟩 14                 Pass: 100%/34  | Total:  3h 30m | Avg:  6m 12s | Max: 28m 33s | Hits:  99%/40122 
      🟩 17                 Pass: 100%/33  | Total:  3h 09m | Avg:  5m 44s | Max: 18m 42s | Hits:  99%/38946 
      🟩 20                 Pass: 100%/21  | Total:  2h 23m | Avg:  6m 48s | Max: 19m 09s | Hits:  99%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 13h 42m | Avg: 7m 20s | Max: 46m 29s | Hits: 95%/273330

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 13h 03m | Avg:  7m 32s | Max: 46m 29s | Hits:  95%/250976
      🟩 arm64              Pass: 100%/8   | Total: 39m 20s | Avg:  4m 55s | Max:  7m 21s | Hits:  98%/22354 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 17m 26s | Hits:  97%/39776 
      🟩 11.8               Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 12.4               Pass: 100%/94  | Total: 11h 57m | Avg:  7m 37s | Max: 46m 29s | Hits:  96%/225490
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 34m 53s | Avg: 17m 26s | Max: 18m 18s | Hits:  37%/6107  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 17m 26s | Hits:  97%/39776 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 11h 22m | Avg:  7m 25s | Max: 46m 29s | Hits:  97%/219383
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 34m 53s | Avg: 17m 26s | Max: 18m 18s | Hits:  37%/6107  
      🟩 nvcc               Pass: 100%/110 | Total: 13h 07m | Avg:  7m 09s | Max: 46m 29s | Hits:  97%/267223
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 25m 00s | Avg:  4m 10s | Max:  5m 40s | Hits:  99%/16160 
      🟩 clang10            Pass: 100%/3   | Total: 15m 32s | Avg:  5m 10s | Max:  5m 34s | Hits:  99%/8109  
      🟩 clang11            Pass: 100%/4   | Total: 16m 19s | Avg:  4m 04s | Max:  4m 42s | Hits:  98%/11185 
      🟩 clang12            Pass: 100%/4   | Total: 16m 55s | Avg:  4m 13s | Max:  5m 04s | Hits:  98%/11185 
      🟩 clang13            Pass: 100%/4   | Total: 16m 47s | Avg:  4m 11s | Max:  5m 01s | Hits:  98%/11185 
      🟩 clang14            Pass: 100%/4   | Total: 28m 29s | Avg:  7m 07s | Max: 12m 07s | Hits:  87%/11185 
      🟩 clang15            Pass: 100%/4   | Total: 16m 42s | Avg:  4m 10s | Max:  4m 59s | Hits:  98%/11177 
      🟩 clang16            Pass: 100%/4   | Total: 16m 47s | Avg:  4m 11s | Max:  4m 50s | Hits:  98%/11177 
      🟩 clang17            Pass: 100%/14  | Total:  2h 45m | Avg: 11m 48s | Max: 39m 38s | Hits:  84%/28461 
      🟩 gcc6               Pass: 100%/2   | Total:  5m 54s | Avg:  2m 57s | Max:  3m 29s | Hits:  99%/5041  
      🟩 gcc7               Pass: 100%/6   | Total: 18m 52s | Avg:  3m 08s | Max:  4m 26s | Hits:  98%/16146 
      🟩 gcc8               Pass: 100%/6   | Total: 34m 50s | Avg:  5m 48s | Max: 14m 16s | Hits:  91%/16154 
      🟩 gcc9               Pass: 100%/6   | Total: 19m 35s | Avg:  3m 15s | Max:  4m 04s | Hits:  99%/16158 
      🟩 gcc10              Pass: 100%/4   | Total: 14m 52s | Avg:  3m 43s | Max:  4m 20s | Hits:  98%/11185 
      🟩 gcc11              Pass: 100%/7   | Total: 48m 30s | Avg:  6m 55s | Max: 19m 30s | Hits:  91%/19241 
      🟩 gcc12              Pass: 100%/4   | Total: 14m 51s | Avg:  3m 42s | Max:  4m 07s | Hits:  99%/11177 
      🟩 gcc13              Pass: 100%/21  | Total:  3h 57m | Avg: 11m 18s | Max: 46m 29s | Hits:  99%/33914 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 35s | Avg:  5m 11s | Max:  5m 36s | Hits:  98%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 26s | Avg: 17m 26s | Max: 17m 26s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 36s | Avg: 12m 18s | Max: 12m 28s | Hits:  99%/5442  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 52m 34s | Avg: 17m 31s | Max: 26m 47s | Hits:  88%/8413  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  5h 17m | Avg:  6m 45s | Max: 39m 38s | Hits:  94%/119824
      🟩 gcc                Pass: 100%/56  | Total:  6h 34m | Avg:  7m 03s | Max: 46m 29s | Hits:  96%/129016
      🟩 Intel              Pass: 100%/3   | Total: 15m 35s | Avg:  5m 11s | Max:  5m 36s | Hits:  98%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 34m | Avg: 15m 46s | Max: 26m 47s | Hits:  93%/16391 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 13h 42m | Avg:  7m 20s | Max: 46m 29s | Hits:  95%/273330
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  9h 02m | Avg:  5m 28s | Max: 26m 47s | Hits:  95%/273310
      🟩 NVRTC              Pass: 100%/4   | Total:  2h 04m | Avg: 31m 04s | Max: 46m 29s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 39m 38s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 00s | Avg:  2m 00s | Max:  2m 00s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 53m 05s | Avg:  3m 47s | Max: 14m 16s | Hits:  96%/37240 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 40m | Avg:  4m 34s | Max: 12m 07s | Hits:  97%/96453 
      🟩 ubuntu22.04        Pass: 100%/57  | Total:  8h 35m | Avg:  9m 02s | Max: 46m 29s | Hits:  94%/123246
      🟩 windows2022        Pass: 100%/6   | Total:  1h 34m | Avg: 15m 46s | Max: 26m 47s | Hits:  93%/16391 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 90a                Pass: 100%/4   | Total: 14m 26s | Avg:  3m 36s | Max:  3m 56s | Hits:  99%/11540 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  2h 51m | Avg:  5m 54s | Max: 37m 18s | Hits:  98%/57992 
      🟩 14                 Pass: 100%/32  | Total:  3h 47m | Avg:  7m 05s | Max: 46m 29s | Hits:  98%/81900 
      🟩 17                 Pass: 100%/31  | Total:  4h 15m | Avg:  8m 15s | Max: 39m 38s | Hits:  92%/84246 
      🟩 20                 Pass: 100%/19  | Total:  2h 46m | Avg:  8m 45s | Max: 26m 47s | Hits:  91%/49192 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

@harrism
Copy link
Contributor

harrism commented Jun 12, 2024

As mentoined in the other PR,

That is the current design, I intended to store the stream_ref in the uninitialized_async_buffer and the call both stream.wait() and finally deallocate_async on it

As mentioned in your async_buffer PR, I don't think you should synchronize in the dtor.

Copy link
Contributor

🟩 CI finished in 1d 02h: Pass: 100%/361 | Total: 1d 20h | Avg: 7m 19s | Max: 46m 29s | Hits: 97%/521640
  • 🟩 cub: Pass: 100%/131 | Total: 18h 56m | Avg: 8m 40s | Max: 41m 23s | Hits: 99%/109044

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total: 18h 16m | Avg:  8m 54s | Max: 41m 23s | Hits:  99%/102236
      🟩 arm64              Pass: 100%/8   | Total: 40m 34s | Avg:  5m 04s | Max:  5m 31s | Hits:  99%/6808  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 13m 44s | Hits:  99%/11554 
      🟩 11.8               Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🟩 12.4               Pass: 100%/113 | Total: 17h 33m | Avg:  9m 19s | Max: 41m 23s | Hits:  99%/94937 
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  7m 20s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1408  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 09m | Avg:  4m 36s | Max: 13m 44s | Hits:  99%/11554 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🟩 nvcc12.4           Pass: 100%/111 | Total: 17h 26m | Avg:  9m 25s | Max: 41m 23s | Hits:  99%/93529 
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  7m 20s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1408  
      🟩 nvcc               Pass: 100%/129 | Total: 18h 49m | Avg:  8m 45s | Max: 41m 23s | Hits:  99%/107636
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 27m 28s | Avg:  4m 34s | Max:  5m 14s | Hits: 100%/4884  
      🟩 clang10            Pass: 100%/3   | Total: 16m 08s | Avg:  5m 22s | Max:  5m 34s | Hits: 100%/2559  
      🟩 clang11            Pass: 100%/4   | Total: 18m 49s | Avg:  4m 42s | Max:  4m 49s | Hits: 100%/3412  
      🟩 clang12            Pass: 100%/4   | Total: 18m 24s | Avg:  4m 36s | Max:  5m 05s | Hits: 100%/3412  
      🟩 clang13            Pass: 100%/4   | Total: 17m 21s | Avg:  4m 20s | Max:  4m 26s | Hits: 100%/3412  
      🟩 clang14            Pass: 100%/4   | Total: 17m 59s | Avg:  4m 29s | Max:  4m 35s | Hits: 100%/3412  
      🟩 clang15            Pass: 100%/4   | Total: 19m 15s | Avg:  4m 48s | Max:  5m 24s | Hits: 100%/3404  
      🟩 clang16            Pass: 100%/4   | Total: 20m 04s | Avg:  5m 01s | Max:  6m 24s | Hits: 100%/3404  
      🟩 clang17            Pass: 100%/26  | Total:  5h 36m | Avg: 12m 57s | Max: 25m 30s | Hits: 100%/21832 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 48s | Hits:  99%/1550  
      🟩 gcc7               Pass: 100%/6   | Total: 24m 35s | Avg:  4m 05s | Max:  4m 50s | Hits:  99%/4887  
      🟩 gcc8               Pass: 100%/6   | Total: 25m 13s | Avg:  4m 12s | Max:  4m 56s | Hits:  99%/4887  
      🟩 gcc9               Pass: 100%/6   | Total: 26m 11s | Avg:  4m 21s | Max:  4m 43s | Hits:  99%/4887  
      🟩 gcc10              Pass: 100%/4   | Total: 18m 21s | Avg:  4m 35s | Max:  5m 08s | Hits:  99%/3412  
      🟩 gcc11              Pass: 100%/7   | Total: 33m 34s | Avg:  4m 47s | Max:  5m 19s | Hits:  99%/5957  
      🟩 gcc12              Pass: 100%/4   | Total: 19m 19s | Avg:  4m 49s | Max:  5m 03s | Hits:  99%/3404  
      🟩 gcc13              Pass: 100%/28  | Total:  6h 43m | Avg: 14m 24s | Max: 41m 23s | Hits:  99%/23828 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 12s | Hits: 100%/2331  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 44s | Avg: 13m 44s | Max: 13m 44s | Hits:  98%/695   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 55s | Avg: 11m 27s | Max: 11m 49s | Hits:  98%/1390  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 34m 45s | Avg: 11m 35s | Max: 11m 58s | Hits:  98%/2085  
    🟩 cxx_name
      🟩 clang              Pass: 100%/59  | Total:  8h 12m | Avg:  8m 20s | Max: 25m 30s | Hits: 100%/49731 
      🟩 gcc                Pass: 100%/63  | Total:  9h 17m | Avg:  8m 51s | Max: 41m 23s | Hits:  99%/52812 
      🟩 Intel              Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 12s | Hits: 100%/2331  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 44s | Hits:  98%/4170  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total: 18h 56m | Avg:  8m 40s | Max: 41m 23s | Hits:  99%/109044
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  8h 19m | Avg:  5m 02s | Max: 13m 44s | Hits:  99%/81812 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 23m | Avg: 17m 54s | Max: 21m 16s | Hits:  99%/6808  
      🟩 GraphCapture       Pass: 100%/8   | Total:  1h 58m | Avg: 14m 50s | Max: 22m 17s | Hits:  99%/6808  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 27m | Avg: 18m 24s | Max: 29m 54s | Hits:  99%/6808  
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 48m | Avg: 28m 34s | Max: 41m 23s | Hits:  99%/6808  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 55m 20s | Avg:  3m 57s | Max:  4m 39s | Hits:  99%/10859 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 42m | Avg:  4m 38s | Max:  5m 34s | Hits:  99%/29855 
      🟩 ubuntu22.04        Pass: 100%/76  | Total: 14h 07m | Avg: 11m 09s | Max: 41m 23s | Hits:  99%/64160 
      🟩 windows2022        Pass: 100%/6   | Total:  1h 11m | Avg: 11m 54s | Max: 13m 44s | Hits:  98%/4170  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 18s | Avg:  4m 46s | Max:  4m 52s | Hits:  99%/2553  
      🟩 90a                Pass: 100%/4   | Total: 15m 13s | Avg:  3m 48s | Max:  3m 57s | Hits:  99%/3404  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total:  4h 13m | Avg:  7m 27s | Max: 24m 33s | Hits:  99%/28503 
      🟩 14                 Pass: 100%/37  | Total:  5h 31m | Avg:  8m 57s | Max: 41m 23s | Hits:  99%/30588 
      🟩 17                 Pass: 100%/36  | Total:  5h 03m | Avg:  8m 25s | Max: 28m 00s | Hits:  99%/29822 
      🟩 20                 Pass: 100%/24  | Total:  4h 09m | Avg: 10m 22s | Max: 40m 07s | Hits:  99%/20131 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 23m | Avg: 5m 47s | Max: 28m 33s | Hits: 99%/139266

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 10h 44m | Avg:  5m 51s | Max: 28m 33s | Hits:  99%/129822
      🟩 arm64              Pass: 100%/8   | Total: 39m 01s | Avg:  4m 52s | Max:  5m 42s | Hits:  99%/9444  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 02m | Avg:  4m 11s | Max: 14m 34s | Hits:  99%/17705 
      🟩 11.8               Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 12.4               Pass: 100%/100 | Total: 10h 09m | Avg:  6m 05s | Max: 28m 33s | Hits:  99%/118018
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total:  7m 36s | Avg:  3m 48s | Max:  3m 59s | Hits: 100%/2360  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 02m | Avg:  4m 11s | Max: 14m 34s | Hits:  99%/17705 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 nvcc12.4           Pass: 100%/98  | Total: 10h 01m | Avg:  6m 08s | Max: 28m 33s | Hits:  99%/115658
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total:  7m 36s | Avg:  3m 48s | Max:  3m 59s | Hits: 100%/2360  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 16m | Avg:  5m 49s | Max: 28m 33s | Hits:  99%/136906
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 26m 44s | Avg:  4m 27s | Max:  6m 52s | Hits: 100%/7080  
      🟩 clang10            Pass: 100%/3   | Total: 13m 31s | Avg:  4m 30s | Max:  4m 51s | Hits: 100%/3540  
      🟩 clang11            Pass: 100%/4   | Total: 15m 10s | Avg:  3m 47s | Max:  3m 56s | Hits: 100%/4720  
      🟩 clang12            Pass: 100%/4   | Total: 14m 53s | Avg:  3m 43s | Max:  3m 54s | Hits: 100%/4720  
      🟩 clang13            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  3m 58s | Hits: 100%/4720  
      🟩 clang14            Pass: 100%/4   | Total: 15m 35s | Avg:  3m 53s | Max:  4m 07s | Hits: 100%/4720  
      🟩 clang15            Pass: 100%/4   | Total: 15m 36s | Avg:  3m 54s | Max:  4m 07s | Hits: 100%/4720  
      🟩 clang16            Pass: 100%/4   | Total: 16m 29s | Avg:  4m 07s | Max:  4m 14s | Hits: 100%/4720  
      🟩 clang17            Pass: 100%/18  | Total:  1h 53m | Avg:  6m 18s | Max: 11m 52s | Hits: 100%/21240 
      🟩 gcc6               Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 41s | Hits:  99%/2360  
      🟩 gcc7               Pass: 100%/6   | Total: 26m 31s | Avg:  4m 25s | Max:  7m 51s | Hits:  92%/7086  
      🟩 gcc8               Pass: 100%/6   | Total: 21m 39s | Avg:  3m 36s | Max:  3m 47s | Hits:  99%/7086  
      🟩 gcc9               Pass: 100%/6   | Total: 21m 47s | Avg:  3m 37s | Max:  4m 02s | Hits:  99%/7086  
      🟩 gcc10              Pass: 100%/4   | Total: 15m 04s | Avg:  3m 46s | Max:  3m 53s | Hits:  99%/4724  
      🟩 gcc11              Pass: 100%/7   | Total: 27m 00s | Avg:  3m 51s | Max:  4m 06s | Hits:  99%/8267  
      🟩 gcc12              Pass: 100%/4   | Total: 16m 32s | Avg:  4m 08s | Max:  4m 22s | Hits:  99%/4724  
      🟩 gcc13              Pass: 100%/20  | Total:  2h 34m | Avg:  7m 44s | Max: 28m 33s | Hits:  99%/23620 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 14m 21s | Avg:  4m 47s | Max:  4m 53s | Hits: 100%/3549  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 14m 34s | Avg: 14m 34s | Max: 14m 34s | Hits:  98%/1176  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 41s | Avg: 11m 50s | Max: 12m 03s | Hits:  98%/2352  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 33m | Avg: 15m 34s | Max: 19m 09s | Hits:  98%/7056  
    🟩 cxx_name
      🟩 clang              Pass: 100%/51  | Total:  4h 06m | Avg:  4m 50s | Max: 11m 52s | Hits: 100%/60180 
      🟩 gcc                Pass: 100%/55  | Total:  4h 50m | Avg:  5m 17s | Max: 28m 33s | Hits:  98%/64953 
      🟩 Intel              Pass: 100%/3   | Total: 14m 21s | Avg:  4m 47s | Max:  4m 53s | Hits: 100%/3549  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 11m | Avg: 14m 37s | Max: 19m 09s | Hits:  98%/10584 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 23m | Avg:  5m 47s | Max: 28m 33s | Hits:  99%/139266
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  7h 45m | Avg:  4m 41s | Max: 17m 12s | Hits:  99%/116850
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 46m | Avg:  9m 38s | Max: 19m 09s | Hits:  99%/12972 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 52m | Avg: 14m 04s | Max: 28m 33s | Hits:  99%/9444  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 48m 23s | Avg:  3m 27s | Max:  3m 51s | Hits:  99%/16529 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 25m | Avg:  4m 09s | Max:  7m 51s | Hits:  98%/41313 
      🟩 ubuntu22.04        Pass: 100%/60  | Total:  5h 58m | Avg:  5m 58s | Max: 28m 33s | Hits:  99%/70840 
      🟩 windows2022        Pass: 100%/9   | Total:  2h 11m | Avg: 14m 37s | Max: 19m 09s | Hits:  98%/10584 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 30s | Avg:  3m 50s | Max:  4m 06s | Hits:  99%/3543  
      🟩 90a                Pass: 100%/4   | Total: 13m 42s | Avg:  3m 25s | Max:  3m 37s | Hits:  99%/4724  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 20m | Avg:  4m 41s | Max: 12m 22s | Hits:  98%/35418 
      🟩 14                 Pass: 100%/34  | Total:  3h 30m | Avg:  6m 12s | Max: 28m 33s | Hits:  99%/40122 
      🟩 17                 Pass: 100%/33  | Total:  3h 09m | Avg:  5m 44s | Max: 18m 42s | Hits:  99%/38946 
      🟩 20                 Pass: 100%/21  | Total:  2h 23m | Avg:  6m 48s | Max: 19m 09s | Hits:  99%/24780 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 13h 42m | Avg: 7m 20s | Max: 46m 29s | Hits: 95%/273330

