Skip to content

Conversation

@bernhardmgruber
Copy link
Contributor

@bernhardmgruber bernhardmgruber commented Feb 24, 2025

Split out of #3821. Contains changes related to radix sort and the computation of compile-time constants. Also some changes in the tests are added, since they cannot change CUB's performance.

  • No SASS diff for cub.test.device_radix_sort_pairs.lid_0 on SM86

@bernhardmgruber bernhardmgruber requested review from a team as code owners February 24, 2025 19:11
@bernhardmgruber bernhardmgruber changed the title Ref radix min max Replace CUB macros in more places Feb 24, 2025
int num_bits = CUB_MIN(RADIX_BITS, end_bit - current_bit);
// FIXME(bgruber): the following replacement changes SASS for cub.test.device_radix_sort_pairs.lid_0
// int num_bits = _CUDA_VSTD::min(+RADIX_BITS, end_bit - current_bit);
int num_bits = CUB_MIN(+RADIX_BITS, end_bit - current_bit);
Copy link
Contributor

@miscco miscco Feb 24, 2025

Choose a reason for hiding this comment

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

I am really curious about why we need +RADIX_BITS, it should already be an int and so are end_bit and current_bit

What does this do?

Suggested change
int num_bits = CUB_MIN(+RADIX_BITS, end_bit - current_bit);
const int num_bits = _CUDA_VSTD::min<int>(RADIX_BITS, end_bit - current_bit);

Copy link
Contributor Author

Choose a reason for hiding this comment

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

The unary plus is needed to produce a pr-value. Otherwise, RADIX_BITS is ODR-used. With your code I get:

error: identifier "cub::CUB_300000_SM_860::detail::radix_sort::AgentRadixSortHistogram< ::cub::CUB_300000_SM_860::AgentRadixSortHistogramPolicy<(int)128, (int)16, (int)1, unsigned int, (int)8> , (bool)1, unsigned int, unsigned int,  ::cub::CUB_300000_SM_860::detail::identity_decomposer_t> ::RADIX_BITS" is undefined in device code

Copy link
Contributor

Choose a reason for hiding this comment

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

This is genius

Copy link
Contributor Author

Choose a reason for hiding this comment

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

This is genius

It's just fighting C++ with C++.

@github-actions
Copy link
Contributor

🟨 CI finished in 1h 41m: Pass: 98%/93 | Total: 2d 14h | Avg: 40m 32s | Max: 1h 23m | Hits: 69%/133775
  • 🟨 cccl_c_parallel: Pass: 50%/2 | Total: 15m 46s | Avg: 7m 53s | Max: 13m 16s | Hits: 96%/154

    🚨 jobs: Test 🚨
      🟩 Build              Pass: 100%/1   | Total:  2m 30s | Avg:  2m 30s | Max:  2m 30s | Hits:  96%/154   
      🔥 Test               Pass:   0%/1   | Total: 13m 16s | Avg: 13m 16s | Max: 13m 16s
    🟨 cpu
      🟨 amd64              Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 ctk
      🟨 12.8               Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 cudacxx
      🟨 nvcc12.8           Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 cudacxx_family
      🟨 nvcc               Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 cxx
      🟨 GCC13              Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 cxx_family
      🟨 GCC                Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    🟨 gpu
      🟨 rtx2080            Pass:  50%/2   | Total: 15m 46s | Avg:  7m 53s | Max: 13m 16s | Hits:  96%/154   
    
  • 🟩 cub: Pass: 100%/45 | Total: 1d 16h | Avg: 54m 08s | Max: 1h 23m | Hits: 53%/53485

    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total:  1d 14h | Avg: 53m 47s | Max:  1h 23m | Hits:  54%/51055 
      🟩 arm64              Pass: 100%/2   | Total:  2h 03m | Avg:  1h 01m | Max:  1h 02m | Hits:  46%/2430  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  5h 01m | Avg:  1h 00m | Max:  1h 04m | Hits:  41%/5908  
      🟩 12.5               Pass: 100%/2   | Total:  2h 21m | Avg:  1h 10m | Max:  1h 13m | Hits:  45%/2248  
      🟩 12.8               Pass: 100%/38  | Total:  1d 09h | Avg: 52m 28s | Max:  1h 23m | Hits:  56%/45329 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m | Hits:  49%/2100  
      🟩 nvcc12.0           Pass: 100%/5   | Total:  5h 01m | Avg:  1h 00m | Max:  1h 04m | Hits:  41%/5908  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  2h 21m | Avg:  1h 10m | Max:  1h 13m | Hits:  45%/2248  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  1d 07h | Avg: 51m 49s | Max:  1h 23m | Hits:  56%/43229 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  2h 08m | Avg:  1h 04m | Max:  1h 05m | Hits:  49%/2100  
      🟩 nvcc               Pass: 100%/43  | Total:  1d 14h | Avg: 53m 40s | Max:  1h 23m | Hits:  54%/51385 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  3h 51m | Avg: 57m 48s | Max:  1h 01m | Hits:  47%/4868  
      🟩 Clang15            Pass: 100%/2   | Total:  1h 54m | Avg: 57m 18s | Max: 58m 22s | Hits:  47%/2430  
      🟩 Clang16            Pass: 100%/2   | Total:  1h 56m | Avg: 58m 11s | Max: 59m 59s | Hits:  47%/2430  
      🟩 Clang17            Pass: 100%/2   | Total:  1h 53m | Avg: 56m 50s | Max: 56m 58s | Hits:  47%/2430  
      🟩 Clang18            Pass: 100%/7   | Total:  5h 52m | Avg: 50m 25s | Max:  1h 05m | Hits:  63%/8175  
      🟩 GCC7               Pass: 100%/2   | Total:  1h 55m | Avg: 57m 31s | Max: 57m 53s | Hits:  46%/2434  
      🟩 GCC8               Pass: 100%/1   | Total:  1h 00m | Avg:  1h 00m | Max:  1h 00m | Hits:  46%/1217  
      🟩 GCC9               Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 02m | Hits:  46%/2434  
      🟩 GCC10              Pass: 100%/2   | Total:  1h 59m | Avg: 59m 45s | Max:  1h 00m | Hits:  46%/2434  
      🟩 GCC11              Pass: 100%/2   | Total:  2h 02m | Avg:  1h 01m | Max:  1h 03m | Hits:  46%/2430  
      🟩 GCC12              Pass: 100%/2   | Total:  2h 06m | Avg:  1h 03m | Max:  1h 03m | Hits:  46%/2430  
      🟩 GCC13              Pass: 100%/11  | Total:  6h 39m | Avg: 36m 16s | Max:  1h 04m | Hits:  75%/13365 
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 27m | Avg:  1h 13m | Max:  1h 23m | Hits:  12%/2080  
      🟩 MSVC14.42          Pass: 100%/2   | Total:  2h 35m | Avg:  1h 17m | Max:  1h 21m | Hits:  12%/2080  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  2h 21m | Avg:  1h 10m | Max:  1h 13m | Hits:  45%/2248  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total: 15h 28m | Avg: 54m 38s | Max:  1h 05m | Hits:  53%/20333 
      🟩 GCC                Pass: 100%/22  | Total: 17h 43m | Avg: 48m 19s | Max:  1h 04m | Hits:  61%/26744 
      🟩 MSVC               Pass: 100%/4   | Total:  5h 03m | Avg:  1h 15m | Max:  1h 23m | Hits:  12%/4160  
      🟩 NVHPC              Pass: 100%/2   | Total:  2h 21m | Avg:  1h 10m | Max:  1h 13m | Hits:  45%/2248  
    🟩 gpu
      🟩 h100               Pass: 100%/3   | Total:  1h 09m | Avg: 23m 09s | Max: 24m 56s | Hits:  82%/3645  
      🟩 rtx2080            Pass: 100%/34  | Total:  1d 11h | Avg:  1h 02m | Max:  1h 23m | Hits:  43%/40120 
      🟩 rtxa6000           Pass: 100%/8   | Total:  4h 10m | Avg: 31m 16s | Max:  1h 01m | Hits:  86%/9720  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total:  1d 13h | Avg:  1h 01m | Max:  1h 23m | Hits:  43%/43765 
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 22m 34s | Avg: 22m 34s | Max: 22m 34s | Hits:  99%/1215  
      🟩 GraphCapture       Pass: 100%/1   | Total: 17m 18s | Avg: 17m 18s | Max: 17m 18s | Hits:  99%/1215  
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 08m | Avg: 22m 48s | Max: 23m 08s | Hits:  99%/3645  
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 03m | Avg: 21m 12s | Max: 21m 38s | Hits:  99%/3645  
    🟩 sm
      🟩 90                 Pass: 100%/3   | Total:  1h 09m | Avg: 23m 09s | Max: 24m 56s | Hits:  82%/3645  
      🟩 90;90a;100         Pass: 100%/1   | Total:  1h 04m | Avg:  1h 04m | Max:  1h 04m | Hits:  46%/1215  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 20h 36m | Avg:  1h 01m | Max:  1h 23m | Hits:  42%/23535 
      🟩 20                 Pass: 100%/25  | Total: 19h 59m | Avg: 47m 59s | Max:  1h 21m | Hits:  62%/29950 
    
