Skip to content

Exclude sm101 from RDC testing. - #4247

Merged
alliepiper merged 1 commit into
NVIDIA:mainfrom
alliepiper:rdc_sm_update
Mar 24, 2025
Merged

alliepiper merged 1 commit into
NVIDIA:mainfrom
alliepiper:rdc_sm_update

Conversation

@alliepiper

Copy link
Copy Markdown
Contributor

No description provided.

@alliepiper
alliepiper requested a review from a team as a code owner March 24, 2025 18:47
@alliepiper
alliepiper requested a review from miscco March 24, 2025 18:47
@github-project-automation github-project-automation Bot moved this to Todo in CCCL Mar 24, 2025
@cccl-authenticator-app cccl-authenticator-app Bot moved this from Todo to In Review in CCCL Mar 24, 2025
@github-actions

Copy link
Copy Markdown
Contributor
ðŸŸĐ CI finished in 1h 37m: Pass: 100%/97 | Total: 2d 20h | Avg: 42m 28s | Max: 1h 23m | Hits: 77%/134019
  • ðŸŸĐ cub: Pass: 100%/45 | Total: 1d 20h | Avg: 58m 40s | Max: 1h 23m | Hits: 73%/53780

    ðŸŸĐ cpu
      ðŸŸĐ amd64              Pass: 100%/43  | Total:  1d 17h | Avg: 58m 21s | Max:  1h 23m | Hits:  74%/51336 
      ðŸŸĐ arm64              Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 05m | Hits:  67%/2444  
    ðŸŸĐ ctk
      ðŸŸĐ 12.0               Pass: 100%/5   | Total:  5h 24m | Avg:  1h 04m | Max:  1h 07m | Hits:  68%/5940  
      ðŸŸĐ 12.6               Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 11m | Hits:  64%/2260  
      ðŸŸĐ 12.8               Pass: 100%/38  | Total:  1d 12h | Avg: 57m 11s | Max:  1h 23m | Hits:  75%/45580 
    ðŸŸĐ cudacxx
      ðŸŸĐ ClangCUDA18        Pass: 100%/2   | Total:  2h 07m | Avg:  1h 03m | Max:  1h 06m | Hits:  74%/2108  
      ðŸŸĐ nvcc12.0           Pass: 100%/5   | Total:  5h 24m | Avg:  1h 04m | Max:  1h 07m | Hits:  68%/5940  
      ðŸŸĐ nvcc12.6           Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 11m | Hits:  64%/2260  
      ðŸŸĐ nvcc12.8           Pass: 100%/36  | Total:  1d 10h | Avg: 56m 49s | Max:  1h 23m | Hits:  75%/43472 
    ðŸŸĐ cudacxx_family
      ðŸŸĐ ClangCUDA          Pass: 100%/2   | Total:  2h 07m | Avg:  1h 03m | Max:  1h 06m | Hits:  74%/2108  
      ðŸŸĐ nvcc               Pass: 100%/43  | Total:  1d 17h | Avg: 58m 25s | Max:  1h 23m | Hits:  73%/51672 
    ðŸŸĐ cxx
      ðŸŸĐ Clang14            Pass: 100%/4   | Total:  4h 16m | Avg:  1h 04m | Max:  1h 07m | Hits:  68%/4896  
      ðŸŸĐ Clang15            Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 01m | Hits:  68%/2444  
      ðŸŸĐ Clang16            Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 07m | Hits:  68%/2444  
      ðŸŸĐ Clang17            Pass: 100%/2   | Total:  2h 09m | Avg:  1h 04m | Max:  1h 09m | Hits:  68%/2444  
      ðŸŸĐ Clang18            Pass: 100%/7   | Total:  6h 12m | Avg: 53m 15s | Max:  1h 09m | Hits:  79%/8218  
      ðŸŸĐ GCC7               Pass: 100%/2   | Total:  2h 12m | Avg:  1h 06m | Max:  1h 07m | Hits:  67%/2448  
