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

Unify assert handling in cccl #2382

Open
wants to merge 20 commits into
base: main
Choose a base branch
from
Open

Conversation

miscco
Copy link
Collaborator

@miscco miscco commented Sep 6, 2024

This works toward unification of assert handling in CCCL

Currently we do not enable assertions even in debug mode, which is ... unfortunate (See #2381)

For libcu++ the user must define _LIBCUDACXX_ENABLE_DEBUG_MODE or _LIBCUDACXX_ENABLE_ASSERTIONS

None of those macros are user facing or documented anywhere, which makes it really difficult to use. Furthermore, this only works on libcu++ and not Thrust and CUB. However, we want a delightful experience across all our libraries.

To improve the situation and give our users the choice we move the assertion handling into a global CCCL wide facility.

The proposal is to add three distinct, user facing flags:

  1. CCCL_ENABLE_HOST_ASSERTIONS This enables use of assertions in host code only
  2. CCCL_ENABLE_DEVICE_ASSERTIONS This enables use of assertions in device code only
  3. CCCL_ENABLE_ASSERTIONS This enables use of assertions in both host and device code

This allows the user to select what kind of assertions they want to use and whether they want to take the compile-time / performance hit of device assertions.

Finally, we also provide internal facilities to actually use those assertions, namely

  1. _CCCL_VERIFY This is always on and reserved for absolutely critical correctness checks.
  2. _CCCL_ASSERT This is conditionally on depending on the user provided flag

@miscco miscco requested review from a team as code owners September 6, 2024 12:05
@miscco miscco added feature request New feature or request. libcu++ For all items related to libcu++ labels Sep 6, 2024
Copy link
Contributor

@bernhardmgruber bernhardmgruber left a comment

Choose a reason for hiding this comment

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

Great work so far, thx! I see no changes to the build system tough. What are users expected to define now to get assertions? DEBUG, _CCCL_ENABLE_DEBUG_MODE, or _CCCL_ENABLE_ASSERTIONS? And why do we need a distinction between a debug mode and assertions enabled?

libcudacxx/include/cuda/std/__cccl/assert.h Outdated Show resolved Hide resolved
Comment on lines -70 to -106
{
#ifdef _LIBCUDACXX_ENABLE_DEBUG_MODE
if (!__libcpp_is_constant_evaluated())
{
__get_db()->__iterator_copy(this, _CUDA_VSTD::addressof(__u));
}
#endif
}
#ifdef _LIBCUDACXX_ENABLE_DEBUG_MODE
_LIBCUDACXX_HIDE_FROM_ABI _CCCL_CONSTEXPR_CXX14 __wrap_iter(const __wrap_iter& __x)
: __i_(__x.base())
{
if (!__libcpp_is_constant_evaluated())
{
__get_db()->__iterator_copy(this, _CUDA_VSTD::addressof(__x));
}
}
_LIBCUDACXX_HIDE_FROM_ABI _CCCL_CONSTEXPR_CXX14 __wrap_iter& operator=(const __wrap_iter& __x)
{
if (this != _CUDA_VSTD::addressof(__x))
{
if (!__libcpp_is_constant_evaluated())
{
__get_db()->__iterator_copy(this, _CUDA_VSTD::addressof(__x));
}
__i_ = __x.__i_;
}
return *this;
}
_LIBCUDACXX_HIDE_FROM_ABI _CCCL_CONSTEXPR_CXX20 ~__wrap_iter()
{
if (!__libcpp_is_constant_evaluated())
{
__get_db()->__erase_i(this);
}
}
#endif
Copy link
Contributor

Choose a reason for hiding this comment

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

Question: Why remove all this? And why as part of this PR? It seems unrelated to the assert unification.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Thats something i had in that branch lying around. We need to get rid of all the old debug handling

Copy link
Contributor

Choose a reason for hiding this comment

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

For next time: please ship this is a separate PR.

@@ -39,6 +39,11 @@ else() # NOT LIBCUDACXX_TEST_WITH_NVRTC
set(LIBCUDACXX_TEST_COMPILER_FLAGS "-DLIBCUDACXX_ENABLE_EXPERIMENTAL_MEMORY_RESOURCE")
endif()

# enable exceptions and assertions in tests
string(APPEND LIBCUDACXX_TEST_COMPILER_FLAGS
" -DLIBCUDACXX_ENABLE_EXCEPTIONS"
Copy link
Contributor

Choose a reason for hiding this comment

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

Enabling exceptions seems unrelated to this PR? Why was it added? Oversight?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I want to enable assertions globally, so we can just as well enable exceptions too

Copy link
Contributor

Choose a reason for hiding this comment

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

I can imagine this introducing all kinds of new side effects and possible requiring additional fixes unrelated to assertions. Can we please do it in a separate PR?

@fbusato
Copy link
Contributor

fbusato commented Sep 6, 2024

would make sense to add an "optimization mode"? namely, mapping assertions to __builtin_assume or equivalent? clang already does this underneath

@miscco
Copy link
Collaborator Author

miscco commented Sep 11, 2024

would make sense to add an "optimization mode"? namely, mapping assertions to __builtin_assume or equivalent? clang already does this underneath

That is exceptionally difficult. On one hand, __builtin_assume is not supported, but more importantly, even clang does not enable it because there are performance implications

@jrhemstad
Copy link
Collaborator

@miscco can you update the PR description with a summary of the approach we're taking to unify things and what the default behavior will be?

@fbusato
Copy link
Contributor

fbusato commented Sep 11, 2024

That is exceptionally difficult. On one hand, __builtin_assume is not supported, but more importantly, even clang does not enable it because there are performance implications

This is mindblowing. I always found user-provided assumptions very useful for optimization, but I understand that this doesn't apply to everything.
When I proposed __builtin_assume I referred to any construct that maps to [[assume]]. LLVM regressions with @llvm.assume() seems more a bug. Anyway, I understand that it is better to separate the two concepts.

Copy link
Collaborator

@dkolsen-pgi dkolsen-pgi left a comment

Choose a reason for hiding this comment

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

The big problem here is that __cccl/assert.h doesn't handle nvc++ -stdpar.

# define _CCCL_VERIFY(expression, message) \
_CCCL_DIAG_PUSH _CCCL_DIAG_SUPPRESS_ICC(4190) _CCCL_ASSERT_IMPL(expression, message) _CCCL_DIAG_POP
#else // ^^^ _CCCL_COMPILER_ICC ^^^ / vvv !_CCCL_COMPILER_ICC vvv
# define _CCCL_VERIFY(expression, message) _CCCL_ASSERT_IMPL(expression, message)
Copy link
Collaborator

Choose a reason for hiding this comment

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

If __CUDA_ARCH__ is defined but CCCL_ENABLE_DEVICE_ASSERTIONS is not defined, then _CCCL_ASSERT_IMPL will be defined as empty, so _CCCL_VERIFY(expression, message) will expand to (expression, message). That will compile and behave correctly, but it's not what you want.

If neither __CUDA_ARCH__ nor CCCL_ENABLE_HOST_ASSERTIONS are defined, then _CCCL_ASSERT_IMPL is not defined at all, so _CCCL_VERIFY(expression, message) will expand to _CCCL_ASSERT_IMPL(expression, message), which is a compilation error.

Since _CCCL_VERIFY is always defined, _CCCL_ASSERT_IMPL must always be defined. If it can't be defined as something meaningful, then it should be #define _CCCL_ASSERT_IMPL(expression, message) ((void)0)

#endif // !CCCL_ENABLE_DEVICE_ASSERTIONS

//! Use internal nvcc implementation on device or the host library for clang-cuda
#ifdef __CUDA_ARCH__
Copy link
Collaborator

Choose a reason for hiding this comment

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

This file, cuda/std/__cccl/assert.h, ignores NVC++ entirely, and won't work correctly for nvc++ -stdpar=gpu. The file assumes that host and device code are compiled separately, and that __CUDA_ARCH__ is defined when compiling device code and __CUDA_ARCH__ is not defined when compiling host code.

nvc++ -stdpar=gpu compiles both host and device code in a single pass and does not define __CUDA_ARCH__. It is probably necessary to give NVC++ special handling, separate from all the logic that is here. _CCCL_ASSERT_IMPL would be defined as something that works in both host and device code with NVC++. (__assert_fail might work in both host and device code with NVC++, but that should be verified.)

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

I reworked the approach to use the host standard library on host and only use the special fallback for nvcc on device.

The _CCCL_ASSERT_IMPL now forwards to _NV_IF_TARGET

libcudacxx/include/cuda/std/__cccl/assert.h Outdated Show resolved Hide resolved
@miscco miscco force-pushed the enable_asserts branch 3 times, most recently from dce12bb to 8e3ed7e Compare September 16, 2024 11:58
Copy link
Contributor

🟨 CI finished in 6h 25m: Pass: 93%/433 | Total: 3d 05h | Avg: 10m 48s | Max: 1h 30m | Hits: 99%/24636
  • 🟨 libcudacxx: Pass: 75%/116 | Total: 1d 16h | Avg: 20m 58s | Max: 1h 30m

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  74%/108 | Total:  1d 13h | Avg: 21m 00s | Max:  1h 30m
      🟩 arm64              Pass: 100%/8   | Total:  2h 45m | Avg: 20m 40s | Max: 25m 33s
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 36m 24s | Avg: 18m 12s | Max: 18m 53s
      🔍 nvcc               Pass:  75%/114 | Total:  1d 15h | Avg: 21m 01s | Max:  1h 30m
    🟨 ctk
      🟥 11.1               Pass:   0%/15  | Total:  4h 09m | Avg: 16m 37s | Max: 24m 30s
      🟩 11.8               Pass: 100%/3   | Total:  1h 12m | Avg: 24m 10s | Max: 27m 24s
      🟨 12.6               Pass:  86%/98  | Total:  1d 11h | Avg: 21m 33s | Max:  1h 30m
    🟨 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 36m 24s | Avg: 18m 12s | Max: 18m 53s
      🟥 nvcc11.1           Pass:   0%/15  | Total:  4h 09m | Avg: 16m 37s | Max: 24m 30s
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 12m | Avg: 24m 10s | Max: 27m 24s
      🟨 nvcc12.6           Pass:  86%/96  | Total:  1d 10h | Avg: 21m 37s | Max:  1h 30m
    🟨 cxx
      🟨 Clang9             Pass:  50%/6   | Total:  1h 38m | Avg: 16m 29s | Max: 24m 30s
      🟩 Clang10            Pass: 100%/3   | Total: 45m 14s | Avg: 15m 04s | Max: 22m 40s
      🟩 Clang11            Pass: 100%/4   | Total:  1h 14m | Avg: 18m 33s | Max: 29m 22s
      🟩 Clang12            Pass: 100%/4   | Total:  1h 35m | Avg: 23m 49s | Max: 26m 35s
      🟩 Clang13            Pass: 100%/4   | Total:  1h 17m | Avg: 19m 18s | Max: 28m 19s
      🟩 Clang14            Pass: 100%/4   | Total:  1h 36m | Avg: 24m 04s | Max: 27m 12s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 22m | Avg: 20m 38s | Max: 22m 03s
      🟩 Clang16            Pass: 100%/4   | Total:  1h 27m | Avg: 21m 47s | Max: 26m 45s
      🟩 Clang17            Pass: 100%/4   | Total:  1h 18m | Avg: 19m 35s | Max: 27m 15s
      🟨 Clang18            Pass:  85%/14  | Total:  7h 46m | Avg: 33m 18s | Max:  1h 30m
      🟥 GCC6               Pass:   0%/2   | Total: 25m 24s | Avg: 12m 42s | Max: 22m 21s
      🟨 GCC7               Pass:  50%/6   | Total:  1h 43m | Avg: 17m 13s | Max: 21m 06s
      🟨 GCC8               Pass:  50%/6   | Total:  1h 48m | Avg: 18m 07s | Max: 24m 32s
      🟨 GCC9               Pass:  50%/6   | Total:  2h 11m | Avg: 21m 52s | Max: 25m 33s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 33m | Avg: 23m 29s | Max: 28m 22s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 17m | Avg: 19m 40s | Max: 27m 24s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 07m | Avg: 16m 49s | Max: 25m 21s
      🟨 GCC13              Pass:  85%/21  | Total:  8h 31m | Avg: 24m 22s | Max:  1h 23m
      🟥 Intel2023.2.0      Pass:   0%/3   | Total: 10m 40s | Avg:  3m 33s | Max:  4m 22s
      🟥 MSVC14.16          Pass:   0%/1   | Total:  9m 59s | Avg:  9m 59s | Max:  9m 59s
      🟥 MSVC14.29          Pass:   0%/2   | Total: 11m 52s | Avg:  5m 56s | Max:  6m 08s
      🟥 MSVC14.39          Pass:   0%/3   | Total: 20m 09s | Avg:  6m 43s | Max:  7m 06s
    🟨 jobs
      🟨 Build              Pass:  77%/103 | Total:  1d 06h | Avg: 17m 36s | Max: 29m 22s
      🟩 NVRTC              Pass: 100%/4   | Total:  1h 53m | Avg: 28m 24s | Max: 37m 17s
      🟨 Test               Pass:  37%/8   | Total:  8h 23m | Avg:  1h 02m | Max:  1h 30m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 03s | Avg:  2m 03s | Max:  2m 03s
    🟨 gpu
      🟨 v100               Pass:  75%/116 | Total:  1d 16h | Avg: 20m 58s | Max:  1h 30m
    🟨 cxx_family
      🟨 Clang              Pass:  90%/51  | Total: 20h 01m | Avg: 23m 33s | Max:  1h 30m
      🟨 GCC                Pass:  75%/56  | Total: 19h 39m | Avg: 21m 03s | Max:  1h 23m
      🟥 Intel              Pass:   0%/3   | Total: 10m 40s | Avg:  3m 33s | Max:  4m 22s
      🟥 MSVC               Pass:   0%/6   | Total: 42m 00s | Avg:  7m 00s | Max:  9m 59s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 12m | Avg: 24m 10s | Max: 27m 24s
      🟩 90a                Pass: 100%/4   | Total: 15m 18s | Avg:  3m 49s | Max:  4m 42s
    🟨 std
      🟨 11                 Pass:  80%/30  | Total: 10h 15m | Avg: 20m 30s | Max:  1h 02m
      🟨 14                 Pass:  69%/33  | Total: 10h 15m | Avg: 18m 38s | Max:  1h 23m
      🟨 17                 Pass:  71%/32  | Total: 12h 00m | Avg: 22m 31s | Max:  1h 30m
      🟨 20                 Pass:  85%/20  | Total:  8h 00m | Avg: 24m 02s | Max:  1h 29m
    