  • 🟩 thrust: Pass: 100%/45 | Total: 21h 18m | Avg: 28m 24s | Max: 56m 34s | Hits: 79%/80136

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 35m 28s | Avg: 17m 44s | Max: 24m 17s | Hits:  89%/3564  
    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total: 20h 27m | Avg: 28m 32s | Max: 56m 34s | Hits:  79%/76573 
      🟩 arm64              Pass: 100%/2   | Total: 50m 44s | Avg: 25m 22s | Max: 26m 23s | Hits:  79%/3563  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  2h 40m | Avg: 32m 05s | Max: 45m 43s | Hits:  74%/8901  
      🟩 12.5               Pass: 100%/2   | Total:  1h 38m | Avg: 49m 08s | Max: 50m 53s | Hits:  72%/3562  
      🟩 12.8               Pass: 100%/38  | Total: 16h 59m | Avg: 26m 49s | Max: 56m 34s | Hits:  80%/67673 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 46m 37s | Avg: 23m 18s | Max: 24m 13s | Hits:  79%/3562  
      🟩 nvcc12.0           Pass: 100%/5   | Total:  2h 40m | Avg: 32m 05s | Max: 45m 43s | Hits:  74%/8901  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 38m | Avg: 49m 08s | Max: 50m 53s | Hits:  72%/3562  
      🟩 nvcc12.8           Pass: 100%/36  | Total: 16h 12m | Avg: 27m 01s | Max: 56m 34s | Hits:  80%/64111 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 46m 37s | Avg: 23m 18s | Max: 24m 13s | Hits:  79%/3562  
      🟩 nvcc               Pass: 100%/43  | Total: 20h 31m | Avg: 28m 38s | Max: 56m 34s | Hits:  79%/76574 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  1h 56m | Avg: 29m 10s | Max: 32m 55s | Hits:  79%/7124  
      🟩 Clang15            Pass: 100%/2   | Total: 53m 11s | Avg: 26m 35s | Max: 27m 07s | Hits:  79%/3562  
      🟩 Clang16            Pass: 100%/2   | Total: 59m 50s | Avg: 29m 55s | Max: 30m 41s | Hits:  79%/3562  
      🟩 Clang17            Pass: 100%/2   | Total: 55m 16s | Avg: 27m 38s | Max: 27m 45s | Hits:  79%/3562  
      🟩 Clang18            Pass: 100%/7   | Total:  2h 25m | Avg: 20m 46s | Max: 29m 03s | Hits:  85%/12467 
      🟩 GCC7               Pass: 100%/2   | Total: 55m 41s | Avg: 27m 50s | Max: 29m 20s | Hits:  79%/3564  
      🟩 GCC8               Pass: 100%/1   | Total: 27m 35s | Avg: 27m 35s | Max: 27m 35s | Hits:  79%/1782  
      🟩 GCC9               Pass: 100%/2   | Total: 56m 35s | Avg: 28m 17s | Max: 29m 38s | Hits:  79%/3564  
      🟩 GCC10              Pass: 100%/2   | Total: 58m 08s | Avg: 29m 04s | Max: 31m 03s | Hits:  79%/3564  
      🟩 GCC11              Pass: 100%/2   | Total: 56m 47s | Avg: 28m 23s | Max: 30m 10s | Hits:  79%/3564  
      🟩 GCC12              Pass: 100%/2   | Total: 56m 14s | Avg: 28m 07s | Max: 28m 26s | Hits:  79%/3564  
      🟩 GCC13              Pass: 100%/10  | Total:  3h 16m | Avg: 19m 36s | Max: 31m 12s | Hits:  87%/17820 
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 39m | Avg: 49m 32s | Max: 53m 21s | Hits:  55%/3550  
      🟩 MSVC14.42          Pass: 100%/3   | Total:  2h 23m | Avg: 47m 51s | Max: 56m 34s | Hits:  60%/5325  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 38m | Avg: 49m 08s | Max: 50m 53s | Hits:  72%/3562  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  7h 10m | Avg: 25m 18s | Max: 32m 55s | Hits:  81%/30277 
      🟩 GCC                Pass: 100%/21  | Total:  8h 27m | Avg: 24m 08s | Max: 31m 12s | Hits:  83%/37422 
      🟩 MSVC               Pass: 100%/5   | Total:  4h 02m | Avg: 48m 31s | Max: 56m 34s | Hits:  58%/8875  
      🟩 NVHPC              Pass: 100%/2   | Total:  1h 38m | Avg: 49m 08s | Max: 50m 53s | Hits:  72%/3562  
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 26m 01s | Avg: 13m 00s | Max: 15m 19s | Hits:  89%/3564  
      🟩 rtx2080            Pass: 100%/33  | Total: 17h 15m | Avg: 31m 23s | Max: 56m 34s | Hits:  76%/58769 
      🟩 rtx4090            Pass: 100%/10  | Total:  3h 36m | Avg: 21m 39s | Max: 55m 55s | Hits:  86%/17803 
    🟩 jobs
      🟩 Build              Pass: 100%/38  | Total: 19h 49m | Avg: 31m 18s | Max: 56m 34s | Hits:  76%/67671 
      🟩 TestCPU            Pass: 100%/3   | Total: 46m 52s | Avg: 15m 37s | Max: 31m 06s | Hits:  90%/5338  
      🟩 TestGPU            Pass: 100%/4   | Total: 41m 48s | Avg: 10m 27s | Max: 11m 11s | Hits:  99%/7127  
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 26m 01s | Avg: 13m 00s | Max: 15m 19s | Hits:  89%/3564  
      🟩 90;90a;100         Pass: 100%/1   | Total: 31m 12s | Avg: 31m 12s | Max: 31m 12s | Hits:  79%/1782  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 10h 47m | Avg: 32m 21s | Max: 56m 34s | Hits:  75%/35611 
      🟩 20                 Pass: 100%/23  | Total:  9h 55m | Avg: 25m 53s | Max: 55m 55s | Hits:  81%/40961 
    
  • 🟩 python: Pass: 100%/1 | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 ctk
      🟩 12.8               Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 40m 16s | Avg: 40m 16s | Max: 40m 16s
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 93)

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


// Always at least one lane
LOG_COUNTER_LANES = CUB_MAX((int(RADIX_BITS) - int(LOG_PACKING_RATIO)), 0),
LOG_COUNTER_LANES = _CUDA_VSTD::max((int(RADIX_BITS) - int(LOG_PACKING_RATIO)), 0),
Copy link
Contributor

Choose a reason for hiding this comment

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

suggestion: max<int>()

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I have been told by my mentor @MFHava a long time ago that I should not specialize function templates, but rely on overloading and template argument deduction. I follow this whenever easily possible. I don't know the rational though. But I don't see a benefit of providing the template argument explicitly here.

Copy link
Contributor

Choose a reason for hiding this comment

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

I'm also siding on using implicit template arguments.

bool is_num_passes_odd = num_passes & 1;
int max_alt_passes = (num_passes * radix_bits) - num_bits;
int alt_end_bit = CUB_MIN(end_bit, begin_bit + (max_alt_passes * alt_radix_bits));
int alt_end_bit = _CUDA_VSTD::min(end_bit, begin_bit + (max_alt_passes * alt_radix_bits));
Copy link
Contributor

Choose a reason for hiding this comment

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

to have more uniform code, should we use _CUDA_VSTD everywhere?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

That's a question for @miscco. I personally have an easier time remembering ::cuda::std.

Copy link
Contributor

Choose a reason for hiding this comment

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

using the macro is technically a bit safer because that also includes our inline ABI namespace which could in theory avoid ambiguities

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Hmm. I can try and use it more often. However, we should probably not use it in any interface, since we don't it to pop up in the documentation.

