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

Simplify argument forwarding in CUB histogram entry-points #1776

Merged
merged 1 commit into from
May 24, 2024

Conversation

bernhardmgruber
Copy link
Contributor

The CUB histogram APIs forward to the multi histogram APIs in many cases, which expect arrays instead of scalar arguments. This PR simplifies the passing of data from one API to the other.

@bernhardmgruber bernhardmgruber added the cub For all items related to CUB label May 24, 2024
@bernhardmgruber bernhardmgruber marked this pull request as ready for review May 24, 2024 15:40
@bernhardmgruber bernhardmgruber requested review from a team as code owners May 24, 2024 15:40
@bernhardmgruber bernhardmgruber enabled auto-merge (squash) May 24, 2024 16:08
Copy link
Contributor

🟩 CI Results: Pass: 100%/198 | Total Time: 1d 06h | Avg Time: 9m 16s | Hits: 99%/118084
  • 🟩 thrust: Pass: 100%/99 | Total Time: 9h 15m | Avg Time: 5m 36s | Hits: 99%/50817

    🟩 cpu
      🟩 amd64              Pass: 100%/91  | Total Time:  8h 53m | Avg Time:  5m 51s | Hits:  99%/46709 
      🟩 arm64              Pass: 100%/8   | Total Time: 22m 15s | Avg Time:  2m 46s | Hits:  99%/4108  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total Time: 51m 54s | Avg Time:  3m 27s | Hits:  99%/7700  
      🟩 11.8               Pass: 100%/3   | Total Time:  9m 36s | Avg Time:  3m 12s | Hits:  99%/1542  
      🟩 12.4               Pass: 100%/81  | Total Time:  8h 13m | Avg Time:  6m 05s | Hits:  99%/41575 
    🟩 cudacxx_full
      🟩 clang-cuda16       Pass: 100%/2   | Total Time:  6m 13s | Avg Time:  3m 06s | Hits: 100%/1026  
      🟩 nvcc11.1           Pass: 100%/15  | Total Time: 51m 54s | Avg Time:  3m 27s | Hits:  99%/7700  
      🟩 nvcc11.8           Pass: 100%/3   | Total Time:  9m 36s | Avg Time:  3m 12s | Hits:  99%/1542  
      🟩 nvcc12.4           Pass: 100%/79  | Total Time:  8h 07m | Avg Time:  6m 10s | Hits:  99%/40549 
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total Time:  6m 13s | Avg Time:  3m 06s | Hits: 100%/1026  
      🟩 nvcc               Pass: 100%/97  | Total Time:  9h 09m | Avg Time:  5m 39s | Hits:  99%/49791 
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total Time: 19m 53s | Avg Time:  3m 18s | Hits: 100%/3078  
      🟩 clang10            Pass: 100%/3   | Total Time: 11m 29s | Avg Time:  3m 49s | Hits: 100%/1539  
      🟩 clang11            Pass: 100%/4   | Total Time: 12m 48s | Avg Time:  3m 12s | Hits: 100%/2052  
      🟩 clang12            Pass: 100%/4   | Total Time: 12m 58s | Avg Time:  3m 14s | Hits: 100%/2052  
      🟩 clang13            Pass: 100%/4   | Total Time: 13m 01s | Avg Time:  3m 15s | Hits: 100%/2052  
      🟩 clang14            Pass: 100%/4   | Total Time: 12m 50s | Avg Time:  3m 12s | Hits: 100%/2052  
      🟩 clang15            Pass: 100%/4   | Total Time: 13m 14s | Avg Time:  3m 18s | Hits: 100%/2052  
      🟩 clang16            Pass: 100%/14  | Total Time:  2h 22m | Avg Time: 10m 11s | Hits: 100%/7182  