      ðŸŸĐ GCC8               Pass: 100%/1   | Total:  1h 00m | Avg:  1h 00m | Max:  1h 00m | Hits:  67%/1224  
      ðŸŸĐ GCC9               Pass: 100%/2   | Total:  2h 06m | Avg:  1h 03m | Max:  1h 04m | Hits:  67%/2448  
      ðŸŸĐ GCC10              Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 07m | Hits:  67%/2448  
      ðŸŸĐ GCC11              Pass: 100%/2   | Total:  2h 18m | Avg:  1h 09m | Max:  1h 10m | Hits:  67%/2444  
      ðŸŸĐ GCC12              Pass: 100%/2   | Total:  2h 10m | Avg:  1h 05m | Max:  1h 07m | Hits:  67%/2444  
      ðŸŸĐ GCC13              Pass: 100%/11  | Total:  7h 45m | Avg: 42m 18s | Max:  1h 13m | Hits:  85%/13442 
      ðŸŸĐ MSVC14.29          Pass: 100%/2   | Total:  2h 24m | Avg:  1h 12m | Max:  1h 16m | Hits:  70%/2088  
      ðŸŸĐ MSVC14.42          Pass: 100%/2   | Total:  2h 38m | Avg:  1h 19m | Max:  1h 23m | Hits:  70%/2088  
      ðŸŸĐ NVHPC25.1          Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 11m | Hits:  64%/2260  
    ðŸŸĐ cxx_family
      ðŸŸĐ Clang              Pass: 100%/17  | Total: 16h 49m | Avg: 59m 23s | Max:  1h 09m | Hits:  72%/20446 
      ðŸŸĐ GCC                Pass: 100%/22  | Total: 19h 44m | Avg: 53m 50s | Max:  1h 13m | Hits:  76%/26898 
      ðŸŸĐ MSVC               Pass: 100%/4   | Total:  5h 03m | Avg:  1h 15m | Max:  1h 23m | Hits:  70%/4176  
      ðŸŸĐ NVHPC              Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 11m | Hits:  64%/2260  
    ðŸŸĐ gpu
      ðŸŸĐ h100               Pass: 100%/3   | Total:  1h 22m | Avg: 27m 21s | Max: 28m 05s | Hits:  89%/3666  
      ðŸŸĐ rtx2080            Pass: 100%/34  | Total:  1d 13h | Avg:  1h 06m | Max:  1h 23m | Hits:  68%/40338 
      ðŸŸĐ rtxa6000           Pass: 100%/8   | Total:  4h 48m | Avg: 36m 04s | Max:  1h 02m | Hits:  91%/9776  
    ðŸŸĐ jobs
      ðŸŸĐ Build              Pass: 100%/37  | Total:  1d 16h | Avg:  1h 05m | Max:  1h 23m | Hits:  68%/44004 
      ðŸŸĐ DeviceLaunch       Pass: 100%/1   | Total: 30m 01s | Avg: 30m 01s | Max: 30m 01s | Hits:  99%/1222  
      ðŸŸĐ GraphCapture       Pass: 100%/1   | Total: 25m 25s | Avg: 25m 25s | Max: 25m 25s | Hits:  99%/1222  
      ðŸŸĐ HostLaunch         Pass: 100%/3   | Total:  1h 29m | Avg: 29m 57s | Max: 32m 54s | Hits:  99%/3666  
      ðŸŸĐ TestGPU            Pass: 100%/3   | Total:  1h 14m | Avg: 24m 53s | Max: 27m 18s | Hits:  99%/3666  
    ðŸŸĐ sm
      ðŸŸĐ 90                 Pass: 100%/3   | Total:  1h 22m | Avg: 27m 21s | Max: 28m 05s | Hits:  89%/3666  
      ðŸŸĐ 90;90a;100         Pass: 100%/1   | Total:  1h 13m | Avg:  1h 13m | Max:  1h 13m | Hits:  67%/1222  
    ðŸŸĐ std
      ðŸŸĐ 17                 Pass: 100%/20  | Total: 22h 19m | Avg:  1h 06m | Max:  1h 16m | Hits:  68%/23662 
      ðŸŸĐ 20                 Pass: 100%/25  | Total: 21h 40m | Avg: 52m 01s | Max:  1h 23m | Hits:  78%/30118 
    