Copy link
Contributor

Choose a reason for hiding this comment

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

Would be great to agree on one way to handle this and follow that throughout. Given @miscco suggestion, I think we want to use _CUDA_VSTD within our implementation and then use ::cuda::std within interfaces?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Whatever we come up with, let's document the decision here: #2635

@bernhardmgruber bernhardmgruber requested a review from a team as a code owner February 25, 2025 09:38
@github-actions
Copy link
Contributor

🟨 CI finished in 51m 35s: Pass: 48%/93 | Total: 14h 50m | Avg: 9m 34s | Max: 50m 17s | Hits: 92%/51280
  • 🟨 thrust: Pass: 4%/45 | Total: 5h 30m | Avg: 7m 20s | Max: 27m 00s | Hits: 99%/3562

    🚨 cudacxx_family: nvcc 🚨
      🟩 ClangCUDA          Pass: 100%/2   | Total: 11m 21s | Avg:  5m 40s | Max:  5m 51s | Hits:  99%/3562  
      🔥 nvcc               Pass:   0%/43  | Total:  5h 18m | Avg:  7m 24s | Max: 27m 00s
    🟨 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 11m 21s | Avg:  5m 40s | Max:  5m 51s | Hits:  99%/3562  
      🟥 nvcc12.0           Pass:   0%/5   | Total: 48m 58s | Avg:  9m 47s | Max: 25m 33s
      🟥 nvcc12.5           Pass:   0%/2   | Total: 23m 10s | Avg: 11m 35s | Max: 11m 45s
      🟥 nvcc12.8           Pass:   0%/36  | Total:  4h 06m | Avg:  6m 51s | Max: 27m 00s
    🟥 cmake_options
      🟥 -DTHRUST_DISPATCH_TYPE=Force32bit Pass:   0%/2   | Total:  6m 23s | Avg:  3m 11s | Max:  6m 23s
    🟨 cpu
      🟨 amd64              Pass:   4%/43  | Total:  5h 17m | Avg:  7m 22s | Max: 27m 00s | Hits:  99%/3562  
      🟥 arm64              Pass:   0%/2   | Total: 12m 56s | Avg:  6m 28s | Max:  6m 44s
    🟨 ctk
      🟥 12.0               Pass:   0%/5   | Total: 48m 58s | Avg:  9m 47s | Max: 25m 33s
      🟥 12.5               Pass:   0%/2   | Total: 23m 10s | Avg: 11m 35s | Max: 11m 45s
      🟨 12.8               Pass:   5%/38  | Total:  4h 18m | Avg:  6m 47s | Max: 27m 00s | Hits:  99%/3562  
    🟨 cxx
      🟥 Clang14            Pass:   0%/4   | Total: 24m 35s | Avg:  6m 08s | Max:  6m 56s
      🟥 Clang15            Pass:   0%/2   | Total: 12m 51s | Avg:  6m 25s | Max:  6m 35s
      🟥 Clang16            Pass:   0%/2   | Total: 13m 00s | Avg:  6m 30s | Max:  6m 38s
      🟥 Clang17            Pass:   0%/2   | Total: 12m 56s | Avg:  6m 28s | Max:  6m 30s
      🟨 Clang18            Pass:  28%/7   | Total: 30m 06s | Avg:  4m 18s | Max:  6m 22s | Hits:  99%/3562  
      🟥 GCC7               Pass:   0%/2   | Total: 12m 03s | Avg:  6m 01s | Max:  6m 13s
      🟥 GCC8               Pass:   0%/1   | Total:  6m 02s | Avg:  6m 02s | Max:  6m 02s
      🟥 GCC9               Pass:   0%/2   | Total: 13m 05s | Avg:  6m 32s | Max:  6m 44s
      🟥 GCC10              Pass:   0%/2   | Total: 13m 08s | Avg:  6m 34s | Max:  6m 55s
      🟥 GCC11              Pass:   0%/2   | Total: 13m 37s | Avg:  6m 48s | Max:  7m 22s
      🟥 GCC12              Pass:   0%/2   | Total: 13m 34s | Avg:  6m 47s | Max:  7m 09s
      🟥 GCC13              Pass:   0%/10  | Total: 38m 45s | Avg:  3m 52s | Max:  7m 36s
      🟥 MSVC14.29          Pass:   0%/2   | Total: 49m 50s | Avg: 24m 55s | Max: 25m 33s
      🟥 MSVC14.42          Pass:   0%/3   | Total: 53m 27s | Avg: 17m 49s | Max: 27m 00s
      🟥 NVHPC24.7          Pass:   0%/2   | Total: 23m 10s | Avg: 11m 35s | Max: 11m 45s
    🟨 cxx_family
      🟨 Clang              Pass:  11%/17  | Total:  1h 33m | Avg:  5m 29s | Max:  6m 56s | Hits:  99%/3562  
      🟥 GCC                Pass:   0%/21  | Total:  1h 50m | Avg:  5m 14s | Max:  7m 36s
      🟥 MSVC               Pass:   0%/5   | Total:  1h 43m | Avg: 20m 39s | Max: 27m 00s
      🟥 NVHPC              Pass:   0%/2   | Total: 23m 10s | Avg: 11m 35s | Max: 11m 45s
    🟨 gpu
      🟥 h100               Pass:   0%/2   | Total:  4m 33s | Avg:  2m 16s | Max:  4m 33s
      🟨 rtx2080            Pass:   6%/33  | Total:  4h 38m | Avg:  8m 25s | Max: 26m 27s | Hits:  99%/3562  
      🟥 rtx4090            Pass:   0%/10  | Total: 47m 21s | Avg:  4m 44s | Max: 27m 00s
    🟨 jobs
      🟨 Build              Pass:   5%/38  | Total:  5h 30m | Avg:  8m 41s | Max: 27m 00s | Hits:  99%/3562  
      🟥 TestCPU            Pass:   0%/3  
      🟥 TestGPU            Pass:   0%/4  
    🟥 sm
      🟥 90                 Pass:   0%/2   | Total:  4m 33s | Avg:  2m 16s | Max:  4m 33s
      🟥 90;90a;100         Pass:   0%/1   | Total:  6m 23s | Avg:  6m 23s | Max:  6m 23s
    🟨 std
      🟨 17                 Pass:   5%/20  | Total:  3h 11m | Avg:  9m 33s | Max: 26m 27s | Hits:  99%/1781  
      🟨 20                 Pass:   4%/23  | Total:  2h 12m | Avg:  5m 46s | Max: 27m 00s | Hits:  99%/1781  
    
  • 🟨 cub: Pass: 88%/45 | Total: 8h 15m | Avg: 11m 00s | Max: 32m 42s | Hits: 92%/47410