  • 🟩 cub: Pass: 100%/136 | Total: 20h 42m | Avg: 9m 08s | Max: 53m 46s | Hits: 99%/4362

    🟩 cpu
      🟩 amd64              Pass: 100%/128 | Total: 20h 08m | Avg:  9m 26s | Max: 53m 46s | Hits:  99%/4362  
      🟩 arm64              Pass: 100%/8   | Total: 33m 37s | Avg:  4m 12s | Max:  4m 47s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 04m | Avg:  4m 17s | Max: 12m 21s | Hits:  99%/727   
      🟩 11.8               Pass: 100%/3   | Total: 14m 33s | Avg:  4m 51s | Max:  5m 06s
      🟩 12.6               Pass: 100%/118 | Total: 19h 23m | Avg:  9m 51s | Max: 53m 46s | Hits:  99%/3635  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  7m 27s | Avg:  3m 43s | Max:  3m 45s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 04m | Avg:  4m 17s | Max: 12m 21s | Hits:  99%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 33s | Avg:  4m 51s | Max:  5m 06s
      🟩 nvcc12.6           Pass: 100%/116 | Total: 19h 16m | Avg:  9m 58s | Max: 53m 46s | Hits:  99%/3635  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 27s | Avg:  3m 43s | Max:  3m 45s
      🟩 nvcc               Pass: 100%/134 | Total: 20h 35m | Avg:  9m 13s | Max: 53m 46s | Hits:  99%/4362  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 27m 48s | Avg:  4m 38s | Max:  5m 17s
      🟩 Clang10            Pass: 100%/3   | Total: 15m 23s | Avg:  5m 07s | Max:  5m 09s
      🟩 Clang11            Pass: 100%/4   | Total: 17m 50s | Avg:  4m 27s | Max:  4m 43s
      🟩 Clang12            Pass: 100%/4   | Total: 17m 32s | Avg:  4m 23s | Max:  4m 34s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 17s | Avg:  4m 34s | Max:  4m 43s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 02s | Avg:  4m 30s | Max:  4m 44s
      🟩 Clang15            Pass: 100%/4   | Total: 19m 03s | Avg:  4m 45s | Max:  5m 04s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 01s | Avg:  4m 45s | Max:  4m 59s
      🟩 Clang17            Pass: 100%/4   | Total: 17m 40s | Avg:  4m 25s | Max:  4m 28s
      🟩 Clang18            Pass: 100%/26  | Total:  6h 51m | Avg: 15m 48s | Max: 37m 04s
      🟩 GCC6               Pass: 100%/2   | Total:  6m 54s | Avg:  3m 27s | Max:  3m 27s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 13m | Avg: 12m 16s | Max: 53m 46s
      🟩 GCC8               Pass: 100%/6   | Total: 23m 13s | Avg:  3m 52s | Max:  4m 26s
      🟩 GCC9               Pass: 100%/6   | Total: 24m 34s | Avg:  4m 05s | Max:  4m 48s
      🟩 GCC10              Pass: 100%/4   | Total: 17m 42s | Avg:  4m 25s | Max:  4m 35s
      🟩 GCC11              Pass: 100%/7   | Total: 32m 39s | Avg:  4m 39s | Max:  5m 06s
      🟩 GCC12              Pass: 100%/4   | Total: 18m 02s | Avg:  4m 30s | Max:  4m 38s
      🟩 GCC13              Pass: 100%/29  | Total:  6h 24m | Avg: 13m 16s | Max: 31m 53s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 16m 04s | Avg:  5m 21s | Max:  5m 47s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 12m 21s | Avg: 12m 21s | Max: 12m 21s | Hits:  99%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 19m 08s | Avg:  9m 34s | Max:  9m 49s | Hits:  99%/1454  
      🟩 MSVC14.39          Pass: 100%/3   | Total: 31m 45s | Avg: 10m 35s | Max: 11m 35s | Hits:  99%/2181  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/63  | Total:  9h 41m | Avg:  9m 14s | Max: 37m 04s
      🟩 GCC                Pass: 100%/64  | Total:  9h 41m | Avg:  9m 05s | Max: 53m 46s
      🟩 Intel              Pass: 100%/3   | Total: 16m 04s | Avg:  5m 21s | Max:  5m 47s
      🟩 MSVC               Pass: 100%/6   | Total:  1h 03m | Avg: 10m 32s | Max: 12m 21s | Hits:  99%/4362  
    🟩 gpu
      🟩 v100               Pass: 100%/136 | Total: 20h 42m | Avg:  9m 08s | Max: 53m 46s | Hits:  99%/4362  
    🟩 jobs
      🟩 Build              Pass: 100%/103 | Total:  8h 58m | Avg:  5m 13s | Max: 53m 46s | Hits:  99%/4362  
      🟩 DeviceLaunch       Pass: 100%/8   | Total:  2h 34m | Avg: 19m 18s | Max: 27m 33s
      🟩 GraphCapture       Pass: 100%/8   | Total:  2h 07m | Avg: 15m 57s | Max: 18m 21s
      🟩 HostLaunch         Pass: 100%/8   | Total:  2h 53m | Avg: 21m 42s | Max: 33m 02s
      🟩 SmallGMem          Pass: 100%/1   | Total: 31m 53s | Avg: 31m 53s | Max: 31m 53s
      🟩 TestGPU            Pass: 100%/8   | Total:  3h 36m | Avg: 27m 05s | Max: 37m 04s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 33s | Avg:  4m 51s | Max:  5m 06s
      🟩 90a                Pass: 100%/4   | Total: 14m 21s | Avg:  3m 35s | Max:  3m 42s
    🟩 std
      🟩 11                 Pass: 100%/35  | Total:  5h 34m | Avg:  9m 33s | Max: 53m 46s
      🟩 14                 Pass: 100%/38  | Total:  4h 54m | Avg:  7m 45s | Max: 25m 36s | Hits:  99%/2181  
      🟩 17                 Pass: 100%/38  | Total:  6h 01m | Avg:  9m 31s | Max: 37m 04s | Hits:  99%/1454  
      🟩 20                 Pass: 100%/25  | Total:  4h 11m | Avg: 10m 03s | Max: 27m 08s | Hits:  99%/727   
    
  • 🟩 thrust: Pass: 100%/122 | Total: 14h 01m | Avg: 6m 54s | Max: 28m 44s | Hits: 99%/20070

    🟩 cpu
      🟩 amd64              Pass: 100%/114 | Total: 13h 25m | Avg:  7m 03s | Max: 28m 44s | Hits:  99%/20070 
      🟩 arm64              Pass: 100%/8   | Total: 36m 29s | Avg:  4m 33s | Max:  5m 15s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 14m | Avg:  4m 59s | Max: 16m 20s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 15m 24s | Avg:  5m 08s | Max:  5m 31s
      🟩 12.6               Pass: 100%/104 | Total: 12h 31m | Avg:  7m 13s | Max: 28m 44s | Hits:  99%/17840 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 16s | Avg:  4m 38s | Max:  4m 45s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 14m | Avg:  4m 59s | Max: 16m 20s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 15m 24s | Avg:  5m 08s | Max:  5m 31s
      🟩 nvcc12.6           Pass: 100%/102 | Total: 12h 22m | Avg:  7m 16s | Max: 28m 44s | Hits:  99%/17840 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 16s | Avg:  4m 38s | Max:  4m 45s
      🟩 nvcc               Pass: 100%/120 | Total: 13h 52m | Avg:  6m 56s | Max: 28m 44s | Hits:  99%/20070 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 29m 34s | Avg:  4m 55s | Max:  5m 57s
      🟩 Clang10            Pass: 100%/3   | Total: 18m 35s | Avg:  6m 11s | Max:  6m 21s
      🟩 Clang11            Pass: 100%/4   | Total: 19m 46s | Avg:  4m 56s | Max:  5m 14s
      🟩 Clang12            Pass: 100%/4   | Total: 19m 24s | Avg:  4m 51s | Max:  5m 12s
      🟩 Clang13            Pass: 100%/4   | Total: 19m 39s | Avg:  4m 54s | Max:  5m 12s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 36s | Avg:  4m 39s | Max:  4m 55s
      🟩 Clang15            Pass: 100%/4   | Total: 19m 32s | Avg:  4m 53s | Max:  5m 27s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 54s | Avg:  4m 58s | Max:  5m 19s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 32s | Avg:  4m 53s | Max:  5m 13s
      🟩 Clang18            Pass: 100%/18  | Total:  2h 29m | Avg:  8m 17s | Max: 24m 11s
      🟩 GCC6               Pass: 100%/2   | Total:  8m 45s | Avg:  4m 22s | Max:  4m 26s
      🟩 GCC7               Pass: 100%/6   | Total: 25m 55s | Avg:  4m 19s | Max:  4m 53s
      🟩 GCC8               Pass: 100%/6   | Total: 52m 04s | Avg:  8m 40s | Max: 28m 44s
      🟩 GCC9               Pass: 100%/6   | Total: 27m 14s | Avg:  4m 32s | Max:  5m 07s
      🟩 GCC10              Pass: 100%/4   | Total: 19m 49s | Avg:  4m 57s | Max:  5m 07s
      🟩 GCC11              Pass: 100%/7   | Total: 35m 21s | Avg:  5m 03s | Max:  5m 31s
      🟩 GCC12              Pass: 100%/4   | Total: 20m 16s | Avg:  5m 04s | Max:  5m 21s
      🟩 GCC13              Pass: 100%/20  | Total:  2h 24m | Avg:  7m 14s | Max: 16m 29s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 20m 04s | Avg:  6m 41s | Max:  7m 09s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 16m 20s | Avg: 16m 20s | Max: 16m 20s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 29m 34s | Avg: 14m 47s | Max: 14m 52s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  1h 47m | Avg: 17m 58s | Max: 21m 06s | Hits:  99%/13380 
    🟩 cxx_family
      🟩 Clang              Pass: 100%/55  | Total:  5h 33m | Avg:  6m 04s | Max: 24m 11s
      🟩 GCC                Pass: 100%/55  | Total:  5h 34m | Avg:  6m 04s | Max: 28m 44s
      🟩 Intel              Pass: 100%/3   | Total: 20m 04s | Avg:  6m 41s | Max:  7m 09s
      🟩 MSVC               Pass: 100%/9   | Total:  2h 33m | Avg: 17m 04s | Max: 21m 06s | Hits:  99%/20070 
    🟩 gpu
      🟩 v100               Pass: 100%/122 | Total: 14h 01m | Avg:  6m 54s | Max: 28m 44s | Hits:  99%/20070 
    🟩 jobs
      🟩 Build              Pass: 100%/103 | Total:  9h 50m | Avg:  5m 43s | Max: 28m 44s | Hits:  99%/13380 
      🟩 TestCPU            Pass: 100%/11  | Total:  1h 57m | Avg: 10m 43s | Max: 21m 06s | Hits:  99%/6690  
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 13m | Avg: 16m 41s | Max: 24m 11s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 15m 24s | Avg:  5m 08s | Max:  5m 31s
      🟩 90a                Pass: 100%/4   | Total: 17m 41s | Avg:  4m 25s | Max:  4m 36s
    🟩 std
      🟩 11                 Pass: 100%/31  | Total:  3h 22m | Avg:  6m 32s | Max: 28m 44s
      🟩 14                 Pass: 100%/35  | Total:  4h 04m | Avg:  6m 59s | Max: 18m 39s | Hits:  99%/8920  
      🟩 17                 Pass: 100%/34  | Total:  3h 46m | Avg:  6m 40s | Max: 20m 27s | Hits:  99%/6690  
      🟩 20                 Pass: 100%/22  | Total:  2h 47m | Avg:  7m 37s | Max: 21m 19s | Hits:  99%/4460  
    