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 13h 03m | Avg:  7m 32s | Max: 46m 29s | Hits:  95%/250976
      🟩 arm64              Pass: 100%/8   | Total: 39m 20s | Avg:  4m 55s | Max:  7m 21s | Hits:  98%/22354 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 17m 26s | Hits:  97%/39776 
      🟩 11.8               Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 12.4               Pass: 100%/94  | Total: 11h 57m | Avg:  7m 37s | Max: 46m 29s | Hits:  96%/225490
    🟩 cudacxx_full
      🟩 clang-cuda17       Pass: 100%/2   | Total: 34m 53s | Avg: 17m 26s | Max: 18m 18s | Hits:  37%/6107  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 10m | Avg:  4m 42s | Max: 17m 26s | Hits:  97%/39776 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 nvcc12.4           Pass: 100%/92  | Total: 11h 22m | Avg:  7m 25s | Max: 46m 29s | Hits:  97%/219383
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total: 34m 53s | Avg: 17m 26s | Max: 18m 18s | Hits:  37%/6107  
      🟩 nvcc               Pass: 100%/110 | Total: 13h 07m | Avg:  7m 09s | Max: 46m 29s | Hits:  97%/267223
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total: 25m 00s | Avg:  4m 10s | Max:  5m 40s | Hits:  99%/16160 
      🟩 clang10            Pass: 100%/3   | Total: 15m 32s | Avg:  5m 10s | Max:  5m 34s | Hits:  99%/8109  
      🟩 clang11            Pass: 100%/4   | Total: 16m 19s | Avg:  4m 04s | Max:  4m 42s | Hits:  98%/11185 
      🟩 clang12            Pass: 100%/4   | Total: 16m 55s | Avg:  4m 13s | Max:  5m 04s | Hits:  98%/11185 
      🟩 clang13            Pass: 100%/4   | Total: 16m 47s | Avg:  4m 11s | Max:  5m 01s | Hits:  98%/11185 
      🟩 clang14            Pass: 100%/4   | Total: 28m 29s | Avg:  7m 07s | Max: 12m 07s | Hits:  87%/11185 
      🟩 clang15            Pass: 100%/4   | Total: 16m 42s | Avg:  4m 10s | Max:  4m 59s | Hits:  98%/11177 
      🟩 clang16            Pass: 100%/4   | Total: 16m 47s | Avg:  4m 11s | Max:  4m 50s | Hits:  98%/11177 
      🟩 clang17            Pass: 100%/14  | Total:  2h 45m | Avg: 11m 48s | Max: 39m 38s | Hits:  84%/28461 
      🟩 gcc6               Pass: 100%/2   | Total:  5m 54s | Avg:  2m 57s | Max:  3m 29s | Hits:  99%/5041  
      🟩 gcc7               Pass: 100%/6   | Total: 18m 52s | Avg:  3m 08s | Max:  4m 26s | Hits:  98%/16146 
      🟩 gcc8               Pass: 100%/6   | Total: 34m 50s | Avg:  5m 48s | Max: 14m 16s | Hits:  91%/16154 
      🟩 gcc9               Pass: 100%/6   | Total: 19m 35s | Avg:  3m 15s | Max:  4m 04s | Hits:  99%/16158 
      🟩 gcc10              Pass: 100%/4   | Total: 14m 52s | Avg:  3m 43s | Max:  4m 20s | Hits:  98%/11185 
      🟩 gcc11              Pass: 100%/7   | Total: 48m 30s | Avg:  6m 55s | Max: 19m 30s | Hits:  91%/19241 
      🟩 gcc12              Pass: 100%/4   | Total: 14m 51s | Avg:  3m 42s | Max:  4m 07s | Hits:  99%/11177 
      🟩 gcc13              Pass: 100%/21  | Total:  3h 57m | Avg: 11m 18s | Max: 46m 29s | Hits:  99%/33914 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 35s | Avg:  5m 11s | Max:  5m 36s | Hits:  98%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 26s | Avg: 17m 26s | Max: 17m 26s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 24m 36s | Avg: 12m 18s | Max: 12m 28s | Hits:  99%/5442  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 52m 34s | Avg: 17m 31s | Max: 26m 47s | Hits:  88%/8413  
    🟩 cxx_name
      🟩 clang              Pass: 100%/47  | Total:  5h 17m | Avg:  6m 45s | Max: 39m 38s | Hits:  94%/119824
      🟩 gcc                Pass: 100%/56  | Total:  6h 34m | Avg:  7m 03s | Max: 46m 29s | Hits:  96%/129016
      🟩 Intel              Pass: 100%/3   | Total: 15m 35s | Avg:  5m 11s | Max:  5m 36s | Hits:  98%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 34m | Avg: 15m 46s | Max: 26m 47s | Hits:  93%/16391 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 13h 42m | Avg:  7m 20s | Max: 46m 29s | Hits:  95%/273330
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  9h 02m | Avg:  5m 28s | Max: 26m 47s | Hits:  95%/273310
      🟩 NVRTC              Pass: 100%/4   | Total:  2h 04m | Avg: 31m 04s | Max: 46m 29s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 39m 38s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 00s | Avg:  2m 00s | Max:  2m 00s
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total: 53m 05s | Avg:  3m 47s | Max: 14m 16s | Hits:  96%/37240 
      🟩 ubuntu20.04        Pass: 100%/35  | Total:  2h 40m | Avg:  4m 34s | Max: 12m 07s | Hits:  97%/96453 
      🟩 ubuntu22.04        Pass: 100%/57  | Total:  8h 35m | Avg:  9m 02s | Max: 46m 29s | Hits:  94%/123246
      🟩 windows2022        Pass: 100%/6   | Total:  1h 34m | Avg: 15m 46s | Max: 26m 47s | Hits:  93%/16391 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 34m 50s | Avg: 11m 36s | Max: 19m 30s | Hits:  80%/8064  
      🟩 90a                Pass: 100%/4   | Total: 14m 26s | Avg:  3m 36s | Max:  3m 56s | Hits:  99%/11540 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  2h 51m | Avg:  5m 54s | Max: 37m 18s | Hits:  98%/57992 
      🟩 14                 Pass: 100%/32  | Total:  3h 47m | Avg:  7m 05s | Max: 46m 29s | Hits:  98%/81900 
      🟩 17                 Pass: 100%/31  | Total:  4h 15m | Avg:  8m 15s | Max: 39m 38s | Hits:  92%/84246 
      🟩 20                 Pass: 100%/19  | Total:  2h 46m | Avg:  8m 45s | Max: 26m 47s | Hits:  91%/49192 
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 361)

# Runner
264 linux-amd64-cpu16
52 linux-amd64-gpu-v100-latest-1
24 linux-arm64-cpu16
21 windows-amd64-cpu16

Copy link
Contributor

🟨 CI finished in 4h 26m: Pass: 99%/421 | Total: 6d 04h | Avg: 21m 10s | Max: 59m 09s | Hits: 79%/525364
  • 🟨 libcudacxx: Pass: 99%/112 | Total: 14h 09m | Avg: 7m 35s | Max: 28m 15s | Hits: 91%/273250

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  99%/104 | Total: 13h 37m | Avg:  7m 51s | Max: 28m 15s | Hits:  90%/250904
      🟩 arm64              Pass: 100%/8   | Total: 32m 23s | Avg:  4m 02s | Max:  4m 51s | Hits:  98%/22346 
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 07m | Avg:  4m 28s | Max: 17m 28s | Hits:  95%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 55m 37s | Avg: 18m 32s | Max: 20m 11s | Hits:  46%/8064  
      🔍 12.5               Pass:  98%/94  | Total: 12h 06m | Avg:  7m 43s | Max: 28m 15s | Hits:  92%/225406
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 34m 16s | Avg: 17m 08s | Max: 18m 10s | Hits:  37%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 07m | Avg:  4m 28s | Max: 17m 28s | Hits:  95%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 55m 37s | Avg: 18m 32s | Max: 20m 11s | Hits:  46%/8064  
      🔍 nvcc12.5           Pass:  98%/92  | Total: 11h 32m | Avg:  7m 31s | Max: 28m 15s | Hits:  93%/219307
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 34m 16s | Avg: 17m 08s | Max: 18m 10s | Hits:  37%/6099  
      🔍 nvcc               Pass:  99%/110 | Total: 13h 35m | Avg:  7m 24s | Max: 28m 15s | Hits:  92%/267151
    🔍 cxx: GCC13 🔍
      🟩 Clang9             Pass: 100%/6   | Total: 24m 06s | Avg:  4m 01s | Max:  5m 08s | Hits:  99%/16160 
      🟩 Clang10            Pass: 100%/3   | Total: 16m 21s | Avg:  5m 27s | Max:  5m 33s | Hits:  97%/8109  
      🟩 Clang11            Pass: 100%/4   | Total: 16m 33s | Avg:  4m 08s | Max:  5m 03s | Hits:  97%/11181 
      🟩 Clang12            Pass: 100%/4   | Total: 30m 10s | Avg:  7m 32s | Max: 18m 49s | Hits:  83%/11181 
      🟩 Clang13            Pass: 100%/4   | Total: 16m 48s | Avg:  4m 12s | Max:  4m 50s | Hits:  98%/11181 
      🟩 Clang14            Pass: 100%/4   | Total: 16m 55s | Avg:  4m 13s | Max:  4m 32s | Hits:  99%/11181 
      🟩 Clang15            Pass: 100%/4   | Total: 33m 13s | Avg:  8m 18s | Max: 19m 44s | Hits:  82%/11173 
      🟩 Clang16            Pass: 100%/4   | Total: 31m 44s | Avg:  7m 56s | Max: 18m 37s | Hits:  85%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  2h 44m | Avg: 11m 46s | Max: 28m 15s | Hits:  82%/28445 
      🟩 GCC6               Pass: 100%/2   | Total:  5m 03s | Avg:  2m 31s | Max:  2m 34s | Hits:  99%/5045  
      🟩 GCC7               Pass: 100%/6   | Total: 42m 52s | Avg:  7m 08s | Max: 18m 42s | Hits:  79%/16146 
      🟩 GCC8               Pass: 100%/6   | Total: 17m 45s | Avg:  2m 57s | Max:  3m 20s | Hits:  99%/16154 
      🟩 GCC9               Pass: 100%/6   | Total: 20m 20s | Avg:  3m 23s | Max:  4m 18s | Hits:  97%/16158 
      🟩 GCC10              Pass: 100%/4   | Total: 30m 29s | Avg:  7m 37s | Max: 19m 21s | Hits:  89%/11181 
      🟩 GCC11              Pass: 100%/7   | Total:  1h 10m | Avg: 10m 08s | Max: 20m 11s | Hits:  75%/19237 
      🟩 GCC12              Pass: 100%/4   | Total: 16m 19s | Avg:  4m 04s | Max:  5m 04s | Hits:  98%/11173 
      🔍 GCC13              Pass:  95%/21  | Total:  3h 22m | Avg:  9m 37s | Max: 28m 06s | Hits:  94%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 34s | Avg:  5m 11s | Max:  5m 44s | Hits:  99%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 28s | Avg: 17m 28s | Max: 17m 28s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 39s | Avg: 11m 49s | Max: 12m 15s | Hits:  96%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 36m 20s | Avg: 12m 06s | Max: 12m 13s | Hits:  98%/8401  
    🔍 cxx_family: GCC 🔍
      🟩 Clang              Pass: 100%/47  | Total:  5h 50m | Avg:  7m 27s | Max: 28m 15s | Hits:  90%/119784
      🔍 GCC                Pass:  98%/56  | Total:  6h 45m | Avg:  7m 14s | Max: 28m 06s | Hits:  90%/128996
      🟩 Intel              Pass: 100%/3   | Total: 15m 34s | Avg:  5m 11s | Max:  5m 44s | Hits:  99%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 17m | Avg: 12m 54s | Max: 17m 28s | Hits:  97%/16371 
    🔍 jobs: Test 🔍
      🟩 Build              Pass: 100%/99  | Total: 10h 23m | Avg:  6m 17s | Max: 20m 11s | Hits:  91%/273230
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 09m | Avg: 17m 25s | Max: 18m 41s | Hits: 100%/20    
      🔍 Test               Pass:  87%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 28m 15s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 50s | Avg:  1m 50s | Max:  1m 50s
    🔍 std: 20 🔍
      🟩 11                 Pass: 100%/29  | Total:  3h 01m | Avg:  6m 14s | Max: 20m 11s | Hits:  93%/58200 
      🟩 14                 Pass: 100%/32  | Total:  4h 09m | Avg:  7m 47s | Max: 23m 21s | Hits:  90%/81788 
      🟩 17                 Pass: 100%/31  | Total:  4h 20m | Avg:  8m 24s | Max: 28m 15s | Hits:  90%/84134 
      🔍 20                 Pass:  94%/19  | Total:  2h 36m | Avg:  8m 15s | Max: 18m 49s | Hits:  91%/49128 
    🟨 gpu
      🟨 v100               Pass:  99%/112 | Total: 14h 09m | Avg:  7m 35s | Max: 28m 15s | Hits:  91%/273250
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 55m 37s | Avg: 18m 32s | Max: 20m 11s | Hits:  46%/8064  
      🟩 90a                Pass: 100%/4   | Total: 13m 45s | Avg:  3m 26s | Max:  3m 47s | Hits:  99%/11536 
    
  • 🟩 cub: Pass: 100%/131 | Total: 3d 05h | Avg: 35m 18s | Max: 57m 31s | Hits: 91%/111124