      🟩 gcc6               Pass: 100%/2   | Total Time:  5m 21s | Avg Time:  2m 40s | Hits:  99%/1026  
      🟩 gcc7               Pass: 100%/6   | Total Time: 17m 23s | Avg Time:  2m 53s | Hits:  99%/3084  
      🟩 gcc8               Pass: 100%/6   | Total Time: 17m 21s | Avg Time:  2m 53s | Hits:  99%/3084  
      🟩 gcc9               Pass: 100%/6   | Total Time: 18m 00s | Avg Time:  3m 00s | Hits:  99%/3084  
      🟩 gcc10              Pass: 100%/4   | Total Time: 13m 05s | Avg Time:  3m 16s | Hits:  99%/2056  
      🟩 gcc11              Pass: 100%/7   | Total Time: 22m 55s | Avg Time:  3m 16s | Hits:  99%/3598  
      🟩 gcc12              Pass: 100%/16  | Total Time:  2h 19m | Avg Time:  8m 41s | Hits:  99%/8224  
      🟩 Intel2023.2.0      Pass: 100%/3   | Total Time: 12m 16s | Avg Time:  4m 05s | Hits: 100%/1548  
      🟩 MSVC14.16          Pass: 100%/1   | Total Time: 13m 13s | Avg Time: 13m 13s | Hits:  98%/509   
      🟩 MSVC14.29          Pass: 100%/2   | Total Time: 22m 47s | Avg Time: 11m 23s | Hits:  98%/1018  
      🟩 MSVC14.39          Pass: 100%/3   | Total Time: 35m 12s | Avg Time: 11m 44s | Hits:  98%/1527  
    🟩 cxx_name
      🟩 clang              Pass: 100%/43  | Total Time:  3h 58m | Avg Time:  5m 33s | Hits: 100%/22059 
      🟩 gcc                Pass: 100%/47  | Total Time:  3h 53m | Avg Time:  4m 57s | Hits:  99%/24156 
      🟩 Intel              Pass: 100%/3   | Total Time: 12m 16s | Avg Time:  4m 05s | Hits: 100%/1548  
      🟩 MSVC               Pass: 100%/6   | Total Time:  1h 11m | Avg Time: 11m 52s | Hits:  98%/3054  
    🟩 gpu
      🟩 v100               Pass: 100%/99  | Total Time:  9h 15m | Avg Time:  5m 36s | Hits:  99%/50817 
    🟩 jobs
      🟩 build              Pass: 100%/91  | Total Time:  5h 40m | Avg Time:  3m 44s | Hits:  99%/46709 
      🟩 test               Pass: 100%/8   | Total Time:  3h 35m | Avg Time: 26m 55s | Hits:  99%/4108  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total Time: 38m 41s | Avg Time:  2m 45s | Hits:  99%/7191  
      🟩 ubuntu20.04        Pass: 100%/35  | Total Time:  1h 55m | Avg Time:  3m 17s | Hits:  99%/17968 
      🟩 ubuntu22.04        Pass: 100%/44  | Total Time:  5h 30m | Avg Time:  7m 30s | Hits:  99%/22604 
      🟩 windows2022        Pass: 100%/6   | Total Time:  1h 11m | Avg Time: 11m 52s | Hits:  98%/3054  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total Time:  9m 36s | Avg Time:  3m 12s | Hits:  99%/1542  
      🟩 90a                Pass: 100%/4   | Total Time: 11m 00s | Avg Time:  2m 45s | Hits:  99%/2056  
    🟩 std
      🟩 11                 Pass: 100%/26  | Total Time:  2h 16m | Avg Time:  5m 15s | Hits:  99%/13354 
      🟩 14                 Pass: 100%/29  | Total Time:  2h 26m | Avg Time:  5m 03s | Hits:  99%/14881 
      🟩 17                 Pass: 100%/28  | Total Time:  2h 24m | Avg Time:  5m 08s | Hits:  99%/14372 
      🟩 20                 Pass: 100%/16  | Total Time:  2h 07m | Avg Time:  7m 59s | Hits:  99%/8210  
    