  • 🟩 cudax: Pass: 100%/58 | Total: 2h 24m | Avg: 2m 29s | Max: 7m 15s | Hits: 90%/204

    🟩 cpu
      🟩 amd64              Pass: 100%/54  | Total:  2h 15m | Avg:  2m 30s | Max:  7m 15s | Hits:  90%/204   
      🟩 arm64              Pass: 100%/4   | Total:  8m 20s | Avg:  2m 05s | Max:  2m 29s
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total: 59m 00s | Avg:  2m 33s | Max:  7m 04s | Hits:  90%/102   
      🟩 12.6               Pass: 100%/35  | Total:  1h 25m | Avg:  2m 26s | Max:  7m 15s | Hits:  90%/102   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total: 59m 00s | Avg:  2m 33s | Max:  7m 04s | Hits:  90%/102   
      🟩 nvcc12.6           Pass: 100%/35  | Total:  1h 25m | Avg:  2m 26s | Max:  7m 15s | Hits:  90%/102   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/58  | Total:  2h 24m | Avg:  2m 29s | Max:  7m 15s | Hits:  90%/204   
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 08s | Avg:  2m 04s | Max:  2m 04s
      🟩 Clang10            Pass: 100%/2   | Total:  3m 58s | Avg:  1m 59s | Max:  2m 01s
      🟩 Clang11            Pass: 100%/4   | Total:  8m 15s | Avg:  2m 03s | Max:  2m 07s
      🟩 Clang12            Pass: 100%/4   | Total:  8m 44s | Avg:  2m 11s | Max:  2m 18s
      🟩 Clang13            Pass: 100%/4   | Total:  8m 19s | Avg:  2m 04s | Max:  2m 07s
      🟩 Clang14            Pass: 100%/6   | Total: 16m 45s | Avg:  2m 47s | Max:  4m 18s
      🟩 Clang15            Pass: 100%/2   | Total:  4m 15s | Avg:  2m 07s | Max:  2m 09s
      🟩 Clang16            Pass: 100%/4   | Total:  9m 30s | Avg:  2m 22s | Max:  2m 39s
      🟩 Clang17            Pass: 100%/2   | Total:  4m 08s | Avg:  2m 04s | Max:  2m 08s
      🟩 Clang18            Pass: 100%/4   | Total: 12m 29s | Avg:  3m 07s | Max:  4m 11s
      🟩 GCC9               Pass: 100%/2   | Total:  3m 56s | Avg:  1m 58s | Max:  2m 03s
      🟩 GCC10              Pass: 100%/4   | Total:  7m 22s | Avg:  1m 50s | Max:  1m 53s
      🟩 GCC11              Pass: 100%/4   | Total:  7m 35s | Avg:  1m 53s | Max:  1m 59s
      🟩 GCC12              Pass: 100%/9   | Total: 25m 04s | Avg:  2m 47s | Max:  4m 00s
      🟩 GCC13              Pass: 100%/3   | Total:  5m 25s | Avg:  1m 48s | Max:  1m 54s
      🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 04s | Avg:  7m 04s | Max:  7m 04s | Hits:  90%/102   
      🟩 MSVC14.39          Pass: 100%/1   | Total:  7m 15s | Avg:  7m 15s | Max:  7m 15s | Hits:  90%/102   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/34  | Total:  1h 20m | Avg:  2m 22s | Max:  4m 18s
      🟩 GCC                Pass: 100%/22  | Total: 49m 22s | Avg:  2m 14s | Max:  4m 00s
      🟩 MSVC               Pass: 100%/2   | Total: 14m 19s | Avg:  7m 09s | Max:  7m 15s | Hits:  90%/204   
    🟩 gpu
      🟩 v100               Pass: 100%/58  | Total:  2h 24m | Avg:  2m 29s | Max:  7m 15s | Hits:  90%/204   
    🟩 jobs
      🟩 Build              Pass: 100%/50  | Total:  1h 52m | Avg:  2m 15s | Max:  7m 15s | Hits:  90%/204   
      🟩 Test               Pass: 100%/8   | Total: 31m 33s | Avg:  3m 56s | Max:  4m 18s
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  1m 59s | Avg:  1m 59s | Max:  1m 59s
      🟩 90a                Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s
    🟩 std
      🟩 17                 Pass: 100%/32  | Total:  1h 12m | Avg:  2m 16s | Max:  4m 11s
      🟩 20                 Pass: 100%/26  | Total:  1h 11m | Avg:  2m 44s | Max:  7m 15s | Hits:  90%/204   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
Thrust
+/- CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
+/- Thrust
+/- CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 433)

# Runner
320 linux-amd64-cpu16
62 linux-amd64-gpu-v100-latest-1
28 linux-arm64-cpu16
23 windows-amd64-cpu16

Copy link
Contributor

🟨 CI finished in 8h 46m: Pass: 95%/433 | Total: 6d 21h | Avg: 22m 56s | Max: 1h 54m | Hits: 78%/24636
  • 🟨 libcudacxx: Pass: 91%/116 | Total: 1d 10h | Avg: 17m 43s | Max: 1h 03m

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  90%/108 | Total:  1d 08h | Avg: 17m 50s | Max:  1h 03m
      🟩 arm64              Pass: 100%/8   | Total:  2h 09m | Avg: 16m 10s | Max: 23m 21s
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 35m 36s | Avg: 17m 48s | Max: 18m 36s
      🔍 nvcc               Pass:  91%/114 | Total:  1d 09h | Avg: 17m 43s | Max:  1h 03m
    🟨 ctk
      🟨 11.1               Pass:  93%/15  | Total:  3h 35m | Avg: 14m 21s | Max: 22m 18s
      🟩 11.8               Pass: 100%/3   | Total:  1h 09m | Avg: 23m 08s | Max: 23m 37s
      🟨 12.6               Pass:  90%/98  | Total:  1d 05h | Avg: 18m 04s | Max:  1h 03m
    🟨 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 35m 36s | Avg: 17m 48s | Max: 18m 36s
      🟨 nvcc11.1           Pass:  93%/15  | Total:  3h 35m | Avg: 14m 21s | Max: 22m 18s
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 09m | Avg: 23m 08s | Max: 23m 37s
      🟨 nvcc12.6           Pass:  90%/96  | Total:  1d 04h | Avg: 18m 04s | Max:  1h 03m
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  1h 17m | Avg: 12m 59s | Max: 21m 31s
      🟩 Clang10            Pass: 100%/3   | Total: 41m 02s | Avg: 13m 40s | Max: 19m 37s
      🟩 Clang11            Pass: 100%/4   | Total: 59m 09s | Avg: 14m 47s | Max: 25m 57s
      🟩 Clang12            Pass: 100%/4   | Total:  1h 07m | Avg: 16m 54s | Max: 26m 24s
      🟩 Clang13            Pass: 100%/4   | Total:  1h 18m | Avg: 19m 30s | Max: 21m 09s
      🟩 Clang14            Pass: 100%/4   | Total:  1h 06m | Avg: 16m 37s | Max: 22m 50s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 14m | Avg: 18m 36s | Max: 27m 48s
      🟩 Clang16            Pass: 100%/4   | Total: 57m 12s | Avg: 14m 18s | Max: 27m 11s
      🟩 Clang17            Pass: 100%/4   | Total:  1h 19m | Avg: 19m 59s | Max: 25m 01s
      🟩 Clang18            Pass: 100%/14  | Total:  6h 00m | Avg: 25m 43s | Max:  1h 02m
      🟩 GCC6               Pass: 100%/2   | Total: 39m 09s | Avg: 19m 34s | Max: 22m 18s
      🟩 GCC7               Pass: 100%/6   | Total:  1h 42m | Avg: 17m 02s | Max: 21m 00s
      🟩 GCC8               Pass: 100%/6   | Total:  1h 46m | Avg: 17m 43s | Max: 24m 31s
      🟩 GCC9               Pass: 100%/6   | Total:  1h 24m | Avg: 14m 02s | Max: 21m 46s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 14m | Avg: 18m 39s | Max: 19m 47s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 00m | Avg: 17m 14s | Max: 25m 26s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 01m | Avg: 15m 19s | Max: 25m 37s
      🟨 GCC13              Pass:  80%/21  | Total:  6h 00m | Avg: 17m 09s | Max:  1h 03m
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 19m | Avg: 26m 24s | Max: 30m 44s
      🟥 MSVC14.16          Pass:   0%/1   | Total: 18m 27s | Avg: 18m 27s | Max: 18m 27s
      🟥 MSVC14.29          Pass:   0%/2   | Total: 17m 54s | Avg:  8m 57s | Max:  9m 02s
      🟥 MSVC14.39          Pass:   0%/3   | Total: 29m 45s | Avg:  9m 55s | Max: 10m 33s
    🟨 cxx_family
      🟩 Clang              Pass: 100%/51  | Total: 16h 02m | Avg: 18m 51s | Max:  1h 02m
      🟨 GCC                Pass:  92%/56  | Total: 15h 48m | Avg: 16m 56s | Max:  1h 03m
      🟩 Intel              Pass: 100%/3   | Total:  1h 19m | Avg: 26m 24s | Max: 30m 44s
      🟥 MSVC               Pass:   0%/6   | Total:  1h 06m | Avg: 11m 01s | Max: 18m 27s
    🟨 jobs
      🟨 Build              Pass:  94%/103 | Total:  1d 03h | Avg: 15m 48s | Max: 30m 44s
      🟥 NVRTC              Pass:   0%/4   | Total: 18m 26s | Avg:  4m 36s | Max:  4m 59s
      🟩 Test               Pass: 100%/8   | Total:  6h 47m | Avg: 50m 56s | Max:  1h 03m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 18s | Avg:  2m 18s | Max:  2m 18s
    🟨 gpu
      🟨 v100               Pass:  91%/116 | Total:  1d 10h | Avg: 17m 43s | Max:  1h 03m
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 09m | Avg: 23m 08s | Max: 23m 37s
      🟩 90a                Pass: 100%/4   | Total: 15m 46s | Avg:  3m 56s | Max:  4m 24s
    🟨 std
      🟨 11                 Pass:  96%/30  | Total:  8h 34m | Avg: 17m 08s | Max: 46m 45s
      🟨 14                 Pass:  87%/33  | Total:  9h 24m | Avg: 17m 06s | Max:  1h 03m
      🟨 17                 Pass:  90%/32  | Total: 10h 11m | Avg: 19m 06s | Max:  1h 02m
      🟨 20                 Pass:  90%/20  | Total:  6h 03m | Avg: 18m 09s | Max:  1h 02m
    
  • 🟨 cub: Pass: 93%/136 | Total: 4d 13h | Avg: 48m 13s | Max: 1h 54m | Hits: 79%/4362