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total:  2d 22h | Avg: 34m 28s | Max: 57m 31s | Hits:  92%/104188
      🟩 arm64              Pass: 100%/8   | Total:  6h 23m | Avg: 47m 59s | Max: 53m 58s | Hits:  85%/6936  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  9h 00m | Avg: 36m 02s | Max: 43m 44s | Hits:  91%/11792 
      🟩 11.8               Pass: 100%/3   | Total:  2h 43m | Avg: 54m 30s | Max: 57m 31s | Hits:  88%/2601  
      🟩 12.5               Pass: 100%/113 | Total:  2d 17h | Avg: 34m 41s | Max: 53m 58s | Hits:  92%/96731 
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 28m 14s | Avg: 14m 07s | Max: 14m 22s | Hits:  92%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  9h 00m | Avg: 36m 02s | Max: 43m 44s | Hits:  91%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total:  2h 43m | Avg: 54m 30s | Max: 57m 31s | Hits:  88%/2601  
      🟩 nvcc12.5           Pass: 100%/111 | Total:  2d 16h | Avg: 35m 04s | Max: 53m 58s | Hits:  92%/95295 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 28m 14s | Avg: 14m 07s | Max: 14m 22s | Hits:  92%/1436  
      🟩 nvcc               Pass: 100%/129 | Total:  3d 04h | Avg: 35m 37s | Max: 57m 31s | Hits:  91%/109688
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  3h 51m | Avg: 38m 31s | Max: 41m 24s | Hits:  90%/4980  
      🟩 Clang10            Pass: 100%/3   | Total:  2h 00m | Avg: 40m 15s | Max: 41m 07s | Hits:  89%/2607  
      🟩 Clang11            Pass: 100%/4   | Total:  2h 45m | Avg: 41m 19s | Max: 45m 32s | Hits:  89%/3476  
      🟩 Clang12            Pass: 100%/4   | Total:  2h 41m | Avg: 40m 28s | Max: 41m 28s | Hits:  89%/3476  
      🟩 Clang13            Pass: 100%/4   | Total:  2h 42m | Avg: 40m 31s | Max: 42m 07s | Hits:  89%/3476  
      🟩 Clang14            Pass: 100%/4   | Total:  2h 45m | Avg: 41m 27s | Max: 43m 30s | Hits:  89%/3476  
      🟩 Clang15            Pass: 100%/4   | Total:  2h 45m | Avg: 41m 16s | Max: 42m 31s | Hits:  89%/3468  
      🟩 Clang16            Pass: 100%/4   | Total:  2h 39m | Avg: 39m 51s | Max: 40m 42s | Hits:  89%/3468  
      🟩 Clang17            Pass: 100%/26  | Total: 11h 29m | Avg: 26m 32s | Max: 46m 56s | Hits:  96%/22244 
      🟩 GCC6               Pass: 100%/2   | Total:  1h 08m | Avg: 34m 02s | Max: 34m 23s | Hits:  91%/1582  
      🟩 GCC7               Pass: 100%/6   | Total:  3h 53m | Avg: 38m 53s | Max: 41m 31s | Hits:  90%/4983  
      🟩 GCC8               Pass: 100%/6   | Total:  3h 46m | Avg: 37m 41s | Max: 41m 37s | Hits:  90%/4983  
      🟩 GCC9               Pass: 100%/6   | Total:  3h 45m | Avg: 37m 32s | Max: 41m 04s | Hits:  90%/4983  
      🟩 GCC10              Pass: 100%/4   | Total:  2h 42m | Avg: 40m 39s | Max: 42m 14s | Hits:  88%/3476  
      🟩 GCC11              Pass: 100%/7   | Total:  5h 23m | Avg: 46m 16s | Max: 57m 31s | Hits:  88%/6069  
      🟩 GCC12              Pass: 100%/4   | Total:  2h 46m | Avg: 41m 33s | Max: 44m 34s | Hits:  88%/3468  
      🟩 GCC13              Pass: 100%/28  | Total: 12h 53m | Avg: 27m 37s | Max: 53m 58s | Hits:  93%/24276 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 08m | Avg: 42m 41s | Max: 44m 17s | Hits:  91%/2379  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 43m 44s | Avg: 43m 44s | Max: 43m 44s | Hits:  91%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 40m | Avg: 50m 27s | Max: 50m 50s | Hits:  91%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  2h 31m | Avg: 50m 30s | Max: 51m 14s | Hits:  91%/2127  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/59  | Total:  1d 09h | Avg: 34m 15s | Max: 46m 56s | Hits:  92%/50671 
      🟩 GCC                Pass: 100%/63  | Total:  1d 12h | Avg: 34m 35s | Max: 57m 31s | Hits:  91%/53820 
      🟩 Intel              Pass: 100%/3   | Total:  2h 08m | Avg: 42m 41s | Max: 44m 17s | Hits:  91%/2379  
      🟩 MSVC               Pass: 100%/6   | Total:  4h 56m | Avg: 49m 21s | Max: 51m 14s | Hits:  91%/4254  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total:  3d 05h | Avg: 35m 18s | Max: 57m 31s | Hits:  91%/111124
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  2d 18h | Avg: 40m 13s | Max: 57m 31s | Hits:  89%/83380 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 24m | Avg: 18m 03s | Max: 20m 41s | Hits:  99%/6936  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 06m | Avg: 15m 50s | Max: 18m 28s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 31m | Avg: 18m 59s | Max: 21m 50s | Hits:  99%/6936  
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 39m | Avg: 27m 29s | Max: 39m 07s | Hits:  99%/6936  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  2h 43m | Avg: 54m 30s | Max: 57m 31s | Hits:  88%/2601  
      🟩 90a                Pass: 100%/4   | Total:  1h 09m | Avg: 17m 27s | Max: 18m 01s | Hits:  88%/3468  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total: 19h 48m | Avg: 34m 57s | Max: 57m 31s | Hits:  91%/29047 
      🟩 14                 Pass: 100%/37  | Total: 22h 19m | Avg: 36m 11s | Max: 53m 13s | Hits:  92%/31174 
      🟩 17                 Pass: 100%/36  | Total: 21h 35m | Avg: 35m 59s | Max: 52m 48s | Hits:  92%/30392 
      🟩 20                 Pass: 100%/24  | Total: 13h 21m | Avg: 33m 23s | Max: 51m 14s | Hits:  92%/20511 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 2d 06h | Avg: 27m 34s | Max: 59m 09s | Hits: 45%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  2d 02h | Avg: 27m 23s | Max: 59m 09s | Hits:  46%/129492
      🟩 arm64              Pass: 100%/8   | Total:  4h 00m | Avg: 30m 03s | Max: 33m 16s | Hits:  32%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  6h 57m | Avg: 27m 49s | Max: 52m 18s | Hits:  32%/17660 
      🟩 11.8               Pass: 100%/3   | Total:  1h 53m | Avg: 37m 43s | Max: 40m 56s | Hits:  32%/3534  
      🟩 12.5               Pass: 100%/100 | Total:  1d 21h | Avg: 27m 13s | Max: 59m 09s | Hits:  48%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 54m 26s | Avg: 27m 13s | Max: 27m 30s | Hits:  31%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  6h 57m | Avg: 27m 49s | Max: 52m 18s | Hits:  32%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 53m | Avg: 37m 43s | Max: 40m 56s | Hits:  32%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total:  1d 20h | Avg: 27m 14s | Max: 59m 09s | Hits:  48%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 54m 26s | Avg: 27m 13s | Max: 27m 30s | Hits:  31%/2354  
      🟩 nvcc               Pass: 100%/116 | Total:  2d 05h | Avg: 27m 34s | Max: 59m 09s | Hits:  45%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 45m | Avg: 27m 33s | Max: 31m 48s | Hits:  32%/7062  
      🟩 Clang10            Pass: 100%/3   | Total:  1h 34m | Avg: 31m 32s | Max: 34m 53s | Hits:  32%/3531  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 58m | Avg: 29m 39s | Max: 31m 45s | Hits:  32%/4708  
      🟩 Clang12            Pass: 100%/4   | Total:  1h 54m | Avg: 28m 40s | Max: 30m 22s | Hits:  32%/4708  
      🟩 Clang13            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 17s | Max: 31m 40s | Hits:  32%/4708  
      🟩 Clang14            Pass: 100%/4   | Total:  2h 03m | Avg: 30m 55s | Max: 34m 14s | Hits:  32%/4708  
      🟩 Clang15            Pass: 100%/4   | Total:  2h 01m | Avg: 30m 25s | Max: 33m 15s | Hits:  32%/4708  
      🟩 Clang16            Pass: 100%/4   | Total:  1h 58m | Avg: 29m 42s | Max: 31m 58s | Hits:  32%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  6h 00m | Avg: 20m 01s | Max: 33m 16s | Hits:  63%/21186 
      🟩 GCC6               Pass: 100%/2   | Total: 50m 12s | Avg: 25m 06s | Max: 27m 39s | Hits:  33%/2354  
      🟩 GCC7               Pass: 100%/6   | Total:  2h 39m | Avg: 26m 37s | Max: 32m 37s | Hits:  32%/7068  
      🟩 GCC8               Pass: 100%/6   | Total:  2h 45m | Avg: 27m 37s | Max: 31m 15s | Hits:  32%/7068  
      🟩 GCC9               Pass: 100%/6   | Total:  2h 57m | Avg: 29m 38s | Max: 35m 33s | Hits:  32%/7068  
      🟩 GCC10              Pass: 100%/4   | Total:  2h 02m | Avg: 30m 44s | Max: 32m 38s | Hits:  32%/4712  
      🟩 GCC11              Pass: 100%/7   | Total:  3h 43m | Avg: 31m 59s | Max: 40m 56s | Hits:  49%/8246  
      🟩 GCC12              Pass: 100%/4   | Total:  2h 03m | Avg: 30m 48s | Max: 32m 46s | Hits:  32%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  6h 20m | Avg: 19m 00s | Max: 33m 09s | Hits:  67%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 02m | Avg: 40m 49s | Max: 46m 51s | Hits:  32%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 52m 18s | Avg: 52m 18s | Max: 52m 18s | Hits:  30%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 52m | Avg: 56m 14s | Max: 56m 41s | Hits:  30%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 47m | Avg: 37m 57s | Max: 59m 09s | Hits:  64%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total: 22h 15m | Avg: 26m 10s | Max: 34m 53s | Hits:  43%/60027 
      🟩 GCC                Pass: 100%/55  | Total: 23h 23m | Avg: 25m 31s | Max: 40m 56s | Hits:  47%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  2h 02m | Avg: 40m 49s | Max: 46m 51s | Hits:  32%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 32m | Avg: 43m 37s | Max: 59m 09s | Hits:  53%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  2d 06h | Avg: 27m 34s | Max: 59m 09s | Hits:  45%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  2d 02h | Avg: 30m 51s | Max: 59m 09s | Hits:  35%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 41m | Avg:  9m 14s | Max: 17m 50s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 37m | Avg: 12m 13s | Max: 14m 40s | Hits:  99%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 53m | Avg: 37m 43s | Max: 40m 56s | Hits:  32%/3534  
      🟩 90a                Pass: 100%/4   | Total:  1h 16m | Avg: 19m 04s | Max: 20m 23s | Hits:  32%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total: 11h 40m | Avg: 23m 20s | Max: 35m 31s | Hits:  45%/35328 
      🟩 14                 Pass: 100%/34  | Total: 16h 41m | Avg: 29m 27s | Max: 58m 14s | Hits:  44%/40020 
      🟩 17                 Pass: 100%/33  | Total: 16h 19m | Avg: 29m 41s | Max: 58m 18s | Hits:  44%/38847 
      🟩 20                 Pass: 100%/21  | Total:  9h 31m | Avg: 27m 14s | Max: 59m 09s | Hits:  50%/24717 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 37m | Avg: 2m 51s | Max: 6m 51s | Hits: 94%/2078

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 26m | Avg:  2m 52s | Max:  6m 51s | Hits:  94%/1926  
      🟩 arm64              Pass: 100%/4   | Total: 11m 18s | Avg:  2m 49s | Max:  3m 09s | Hits:  94%/152   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total:  1h 05m | Avg:  2m 51s | Max:  6m 39s | Hits:  94%/868   
      🟩 12.5               Pass: 100%/32  | Total:  1h 31m | Avg:  2m 51s | Max:  6m 51s | Hits:  95%/1210  
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 05m | Avg:  2m 51s | Max:  6m 39s | Hits:  94%/868   
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 31m | Avg:  2m 51s | Max:  6m 51s | Hits:  95%/1210  
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  6m 51s | Hits:  94%/2078  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  5m 06s | Avg:  2m 33s | Max:  2m 41s | Hits:  97%/76    
      🟩 Clang10            Pass: 100%/2   | Total:  5m 45s | Avg:  2m 52s | Max:  3m 27s | Hits:  97%/76    
      🟩 Clang11            Pass: 100%/4   | Total: 10m 09s | Avg:  2m 32s | Max:  2m 51s | Hits:  97%/152   
      🟩 Clang12            Pass: 100%/4   | Total: 10m 16s | Avg:  2m 34s | Max:  2m 44s | Hits:  97%/152   
      🟩 Clang13            Pass: 100%/4   | Total:  9m 47s | Avg:  2m 26s | Max:  2m 38s | Hits:  97%/152   
      🟩 Clang14            Pass: 100%/6   | Total: 17m 33s | Avg:  2m 55s | Max:  4m 35s | Hits:  98%/228   
      🟩 Clang15            Pass: 100%/2   | Total:  4m 38s | Avg:  2m 19s | Max:  2m 20s | Hits:  97%/76    
      🟩 Clang16            Pass: 100%/6   | Total: 19m 58s | Avg:  3m 19s | Max:  5m 19s | Hits:  98%/228   
      🟩 GCC9               Pass: 100%/2   | Total:  4m 19s | Avg:  2m 09s | Max:  2m 18s | Hits:  92%/76    
      🟩 GCC10              Pass: 100%/4   | Total: 10m 22s | Avg:  2m 35s | Max:  2m 46s | Hits:  92%/152   
      🟩 GCC11              Pass: 100%/4   | Total:  9m 33s | Avg:  2m 23s | Max:  2m 30s | Hits:  92%/152   
      🟩 GCC12              Pass: 100%/12  | Total: 33m 39s | Avg:  2m 48s | Max:  3m 45s | Hits:  92%/456   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 58s | Avg:  2m 58s | Max:  2m 58s | Hits:  97%/38    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  6m 39s | Avg:  6m 39s | Max:  6m 39s | Hits:  71%/32    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 51s | Avg:  6m 51s | Max:  6m 51s | Hits:  71%/32    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 23m | Avg:  2m 46s | Max:  5m 19s | Hits:  97%/1140  
      🟩 GCC                Pass: 100%/22  | Total: 57m 53s | Avg:  2m 37s | Max:  3m 45s | Hits:  92%/836   
      🟩 Intel              Pass: 100%/1   | Total:  2m 58s | Avg:  2m 58s | Max:  2m 58s | Hits:  97%/38    
      🟩 MSVC               Pass: 100%/2   | Total: 13m 30s | Avg:  6m 45s | Max:  6m 51s | Hits:  71%/64    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  6m 51s | Hits:  94%/2078  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 05m | Avg:  2m 40s | Max:  6m 51s | Hits:  94%/1774  
      🟩 Test               Pass: 100%/8   | Total: 32m 03s | Avg:  4m 00s | Max:  5m 19s | Hits:  97%/304   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 04s | Avg:  2m 04s | Max:  2m 04s | Hits:  92%/38    
      🟩 90a                Pass: 100%/1   | Total:  1m 57s | Avg:  1m 57s | Max:  1m 57s | Hits:  92%/38    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 23m | Avg:  2m 42s | Max:  5m 19s | Hits:  95%/1178  
      🟩 20                 Pass: 100%/24  | Total:  1h 13m | Avg:  3m 04s | Max:  6m 51s | Hits:  94%/900   
    
  • 🟩 cccl: Pass: 100%/4 | Total: 17m 57s | Avg: 4m 29s | Max: 5m 13s

    🟩 cpu
      🟩 amd64              Pass: 100%/4   | Total: 17m 57s | Avg:  4m 29s | Max:  5m 13s
    🟩 ctk
      🟩 11.1               Pass: 100%/2   | Total:  8m 09s | Avg:  4m 04s | Max:  4m 36s
      🟩 12.5               Pass: 100%/2   | Total:  9m 48s | Avg:  4m 54s | Max:  5m 13s
    🟩 cudacxx
      🟩 nvcc11.1           Pass: 100%/2   | Total:  8m 09s | Avg:  4m 04s | Max:  4m 36s
      🟩 nvcc12.5           Pass: 100%/2   | Total:  9m 48s | Avg:  4m 54s | Max:  5m 13s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/4   | Total: 17m 57s | Avg:  4m 29s | Max:  5m 13s
    🟩 cxx
      🟩 Clang9             Pass: 100%/1   | Total:  4m 36s | Avg:  4m 36s | Max:  4m 36s
      🟩 Clang17            Pass: 100%/1   | Total:  4m 35s | Avg:  4m 35s | Max:  4m 35s
      🟩 GCC6               Pass: 100%/1   | Total:  3m 33s | Avg:  3m 33s | Max:  3m 33s
      🟩 GCC13              Pass: 100%/1   | Total:  5m 13s | Avg:  5m 13s | Max:  5m 13s
    🟩 cxx_family
      🟩 Clang              Pass: 100%/2   | Total:  9m 11s | Avg:  4m 35s | Max:  4m 36s
      🟩 GCC                Pass: 100%/2   | Total:  8m 46s | Avg:  4m 23s | Max:  5m 13s
    🟩 gpu
      🟩 v100               Pass: 100%/4   | Total: 17m 57s | Avg:  4m 29s | Max:  5m 13s
    🟩 jobs
      🟩 Infra              Pass: 100%/4   | Total: 17m 57s | Avg:  4m 29s | Max:  5m 13s
    
  • 🟩 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: 421)

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

@miscco miscco marked this pull request as ready for review July 29, 2024 13:11
@miscco miscco requested review from a team as code owners July 29, 2024 13:11
@miscco miscco requested a review from alliepiper July 29, 2024 13:11
@miscco miscco enabled auto-merge (squash) July 29, 2024 13:11
Copy link
Contributor

🟨 CI finished in 11h 43m: Pass: 99%/417 | Total: 2d 00h | Avg: 6m 55s | Max: 48m 40s | Hits: 95%/523630
  • 🟨 cub: Pass: 98%/131 | Total: 19h 48m | Avg: 9m 04s | Max: 48m 40s | Hits: 99%/109390

