Incomplete type when compiling a wmma::fragment type with jitify #8155
Description
I'm not sure whether this is an issue with CuPy, but I am running into another problem. It works when jitify=False. But as it is, I'm just getting an incomplete type error. Compiling just the kernel code for the following does work with NVCC even though the Intellisense is messed up when loaded in Visual Studio.
import cupy as cp
kernel_code = r'''
#include <mma.h>
using namespace nvcuda;
extern "C" __global__ void mykernel() {
wmma::fragment<wmma::accumulator, 16, 16, 8, float> v16;
return ;
}
'''
module = cp.RawModule(code=kernel_code, backend='nvrtc', jitify=True, enable_cooperative_groups=True)
module.get_function('mykernel')((1,),(1,),())PS D:\Users\Marko\Source\Repos\The Spiral Language\Spiral Compilation Tests> d:; cd 'd:\Users\Marko\Source\Repos\The Spiral Language\Spiral Compilation Tests'; & 'C:\Users\mrakg\AppData\Local\Programs\Python\Python311\python.exe' 'c:\Users\mrakg\.vscode\extensions\ms-python.python-2023.22.1\pythonFiles\lib\python\debugpy\adapter/../..\debugpy\launcher' '53548' '--' 'D:\Users\Marko\Source\Repos\The Spiral Language\Spiral Compilation Tests\cuda_experiments\tensor1\bug_mma.py'
---------------------------------------------------
--- JIT compile log for C:\Users\mrakg\AppData\Local\Temp\tmpu7gc6bb7\2983982998ae8febc0583032d61861b2579068a4.cubin.cu ---
---------------------------------------------------
C:\Users\mrakg\AppData\Local\Temp\tmpu7gc6bb7\2983982998ae8febc0583032d61861b2579068a4.cubin.cu(7): error: incomplete type is not allowed
wmma::fragment<wmma::accumulator, 16, 16, 8, float> v16;
^
1 error detected in the compilation of "C:\Users\mrakg\AppData\Local\Temp\tmpu7gc6bb7\2983982998ae8febc0583032d61861b2579068a4.cubin.cu".
---------------------------------------------------
Traceback (most recent call last):
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 250, in _jitify_prep
name, options, headers, include_names = jitify.jitify(source, options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy\cuda\jitify.pyx", line 240, in cupy.cuda.jitify.jitify
File "cupy\cuda\jitify.pyx", line 264, in cupy.cuda.jitify.jitify
RuntimeError: Runtime compilation failed
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "D:\Users\Marko\Source\Repos\The Spiral Language\Spiral Compilation Tests\cuda_experiments\tensor1\bug_mma.py", line 12, in <module>
module.get_function('mykernel')((1,),(1,),())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy\_core\raw.pyx", line 487, in cupy._core.raw.RawModule.get_function
File "cupy\_core\raw.pyx", line 100, in cupy._core.raw.RawKernel.kernel.__get__
File "cupy\_core\raw.pyx", line 117, in cupy._core.raw.RawKernel._kernel
File "cupy\_util.pyx", line 64, in cupy._util.memoize.decorator.ret
File "cupy\_core\raw.pyx", line 538, in cupy._core.raw._get_raw_module
File "cupy\_core\core.pyx", line 2236, in cupy._core.core.compile_with_cache
File "cupy\_core\core.pyx", line 2254, in cupy._core.core.compile_with_cache
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 484, in _compile_module_with_cache
return _compile_with_cache_cuda(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 562, in _compile_with_cache_cuda
ptx, mapping = compile_using_nvrtc(
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 319, in compile_using_nvrtc
return _compile(source, options, cu_path,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 284, in _compile
options, headers, include_names = _jitify_prep(
^^^^^^^^^^^^^
File "C:\Users\mrakg\AppData\Local\Programs\Python\Python311\Lib\site-packages\cupy\cuda\compiler.py", line 257, in _jitify_prep
raise JitifyException(str(cex)) from e
cupy.cuda.compiler.JitifyException: Runtime compilation failed
Originally posted by @mrakgr in #8146 (comment)