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  92%/128 | Total:  4d 05h | Avg: 47m 46s | Max:  1h 54m | Hits:  79%/4362  
      🟩 arm64              Pass: 100%/8   | Total:  7h 24m | Avg: 55m 31s | Max:  1h 00m
    🔍 ctk: 12.6 🔍
      🟩 11.1               Pass: 100%/15  | Total: 10h 18m | Avg: 41m 14s | Max: 46m 10s | Hits:  82%/727   
      🟩 11.8               Pass: 100%/3   | Total:  2h 56m | Avg: 58m 53s | Max: 59m 57s
      🔍 12.6               Pass:  92%/118 | Total:  4d 00h | Avg: 48m 50s | Max:  1h 54m | Hits:  79%/3635  
    🔍 cudacxx: nvcc12.6 🔍
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  1h 59m | Avg: 59m 44s | Max:  1h 00m
      🟩 nvcc11.1           Pass: 100%/15  | Total: 10h 18m | Avg: 41m 14s | Max: 46m 10s | Hits:  82%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total:  2h 56m | Avg: 58m 53s | Max: 59m 57s
      🔍 nvcc12.6           Pass:  92%/116 | Total:  3d 22h | Avg: 48m 39s | Max:  1h 54m | Hits:  79%/3635  
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total:  1h 59m | Avg: 59m 44s | Max:  1h 00m
      🔍 nvcc               Pass:  93%/134 | Total:  4d 11h | Avg: 48m 03s | Max:  1h 54m | Hits:  79%/4362  
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 16m | Avg: 22m 46s | Max: 41m 11s
      🟩 Clang10            Pass: 100%/3   | Total: 54m 34s | Avg: 18m 11s | Max: 43m 47s
      🟩 Clang11            Pass: 100%/4   | Total:  2h 58m | Avg: 44m 36s | Max: 47m 17s
      🟩 Clang12            Pass: 100%/4   | Total:  2h 17m | Avg: 34m 17s | Max: 45m 54s
      🟩 Clang13            Pass: 100%/4   | Total:  2h 57m | Avg: 44m 26s | Max: 45m 00s
      🟩 Clang14            Pass: 100%/4   | Total:  2h 53m | Avg: 43m 23s | Max: 44m 24s
      🟩 Clang15            Pass: 100%/4   | Total:  2h 59m | Avg: 44m 51s | Max: 47m 05s
      🟩 Clang16            Pass: 100%/4   | Total:  2h 59m | Avg: 44m 55s | Max: 46m 22s
      🟩 Clang17            Pass: 100%/4   | Total:  2h 55m | Avg: 43m 58s | Max: 44m 51s
      🟨 Clang18            Pass:  84%/26  | Total:  1d 01h | Avg: 58m 59s | Max:  1h 27m
      🟩 GCC6               Pass: 100%/2   | Total:  1h 23m | Avg: 41m 36s | Max: 42m 32s
      🟩 GCC7               Pass: 100%/6   | Total:  3h 33m | Avg: 35m 31s | Max: 44m 15s
      🟩 GCC8               Pass: 100%/6   | Total:  3h 37m | Avg: 36m 15s | Max: 47m 16s
      🟩 GCC9               Pass: 100%/6   | Total:  2h 16m | Avg: 22m 48s | Max: 45m 17s
      🟩 GCC10              Pass: 100%/4   | Total:  2h 11m | Avg: 32m 52s | Max:  1h 16m
      🟩 GCC11              Pass: 100%/7   | Total:  3h 58m | Avg: 34m 03s | Max: 59m 57s
      🟩 GCC12              Pass: 100%/4   | Total:  3h 31m | Avg: 52m 47s | Max: 58m 10s
      🟨 GCC13              Pass:  82%/29  | Total:  1d 08h | Avg:  1h 06m | Max:  1h 54m
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 45m | Avg: 55m 01s | Max:  1h 02m
      🟩 MSVC14.16          Pass: 100%/1   | Total: 46m 10s | Avg: 46m 10s | Max: 46m 10s | Hits:  82%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 43m | Avg: 51m 57s | Max: 52m 01s | Hits:  79%/1454  
      🟩 MSVC14.39          Pass: 100%/3   | Total:  2h 37m | Avg: 52m 26s | Max: 54m 40s | Hits:  79%/2181  
    🟨 cxx_family
      🟨 Clang              Pass:  93%/63  | Total:  2d 00h | Avg: 46m 27s | Max:  1h 27m
      🟨 GCC                Pass:  92%/64  | Total:  2d 04h | Avg: 49m 22s | Max:  1h 54m
      🟩 Intel              Pass: 100%/3   | Total:  2h 45m | Avg: 55m 01s | Max:  1h 02m
      🟩 MSVC               Pass: 100%/6   | Total:  5h 07m | Avg: 51m 14s | Max: 54m 40s | Hits:  79%/4362  
    🟨 jobs
      🟩 Build              Pass: 100%/103 | Total:  2d 18h | Avg: 38m 56s | Max:  1h 16m | Hits:  79%/4362  
      🟩 DeviceLaunch       Pass: 100%/8   | Total: 10h 01m | Avg:  1h 15m | Max:  1h 26m
      🟩 GraphCapture       Pass: 100%/8   | Total:  9h 49m | Avg:  1h 13m | Max:  1h 28m
      🟩 HostLaunch         Pass: 100%/8   | Total:  9h 58m | Avg:  1h 14m | Max:  1h 27m
      🟥 SmallGMem          Pass:   0%/1   | Total:  1h 38m | Avg:  1h 38m | Max:  1h 38m
      🟥 TestGPU            Pass:   0%/8   | Total: 11h 00m | Avg:  1h 22m | Max:  1h 54m
    🟨 gpu
      🟨 v100               Pass:  93%/136 | Total:  4d 13h | Avg: 48m 13s | Max:  1h 54m | Hits:  79%/4362  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  2h 56m | Avg: 58m 53s | Max: 59m 57s
      🟩 90a                Pass: 100%/4   | Total: 15m 16s | Avg:  3m 49s | Max:  3m 58s
    🟨 std
      🟨 11                 Pass:  94%/35  | Total:  1d 05h | Avg: 50m 05s | Max:  1h 27m
      🟨 14                 Pass:  94%/38  | Total:  1d 00h | Avg: 38m 05s | Max:  1h 54m | Hits:  80%/2181  
      🟨 17                 Pass:  92%/38  | Total:  1d 08h | Avg: 51m 35s | Max:  1h 38m | Hits:  79%/1454  
      🟨 20                 Pass:  92%/25  | Total: 23h 18m | Avg: 55m 55s | Max:  1h 41m | Hits:  76%/727   
    
  • 🟥 pycuda: Pass: 0%/1 | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s

    🟥 cpu
      🟥 amd64              Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 ctk
      🟥 12.5               Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 cudacxx
      🟥 nvcc12.5           Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 cudacxx_family
      🟥 nvcc               Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 cxx
      🟥 GCC13              Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 cxx_family
      🟥 GCC                Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 gpu
      🟥 v100               Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    🟥 jobs
      🟥 Test               Pass:   0%/1   | Total: 12m 38s | Avg: 12m 38s | Max: 12m 38s
    
  • 🟩 thrust: Pass: 100%/122 | Total: 19h 09m | Avg: 9m 25s | Max: 1h 05m | Hits: 78%/20070

    🟩 cpu
      🟩 amd64              Pass: 100%/114 | Total: 18h 27m | Avg:  9m 42s | Max:  1h 05m | Hits:  78%/20070 
      🟩 arm64              Pass: 100%/8   | Total: 41m 39s | Avg:  5m 12s | Max:  7m 50s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 48m | Avg:  7m 15s | Max: 54m 08s | Hits:  67%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 14m 45s | Avg:  4m 55s | Max:  4m 59s
      🟩 12.6               Pass: 100%/104 | Total: 17h 05m | Avg:  9m 51s | Max:  1h 05m | Hits:  80%/17840 
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 35s | Avg:  4m 47s | Max:  4m 48s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 48m | Avg:  7m 15s | Max: 54m 08s | Hits:  67%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 45s | Avg:  4m 55s | Max:  4m 59s
      🟩 nvcc12.6           Pass: 100%/102 | Total: 16h 56m | Avg:  9m 57s | Max:  1h 05m | Hits:  80%/17840 
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 35s | Avg:  4m 47s | Max:  4m 48s
      🟩 nvcc               Pass: 100%/120 | Total: 18h 59m | Avg:  9m 29s | Max:  1h 05m | Hits:  78%/20070 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 28m 53s | Avg:  4m 48s | Max:  6m 04s
      🟩 Clang10            Pass: 100%/3   | Total: 17m 22s | Avg:  5m 47s | Max:  6m 16s
      🟩 Clang11            Pass: 100%/4   | Total: 20m 50s | Avg:  5m 12s | Max:  5m 30s
      🟩 Clang12            Pass: 100%/4   | Total: 19m 40s | Avg:  4m 55s | Max:  5m 02s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 45s | Avg:  4m 41s | Max:  4m 44s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 48s | Avg:  4m 42s | Max:  4m 59s
      🟩 Clang15            Pass: 100%/4   | Total: 20m 39s | Avg:  5m 09s | Max:  5m 37s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 20s | Avg:  4m 50s | Max:  5m 16s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 42s | Avg:  4m 55s | Max:  5m 13s
      🟩 Clang18            Pass: 100%/18  | Total:  2h 23m | Avg:  7m 56s | Max: 21m 09s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 24s | Avg:  3m 42s | Max:  3m 52s
      🟩 GCC7               Pass: 100%/6   | Total: 25m 26s | Avg:  4m 14s | Max:  4m 53s
      🟩 GCC8               Pass: 100%/6   | Total: 26m 10s | Avg:  4m 21s | Max:  4m 59s
      🟩 GCC9               Pass: 100%/6   | Total: 27m 42s | Avg:  4m 37s | Max:  5m 06s
      🟩 GCC10              Pass: 100%/4   | Total: 21m 11s | Avg:  5m 17s | Max:  5m 36s
      🟩 GCC11              Pass: 100%/7   | Total: 35m 28s | Avg:  5m 04s | Max:  5m 27s
      🟩 GCC12              Pass: 100%/4   | Total: 37m 52s | Avg:  9m 28s | Max: 14m 43s
      🟩 GCC13              Pass: 100%/20  | Total:  2h 41m | Avg:  8m 05s | Max: 15m 10s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 54m 20s | Avg: 18m 06s | Max: 22m 47s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 54m 08s | Avg: 54m 08s | Max: 54m 08s | Hits:  67%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 51m | Avg: 55m 46s | Max: 59m 51s | Hits:  68%/4460  
      🟩 MSVC14.39          Pass: 100%/6   | Total:  4h 19m | Avg: 43m 12s | Max:  1h 05m | Hits:  83%/13380 
    🟩 cxx_family
      🟩 Clang              Pass: 100%/55  | Total:  5h 27m | Avg:  5m 56s | Max: 21m 09s
      🟩 GCC                Pass: 100%/55  | Total:  5h 42m | Avg:  6m 14s | Max: 15m 10s
      🟩 Intel              Pass: 100%/3   | Total: 54m 20s | Avg: 18m 06s | Max: 22m 47s
      🟩 MSVC               Pass: 100%/9   | Total:  7h 04m | Avg: 47m 12s | Max:  1h 05m | Hits:  78%/20070 
    🟩 gpu
      🟩 v100               Pass: 100%/122 | Total: 19h 09m | Avg:  9m 25s | Max:  1h 05m | Hits:  78%/20070 
    🟩 jobs
      🟩 Build              Pass: 100%/103 | Total: 14h 50m | Avg:  8m 38s | Max:  1h 05m | Hits:  68%/13380 
      🟩 TestCPU            Pass: 100%/11  | Total:  2h 09m | Avg: 11m 48s | Max: 25m 37s | Hits:  99%/6690  
      🟩 TestGPU            Pass: 100%/8   | Total:  2h 09m | Avg: 16m 08s | Max: 21m 09s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 45s | Avg:  4m 55s | Max:  4m 59s
      🟩 90a                Pass: 100%/4   | Total: 17m 52s | Avg:  4m 28s | Max:  4m 38s
    🟩 std
      🟩 11                 Pass: 100%/31  | Total:  2h 57m | Avg:  5m 42s | Max: 21m 01s
      🟩 14                 Pass: 100%/35  | Total:  6h 27m | Avg: 11m 04s | Max:  1h 00m | Hits:  76%/8920  
      🟩 17                 Pass: 100%/34  | Total:  6h 03m | Avg: 10m 41s | Max:  1h 05m | Hits:  78%/6690  
      🟩 20                 Pass: 100%/22  | Total:  3h 41m | Avg: 10m 02s | Max: 59m 08s | Hits:  83%/4460  
    
  • 🟩 cudax: Pass: 100%/58 | Total: 2h 38m | Avg: 2m 44s | Max: 11m 48s | Hits: 90%/204