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  98%/123 | Total: 19h 09m | Avg:  9m 20s | Max: 48m 40s | Hits:  99%/102454
      🟩 arm64              Pass: 100%/8   | Total: 38m 07s | Avg:  4m 45s | Max:  5m 16s | Hits:  99%/6936  
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 44m | Avg:  6m 58s | Max: 43m 12s | Hits:  97%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 13m 16s | Avg:  4m 25s | Max:  4m 39s | Hits:  99%/2601  
      🔍 12.5               Pass:  98%/113 | Total: 17h 50m | Avg:  9m 28s | Max: 48m 40s | Hits:  99%/94997 
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 44m | Avg:  6m 58s | Max: 43m 12s | Hits:  97%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 16s | Avg:  4m 25s | Max:  4m 39s | Hits:  99%/2601  
      🔍 nvcc12.5           Pass:  98%/111 | Total: 17h 42m | Avg:  9m 34s | Max: 48m 40s | Hits:  99%/93561 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 21s | Avg:  3m 40s | Max:  3m 45s | Hits: 100%/1436  
      🔍 nvcc               Pass:  98%/129 | Total: 19h 40m | Avg:  9m 09s | Max: 48m 40s | Hits:  99%/107954
    🔍 jobs: DeviceLaunch 🔍
      🟩 Build              Pass: 100%/99  | Total:  8h 33m | Avg:  5m 11s | Max: 43m 12s | Hits:  99%/83380 
      🔍 DeviceLaunch       Pass:  75%/8   | Total:  2h 01m | Avg: 15m 07s | Max: 22m 04s | Hits:  99%/5202  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 10m | Avg: 16m 18s | Max: 18m 55s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 41m | Avg: 20m 13s | Max: 32m 25s | Hits:  99%/6936  
      🟩 TestGPU            Pass: 100%/8   | Total:  4h 21m | Avg: 32m 42s | Max: 48m 40s | Hits:  99%/6936  
    🔍 std: 20 🔍
      🟩 11                 Pass: 100%/34  | Total:  4h 32m | Avg:  8m 00s | Max: 29m 26s | Hits:  99%/29047 
      🟩 14                 Pass: 100%/37  | Total:  5h 53m | Avg:  9m 33s | Max: 43m 12s | Hits:  98%/31174 
      🟩 17                 Pass: 100%/36  | Total:  5h 42m | Avg:  9m 30s | Max: 48m 40s | Hits:  99%/30392 
      🔍 20                 Pass:  91%/24  | Total:  3h 39m | Avg:  9m 09s | Max: 38m 15s | Hits:  99%/18777 
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 26m 27s | Avg:  4m 24s | Max:  5m 15s | Hits: 100%/4980  
      🟩 Clang10            Pass: 100%/3   | Total: 16m 04s | Avg:  5m 21s | Max:  5m 47s | Hits: 100%/2607  
      🟩 Clang11            Pass: 100%/4   | Total: 17m 26s | Avg:  4m 21s | Max:  4m 25s | Hits: 100%/3476  
      🟩 Clang12            Pass: 100%/4   | Total: 17m 20s | Avg:  4m 20s | Max:  4m 41s | Hits: 100%/3476  
      🟩 Clang13            Pass: 100%/4   | Total: 17m 43s | Avg:  4m 25s | Max:  4m 37s | Hits: 100%/3476  
      🟩 Clang14            Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 31s | Hits: 100%/3476  
      🟩 Clang15            Pass: 100%/4   | Total: 18m 03s | Avg:  4m 30s | Max:  4m 47s | Hits: 100%/3468  
      🟩 Clang16            Pass: 100%/4   | Total: 18m 06s | Avg:  4m 31s | Max:  4m 38s | Hits: 100%/3468  
      🟨 Clang17            Pass:  96%/26  | Total:  6h 23m | Avg: 14m 44s | Max: 38m 15s | Hits: 100%/21377 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 26s | Avg:  3m 43s | Max:  3m 58s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 03m | Avg: 10m 30s | Max: 43m 12s | Hits:  93%/4983  
      🟩 GCC8               Pass: 100%/6   | Total: 23m 52s | Avg:  3m 58s | Max:  4m 21s | Hits:  99%/4983  
      🟩 GCC9               Pass: 100%/6   | Total: 24m 07s | Avg:  4m 01s | Max:  4m 30s | Hits:  99%/4983  
      🟩 GCC10              Pass: 100%/4   | Total: 17m 59s | Avg:  4m 29s | Max:  4m 40s | Hits:  99%/3476  
      🟩 GCC11              Pass: 100%/7   | Total: 31m 53s | Avg:  4m 33s | Max:  4m 51s | Hits:  99%/6069  
      🟩 GCC12              Pass: 100%/4   | Total: 18m 44s | Avg:  4m 41s | Max:  5m 06s | Hits:  99%/3468  
      🟨 GCC13              Pass:  96%/28  | Total:  6h 27m | Avg: 13m 51s | Max: 48m 40s | Hits:  99%/23409 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 11s | Hits: 100%/2379  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 21s | Avg: 13m 21s | Max: 13m 21s | Hits:  99%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 20m 23s | Avg: 10m 11s | Max: 10m 12s | Hits:  99%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 32m 04s | Avg: 10m 41s | Max: 11m 22s | Hits:  99%/2127  
    🟨 cxx_family
      🟨 Clang              Pass:  98%/59  | Total:  8h 51m | Avg:  9m 00s | Max: 38m 15s | Hits: 100%/49804 
      🟨 GCC                Pass:  98%/63  | Total:  9h 34m | Avg:  9m 07s | Max: 48m 40s | Hits:  98%/52953 
      🟩 Intel              Pass: 100%/3   | Total: 15m 19s | Avg:  5m 06s | Max:  5m 11s | Hits: 100%/2379  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 05m | Avg: 10m 58s | Max: 13m 21s | Hits:  99%/4254  
    🟨 gpu
      🟨 v100               Pass:  98%/131 | Total: 19h 48m | Avg:  9m 04s | Max: 48m 40s | Hits:  99%/109390
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 16s | Avg:  4m 25s | Max:  4m 39s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total: 14m 02s | Avg:  3m 30s | Max:  3m 35s | Hits:  99%/3468  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 11h 18m | Avg: 5m 45s | Max: 27m 48s | Hits: 99%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 10h 46m | Avg:  5m 52s | Max: 27m 48s | Hits:  99%/129492
      🟩 arm64              Pass: 100%/8   | Total: 32m 28s | Avg:  4m 03s | Max:  4m 31s | Hits:  99%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total: 56m 33s | Avg:  3m 46s | Max: 13m 01s | Hits:  99%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 11m 21s | Avg:  3m 47s | Max:  3m 52s | Hits:  99%/3534  
      🟩 12.5               Pass: 100%/100 | Total: 10h 10m | Avg:  6m 06s | Max: 27m 48s | Hits:  99%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 23s | Avg:  3m 41s | Max:  3m 43s | Hits: 100%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total: 56m 33s | Avg:  3m 46s | Max: 13m 01s | Hits:  99%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 11m 21s | Avg:  3m 47s | Max:  3m 52s | Hits:  99%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total: 10h 03m | Avg:  6m 09s | Max: 27m 48s | Hits:  99%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 23s | Avg:  3m 41s | Max:  3m 43s | Hits: 100%/2354  
      🟩 nvcc               Pass: 100%/116 | Total: 11h 11m | Avg:  5m 47s | Max: 27m 48s | Hits:  99%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 22m 54s | Avg:  3m 49s | Max:  4m 41s | Hits: 100%/7062  
      🟩 Clang10            Pass: 100%/3   | Total: 12m 34s | Avg:  4m 11s | Max:  4m 36s | Hits: 100%/3531  
      🟩 Clang11            Pass: 100%/4   | Total: 14m 48s | Avg:  3m 42s | Max:  4m 03s | Hits: 100%/4708  
      🟩 Clang12            Pass: 100%/4   | Total: 14m 41s | Avg:  3m 40s | Max:  3m 50s | Hits: 100%/4708  
      🟩 Clang13            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  3m 54s | Hits: 100%/4708  
      🟩 Clang14            Pass: 100%/4   | Total: 14m 46s | Avg:  3m 41s | Max:  4m 01s | Hits: 100%/4708  
      🟩 Clang15            Pass: 100%/4   | Total: 15m 14s | Avg:  3m 48s | Max:  4m 00s | Hits: 100%/4708  
      🟩 Clang16            Pass: 100%/4   | Total: 15m 15s | Avg:  3m 48s | Max:  3m 58s | Hits: 100%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  2h 23m | Avg:  7m 59s | Max: 27m 48s | Hits: 100%/21186 
      🟩 GCC6               Pass: 100%/2   | Total:  6m 24s | Avg:  3m 12s | Max:  3m 13s | Hits:  99%/2354  
      🟩 GCC7               Pass: 100%/6   | Total: 19m 26s | Avg:  3m 14s | Max:  3m 39s | Hits:  99%/7068  
      🟩 GCC8               Pass: 100%/6   | Total: 19m 57s | Avg:  3m 19s | Max:  4m 00s | Hits:  99%/7068  
      🟩 GCC9               Pass: 100%/6   | Total: 20m 04s | Avg:  3m 20s | Max:  3m 44s | Hits:  99%/7068  
      🟩 GCC10              Pass: 100%/4   | Total: 15m 05s | Avg:  3m 46s | Max:  3m 50s | Hits:  99%/4712  
      🟩 GCC11              Pass: 100%/7   | Total: 26m 17s | Avg:  3m 45s | Max:  3m 55s | Hits:  99%/8246  
      🟩 GCC12              Pass: 100%/4   | Total: 15m 40s | Avg:  3m 55s | Max:  4m 06s | Hits:  99%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  2h 28m | Avg:  7m 24s | Max: 24m 38s | Hits:  99%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 14m 01s | Avg:  4m 40s | Max:  4m 42s | Hits: 100%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 13m 01s | Avg: 13m 01s | Max: 13m 01s | Hits:  98%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 22m 42s | Avg: 11m 21s | Max: 11m 24s | Hits:  98%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 28m | Avg: 14m 45s | Max: 17m 52s | Hits:  98%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total:  4h 29m | Avg:  5m 17s | Max: 27m 48s | Hits: 100%/60027 
      🟩 GCC                Pass: 100%/55  | Total:  4h 31m | Avg:  4m 55s | Max: 24m 38s | Hits:  99%/64788 
      🟩 Intel              Pass: 100%/3   | Total: 14m 01s | Avg:  4m 40s | Max:  4m 42s | Hits: 100%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  2h 04m | Avg: 13m 48s | Max: 17m 52s | Hits:  98%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 11h 18m | Avg:  5m 45s | Max: 27m 48s | Hits:  99%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  6h 59m | Avg:  4m 14s | Max: 13m 01s | Hits:  99%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 42m | Avg:  9m 21s | Max: 17m 52s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 36m | Avg: 19m 32s | Max: 27m 48s | Hits:  99%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 11m 21s | Avg:  3m 47s | Max:  3m 52s | Hits:  99%/3534  
      🟩 90a                Pass: 100%/4   | Total: 14m 09s | Avg:  3m 32s | Max:  4m 03s | Hits:  99%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  2h 10m | Avg:  4m 20s | Max: 14m 28s | Hits:  99%/35328 
      🟩 14                 Pass: 100%/34  | Total:  3h 34m | Avg:  6m 18s | Max: 27m 48s | Hits:  99%/40020 
      🟩 17                 Pass: 100%/33  | Total:  3h 26m | Avg:  6m 14s | Max: 26m 14s | Hits:  99%/38847 
      🟩 20                 Pass: 100%/21  | Total:  2h 08m | Avg:  6m 06s | Max: 17m 50s | Hits:  99%/24717 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 14h 28m | Avg: 7m 45s | Max: 37m 54s | Hits: 91%/273250

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 13h 43m | Avg:  7m 55s | Max: 37m 54s | Hits:  91%/250904
      🟩 arm64              Pass: 100%/8   | Total: 44m 49s | Avg:  5m 36s | Max: 17m 58s | Hits:  91%/22346 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 20m | Avg:  5m 21s | Max: 17m 00s | Hits:  90%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 23m 44s | Avg:  7m 54s | Max: 17m 59s | Hits:  79%/8064  
      🟩 12.5               Pass: 100%/94  | Total: 12h 44m | Avg:  8m 08s | Max: 37m 54s | Hits:  92%/225406
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 35m 38s | Avg: 17m 49s | Max: 18m 00s | Hits:  37%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 20m | Avg:  5m 21s | Max: 17m 00s | Hits:  90%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 23m 44s | Avg:  7m 54s | Max: 17m 59s | Hits:  79%/8064  
      🟩 nvcc12.5           Pass: 100%/92  | Total: 12h 08m | Avg:  7m 55s | Max: 37m 54s | Hits:  94%/219307
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 35m 38s | Avg: 17m 49s | Max: 18m 00s | Hits:  37%/6099  
      🟩 nvcc               Pass: 100%/110 | Total: 13h 52m | Avg:  7m 34s | Max: 37m 54s | Hits:  93%/267151
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 37m 58s | Avg:  6m 19s | Max: 16m 08s | Hits:  88%/16160 
      🟩 Clang10            Pass: 100%/3   | Total: 28m 59s | Avg:  9m 39s | Max: 19m 01s | Hits:  79%/8109  
      🟩 Clang11            Pass: 100%/4   | Total: 30m 30s | Avg:  7m 37s | Max: 19m 27s | Hits:  83%/11181 
      🟩 Clang12            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  4m 14s | Hits:  98%/11181 
      🟩 Clang13            Pass: 100%/4   | Total: 16m 38s | Avg:  4m 09s | Max:  4m 49s | Hits:  98%/11181 
      🟩 Clang14            Pass: 100%/4   | Total: 31m 39s | Avg:  7m 54s | Max: 19m 08s | Hits:  82%/11181 
      🟩 Clang15            Pass: 100%/4   | Total: 15m 39s | Avg:  3m 54s | Max:  4m 12s | Hits:  99%/11173 
      🟩 Clang16            Pass: 100%/4   | Total: 16m 34s | Avg:  4m 08s | Max:  4m 59s | Hits:  98%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  2h 48m | Avg: 12m 03s | Max: 37m 54s | Hits:  86%/28445 
      🟩 GCC6               Pass: 100%/2   | Total:  4m 49s | Avg:  2m 24s | Max:  2m 30s | Hits:  99%/5045  
      🟩 GCC7               Pass: 100%/6   | Total: 18m 22s | Avg:  3m 03s | Max:  3m 31s | Hits:  98%/16146 
      🟩 GCC8               Pass: 100%/6   | Total: 29m 44s | Avg:  4m 57s | Max: 14m 28s | Hits:  88%/16154 
      🟩 GCC9               Pass: 100%/6   | Total: 34m 45s | Avg:  5m 47s | Max: 19m 17s | Hits:  93%/16158 
      🟩 GCC10              Pass: 100%/4   | Total: 15m 50s | Avg:  3m 57s | Max:  4m 24s | Hits:  96%/11181 
      🟩 GCC11              Pass: 100%/7   | Total: 53m 18s | Avg:  7m 36s | Max: 20m 03s | Hits:  81%/19237 
      🟩 GCC12              Pass: 100%/4   | Total: 15m 38s | Avg:  3m 54s | Max:  4m 25s | Hits:  98%/11173 
      🟩 GCC13              Pass: 100%/21  | Total:  4h 02m | Avg: 11m 31s | Max: 37m 11s | Hits:  91%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 14m 30s | Avg:  4m 50s | Max:  5m 20s | Hits:  99%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 17m 00s | Avg: 17m 00s | Max: 17m 00s | Hits:  99%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 23m 47s | Avg: 11m 53s | Max: 12m 04s | Hits:  98%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 36m 40s | Avg: 12m 13s | Max: 12m 35s | Hits:  99%/8401  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/47  | Total:  6h 02m | Avg:  7m 42s | Max: 37m 54s | Hits:  90%/119784
      🟩 GCC                Pass: 100%/56  | Total:  6h 54m | Avg:  7m 24s | Max: 37m 11s | Hits:  92%/128996
      🟩 Intel              Pass: 100%/3   | Total: 14m 30s | Avg:  4m 50s | Max:  5m 20s | Hits:  99%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  1h 17m | Avg: 12m 54s | Max: 17m 00s | Hits:  99%/16371 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 14h 28m | Avg:  7m 45s | Max: 37m 54s | Hits:  91%/273250
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  9h 48m | Avg:  5m 56s | Max: 20m 03s | Hits:  91%/273230
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 36m | Avg: 24m 13s | Max: 37m 11s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  3h 01m | Avg: 22m 39s | Max: 37m 54s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 00s | Avg:  2m 00s | Max:  2m 00s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 23m 44s | Avg:  7m 54s | Max: 17m 59s | Hits:  79%/8064  
      🟩 90a                Pass: 100%/4   | Total: 14m 09s | Avg:  3m 32s | Max:  4m 01s | Hits:  99%/11536 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  2h 27m | Avg:  5m 04s | Max: 19m 38s | Hits:  97%/58200 
      🟩 14                 Pass: 100%/32  | Total:  4h 09m | Avg:  7m 47s | Max: 37m 11s | Hits:  95%/81788 
      🟩 17                 Pass: 100%/31  | Total:  4h 35m | Avg:  8m 52s | Max: 37m 54s | Hits:  87%/84134 
      🟩 20                 Pass: 100%/19  | Total:  3h 14m | Avg: 10m 15s | Max: 36m 47s | Hits:  87%/49128 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 18m | Avg: 2m 31s | Max: 7m 46s | Hits: 97%/2078

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 09m | Avg:  2m 32s | Max:  7m 46s | Hits:  97%/1926  
      🟩 arm64              Pass: 100%/4   | Total:  9m 00s | Avg:  2m 15s | Max:  2m 29s | Hits:  97%/152   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total: 59m 12s | Avg:  2m 34s | Max:  7m 46s | Hits:  96%/868   
      🟩 12.5               Pass: 100%/32  | Total:  1h 19m | Avg:  2m 28s | Max:  6m 53s | Hits:  97%/1210  
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total: 59m 12s | Avg:  2m 34s | Max:  7m 46s | Hits:  96%/868   
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 19m | Avg:  2m 28s | Max:  6m 53s | Hits:  97%/1210  
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 18m | Avg:  2m 31s | Max:  7m 46s | Hits:  97%/2078  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 19s | Avg:  2m 09s | Max:  2m 20s | Hits: 100%/76    
      🟩 Clang10            Pass: 100%/2   | Total:  4m 13s | Avg:  2m 06s | Max:  2m 11s | Hits: 100%/76    
      🟩 Clang11            Pass: 100%/4   | Total:  8m 11s | Avg:  2m 02s | Max:  2m 05s | Hits: 100%/152   
      🟩 Clang12            Pass: 100%/4   | Total:  8m 12s | Avg:  2m 03s | Max:  2m 20s | Hits: 100%/152   
      🟩 Clang13            Pass: 100%/4   | Total:  8m 19s | Avg:  2m 04s | Max:  2m 12s | Hits: 100%/152   
      🟩 Clang14            Pass: 100%/6   | Total: 16m 04s | Avg:  2m 40s | Max:  4m 08s | Hits: 100%/228   
      🟩 Clang15            Pass: 100%/2   | Total:  4m 09s | Avg:  2m 04s | Max:  2m 09s | Hits: 100%/76    
      🟩 Clang16            Pass: 100%/6   | Total: 16m 55s | Avg:  2m 49s | Max:  4m 14s | Hits: 100%/228   
      🟩 GCC9               Pass: 100%/2   | Total:  3m 46s | Avg:  1m 53s | Max:  1m 54s | Hits:  94%/76    
      🟩 GCC10              Pass: 100%/4   | Total:  8m 13s | Avg:  2m 03s | Max:  2m 29s | Hits:  94%/152   
      🟩 GCC11              Pass: 100%/4   | Total:  7m 35s | Avg:  1m 53s | Max:  2m 01s | Hits:  94%/152   
      🟩 GCC12              Pass: 100%/12  | Total: 31m 18s | Avg:  2m 36s | Max:  4m 07s | Hits:  94%/456   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 32s | Avg:  2m 32s | Max:  2m 32s | Hits: 100%/38    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 46s | Avg:  7m 46s | Max:  7m 46s | Hits:  75%/32    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 53s | Avg:  6m 53s | Max:  6m 53s | Hits:  75%/32    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 10m | Avg:  2m 20s | Max:  4m 14s | Hits: 100%/1140  
      🟩 GCC                Pass: 100%/22  | Total: 50m 52s | Avg:  2m 18s | Max:  4m 07s | Hits:  94%/836   
      🟩 Intel              Pass: 100%/1   | Total:  2m 32s | Avg:  2m 32s | Max:  2m 32s | Hits: 100%/38    
      🟩 MSVC               Pass: 100%/2   | Total: 14m 39s | Avg:  7m 19s | Max:  7m 46s | Hits:  75%/64    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 18m | Avg:  2m 31s | Max:  7m 46s | Hits:  97%/2078  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  1h 47m | Avg:  2m 17s | Max:  7m 46s | Hits:  97%/1774  
      🟩 Test               Pass: 100%/8   | Total: 30m 50s | Avg:  3m 51s | Max:  4m 14s | Hits:  97%/304   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  1m 58s | Avg:  1m 58s | Max:  1m 58s | Hits:  94%/38    
      🟩 90a                Pass: 100%/1   | Total:  1m 42s | Avg:  1m 42s | Max:  1m 42s | Hits:  94%/38    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 10m | Avg:  2m 17s | Max:  4m 14s | Hits:  97%/1178  
      🟩 20                 Pass: 100%/24  | Total:  1h 07m | Avg:  2m 48s | Max:  7m 46s | Hits:  96%/900   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 11m 41s | Avg: 11m 41s | Max: 11m 41s
    

👃 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
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.

Really looking forward to having this utility!
Just two minor, non-blocking, optional comments related to docs.