  • ðŸŸĐ thrust: Pass: 100%/45 | Total: 22h 53m | Avg: 30m 30s | Max: 58m 59s | Hits: 79%/79911

    ðŸŸĐ cmake_options
      ðŸŸĐ -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 40m 35s | Avg: 20m 17s | Max: 28m 37s | Hits:  88%/3554  
    ðŸŸĐ cpu
      ðŸŸĐ amd64              Pass: 100%/43  | Total: 21h 58m | Avg: 30m 39s | Max: 58m 59s | Hits:  79%/76358 
      ðŸŸĐ arm64              Pass: 100%/2   | Total: 55m 00s | Avg: 27m 30s | Max: 29m 29s | Hits:  77%/3553  
    ðŸŸĐ ctk
      ðŸŸĐ 12.0               Pass: 100%/5   | Total:  3h 02m | Avg: 36m 26s | Max: 54m 53s | Hits:  74%/8876  
      ðŸŸĐ 12.6               Pass: 100%/2   | Total:  1h 43m | Avg: 51m 54s | Max: 54m 29s | Hits:  65%/3552  
      ðŸŸĐ 12.8               Pass: 100%/38  | Total: 18h 07m | Avg: 28m 36s | Max: 58m 59s | Hits:  80%/67483 
    ðŸŸĐ cudacxx
      ðŸŸĐ ClangCUDA18        Pass: 100%/2   | Total: 52m 12s | Avg: 26m 06s | Max: 27m 17s | Hits:  77%/3552  
      ðŸŸĐ nvcc12.0           Pass: 100%/5   | Total:  3h 02m | Avg: 36m 26s | Max: 54m 53s | Hits:  74%/8876  
      ðŸŸĐ nvcc12.6           Pass: 100%/2   | Total:  1h 43m | Avg: 51m 54s | Max: 54m 29s | Hits:  65%/3552  
      ðŸŸĐ nvcc12.8           Pass: 100%/36  | Total: 17h 14m | Avg: 28m 44s | Max: 58m 59s | Hits:  80%/63931 
    ðŸŸĐ cudacxx_family
      ðŸŸĐ ClangCUDA          Pass: 100%/2   | Total: 52m 12s | Avg: 26m 06s | Max: 27m 17s | Hits:  77%/3552  
      ðŸŸĐ nvcc               Pass: 100%/43  | Total: 22h 00m | Avg: 30m 43s | Max: 58m 59s | Hits:  79%/76359 
    ðŸŸĐ cxx
      ðŸŸĐ Clang14            Pass: 100%/4   | Total:  1h 57m | Avg: 29m 21s | Max: 30m 41s | Hits:  77%/7104  
      ðŸŸĐ Clang15            Pass: 100%/2   | Total: 59m 52s | Avg: 29m 56s | Max: 31m 21s | Hits:  77%/3552  
      ðŸŸĐ Clang16            Pass: 100%/2   | Total: 59m 49s | Avg: 29m 54s | Max: 31m 06s | Hits:  77%/3552  
      ðŸŸĐ Clang17            Pass: 100%/2   | Total: 58m 51s | Avg: 29m 25s | Max: 30m 09s | Hits:  77%/3552  
      ðŸŸĐ Clang18            Pass: 100%/7   | Total:  2h 33m | Avg: 21m 54s | Max: 29m 28s | Hits:  83%/12432 
      ðŸŸĐ GCC7               Pass: 100%/2   | Total:  1h 05m | Avg: 32m 31s | Max: 34m 26s | Hits:  77%/3554  
      ðŸŸĐ GCC8               Pass: 100%/1   | Total: 30m 58s | Avg: 30m 58s | Max: 30m 58s | Hits:  77%/1777  
      ðŸŸĐ GCC9               Pass: 100%/2   | Total:  1h 05m | Avg: 32m 42s | Max: 34m 06s | Hits:  77%/3554  