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  88%/43  | Total:  8h 04m | Avg: 11m 15s | Max: 32m 42s | Hits:  92%/44980 
      🟩 arm64              Pass: 100%/2   | Total: 10m 54s | Avg:  5m 27s | Max:  5m 45s | Hits:  99%/2430  
    🔍 ctk: 12.8 🔍
      🟩 12.0               Pass: 100%/5   | Total: 50m 44s | Avg: 10m 08s | Max: 28m 49s | Hits:  85%/5908  
      🟩 12.5               Pass: 100%/2   | Total: 19m 24s | Avg:  9m 42s | Max:  9m 57s | Hits:  98%/2248  
      🔍 12.8               Pass:  86%/38  | Total:  7h 05m | Avg: 11m 11s | Max: 32m 42s | Hits:  93%/39254 
    🔍 cudacxx: nvcc12.8 🔍
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 53s | Avg:  4m 56s | Max:  4m 59s | Hits: 100%/2100  
      🟩 nvcc12.0           Pass: 100%/5   | Total: 50m 44s | Avg: 10m 08s | Max: 28m 49s | Hits:  85%/5908  
      🟩 nvcc12.5           Pass: 100%/2   | Total: 19m 24s | Avg:  9m 42s | Max:  9m 57s | Hits:  98%/2248  
      🔍 nvcc12.8           Pass:  86%/36  | Total:  6h 55m | Avg: 11m 32s | Max: 32m 42s | Hits:  92%/37154 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 53s | Avg:  4m 56s | Max:  4m 59s | Hits: 100%/2100  
      🔍 nvcc               Pass:  88%/43  | Total:  8h 05m | Avg: 11m 17s | Max: 32m 42s | Hits:  92%/45310 
    🔍 sm: 90 🔍
      🔍 90                 Pass:  66%/3   | Total: 51m 06s | Avg: 17m 02s | Max: 23m 07s | Hits:  99%/2430  
      🟩 90;90a;100         Pass: 100%/1   | Total:  6m 56s | Avg:  6m 56s | Max:  6m 56s | Hits:  99%/1215  
    🔍 std: 20 🔍
      🟩 17                 Pass: 100%/20  | Total:  3h 13m | Avg:  9m 39s | Max: 30m 02s | Hits:  88%/23535 
      🔍 20                 Pass:  80%/25  | Total:  5h 02m | Avg: 12m 05s | Max: 32m 42s | Hits:  96%/23875 
    🟨 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 22m 40s | Avg:  5m 40s | Max:  6m 11s | Hits: 100%/4868  
      🟩 Clang15            Pass: 100%/2   | Total: 12m 43s | Avg:  6m 21s | Max:  6m 29s | Hits: 100%/2430  
      🟩 Clang16            Pass: 100%/2   | Total: 12m 28s | Avg:  6m 14s | Max:  6m 22s | Hits: 100%/2430  
      🟩 Clang17            Pass: 100%/2   | Total: 12m 05s | Avg:  6m 02s | Max:  6m 12s | Hits: 100%/2430  
      🟨 Clang18            Pass:  85%/7   | Total:  1h 08m | Avg:  9m 49s | Max: 22m 24s | Hits: 100%/6960  
      🟩 GCC7               Pass: 100%/2   | Total: 11m 13s | Avg:  5m 36s | Max:  5m 55s | Hits:  99%/2434  
      🟩 GCC8               Pass: 100%/1   | Total:  6m 08s | Avg:  6m 08s | Max:  6m 08s | Hits:  99%/1217  
      🟩 GCC9               Pass: 100%/2   | Total: 12m 05s | Avg:  6m 02s | Max:  6m 09s | Hits:  99%/2434  
      🟩 GCC10              Pass: 100%/2   | Total: 12m 25s | Avg:  6m 12s | Max:  6m 22s | Hits:  99%/2434  
      🟩 GCC11              Pass: 100%/2   | Total: 12m 34s | Avg:  6m 17s | Max:  6m 20s | Hits:  99%/2430  
      🟩 GCC12              Pass: 100%/2   | Total: 12m 54s | Avg:  6m 27s | Max:  6m 27s | Hits:  99%/2430  
      🟨 GCC13              Pass:  63%/11  | Total:  2h 39m | Avg: 14m 28s | Max: 23m 22s | Hits:  99%/8505  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 58m 51s | Avg: 29m 25s | Max: 30m 02s | Hits:  15%/2080  
      🟩 MSVC14.42          Pass: 100%/2   | Total:  1h 01m | Avg: 30m 55s | Max: 32m 42s | Hits:  15%/2080  
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 19m 24s | Avg:  9m 42s | Max:  9m 57s | Hits:  98%/2248  
    🟨 cxx_family
      🟨 Clang              Pass:  94%/17  | Total:  2h 08m | Avg:  7m 34s | Max: 22m 24s | Hits: 100%/19118 
      🟨 GCC                Pass:  81%/22  | Total:  3h 46m | Avg: 10m 17s | Max: 23m 22s | Hits:  99%/21884 
      🟩 MSVC               Pass: 100%/4   | Total:  2h 00m | Avg: 30m 10s | Max: 32m 42s | Hits:  15%/4160  
      🟩 NVHPC              Pass: 100%/2   | Total: 19m 24s | Avg:  9m 42s | Max:  9m 57s | Hits:  98%/2248  
    🟨 gpu
      🟨 h100               Pass:  66%/3   | Total: 51m 06s | Avg: 17m 02s | Max: 23m 07s | Hits:  99%/2430  
      🟩 rtx2080            Pass: 100%/34  | Total:  5h 07m | Avg:  9m 03s | Max: 32m 42s | Hits:  91%/40120 
      🟨 rtxa6000           Pass:  50%/8   | Total:  2h 16m | Avg: 17m 01s | Max: 23m 22s | Hits:  99%/4860  
    🟨 jobs
      🟩 Build              Pass: 100%/37  | Total:  5h 25m | Avg:  8m 47s | Max: 32m 42s | Hits:  91%/43765 
      🟥 DeviceLaunch       Pass:   0%/1   | Total: 20m 26s | Avg: 20m 26s | Max: 20m 26s
      🟥 GraphCapture       Pass:   0%/1   | Total: 16m 33s | Avg: 16m 33s | Max: 16m 33s
      🟥 HostLaunch         Pass:   0%/3   | Total:  1h 08m | Avg: 22m 57s | Max: 23m 22s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 03m | Avg: 21m 18s | Max: 23m 03s | Hits:  99%/3645  
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 14m 41s | Avg: 7m 20s | Max: 12m 24s | Hits: 98%/308

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 ctk
      🟩 12.8               Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total: 14m 41s | Avg:  7m 20s | Max: 12m 24s | Hits:  98%/308   
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  2m 17s | Avg:  2m 17s | Max:  2m 17s | Hits:  98%/154   
      🟩 Test               Pass: 100%/1   | Total: 12m 24s | Avg: 12m 24s | Max: 12m 24s | Hits:  98%/154   
    
  • 🟩 python: Pass: 100%/1 | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 ctk
      🟩 12.8               Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 50m 17s | Avg: 50m 17s | Max: 50m 17s
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 93)

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

@github-actions
Copy link
Contributor

🟨 CI finished in 1h 03m: Pass: 94%/93 | Total: 16h 43m | Avg: 10m 47s | Max: 49m 06s | Hits: 94%/127854
  • 🟨 cub: Pass: 88%/45 | Total: 8h 16m | Avg: 11m 01s | Max: 30m 29s | Hits: 92%/47410

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  88%/43  | Total:  8h 04m | Avg: 11m 16s | Max: 30m 29s | Hits:  92%/44980 
      🟩 arm64              Pass: 100%/2   | Total: 11m 29s | Avg:  5m 44s | Max:  6m 01s | Hits:  99%/2430  
    🔍 ctk: 12.8 🔍
      🟩 12.0               Pass: 100%/5   | Total: 47m 51s | Avg:  9m 34s | Max: 25m 44s | Hits:  85%/5908  
      🟩 12.5               Pass: 100%/2   | Total: 20m 39s | Avg: 10m 19s | Max: 10m 38s | Hits:  98%/2248  
      🔍 12.8               Pass:  86%/38  | Total:  7h 07m | Avg: 11m 15s | Max: 30m 29s | Hits:  93%/39254 
    🔍 cudacxx: nvcc12.8 🔍
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 23s | Avg:  4m 41s | Max:  4m 47s | Hits: 100%/2100  
      🟩 nvcc12.0           Pass: 100%/5   | Total: 47m 51s | Avg:  9m 34s | Max: 25m 44s | Hits:  85%/5908  
      🟩 nvcc12.5           Pass: 100%/2   | Total: 20m 39s | Avg: 10m 19s | Max: 10m 38s | Hits:  98%/2248  
      🔍 nvcc12.8           Pass:  86%/36  | Total:  6h 58m | Avg: 11m 37s | Max: 30m 29s | Hits:  92%/37154 
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 23s | Avg:  4m 41s | Max:  4m 47s | Hits: 100%/2100  
      🔍 nvcc               Pass:  88%/43  | Total:  8h 07m | Avg: 11m 19s | Max: 30m 29s | Hits:  92%/45310 
    🔍 sm: 90 🔍
      🔍 90                 Pass:  66%/3   | Total: 49m 11s | Avg: 16m 23s | Max: 23m 12s | Hits:  99%/2430  
      🟩 90;90a;100         Pass: 100%/1   | Total:  7m 21s | Avg:  7m 21s | Max:  7m 21s | Hits:  99%/1215  
    🔍 std: 20 🔍
      🟩 17                 Pass: 100%/20  | Total:  3h 09m | Avg:  9m 28s | Max: 28m 30s | Hits:  88%/23535 
      🔍 20                 Pass:  80%/25  | Total:  5h 06m | Avg: 12m 16s | Max: 30m 29s | Hits:  96%/23875 
    🟨 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 23m 02s | Avg:  5m 45s | Max:  6m 15s | Hits: 100%/4868  
      🟩 Clang15            Pass: 100%/2   | Total: 12m 02s | Avg:  6m 01s | Max:  6m 05s | Hits: 100%/2430  
      🟩 Clang16            Pass: 100%/2   | Total: 12m 15s | Avg:  6m 07s | Max:  6m 09s | Hits: 100%/2430  
      🟩 Clang17            Pass: 100%/2   | Total: 12m 08s | Avg:  6m 04s | Max:  6m 15s | Hits: 100%/2430  
      🟨 Clang18            Pass:  85%/7   | Total:  1h 10m | Avg: 10m 08s | Max: 24m 05s | Hits:  99%/6960  
      🟩 GCC7               Pass: 100%/2   | Total: 11m 36s | Avg:  5m 48s | Max:  5m 58s | Hits:  99%/2434  
      🟩 GCC8               Pass: 100%/1   | Total:  6m 08s | Avg:  6m 08s | Max:  6m 08s | Hits:  99%/1217  
      🟩 GCC9               Pass: 100%/2   | Total: 11m 52s | Avg:  5m 56s | Max:  6m 05s | Hits:  99%/2434  
      🟩 GCC10              Pass: 100%/2   | Total: 12m 26s | Avg:  6m 13s | Max:  6m 18s | Hits:  99%/2434  
      🟩 GCC11              Pass: 100%/2   | Total: 13m 17s | Avg:  6m 38s | Max:  6m 43s | Hits:  99%/2430  
      🟩 GCC12              Pass: 100%/2   | Total: 13m 04s | Avg:  6m 32s | Max:  6m 35s | Hits:  99%/2430  
      🟨 GCC13              Pass:  63%/11  | Total:  2h 44m | Avg: 14m 58s | Max: 25m 47s | Hits:  99%/8505  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 54m 14s | Avg: 27m 07s | Max: 28m 30s | Hits:  15%/2080  
      🟩 MSVC14.42          Pass: 100%/2   | Total: 58m 02s | Avg: 29m 01s | Max: 30m 29s | Hits:  15%/2080  
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 20m 39s | Avg: 10m 19s | Max: 10m 38s | Hits:  98%/2248  
    🟨 cxx_family
      🟨 Clang              Pass:  94%/17  | Total:  2h 10m | Avg:  7m 40s | Max: 24m 05s | Hits:  99%/19118 
      🟨 GCC                Pass:  81%/22  | Total:  3h 53m | Avg: 10m 35s | Max: 25m 47s | Hits:  99%/21884 
      🟩 MSVC               Pass: 100%/4   | Total:  1h 52m | Avg: 28m 04s | Max: 30m 29s | Hits:  15%/4160  
      🟩 NVHPC              Pass: 100%/2   | Total: 20m 39s | Avg: 10m 19s | Max: 10m 38s | Hits:  98%/2248  
    🟨 gpu
      🟨 h100               Pass:  66%/3   | Total: 49m 11s | Avg: 16m 23s | Max: 23m 12s | Hits:  99%/2430  
      🟩 rtx2080            Pass: 100%/34  | Total:  5h 02m | Avg:  8m 53s | Max: 30m 29s | Hits:  91%/40120 
      🟨 rtxa6000           Pass:  50%/8   | Total:  2h 24m | Avg: 18m 06s | Max: 25m 47s | Hits:  99%/4860  
    🟨 jobs
      🟩 Build              Pass: 100%/37  | Total:  5h 19m | Avg:  8m 38s | Max: 30m 29s | Hits:  91%/43765 
      🟥 DeviceLaunch       Pass:   0%/1   | Total: 22m 47s | Avg: 22m 47s | Max: 22m 47s
      🟥 GraphCapture       Pass:   0%/1   | Total: 16m 01s | Avg: 16m 01s | Max: 16m 01s
      🟥 HostLaunch         Pass:   0%/3   | Total:  1h 13m | Avg: 24m 21s | Max: 25m 47s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 04m | Avg: 21m 33s | Max: 24m 04s | Hits:  99%/3645  
    