Copy link
Contributor

🟨 CI finished in 8h 16m: Pass: 99%/417 | Total: 4d 01h | Avg: 13m 58s | Max: 1h 47m | Hits: 75%/523960
  • 🟨 cub: Pass: 98%/131 | Total: 1d 19h | Avg: 19m 54s | Max: 1h 47m | Hits: 87%/109390

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  98%/123 | Total:  1d 17h | Avg: 20m 06s | Max:  1h 47m | Hits:  86%/102454
      🟩 arm64              Pass: 100%/8   | Total:  2h 15m | Avg: 16m 57s | Max: 54m 35s | Hits:  88%/6936  
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 45m | Avg:  7m 03s | Max: 55m 23s | Hits:  93%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 14m 19s | Avg:  4m 46s | Max:  5m 01s | Hits:  99%/2601  
      🔍 12.5               Pass:  98%/113 | Total:  1d 17h | Avg: 22m 01s | Max:  1h 47m | Hits:  85%/94997 
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 39s | Hits: 100%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 45m | Avg:  7m 03s | Max: 55m 23s | Hits:  93%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 19s | Avg:  4m 46s | Max:  5m 01s | Hits:  99%/2601  
      🔍 nvcc12.5           Pass:  98%/111 | Total:  1d 17h | Avg: 22m 21s | Max:  1h 47m | Hits:  85%/93561 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 39s | Hits: 100%/1436  
      🔍 nvcc               Pass:  98%/129 | Total:  1d 19h | Avg: 20m 10s | Max:  1h 47m | Hits:  86%/107954
    🔍 cxx: GCC13 🔍
      🟩 Clang9             Pass: 100%/6   | Total:  1h 10m | Avg: 11m 48s | Max: 49m 31s | Hits:  93%/4980  
      🟩 Clang10            Pass: 100%/3   | Total: 59m 46s | Avg: 19m 55s | Max: 49m 03s | Hits:  87%/2607  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 02m | Avg: 15m 38s | Max: 48m 58s | Hits:  90%/3476  
      🟩 Clang12            Pass: 100%/4   | Total:  1h 07m | Avg: 16m 51s | Max: 53m 27s | Hits:  90%/3476  
      🟩 Clang13            Pass: 100%/4   | Total:  1h 03m | Avg: 15m 54s | Max: 50m 05s | Hits:  90%/3476  
      🟩 Clang14            Pass: 100%/4   | Total:  1h 05m | Avg: 16m 25s | Max: 51m 32s | Hits:  90%/3476  
      🟩 Clang15            Pass: 100%/4   | Total:  1h 05m | Avg: 16m 15s | Max: 51m 37s | Hits:  90%/3468  
      🟩 Clang16            Pass: 100%/4   | Total:  1h 05m | Avg: 16m 17s | Max: 51m 41s | Hits:  90%/3468  
      🟩 Clang17            Pass: 100%/26  | Total:  8h 05m | Avg: 18m 41s | Max: 52m 30s | Hits:  96%/22244 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 37s | Avg:  3m 48s | Max:  4m 00s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 57m | Avg: 19m 31s | Max: 52m 31s | Hits:  84%/4983  
      🟩 GCC8               Pass: 100%/6   | Total:  1h 12m | Avg: 12m 09s | Max: 53m 06s | Hits:  92%/4983  
      🟩 GCC9               Pass: 100%/6   | Total:  1h 11m | Avg: 11m 52s | Max: 51m 00s | Hits:  92%/4983  
      🟩 GCC10              Pass: 100%/4   | Total:  1h 03m | Avg: 15m 56s | Max: 50m 14s | Hits:  88%/3476  
      🟩 GCC11              Pass: 100%/7   | Total:  1h 17m | Avg: 11m 08s | Max: 49m 44s | Hits:  92%/6069  
      🟩 GCC12              Pass: 100%/4   | Total:  1h 05m | Avg: 16m 24s | Max: 51m 56s | Hits:  88%/3468  
      🔍 GCC13              Pass:  92%/28  | Total:  9h 53m | Avg: 21m 11s | Max:  1h 47m | Hits:  93%/22542 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 44m | Avg: 54m 45s | Max: 55m 01s | Hits:   4%/2379  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 55m 23s | Avg: 55m 23s | Max: 55m 23s | Hits:   1%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 03m | Avg:  1h 01m | Max:  1h 02m | Hits:   1%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  3h 09m | Avg:  1h 03m | Max:  1h 04m | Hits:   1%/2127  
    🔍 cxx_family: GCC 🔍
      🟩 Clang              Pass: 100%/59  | Total: 16h 45m | Avg: 17m 03s | Max: 53m 27s | Hits:  93%/50671 
      🔍 GCC                Pass:  96%/63  | Total: 17h 49m | Avg: 16m 58s | Max:  1h 47m | Hits:  91%/52086 
      🟩 Intel              Pass: 100%/3   | Total:  2h 44m | Avg: 54m 45s | Max: 55m 01s | Hits:   4%/2379  
      🟩 MSVC               Pass: 100%/6   | Total:  6h 08m | Avg:  1h 01m | Max:  1h 04m | Hits:   1%/4254  
    🔍 std: 14 🔍
      🟩 11                 Pass: 100%/34  | Total: 19h 33m | Avg: 34m 30s | Max: 54m 35s | Hits:  73%/29047 
      🔍 14                 Pass:  94%/37  | Total:  7h 34m | Avg: 12m 17s | Max:  1h 03m | Hits:  90%/29440 
      🟩 17                 Pass: 100%/36  | Total:  9h 23m | Avg: 15m 39s | Max:  1h 02m | Hits:  91%/30392 
      🟩 20                 Pass: 100%/24  | Total:  6h 57m | Avg: 17m 22s | Max:  1h 47m | Hits:  94%/20511 
    🟨 jobs
      🟩 Build              Pass: 100%/99  | Total:  1d 06h | Avg: 18m 30s | Max:  1h 04m | Hits:  83%/83380 
      🟨 DeviceLaunch       Pass:  87%/8   | Total:  3h 57m | Avg: 29m 41s | Max:  1h 47m | Hits:  94%/6069  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 43m | Avg: 20m 28s | Max: 40m 16s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 45m | Avg: 20m 39s | Max: 29m 49s | Hits:  99%/6936  
      🟨 TestGPU            Pass:  87%/8   | Total:  3h 30m | Avg: 26m 18s | Max: 50m 33s | Hits:  99%/6069  
    🟨 gpu
      🟨 v100               Pass:  98%/131 | Total:  1d 19h | Avg: 19m 54s | Max:  1h 47m | Hits:  87%/109390
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 19s | Avg:  4m 46s | Max:  5m 01s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total: 32m 57s | Avg:  8m 14s | Max: 21m 24s | Hits:  88%/3468  
    
  • 🟩 thrust: Pass: 100%/118 | Total: 1d 05h | Avg: 15m 03s | Max: 1h 07m | Hits: 55%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total:  1d 03h | Avg: 15m 14s | Max:  1h 07m | Hits:  56%/129492
      🟩 arm64              Pass: 100%/8   | Total:  1h 40m | Avg: 12m 30s | Max: 25m 52s | Hits:  47%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 35m | Avg: 10m 23s | Max: 53m 05s | Hits:  51%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 22m 33s | Avg:  7m 31s | Max:  7m 48s | Hits:  55%/3534  
      🟩 12.5               Pass: 100%/100 | Total:  1d 02h | Avg: 15m 59s | Max:  1h 07m | Hits:  56%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 16m 25s | Avg:  8m 12s | Max:  8m 21s | Hits:  57%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 35m | Avg: 10m 23s | Max: 53m 05s | Hits:  51%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 22m 33s | Avg:  7m 31s | Max:  7m 48s | Hits:  55%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total:  1d 02h | Avg: 16m 08s | Max:  1h 07m | Hits:  56%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 16m 25s | Avg:  8m 12s | Max:  8m 21s | Hits:  57%/2354  
      🟩 nvcc               Pass: 100%/116 | Total:  1d 05h | Avg: 15m 10s | Max:  1h 07m | Hits:  55%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 05m | Avg: 10m 58s | Max: 27m 15s | Hits:  49%/7062  
      🟩 Clang10            Pass: 100%/3   | Total: 43m 12s | Avg: 14m 24s | Max: 26m 53s | Hits:  44%/3531  
      🟩 Clang11            Pass: 100%/4   | Total: 53m 47s | Avg: 13m 26s | Max: 28m 46s | Hits:  47%/4708  
      🟩 Clang12            Pass: 100%/4   | Total: 51m 56s | Avg: 12m 59s | Max: 27m 17s | Hits:  47%/4708  
      🟩 Clang13            Pass: 100%/4   | Total: 51m 12s | Avg: 12m 48s | Max: 26m 48s | Hits:  47%/4708  
      🟩 Clang14            Pass: 100%/4   | Total: 56m 26s | Avg: 14m 06s | Max: 30m 46s | Hits:  47%/4708  
      🟩 Clang15            Pass: 100%/4   | Total: 52m 29s | Avg: 13m 07s | Max: 27m 35s | Hits:  47%/4708  
      🟩 Clang16            Pass: 100%/4   | Total: 54m 27s | Avg: 13m 36s | Max: 28m 36s | Hits:  47%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  3h 17m | Avg: 10m 58s | Max: 26m 56s | Hits:  72%/21186 
      🟩 GCC6               Pass: 100%/2   | Total: 15m 06s | Avg:  7m 33s | Max:  7m 57s | Hits:  54%/2354  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 23m | Avg: 13m 55s | Max: 30m 12s | Hits:  43%/7068  
      🟩 GCC8               Pass: 100%/6   | Total:  1h 02m | Avg: 10m 25s | Max: 26m 02s | Hits:  49%/7068  
      🟩 GCC9               Pass: 100%/6   | Total:  1h 09m | Avg: 11m 33s | Max: 29m 53s | Hits:  49%/7068  
      🟩 GCC10              Pass: 100%/4   | Total: 50m 04s | Avg: 12m 31s | Max: 26m 22s | Hits:  47%/4712  
      🟩 GCC11              Pass: 100%/7   | Total:  1h 00m | Avg:  8m 41s | Max: 22m 42s | Hits:  69%/8246  
      🟩 GCC12              Pass: 100%/4   | Total: 58m 08s | Avg: 14m 32s | Max: 31m 54s | Hits:  47%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  3h 35m | Avg: 10m 45s | Max: 25m 52s | Hits:  77%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 03m | Avg: 41m 13s | Max: 44m 00s | Hits:   4%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 53m 05s | Avg: 53m 05s | Max: 53m 05s | Hits:   2%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 58m | Avg: 59m 03s | Max:  1h 01m | Hits:   2%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  4h 01m | Avg: 40m 10s | Max:  1h 07m | Hits:  50%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total: 10h 26m | Avg: 12m 17s | Max: 30m 46s | Hits:  56%/60027 
      🟩 GCC                Pass: 100%/55  | Total: 10h 14m | Avg: 11m 10s | Max: 31m 54s | Hits:  61%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  2h 03m | Avg: 41m 13s | Max: 44m 00s | Hits:   4%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 52m | Avg: 45m 48s | Max:  1h 07m | Hits:  34%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total:  1d 05h | Avg: 15m 03s | Max:  1h 07m | Hits:  55%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  1d 01h | Avg: 15m 43s | Max:  1h 07m | Hits:  47%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 45m | Avg:  9m 34s | Max: 19m 20s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  1h 55m | Avg: 14m 26s | Max: 22m 05s | Hits:  99%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 22m 33s | Avg:  7m 31s | Max:  7m 48s | Hits:  55%/3534  
      🟩 90a                Pass: 100%/4   | Total: 41m 14s | Avg: 10m 18s | Max: 18m 15s | Hits:  47%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total: 10h 21m | Avg: 20m 42s | Max: 35m 59s | Hits:  38%/35328 
      🟩 14                 Pass: 100%/34  | Total:  8h 02m | Avg: 14m 11s | Max: 56m 24s | Hits:  58%/40020 
      🟩 17                 Pass: 100%/33  | Total:  7h 06m | Avg: 12m 55s | Max:  1h 02m | Hits:  61%/38847 
      🟩 20                 Pass: 100%/21  | Total:  4h 07m | Avg: 11m 46s | Max:  1h 07m | Hits:  67%/24717 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 21h 00m | Avg: 11m 15s | Max: 41m 25s | Hits: 81%/273250

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total: 20h 05m | Avg: 11m 35s | Max: 41m 25s | Hits:  81%/250904
      🟩 arm64              Pass: 100%/8   | Total: 55m 40s | Avg:  6m 57s | Max: 14m 51s | Hits:  92%/22346 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  4h 05m | Avg: 16m 22s | Max: 41m 25s | Hits:  85%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 34m 22s | Avg: 11m 27s | Max: 16m 52s | Hits:  73%/8064  
      🟩 12.5               Pass: 100%/94  | Total: 16h 20m | Avg: 10m 25s | Max: 39m 13s | Hits:  81%/225406
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 34m 41s | Avg: 17m 20s | Max: 17m 45s | Hits:  37%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  4h 05m | Avg: 16m 22s | Max: 41m 25s | Hits:  85%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 34m 22s | Avg: 11m 27s | Max: 16m 52s | Hits:  73%/8064  
      🟩 nvcc12.5           Pass: 100%/92  | Total: 15h 45m | Avg: 10m 16s | Max: 39m 13s | Hits:  82%/219307
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 34m 41s | Avg: 17m 20s | Max: 17m 45s | Hits:  37%/6099  
      🟩 nvcc               Pass: 100%/110 | Total: 20h 26m | Avg: 11m 08s | Max: 41m 25s | Hits:  82%/267151
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 59m 12s | Avg:  9m 52s | Max: 28m 30s | Hits:  91%/16160 
      🟩 Clang10            Pass: 100%/3   | Total: 43m 54s | Avg: 14m 38s | Max: 25m 04s | Hits:  71%/8109  
      🟩 Clang11            Pass: 100%/4   | Total: 25m 35s | Avg:  6m 23s | Max: 11m 51s | Hits:  92%/11181 
      🟩 Clang12            Pass: 100%/4   | Total: 28m 05s | Avg:  7m 01s | Max: 11m 09s | Hits:  90%/11181 
      🟩 Clang13            Pass: 100%/4   | Total: 25m 11s | Avg:  6m 17s | Max: 10m 50s | Hits:  92%/11181 
      🟩 Clang14            Pass: 100%/4   | Total: 24m 52s | Avg:  6m 13s | Max: 11m 02s | Hits:  92%/11181 
      🟩 Clang15            Pass: 100%/4   | Total: 25m 52s | Avg:  6m 28s | Max: 10m 51s | Hits:  92%/11173 
      🟩 Clang16            Pass: 100%/4   | Total: 26m 27s | Avg:  6m 36s | Max: 11m 38s | Hits:  92%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  2h 36m | Avg: 11m 12s | Max: 23m 35s | Hits:  81%/28445 
      🟩 GCC6               Pass: 100%/2   | Total: 41m 26s | Avg: 20m 43s | Max: 38m 25s | Hits:  89%/5045  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 04m | Avg: 10m 43s | Max: 37m 50s | Hits:  91%/16146 
      🟩 GCC8               Pass: 100%/6   | Total:  1h 08m | Avg: 11m 26s | Max: 41m 25s | Hits:  91%/16154 
      🟩 GCC9               Pass: 100%/6   | Total:  1h 06m | Avg: 11m 08s | Max: 38m 53s | Hits:  90%/16158 
      🟩 GCC10              Pass: 100%/4   | Total: 23m 46s | Avg:  5m 56s | Max: 10m 26s | Hits:  92%/11181 
      🟩 GCC11              Pass: 100%/7   | Total: 58m 24s | Avg:  8m 20s | Max: 16m 52s | Hits:  84%/19237 
      🟩 GCC12              Pass: 100%/4   | Total: 27m 05s | Avg:  6m 46s | Max: 12m 52s | Hits:  91%/11173 
      🟩 GCC13              Pass: 100%/21  | Total:  3h 58m | Avg: 11m 21s | Max: 32m 49s | Hits:  93%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 08m | Avg: 22m 46s | Max: 23m 41s | Hits:   4%/8099  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 30m 37s | Avg: 30m 37s | Max: 30m 37s | Hits:   6%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 58m 19s | Avg: 29m 09s | Max: 31m 22s | Hits:   6%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  1h 38m | Avg: 32m 46s | Max: 39m 13s | Hits:   6%/8401  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/47  | Total:  6h 56m | Avg:  8m 51s | Max: 28m 30s | Hits:  88%/119784
      🟩 GCC                Pass: 100%/56  | Total:  9h 49m | Avg: 10m 31s | Max: 41m 25s | Hits:  90%/128996
      🟩 Intel              Pass: 100%/3   | Total:  1h 08m | Avg: 22m 46s | Max: 23m 41s | Hits:   4%/8099  
      🟩 MSVC               Pass: 100%/6   | Total:  3h 07m | Avg: 31m 12s | Max: 39m 13s | Hits:   6%/16371 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total: 21h 00m | Avg: 11m 15s | Max: 41m 25s | Hits:  81%/273250
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 17h 04m | Avg: 10m 20s | Max: 41m 25s | Hits:  81%/273230
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 29m | Avg: 22m 26s | Max: 32m 49s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  2h 24m | Avg: 18m 04s | Max: 24m 33s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 34m 22s | Avg: 11m 27s | Max: 16m 52s | Hits:  73%/8064  
      🟩 90a                Pass: 100%/4   | Total: 18m 03s | Avg:  4m 30s | Max:  6m 04s | Hits:  93%/11536 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total:  8h 12m | Avg: 16m 58s | Max: 41m 25s | Hits:  78%/58200 
      🟩 14                 Pass: 100%/32  | Total:  4h 36m | Avg:  8m 39s | Max: 30m 37s | Hits:  81%/81788 
      🟩 17                 Pass: 100%/31  | Total:  4h 49m | Avg:  9m 19s | Max: 31m 22s | Hits:  82%/84134 
      🟩 20                 Pass: 100%/19  | Total:  3h 20m | Avg: 10m 34s | Max: 39m 13s | Hits:  85%/49128 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 46m | Avg: 3m 01s | Max: 7m 43s | Hits: 64%/2408