    🟩 cpu
      🟩 amd64              Pass: 100%/54  | Total:  2h 30m | Avg:  2m 46s | Max: 11m 48s | Hits:  90%/204   
      🟩 arm64              Pass: 100%/4   | Total:  8m 35s | Avg:  2m 08s | Max:  2m 35s
    🟩 ctk
      🟩 12.0               Pass: 100%/23  | Total:  1h 04m | Avg:  2m 49s | Max: 11m 48s | Hits:  90%/102   
      🟩 12.6               Pass: 100%/35  | Total:  1h 33m | Avg:  2m 41s | Max: 11m 03s | Hits:  90%/102   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 04m | Avg:  2m 49s | Max: 11m 48s | Hits:  90%/102   
      🟩 nvcc12.6           Pass: 100%/35  | Total:  1h 33m | Avg:  2m 41s | Max: 11m 03s | Hits:  90%/102   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/58  | Total:  2h 38m | Avg:  2m 44s | Max: 11m 48s | Hits:  90%/204   
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 44s | Avg:  2m 22s | Max:  2m 31s
      🟩 Clang10            Pass: 100%/2   | Total:  4m 17s | Avg:  2m 08s | Max:  2m 11s
      🟩 Clang11            Pass: 100%/4   | Total:  8m 28s | Avg:  2m 07s | Max:  2m 14s
      🟩 Clang12            Pass: 100%/4   | Total:  8m 09s | Avg:  2m 02s | Max:  2m 14s
      🟩 Clang13            Pass: 100%/4   | Total:  8m 59s | Avg:  2m 14s | Max:  2m 47s
      🟩 Clang14            Pass: 100%/6   | Total: 17m 10s | Avg:  2m 51s | Max:  4m 30s
      🟩 Clang15            Pass: 100%/2   | Total:  4m 10s | Avg:  2m 05s | Max:  2m 09s
      🟩 Clang16            Pass: 100%/4   | Total:  8m 17s | Avg:  2m 04s | Max:  2m 09s
      🟩 Clang17            Pass: 100%/2   | Total:  4m 06s | Avg:  2m 03s | Max:  2m 04s
      🟩 Clang18            Pass: 100%/4   | Total: 14m 09s | Avg:  3m 32s | Max:  4m 59s
      🟩 GCC9               Pass: 100%/2   | Total:  3m 32s | Avg:  1m 46s | Max:  1m 47s
      🟩 GCC10              Pass: 100%/4   | Total:  8m 20s | Avg:  2m 05s | Max:  2m 16s
      🟩 GCC11              Pass: 100%/4   | Total:  8m 04s | Avg:  2m 01s | Max:  2m 04s
      🟩 GCC12              Pass: 100%/9   | Total: 26m 30s | Avg:  2m 56s | Max:  4m 07s
      🟩 GCC13              Pass: 100%/3   | Total:  7m 02s | Avg:  2m 20s | Max:  2m 35s
      🟩 MSVC14.36          Pass: 100%/1   | Total: 11m 48s | Avg: 11m 48s | Max: 11m 48s | Hits:  90%/102   
      🟩 MSVC14.39          Pass: 100%/1   | Total: 11m 03s | Avg: 11m 03s | Max: 11m 03s | Hits:  90%/102   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/34  | Total:  1h 22m | Avg:  2m 25s | Max:  4m 59s
      🟩 GCC                Pass: 100%/22  | Total: 53m 28s | Avg:  2m 25s | Max:  4m 07s
      🟩 MSVC               Pass: 100%/2   | Total: 22m 51s | Avg: 11m 25s | Max: 11m 48s | Hits:  90%/204   
    🟩 gpu
      🟩 v100               Pass: 100%/58  | Total:  2h 38m | Avg:  2m 44s | Max: 11m 48s | Hits:  90%/204   
    🟩 jobs
      🟩 Build              Pass: 100%/50  | Total:  2h 05m | Avg:  2m 30s | Max: 11m 48s | Hits:  90%/204   
      🟩 Test               Pass: 100%/8   | Total: 33m 09s | Avg:  4m 08s | Max:  4m 59s
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  1m 57s | Avg:  1m 57s | Max:  1m 57s
      🟩 90a                Pass: 100%/1   | Total:  2m 30s | Avg:  2m 30s | Max:  2m 30s
    🟩 std
      🟩 17                 Pass: 100%/32  | Total:  1h 17m | Avg:  2m 25s | Max:  4m 30s
      🟩 20                 Pass: 100%/26  | Total:  1h 21m | Avg:  3m 07s | Max: 11m 48s | Hits:  90%/204   
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
+/- Thrust
+/- CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
+/- Thrust
+/- CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 433)

# Runner
320 linux-amd64-cpu16
62 linux-amd64-gpu-v100-latest-1
28 linux-arm64-cpu16
23 windows-amd64-cpu16

Copy link
Collaborator

@dkolsen-pgi dkolsen-pgi left a comment

Choose a reason for hiding this comment

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

I only looked at cuda/std/__cccl/assert.h. It looks fine to me. Thank you for using NV_IF_TARGET only for NVC++. I was going to suggest that.

@jrhemstad
Copy link
Collaborator

CCCL_ENABLE_HOST_ASSERTIONS This enables use of assertions in host code only
CCCL_ENABLE_DEVICE_ASSERTIONS This enables use of assertions in device code only
CCCL_ENABLE_ASSERTIONS This enables use of assertions in both host and device code

What is the default state for these flags and how does it interact with NDEBUG?

@miscco
Copy link
Collaborator Author

miscco commented Sep 19, 2024

CCCL_ENABLE_HOST_ASSERTIONS This enables use of assertions in host code only
CCCL_ENABLE_DEVICE_ASSERTIONS This enables use of assertions in device code only
CCCL_ENABLE_ASSERTIONS This enables use of assertions in both host and device code

What is the default state for these flags and how does it interact with NDEBUG?

I need to write some documentation dont I

The default is that those flags are not defined.

We only define them when the user defines DEBUG or _DEBUG and when the user defines CCCL_ENABLE_ASSERTIONS

Copy link
Contributor

🟨 CI finished in 52m 10s: Pass: 97%/364 | Total: 1d 20h | Avg: 7m 17s | Max: 43m 21s | Hits: 77%/23013
  • 🟨 libcudacxx: Pass: 92%/104 | Total: 20h 10m | Avg: 11m 38s | Max: 43m 21s | Hits: 42%/8747

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  91%/96  | Total: 19h 17m | Avg: 12m 03s | Max: 43m 21s | Hits:  42%/8747  
      🟩 arm64              Pass: 100%/8   | Total: 52m 51s | Avg:  6m 36s | Max: 16m 01s
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 36m 55s | Avg: 18m 27s | Max: 19m 18s
      🔍 nvcc               Pass:  92%/102 | Total: 19h 33m | Avg: 11m 30s | Max: 43m 21s | Hits:  42%/8747  
    🟨 ctk
      🟨 11.1               Pass:  93%/15  | Total:  1h 46m | Avg:  7m 04s | Max: 21m 48s
      🟩 11.8               Pass: 100%/3   | Total:  1h 11m | Avg: 23m 51s | Max: 27m 43s
      🟨 12.6               Pass:  91%/86  | Total: 17h 12m | Avg: 12m 00s | Max: 43m 21s | Hits:  42%/8747  
    🟨 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 36m 55s | Avg: 18m 27s | Max: 19m 18s
      🟨 nvcc11.1           Pass:  93%/15  | Total:  1h 46m | Avg:  7m 04s | Max: 21m 48s
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 11m | Avg: 23m 51s | Max: 27m 43s
      🟨 nvcc12.6           Pass:  91%/84  | Total: 16h 35m | Avg: 11m 51s | Max: 43m 21s | Hits:  42%/8747  
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 52m 07s | Avg:  8m 41s | Max: 20m 05s
      🟩 Clang10            Pass: 100%/3   | Total: 41m 19s | Avg: 13m 46s | Max: 21m 06s
      🟩 Clang11            Pass: 100%/4   | Total: 52m 28s | Avg: 13m 07s | Max: 25m 40s
      🟩 Clang12            Pass: 100%/4   | Total: 34m 08s | Avg:  8m 32s | Max: 21m 24s
      🟩 Clang13            Pass: 100%/4   | Total: 34m 59s | Avg:  8m 44s | Max: 22m 29s
      🟩 Clang14            Pass: 100%/4   | Total: 53m 13s | Avg: 13m 18s | Max: 21m 06s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 17m | Avg: 19m 29s | Max: 27m 08s
      🟩 Clang16            Pass: 100%/4   | Total: 17m 09s | Avg:  4m 17s | Max:  4m 55s
      🟩 Clang17            Pass: 100%/4   | Total: 26m 10s | Avg:  6m 32s | Max: 12m 45s
      🟨 Clang18            Pass:  87%/8   | Total:  1h 42m | Avg: 12m 50s | Max: 21m 41s
      🟩 GCC6               Pass: 100%/2   | Total:  5m 32s | Avg:  2m 46s | Max:  2m 47s
      🟩 GCC7               Pass: 100%/6   | Total: 49m 39s | Avg:  8m 16s | Max: 21m 48s
      🟩 GCC8               Pass: 100%/6   | Total: 20m 10s | Avg:  3m 21s | Max:  4m 06s
      🟩 GCC9               Pass: 100%/6   | Total: 35m 27s | Avg:  5m 54s | Max: 17m 30s
      🟩 GCC10              Pass: 100%/4   | Total: 29m 32s | Avg:  7m 23s | Max: 17m 36s
      🟩 GCC11              Pass: 100%/7   | Total:  1h 49m | Avg: 15m 42s | Max: 27m 43s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 05m | Avg: 16m 25s | Max: 23m 25s
      🟨 GCC13              Pass:  64%/17  | Total:  3h 09m | Avg: 11m 09s | Max: 29m 39s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  1h 14m | Avg: 24m 52s | Max: 30m 49s
      🟥 MSVC14.16          Pass:   0%/1   | Total: 19m 51s | Avg: 19m 51s | Max: 19m 51s
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 14m | Avg: 37m 11s | Max: 37m 57s | Hits:  43%/5666  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 43m 21s | Avg: 43m 21s | Max: 43m 21s | Hits:  40%/3081  
    🟨 cxx_family
      🟨 Clang              Pass:  97%/45  | Total:  8h 12m | Avg: 10m 56s | Max: 27m 08s
      🟨 GCC                Pass:  88%/52  | Total:  8h 25m | Avg:  9m 43s | Max: 29m 39s
      🟩 Intel              Pass: 100%/3   | Total:  1h 14m | Avg: 24m 52s | Max: 30m 49s
      🟨 MSVC               Pass:  75%/4   | Total:  2h 17m | Avg: 34m 23s | Max: 43m 21s | Hits:  42%/8747  
    🟨 jobs
      🟨 Build              Pass:  98%/96  | Total: 17h 30m | Avg: 10m 56s | Max: 43m 21s | Hits:  42%/8747  
      🟥 NVRTC              Pass:   0%/4   | Total:  1h 33m | Avg: 23m 17s | Max: 26m 35s
      🟥 Test               Pass:   0%/3   | Total:  1h 04m | Avg: 21m 30s | Max: 29m 39s
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  2m 18s | Avg:  2m 18s | Max:  2m 18s
    🟨 gpu
      🟨 v100               Pass:  92%/104 | Total: 20h 10m | Avg: 11m 38s | Max: 43m 21s | Hits:  42%/8747  
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 11m | Avg: 23m 51s | Max: 27m 43s
      🟩 90a                Pass: 100%/4   | Total: 15m 27s | Avg:  3m 51s | Max:  4m 12s
    🟨 std
      🟨 11                 Pass:  92%/28  | Total:  4h 29m | Avg:  9m 37s | Max: 22m 23s
      🟨 14                 Pass:  92%/28  | Total:  5h 13m | Avg: 11m 12s | Max: 36m 25s | Hits:  45%/2753  
      🟨 17                 Pass:  96%/27  | Total:  5h 34m | Avg: 12m 23s | Max: 37m 57s | Hits:  42%/2913  
      🟨 20                 Pass:  85%/20  | Total:  4h 50m | Avg: 14m 30s | Max: 43m 21s | Hits:  40%/3081  
    
  • 🟩 cub: Pass: 100%/104 | Total: 10h 52m | Avg: 6m 16s | Max: 35m 47s | Hits: 99%/2908