      ðŸŸĐ GCC10              Pass: 100%/2   | Total:  1h 03m | Avg: 31m 47s | Max: 32m 54s | Hits:  77%/3554  
      ðŸŸĐ GCC11              Pass: 100%/2   | Total: 59m 37s | Avg: 29m 48s | Max: 29m 57s | Hits:  77%/3554  
      ðŸŸĐ GCC12              Pass: 100%/2   | Total:  1h 06m | Avg: 33m 20s | Max: 33m 38s | Hits:  77%/3554  
      ðŸŸĐ GCC13              Pass: 100%/10  | Total:  3h 39m | Avg: 21m 57s | Max: 33m 43s | Hits:  86%/17770 
      ðŸŸĐ MSVC14.29          Pass: 100%/2   | Total:  1h 47m | Avg: 53m 39s | Max: 54m 53s | Hits:  65%/3540  
      ðŸŸĐ MSVC14.42          Pass: 100%/3   | Total:  2h 21m | Avg: 47m 15s | Max: 58m 59s | Hits:  76%/5310  
      ðŸŸĐ NVHPC25.1          Pass: 100%/2   | Total:  1h 43m | Avg: 51m 54s | Max: 54m 29s | Hits:  65%/3552  
    ðŸŸĐ cxx_family
      ðŸŸĐ Clang              Pass: 100%/17  | Total:  7h 29m | Avg: 26m 25s | Max: 31m 21s | Hits:  79%/30192 
      ðŸŸĐ GCC                Pass: 100%/21  | Total:  9h 30m | Avg: 27m 11s | Max: 34m 26s | Hits:  81%/37317 
      ðŸŸĐ MSVC               Pass: 100%/5   | Total:  4h 09m | Avg: 49m 49s | Max: 58m 59s | Hits:  72%/8850  
      ðŸŸĐ NVHPC              Pass: 100%/2   | Total:  1h 43m | Avg: 51m 54s | Max: 54m 29s | Hits:  65%/3552  
    ðŸŸĐ gpu
      ðŸŸĐ h100               Pass: 100%/2   | Total: 31m 14s | Avg: 15m 37s | Max: 18m 43s | Hits:  88%/3554  
      ðŸŸĐ rtx2080            Pass: 100%/33  | Total: 18h 39m | Avg: 33m 55s | Max: 58m 59s | Hits:  75%/58604 
      ðŸŸĐ rtx4090            Pass: 100%/10  | Total:  3h 42m | Avg: 22m 13s | Max: 56m 22s | Hits:  89%/17753 
    ðŸŸĐ jobs
      ðŸŸĐ Build              Pass: 100%/38  | Total: 21h 22m | Avg: 33m 45s | Max: 58m 59s | Hits:  75%/67481 
      ðŸŸĐ TestCPU            Pass: 100%/3   | Total: 42m 26s | Avg: 14m 08s | Max: 26m 26s | Hits:  99%/5323  
      ðŸŸĐ TestGPU            Pass: 100%/4   | Total: 47m 56s | Avg: 11m 59s | Max: 12m 35s | Hits:  99%/7107  
    ðŸŸĐ sm
      ðŸŸĐ 90                 Pass: 100%/2   | Total: 31m 14s | Avg: 15m 37s | Max: 18m 43s | Hits:  88%/3554  
      ðŸŸĐ 90;90a;100         Pass: 100%/1   | Total: 33m 43s | Avg: 33m 43s | Max: 33m 43s | Hits:  77%/1777  
    ðŸŸĐ std
      ðŸŸĐ 17                 Pass: 100%/20  | Total: 11h 59m | Avg: 35m 57s | Max: 58m 59s | Hits:  74%/35511 
      ðŸŸĐ 20                 Pass: 100%/23  | Total: 10h 13m | Avg: 26m 40s | Max: 56m 22s | Hits:  82%/40846 
    