  • 🟩 thrust: Pass: 100%/45 | Total: 7h 23m | Avg: 9m 50s | Max: 31m 16s | Hits: 95%/80136

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 18m 32s | Avg:  9m 16s | Max: 11m 08s | Hits:  99%/3564  
    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total:  7h 09m | Avg:  9m 59s | Max: 31m 16s | Hits:  95%/76573 
      🟩 arm64              Pass: 100%/2   | Total: 13m 27s | Avg:  6m 43s | Max:  6m 58s | Hits:  98%/3563  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total: 49m 19s | Avg:  9m 51s | Max: 23m 33s | Hits:  92%/8901  
      🟩 12.5               Pass: 100%/2   | Total: 31m 27s | Avg: 15m 43s | Max: 16m 55s | Hits:  97%/3562  
      🟩 12.8               Pass: 100%/38  | Total:  6h 02m | Avg:  9m 32s | Max: 31m 16s | Hits:  95%/67673 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 10m 03s | Avg:  5m 01s | Max:  5m 03s | Hits:  99%/3562  
      🟩 nvcc12.0           Pass: 100%/5   | Total: 49m 19s | Avg:  9m 51s | Max: 23m 33s | Hits:  92%/8901  
      🟩 nvcc12.5           Pass: 100%/2   | Total: 31m 27s | Avg: 15m 43s | Max: 16m 55s | Hits:  97%/3562  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  5h 52m | Avg:  9m 47s | Max: 31m 16s | Hits:  95%/64111 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 03s | Avg:  5m 01s | Max:  5m 03s | Hits:  99%/3562  
      🟩 nvcc               Pass: 100%/43  | Total:  7h 13m | Avg: 10m 04s | Max: 31m 16s | Hits:  95%/76574 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 26m 39s | Avg:  6m 39s | Max:  7m 04s | Hits:  98%/7124  
      🟩 Clang15            Pass: 100%/2   | Total: 13m 49s | Avg:  6m 54s | Max:  7m 02s | Hits:  98%/3562  
      🟩 Clang16            Pass: 100%/2   | Total: 14m 57s | Avg:  7m 28s | Max:  7m 39s | Hits:  98%/3562  
      🟩 Clang17            Pass: 100%/2   | Total: 13m 33s | Avg:  6m 46s | Max:  6m 47s | Hits:  98%/3562  
      🟩 Clang18            Pass: 100%/7   | Total: 48m 27s | Avg:  6m 55s | Max: 10m 09s | Hits:  99%/12467 
      🟩 GCC7               Pass: 100%/2   | Total: 13m 05s | Avg:  6m 32s | Max:  6m 38s | Hits:  98%/3564  
      🟩 GCC8               Pass: 100%/1   | Total:  6m 38s | Avg:  6m 38s | Max:  6m 38s | Hits:  98%/1782  
      🟩 GCC9               Pass: 100%/2   | Total: 13m 44s | Avg:  6m 52s | Max:  7m 11s | Hits:  98%/3564  
      🟩 GCC10              Pass: 100%/2   | Total: 14m 13s | Avg:  7m 06s | Max:  7m 19s | Hits:  98%/3564  
      🟩 GCC11              Pass: 100%/2   | Total: 13m 54s | Avg:  6m 57s | Max:  7m 12s | Hits:  98%/3564  
      🟩 GCC12              Pass: 100%/2   | Total: 16m 11s | Avg:  8m 05s | Max:  8m 08s | Hits:  98%/3564  
      🟩 GCC13              Pass: 100%/10  | Total:  1h 22m | Avg:  8m 17s | Max: 11m 21s | Hits:  98%/17820 
      🟩 MSVC14.29          Pass: 100%/2   | Total: 48m 47s | Avg: 24m 23s | Max: 25m 14s | Hits:  70%/3550  
      🟩 MSVC14.42          Pass: 100%/3   | Total:  1h 24m | Avg: 28m 15s | Max: 31m 16s | Hits:  70%/5325  
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 31m 27s | Avg: 15m 43s | Max: 16m 55s | Hits:  97%/3562  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  1h 57m | Avg:  6m 54s | Max: 10m 09s | Hits:  98%/30277 
      🟩 GCC                Pass: 100%/21  | Total:  2h 40m | Avg:  7m 39s | Max: 11m 21s | Hits:  98%/37422 
      🟩 MSVC               Pass: 100%/5   | Total:  2h 13m | Avg: 26m 42s | Max: 31m 16s | Hits:  70%/8875  
      🟩 NVHPC              Pass: 100%/2   | Total: 31m 27s | Avg: 15m 43s | Max: 16m 55s | Hits:  97%/3562  
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 15m 50s | Avg:  7m 55s | Max: 10m 43s | Hits:  99%/3564  
      🟩 rtx2080            Pass: 100%/33  | Total:  4h 59m | Avg:  9m 04s | Max: 26m 43s | Hits:  95%/58769 
      🟩 rtx4090            Pass: 100%/10  | Total:  2h 07m | Avg: 12m 47s | Max: 31m 16s | Hits:  93%/17803 
    🟩 jobs
      🟩 Build              Pass: 100%/38  | Total:  5h 52m | Avg:  9m 16s | Max: 26m 47s | Hits:  95%/67671 
      🟩 TestCPU            Pass: 100%/3   | Total: 47m 06s | Avg: 15m 42s | Max: 31m 16s | Hits:  90%/5338  
      🟩 TestGPU            Pass: 100%/4   | Total: 43m 21s | Avg: 10m 50s | Max: 11m 21s | Hits:  99%/7127  
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 15m 50s | Avg:  7m 55s | Max: 10m 43s | Hits:  99%/3564  
      🟩 90;90a;100         Pass: 100%/1   | Total:  6m 49s | Avg:  6m 49s | Max:  6m 49s | Hits:  98%/1782  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total:  3h 19m | Avg:  9m 58s | Max: 26m 43s | Hits:  94%/35611 
      🟩 20                 Pass: 100%/23  | Total:  3h 45m | Avg:  9m 47s | Max: 31m 16s | Hits:  96%/40961 
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 15m 08s | Avg: 7m 34s | Max: 12m 49s | Hits: 98%/308

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 ctk
      🟩 12.8               Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total: 15m 08s | Avg:  7m 34s | Max: 12m 49s | Hits:  98%/308   
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  2m 19s | Avg:  2m 19s | Max:  2m 19s | Hits:  98%/154   
      🟩 Test               Pass: 100%/1   | Total: 12m 49s | Avg: 12m 49s | Max: 12m 49s | Hits:  98%/154   
    