    🟩 cpu
      🟩 amd64              Pass: 100%/96  | Total: 10h 18m | Avg:  6m 26s | Max: 35m 47s | Hits:  99%/2908  
      🟩 arm64              Pass: 100%/8   | Total: 34m 19s | Avg:  4m 17s | Max:  4m 30s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 06m | Avg:  4m 25s | Max: 15m 11s | Hits:  99%/727   
      🟩 11.8               Pass: 100%/3   | Total: 14m 00s | Avg:  4m 40s | Max:  5m 00s
      🟩 12.6               Pass: 100%/86  | Total:  9h 32m | Avg:  6m 39s | Max: 35m 47s | Hits:  99%/2181  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  7m 08s | Avg:  3m 34s | Max:  3m 35s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 06m | Avg:  4m 25s | Max: 15m 11s | Hits:  99%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 00s | Avg:  4m 40s | Max:  5m 00s
      🟩 nvcc12.6           Pass: 100%/84  | Total:  9h 24m | Avg:  6m 43s | Max: 35m 47s | Hits:  99%/2181  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 08s | Avg:  3m 34s | Max:  3m 35s
      🟩 nvcc               Pass: 100%/102 | Total: 10h 45m | Avg:  6m 19s | Max: 35m 47s | Hits:  99%/2908  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 27m 50s | Avg:  4m 38s | Max:  5m 36s
      🟩 Clang10            Pass: 100%/3   | Total: 15m 25s | Avg:  5m 08s | Max:  5m 19s
      🟩 Clang11            Pass: 100%/4   | Total: 17m 30s | Avg:  4m 22s | Max:  4m 26s
      🟩 Clang12            Pass: 100%/4   | Total: 18m 09s | Avg:  4m 32s | Max:  4m 50s
      🟩 Clang13            Pass: 100%/4   | Total: 18m 54s | Avg:  4m 43s | Max:  5m 00s
      🟩 Clang14            Pass: 100%/4   | Total: 17m 12s | Avg:  4m 18s | Max:  4m 26s
      🟩 Clang15            Pass: 100%/4   | Total: 17m 38s | Avg:  4m 24s | Max:  4m 30s
      🟩 Clang16            Pass: 100%/4   | Total: 18m 21s | Avg:  4m 35s | Max:  4m 44s
      🟩 Clang17            Pass: 100%/4   | Total: 18m 25s | Avg:  4m 36s | Max:  5m 04s
      🟩 Clang18            Pass: 100%/9   | Total:  1h 20m | Avg:  8m 59s | Max: 28m 04s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 41s | Avg:  3m 50s | Max:  3m 54s
      🟩 GCC7               Pass: 100%/6   | Total: 23m 20s | Avg:  3m 53s | Max:  4m 27s
      🟩 GCC8               Pass: 100%/6   | Total: 24m 10s | Avg:  4m 01s | Max:  4m 53s
      🟩 GCC9               Pass: 100%/6   | Total: 24m 03s | Avg:  4m 00s | Max:  4m 24s
      🟩 GCC10              Pass: 100%/4   | Total: 18m 10s | Avg:  4m 32s | Max:  4m 42s
      🟩 GCC11              Pass: 100%/7   | Total: 32m 16s | Avg:  4m 36s | Max:  5m 00s
      🟩 GCC12              Pass: 100%/4   | Total: 18m 37s | Avg:  4m 39s | Max:  4m 52s
      🟩 GCC13              Pass: 100%/16  | Total:  2h 56m | Avg: 11m 03s | Max: 35m 47s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 17m 44s | Avg:  5m 54s | Max:  6m 02s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s | Hits:  99%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total: 29m 22s | Avg: 14m 41s | Max: 16m 19s | Hits:  99%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 14m 41s | Avg: 14m 41s | Max: 14m 41s | Hits:  99%/727   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  4h 10m | Avg:  5m 26s | Max: 28m 04s
      🟩 GCC                Pass: 100%/51  | Total:  5h 25m | Avg:  6m 22s | Max: 35m 47s
      🟩 Intel              Pass: 100%/3   | Total: 17m 44s | Avg:  5m 54s | Max:  6m 02s
      🟩 MSVC               Pass: 100%/4   | Total: 59m 14s | Avg: 14m 48s | Max: 16m 19s | Hits:  99%/2908  
    🟩 gpu
      🟩 v100               Pass: 100%/104 | Total: 10h 52m | Avg:  6m 16s | Max: 35m 47s | Hits:  99%/2908  
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  7h 44m | Avg:  4m 50s | Max: 16m 19s | Hits:  99%/2908  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 16m 32s | Avg: 16m 32s | Max: 16m 32s
      🟩 GraphCapture       Pass: 100%/1   | Total: 20m 30s | Avg: 20m 30s | Max: 20m 30s
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 00m | Avg: 20m 16s | Max: 24m 14s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 29m | Avg: 29m 59s | Max: 35m 47s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 00s | Avg:  4m 40s | Max:  5m 00s
      🟩 90a                Pass: 100%/4   | Total: 14m 29s | Avg:  3m 37s | Max:  3m 43s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 34m | Avg:  5m 31s | Max: 26m 06s
      🟩 14                 Pass: 100%/27  | Total:  2h 18m | Avg:  5m 07s | Max: 15m 11s | Hits:  99%/1454  
      🟩 17                 Pass: 100%/26  | Total:  2h 08m | Avg:  4m 56s | Max: 16m 19s | Hits:  99%/727   
      🟩 20                 Pass: 100%/23  | Total:  3h 51m | Avg: 10m 02s | Max: 35m 47s | Hits:  99%/727   
    
  • 🟩 thrust: Pass: 100%/103 | Total: 10h 16m | Avg: 5m 59s | Max: 23m 48s | Hits: 99%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total:  9h 39m | Avg:  6m 06s | Max: 23m 48s | Hits:  99%/11150 
      🟩 arm64              Pass: 100%/8   | Total: 36m 39s | Avg:  4m 34s | Max:  5m 09s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 18m | Avg:  5m 15s | Max: 21m 05s | Hits:  99%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 15m 07s | Avg:  5m 02s | Max:  5m 29s
      🟩 12.6               Pass: 100%/85  | Total:  8h 42m | Avg:  6m 08s | Max: 23m 48s | Hits:  99%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  9m 46s | Avg:  4m 53s | Max:  5m 01s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 18m | Avg:  5m 15s | Max: 21m 05s | Hits:  99%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 15m 07s | Avg:  5m 02s | Max:  5m 29s
      🟩 nvcc12.6           Pass: 100%/83  | Total:  8h 32m | Avg:  6m 10s | Max: 23m 48s | Hits:  99%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  9m 46s | Avg:  4m 53s | Max:  5m 01s
      🟩 nvcc               Pass: 100%/101 | Total: 10h 06m | Avg:  6m 00s | Max: 23m 48s | Hits:  99%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 30m 06s | Avg:  5m 01s | Max:  6m 06s
      🟩 Clang10            Pass: 100%/3   | Total: 17m 58s | Avg:  5m 59s | Max:  6m 06s
      🟩 Clang11            Pass: 100%/4   | Total: 19m 25s | Avg:  4m 51s | Max:  5m 23s
      🟩 Clang12            Pass: 100%/4   | Total: 19m 26s | Avg:  4m 51s | Max:  5m 02s
      🟩 Clang13            Pass: 100%/4   | Total: 19m 43s | Avg:  4m 55s | Max:  5m 12s
      🟩 Clang14            Pass: 100%/4   | Total: 20m 14s | Avg:  5m 03s | Max:  5m 17s
      🟩 Clang15            Pass: 100%/4   | Total: 20m 22s | Avg:  5m 05s | Max:  5m 21s
      🟩 Clang16            Pass: 100%/4   | Total: 19m 22s | Avg:  4m 50s | Max:  5m 01s
      🟩 Clang17            Pass: 100%/4   | Total: 20m 22s | Avg:  5m 05s | Max:  5m 35s
      🟩 Clang18            Pass: 100%/9   | Total: 59m 19s | Avg:  6m 35s | Max: 18m 51s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 48s | Avg:  3m 54s | Max:  4m 01s
      🟩 GCC7               Pass: 100%/6   | Total: 25m 39s | Avg:  4m 16s | Max:  5m 03s
      🟩 GCC8               Pass: 100%/6   | Total: 25m 22s | Avg:  4m 13s | Max:  4m 41s
      🟩 GCC9               Pass: 100%/6   | Total: 26m 36s | Avg:  4m 26s | Max:  4m 41s
      🟩 GCC10              Pass: 100%/4   | Total: 19m 41s | Avg:  4m 55s | Max:  5m 26s
      🟩 GCC11              Pass: 100%/7   | Total: 34m 40s | Avg:  4m 57s | Max:  5m 29s
      🟩 GCC12              Pass: 100%/4   | Total: 20m 16s | Avg:  5m 04s | Max:  5m 12s
      🟩 GCC13              Pass: 100%/14  | Total:  1h 32m | Avg:  6m 37s | Max: 19m 19s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total: 19m 01s | Avg:  6m 20s | Max:  6m 23s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 21m 05s | Avg: 21m 05s | Max: 21m 05s | Hits:  99%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total: 35m 25s | Avg: 17m 42s | Max: 18m 21s | Hits:  99%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total: 41m 40s | Avg: 20m 50s | Max: 23m 48s | Hits:  99%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  4h 06m | Avg:  5m 21s | Max: 18m 51s
      🟩 GCC                Pass: 100%/49  | Total:  4h 12m | Avg:  5m 09s | Max: 19m 19s
      🟩 Intel              Pass: 100%/3   | Total: 19m 01s | Avg:  6m 20s | Max:  6m 23s
      🟩 MSVC               Pass: 100%/5   | Total:  1h 38m | Avg: 19m 38s | Max: 23m 48s | Hits:  99%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total: 10h 16m | Avg:  5m 59s | Max: 23m 48s | Hits:  99%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  8h 38m | Avg:  5m 24s | Max: 21m 05s | Hits:  99%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total: 45m 07s | Avg: 11m 16s | Max: 23m 48s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 52m 44s | Avg: 17m 34s | Max: 19m 19s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 15m 07s | Avg:  5m 02s | Max:  5m 29s
      🟩 90a                Pass: 100%/4   | Total: 16m 07s | Avg:  4m 01s | Max:  4m 17s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  2h 24m | Avg:  5m 09s | Max: 19m 19s
      🟩 14                 Pass: 100%/27  | Total:  2h 38m | Avg:  5m 51s | Max: 21m 05s | Hits:  99%/4460  
      🟩 17                 Pass: 100%/26  | Total:  2h 24m | Avg:  5m 33s | Max: 17m 04s | Hits:  99%/2230  
      🟩 20                 Pass: 100%/22  | Total:  2h 49m | Avg:  7m 42s | Max: 23m 48s | Hits:  99%/4460  
    
  • 🟩 cudax: Pass: 100%/52 | Total: 2h 40m | Avg: 3m 05s | Max: 10m 41s | Hits: 80%/208

    🟩 cpu
      🟩 amd64              Pass: 100%/48  | Total:  2h 29m | Avg:  3m 07s | Max: 10m 41s | Hits:  80%/208   
      🟩 arm64              Pass: 100%/4   | Total: 11m 08s | Avg:  2m 47s | Max:  3m 05s
    🟩 ctk
      🟩 12.0               Pass: 100%/19  | Total: 56m 48s | Avg:  2m 59s | Max: 10m 27s | Hits:  80%/104   
      🟩 12.6               Pass: 100%/33  | Total:  1h 44m | Avg:  3m 09s | Max: 10m 41s | Hits:  80%/104   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/19  | Total: 56m 48s | Avg:  2m 59s | Max: 10m 27s | Hits:  80%/104   
      🟩 nvcc12.6           Pass: 100%/33  | Total:  1h 44m | Avg:  3m 09s | Max: 10m 41s | Hits:  80%/104   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/52  | Total:  2h 40m | Avg:  3m 05s | Max: 10m 41s | Hits:  80%/208   
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  5m 33s | Avg:  2m 46s | Max:  3m 07s
      🟩 Clang10            Pass: 100%/2   | Total:  5m 08s | Avg:  2m 34s | Max:  2m 45s
      🟩 Clang11            Pass: 100%/4   | Total: 10m 35s | Avg:  2m 38s | Max:  3m 04s
      🟩 Clang12            Pass: 100%/4   | Total:  9m 50s | Avg:  2m 27s | Max:  2m 37s
      🟩 Clang13            Pass: 100%/4   | Total: 10m 49s | Avg:  2m 42s | Max:  2m 58s
      🟩 Clang14            Pass: 100%/4   | Total: 12m 25s | Avg:  3m 06s | Max:  4m 02s
      🟩 Clang15            Pass: 100%/2   | Total:  5m 38s | Avg:  2m 49s | Max:  2m 52s
      🟩 Clang16            Pass: 100%/4   | Total: 10m 58s | Avg:  2m 44s | Max:  3m 07s
      🟩 Clang17            Pass: 100%/2   | Total:  5m 39s | Avg:  2m 49s | Max:  2m 55s
      🟩 Clang18            Pass: 100%/2   | Total:  7m 11s | Avg:  3m 35s | Max:  4m 39s
      🟩 GCC9               Pass: 100%/2   | Total:  4m 52s | Avg:  2m 26s | Max:  2m 42s
      🟩 GCC10              Pass: 100%/4   | Total:  9m 51s | Avg:  2m 27s | Max:  2m 37s
      🟩 GCC11              Pass: 100%/4   | Total: 10m 46s | Avg:  2m 41s | Max:  3m 03s
      🟩 GCC12              Pass: 100%/7   | Total: 22m 14s | Avg:  3m 10s | Max:  4m 21s
      🟩 GCC13              Pass: 100%/3   | Total:  8m 12s | Avg:  2m 44s | Max:  3m 05s
      🟩 MSVC14.36          Pass: 100%/1   | Total: 10m 27s | Avg: 10m 27s | Max: 10m 27s | Hits:  80%/104   
      🟩 MSVC14.39          Pass: 100%/1   | Total: 10m 41s | Avg: 10m 41s | Max: 10m 41s | Hits:  80%/104   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 23m | Avg:  2m 47s | Max:  4m 39s
      🟩 GCC                Pass: 100%/20  | Total: 55m 55s | Avg:  2m 47s | Max:  4m 21s
      🟩 MSVC               Pass: 100%/2   | Total: 21m 08s | Avg: 10m 34s | Max: 10m 41s | Hits:  80%/208   
    🟩 gpu
      🟩 v100               Pass: 100%/52  | Total:  2h 40m | Avg:  3m 05s | Max: 10m 41s | Hits:  80%/208   
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 19m | Avg:  2m 58s | Max: 10m 41s | Hits:  80%/208   
      🟩 Test               Pass: 100%/5   | Total: 21m 07s | Avg:  4m 13s | Max:  4m 39s
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 14s | Avg:  2m 14s | Max:  2m 14s
      🟩 90a                Pass: 100%/1   | Total:  2m 13s | Avg:  2m 13s | Max:  2m 13s
    🟩 std
      🟩 17                 Pass: 100%/28  | Total:  1h 15m | Avg:  2m 42s | Max:  4m 06s
      🟩 20                 Pass: 100%/24  | Total:  1h 25m | Avg:  3m 32s | Max: 10m 41s | Hits:  80%/208   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
Thrust
+/- CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
+/- Thrust
+/- CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 364)