  • ðŸŸĐ stdpar: Pass: 100%/4 | Total: 17m 00s | Avg: 4m 15s | Max: 5m 09s

    ðŸŸĐ cpu
      ðŸŸĐ amd64              Pass: 100%/2   | Total: 10m 15s | Avg:  5m 07s | Max:  5m 09s
      ðŸŸĐ arm64              Pass: 100%/2   | Total:  6m 45s | Avg:  3m 22s | Max:  3m 25s
    ðŸŸĐ ctk
      ðŸŸĐ 12.6               Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ cudacxx
      ðŸŸĐ nvcc12.6           Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ cudacxx_family
      ðŸŸĐ nvcc               Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ cxx
      ðŸŸĐ NVHPC25.1          Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ cxx_family
      ðŸŸĐ NVHPC              Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ gpu
      ðŸŸĐ rtx2080            Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ jobs
      ðŸŸĐ Build              Pass: 100%/4   | Total: 17m 00s | Avg:  4m 15s | Max:  5m 09s
    ðŸŸĐ std
      ðŸŸĐ 17                 Pass: 100%/2   | Total:  8m 34s | Avg:  4m 17s | Max:  5m 09s
      ðŸŸĐ 20                 Pass: 100%/2   | Total:  8m 26s | Avg:  4m 13s | Max:  5m 06s
    
  • ðŸŸĐ cccl_c_parallel: Pass: 100%/2 | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits: 90%/328

    ðŸŸĐ cpu
      ðŸŸĐ amd64              Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ ctk
      ðŸŸĐ 12.8               Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ cudacxx
      ðŸŸĐ nvcc12.8           Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ cudacxx_family
      ðŸŸĐ nvcc               Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ cxx
      ðŸŸĐ GCC13              Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ cxx_family
      ðŸŸĐ GCC                Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ gpu
      ðŸŸĐ rtx2080            Pass: 100%/2   | Total: 20m 49s | Avg: 10m 24s | Max: 18m 12s | Hits:  90%/328   
    ðŸŸĐ jobs
      ðŸŸĐ Build              Pass: 100%/1   | Total:  2m 37s | Avg:  2m 37s | Max:  2m 37s | Hits:  81%/164   
      ðŸŸĐ Test               Pass: 100%/1   | Total: 18m 12s | Avg: 18m 12s | Max: 18m 12s | Hits:  98%/164   
    
  • ðŸŸĐ python: Pass: 100%/1 | Total: 1h 08m | Avg: 1h 08m | Max: 1h 08m

    ðŸŸĐ cpu
      ðŸŸĐ amd64              Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ ctk
      ðŸŸĐ 12.8               Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ cudacxx
      ðŸŸĐ nvcc12.8           Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ cudacxx_family
      ðŸŸĐ nvcc               Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ cxx
      ðŸŸĐ GCC13              Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ cxx_family
      ðŸŸĐ GCC                Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ gpu
      ðŸŸĐ rtx2080            Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    ðŸŸĐ jobs
      ðŸŸĐ Test               Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 97)

# Runner
68 linux-amd64-cpu16
9 windows-amd64-cpu16
6 linux-arm64-cpu16
6 linux-amd64-gpu-rtxa6000-latest-1
3 linux-amd64-gpu-h100-latest-1
3 linux-amd64-gpu-rtx4090-latest-1
2 linux-amd64-gpu-rtx2080-latest-1

@alliepiper
alliepiper merged commit 92b1d28 into NVIDIA:main Mar 24, 2025
@github-project-automation github-project-automation Bot moved this from In Review to Done in CCCL Mar 24, 2025
@alliepiper
alliepiper deleted the rdc_sm_update branch March 24, 2025 20:29
caugonnet pushed a commit to caugonnet/cccl that referenced this pull request Mar 25, 2025
caugonnet added a commit that referenced this pull request Mar 26, 2025
* Enable NVHPC in CUDASTF CI