  • 🟩 python: Pass: 100%/1 | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 ctk
      🟩 12.8               Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 49m 06s | Avg: 49m 06s | Max: 49m 06s
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 93)

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

@github-actions
Copy link
Contributor

🟩 CI finished in 1h 13m: Pass: 100%/93 | Total: 1d 20h | Avg: 28m 45s | Max: 1h 08m | Hits: 90%/133929
  • 🟩 cub: Pass: 100%/45 | Total: 1d 08h | Avg: 43m 21s | Max: 1h 08m | Hits: 86%/53485

    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total:  1d 06h | Avg: 42m 57s | Max:  1h 08m | Hits:  86%/51055 
      🟩 arm64              Pass: 100%/2   | Total:  1h 44m | Avg: 52m 03s | Max: 52m 53s | Hits:  91%/2430  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  3h 55m | Avg: 47m 03s | Max: 57m 07s | Hits:  77%/5908  
      🟩 12.5               Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 56m 06s | Hits:  89%/2248  
      🟩 12.8               Pass: 100%/38  | Total:  1d 02h | Avg: 42m 21s | Max:  1h 08m | Hits:  87%/45329 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  1h 56m | Avg: 58m 22s | Max:  1h 00m | Hits:  92%/2100  
      🟩 nvcc12.0           Pass: 100%/5   | Total:  3h 55m | Avg: 47m 03s | Max: 57m 07s | Hits:  77%/5908  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 56m 06s | Hits:  89%/2248  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  1d 00h | Avg: 41m 28s | Max:  1h 08m | Hits:  87%/43229 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  1h 56m | Avg: 58m 22s | Max:  1h 00m | Hits:  92%/2100  
      🟩 nvcc               Pass: 100%/43  | Total:  1d 06h | Avg: 42m 39s | Max:  1h 08m | Hits:  86%/51385 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  2h 58m | Avg: 44m 35s | Max: 45m 27s | Hits:  91%/4868  
      🟩 Clang15            Pass: 100%/2   | Total:  1h 29m | Avg: 44m 37s | Max: 45m 03s | Hits:  91%/2430  
      🟩 Clang16            Pass: 100%/2   | Total:  1h 27m | Avg: 43m 57s | Max: 44m 41s | Hits:  91%/2430  
      🟩 Clang17            Pass: 100%/2   | Total:  1h 29m | Avg: 44m 49s | Max: 46m 36s | Hits:  91%/2430  
      🟩 Clang18            Pass: 100%/7   | Total:  5h 00m | Avg: 42m 53s | Max:  1h 00m | Hits:  94%/8175  
      🟩 GCC7               Pass: 100%/2   | Total:  1h 29m | Avg: 44m 42s | Max: 46m 18s | Hits:  91%/2434  
      🟩 GCC8               Pass: 100%/1   | Total: 42m 16s | Avg: 42m 16s | Max: 42m 16s | Hits:  91%/1217  
      🟩 GCC9               Pass: 100%/2   | Total:  1h 31m | Avg: 45m 42s | Max: 46m 31s | Hits:  91%/2434  
      🟩 GCC10              Pass: 100%/2   | Total:  1h 32m | Avg: 46m 05s | Max: 47m 38s | Hits:  91%/2434  
      🟩 GCC11              Pass: 100%/2   | Total:  1h 32m | Avg: 46m 27s | Max: 49m 39s | Hits:  91%/2430  
      🟩 GCC12              Pass: 100%/2   | Total:  1h 29m | Avg: 44m 59s | Max: 45m 26s | Hits:  91%/2430  
      🟩 GCC13              Pass: 100%/11  | Total:  5h 47m | Avg: 31m 35s | Max: 56m 13s | Hits:  95%/13365 
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 00m | Avg:  1h 00m | Max:  1h 03m | Hits:  15%/2080  
      🟩 MSVC14.42          Pass: 100%/2   | Total:  2h 13m | Avg:  1h 06m | Max:  1h 08m | Hits:  15%/2080  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 56m 06s | Hits:  89%/2248  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total: 12h 25m | Avg: 43m 50s | Max:  1h 00m | Hits:  92%/20333 
      🟩 GCC                Pass: 100%/22  | Total: 14h 05m | Avg: 38m 26s | Max: 56m 13s | Hits:  93%/26744 
      🟩 MSVC               Pass: 100%/4   | Total:  4h 14m | Avg:  1h 03m | Max:  1h 08m | Hits:  15%/4160  
      🟩 NVHPC              Pass: 100%/2   | Total:  1h 46m | Avg: 53m 09s | Max: 56m 06s | Hits:  89%/2248  
    🟩 gpu
      🟩 h100               Pass: 100%/3   | Total:  1h 04m | Avg: 21m 34s | Max: 23m 47s | Hits:  96%/3645  
      🟩 rtx2080            Pass: 100%/34  | Total:  1d 03h | Avg: 49m 07s | Max:  1h 08m | Hits:  83%/40120 
      🟩 rtxa6000           Pass: 100%/8   | Total:  3h 36m | Avg: 27m 01s | Max: 47m 40s | Hits:  97%/9720  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total:  1d 05h | Avg: 48m 08s | Max:  1h 08m | Hits:  84%/43765 
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 21m 39s | Avg: 21m 39s | Max: 21m 39s | Hits:  99%/1215  
      🟩 GraphCapture       Pass: 100%/1   | Total: 16m 20s | Avg: 16m 20s | Max: 16m 20s | Hits:  99%/1215  
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 08m | Avg: 22m 58s | Max: 23m 47s | Hits:  99%/3645  
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 03m | Avg: 21m 10s | Max: 21m 35s | Hits:  99%/3645  
    🟩 sm
      🟩 90                 Pass: 100%/3   | Total:  1h 04m | Avg: 21m 34s | Max: 23m 47s | Hits:  96%/3645  
      🟩 90;90a;100         Pass: 100%/1   | Total: 56m 13s | Avg: 56m 13s | Max: 56m 13s | Hits:  91%/1215  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 16h 15m | Avg: 48m 45s | Max:  1h 04m | Hits:  81%/23535 
      🟩 20                 Pass: 100%/25  | Total: 16h 16m | Avg: 39m 02s | Max:  1h 08m | Hits:  91%/29950 
    
  • 🟩 thrust: Pass: 100%/45 | Total: 10h 56m | Avg: 14m 35s | Max: 34m 54s | Hits: 92%/80136