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 34m | Avg:  3m 01s | Max:  7m 43s | Hits:  65%/2232  
      🟩 arm64              Pass: 100%/4   | Total: 11m 53s | Avg:  2m 58s | Max:  3m 17s | Hits:  61%/176   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total:  1h 12m | Avg:  3m 09s | Max:  7m 43s | Hits:  65%/1006  
      🟩 12.5               Pass: 100%/32  | Total:  1h 33m | Avg:  2m 55s | Max:  6m 57s | Hits:  64%/1402  
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 12m | Avg:  3m 09s | Max:  7m 43s | Hits:  65%/1006  
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 33m | Avg:  2m 55s | Max:  6m 57s | Hits:  64%/1402  
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 46m | Avg:  3m 01s | Max:  7m 43s | Hits:  64%/2408  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 57s | Avg:  2m 28s | Max:  2m 32s | Hits:  63%/88    
      🟩 Clang10            Pass: 100%/2   | Total:  5m 04s | Avg:  2m 32s | Max:  2m 35s | Hits:  63%/88    
      🟩 Clang11            Pass: 100%/4   | Total: 10m 20s | Avg:  2m 35s | Max:  2m 45s | Hits:  63%/176   
      🟩 Clang12            Pass: 100%/4   | Total:  9m 52s | Avg:  2m 28s | Max:  2m 40s | Hits:  63%/176   
      🟩 Clang13            Pass: 100%/4   | Total: 10m 02s | Avg:  2m 30s | Max:  2m 43s | Hits:  63%/176   
      🟩 Clang14            Pass: 100%/6   | Total: 20m 08s | Avg:  3m 21s | Max:  5m 03s | Hits:  75%/264   
      🟩 Clang15            Pass: 100%/2   | Total:  5m 14s | Avg:  2m 37s | Max:  2m 41s | Hits:  63%/88    
      🟩 Clang16            Pass: 100%/6   | Total: 19m 21s | Avg:  3m 13s | Max:  3m 58s | Hits:  75%/264   
      🟩 GCC9               Pass: 100%/2   | Total:  5m 02s | Avg:  2m 31s | Max:  2m 35s | Hits:  59%/88    
      🟩 GCC10              Pass: 100%/4   | Total: 10m 11s | Avg:  2m 32s | Max:  2m 39s | Hits:  59%/176   
      🟩 GCC11              Pass: 100%/4   | Total:  9m 34s | Avg:  2m 23s | Max:  2m 29s | Hits:  59%/176   
      🟩 GCC12              Pass: 100%/12  | Total: 38m 34s | Avg:  3m 12s | Max:  5m 28s | Hits:  71%/528   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  3m 17s | Avg:  3m 17s | Max:  3m 17s | Hits:  38%/44    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 43s | Avg:  7m 43s | Max:  7m 43s | Hits:   7%/38    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 57s | Avg:  6m 57s | Max:  6m 57s | Hits:   7%/38    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 24m | Avg:  2m 49s | Max:  5m 03s | Hits:  68%/1320  
      🟩 GCC                Pass: 100%/22  | Total:  1h 03m | Avg:  2m 52s | Max:  5m 28s | Hits:  65%/968   
      🟩 Intel              Pass: 100%/1   | Total:  3m 17s | Avg:  3m 17s | Max:  3m 17s | Hits:  38%/44    
      🟩 MSVC               Pass: 100%/2   | Total: 14m 40s | Avg:  7m 20s | Max:  7m 43s | Hits:   7%/76    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 46m | Avg:  3m 01s | Max:  7m 43s | Hits:  64%/2408  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 10m | Avg:  2m 46s | Max:  7m 43s | Hits:  59%/2056  
      🟩 Test               Pass: 100%/8   | Total: 35m 36s | Avg:  4m 27s | Max:  5m 28s | Hits:  97%/352   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 12s | Avg:  2m 12s | Max:  2m 12s | Hits:  59%/44    
      🟩 90a                Pass: 100%/1   | Total:  2m 03s | Avg:  2m 03s | Max:  2m 03s | Hits:  59%/44    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 26m | Avg:  2m 47s | Max:  5m 09s | Hits:  65%/1364  
      🟩 20                 Pass: 100%/24  | Total:  1h 19m | Avg:  3m 19s | Max:  7m 43s | Hits:  63%/1044  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 50s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 11m 50s | Avg: 11m 50s | Max: 11m 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: 417)

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

It serves no purpose as it only ever forwards via ADL and also breaks older nvcc
`cuda::uninitialized_buffer` provides an allocation of `N` elements of type `T` utilitzing a `cuda::mr::resource` to allocate the storage.

`cuda::uninitialized_buffer` takes care of alignment and deallocation of the storage. The user is required to ensure that the lifetime of the memory resource exceeds the lifetime of the buffer.
Copy link
Contributor

🟨 CI finished in 4h 28m: Pass: 99%/417 | Total: 4d 04h | Avg: 14m 25s | Max: 1h 07m | Hits: 61%/524077
  • 🟨 cub: Pass: 98%/131 | Total: 1d 10h | Avg: 15m 51s | Max: 1h 04m | Hits: 88%/109396

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  98%/123 | Total:  1d 06h | Avg: 14m 49s | Max:  1h 03m | Hits:  90%/102460
      🟩 arm64              Pass: 100%/8   | Total:  4h 12m | Avg: 31m 33s | Max:  1h 04m | Hits:  56%/6936  
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  1h 41m | Avg:  6m 47s | Max: 50m 29s | Hits:  97%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🔍 12.5               Pass:  98%/113 | Total:  1d 08h | Avg: 17m 21s | Max:  1h 04m | Hits:  87%/95003 
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 22s | Avg:  3m 41s | Max:  3m 41s | Hits: 100%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 41m | Avg:  6m 47s | Max: 50m 29s | Hits:  97%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🔍 nvcc12.5           Pass:  98%/111 | Total:  1d 08h | Avg: 17m 36s | Max:  1h 04m | Hits:  87%/93567 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 22s | Avg:  3m 41s | Max:  3m 41s | Hits: 100%/1436  
      🔍 nvcc               Pass:  98%/129 | Total:  1d 10h | Avg: 16m 02s | Max:  1h 04m | Hits:  88%/107960
    🔍 cxx: GCC13 🔍
      🟩 Clang9             Pass: 100%/6   | Total: 27m 24s | Avg:  4m 34s | Max:  5m 18s | Hits: 100%/4980  
      🟩 Clang10            Pass: 100%/3   | Total: 15m 30s | Avg:  5m 10s | Max:  5m 33s | Hits: 100%/2607  
      🟩 Clang11            Pass: 100%/4   | Total: 16m 59s | Avg:  4m 14s | Max:  4m 28s | Hits: 100%/3476  
      🟩 Clang12            Pass: 100%/4   | Total: 17m 17s | Avg:  4m 19s | Max:  4m 29s | Hits:  99%/3476  
      🟩 Clang13            Pass: 100%/4   | Total: 16m 49s | Avg:  4m 12s | Max:  4m 14s | Hits: 100%/3476  
      🟩 Clang14            Pass: 100%/4   | Total: 17m 23s | Avg:  4m 20s | Max:  4m 33s | Hits: 100%/3476  
      🟩 Clang15            Pass: 100%/4   | Total: 18m 22s | Avg:  4m 35s | Max:  4m 47s | Hits: 100%/3468  
      🟩 Clang16            Pass: 100%/4   | Total: 17m 49s | Avg:  4m 27s | Max:  4m 39s | Hits: 100%/3468  
      🟩 Clang17            Pass: 100%/26  | Total:  7h 09m | Avg: 16m 31s | Max: 49m 06s | Hits:  99%/22244 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 07s | Avg:  3m 33s | Max:  3m 34s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total: 22m 46s | Avg:  3m 47s | Max:  4m 21s | Hits:  99%/4983  
      🟩 GCC8               Pass: 100%/6   | Total: 23m 13s | Avg:  3m 52s | Max:  4m 13s | Hits:  99%/4983  
      🟩 GCC9               Pass: 100%/6   | Total: 23m 43s | Avg:  3m 57s | Max:  4m 30s | Hits:  99%/4983  
      🟩 GCC10              Pass: 100%/4   | Total: 17m 40s | Avg:  4m 25s | Max:  4m 34s | Hits:  99%/3476  
      🟩 GCC11              Pass: 100%/7   | Total: 31m 52s | Avg:  4m 33s | Max:  5m 01s | Hits:  99%/6069  
      🟩 GCC12              Pass: 100%/4   | Total: 18m 05s | Avg:  4m 31s | Max:  4m 40s | Hits:  99%/3468  
      🔍 GCC13              Pass:  92%/28  | Total: 14h 03m | Avg: 30m 07s | Max:  1h 04m | Hits:  59%/22542 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 44m | Avg: 54m 59s | Max: 58m 01s | Hits:  51%/2385  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 50m 29s | Avg: 50m 29s | Max: 50m 29s | Hits:  54%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 55m | Avg: 57m 51s | Max: 57m 54s | Hits:  54%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  3h 00m | Avg:  1h 00m | Max:  1h 03m | Hits:  54%/2127  
    🔍 cxx_family: GCC 🔍
      🟩 Clang              Pass: 100%/59  | Total:  9h 37m | Avg:  9m 47s | Max: 49m 06s | Hits:  99%/50671 
      🔍 GCC                Pass:  96%/63  | Total: 16h 27m | Avg: 15m 40s | Max:  1h 04m | Hits:  82%/52086 
      🟩 Intel              Pass: 100%/3   | Total:  2h 44m | Avg: 54m 59s | Max: 58m 01s | Hits:  51%/2385  
      🟩 MSVC               Pass: 100%/6   | Total:  5h 46m | Avg: 57m 48s | Max:  1h 03m | Hits:  54%/4254  
    🔍 jobs: TestGPU 🔍
      🟩 Build              Pass: 100%/99  | Total: 23h 00m | Avg: 13m 56s | Max:  1h 04m | Hits:  85%/83386 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  3h 31m | Avg: 26m 28s | Max: 49m 06s | Hits:  99%/6936  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 25m | Avg: 18m 13s | Max: 28m 37s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 39m | Avg: 19m 57s | Max: 25m 51s | Hits:  99%/6936  
      🔍 TestGPU            Pass:  75%/8   | Total:  2h 59m | Avg: 22m 26s | Max: 36m 05s | Hits:  99%/5202  
    🟨 std
      🟩 11                 Pass: 100%/34  | Total:  7h 53m | Avg: 13m 55s | Max: 54m 48s | Hits:  90%/29049 
      🟨 14                 Pass:  97%/37  | Total: 10h 08m | Avg: 16m 27s | Max:  1h 01m | Hits:  88%/30309 
      🟩 17                 Pass: 100%/36  | Total:  9h 11m | Avg: 15m 18s | Max: 58m 41s | Hits:  89%/30394 
      🟨 20                 Pass:  95%/24  | Total:  7h 23m | Avg: 18m 28s | Max:  1h 04m | Hits:  86%/19644 
    🟨 gpu
      🟨 v100               Pass:  98%/131 | Total:  1d 10h | Avg: 15m 51s | Max:  1h 04m | Hits:  88%/109396
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total:  1h 29m | Avg: 22m 22s | Max: 24m 03s | Hits:  13%/3468  
    
  • 🟨 libcudacxx: Pass: 99%/112 | Total: 1d 15h | Avg: 20m 55s | Max: 1h 07m | Hits: 42%/273251

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  99%/104 | Total:  1d 12h | Avg: 21m 10s | Max:  1h 07m | Hits:  43%/250905
      🟩 arm64              Pass: 100%/8   | Total:  2h 22m | Avg: 17m 49s | Max: 20m 29s | Hits:  38%/22346 
    🔍 ctk: 12.5 🔍
      🟩 11.1               Pass: 100%/15  | Total:  4h 20m | Avg: 17m 22s | Max: 39m 59s | Hits:  76%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🔍 12.5               Pass:  98%/94  | Total:  1d 10h | Avg: 21m 47s | Max:  1h 07m | Hits:  35%/225407
    🔍 cudacxx: nvcc12.5 🔍
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 37m 12s | Avg: 18m 36s | Max: 18m 48s | Hits:  31%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  4h 20m | Avg: 17m 22s | Max: 39m 59s | Hits:  76%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🔍 nvcc12.5           Pass:  98%/92  | Total:  1d 09h | Avg: 21m 51s | Max:  1h 07m | Hits:  35%/219308
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 37m 12s | Avg: 18m 36s | Max: 18m 48s | Hits:  31%/6099  
      🔍 nvcc               Pass:  99%/110 | Total:  1d 14h | Avg: 20m 58s | Max:  1h 07m | Hits:  42%/267152
    🔍 cxx: GCC13 🔍
      🟩 Clang9             Pass: 100%/6   | Total:  2h 02m | Avg: 20m 22s | Max: 25m 55s | Hits:  39%/16160 
      🟩 Clang10            Pass: 100%/3   | Total:  1h 06m | Avg: 22m 01s | Max: 24m 09s | Hits:  35%/8109  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 17m | Avg: 19m 28s | Max: 20m 41s | Hits:  33%/11181 
      🟩 Clang12            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 10s | Max: 21m 08s | Hits:  33%/11181 
      🟩 Clang13            Pass: 100%/4   | Total:  1h 19m | Avg: 19m 56s | Max: 21m 02s | Hits:  33%/11181 
      🟩 Clang14            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 12s | Max: 21m 16s | Hits:  38%/11181 
      🟩 Clang15            Pass: 100%/4   | Total:  1h 19m | Avg: 19m 49s | Max: 20m 52s | Hits:  38%/11173 
      🟩 Clang16            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 05s | Max: 21m 42s | Hits:  38%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  6h 33m | Avg: 28m 07s | Max:  1h 07m | Hits:  36%/28445 
      🟩 GCC6               Pass: 100%/2   | Total: 42m 38s | Avg: 21m 19s | Max: 39m 59s | Hits:  89%/5045  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 41m | Avg: 16m 50s | Max: 37m 09s | Hits:  64%/16146 
      🟩 GCC8               Pass: 100%/6   | Total:  1h 40m | Avg: 16m 44s | Max: 38m 37s | Hits:  64%/16154 
      🟩 GCC9               Pass: 100%/6   | Total:  1h 43m | Avg: 17m 10s | Max: 37m 52s | Hits:  64%/16158 
      🟩 GCC10              Pass: 100%/4   | Total:  1h 18m | Avg: 19m 33s | Max: 20m 13s | Hits:  38%/11181 
      🟩 GCC11              Pass: 100%/7   | Total:  1h 52m | Avg: 16m 06s | Max: 20m 23s | Hits:  52%/19237 
      🟩 GCC12              Pass: 100%/4   | Total:  1h 19m | Avg: 19m 47s | Max: 21m 38s | Hits:  38%/11173 
      🔍 GCC13              Pass:  95%/21  | Total:  7h 05m | Avg: 20m 14s | Max: 37m 05s | Hits:  37%/33897 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 09m | Avg: 23m 15s | Max: 24m 07s | Hits:   3%/8105  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 26m 52s | Avg: 26m 52s | Max: 26m 52s | Hits:  32%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 51m 54s | Avg: 25m 57s | Max: 27m 46s | Hits:  30%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  1h 32m | Avg: 30m 44s | Max: 34m 30s | Hits:  29%/8401  
    🔍 cxx_family: GCC 🔍
      🟩 Clang              Pass: 100%/47  | Total: 17h 41m | Avg: 22m 34s | Max:  1h 07m | Hits:  36%/119784
      🔍 GCC                Pass:  98%/56  | Total: 17h 22m | Avg: 18m 36s | Max: 39m 59s | Hits:  52%/128991
      🟩 Intel              Pass: 100%/3   | Total:  1h 09m | Avg: 23m 15s | Max: 24m 07s | Hits:   3%/8105  
      🟩 MSVC               Pass: 100%/6   | Total:  2h 50m | Avg: 28m 29s | Max: 34m 30s | Hits:  30%/16371 
    🔍 jobs: NVRTC 🔍
      🟩 Build              Pass: 100%/99  | Total:  1d 07h | Avg: 19m 20s | Max: 39m 59s | Hits:  42%/273236
      🔍 NVRTC              Pass:  75%/4   | Total:  1h 29m | Avg: 22m 25s | Max: 27m 46s | Hits: 100%/15    
      🟩 Test               Pass: 100%/8   | Total:  5h 37m | Avg: 42m 13s | Max:  1h 07m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 52s | Avg:  1m 52s | Max:  1m 52s
    🔍 std: 17 🔍
      🟩 11                 Pass: 100%/29  | Total: 11h 23m | Avg: 23m 34s | Max: 39m 59s | Hits:  53%/58202 
      🟩 14                 Pass: 100%/32  | Total:  9h 19m | Avg: 17m 29s | Max: 33m 55s | Hits:  42%/81790 
      🔍 17                 Pass:  96%/31  | Total: 10h 38m | Avg: 20m 36s | Max:  1h 03m | Hits:  40%/84131 
      🟩 20                 Pass: 100%/19  | Total:  7h 39m | Avg: 24m 12s | Max:  1h 07m | Hits:  33%/49128 
    🟨 gpu
      🟨 v100               Pass:  99%/112 | Total:  1d 15h | Avg: 20m 55s | Max:  1h 07m | Hits:  42%/273251
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🟩 90a                Pass: 100%/4   | Total: 51m 22s | Avg: 12m 50s | Max: 15m 14s | Hits:  36%/11536 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 23h 42m | Avg: 12m 03s | Max: 1h 03m | Hits: 77%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 21h 25m | Avg: 11m 41s | Max:  1h 03m | Hits:  79%/129492
      🟩 arm64              Pass: 100%/8   | Total:  2h 17m | Avg: 17m 10s | Max: 31m 54s | Hits:  57%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 45m | Avg:  7m 02s | Max: 53m 13s | Hits:  86%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 12.5               Pass: 100%/100 | Total: 21h 46m | Avg: 13m 03s | Max:  1h 03m | Hits:  75%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 47s | Hits: 100%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 45m | Avg:  7m 02s | Max: 53m 13s | Hits:  86%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total: 21h 39m | Avg: 13m 15s | Max:  1h 03m | Hits:  75%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 47s | Hits: 100%/2354  
      🟩 nvcc               Pass: 100%/116 | Total: 23h 35m | Avg: 12m 12s | Max:  1h 03m | Hits:  77%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 38m 43s | Avg:  6m 27s | Max:  8m 37s | Hits:  63%/7062  
      🟩 Clang10            Pass: 100%/3   | Total: 20m 50s | Avg:  6m 56s | Max:  8m 28s | Hits:  63%/3531  
      🟩 Clang11            Pass: 100%/4   | Total: 26m 11s | Avg:  6m 32s | Max:  7m 43s | Hits:  59%/4708  
      🟩 Clang12            Pass: 100%/4   | Total: 26m 34s | Avg:  6m 38s | Max:  7m 59s | Hits:  59%/4708  
      🟩 Clang13            Pass: 100%/4   | Total: 27m 53s | Avg:  6m 58s | Max:  8m 18s | Hits:  59%/4708  
      🟩 Clang14            Pass: 100%/4   | Total: 14m 35s | Avg:  3m 38s | Max:  3m 48s | Hits: 100%/4708  
      🟩 Clang15            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  4m 15s | Hits: 100%/4708  
      🟩 Clang16            Pass: 100%/4   | Total: 15m 28s | Avg:  3m 52s | Max:  4m 05s | Hits: 100%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  2h 08m | Avg:  7m 07s | Max: 25m 22s | Hits: 100%/21186 
      🟩 GCC6               Pass: 100%/2   | Total:  6m 09s | Avg:  3m 04s | Max:  3m 11s | Hits:  99%/2354  
      🟩 GCC7               Pass: 100%/6   | Total: 20m 18s | Avg:  3m 23s | Max:  3m 52s | Hits:  99%/7068  
      🟩 GCC8               Pass: 100%/6   | Total: 19m 38s | Avg:  3m 16s | Max:  3m 43s | Hits:  99%/7068  
      🟩 GCC9               Pass: 100%/6   | Total: 20m 00s | Avg:  3m 20s | Max:  3m 45s | Hits:  99%/7068  
      🟩 GCC10              Pass: 100%/4   | Total: 44m 49s | Avg: 11m 12s | Max: 33m 50s | Hits:  79%/4712  
      🟩 GCC11              Pass: 100%/7   | Total: 25m 02s | Avg:  3m 34s | Max:  3m 55s | Hits:  99%/8246  
      🟩 GCC12              Pass: 100%/4   | Total: 15m 07s | Avg:  3m 46s | Max:  4m 01s | Hits:  99%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  7h 20m | Avg: 22m 01s | Max: 42m 48s | Hits:  53%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 57m | Avg: 39m 04s | Max: 42m 15s | Hits:   6%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 53m 13s | Avg: 53m 13s | Max: 53m 13s | Hits:   5%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 54m | Avg: 57m 22s | Max:  1h 02m | Hits:  11%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 52m | Avg: 38m 42s | Max:  1h 03m | Hits:  55%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total:  5h 13m | Avg:  6m 09s | Max: 25m 22s | Hits:  83%/60027 
      🟩 GCC                Pass: 100%/55  | Total:  9h 51m | Avg: 10m 45s | Max: 42m 48s | Hits:  81%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  1h 57m | Avg: 39m 04s | Max: 42m 15s | Hits:   6%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 40m | Avg: 44m 27s | Max:  1h 03m | Hits:  40%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 23h 42m | Avg: 12m 03s | Max:  1h 03m | Hits:  77%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 19h 05m | Avg: 11m 34s | Max:  1h 03m | Hits:  74%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 41m | Avg:  9m 13s | Max: 19m 06s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 55m | Avg: 21m 59s | Max: 42m 48s | Hits:  89%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 90a                Pass: 100%/4   | Total:  1h 15m | Avg: 18m 58s | Max: 20m 56s | Hits:  15%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  3h 49m | Avg:  7m 39s | Max: 33m 44s | Hits:  89%/35328 
      🟩 14                 Pass: 100%/34  | Total:  7h 25m | Avg: 13m 05s | Max: 56m 02s | Hits:  73%/40020 
      🟩 17                 Pass: 100%/33  | Total:  6h 58m | Avg: 12m 41s | Max:  1h 03m | Hits:  75%/38847 
      🟩 20                 Pass: 100%/21  | Total:  5h 29m | Avg: 15m 40s | Max: 59m 25s | Hits:  70%/24717 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 37m | Avg: 2m 51s | Max: 7m 18s | Hits: 61%/2518