# Runner
297 linux-amd64-cpu16
28 linux-arm64-cpu16
24 linux-amd64-gpu-v100-latest-1
15 windows-amd64-cpu16

@miscco miscco force-pushed the enable_asserts branch 2 times, most recently from 76b8117 to fa5ebe7 Compare September 20, 2024 16:07
Copy link
Contributor

🟨 CI finished in 2h 03m: Pass: 97%/364 | Total: 4d 00h | Avg: 15m 57s | Max: 1h 24m | Hits: 15%/25679
  • 🟨 libcudacxx: Pass: 90%/104 | Total: 1d 17h | Avg: 23m 44s | Max: 1h 24m | Hits: 14%/11407

    🔍 cpu: amd64 🔍
      🔍 amd64              Pass:  89%/96  | Total:  1d 14h | Avg: 23m 53s | Max:  1h 24m | Hits:  14%/11407 
      🟩 arm64              Pass: 100%/8   | Total:  2h 56m | Avg: 22m 05s | Max: 28m 16s
    🔍 ctk: 12.6 🔍
      🟩 11.1               Pass: 100%/15  | Total:  5h 33m | Avg: 22m 15s | Max: 44m 11s | Hits:  16%/2654  
      🟩 11.8               Pass: 100%/3   | Total:  1h 12m | Avg: 24m 02s | Max: 27m 44s
      🔍 12.6               Pass:  88%/86  | Total:  1d 10h | Avg: 23m 59s | Max:  1h 24m | Hits:  14%/8753  
    🔍 cudacxx: nvcc12.6 🔍
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 37m 21s | Avg: 18m 40s | Max: 20m 01s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  5h 33m | Avg: 22m 15s | Max: 44m 11s | Hits:  16%/2654  
      🟩 nvcc11.8           Pass: 100%/3   | Total:  1h 12m | Avg: 24m 02s | Max: 27m 44s
      🔍 nvcc12.6           Pass:  88%/84  | Total:  1d 09h | Avg: 24m 07s | Max:  1h 24m | Hits:  14%/8753  
    🔍 cudacxx_family: nvcc 🔍
      🟩 ClangCUDA          Pass: 100%/2   | Total: 37m 21s | Avg: 18m 40s | Max: 20m 01s
      🔍 nvcc               Pass:  90%/102 | Total:  1d 16h | Avg: 23m 50s | Max:  1h 24m | Hits:  14%/11407 
    🟨 cxx
      🟩 Clang9             Pass: 100%/6   | Total:  2h 16m | Avg: 22m 43s | Max: 27m 08s
      🟩 Clang10            Pass: 100%/3   | Total:  1h 11m | Avg: 23m 57s | Max: 27m 34s
      🟩 Clang11            Pass: 100%/4   | Total:  1h 33m | Avg: 23m 20s | Max: 25m 13s
      🟩 Clang12            Pass: 100%/4   | Total:  1h 40m | Avg: 25m 09s | Max: 29m 46s
      🟩 Clang13            Pass: 100%/4   | Total:  1h 34m | Avg: 23m 44s | Max: 26m 14s
      🟩 Clang14            Pass: 100%/4   | Total:  1h 39m | Avg: 24m 58s | Max: 29m 17s
      🟩 Clang15            Pass: 100%/4   | Total:  1h 35m | Avg: 23m 58s | Max: 28m 34s
      🟩 Clang16            Pass: 100%/4   | Total:  1h 39m | Avg: 24m 46s | Max: 30m 47s
      🟩 Clang17            Pass: 100%/4   | Total:  1h 33m | Avg: 23m 16s | Max: 26m 25s
      🟨 Clang18            Pass:  87%/8   | Total:  2h 44m | Avg: 20m 30s | Max: 25m 59s
      🟩 GCC6               Pass: 100%/2   | Total: 38m 20s | Avg: 19m 10s | Max: 21m 42s
      🟩 GCC7               Pass: 100%/6   | Total:  2h 07m | Avg: 21m 13s | Max: 24m 40s
      🟩 GCC8               Pass: 100%/6   | Total:  2h 07m | Avg: 21m 16s | Max: 24m 46s
      🟩 GCC9               Pass: 100%/6   | Total:  2h 17m | Avg: 22m 53s | Max: 26m 15s
      🟩 GCC10              Pass: 100%/4   | Total:  1h 34m | Avg: 23m 43s | Max: 29m 21s
      🟩 GCC11              Pass: 100%/7   | Total:  2h 44m | Avg: 23m 33s | Max: 27m 44s
      🟩 GCC12              Pass: 100%/4   | Total:  1h 41m | Avg: 25m 24s | Max: 29m 53s
      🟨 GCC13              Pass:  64%/17  | Total:  7h 24m | Avg: 26m 08s | Max:  1h 24m
      🟥 Intel2023.2.0      Pass:   0%/3   | Total: 11m 58s | Avg:  3m 59s | Max:  5m 57s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 44m 11s | Avg: 44m 11s | Max: 44m 11s | Hits:  16%/2654  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 21m | Avg: 40m 35s | Max: 40m 55s | Hits:  14%/5670  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 46m 41s | Avg: 46m 41s | Max: 46m 41s | Hits:  13%/3083  
    🟨 cxx_family
      🟨 Clang              Pass:  97%/45  | Total: 17h 29m | Avg: 23m 18s | Max: 30m 47s
      🟨 GCC                Pass:  88%/52  | Total: 20h 36m | Avg: 23m 46s | Max:  1h 24m
      🟥 Intel              Pass:   0%/3   | Total: 11m 58s | Avg:  3m 59s | Max:  5m 57s
      🟩 MSVC               Pass: 100%/4   | Total:  2h 52m | Avg: 43m 00s | Max: 46m 41s | Hits:  14%/11407 
    🟨 jobs
      🟨 Build              Pass:  96%/96  | Total:  1d 13h | Avg: 23m 10s | Max: 46m 41s | Hits:  14%/11407 
      🟥 NVRTC              Pass:   0%/4   | Total:  1h 33m | Avg: 23m 17s | Max: 25m 36s
      🟥 Test               Pass:   0%/3   | Total:  2h 29m | Avg: 49m 52s | Max:  1h 24m
      🟩 VerifyCodegen      Pass: 100%/1   | Total:  1m 49s | Avg:  1m 49s | Max:  1m 49s
    🟨 gpu
      🟨 v100               Pass:  90%/104 | Total:  1d 17h | Avg: 23m 44s | Max:  1h 24m | Hits:  14%/11407 
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total:  1h 12m | Avg: 24m 02s | Max: 27m 44s
      🟩 90a                Pass: 100%/4   | Total:  1h 10m | Avg: 17m 36s | Max: 20m 47s
    🟨 std
      🟨 11                 Pass:  89%/28  | Total:  9h 45m | Avg: 20m 53s | Max: 47m 44s
      🟨 14                 Pass:  92%/28  | Total: 10h 13m | Avg: 21m 54s | Max: 44m 11s | Hits:  15%/5409  
      🟨 17                 Pass:  92%/27  | Total: 11h 07m | Avg: 24m 44s | Max: 40m 55s | Hits:  14%/2915  
      🟨 20                 Pass:  85%/20  | Total: 10h 01m | Avg: 30m 04s | Max:  1h 24m | Hits:  13%/3083  
    
  • 🟩 cub: Pass: 100%/104 | Total: 1d 02h | Avg: 15m 12s | Max: 1h 16m | Hits: 2%/2908

    🟩 cpu
      🟩 amd64              Pass: 100%/96  | Total: 22h 23m | Avg: 13m 59s | Max:  1h 16m | Hits:   2%/2908  
      🟩 arm64              Pass: 100%/8   | Total:  3h 57m | Avg: 29m 44s | Max:  1h 00m
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  1h 49m | Avg:  7m 17s | Max: 58m 06s | Hits:   2%/727   
      🟩 11.8               Pass: 100%/3   | Total: 14m 01s | Avg:  4m 40s | Max:  4m 59s
      🟩 12.6               Pass: 100%/86  | Total:  1d 00h | Avg: 16m 57s | Max:  1h 16m | Hits:   2%/2181  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  7m 37s | Avg:  3m 48s | Max:  3m 51s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  1h 49m | Avg:  7m 17s | Max: 58m 06s | Hits:   2%/727   
      🟩 nvcc11.8           Pass: 100%/3   | Total: 14m 01s | Avg:  4m 40s | Max:  4m 59s
      🟩 nvcc12.6           Pass: 100%/84  | Total:  1d 00h | Avg: 17m 15s | Max:  1h 16m | Hits:   2%/2181  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  7m 37s | Avg:  3m 48s | Max:  3m 51s
      🟩 nvcc               Pass: 100%/102 | Total:  1d 02h | Avg: 15m 25s | Max:  1h 16m | Hits:   2%/2908  
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 26m 25s | Avg:  4m 24s | Max:  5m 01s
      🟩 Clang10            Pass: 100%/3   | Total: 16m 36s | Avg:  5m 32s | Max:  5m 41s
      🟩 Clang11            Pass: 100%/4   | Total: 17m 50s | Avg:  4m 27s | Max:  4m 48s
      🟩 Clang12            Pass: 100%/4   | Total: 17m 32s | Avg:  4m 23s | Max:  4m 47s
      🟩 Clang13            Pass: 100%/4   | Total: 17m 37s | Avg:  4m 24s | Max:  4m 42s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 11s | Avg:  4m 32s | Max:  4m 47s
      🟩 Clang15            Pass: 100%/4   | Total: 18m 27s | Avg:  4m 36s | Max:  5m 07s
      🟩 Clang16            Pass: 100%/4   | Total: 18m 34s | Avg:  4m 38s | Max:  4m 54s
      🟩 Clang17            Pass: 100%/4   | Total: 18m 27s | Avg:  4m 36s | Max:  5m 04s
      🟩 Clang18            Pass: 100%/9   | Total:  1h 22m | Avg:  9m 08s | Max: 30m 08s
      🟩 GCC6               Pass: 100%/2   | Total:  7m 24s | Avg:  3m 42s | Max:  3m 49s
      🟩 GCC7               Pass: 100%/6   | Total: 23m 45s | Avg:  3m 57s | Max:  4m 44s
      🟩 GCC8               Pass: 100%/6   | Total: 24m 16s | Avg:  4m 02s | Max:  4m 41s
      🟩 GCC9               Pass: 100%/6   | Total: 24m 42s | Avg:  4m 07s | Max:  4m 37s
      🟩 GCC10              Pass: 100%/4   | Total: 17m 16s | Avg:  4m 19s | Max:  4m 27s
      🟩 GCC11              Pass: 100%/7   | Total: 31m 16s | Avg:  4m 28s | Max:  4m 59s
      🟩 GCC12              Pass: 100%/4   | Total:  3h 42m | Avg: 55m 31s | Max:  1h 01m
      🟩 GCC13              Pass: 100%/16  | Total:  9h 00m | Avg: 33m 47s | Max:  1h 00m
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 50m | Avg: 56m 51s | Max: 58m 29s
      🟩 MSVC14.16          Pass: 100%/1   | Total: 58m 06s | Avg: 58m 06s | Max: 58m 06s | Hits:   2%/727   
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 12m | Avg:  1h 06m | Max:  1h 07m | Hits:   2%/1454  
      🟩 MSVC14.39          Pass: 100%/1   | Total:  1h 16m | Avg:  1h 16m | Max:  1h 16m | Hits:   2%/727   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  4h 11m | Avg:  5m 28s | Max: 30m 08s
      🟩 GCC                Pass: 100%/51  | Total: 14h 51m | Avg: 17m 28s | Max:  1h 01m
      🟩 Intel              Pass: 100%/3   | Total:  2h 50m | Avg: 56m 51s | Max: 58m 29s
      🟩 MSVC               Pass: 100%/4   | Total:  4h 27m | Avg:  1h 06m | Max:  1h 16m | Hits:   2%/2908  
    🟩 gpu
      🟩 v100               Pass: 100%/104 | Total:  1d 02h | Avg: 15m 12s | Max:  1h 16m | Hits:   2%/2908  
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total: 23h 30m | Avg: 14m 41s | Max:  1h 16m | Hits:   2%/2908  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 18m 54s | Avg: 18m 54s | Max: 18m 54s
      🟩 GraphCapture       Pass: 100%/1   | Total: 15m 26s | Avg: 15m 26s | Max: 15m 26s
      🟩 HostLaunch         Pass: 100%/3   | Total: 57m 02s | Avg: 19m 00s | Max: 23m 01s
      🟩 TestGPU            Pass: 100%/3   | Total:  1h 19m | Avg: 26m 29s | Max: 30m 08s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 14m 01s | Avg:  4m 40s | Max:  4m 59s
      🟩 90a                Pass: 100%/4   | Total:  1h 34m | Avg: 23m 32s | Max: 24m 23s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  6h 16m | Avg: 13m 27s | Max:  1h 01m
      🟩 14                 Pass: 100%/27  | Total:  6h 36m | Avg: 14m 42s | Max:  1h 04m | Hits:   2%/1454  
      🟩 17                 Pass: 100%/26  | Total:  5h 51m | Avg: 13m 30s | Max:  1h 07m | Hits:   2%/727   
      🟩 20                 Pass: 100%/23  | Total:  7h 36m | Avg: 19m 49s | Max:  1h 16m | Hits:   2%/727   
    