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 23m 25s | Avg: 11m 42s | Max: 12m 22s | Hits:  97%/3564  
    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total: 10h 33m | Avg: 14m 44s | Max: 34m 54s | Hits:  92%/76573 
      🟩 arm64              Pass: 100%/2   | Total: 23m 25s | Avg: 11m 42s | Max: 12m 20s | Hits:  94%/3563  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  1h 19m | Avg: 15m 49s | Max: 30m 00s | Hits:  89%/8901  
      🟩 12.5               Pass: 100%/2   | Total: 46m 25s | Avg: 23m 12s | Max: 23m 22s | Hits:  93%/3562  
      🟩 12.8               Pass: 100%/38  | Total:  8h 51m | Avg: 13m 59s | Max: 34m 54s | Hits:  92%/67673 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 22m 23s | Avg: 11m 11s | Max: 11m 16s | Hits:  94%/3562  
      🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 19m | Avg: 15m 49s | Max: 30m 00s | Hits:  89%/8901  
      🟩 nvcc12.5           Pass: 100%/2   | Total: 46m 25s | Avg: 23m 12s | Max: 23m 22s | Hits:  93%/3562  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  8h 29m | Avg: 14m 08s | Max: 34m 54s | Hits:  92%/64111 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 22m 23s | Avg: 11m 11s | Max: 11m 16s | Hits:  94%/3562  
      🟩 nvcc               Pass: 100%/43  | Total: 10h 34m | Avg: 14m 45s | Max: 34m 54s | Hits:  92%/76574 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 48m 07s | Avg: 12m 01s | Max: 12m 26s | Hits:  94%/7124  
      🟩 Clang15            Pass: 100%/2   | Total: 25m 47s | Avg: 12m 53s | Max: 13m 37s | Hits:  94%/3562  
      🟩 Clang16            Pass: 100%/2   | Total: 24m 02s | Avg: 12m 01s | Max: 12m 15s | Hits:  94%/3562  
      🟩 Clang17            Pass: 100%/2   | Total: 25m 26s | Avg: 12m 43s | Max: 12m 59s | Hits:  94%/3562  
      🟩 Clang18            Pass: 100%/7   | Total:  1h 15m | Avg: 10m 49s | Max: 12m 37s | Hits:  96%/12467 
      🟩 GCC7               Pass: 100%/2   | Total: 24m 54s | Avg: 12m 27s | Max: 13m 02s | Hits:  94%/3564  
      🟩 GCC8               Pass: 100%/1   | Total: 12m 05s | Avg: 12m 05s | Max: 12m 05s | Hits:  94%/1782  
      🟩 GCC9               Pass: 100%/2   | Total: 24m 48s | Avg: 12m 24s | Max: 12m 39s | Hits:  94%/3564  
      🟩 GCC10              Pass: 100%/2   | Total: 24m 50s | Avg: 12m 25s | Max: 12m 32s | Hits:  94%/3564  
      🟩 GCC11              Pass: 100%/2   | Total: 26m 34s | Avg: 13m 17s | Max: 13m 51s | Hits:  94%/3564  
      🟩 GCC12              Pass: 100%/2   | Total: 25m 37s | Avg: 12m 48s | Max: 12m 51s | Hits:  94%/3564  
      🟩 GCC13              Pass: 100%/10  | Total:  1h 55m | Avg: 11m 34s | Max: 14m 14s | Hits:  96%/17820 
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 00m | Avg: 30m 20s | Max: 30m 40s | Hits:  66%/3550  
      🟩 MSVC14.42          Pass: 100%/3   | Total:  1h 36m | Avg: 32m 05s | Max: 34m 54s | Hits:  67%/5325  
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 46m 25s | Avg: 23m 12s | Max: 23m 22s | Hits:  93%/3562  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  3h 19m | Avg: 11m 42s | Max: 13m 37s | Hits:  95%/30277 
      🟩 GCC                Pass: 100%/21  | Total:  4h 14m | Avg: 12m 07s | Max: 14m 14s | Hits:  95%/37422 
      🟩 MSVC               Pass: 100%/5   | Total:  2h 36m | Avg: 31m 23s | Max: 34m 54s | Hits:  67%/8875  
      🟩 NVHPC              Pass: 100%/2   | Total: 46m 25s | Avg: 23m 12s | Max: 23m 22s | Hits:  93%/3562  
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 19m 36s | Avg:  9m 48s | Max: 10m 44s | Hits:  97%/3564  
      🟩 rtx2080            Pass: 100%/33  | Total:  8h 03m | Avg: 14m 39s | Max: 30m 40s | Hits:  92%/58769 
      🟩 rtx4090            Pass: 100%/10  | Total:  2h 33m | Avg: 15m 21s | Max: 34m 54s | Hits:  92%/17803 
    🟩 jobs
      🟩 Build              Pass: 100%/38  | Total:  9h 26m | Avg: 14m 54s | Max: 34m 54s | Hits:  91%/67671 
      🟩 TestCPU            Pass: 100%/3   | Total: 46m 50s | Avg: 15m 36s | Max: 31m 26s | Hits:  90%/5338  
      🟩 TestGPU            Pass: 100%/4   | Total: 43m 24s | Avg: 10m 51s | Max: 11m 23s | Hits:  99%/7127  
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 19m 36s | Avg:  9m 48s | Max: 10m 44s | Hits:  97%/3564  
      🟩 90;90a;100         Pass: 100%/1   | Total: 12m 47s | Avg: 12m 47s | Max: 12m 47s | Hits:  94%/1782  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total:  5h 15m | Avg: 15m 45s | Max: 30m 40s | Hits:  90%/35611 
      🟩 20                 Pass: 100%/23  | Total:  5h 18m | Avg: 13m 50s | Max: 34m 54s | Hits:  93%/40961 
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 15m 23s | Avg: 7m 41s | Max: 13m 08s | Hits: 98%/308

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 ctk
      🟩 12.8               Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total: 15m 23s | Avg:  7m 41s | Max: 13m 08s | Hits:  98%/308   
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  2m 15s | Avg:  2m 15s | Max:  2m 15s | Hits:  98%/154   
      🟩 Test               Pass: 100%/1   | Total: 13m 08s | Avg: 13m 08s | Max: 13m 08s | Hits:  98%/154   
    
  • 🟩 python: Pass: 100%/1 | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 ctk
      🟩 12.8               Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 50m 25s | Avg: 50m 25s | Max: 50m 25s
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 93)

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

@bernhardmgruber bernhardmgruber enabled auto-merge (squash) February 25, 2025 17:22
@github-actions
Copy link
Contributor

🟩 CI finished in 1h 13m: Pass: 100%/93 | Total: 21h 03m | Avg: 13m 35s | Max: 1h 12m | Hits: 94%/133929
  • 🟩 cub: Pass: 100%/45 | Total: 12h 12m | Avg: 16m 16s | Max: 1h 12m | Hits: 92%/53485

    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total: 12h 01m | Avg: 16m 46s | Max:  1h 12m | Hits:  92%/51055 
      🟩 arm64              Pass: 100%/2   | Total: 10m 50s | Avg:  5m 25s | Max:  5m 44s | Hits:  99%/2430  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  1h 19m | Avg: 15m 58s | Max: 57m 36s | Hits:  85%/5908  
      🟩 12.5               Pass: 100%/2   | Total:  1h 45m | Avg: 52m 33s | Max: 52m 35s | Hits:  88%/2248  
      🟩 12.8               Pass: 100%/38  | Total:  9h 07m | Avg: 14m 23s | Max:  1h 12m | Hits:  94%/45329 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 37s | Avg:  4m 48s | Max:  4m 55s | Hits: 100%/2100  
      🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 19m | Avg: 15m 58s | Max: 57m 36s | Hits:  85%/5908  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 45m | Avg: 52m 33s | Max: 52m 35s | Hits:  88%/2248  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  8h 57m | Avg: 14m 55s | Max:  1h 12m | Hits:  93%/43229 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 37s | Avg:  4m 48s | Max:  4m 55s | Hits: 100%/2100  
      🟩 nvcc               Pass: 100%/43  | Total: 12h 02m | Avg: 16m 48s | Max:  1h 12m | Hits:  92%/51385 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 23m 06s | Avg:  5m 46s | Max:  6m 09s | Hits: 100%/4868  
      🟩 Clang15            Pass: 100%/2   | Total: 11m 59s | Avg:  5m 59s | Max:  6m 00s | Hits: 100%/2430  
      🟩 Clang16            Pass: 100%/2   | Total: 12m 03s | Avg:  6m 01s | Max:  6m 02s | Hits: 100%/2430  
      🟩 Clang17            Pass: 100%/2   | Total: 11m 49s | Avg:  5m 54s | Max:  6m 00s | Hits: 100%/2430  
      🟩 Clang18            Pass: 100%/7   | Total:  1h 14m | Avg: 10m 37s | Max: 24m 58s | Hits: 100%/8175  
      🟩 GCC7               Pass: 100%/2   | Total: 11m 21s | Avg:  5m 40s | Max:  5m 59s | Hits:  99%/2434  
      🟩 GCC8               Pass: 100%/1   | Total:  5m 56s | Avg:  5m 56s | Max:  5m 56s | Hits:  99%/1217  
      🟩 GCC9               Pass: 100%/2   | Total: 12m 09s | Avg:  6m 04s | Max:  6m 29s | Hits:  99%/2434  
      🟩 GCC10              Pass: 100%/2   | Total: 12m 22s | Avg:  6m 11s | Max:  6m 14s | Hits:  99%/2434  
      🟩 GCC11              Pass: 100%/2   | Total: 12m 56s | Avg:  6m 28s | Max:  6m 38s | Hits:  99%/2430  
      🟩 GCC12              Pass: 100%/2   | Total: 12m 59s | Avg:  6m 29s | Max:  6m 30s | Hits:  99%/2430  
      🟩 GCC13              Pass: 100%/11  | Total:  2h 43m | Avg: 14m 52s | Max: 23m 57s | Hits:  99%/13365 
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 02m | Avg:  1h 01m | Max:  1h 05m | Hits:  15%/2080  
      🟩 MSVC14.42          Pass: 100%/2   | Total:  2h 19m | Avg:  1h 09m | Max:  1h 12m | Hits:  15%/2080  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 45m | Avg: 52m 33s | Max: 52m 35s | Hits:  88%/2248  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  2h 13m | Avg:  7m 50s | Max: 24m 58s | Hits: 100%/20333 
      🟩 GCC                Pass: 100%/22  | Total:  3h 51m | Avg: 10m 30s | Max: 23m 57s | Hits:  99%/26744 
      🟩 MSVC               Pass: 100%/4   | Total:  4h 22m | Avg:  1h 05m | Max:  1h 12m | Hits:  15%/4160  
      🟩 NVHPC              Pass: 100%/2   | Total:  1h 45m | Avg: 52m 33s | Max: 52m 35s | Hits:  88%/2248  
    🟩 gpu
      🟩 h100               Pass: 100%/3   | Total: 49m 24s | Avg: 16m 28s | Max: 23m 17s | Hits:  99%/3645  
      🟩 rtx2080            Pass: 100%/34  | Total:  8h 54m | Avg: 15m 42s | Max:  1h 12m | Hits:  90%/40120 
      🟩 rtxa6000           Pass: 100%/8   | Total:  2h 28m | Avg: 18m 34s | Max: 24m 58s | Hits:  99%/9720  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total:  9h 11m | Avg: 14m 55s | Max:  1h 12m | Hits:  91%/43765 
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 23m 31s | Avg: 23m 31s | Max: 23m 31s | Hits:  99%/1215  
      🟩 GraphCapture       Pass: 100%/1   | Total: 18m 08s | Avg: 18m 08s | Max: 18m 08s | Hits:  99%/1215  
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 10m | Avg: 23m 34s | Max: 24m 58s | Hits:  99%/3645  
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 07m | Avg: 22m 35s | Max: 23m 57s | Hits:  99%/3645  
    🟩 sm
      🟩 90                 Pass: 100%/3   | Total: 49m 24s | Avg: 16m 28s | Max: 23m 17s | Hits:  99%/3645  
      🟩 90;90a;100         Pass: 100%/1   | Total:  6m 38s | Avg:  6m 38s | Max:  6m 38s | Hits:  99%/1215  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total:  5h 38m | Avg: 16m 55s | Max:  1h 07m | Hits:  88%/23535 
      🟩 20                 Pass: 100%/25  | Total:  6h 33m | Avg: 15m 44s | Max:  1h 12m | Hits:  96%/29950 
    