* Use nvtx_range in the POTRI example

* no need to include nvtx3 anymore here

* Do not use nvtx3 directly

* fix compilation

* WIP: try to pass the type of the execution place to the parallel_for_scope

* pass the exec_place type to parallel_for_scope

* remove a device annotation for a host only lambda

* is_shape_of_v is not working

* experiment to see if we can avoid generating device code in parallel_for with a host place

* fixes for a previous conflict merge

* disable an invalid test

* better typing for ctx.parallel_for with a partition

* use ::std and more types for parallel_for

* Add transform c parallel implementation (#4048)

* Enable setting _CUB_HAS_TRANSFORM_UBLKCP as flag

* Stale comment

* Update make_kernel_user_binary_operator to accept lhs/rhs types

* Add transform c.parallel implementation

* Add tests for c.parallel transform

* Use launcher factory to query ptx version

* Refactor how we get iterator names

* Add comment explaining why we need -default-device

* Address remaining review feedback

* Undo change to make_iterator_kernel_arg

* Restore the comment

* Restore comment

---------

Co-authored-by: Ashwin Srinath <shwina@users.noreply.github.com>

* Drop duplicated system header blocks (#4245)

Those were accidentally duplicated

* Exclude sm101 from RDC testing. (#4247)

* Make `cuda::stream_ref` constructible on device (#4243)

* Make `cuda::stream_ref` constructible on device

There is no reason we should not be able to construct it or extract the pointer out of it on device.

* Pass by value

* Make nvbench work

* Fix logic in test_segmented_reduce (#4198)

* Fix logic in test_segmented_reduce, also test over different types of offsets

To resolve gh-4197, use `cupy.cumsum` to accumulate over random partition
sizes to form correct offsets sequence.

Add assertions to verify that `offsets` is a non-decreasing sequence, and
that its last element equals the size of the input array.

Perform the test for several plausible offset data types.

* Changes per PR review comments

1. Use `cupy.random` to draw random sample on GPU, rather than on CPU
   followed by a transfer
2. Use `cp.empty` to allocate output, rather than `cp.zeros`

* Add new `WarpReduce` overloadings (#3884)

Co-authored-by: Bernhard Manfred Gruber <bernhardmgruber@gmail.com>

* Fix #4250 (#4251)

* Refactor fp masks (#4246)

* Implement `views::all` (#4244)

* Implement `views::all`

* [cudax] incorporate P3557 (constexpr completion signatures) into Âĩstdex (#3841)

* incorporate P3557 (constexpr completion signatures) into ustdex

* remove the need for nvcc-specific workarounds

* review feedback

* tweaks to ustdex for clangd

* fix typo

* use concepts portability macros for C++17 support

* Add fixed size segmented reduce (#3969)

* Adds fixed size segmented reduce

* remove unnecessary changes

* revert changes

* Properly deal with parallel_for overloads with grids, add an is_host() for exec_place

* Remove test doing illegal things, and which is not really useful anymore

---------

Co-authored-by: Ashwin Srinath <3190405+shwina@users.noreply.github.com>
Co-authored-by: Ashwin Srinath <shwina@users.noreply.github.com>
Co-authored-by: Michael Schellenberger Costa <miscco@nvidia.com>
Co-authored-by: Allison Piper <alliepiper16@gmail.com>
Co-authored-by: Oleksandr Pavlyk <21087696+oleksandr-pavlyk@users.noreply.github.com>
Co-authored-by: Federico Busato <50413820+fbusato@users.noreply.github.com>
Co-authored-by: Bernhard Manfred Gruber <bernhardmgruber@gmail.com>
Co-authored-by: David Bayer <48736217+davebayer@users.noreply.github.com>
Co-authored-by: Eric Niebler <eniebler@nvidia.com>
Co-authored-by: Srinivas Yadav <43375352+srinivasyadav18@users.noreply.github.com>
davebayer pushed a commit to davebayer/cccl that referenced this pull request Apr 7, 2025
davebayer added a commit to davebayer/cccl that referenced this pull request Apr 7, 2025
* Enable NVHPC in CUDASTF CI