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 25m | Avg:  2m 50s | Max:  7m 18s | Hits:  62%/2334  
      🟩 arm64              Pass: 100%/4   | Total: 11m 57s | Avg:  2m 59s | Max:  3m 05s | Hits:  45%/184   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total:  1h 02m | Avg:  2m 42s | Max:  7m 18s | Hits:  74%/1052  
      🟩 12.5               Pass: 100%/32  | Total:  1h 34m | Avg:  2m 57s | Max:  6m 47s | Hits:  51%/1466  
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 02m | Avg:  2m 42s | Max:  7m 18s | Hits:  74%/1052  
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 34m | Avg:  2m 57s | Max:  6m 47s | Hits:  51%/1466  
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  7m 18s | Hits:  61%/2518  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  5m 06s | Avg:  2m 33s | Max:  2m 38s | Hits:  47%/92    
      🟩 Clang10            Pass: 100%/2   | Total:  5m 10s | Avg:  2m 35s | Max:  2m 46s | Hits:  47%/92    
      🟩 Clang11            Pass: 100%/4   | Total: 10m 00s | Avg:  2m 30s | Max:  2m 43s | Hits:  47%/184   
      🟩 Clang12            Pass: 100%/4   | Total:  9m 58s | Avg:  2m 29s | Max:  2m 42s | Hits:  47%/184   
      🟩 Clang13            Pass: 100%/4   | Total:  9m 54s | Avg:  2m 28s | Max:  2m 41s | Hits:  47%/184   
      🟩 Clang14            Pass: 100%/6   | Total: 16m 43s | Avg:  2m 47s | Max:  4m 11s | Hits:  81%/276   
      🟩 Clang15            Pass: 100%/2   | Total:  5m 19s | Avg:  2m 39s | Max:  2m 49s | Hits:  47%/92    
      🟩 Clang16            Pass: 100%/6   | Total: 19m 46s | Avg:  3m 17s | Max:  4m 22s | Hits:  65%/276   
      🟩 GCC9               Pass: 100%/2   | Total:  4m 12s | Avg:  2m 06s | Max:  2m 27s | Hits:  67%/92    
      🟩 GCC10              Pass: 100%/4   | Total:  8m 58s | Avg:  2m 14s | Max:  2m 29s | Hits:  67%/184   
      🟩 GCC11              Pass: 100%/4   | Total:  8m 50s | Avg:  2m 12s | Max:  2m 28s | Hits:  67%/184   
      🟩 GCC12              Pass: 100%/12  | Total: 35m 56s | Avg:  2m 59s | Max:  4m 34s | Hits:  72%/552   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  3m 09s | Avg:  3m 09s | Max:  3m 09s | Hits:  34%/46    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 18s | Avg:  7m 18s | Max:  7m 18s | Hits:  17%/40    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 47s | Avg:  6m 47s | Max:  6m 47s | Hits:  17%/40    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 21m | Avg:  2m 43s | Max:  4m 22s | Hits:  57%/1380  
      🟩 GCC                Pass: 100%/22  | Total: 57m 56s | Avg:  2m 38s | Max:  4m 34s | Hits:  70%/1012  
      🟩 Intel              Pass: 100%/1   | Total:  3m 09s | Avg:  3m 09s | Max:  3m 09s | Hits:  34%/46    
      🟩 MSVC               Pass: 100%/2   | Total: 14m 05s | Avg:  7m 02s | Max:  7m 18s | Hits:  17%/80    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  7m 18s | Hits:  61%/2518  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 03m | Avg:  2m 38s | Max:  7m 18s | Hits:  54%/2150  
      🟩 Test               Pass: 100%/8   | Total: 33m 15s | Avg:  4m 09s | Max:  4m 34s | Hits:  97%/368   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 07s | Avg:  2m 07s | Max:  2m 07s | Hits:  91%/46    
      🟩 90a                Pass: 100%/1   | Total:  2m 01s | Avg:  2m 01s | Max:  2m 01s | Hits:  43%/46    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 22m | Avg:  2m 40s | Max:  4m 24s | Hits:  61%/1426  
      🟩 20                 Pass: 100%/24  | Total:  1h 14m | Avg:  3m 05s | Max:  7m 18s | Hits:  60%/1092  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    

👃 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

auto-merge was automatically disabled July 31, 2024 12:15

Pull Request is not mergeable

Copy link
Contributor

🟩 CI finished in 5h 41m: Pass: 100%/417 | Total: 4d 05h | Avg: 14m 32s | Max: 1h 07m | Hits: 61%/525816
  • 🟩 cub: Pass: 100%/131 | Total: 1d 11h | Avg: 16m 18s | Max: 1h 04m | Hits: 88%/111130

    🟩 cpu
      🟩 amd64              Pass: 100%/123 | Total:  1d 07h | Avg: 15m 18s | Max:  1h 03m | Hits:  91%/104194
      🟩 arm64              Pass: 100%/8   | Total:  4h 12m | Avg: 31m 33s | Max:  1h 04m | Hits:  56%/6936  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 41m | Avg:  6m 47s | Max: 50m 29s | Hits:  97%/11792 
      🟩 11.8               Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🟩 12.5               Pass: 100%/113 | Total:  1d 09h | Avg: 17m 52s | Max:  1h 04m | Hits:  87%/96737 
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 22s | Avg:  3m 41s | Max:  3m 41s | Hits: 100%/1436  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 41m | Avg:  6m 47s | Max: 50m 29s | Hits:  97%/11792 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🟩 nvcc12.5           Pass: 100%/111 | Total:  1d 09h | Avg: 18m 08s | Max:  1h 04m | Hits:  87%/95301 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 22s | Avg:  3m 41s | Max:  3m 41s | Hits: 100%/1436  
      🟩 nvcc               Pass: 100%/129 | Total:  1d 11h | Avg: 16m 29s | Max:  1h 04m | Hits:  88%/109694
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 27m 24s | Avg:  4m 34s | Max:  5m 18s | Hits: 100%/4980  
      🟩 Clang10            Pass: 100%/3   | Total: 15m 30s | Avg:  5m 10s | Max:  5m 33s | Hits: 100%/2607  
      🟩 Clang11            Pass: 100%/4   | Total: 16m 59s | Avg:  4m 14s | Max:  4m 28s | Hits: 100%/3476  
      🟩 Clang12            Pass: 100%/4   | Total: 17m 17s | Avg:  4m 19s | Max:  4m 29s | Hits:  99%/3476  
      🟩 Clang13            Pass: 100%/4   | Total: 16m 49s | Avg:  4m 12s | Max:  4m 14s | Hits: 100%/3476  
      🟩 Clang14            Pass: 100%/4   | Total: 17m 23s | Avg:  4m 20s | Max:  4m 33s | Hits: 100%/3476  
      🟩 Clang15            Pass: 100%/4   | Total: 18m 22s | Avg:  4m 35s | Max:  4m 47s | Hits: 100%/3468  
      🟩 Clang16            Pass: 100%/4   | Total: 17m 49s | Avg:  4m 27s | Max:  4m 39s | Hits: 100%/3468  
      🟩 Clang17            Pass: 100%/26  | Total:  7h 09m | Avg: 16m 31s | Max: 49m 06s | Hits:  99%/22244 
      🟩 GCC6               Pass: 100%/2   | Total:  7m 07s | Avg:  3m 33s | Max:  3m 34s | Hits:  99%/1582  
      🟩 GCC7               Pass: 100%/6   | Total: 22m 46s | Avg:  3m 47s | Max:  4m 21s | Hits:  99%/4983  
      🟩 GCC8               Pass: 100%/6   | Total: 23m 13s | Avg:  3m 52s | Max:  4m 13s | Hits:  99%/4983  
      🟩 GCC9               Pass: 100%/6   | Total: 23m 43s | Avg:  3m 57s | Max:  4m 30s | Hits:  99%/4983  
      🟩 GCC10              Pass: 100%/4   | Total: 17m 40s | Avg:  4m 25s | Max:  4m 34s | Hits:  99%/3476  
      🟩 GCC11              Pass: 100%/7   | Total: 31m 52s | Avg:  4m 33s | Max:  5m 01s | Hits:  99%/6069  
      🟩 GCC12              Pass: 100%/4   | Total: 18m 05s | Avg:  4m 31s | Max:  4m 40s | Hits:  99%/3468  
      🟩 GCC13              Pass: 100%/28  | Total: 15h 01m | Avg: 32m 12s | Max:  1h 04m | Hits:  62%/24276 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 44m | Avg: 54m 59s | Max: 58m 01s | Hits:  51%/2385  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 50m 29s | Avg: 50m 29s | Max: 50m 29s | Hits:  54%/709   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 55m | Avg: 57m 51s | Max: 57m 54s | Hits:  54%/1418  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  3h 00m | Avg:  1h 00m | Max:  1h 03m | Hits:  54%/2127  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/59  | Total:  9h 37m | Avg:  9m 47s | Max: 49m 06s | Hits:  99%/50671 
      🟩 GCC                Pass: 100%/63  | Total: 17h 26m | Avg: 16m 36s | Max:  1h 04m | Hits:  82%/53820 
      🟩 Intel              Pass: 100%/3   | Total:  2h 44m | Avg: 54m 59s | Max: 58m 01s | Hits:  51%/2385  
      🟩 MSVC               Pass: 100%/6   | Total:  5h 46m | Avg: 57m 48s | Max:  1h 03m | Hits:  54%/4254  
    🟩 gpu
      🟩 v100               Pass: 100%/131 | Total:  1d 11h | Avg: 16m 18s | Max:  1h 04m | Hits:  88%/111130
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 23h 00m | Avg: 13m 56s | Max:  1h 04m | Hits:  85%/83386 
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  3h 31m | Avg: 26m 28s | Max: 49m 06s | Hits:  99%/6936  
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 25m | Avg: 18m 13s | Max: 28m 37s | Hits:  99%/6936  
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 39m | Avg: 19m 57s | Max: 25m 51s | Hits:  99%/6936  
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 58m | Avg: 29m 45s | Max: 36m 18s | Hits:  99%/6936  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 13m 12s | Avg:  4m 24s | Max:  4m 41s | Hits:  99%/2601  
      🟩 90a                Pass: 100%/4   | Total:  1h 29m | Avg: 22m 22s | Max: 24m 03s | Hits:  13%/3468  
    🟩 std
      🟩 11                 Pass: 100%/34  | Total:  7h 53m | Avg: 13m 55s | Max: 54m 48s | Hits:  90%/29049 
      🟩 14                 Pass: 100%/37  | Total: 10h 35m | Avg: 17m 09s | Max:  1h 01m | Hits:  88%/31176 
      🟩 17                 Pass: 100%/36  | Total:  9h 11m | Avg: 15m 18s | Max: 58m 41s | Hits:  89%/30394 
      🟩 20                 Pass: 100%/24  | Total:  7h 55m | Avg: 19m 48s | Max:  1h 04m | Hits:  87%/20511 
    
  • 🟩 thrust: Pass: 100%/118 | Total: 23h 42m | Avg: 12m 03s | Max: 1h 03m | Hits: 77%/138912

    🟩 cpu
      🟩 amd64              Pass: 100%/110 | Total: 21h 25m | Avg: 11m 41s | Max:  1h 03m | Hits:  79%/129492
      🟩 arm64              Pass: 100%/8   | Total:  2h 17m | Avg: 17m 10s | Max: 31m 54s | Hits:  57%/9420  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 45m | Avg:  7m 02s | Max: 53m 13s | Hits:  86%/17660 
      🟩 11.8               Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 12.5               Pass: 100%/100 | Total: 21h 46m | Avg: 13m 03s | Max:  1h 03m | Hits:  75%/117718
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 47s | Hits: 100%/2354  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 45m | Avg:  7m 02s | Max: 53m 13s | Hits:  86%/17660 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 nvcc12.5           Pass: 100%/98  | Total: 21h 39m | Avg: 13m 15s | Max:  1h 03m | Hits:  75%/115364
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 14s | Avg:  3m 37s | Max:  3m 47s | Hits: 100%/2354  
      🟩 nvcc               Pass: 100%/116 | Total: 23h 35m | Avg: 12m 12s | Max:  1h 03m | Hits:  77%/136558
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 38m 43s | Avg:  6m 27s | Max:  8m 37s | Hits:  63%/7062  
      🟩 Clang10            Pass: 100%/3   | Total: 20m 50s | Avg:  6m 56s | Max:  8m 28s | Hits:  63%/3531  
      🟩 Clang11            Pass: 100%/4   | Total: 26m 11s | Avg:  6m 32s | Max:  7m 43s | Hits:  59%/4708  
      🟩 Clang12            Pass: 100%/4   | Total: 26m 34s | Avg:  6m 38s | Max:  7m 59s | Hits:  59%/4708  
      🟩 Clang13            Pass: 100%/4   | Total: 27m 53s | Avg:  6m 58s | Max:  8m 18s | Hits:  59%/4708  
      🟩 Clang14            Pass: 100%/4   | Total: 14m 35s | Avg:  3m 38s | Max:  3m 48s | Hits: 100%/4708  
      🟩 Clang15            Pass: 100%/4   | Total: 15m 24s | Avg:  3m 51s | Max:  4m 15s | Hits: 100%/4708  
      🟩 Clang16            Pass: 100%/4   | Total: 15m 28s | Avg:  3m 52s | Max:  4m 05s | Hits: 100%/4708  
      🟩 Clang17            Pass: 100%/18  | Total:  2h 08m | Avg:  7m 07s | Max: 25m 22s | Hits: 100%/21186 
      🟩 GCC6               Pass: 100%/2   | Total:  6m 09s | Avg:  3m 04s | Max:  3m 11s | Hits:  99%/2354  
      🟩 GCC7               Pass: 100%/6   | Total: 20m 18s | Avg:  3m 23s | Max:  3m 52s | Hits:  99%/7068  
      🟩 GCC8               Pass: 100%/6   | Total: 19m 38s | Avg:  3m 16s | Max:  3m 43s | Hits:  99%/7068  
      🟩 GCC9               Pass: 100%/6   | Total: 20m 00s | Avg:  3m 20s | Max:  3m 45s | Hits:  99%/7068  
      🟩 GCC10              Pass: 100%/4   | Total: 44m 49s | Avg: 11m 12s | Max: 33m 50s | Hits:  79%/4712  
      🟩 GCC11              Pass: 100%/7   | Total: 25m 02s | Avg:  3m 34s | Max:  3m 55s | Hits:  99%/8246  
      🟩 GCC12              Pass: 100%/4   | Total: 15m 07s | Avg:  3m 46s | Max:  4m 01s | Hits:  99%/4712  
      🟩 GCC13              Pass: 100%/20  | Total:  7h 20m | Avg: 22m 01s | Max: 42m 48s | Hits:  53%/23560 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 57m | Avg: 39m 04s | Max: 42m 15s | Hits:   6%/3540  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 53m 13s | Avg: 53m 13s | Max: 53m 13s | Hits:   5%/1173  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 54m | Avg: 57m 22s | Max:  1h 02m | Hits:  11%/2346  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  3h 52m | Avg: 38m 42s | Max:  1h 03m | Hits:  55%/7038  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/51  | Total:  5h 13m | Avg:  6m 09s | Max: 25m 22s | Hits:  83%/60027 
      🟩 GCC                Pass: 100%/55  | Total:  9h 51m | Avg: 10m 45s | Max: 42m 48s | Hits:  81%/64788 
      🟩 Intel              Pass: 100%/3   | Total:  1h 57m | Avg: 39m 04s | Max: 42m 15s | Hits:   6%/3540  
      🟩 MSVC               Pass: 100%/9   | Total:  6h 40m | Avg: 44m 27s | Max:  1h 03m | Hits:  40%/10557 
    🟩 gpu
      🟩 v100               Pass: 100%/118 | Total: 23h 42m | Avg: 12m 03s | Max:  1h 03m | Hits:  77%/138912
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total: 19h 05m | Avg: 11m 34s | Max:  1h 03m | Hits:  74%/116553
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 41m | Avg:  9m 13s | Max: 19m 06s | Hits:  99%/12939 
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 55m | Avg: 21m 59s | Max: 42m 48s | Hits:  89%/9420  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 10m 48s | Avg:  3m 36s | Max:  3m 52s | Hits:  99%/3534  
      🟩 90a                Pass: 100%/4   | Total:  1h 15m | Avg: 18m 58s | Max: 20m 56s | Hits:  15%/4712  
    🟩 std
      🟩 11                 Pass: 100%/30  | Total:  3h 49m | Avg:  7m 39s | Max: 33m 44s | Hits:  89%/35328 
      🟩 14                 Pass: 100%/34  | Total:  7h 25m | Avg: 13m 05s | Max: 56m 02s | Hits:  73%/40020 
      🟩 17                 Pass: 100%/33  | Total:  6h 58m | Avg: 12m 41s | Max:  1h 03m | Hits:  75%/38847 
      🟩 20                 Pass: 100%/21  | Total:  5h 29m | Avg: 15m 40s | Max: 59m 25s | Hits:  70%/24717 
    