  • 🟩 thrust: Pass: 100%/45 | Total: 7h 44m | Avg: 10m 19s | Max: 38m 19s | Hits: 95%/80136

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 16m 55s | Avg:  8m 27s | Max: 11m 05s | Hits:  99%/3564  
    🟩 cpu
      🟩 amd64              Pass: 100%/43  | Total:  7h 35m | Avg: 10m 35s | Max: 38m 19s | Hits:  95%/76573 
      🟩 arm64              Pass: 100%/2   | Total:  9m 31s | Avg:  4m 45s | Max:  5m 05s | Hits:  99%/3563  
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total: 49m 41s | Avg:  9m 56s | Max: 29m 40s | Hits:  94%/8901  
      🟩 12.5               Pass: 100%/2   | Total: 47m 02s | Avg: 23m 31s | Max: 24m 09s | Hits:  93%/3562  
      🟩 12.8               Pass: 100%/38  | Total:  6h 08m | Avg:  9m 41s | Max: 38m 19s | Hits:  95%/67673 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 10m 19s | Avg:  5m 09s | Max:  5m 18s | Hits: 100%/3562  
      🟩 nvcc12.0           Pass: 100%/5   | Total: 49m 41s | Avg:  9m 56s | Max: 29m 40s | Hits:  94%/8901  
      🟩 nvcc12.5           Pass: 100%/2   | Total: 47m 02s | Avg: 23m 31s | Max: 24m 09s | Hits:  93%/3562  
      🟩 nvcc12.8           Pass: 100%/36  | Total:  5h 57m | Avg:  9m 56s | Max: 38m 19s | Hits:  95%/64111 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 10m 19s | Avg:  5m 09s | Max:  5m 18s | Hits: 100%/3562  
      🟩 nvcc               Pass: 100%/43  | Total:  7h 34m | Avg: 10m 34s | Max: 38m 19s | Hits:  95%/76574 
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 20m 32s | Avg:  5m 08s | Max:  5m 20s | Hits: 100%/7124  
      🟩 Clang15            Pass: 100%/2   | Total: 10m 57s | Avg:  5m 28s | Max:  5m 40s | Hits: 100%/3562  
      🟩 Clang16            Pass: 100%/2   | Total: 10m 57s | Avg:  5m 28s | Max:  5m 39s | Hits: 100%/3562  
      🟩 Clang17            Pass: 100%/2   | Total: 11m 13s | Avg:  5m 36s | Max:  5m 43s | Hits: 100%/3562  
      🟩 Clang18            Pass: 100%/7   | Total: 42m 49s | Avg:  6m 07s | Max: 10m 15s | Hits: 100%/12467 
      🟩 GCC7               Pass: 100%/2   | Total: 10m 27s | Avg:  5m 13s | Max:  5m 17s | Hits:  99%/3564  
      🟩 GCC8               Pass: 100%/1   | Total:  5m 21s | Avg:  5m 21s | Max:  5m 21s | Hits:  99%/1782  
      🟩 GCC9               Pass: 100%/2   | Total: 10m 25s | Avg:  5m 12s | Max:  5m 33s | Hits:  99%/3564  
      🟩 GCC10              Pass: 100%/2   | Total: 10m 53s | Avg:  5m 26s | Max:  5m 34s | Hits:  99%/3564  
      🟩 GCC11              Pass: 100%/2   | Total: 11m 19s | Avg:  5m 39s | Max:  5m 53s | Hits:  99%/3564  
      🟩 GCC12              Pass: 100%/2   | Total: 11m 20s | Avg:  5m 40s | Max:  5m 47s | Hits:  99%/3564  
      🟩 GCC13              Pass: 100%/10  | Total:  1h 47m | Avg: 10m 47s | Max: 38m 19s | Hits:  94%/17820 
      🟩 MSVC14.29          Pass: 100%/2   | Total: 58m 04s | Avg: 29m 02s | Max: 29m 40s | Hits:  70%/3550  
      🟩 MSVC14.42          Pass: 100%/3   | Total:  1h 35m | Avg: 31m 55s | Max: 34m 28s | Hits:  70%/5325  
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 47m 02s | Avg: 23m 31s | Max: 24m 09s | Hits:  93%/3562  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  1h 36m | Avg:  5m 40s | Max: 10m 15s | Hits: 100%/30277 
      🟩 GCC                Pass: 100%/21  | Total:  2h 47m | Avg:  7m 58s | Max: 38m 19s | Hits:  97%/37422 
      🟩 MSVC               Pass: 100%/5   | Total:  2h 33m | Avg: 30m 46s | Max: 34m 28s | Hits:  70%/8875  
      🟩 NVHPC              Pass: 100%/2   | Total: 47m 02s | Avg: 23m 31s | Max: 24m 09s | Hits:  93%/3562  
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 16m 31s | Avg:  8m 15s | Max: 11m 45s | Hits:  99%/3564  
      🟩 rtx2080            Pass: 100%/33  | Total:  5h 18m | Avg:  9m 39s | Max: 38m 19s | Hits:  95%/58769 
      🟩 rtx4090            Pass: 100%/10  | Total:  2h 09m | Avg: 12m 59s | Max: 34m 28s | Hits:  94%/17803 
    🟩 jobs
      🟩 Build              Pass: 100%/38  | Total:  6h 14m | Avg:  9m 51s | Max: 38m 19s | Hits:  95%/67671 
      🟩 TestCPU            Pass: 100%/3   | Total: 45m 47s | Avg: 15m 15s | Max: 30m 30s | Hits:  90%/5338  
      🟩 TestGPU            Pass: 100%/4   | Total: 44m 18s | Avg: 11m 04s | Max: 11m 45s | Hits:  99%/7127  
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 16m 31s | Avg:  8m 15s | Max: 11m 45s | Hits:  99%/3564  
      🟩 90;90a;100         Pass: 100%/1   | Total: 38m 19s | Avg: 38m 19s | Max: 38m 19s | Hits:  48%/1782  
    🟩 std
      🟩 17                 Pass: 100%/20  | Total:  3h 18m | Avg:  9m 56s | Max: 30m 48s | Hits:  95%/35611 
      🟩 20                 Pass: 100%/23  | Total:  4h 09m | Avg: 10m 49s | Max: 38m 19s | Hits:  94%/40961 
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 15m 54s | Avg: 7m 57s | Max: 13m 37s | Hits: 98%/308

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 ctk
      🟩 12.8               Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total: 15m 54s | Avg:  7m 57s | Max: 13m 37s | Hits:  98%/308   
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  2m 17s | Avg:  2m 17s | Max:  2m 17s | Hits:  98%/154   
      🟩 Test               Pass: 100%/1   | Total: 13m 37s | Avg: 13m 37s | Max: 13m 37s | Hits:  98%/154   
    
  • 🟩 python: Pass: 100%/1 | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 ctk
      🟩 12.8               Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 cudacxx
      🟩 nvcc12.8           Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 50m 28s | Avg: 50m 28s | Max: 50m 28s
    

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 93)

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

@bernhardmgruber bernhardmgruber merged commit 1bb4e6a into NVIDIA:main Feb 25, 2025
108 of 111 checks passed
@bernhardmgruber bernhardmgruber deleted the ref_radix_min_max branch February 25, 2025 20:24
davebayer pushed a commit to davebayer/cccl that referenced this pull request Apr 7, 2025
No SASS change on cub.test.device_radix_sort_pairs.lid_0 for SM86
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.

4 participants