  • 🟩 cub: Pass: 100%/99 | Total Time: 21h 21m | Avg Time: 12m 56s | Hits: 99%/67267

    🟩 cpu
      🟩 amd64              Pass: 100%/91  | Total Time: 20h 35m | Avg Time: 13m 34s | Hits:  99%/61635 
      🟩 arm64              Pass: 100%/8   | Total Time: 45m 43s | Avg Time:  5m 42s | Hits:  99%/5632  
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total Time:  1h 07m | Avg Time:  4m 28s | Hits:  99%/9350  
      🟩 11.8               Pass: 100%/3   | Total Time: 16m 08s | Avg Time:  5m 22s | Hits:  99%/2112  
      🟩 12.4               Pass: 100%/81  | Total Time: 19h 58m | Avg Time: 14m 47s | Hits:  99%/55805 
    🟩 cudacxx_full
      🟩 clang-cuda16       Pass: 100%/2   | Total Time: 10m 47s | Avg Time:  5m 23s | Hits:  99%/1116  
      🟩 nvcc11.1           Pass: 100%/15  | Total Time:  1h 07m | Avg Time:  4m 28s | Hits:  99%/9350  
      🟩 nvcc11.8           Pass: 100%/3   | Total Time: 16m 08s | Avg Time:  5m 22s | Hits:  99%/2112  
      🟩 nvcc12.4           Pass: 100%/79  | Total Time: 19h 47m | Avg Time: 15m 02s | Hits:  99%/54689 
    🟩 cudacxx_name
      🟩 clang-cuda         Pass: 100%/2   | Total Time: 10m 47s | Avg Time:  5m 23s | Hits:  99%/1116  
      🟩 nvcc               Pass: 100%/97  | Total Time: 21h 10m | Avg Time: 13m 06s | Hits:  99%/66151 
    🟩 cxx_full
      🟩 clang9             Pass: 100%/6   | Total Time: 27m 43s | Avg Time:  4m 37s | Hits:  99%/4002  
      🟩 clang10            Pass: 100%/3   | Total Time: 16m 00s | Avg Time:  5m 20s | Hits:  99%/2118  
      🟩 clang11            Pass: 100%/4   | Total Time: 18m 53s | Avg Time:  4m 43s | Hits:  99%/2824  
      🟩 clang12            Pass: 100%/4   | Total Time: 19m 34s | Avg Time:  4m 53s | Hits:  99%/2824  
      🟩 clang13            Pass: 100%/4   | Total Time: 19m 56s | Avg Time:  4m 59s | Hits:  99%/2824  
      🟩 clang14            Pass: 100%/4   | Total Time: 20m 01s | Avg Time:  5m 00s | Hits:  99%/2824  
      🟩 clang15            Pass: 100%/4   | Total Time: 19m 41s | Avg Time:  4m 55s | Hits:  99%/2816  
      🟩 clang16            Pass: 100%/14  | Total Time:  8h 23m | Avg Time: 35m 56s | Hits:  99%/9564  
      🟩 gcc6               Pass: 100%/2   | Total Time:  7m 29s | Avg Time:  3m 44s | Hits:  99%/1256  
      🟩 gcc7               Pass: 100%/6   | Total Time: 25m 58s | Avg Time:  4m 19s | Hits:  99%/4005  
      🟩 gcc8               Pass: 100%/6   | Total Time: 26m 22s | Avg Time:  4m 23s | Hits:  99%/4005  
      🟩 gcc9               Pass: 100%/6   | Total Time: 27m 22s | Avg Time:  4m 33s | Hits:  99%/4005  
      🟩 gcc10              Pass: 100%/4   | Total Time: 20m 07s | Avg Time:  5m 01s | Hits:  99%/2824  
      🟩 gcc11              Pass: 100%/7   | Total Time: 36m 52s | Avg Time:  5m 16s | Hits:  99%/4928  
      🟩 gcc12              Pass: 100%/16  | Total Time:  6h 44m | Avg Time: 25m 15s | Hits:  99%/11264 
      🟩 Intel2023.2.0      Pass: 100%/3   | Total Time: 16m 04s | Avg Time:  5m 21s | Hits:  99%/1890  
      🟩 MSVC14.16          Pass: 100%/1   | Total Time: 13m 40s | Avg Time: 13m 40s | Hits:  98%/549   
      🟩 MSVC14.29          Pass: 100%/2   | Total Time: 22m 59s | Avg Time: 11m 29s | Hits:  98%/1098  
      🟩 MSVC14.39          Pass: 100%/3   | Total Time: 35m 41s | Avg Time: 11m 53s | Hits:  98%/1647  
    🟩 cxx_name
      🟩 clang              Pass: 100%/43  | Total Time: 10h 44m | Avg Time: 14m 59s | Hits:  99%/29796 
      🟩 gcc                Pass: 100%/47  | Total Time:  9h 08m | Avg Time: 11m 39s | Hits:  99%/32287 
      🟩 Intel              Pass: 100%/3   | Total Time: 16m 04s | Avg Time:  5m 21s | Hits:  99%/1890  
      🟩 MSVC               Pass: 100%/6   | Total Time:  1h 12m | Avg Time: 12m 03s | Hits:  98%/3294  
    🟩 gpu
      🟩 v100               Pass: 100%/99  | Total Time: 21h 21m | Avg Time: 12m 56s | Hits:  99%/67267 
    🟩 jobs
      🟩 build              Pass: 100%/91  | Total Time:  8h 06m | Avg Time:  5m 20s | Hits:  99%/61635 
      🟩 test               Pass: 100%/8   | Total Time: 13h 15m | Avg Time:  1h 39m | Hits:  99%/5632  
    🟩 os
      🟩 ubuntu18.04        Pass: 100%/14  | Total Time: 53m 20s | Avg Time:  3m 48s | Hits:  99%/8801  
      🟩 ubuntu20.04        Pass: 100%/35  | Total Time:  2h 56m | Avg Time:  5m 01s | Hits:  99%/24710 
      🟩 ubuntu22.04        Pass: 100%/44  | Total Time: 16h 19m | Avg Time: 22m 16s | Hits:  99%/30462 
      🟩 windows2022        Pass: 100%/6   | Total Time:  1h 12m | Avg Time: 12m 03s | Hits:  98%/3294  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total Time: 16m 08s | Avg Time:  5m 22s | Hits:  99%/2112  
      🟩 90a                Pass: 100%/4   | Total Time: 15m 02s | Avg Time:  3m 45s | Hits:  99%/2816  
    🟩 std
      🟩 11                 Pass: 100%/26  | Total Time:  3h 55m | Avg Time:  9m 03s | Hits:  99%/17873 
      🟩 14                 Pass: 100%/29  | Total Time:  6h 05m | Avg Time: 12m 36s | Hits:  99%/19520 
      🟩 17                 Pass: 100%/28  | Total Time:  7h 09m | Avg Time: 15m 19s | Hits:  99%/18901 
      🟩 20                 Pass: 100%/16  | Total Time:  4h 11m | Avg Time: 15m 43s | Hits:  99%/10973 
    

🏃‍ Runner counts (total jobs: 198)

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

👃 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

@bernhardmgruber bernhardmgruber merged commit 7fe0eb4 into NVIDIA:main May 24, 2024
5 checks passed
@bernhardmgruber bernhardmgruber deleted the simplify branch May 27, 2024 09:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cub For all items related to CUB
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

3 participants