* Use nvtx_range in the POTRI example

* no need to include nvtx3 anymore here

* Do not use nvtx3 directly

* fix compilation

* WIP: try to pass the type of the execution place to the parallel_for_scope

* pass the exec_place type to parallel_for_scope

* remove a device annotation for a host only lambda

* is_shape_of_v is not working

* experiment to see if we can avoid generating device code in parallel_for with a host place

* fixes for a previous conflict merge

* disable an invalid test

* better typing for ctx.parallel_for with a partition

* use ::std and more types for parallel_for

* Add transform c parallel implementation (NVIDIA#4048)

* Enable setting _CUB_HAS_TRANSFORM_UBLKCP as flag

* Stale comment

* Update make_kernel_user_binary_operator to accept lhs/rhs types

* Add transform c.parallel implementation

* Add tests for c.parallel transform

* Use launcher factory to query ptx version

* Refactor how we get iterator names

* Add comment explaining why we need -default-device

* Address remaining review feedback

* Undo change to make_iterator_kernel_arg

* Restore the comment

* Restore comment

---------

Co-authored-by: Ashwin Srinath <shwina@users.noreply.github.com>

* Drop duplicated system header blocks (NVIDIA#4245)

Those were accidentally duplicated

* Exclude sm101 from RDC testing. (NVIDIA#4247)

* Make `cuda::stream_ref` constructible on device (NVIDIA#4243)

* Make `cuda::stream_ref` constructible on device

There is no reason we should not be able to construct it or extract the pointer out of it on device.

* Pass by value

* Make nvbench work

* Fix logic in test_segmented_reduce (NVIDIA#4198)

* Fix logic in test_segmented_reduce, also test over different types of offsets

To resolve NVIDIAgh-4197, use `cupy.cumsum` to accumulate over random partition
sizes to form correct offsets sequence.

Add assertions to verify that `offsets` is a non-decreasing sequence, and
that its last element equals the size of the input array.

Perform the test for several plausible offset data types.

* Changes per PR review comments

1. Use `cupy.random` to draw random sample on GPU, rather than on CPU
   followed by a transfer
2. Use `cp.empty` to allocate output, rather than `cp.zeros`

* Add new `WarpReduce` overloadings (NVIDIA#3884)

Co-authored-by: Bernhard Manfred Gruber <bernhardmgruber@gmail.com>

* Fix NVIDIA#4250 (NVIDIA#4251)

* Refactor fp masks (NVIDIA#4246)

* Implement `views::all` (NVIDIA#4244)

* Implement `views::all`

* [cudax] incorporate P3557 (constexpr completion signatures) into Âĩstdex (NVIDIA#3841)

* incorporate P3557 (constexpr completion signatures) into ustdex

* remove the need for nvcc-specific workarounds

* review feedback

* tweaks to ustdex for clangd

* fix typo

* use concepts portability macros for C++17 support

* Add fixed size segmented reduce (NVIDIA#3969)

* Adds fixed size segmented reduce

* remove unnecessary changes

* revert changes

* Properly deal with parallel_for overloads with grids, add an is_host() for exec_place

* Remove test doing illegal things, and which is not really useful anymore

---------

Co-authored-by: Ashwin Srinath <3190405+shwina@users.noreply.github.com>
Co-authored-by: Ashwin Srinath <shwina@users.noreply.github.com>
Co-authored-by: Michael Schellenberger Costa <miscco@nvidia.com>
Co-authored-by: Allison Piper <alliepiper16@gmail.com>
Co-authored-by: Oleksandr Pavlyk <21087696+oleksandr-pavlyk@users.noreply.github.com>
Co-authored-by: Federico Busato <50413820+fbusato@users.noreply.github.com>
Co-authored-by: Bernhard Manfred Gruber <bernhardmgruber@gmail.com>
Co-authored-by: David Bayer <48736217+davebayer@users.noreply.github.com>
Co-authored-by: Eric Niebler <eniebler@nvidia.com>
Co-authored-by: Srinivas Yadav <43375352+srinivasyadav18@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

2 participants