  • 🟩 thrust: Pass: 100%/103 | Total: 1d 02h | Avg: 15m 32s | Max: 1h 18m | Hits: 19%/11150

    🟩 cpu
      🟩 amd64              Pass: 100%/95  | Total: 23h 55m | Avg: 15m 06s | Max:  1h 18m | Hits:  19%/11150 
      🟩 arm64              Pass: 100%/8   | Total:  2h 45m | Avg: 20m 39s | Max: 39m 55s
    🟩 ctk
      🟩 11.1               Pass: 100%/15  | Total:  2h 56m | Avg: 11m 47s | Max:  1h 08m | Hits:   0%/2230  
      🟩 11.8               Pass: 100%/3   | Total: 27m 29s | Avg:  9m 09s | Max:  9m 45s
      🟩 12.6               Pass: 100%/85  | Total: 23h 16m | Avg: 16m 25s | Max:  1h 18m | Hits:  24%/8920  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  8m 39s | Avg:  4m 19s | Max:  4m 21s
      🟩 nvcc11.1           Pass: 100%/15  | Total:  2h 56m | Avg: 11m 47s | Max:  1h 08m | Hits:   0%/2230  
      🟩 nvcc11.8           Pass: 100%/3   | Total: 27m 29s | Avg:  9m 09s | Max:  9m 45s
      🟩 nvcc12.6           Pass: 100%/83  | Total: 23h 07m | Avg: 16m 42s | Max:  1h 18m | Hits:  24%/8920  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  8m 39s | Avg:  4m 19s | Max:  4m 21s
      🟩 nvcc               Pass: 100%/101 | Total:  1d 02h | Avg: 15m 45s | Max:  1h 18m | Hits:  19%/11150 
    🟩 cxx
      🟩 Clang9             Pass: 100%/6   | Total: 53m 21s | Avg:  8m 53s | Max:  9m 57s
      🟩 Clang10            Pass: 100%/3   | Total: 30m 29s | Avg: 10m 09s | Max: 11m 20s
      🟩 Clang11            Pass: 100%/4   | Total: 36m 17s | Avg:  9m 04s | Max:  9m 53s
      🟩 Clang12            Pass: 100%/4   | Total: 36m 45s | Avg:  9m 11s | Max: 10m 16s
      🟩 Clang13            Pass: 100%/4   | Total: 36m 51s | Avg:  9m 12s | Max: 10m 09s
      🟩 Clang14            Pass: 100%/4   | Total: 18m 26s | Avg:  4m 36s | Max:  4m 58s
      🟩 Clang15            Pass: 100%/4   | Total: 19m 29s | Avg:  4m 52s | Max:  5m 09s
      🟩 Clang16            Pass: 100%/4   | Total: 20m 43s | Avg:  5m 10s | Max:  5m 57s
      🟩 Clang17            Pass: 100%/4   | Total: 19m 23s | Avg:  4m 50s | Max:  5m 11s
      🟩 Clang18            Pass: 100%/9   | Total: 53m 13s | Avg:  5m 54s | Max: 14m 35s
      🟩 GCC6               Pass: 100%/2   | Total: 14m 55s | Avg:  7m 27s | Max:  7m 29s
      🟩 GCC7               Pass: 100%/6   | Total: 47m 12s | Avg:  7m 52s | Max:  9m 16s
      🟩 GCC8               Pass: 100%/6   | Total: 49m 04s | Avg:  8m 10s | Max:  9m 08s
      🟩 GCC9               Pass: 100%/6   | Total: 51m 50s | Avg:  8m 38s | Max: 10m 21s
      🟩 GCC10              Pass: 100%/4   | Total: 34m 36s | Avg:  8m 39s | Max:  9m 16s
      🟩 GCC11              Pass: 100%/7   | Total:  1h 04m | Avg:  9m 15s | Max: 11m 01s
      🟩 GCC12              Pass: 100%/4   | Total:  2h 44m | Avg: 41m 08s | Max: 50m 22s
      🟩 GCC13              Pass: 100%/14  | Total:  6h 09m | Avg: 26m 24s | Max: 39m 55s
      🟩 Intel2023.2.0      Pass: 100%/3   | Total:  2h 42m | Avg: 54m 13s | Max: 59m 23s
      🟩 MSVC14.16          Pass: 100%/1   | Total:  1h 08m | Avg:  1h 08m | Max:  1h 08m | Hits:   0%/2230  
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 23m | Avg:  1h 11m | Max:  1h 14m | Hits:   0%/4460  
      🟩 MSVC14.39          Pass: 100%/2   | Total:  1h 43m | Avg: 51m 57s | Max:  1h 18m | Hits:  49%/4460  
    🟩 cxx_family
      🟩 Clang              Pass: 100%/46  | Total:  5h 24m | Avg:  7m 03s | Max: 14m 35s
      🟩 GCC                Pass: 100%/49  | Total: 13h 16m | Avg: 16m 15s | Max: 50m 22s
      🟩 Intel              Pass: 100%/3   | Total:  2h 42m | Avg: 54m 13s | Max: 59m 23s
      🟩 MSVC               Pass: 100%/5   | Total:  5h 16m | Avg:  1h 03m | Max:  1h 18m | Hits:  19%/11150 
    🟩 gpu
      🟩 v100               Pass: 100%/103 | Total:  1d 02h | Avg: 15m 32s | Max:  1h 18m | Hits:  19%/11150 
    🟩 jobs
      🟩 Build              Pass: 100%/96  | Total:  1d 00h | Avg: 15m 37s | Max:  1h 18m | Hits:   0%/8920  
      🟩 TestCPU            Pass: 100%/4   | Total: 47m 16s | Avg: 11m 49s | Max: 25m 34s | Hits:  99%/2230  
      🟩 TestGPU            Pass: 100%/3   | Total: 53m 34s | Avg: 17m 51s | Max: 26m 09s
    🟩 sm
      🟩 60;70;80;90        Pass: 100%/3   | Total: 27m 29s | Avg:  9m 09s | Max:  9m 45s
      🟩 90a                Pass: 100%/4   | Total:  1h 41m | Avg: 25m 28s | Max: 30m 29s
    🟩 std
      🟩 11                 Pass: 100%/28  | Total:  5h 47m | Avg: 12m 23s | Max: 49m 06s
      🟩 14                 Pass: 100%/27  | Total:  7h 42m | Avg: 17m 08s | Max:  1h 09m | Hits:   0%/4460  
      🟩 17                 Pass: 100%/26  | Total:  6h 42m | Avg: 15m 29s | Max:  1h 14m | Hits:   0%/2230  
      🟩 20                 Pass: 100%/22  | Total:  6h 27m | Avg: 17m 37s | Max:  1h 18m | Hits:  49%/4460  
    
  • 🟩 cudax: Pass: 100%/52 | Total: 2h 24m | Avg: 2m 46s | Max: 14m 03s | Hits: 14%/214

    🟩 cpu
      🟩 amd64              Pass: 100%/48  | Total:  2h 14m | Avg:  2m 48s | Max: 14m 03s | Hits:  14%/214   
      🟩 arm64              Pass: 100%/4   | Total:  9m 48s | Avg:  2m 27s | Max:  2m 54s
    🟩 ctk
      🟩 12.0               Pass: 100%/19  | Total: 54m 33s | Avg:  2m 52s | Max: 13m 04s | Hits:  14%/107   
      🟩 12.6               Pass: 100%/33  | Total:  1h 30m | Avg:  2m 43s | Max: 14m 03s | Hits:  14%/107   
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/19  | Total: 54m 33s | Avg:  2m 52s | Max: 13m 04s | Hits:  14%/107   
      🟩 nvcc12.6           Pass: 100%/33  | Total:  1h 30m | Avg:  2m 43s | Max: 14m 03s | Hits:  14%/107   
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/52  | Total:  2h 24m | Avg:  2m 46s | Max: 14m 03s | Hits:  14%/214   
    🟩 cxx
      🟩 Clang9             Pass: 100%/2   | Total:  4m 02s | Avg:  2m 01s | Max:  2m 06s
      🟩 Clang10            Pass: 100%/2   | Total:  4m 02s | Avg:  2m 01s | Max:  2m 04s
      🟩 Clang11            Pass: 100%/4   | Total:  8m 20s | Avg:  2m 05s | Max:  2m 14s
      🟩 Clang12            Pass: 100%/4   | Total:  8m 08s | Avg:  2m 02s | Max:  2m 09s
      🟩 Clang13            Pass: 100%/4   | Total:  8m 13s | Avg:  2m 03s | Max:  2m 10s
      🟩 Clang14            Pass: 100%/4   | Total: 10m 55s | Avg:  2m 43s | Max:  4m 20s
      🟩 Clang15            Pass: 100%/2   | Total:  4m 16s | Avg:  2m 08s | Max:  2m 14s
      🟩 Clang16            Pass: 100%/4   | Total:  8m 32s | Avg:  2m 08s | Max:  2m 22s
      🟩 Clang17            Pass: 100%/2   | Total:  4m 28s | Avg:  2m 14s | Max:  2m 17s
      🟩 Clang18            Pass: 100%/2   | Total:  6m 47s | Avg:  3m 23s | Max:  4m 34s
      🟩 GCC9               Pass: 100%/2   | Total:  4m 20s | Avg:  2m 10s | Max:  2m 26s
      🟩 GCC10              Pass: 100%/4   | Total:  7m 25s | Avg:  1m 51s | Max:  1m 56s
      🟩 GCC11              Pass: 100%/4   | Total:  7m 39s | Avg:  1m 54s | Max:  2m 00s
      🟩 GCC12              Pass: 100%/7   | Total: 22m 36s | Avg:  3m 13s | Max:  3m 57s
      🟩 GCC13              Pass: 100%/3   | Total:  7m 46s | Avg:  2m 35s | Max:  2m 54s
      🟩 MSVC14.36          Pass: 100%/1   | Total: 13m 04s | Avg: 13m 04s | Max: 13m 04s | Hits:  14%/107   
      🟩 MSVC14.39          Pass: 100%/1   | Total: 14m 03s | Avg: 14m 03s | Max: 14m 03s | Hits:  14%/107   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/30  | Total:  1h 07m | Avg:  2m 15s | Max:  4m 34s
      🟩 GCC                Pass: 100%/20  | Total: 49m 46s | Avg:  2m 29s | Max:  3m 57s
      🟩 MSVC               Pass: 100%/2   | Total: 27m 07s | Avg: 13m 33s | Max: 14m 03s | Hits:  14%/214   
    🟩 gpu
      🟩 v100               Pass: 100%/52  | Total:  2h 24m | Avg:  2m 46s | Max: 14m 03s | Hits:  14%/214   
    🟩 jobs
      🟩 Build              Pass: 100%/47  | Total:  2h 04m | Avg:  2m 38s | Max: 14m 03s | Hits:  14%/214   
      🟩 Test               Pass: 100%/5   | Total: 20m 06s | Avg:  4m 01s | Max:  4m 34s
    🟩 sm
      🟩 90                 Pass: 100%/1   | Total:  2m 29s | Avg:  2m 29s | Max:  2m 29s
      🟩 90a                Pass: 100%/1   | Total:  2m 19s | Avg:  2m 19s | Max:  2m 19s
    🟩 std
      🟩 17                 Pass: 100%/28  | Total:  1h 04m | Avg:  2m 18s | Max:  3m 57s
      🟩 20                 Pass: 100%/24  | Total:  1h 20m | Avg:  3m 20s | Max: 14m 03s | Hits:  14%/214   
    
  • 🟩 pycuda: Pass: 100%/1 | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 ctk
      🟩 12.5               Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 cudacxx
      🟩 nvcc12.5           Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 gpu
      🟩 v100               Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 15m 45s | Avg: 15m 45s | Max: 15m 45s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
Thrust
+/- CUDA Experimental
pycuda
CUDA C Core Library

Modifications in project or dependencies?

Project
CCCL Infrastructure
+/- libcu++
+/- CUB
+/- Thrust
+/- CUDA Experimental
+/- pycuda
+/- CUDA C Core Library

🏃‍ Runner counts (total jobs: 364)

# Runner
297 linux-amd64-cpu16
28 linux-arm64-cpu16
24 linux-amd64-gpu-v100-latest-1
15 windows-amd64-cpu16

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature request New feature or request. libcu++ For all items related to libcu++
Projects
Status: In Progress
Development

Successfully merging this pull request may close these issues.

5 participants