  • 🟩 libcudacxx: Pass: 100%/112 | Total: 1d 14h | Avg: 20m 51s | Max: 1h 07m | Hits: 42%/273256

    🟩 cpu
      🟩 amd64              Pass: 100%/104 | Total:  1d 12h | Avg: 21m 05s | Max:  1h 07m | Hits:  43%/250910
      🟩 arm64              Pass: 100%/8   | Total:  2h 22m | Avg: 17m 49s | Max: 20m 29s | Hits:  38%/22346 
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  4h 20m | Avg: 17m 22s | Max: 39m 59s | Hits:  76%/39780 
      🟩 11.8               Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🟩 12.5               Pass: 100%/94  | Total:  1d 09h | Avg: 21m 41s | Max:  1h 07m | Hits:  35%/225412
    🟩 cudacxx
      🟩 ClangCUDA17        Pass: 100%/2   | Total: 37m 12s | Avg: 18m 36s | Max: 18m 48s | Hits:  31%/6099  
      🟩 nvcc11.1           Pass: 100%/15  | Total:  4h 20m | Avg: 17m 22s | Max: 39m 59s | Hits:  76%/39780 
      🟩 nvcc11.8           Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🟩 nvcc12.5           Pass: 100%/92  | Total:  1d 09h | Avg: 21m 45s | Max:  1h 07m | Hits:  35%/219313
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 37m 12s | Avg: 18m 36s | Max: 18m 48s | Hits:  31%/6099  
      🟩 nvcc               Pass: 100%/110 | Total:  1d 14h | Avg: 20m 53s | Max:  1h 07m | Hits:  42%/267157
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 02m | Avg: 20m 22s | Max: 25m 55s | Hits:  39%/16160 
      🟩 Clang10            Pass: 100%/3   | Total:  1h 06m | Avg: 22m 01s | Max: 24m 09s | Hits:  35%/8109  
      🟩 Clang11            Pass: 100%/4   | Total:  1h 17m | Avg: 19m 28s | Max: 20m 41s | Hits:  33%/11181 
      🟩 Clang12            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 10s | Max: 21m 08s | Hits:  33%/11181 
      🟩 Clang13            Pass: 100%/4   | Total:  1h 19m | Avg: 19m 56s | Max: 21m 02s | Hits:  33%/11181 
      🟩 Clang14            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 12s | Max: 21m 16s | Hits:  38%/11181 
      🟩 Clang15            Pass: 100%/4   | Total:  1h 19m | Avg: 19m 49s | Max: 20m 52s | Hits:  38%/11173 
      🟩 Clang16            Pass: 100%/4   | Total:  1h 20m | Avg: 20m 05s | Max: 21m 42s | Hits:  38%/11173 
      🟩 Clang17            Pass: 100%/14  | Total:  6h 33m | Avg: 28m 07s | Max:  1h 07m | Hits:  36%/28445 
      🟩 GCC6               Pass: 100%/2   | Total: 42m 38s | Avg: 21m 19s | Max: 39m 59s | Hits:  89%/5045  
      🟩 GCC7               Pass: 100%/6   | Total:  1h 41m | Avg: 16m 50s | Max: 37m 09s | Hits:  64%/16146 
      🟩 GCC8               Pass: 100%/6   | Total:  1h 40m | Avg: 16m 44s | Max: 38m 37s | Hits:  64%/16154 
      🟩 GCC9               Pass: 100%/6   | Total:  1h 43m | Avg: 17m 10s | Max: 37m 52s | Hits:  64%/16158 
      🟩 GCC10              Pass: 100%/4   | Total:  1h 18m | Avg: 19m 33s | Max: 20m 13s | Hits:  38%/11181 
      🟩 GCC11              Pass: 100%/7   | Total:  1h 52m | Avg: 16m 06s | Max: 20m 23s | Hits:  52%/19237 
      🟩 GCC12              Pass: 100%/4   | Total:  1h 19m | Avg: 19m 47s | Max: 21m 38s | Hits:  38%/11173 
      🟩 GCC13              Pass: 100%/21  | Total:  6h 56m | Avg: 19m 50s | Max: 37m 05s | Hits:  37%/33902 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 09m | Avg: 23m 15s | Max: 24m 07s | Hits:   3%/8105  
      🟩 MSVC14.16          Pass: 100%/1   | Total: 26m 52s | Avg: 26m 52s | Max: 26m 52s | Hits:  32%/2536  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 51m 54s | Avg: 25m 57s | Max: 27m 46s | Hits:  30%/5434  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  1h 32m | Avg: 30m 44s | Max: 34m 30s | Hits:  29%/8401  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/47  | Total: 17h 41m | Avg: 22m 34s | Max:  1h 07m | Hits:  36%/119784
      🟩 GCC                Pass: 100%/56  | Total: 17h 13m | Avg: 18m 27s | Max: 39m 59s | Hits:  52%/128996
      🟩 Intel              Pass: 100%/3   | Total:  1h 09m | Avg: 23m 15s | Max: 24m 07s | Hits:   3%/8105  
      🟩 MSVC               Pass: 100%/6   | Total:  2h 50m | Avg: 28m 29s | Max: 34m 30s | Hits:  30%/16371 
    🟩 gpu
      🟩 v100               Pass: 100%/112 | Total:  1d 14h | Avg: 20m 51s | Max:  1h 07m | Hits:  42%/273256
    🟩 jobs
      🟩 Build              Pass: 100%/99  | Total:  1d 07h | Avg: 19m 20s | Max: 39m 59s | Hits:  42%/273236
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 21m | Avg: 20m 20s | Max: 22m 18s | Hits: 100%/20    
      🟩 Test               Pass: 100%/8   | Total:  5h 37m | Avg: 42m 13s | Max:  1h 07m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 52s | Avg:  1m 52s | Max:  1m 52s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 35m 55s | Avg: 11m 58s | Max: 17m 50s | Hits:  72%/8064  
      🟩 90a                Pass: 100%/4   | Total: 51m 22s | Avg: 12m 50s | Max: 15m 14s | Hits:  36%/11536 
    🟩 std
      🟩 11                 Pass: 100%/29  | Total: 11h 23m | Avg: 23m 34s | Max: 39m 59s | Hits:  53%/58202 
      🟩 14                 Pass: 100%/32  | Total:  9h 19m | Avg: 17m 29s | Max: 33m 55s | Hits:  42%/81790 
      🟩 17                 Pass: 100%/31  | Total: 10h 30m | Avg: 20m 20s | Max:  1h 03m | Hits:  40%/84136 
      🟩 20                 Pass: 100%/19  | Total:  7h 39m | Avg: 24m 12s | Max:  1h 07m | Hits:  33%/49128 
    
  • 🟩 cudax: Pass: 100%/55 | Total: 2h 37m | Avg: 2m 51s | Max: 7m 18s | Hits: 61%/2518

    🟩 cpu
      🟩 amd64              Pass: 100%/51  | Total:  2h 25m | Avg:  2m 50s | Max:  7m 18s | Hits:  62%/2334  
      🟩 arm64              Pass: 100%/4   | Total: 11m 57s | Avg:  2m 59s | Max:  3m 05s | Hits:  45%/184   
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total:  1h 02m | Avg:  2m 42s | Max:  7m 18s | Hits:  74%/1052  
      🟩 12.5               Pass: 100%/32  | Total:  1h 34m | Avg:  2m 57s | Max:  6m 47s | Hits:  51%/1466  
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 02m | Avg:  2m 42s | Max:  7m 18s | Hits:  74%/1052  
      🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 34m | Avg:  2m 57s | Max:  6m 47s | Hits:  51%/1466  
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  7m 18s | Hits:  61%/2518  
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  5m 06s | Avg:  2m 33s | Max:  2m 38s | Hits:  47%/92    
      🟩 Clang10            Pass: 100%/2   | Total:  5m 10s | Avg:  2m 35s | Max:  2m 46s | Hits:  47%/92    
      🟩 Clang11            Pass: 100%/4   | Total: 10m 00s | Avg:  2m 30s | Max:  2m 43s | Hits:  47%/184   
      🟩 Clang12            Pass: 100%/4   | Total:  9m 58s | Avg:  2m 29s | Max:  2m 42s | Hits:  47%/184   
      🟩 Clang13            Pass: 100%/4   | Total:  9m 54s | Avg:  2m 28s | Max:  2m 41s | Hits:  47%/184   
      🟩 Clang14            Pass: 100%/6   | Total: 16m 43s | Avg:  2m 47s | Max:  4m 11s | Hits:  81%/276   
      🟩 Clang15            Pass: 100%/2   | Total:  5m 19s | Avg:  2m 39s | Max:  2m 49s | Hits:  47%/92    
      🟩 Clang16            Pass: 100%/6   | Total: 19m 46s | Avg:  3m 17s | Max:  4m 22s | Hits:  65%/276   
      🟩 GCC9               Pass: 100%/2   | Total:  4m 12s | Avg:  2m 06s | Max:  2m 27s | Hits:  67%/92    
      🟩 GCC10              Pass: 100%/4   | Total:  8m 58s | Avg:  2m 14s | Max:  2m 29s | Hits:  67%/184   
      🟩 GCC11              Pass: 100%/4   | Total:  8m 50s | Avg:  2m 12s | Max:  2m 28s | Hits:  67%/184   
      🟩 GCC12              Pass: 100%/12  | Total: 35m 56s | Avg:  2m 59s | Max:  4m 34s | Hits:  72%/552   
      🟩 Intel2023.2.0      Pass: 100%/1   | Total:  3m 09s | Avg:  3m 09s | Max:  3m 09s | Hits:  34%/46    
      🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 18s | Avg:  7m 18s | Max:  7m 18s | Hits:  17%/40    
      🟩 MSVC14.39          Pass: 100%/1   | Total:  6m 47s | Avg:  6m 47s | Max:  6m 47s | Hits:  17%/40    
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 21m | Avg:  2m 43s | Max:  4m 22s | Hits:  57%/1380  
      🟩 GCC                Pass: 100%/22  | Total: 57m 56s | Avg:  2m 38s | Max:  4m 34s | Hits:  70%/1012  
      🟩 Intel              Pass: 100%/1   | Total:  3m 09s | Avg:  3m 09s | Max:  3m 09s | Hits:  34%/46    
      🟩 MSVC               Pass: 100%/2   | Total: 14m 05s | Avg:  7m 02s | Max:  7m 18s | Hits:  17%/80    
    🟩 gpu
      🟩 v100               Pass: 100%/55  | Total:  2h 37m | Avg:  2m 51s | Max:  7m 18s | Hits:  61%/2518  
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 03m | Avg:  2m 38s | Max:  7m 18s | Hits:  54%/2150  
      🟩 Test               Pass: 100%/8   | Total: 33m 15s | Avg:  4m 09s | Max:  4m 34s | Hits:  97%/368   
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 07s | Avg:  2m 07s | Max:  2m 07s | Hits:  91%/46    
      🟩 90a                Pass: 100%/1   | Total:  2m 01s | Avg:  2m 01s | Max:  2m 01s | Hits:  43%/46    
    🟩 std
      🟩 17                 Pass: 100%/31  | Total:  1h 22m | Avg:  2m 40s | Max:  4m 24s | Hits:  61%/1426  
      🟩 20                 Pass: 100%/24  | Total:  1h 14m | Avg:  3m 05s | Max:  7m 18s | Hits:  60%/1092  
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
    

👃 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

@miscco miscco merged commit 27253d7 into NVIDIA:main Jul 31, 2024
430 checks passed
@miscco miscco deleted the device_buffer branch July 31, 2024 13:01
@harrism
Copy link
Contributor

harrism commented Jul 31, 2024

Why would we merge a PR that has [PoC] in the title? I would have reviewed more carefully...

@miscco
Copy link
Collaborator Author

miscco commented Aug 1, 2024

Two things:

  1. I need to get better at writing design docs and distributing information
  2. This is going into our CUDA Next library which is not included in the CTK and meant as a playground for experimental features. So something that is in the early design phase is exactly what we want into CUDA Next to flesh out the design.

@gonzalobg
Copy link
Collaborator

gonzalobg commented Aug 1, 2024

It is easy to make mistakes with uninitialized memory, but many are willing to take the risk as a performance optimization. To minimize that risk, applications often work with uninitialized memory as follows:

  • Most uses of uninitialized memory are temporally scoped between allocation and initialization.
  • After initialization, the memory is no longer uninitialized, i.e., safe to use, without pitfalls.
  • The time span, during which memory is uninitialized, is often brief: most code programmers write against memory allocated as uninitialized, deals with initialized memory.

I think that this design does not currently account for the above (but could be extended later maybe! see below):

  • It does not provide a way to obtain "owning initialized" vocabulary data-structures from uninitialized_buffer (an initialized vector, unique_ptr<T>, mdarray<T>, etc.), i.e., provides no way to account for the temporally scoped use of uninitialized memory in applications.
  • Instead it provides an owning type of "always uninitialized" memory such that all uses of it, or of spans created from it, must assume the memory may be uninitialized.
  • While the conversion to span is technically correct (spans can be invalid), I've yet to meet anyone that writes code that assumes spans may be uninitialized, since most come from containers (i.e. the precondition that spans are valid is a common and pervasive one).

I think there is room for an utility that does not account for any of the above:

  • Sometimes one does not have temporal scoping, e.g., within the implementation of vector (although I don't see how exactly to use this to implement something like vector, since I'd be expecting more something like an allocator; maybe there is an example somewhere?).
  • Temporal scoping could be provided later, e.g., by adding constructors to vector and others that move storage from an uninitialized_buffer into an allocator.
    • Is this something that will be pursued?
    • It's not clear to me that an "uninitialized_buffer to container" API is better than just providing a simple unsafe_set_size method to these data-structures, like Rust does. That provides more functionality than this type, at much lower API overhead, while perfectly capturing the temporal scope of dealing with uninitialized memory in practice.
  • I think I'd be happy with dropping uninitialized_ from the name and calling it just buffer. The uninitialized_ is not accurate (the whole point is eventually holding initialized memory, so maybe_uninitialized_ would be accurate), and it is dropped the moment one creates a span from it, which does not call out anything about that.

@miscco
Copy link
Collaborator Author

miscco commented Aug 1, 2024

Thanks a lot for the comment, much appreciated. I believe that we need to better explain the intend of this type. uninitialized_buffer is effectively a glorified allocation / pointer.

What it does is taking away many of the sharp edges that raw allocations have.

  1. It handles deallocation for the user
  2. It stores size information together with the allocation
  3. It ensures that alignment and size of T is properly accounted for
  4. It improves safety in heterogeneous settings

That is the whole purpose of this class and I believe it can be incredibly useful as a building block for higher level types such as cuda::vector but you should think of it exactly as you think about a pointer returned from cudaMalloc or new

@gonzalobg
Copy link
Collaborator

Looking forward to see this inside cuda::vector. I think that if this is used there, then that would be a great example of how to use this type! And may make it easier to provide a way to improve the ergonomics of temporally uninitialized by just having some scary constructor that allows going from fully uninitialized to partially uninitialized.

pciolkosz pushed a commit to pciolkosz/cccl that referenced this pull request Aug 4, 2024
)

* Drop `cuda::get_property` CPO

It serves no purpose as it only ever forwards via ADL and also breaks older nvcc

* Ensure that we test memory resources

* Implement `cuda::uninitialized_buffer`

`cuda::uninitialized_buffer` provides an allocation of `N` elements of type `T` utilitzing a `cuda::mr::resource` to allocate the storage.

`cuda::uninitialized_buffer` takes care of alignment and deallocation of the storage. The user is required to ensure that the lifetime of the memory resource exceeds the lifetime of the buffer.
pciolkosz pushed a commit to pciolkosz/cccl that referenced this pull request Aug 4, 2024
)

* Drop `cuda::get_property` CPO

It serves no purpose as it only ever forwards via ADL and also breaks older nvcc

* Ensure that we test memory resources

* Implement `cuda::uninitialized_buffer`

`cuda::uninitialized_buffer` provides an allocation of `N` elements of type `T` utilitzing a `cuda::mr::resource` to allocate the storage.

`cuda::uninitialized_buffer` takes care of alignment and deallocation of the storage. The user is required to ensure that the lifetime of the memory resource exceeds the lifetime of the buffer.
@harrism
Copy link
Contributor

harrism commented Aug 5, 2024

It would be nice to have utilities for easy conversion from a ubuffer to initialized containers like vector.

RMM's device_uvector has been incredibly useful in RAPIDS. The combination of stream ordering and not having to launch a kernel and sync the device (like thrust::vector) provides quite big performance gains in libcudf when allocating output vectors.

But I agree it would be nice to be able to use those only between allocation and initialization inside a kernel, and to (cheaply) convert them to initialized types or spans afterwards.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CUDA Next Feature intended for the Cuda Next experimental library feature request New feature or request.
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

A low level, untyped, uninitialized RAII abstraction over an allocation cuda::buffer<Properties...>
6 participants